Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [VLAN]: Fix net_device leak.
  [PPP] generic: Fix receive path data clobbering & non-linear handling
  [PPP] generic: Call skb_cow_head before scribbling over skb
  [NET] skbuff: Add skb_cow_head
  [BRIDGE]: Kill clone argument to br_flood_*
  [PPP] pppoe: Fill in header directly in __pppoe_xmit
  [PPP] pppoe: Fix data clobbering in __pppoe_xmit and return value
  [PPP] pppoe: Fix skb_unshare_check call position
  [SCTP]: Convert bind_addr_list locking to RCU
  [SCTP]: Add RCU synchronization around sctp_localaddr_list
  [PKT_SCHED]: sch_cbq.c: Shut up uninitialized variable warning
  [PKTGEN]: srcmac fix
  [IPV6]: Fix source address selection.
  [IPV4]: Just increment OutDatagrams once per a datagram.
  [IPV6]: Just increment OutDatagrams once per a datagram.
  [IPV6]: Fix unbalanced socket reference with MSG_CONFIRM.
  [NET_SCHED] protect action config/dump from irqs
  [NET]: Fix two issues wrt. SO_BINDTODEVICE.

22 files changed, 307 insertions, 313 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 1583c5ef963..2a546919d6f 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -562,8 +562,6 @@ static int register_vlan_device(struct net_device *real_dev,
 	if (err < 0)
 		goto out_free_newdev;
 
-	/* Account for reference in struct vlan_dev_info */
-	dev_hold(real_dev);
 #ifdef VLAN_DEBUG
 	printk(VLAN_DBG "Allocated new device successfully, returning.\n");
 #endif
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 0eded176ce9..99292e8e1d0 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -41,11 +41,11 @@ int br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_pull(skb, ETH_HLEN);
 
 	if (dest[0] & 1)
-		br_flood_deliver(br, skb, 0);
+		br_flood_deliver(br, skb);
 	else if ((dst = __br_fdb_get(br, dest)) != NULL)
 		br_deliver(dst->dst, skb);
 	else
-		br_flood_deliver(br, skb, 0);
+		br_flood_deliver(br, skb);
 
 	return 0;
 }
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index ada7f495445..bdd7c35c3c7 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -100,24 +100,13 @@ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 }
 
 /* called under bridge lock */
-static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone,
+static void br_flood(struct net_bridge *br, struct sk_buff *skb,
 	void (*__packet_hook)(const struct net_bridge_port *p,
 			      struct sk_buff *skb))
 {
 	struct net_bridge_port *p;
 	struct net_bridge_port *prev;
 
-	if (clone) {
-		struct sk_buff *skb2;
-
-		if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) {
-			br->statistics.tx_dropped++;
-			return;
-		}
-
-		skb = skb2;
-	}
-
 	prev = NULL;
 
 	list_for_each_entry_rcu(p, &br->port_list, list) {
@@ -148,13 +137,13 @@ static void br_flood(struct net_bridge *br, struct sk_buff *skb, int clone,
 
 
 /* called with rcu_read_lock */
-void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, int clone)
+void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb)
 {
-	br_flood(br, skb, clone, __br_deliver);
+	br_flood(br, skb, __br_deliver);
 }
 
 /* called under bridge lock */
-void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, int clone)
+void br_flood_forward(struct net_bridge *br, struct sk_buff *skb)
 {
-	br_flood(br, skb, clone, __br_forward);
+	br_flood(br, skb, __br_forward);
 }
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 6f468fc3357..3a8a015c92e 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -43,7 +43,7 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	struct net_bridge_port *p = rcu_dereference(skb->dev->br_port);
 	struct net_bridge *br;
 	struct net_bridge_fdb_entry *dst;
-	int passedup = 0;
+	struct sk_buff *skb2;
 
 	if (!p || p->state == BR_STATE_DISABLED)
 		goto drop;
@@ -55,39 +55,35 @@ int br_handle_frame_finish(struct sk_buff *skb)
 	if (p->state == BR_STATE_LEARNING)
 		goto drop;
 
-	if (br->dev->flags & IFF_PROMISC) {
-		struct sk_buff *skb2;
+	/* The packet skb2 goes to the local host (NULL to skip). */
+	skb2 = NULL;
 
-		skb2 = skb_clone(skb, GFP_ATOMIC);
-		if (skb2 != NULL) {
-			passedup = 1;
-			br_pass_frame_up(br, skb2);
-		}
-	}
+	if (br->dev->flags & IFF_PROMISC)
+		skb2 = skb;
+
+	dst = NULL;
 
 	if (is_multicast_ether_addr(dest)) {
 		br->statistics.multicast++;
-		br_flood_forward(br, skb, !passedup);
-		if (!passedup)
-			br_pass_frame_up(br, skb);
-		goto out;
+		skb2 = skb;
+	} else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) {
+		skb2 = skb;
+		/* Do not forward the packet since it's local. */
+		skb = NULL;
 	}
 
-	dst = __br_fdb_get(br, dest);
-	if (dst != NULL && dst->is_local) {
-		if (!passedup)
-			br_pass_frame_up(br, skb);
-		else
-			kfree_skb(skb);
-		goto out;
-	}
+	if (skb2 == skb)
+		skb2 = skb_clone(skb, GFP_ATOMIC);
 
-	if (dst != NULL) {
-		br_forward(dst->dst, skb);
-		goto out;
-	}
+	if (skb2)
+		br_pass_frame_up(br, skb2);
 
-	br_flood_forward(br, skb, 0);
+	if (skb) {
+		if (dst)
+			br_forward(dst->dst, skb);
+		else
+			br_flood_forward(br, skb);
+	}
 
 out:
 	return 0;
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3ee2022928e..fc13130035e 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -183,7 +183,7 @@ int nf_bridge_copy_header(struct sk_buff *skb)
 	int err;
 	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
 
-	err = skb_cow(skb, header_size);
+	err = skb_cow_head(skb, header_size);
 	if (err)
 		return err;
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 21bf3a9a03f..e6dc6f52990 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -170,12 +170,8 @@ extern int br_dev_queue_push_xmit(struct sk_buff *skb);
 extern void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb);
 extern int br_forward_finish(struct sk_buff *skb);
-extern void br_flood_deliver(struct net_bridge *br,
-		      struct sk_buff *skb,
-		      int clone);
-extern void br_flood_forward(struct net_bridge *br,
-		      struct sk_buff *skb,
-		      int clone);
+extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb);
+extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb);
 
 /* br_if.c */
 extern void br_port_carrier_check(struct net_bridge_port *p);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 36fdea71d74..803d0c8826a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -111,6 +111,9 @@
  *
  * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com>
  *
+ * Fixed src_mac command to set source mac of packet to value specified in
+ * command by Adit Ranadive <adit.262@gmail.com>
+ *
  */
 #include <linux/sys.h>
 #include <linux/types.h>
@@ -1451,8 +1454,11 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 	if (!strcmp(name, "src_mac")) {
 		char *v = valstr;
+		unsigned char old_smac[ETH_ALEN];
 		unsigned char *m = pkt_dev->src_mac;
 
+		memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN);
+
 		len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
 		if (len < 0) {
 			return len;
@@ -1481,6 +1487,10 @@ static ssize_t pktgen_if_write(struct file *file,
 			}
 		}
 
+		/* Set up Src MAC */
+		if (compare_ether_addr(old_smac, pkt_dev->src_mac))
+			memcpy(&(pkt_dev->hh[6]), pkt_dev->src_mac, ETH_ALEN);
+
 		sprintf(pg_result, "OK: srcmac");
 		return count;
 	}
diff --git a/net/core/sock.c b/net/core/sock.c
index cfed7d42c48..190de61cd64 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -362,6 +362,61 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
 }
 EXPORT_SYMBOL(sk_dst_check);
 
+static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
+{
+	int ret = -ENOPROTOOPT;
+#ifdef CONFIG_NETDEVICES
+	char devname[IFNAMSIZ];
+	int index;
+
+	/* Sorry... */
+	ret = -EPERM;
+	if (!capable(CAP_NET_RAW))
+		goto out;
+
+	ret = -EINVAL;
+	if (optlen < 0)
+		goto out;
+
+	/* Bind this socket to a particular device like "eth0",
+	 * as specified in the passed interface name. If the
+	 * name is "" or the option length is zero the socket
+	 * is not bound.
+	 */
+	if (optlen > IFNAMSIZ - 1)
+		optlen = IFNAMSIZ - 1;
+	memset(devname, 0, sizeof(devname));
+
+	ret = -EFAULT;
+	if (copy_from_user(devname, optval, optlen))
+		goto out;
+
+	if (devname[0] == '\0') {
+		index = 0;
+	} else {
+		struct net_device *dev = dev_get_by_name(devname);
+
+		ret = -ENODEV;
+		if (!dev)
+			goto out;
+
+		index = dev->ifindex;
+		dev_put(dev);
+	}
+
+	lock_sock(sk);
+	sk->sk_bound_dev_if = index;
+	sk_dst_reset(sk);
+	release_sock(sk);
+
+	ret = 0;
+
+out:
+#endif
+
+	return ret;
+}
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -390,6 +445,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 	}
 #endif
 
+	if (optname == SO_BINDTODEVICE)
+		return sock_bindtodevice(sk, optval, optlen);
+
 	if (optlen < sizeof(int))
 		return -EINVAL;
 
@@ -578,54 +636,6 @@ set_rcvbuf:
 		ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
 		break;
 
-#ifdef CONFIG_NETDEVICES
-	case SO_BINDTODEVICE:
-	{
-		char devname[IFNAMSIZ];
-
-		/* Sorry... */
-		if (!capable(CAP_NET_RAW)) {
-			ret = -EPERM;
-			break;
-		}
-
-		/* Bind this socket to a particular device like "eth0",
-		 * as specified in the passed interface name. If the
-		 * name is "" or the option length is zero the socket
-		 * is not bound.
-		 */
-
-		if (!valbool) {
-			sk->sk_bound_dev_if = 0;
-		} else {
-			if (optlen > IFNAMSIZ - 1)
-				optlen = IFNAMSIZ - 1;
-			memset(devname, 0, sizeof(devname));
-			if (copy_from_user(devname, optval, optlen)) {
-				ret = -EFAULT;
-				break;
-			}
-
-			/* Remove any cached route for this socket. */
-			sk_dst_reset(sk);
-
-			if (devname[0] == '\0') {
-				sk->sk_bound_dev_if = 0;
-			} else {
-				struct net_device *dev = dev_get_by_name(devname);
-				if (!dev) {
-					ret = -ENODEV;
-					break;
-				}
-				sk->sk_bound_dev_if = dev->ifindex;
-				dev_put(dev);
-			}
-		}
-		break;
-	}
-#endif
-
-
 	case SO_ATTACH_FILTER:
 		ret = -EINVAL;
 		if (optlen == sizeof(struct sock_fprog)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 28355350fb6..69d4bd10f9c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -505,6 +505,8 @@ send:
 out:
 	up->len = 0;
 	up->pending = 0;
+	if (!err)
+		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
 	return err;
 }
 
@@ -693,10 +695,8 @@ out:
 	ip_rt_put(rt);
 	if (free)
 		kfree(ipc.opt);
-	if (!err) {
-		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
+	if (!err)
 		return len;
-	}
 	/*
 	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
 	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 91ef3be5aba..45b4c82148a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1021,7 +1021,7 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
 				hiscore.rule++;
 			}
 			if (ipv6_saddr_preferred(score.addr_type) ||
-			   (((ifa_result->flags &
+			   (((ifa->flags &
 			    (IFA_F_DEPRECATED|IFA_F_OPTIMISTIC)) == 0))) {
 				score.attrs |= IPV6_SADDR_SCORE_PREFERRED;
 				if (!(hiscore.attrs & IPV6_SADDR_SCORE_PREFERRED)) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e27383d855d..77167afa345 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -882,11 +882,10 @@ back_from_confirm:
 			ip6_flush_pending_frames(sk);
 		else if (!(msg->msg_flags & MSG_MORE))
 			err = rawv6_push_pending_frames(sk, &fl, rp);
+		release_sock(sk);
 	}
 done:
 	dst_release(dst);
-	if (!inet->hdrincl)
-		release_sock(sk);
 out:
 	fl6_sock_release(flowlabel);
 	return err<0?err:len;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4210951edb6..c347f3e30e2 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -555,6 +555,8 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 out:
 	up->len = 0;
 	up->pending = 0;
+	if (!err)
+		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, up->pcflag);
 	return err;
 }
 
@@ -823,10 +825,8 @@ do_append_data:
 	release_sock(sk);
 out:
 	fl6_sock_release(flowlabel);
-	if (!err) {
-		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
+	if (!err)
 		return len;
-	}
 	/*
 	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
 	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index feef366cad5..72cdb0fade2 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -68,7 +68,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 	int err = 0, index = -1,i = 0, s_i = 0, n_i = 0;
 	struct rtattr *r ;
 
-	read_lock(hinfo->lock);
+	read_lock_bh(hinfo->lock);
 
 	s_i = cb->args[0];
 
@@ -96,7 +96,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 		}
 	}
 done:
-	read_unlock(hinfo->lock);
+	read_unlock_bh(hinfo->lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;
@@ -156,13 +156,13 @@ struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo)
 {
 	struct tcf_common *p;
 
-	read_lock(hinfo->lock);
+	read_lock_bh(hinfo->lock);
 	for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p;
 	     p = p->tcfc_next) {
 		if (p->tcfc_index == index)
 			break;
 	}
-	read_unlock(hinfo->lock);
+	read_unlock_bh(hinfo->lock);
 
 	return p;
 }
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 6085be57845..17f6f27e28a 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -56,7 +56,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c
 	int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
 	struct rtattr *r;
 
-	read_lock(&police_lock);
+	read_lock_bh(&police_lock);
 
 	s_i = cb->args[0];
 
@@ -85,7 +85,7 @@ static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *c
 		}
 	}
 done:
-	read_unlock(&police_lock);
+	read_unlock_bh(&police_lock);
 	if (n_i)
 		cb->args[0] += n_i;
 	return n_i;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index e38c2839b25..cbef3bbfc20 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -380,7 +380,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	int len = skb->len;
-	int ret;
+	int uninitialized_var(ret);
 	struct cbq_class *cl = cbq_classify(skb, sch, &ret);
 
 #ifdef CONFIG_NET_CLS_ACT
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 2ad1caf1ea4..9bad8ba0fed 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -99,7 +99,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
 
 	/* Initialize the bind addr area.  */
 	sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port);
-	rwlock_init(&asoc->base.addr_lock);
 
 	asoc->state = SCTP_STATE_CLOSED;
 
@@ -937,8 +936,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
 {
 	struct sctp_transport *transport;
 
-	sctp_read_lock(&asoc->base.addr_lock);
-
 	if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) &&
 	    (htons(asoc->peer.port) == paddr->v4.sin_port)) {
 		transport = sctp_assoc_lookup_paddr(asoc, paddr);
@@ -952,7 +949,6 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
 	transport = NULL;
 
 out:
-	sctp_read_unlock(&asoc->base.addr_lock);
 	return transport;
 }
 
@@ -1376,19 +1372,13 @@ int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *asoc,
 int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
 			    const union sctp_addr *laddr)
 {
-	int found;
+	int found = 0;
 
-	sctp_read_lock(&asoc->base.addr_lock);
 	if ((asoc->base.bind_addr.port == ntohs(laddr->v4.sin_port)) &&
 	    sctp_bind_addr_match(&asoc->base.bind_addr, laddr,
-				 sctp_sk(asoc->base.sk))) {
+				 sctp_sk(asoc->base.sk)))
 		found = 1;
-		goto out;
-	}
 
-	found = 0;
-out:
-	sctp_read_unlock(&asoc->base.addr_lock);
 	return found;
 }
 
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index fdb287a9e2e..d35cbf5aae3 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -163,9 +163,15 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
 		addr->a.v4.sin_port = htons(bp->port);
 
 	addr->use_as_src = use_as_src;
+	addr->valid = 1;
 
 	INIT_LIST_HEAD(&addr->list);
-	list_add_tail(&addr->list, &bp->address_list);
+	INIT_RCU_HEAD(&addr->rcu);
+
+	/* We always hold a socket lock when calling this function,
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_add_tail_rcu(&addr->list, &bp->address_list);
 	SCTP_DBG_OBJCNT_INC(addr);
 
 	return 0;
@@ -174,23 +180,35 @@ int sctp_add_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *new,
 /* Delete an address from the bind address list in the SCTP_bind_addr
  * structure.
  */
-int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr)
+int sctp_del_bind_addr(struct sctp_bind_addr *bp, union sctp_addr *del_addr,
+			void (*rcu_call)(struct rcu_head *head,
+					 void (*func)(struct rcu_head *head)))
 {
-	struct list_head *pos, *temp;
-	struct sctp_sockaddr_entry *addr;
+	struct sctp_sockaddr_entry *addr, *temp;
 
-	list_for_each_safe(pos, temp, &bp->address_list) {
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	/* We hold the socket lock when calling this function,
+	 * and that acts as a writer synchronizing lock.
+	 */
+	list_for_each_entry_safe(addr, temp, &bp->address_list, list) {
 		if (sctp_cmp_addr_exact(&addr->a, del_addr)) {
 			/* Found the exact match. */
-			list_del(pos);
-			kfree(addr);
-			SCTP_DBG_OBJCNT_DEC(addr);
-
-			return 0;
+			addr->valid = 0;
+			list_del_rcu(&addr->list);
+			break;
 		}
 	}
 
+	/* Call the rcu callback provided in the args.  This function is
+	 * called by both BH packet processing and user side socket option
+	 * processing, but it works on different lists in those 2 contexts.
+	 * Each context provides it's own callback, whether call_rcu_bh()
+	 * or call_rcu(), to make sure that we wait for an appropriate time.
+	 */
+	if (addr && !addr->valid) {
+		rcu_call(&addr->rcu, sctp_local_addr_free);
+		SCTP_DBG_OBJCNT_DEC(addr);
+	}
+
 	return -EINVAL;
 }
 
@@ -300,15 +318,20 @@ int sctp_bind_addr_match(struct sctp_bind_addr *bp,
 			 struct sctp_sock *opt)
 {
 	struct sctp_sockaddr_entry *laddr;
-	struct list_head *pos;
-
-	list_for_each(pos, &bp->address_list) {
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
-		if (opt->pf->cmp_addr(&laddr->a, addr, opt))
-			return 1;
+	int match = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
+		if (opt->pf->cmp_addr(&laddr->a, addr, opt)) {
+			match = 1;
+			break;
+		}
 	}
+	rcu_read_unlock();
 
-	return 0;
+	return match;
 }
 
 /* Find the first address in the bind address list that is not present in
@@ -323,18 +346,19 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr	*bp,
 	union sctp_addr			*addr;
 	void 				*addr_buf;
 	struct sctp_af			*af;
-	struct list_head		*pos;
 	int				i;
 
-	list_for_each(pos, &bp->address_list) {
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
-
+	/* This is only called sctp_send_asconf_del_ip() and we hold
+	 * the socket lock in that code patch, so that address list
+	 * can't change.
+	 */
+	list_for_each_entry(laddr, &bp->address_list, list) {
 		addr_buf = (union sctp_addr *)addrs;
 		for (i = 0; i < addrcnt; i++) {
 			addr = (union sctp_addr *)addr_buf;
 			af = sctp_get_af_specific(addr->v4.sin_family);
 			if (!af)
-				return NULL;
+				break;
 
 			if (opt->pf->cmp_addr(&laddr->a, addr, opt))
 				break;
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 1404a9e2e78..8f485a0d14b 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -92,7 +92,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
 
 	/* Initialize the bind addr area */
 	sctp_bind_addr_init(&ep->base.bind_addr, 0);
-	rwlock_init(&ep->base.addr_lock);
 
 	/* Remember who we are attached to.  */
 	ep->base.sk = sk;
@@ -225,21 +224,14 @@ void sctp_endpoint_put(struct sctp_endpoint *ep)
 struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep,
 					       const union sctp_addr *laddr)
 {
-	struct sctp_endpoint *retval;
+	struct sctp_endpoint *retval = NULL;
 
-	sctp_read_lock(&ep->base.addr_lock);
 	if (htons(ep->base.bind_addr.port) == laddr->v4.sin_port) {
 		if (sctp_bind_addr_match(&ep->base.bind_addr, laddr,
-					 sctp_sk(ep->base.sk))) {
+					 sctp_sk(ep->base.sk)))
 			retval = ep;
-			goto out;
-		}
 	}
 
-	retval = NULL;
-
-out:
-	sctp_read_unlock(&ep->base.addr_lock);
 	return retval;
 }
 
@@ -261,9 +253,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc(
 	list_for_each(pos, &ep->asocs) {
 		asoc = list_entry(pos, struct sctp_association, asocs);
 		if (rport == asoc->peer.port) {
-			sctp_read_lock(&asoc->base.addr_lock);
 			*transport = sctp_assoc_lookup_paddr(asoc, paddr);
-			sctp_read_unlock(&asoc->base.addr_lock);
 
 			if (*transport)
 				return asoc;
@@ -295,20 +285,17 @@ struct sctp_association *sctp_endpoint_lookup_assoc(
 int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
 				const union sctp_addr *paddr)
 {
-	struct list_head *pos;
 	struct sctp_sockaddr_entry *addr;
 	struct sctp_bind_addr *bp;
 
-	sctp_read_lock(&ep->base.addr_lock);
 	bp = &ep->base.bind_addr;
-	list_for_each(pos, &bp->address_list) {
-		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
-		if (sctp_has_association(&addr->a, paddr)) {
-			sctp_read_unlock(&ep->base.addr_lock);
+	/* This function is called with the socket lock held,
+	 * so the address_list can not change.
+	 */
+	list_for_each_entry(addr, &bp->address_list, list) {
+		if (sctp_has_association(&addr->a, paddr))
 			return 1;
-		}
 	}
-	sctp_read_unlock(&ep->base.addr_lock);
 
 	return 0;
 }
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index f8aa23dda1c..670fd2740b8 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -77,13 +77,18 @@
 
 #include <asm/uaccess.h>
 
-/* Event handler for inet6 address addition/deletion events.  */
+/* Event handler for inet6 address addition/deletion events.
+ * The sctp_local_addr_list needs to be protocted by a spin lock since
+ * multiple notifiers (say IPv4 and IPv6) may be running at the same
+ * time and thus corrupt the list.
+ * The reader side is protected with RCU.
+ */
 static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 				void *ptr)
 {
 	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
-	struct sctp_sockaddr_entry *addr;
-	struct list_head *pos, *temp;
+	struct sctp_sockaddr_entry *addr = NULL;
+	struct sctp_sockaddr_entry *temp;
 
 	switch (ev) {
 	case NETDEV_UP:
@@ -94,19 +99,26 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 			memcpy(&addr->a.v6.sin6_addr, &ifa->addr,
 				 sizeof(struct in6_addr));
 			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
-			list_add_tail(&addr->list, &sctp_local_addr_list);
+			addr->valid = 1;
+			spin_lock_bh(&sctp_local_addr_lock);
+			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
+			spin_unlock_bh(&sctp_local_addr_lock);
 		}
 		break;
 	case NETDEV_DOWN:
-		list_for_each_safe(pos, temp, &sctp_local_addr_list) {
-			addr = list_entry(pos, struct sctp_sockaddr_entry, list);
-			if (ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) {
-				list_del(pos);
-				kfree(addr);
+		spin_lock_bh(&sctp_local_addr_lock);
+		list_for_each_entry_safe(addr, temp,
+					&sctp_local_addr_list, list) {
+			if (ipv6_addr_equal(&addr->a.v6.sin6_addr,
+					     &ifa->addr)) {
+				addr->valid = 0;
+				list_del_rcu(&addr->list);
 				break;
 			}
 		}
-
+		spin_unlock_bh(&sctp_local_addr_lock);
+		if (addr && !addr->valid)
+			call_rcu(&addr->rcu, sctp_local_addr_free);
 		break;
 	}
 
@@ -290,9 +302,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 			      union sctp_addr *saddr)
 {
 	struct sctp_bind_addr *bp;
-	rwlock_t *addr_lock;
 	struct sctp_sockaddr_entry *laddr;
-	struct list_head *pos;
 	sctp_scope_t scope;
 	union sctp_addr *baddr = NULL;
 	__u8 matchlen = 0;
@@ -312,14 +322,14 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 	scope = sctp_scope(daddr);
 
 	bp = &asoc->base.bind_addr;
-	addr_lock = &asoc->base.addr_lock;
 
 	/* Go through the bind address list and find the best source address
 	 * that matches the scope of the destination address.
 	 */
-	sctp_read_lock(addr_lock);
-	list_for_each(pos, &bp->address_list) {
-		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
+	rcu_read_lock();
+	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+		if (!laddr->valid)
+			continue;
 		if ((laddr->use_as_src) &&
 		    (laddr->a.sa.sa_family == AF_INET6) &&
 		    (scope <= sctp_scope(&laddr->a))) {
@@ -341,7 +351,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc,
 		       __FUNCTION__, asoc, NIP6(daddr->v6.sin6_addr));
 	}
 
-	sctp_read_unlock(addr_lock);
+	rcu_read_unlock();
 }
 
 /* Make a copy of all potential local addresses. */
@@ -367,7 +377,9 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 			addr->a.v6.sin6_port = 0;
 			addr->a.v6.sin6_addr = ifp->addr;
 			addr->a.v6.sin6_scope_id = dev->ifindex;
+			addr->valid = 1;
 			INIT_LIST_HEAD(&addr->list);
+			INIT_RCU_HEAD(&addr->rcu);
 			list_add_tail(&addr->list, addrlist);
 		}
 	}
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e98579b788b..3d036cdfae4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -153,6 +153,9 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist,
 			addr->a.v4.sin_family = AF_INET;
 			addr->a.v4.sin_port = 0;
 			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
+			addr->valid = 1;
+			INIT_LIST_HEAD(&addr->list);
+			INIT_RCU_HEAD(&addr->rcu);
 			list_add_tail(&addr->list, addrlist);
 		}
 	}
@@ -192,16 +195,24 @@ static void sctp_free_local_addr_list(void)
 	}
 }
 
+void sctp_local_addr_free(struct rcu_head *head)
+{
+	struct sctp_sockaddr_entry *e = container_of(head,
+				struct sctp_sockaddr_entry, rcu);
+	kfree(e);
+}
+
 /* Copy the local addresses which are valid for 'scope' into 'bp'.  */
 int sctp_copy_local_addr_list(struct sctp_bind_addr *bp, sctp_scope_t scope,
 			      gfp_t gfp, int copy_flags)
 {
 	struct sctp_sockaddr_entry *addr;
 	int error = 0;
-	struct list_head *pos, *temp;