Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187a999 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...

1 files changed, 190 insertions, 114 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4ab4c38958c..cfdcf7b2daf 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -253,37 +253,32 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev)
 	return !qdisc_tx_is_noop(dev);
 }
 
-static void addrconf_del_timer(struct inet6_ifaddr *ifp)
+static void addrconf_del_rs_timer(struct inet6_dev *idev)
 {
-	if (del_timer(&ifp->timer))
+	if (del_timer(&idev->rs_timer))
+		__in6_dev_put(idev);
+}
+
+static void addrconf_del_dad_timer(struct inet6_ifaddr *ifp)
+{
+	if (del_timer(&ifp->dad_timer))
 		__in6_ifa_put(ifp);
 }
 
-enum addrconf_timer_t {
-	AC_NONE,
-	AC_DAD,
-	AC_RS,
-};
+static void addrconf_mod_rs_timer(struct inet6_dev *idev,
+				  unsigned long when)
+{
+	if (!timer_pending(&idev->rs_timer))
+		in6_dev_hold(idev);
+	mod_timer(&idev->rs_timer, jiffies + when);
+}
 
-static void addrconf_mod_timer(struct inet6_ifaddr *ifp,
-			       enum addrconf_timer_t what,
-			       unsigned long when)
+static void addrconf_mod_dad_timer(struct inet6_ifaddr *ifp,
+				   unsigned long when)
 {
-	if (!del_timer(&ifp->timer))
+	if (!timer_pending(&ifp->dad_timer))
 		in6_ifa_hold(ifp);
-
-	switch (what) {
-	case AC_DAD:
-		ifp->timer.function = addrconf_dad_timer;
-		break;
-	case AC_RS:
-		ifp->timer.function = addrconf_rs_timer;
-		break;
-	default:
-		break;
-	}
-	ifp->timer.expires = jiffies + when;
-	add_timer(&ifp->timer);
+	mod_timer(&ifp->dad_timer, jiffies + when);
 }
 
 static int snmp6_alloc_dev(struct inet6_dev *idev)
@@ -326,6 +321,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev)
 
 	WARN_ON(!list_empty(&idev->addr_list));
 	WARN_ON(idev->mc_list != NULL);
+	WARN_ON(timer_pending(&idev->rs_timer));
 
 #ifdef NET_REFCNT_DEBUG
 	pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL");
@@ -357,7 +353,8 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 	rwlock_init(&ndev->lock);
 	ndev->dev = dev;
 	INIT_LIST_HEAD(&ndev->addr_list);
-
+	setup_timer(&ndev->rs_timer, addrconf_rs_timer,
+		    (unsigned long)ndev);
 	memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf));
 	ndev->cnf.mtu6 = dev->mtu;
 	ndev->cnf.sysctl = NULL;
@@ -776,7 +773,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
 
 	in6_dev_put(ifp->idev);
 
-	if (del_timer(&ifp->timer))
+	if (del_timer(&ifp->dad_timer))
 		pr_notice("Timer is still running, when freeing ifa=%p\n", ifp);
 
 	if (ifp->state != INET6_IFADDR_STATE_DEAD) {
@@ -869,9 +866,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
 
 	spin_lock_init(&ifa->lock);
 	spin_lock_init(&ifa->state_lock);
-	init_timer(&ifa->timer);
+	setup_timer(&ifa->dad_timer, addrconf_dad_timer,
+		    (unsigned long)ifa);
 	INIT_HLIST_NODE(&ifa->addr_lst);
-	ifa->timer.data = (unsigned long) ifa;
 	ifa->scope = scope;
 	ifa->prefix_len = pfxlen;
 	ifa->flags = flags | IFA_F_TENTATIVE;
@@ -994,7 +991,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	}
 	write_unlock_bh(&idev->lock);
 
-	addrconf_del_timer(ifp);
+	addrconf_del_dad_timer(ifp);
 
 	ipv6_ifa_notify(RTM_DELADDR, ifp);
 
@@ -1126,8 +1123,7 @@ retry:
 
 	ift = !max_addresses ||
 	      ipv6_count_addresses(idev) < max_addresses ?
-		ipv6_add_addr(idev, &addr, tmp_plen,
-			      ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK,
+		ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_scope(&addr),
 			      addr_flags) : NULL;
 	if (IS_ERR_OR_NULL(ift)) {
 		in6_ifa_put(ifp);
@@ -1448,6 +1444,23 @@ try_nextdev:
 }
 EXPORT_SYMBOL(ipv6_dev_get_saddr);
 
+int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
+		      unsigned char banned_flags)
+{
+	struct inet6_ifaddr *ifp;
+	int err = -EADDRNOTAVAIL;
+
+	list_for_each_entry(ifp, &idev->addr_list, if_list) {
+		if (ifp->scope == IFA_LINK &&
+		    !(ifp->flags & banned_flags)) {
+			*addr = ifp->addr;
+			err = 0;
+			break;
+		}
+	}
+	return err;
+}
+
 int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 		    unsigned char banned_flags)
 {
@@ -1457,17 +1470,8 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 	rcu_read_lock();
 	idev = __in6_dev_get(dev);
 	if (idev) {
-		struct inet6_ifaddr *ifp;
-
 		read_lock_bh(&idev->lock);
-		list_for_each_entry(ifp, &idev->addr_list, if_list) {
-			if (ifp->scope == IFA_LINK &&
-			    !(ifp->flags & banned_flags)) {
-				*addr = ifp->addr;
-				err = 0;
-				break;
-			}
-		}
+		err = __ipv6_get_lladdr(idev, addr, banned_flags);
 		read_unlock_bh(&idev->lock);
 	}
 	rcu_read_unlock();
@@ -1581,7 +1585,7 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed)
 {
 	if (ifp->flags&IFA_F_PERMANENT) {
 		spin_lock_bh(&ifp->lock);
-		addrconf_del_timer(ifp);
+		addrconf_del_dad_timer(ifp);
 		ifp->flags |= IFA_F_TENTATIVE;
 		if (dad_failed)
 			ifp->flags |= IFA_F_DADFAILED;
@@ -2402,6 +2406,7 @@ err_exit:
  *	Manual configuration of address on an interface
  */
 static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *pfx,
+			  const struct in6_addr *peer_pfx,
 			  unsigned int plen, __u8 ifa_flags, __u32 prefered_lft,
 			  __u32 valid_lft)
 {
@@ -2457,6 +2462,8 @@ static int inet6_addr_add(struct net *net, int ifindex, const struct in6_addr *p
 		ifp->valid_lft = valid_lft;
 		ifp->prefered_lft = prefered_lft;
 		ifp->tstamp = jiffies;
+		if (peer_pfx)
+			ifp->peer_addr = *peer_pfx;
 		spin_unlock_bh(&ifp->lock);
 
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
@@ -2500,12 +2507,6 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p
 			read_unlock_bh(&idev->lock);
 
 			ipv6_del_addr(ifp);
-
-			/* If the last address is deleted administratively,
-			   disable IPv6 on this interface.
-			 */
-			if (list_empty(&idev->addr_list))
-				addrconf_ifdown(idev->dev, 1);
 			return 0;
 		}
 	}
@@ -2526,7 +2527,7 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
 		return -EFAULT;
 
 	rtnl_lock();
-	err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+	err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL,
 			     ireq.ifr6_prefixlen, IFA_F_PERMANENT,
 			     INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	rtnl_unlock();
@@ -2761,8 +2762,6 @@ static void addrconf_gre_config(struct net_device *dev)
 	struct inet6_dev *idev;
 	struct in6_addr addr;
 
-	pr_info("%s(%s)\n", __func__, dev->name);
-
 	ASSERT_RTNL();
 
 	if ((idev = ipv6_find_idev(dev)) == NULL) {
@@ -2829,9 +2828,9 @@ static void addrconf_ip6_tnl_config(struct net_device *dev)
 }
 
 static int addrconf_notify(struct notifier_block *this, unsigned long event,
-			   void *data)
+			   void *ptr)
 {
-	struct net_device *dev = (struct net_device *) data;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	int run_pending = 0;
 	int err;
@@ -3039,7 +3038,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 		hlist_for_each_entry_rcu(ifa, h, addr_lst) {
 			if (ifa->idev == idev) {
 				hlist_del_init_rcu(&ifa->addr_lst);
-				addrconf_del_timer(ifa);
+				addrconf_del_dad_timer(ifa);
 				goto restart;
 			}
 		}
@@ -3048,6 +3047,8 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 	write_lock_bh(&idev->lock);
 
+	addrconf_del_rs_timer(idev);
+
 	/* Step 2: clear flags for stateless addrconf */
 	if (!how)
 		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
@@ -3077,7 +3078,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 	while (!list_empty(&idev->addr_list)) {
 		ifa = list_first_entry(&idev->addr_list,
 				       struct inet6_ifaddr, if_list);
-		addrconf_del_timer(ifa);
+		addrconf_del_dad_timer(ifa);
 
 		list_del(&ifa->if_list);
 
@@ -3119,10 +3120,10 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 static void addrconf_rs_timer(unsigned long data)
 {
-	struct inet6_ifaddr *ifp = (struct inet6_ifaddr *) data;
-	struct inet6_dev *idev = ifp->idev;
+	struct inet6_dev *idev = (struct inet6_dev *)data;
+	struct in6_addr lladdr;
 
-	read_lock(&idev->lock);
+	write_lock(&idev->lock);
 	if (idev->dead || !(idev->if_flags & IF_READY))
 		goto out;
 
@@ -3133,18 +3134,19 @@ static void addrconf_rs_timer(unsigned long data)
 	if (idev->if_flags & IF_RA_RCVD)
 		goto out;
 
-	spin_lock(&ifp->lock);
-	if (ifp->probes++ < idev->cnf.rtr_solicits) {
-		/* The wait after the last probe can be shorter */
-		addrconf_mod_timer(ifp, AC_RS,
-				   (ifp->probes == idev->cnf.rtr_solicits) ?
-				   idev->cnf.rtr_solicit_delay :
-				   idev->cnf.rtr_solicit_interval);
-		spin_unlock(&ifp->lock);
+	if (idev->rs_probes++ < idev->cnf.rtr_solicits) {
+		if (!__ipv6_get_lladdr(idev, &lladdr, IFA_F_TENTATIVE))
+			ndisc_send_rs(idev->dev, &lladdr,
+				      &in6addr_linklocal_allrouters);
+		else
+			goto out;
 
-		ndisc_send_rs(idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
+		/* The wait after the last probe can be shorter */
+		addrconf_mod_rs_timer(idev, (idev->rs_probes ==
+					     idev->cnf.rtr_solicits) ?
+				      idev->cnf.rtr_solicit_delay :
+				      idev->cnf.rtr_solicit_interval);
 	} else {
-		spin_unlock(&ifp->lock);
 		/*
 		 * Note: we do not support deprecated "all on-link"
 		 * assumption any longer.
@@ -3153,8 +3155,8 @@ static void addrconf_rs_timer(unsigned long data)
 	}
 
 out:
-	read_unlock(&idev->lock);
-	in6_ifa_put(ifp);
+	write_unlock(&idev->lock);
+	in6_dev_put(idev);
 }
 
 /*
@@ -3170,8 +3172,8 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
 	else
 		rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1);
 
-	ifp->probes = idev->cnf.dad_transmits;
-	addrconf_mod_timer(ifp, AC_DAD, rand_num);
+	ifp->dad_probes = idev->cnf.dad_transmits;
+	addrconf_mod_dad_timer(ifp, rand_num);
 }
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp)
@@ -3232,40 +3234,40 @@ static void addrconf_dad_timer(unsigned long data)
 	struct inet6_dev *idev = ifp->idev;
 	struct in6_addr mcaddr;
 
-	if (!ifp->probes && addrconf_dad_end(ifp))
+	if (!ifp->dad_probes && addrconf_dad_end(ifp))
 		goto out;
 
-	read_lock(&idev->lock);
+	write_lock(&idev->lock);
 	if (idev->dead || !(idev->if_flags & IF_READY)) {
-		read_unlock(&idev->lock);
+		write_unlock(&idev->lock);
 		goto out;
 	}
 
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-		read_unlock(&idev->lock);
+		write_unlock(&idev->lock);
 		goto out;
 	}
 
-	if (ifp->probes == 0) {
+	if (ifp->dad_probes == 0) {
 		/*
 		 * DAD was successful
 		 */
 
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED);
 		spin_unlock(&ifp->lock);
-		read_unlock(&idev->lock);
+		write_unlock(&idev->lock);
 
 		addrconf_dad_completed(ifp);
 
 		goto out;
 	}
 
-	ifp->probes--;
-	addrconf_mod_timer(ifp, AC_DAD, ifp->idev->nd_parms->retrans_time);
+	ifp->dad_probes--;
+	addrconf_mod_dad_timer(ifp, ifp->idev->nd_parms->retrans_time);
 	spin_unlock(&ifp->lock);
-	read_unlock(&idev->lock);
+	write_unlock(&idev->lock);
 
 	/* send a neighbour solicitation for our addr */
 	addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
@@ -3277,6 +3279,10 @@ out:
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 {
 	struct net_device *dev = ifp->idev->dev;
+	struct in6_addr lladdr;
+	bool send_rs, send_mld;
+
+	addrconf_del_dad_timer(ifp);
 
 	/*
 	 *	Configure the address for reception. Now it is valid.
@@ -3288,22 +3294,41 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	   router advertisements, start sending router solicitations.
 	 */
 
-	if (ipv6_accept_ra(ifp->idev) &&
-	    ifp->idev->cnf.rtr_solicits > 0 &&
-	    (dev->flags&IFF_LOOPBACK) == 0 &&
-	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) {
+	read_lock_bh(&ifp->idev->lock);
+	spin_lock(&ifp->lock);
+	send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL &&
+		   ifp->idev->valid_ll_addr_cnt == 1;
+	send_rs = send_mld &&
+		  ipv6_accept_ra(ifp->idev) &&
+		  ifp->idev->cnf.rtr_solicits > 0 &&
+		  (dev->flags&IFF_LOOPBACK) == 0;
+	spin_unlock(&ifp->lock);
+	read_unlock_bh(&ifp->idev->lock);
+
+	/* While dad is in progress mld report's source address is in6_addrany.
+	 * Resend with proper ll now.
+	 */
+	if (send_mld)
+		ipv6_mc_dad_complete(ifp->idev);
+
+	if (send_rs) {
 		/*
 		 *	If a host as already performed a random delay
 		 *	[...] as part of DAD [...] there is no need
 		 *	to delay again before sending the first RS
 		 */
-		ndisc_send_rs(ifp->idev->dev, &ifp->addr, &in6addr_linklocal_allrouters);
+		if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE))
+			return;
+		ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters);
 
-		spin_lock_bh(&ifp->lock);
-		ifp->probes = 1;
+		write_lock_bh(&ifp->idev->lock);
+		spin_lock(&ifp->lock);
+		ifp->idev->rs_probes = 1;
 		ifp->idev->if_flags |= IF_RS_SENT;
-		addrconf_mod_timer(ifp, AC_RS, ifp->idev->cnf.rtr_solicit_interval);
-		spin_unlock_bh(&ifp->lock);
+		addrconf_mod_rs_timer(ifp->idev,
+				      ifp->idev->cnf.rtr_solicit_interval);
+		spin_unlock(&ifp->lock);
+		write_unlock_bh(&ifp->idev->lock);
 	}
 }
 
@@ -3615,18 +3640,20 @@ restart:
 	rcu_read_unlock_bh();
 }
 
-static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local)
+static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local,
+				     struct in6_addr **peer_pfx)
 {
 	struct in6_addr *pfx = NULL;
 
+	*peer_pfx = NULL;
+
 	if (addr)
 		pfx = nla_data(addr);
 
 	if (local) {
 		if (pfx && nla_memcmp(local, pfx, sizeof(*pfx)))
-			pfx = NULL;
-		else
-			pfx = nla_data(local);
+			*peer_pfx = pfx;
+		pfx = nla_data(local);
 	}
 
 	return pfx;
@@ -3644,7 +3671,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
 	struct nlattr *tb[IFA_MAX+1];
-	struct in6_addr *pfx;
+	struct in6_addr *pfx, *peer_pfx;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
@@ -3652,7 +3679,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	ifm = nlmsg_data(nlh);
-	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
 	if (pfx == NULL)
 		return -EINVAL;
 
@@ -3710,7 +3737,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct net *net = sock_net(skb->sk);
 	struct ifaddrmsg *ifm;
 	struct nlattr *tb[IFA_MAX+1];
-	struct in6_addr *pfx;
+	struct in6_addr *pfx, *peer_pfx;
 	struct inet6_ifaddr *ifa;
 	struct net_device *dev;
 	u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME;
@@ -3722,7 +3749,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return err;
 
 	ifm = nlmsg_data(nlh);
-	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+	pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
 	if (pfx == NULL)
 		return -EINVAL;
 
@@ -3750,7 +3777,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 		 * It would be best to check for !NLM_F_CREATE here but
 		 * userspace alreay relies on not having to provide this.
 		 */
-		return inet6_addr_add(net, ifm->ifa_index, pfx,
+		return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
 				      ifm->ifa_prefixlen, ifa_flags,
 				      preferred_lft, valid_lft);
 	}
@@ -3807,6 +3834,7 @@ static inline int rt_scope(int ifa_scope)
 static inline int inet6_ifaddr_msgsize(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ifaddrmsg))
+	       + nla_total_size(16) /* IFA_LOCAL */
 	       + nla_total_size(16) /* IFA_ADDRESS */
 	       + nla_total_size(sizeof(struct ifa_cacheinfo));
 }
@@ -3845,13 +3873,22 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 		valid = INFINITY_LIFE_TIME;
 	}
 
-	if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0 ||
-	    put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) {
-		nlmsg_cancel(skb, nlh);
-		return -EMSGSIZE;
-	}
+	if (!ipv6_addr_any(&ifa->peer_addr)) {
+		if (nla_put(skb, IFA_LOCAL, 16, &ifa->addr) < 0 ||
+		    nla_put(skb, IFA_ADDRESS, 16, &ifa->peer_addr) < 0)
+			goto error;
+	} else
+		if (nla_put(skb, IFA_ADDRESS, 16, &ifa->addr) < 0)
+			goto error;
+
+	if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
+		goto error;
 
 	return nlmsg_end(skb, nlh);
+
+error:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
 }
 
 static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
@@ -4051,7 +4088,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	struct net *net = sock_net(in_skb->sk);
 	struct ifaddrmsg *ifm;
 	struct nlattr *tb[IFA_MAX+1];
-	struct in6_addr *addr = NULL;
+	struct in6_addr *addr = NULL, *peer;
 	struct net_device *dev = NULL;
 	struct inet6_ifaddr *ifa;
 	struct sk_buff *skb;
@@ -4061,7 +4098,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	if (err < 0)
 		goto errout;
 
-	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL]);
+	addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer);
 	if (addr == NULL) {
 		err = -EINVAL;
 		goto errout;
@@ -4339,8 +4376,11 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 
 	write_lock_bh(&idev->lock);
 
-	if (update_rs)
+	if (update_rs) {
 		idev->if_flags |= IF_RS_SENT;
+		idev->rs_probes = 1;
+		addrconf_mod_rs_timer(idev, idev->cnf.rtr_solicit_interval);
+	}
 
 	/* Well, that's kinda nasty ... */
 	list_for_each_entry(ifp, &idev->addr_list, if_list) {
@@ -4353,6 +4393,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
 	}
 
 	write_unlock_bh(&idev->lock);
+	addrconf_verify(0);
 	return 0;
 }
 
@@ -4550,6 +4591,19 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
 }
 
+static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count)
+{
+	write_lock_bh(&ifp->idev->lock);
+	spin_lock(&ifp->lock);
+	if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|
+			    IFA_F_DADFAILED)) == IFA_F_PERMANENT) &&
+	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL))
+		ifp->idev->valid_ll_addr_cnt += count;
+	WARN_ON(ifp->idev->valid_ll_addr_cnt < 0);
+	spin_unlock(&ifp->lock);
+	write_unlock_bh(&ifp->idev->lock);
+}
+
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
@@ -4558,6 +4612,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 	switch (event) {
 	case RTM_NEWADDR:
+		update_valid_ll_addr_cnt(ifp, 1);
+
 		/*
 		 * If the address was optimistic
 		 * we inserted the route at the start of
@@ -4568,11 +4624,28 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 			ip6_ins_rt(ifp->rt);
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
+		if (!ipv6_addr_any(&ifp->peer_addr))
+			addrconf_prefix_route(&ifp->peer_addr, 128,
+					      ifp->idev->dev, 0, 0);
 		break;
 	case RTM_DELADDR:
+		update_valid_ll_addr_cnt(ifp, -1);
+
 		if (ifp->idev->cnf.forwarding)
 			addrconf_leave_anycast(ifp);
 		addrconf_leave_solict(ifp->idev, &ifp->addr);
+		if (!ipv6_addr_any(&ifp->peer_addr)) {
+			struct rt6_info *rt;
+			struct net_device *dev = ifp->idev->dev;
+
+			rt = rt6_lookup(dev_net(dev), &ifp->peer_addr, NULL,
+					dev->ifindex, 1);
+			if (rt) {
+				dst_hold(&rt->dst);
+				if (ip6_del_rt(rt))
+					dst_free(&rt->dst);
+			}
+		}
 		dst_hold(&ifp->rt->dst);
 
 		if (ip6_del_rt(ifp->rt))
@@ -4593,13 +4666,13 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 #ifdef CONFIG_SYSCTL
 
 static
-int addrconf_sysctl_forward(ctl_table *ctl, int write,
+int addrconf_sysctl_forward(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
 	int val = *valp;
 	loff_t pos = *ppos;
-	ctl_table lctl;
+	struct ctl_table lctl;
 	int ret;
 
 	/*
@@ -4620,13 +4693,16 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write,
 
 static void dev_disable_change(struct inet6_dev *idev)
 {
+	struct netdev_notifier_info info;
+
 	if (!idev || !idev->dev)
 		return;
 
+	netdev_notifier_info_init(&info, idev->dev);
 	if (idev->cnf.disable_ipv6)
-		addrconf_notify(NULL, NETDEV_DOWN, idev->dev);
+		addrconf_notify(NULL, NETDEV_DOWN, &info);
 	else
-		addrconf_notify(NULL, NETDEV_UP, idev->dev);
+		addrconf_notify(NULL, NETDEV_UP, &info);
 }
 
 static void addrconf_disable_change(struct net *net, __s32 newf)
@@ -4675,13 +4751,13 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
 }
 
 static
-int addrconf_sysctl_disable(ctl_table *ctl, int write,
+int addrconf_sysctl_disable(struct ctl_table *ctl, int write,
 			    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	int *valp = ctl->data;
 	int val = *valp;
 	loff_t pos = *ppos;
-	ctl_table lctl;
+	struct ctl_table lctl;
 	int ret;
 
 	/*
@@ -4703,7 +4779,7 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write,
 static struct addrconf_sysctl_table
 {
 	struct ctl_table_header *sysctl_header;
-	ctl_table addrconf_vars[DEVCONF_MAX+1];
+	struct ctl_table addrconf_vars[DEVCONF_MAX+1];
 } addrconf_sysctl __read_mostly = {
 	.sysctl_header = NULL,
 	.addrconf_vars = {