Merge branch 'master'

19 files changed, 334 insertions, 96 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 91e412b0ab00..67465b65abe4 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -753,6 +753,8 @@ static int vlan_ioctl_handler(void __user *arg)
 		break;
 	case GET_VLAN_REALDEV_NAME_CMD:
 		err = vlan_dev_get_realdev_name(args.device1, args.u.device2);
+		if (err)
+			goto out;
 		if (copy_to_user(arg, &args,
 				 sizeof(struct vlan_ioctl_args))) {
 			err = -EFAULT;
@@ -761,6 +763,8 @@ static int vlan_ioctl_handler(void __user *arg)
 
 	case GET_VLAN_VID_CMD:
 		err = vlan_dev_get_vid(args.device1, &vid);
+		if (err)
+			goto out;
 		args.u.VID = vid;
 		if (copy_to_user(arg, &args,
 				 sizeof(struct vlan_ioctl_args))) {
@@ -774,7 +778,7 @@ static int vlan_ioctl_handler(void __user *arg)
 			__FUNCTION__, args.cmd);
 		return -EINVAL;
 	};
-
+out:
 	return err;
 }
 
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index d8e36b775125..23422bd53a5e 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -295,7 +295,7 @@ static int check_hbh_len(struct sk_buff *skb)
 	len -= 2;
 
 	while (len > 0) {
-		int optlen = raw[off+1]+2;
+		int optlen = skb->nh.raw[off+1]+2;
 
 		switch (skb->nh.raw[off]) {
 		case IPV6_TLV_PAD0:
@@ -308,18 +308,15 @@ static int check_hbh_len(struct sk_buff *skb)
 		case IPV6_TLV_JUMBO:
 			if (skb->nh.raw[off+1] != 4 || (off&3) != 2)
 				goto bad;
-
 			pkt_len = ntohl(*(u32*)(skb->nh.raw+off+2));
-
+			if (pkt_len <= IPV6_MAXPLEN ||
+			    skb->nh.ipv6h->payload_len)
+				goto bad;
 			if (pkt_len > skb->len - sizeof(struct ipv6hdr))
 				goto bad;
-			if (pkt_len + sizeof(struct ipv6hdr) < skb->len) {
-				if (__pskb_trim(skb,
-				    pkt_len + sizeof(struct ipv6hdr)))
-					goto bad;
-				if (skb->ip_summed == CHECKSUM_HW)
-					skb->ip_summed = CHECKSUM_NONE;
-			}
+			if (pskb_trim_rcsum(skb,
+			    pkt_len+sizeof(struct ipv6hdr)))
+				goto bad;
 			break;
 		default:
 			if (optlen > len)
@@ -372,6 +369,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook,
 	if (hdr->nexthdr == NEXTHDR_HOP && check_hbh_len(skb))
 			goto inhdr_error;
 
+ 	nf_bridge_put(skb->nf_bridge);
 	if ((nf_bridge = nf_bridge_alloc(skb)) == NULL)
 		return NF_DROP;
 	setup_pre_routing(skb);
@@ -455,6 +453,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff **pskb,
 			skb->ip_summed = CHECKSUM_NONE;
 	}
 
+ 	nf_bridge_put(skb->nf_bridge);
 	if ((nf_bridge = nf_bridge_alloc(skb)) == NULL)
 		return NF_DROP;
 	setup_pre_routing(skb);
diff --git a/net/core/filter.c b/net/core/filter.c
index 2841bfce29d6..3a10e0bc90e8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -293,7 +293,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
 	struct sock_filter *ftest;
 	int pc;
 
-	if (((unsigned int)flen >= (~0U / sizeof(struct sock_filter))) || flen == 0)
+	if (flen == 0 || flen > BPF_MAXINSNS)
 		return -EINVAL;
 
 	/* check the filter code now */
@@ -360,7 +360,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
-        if (fprog->filter == NULL || fprog->len > BPF_MAXINSNS)
+        if (fprog->filter == NULL)
                 return -EINVAL;
 
 	fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ca03521112c5..656e13e38cfb 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1251,7 +1251,7 @@ static int dccp_v4_destroy_sock(struct sock *sk)
 	struct dccp_sock *dp = dccp_sk(sk);
 
 	/*
-	 * DCCP doesn't use sk_qrite_queue, just sk_send_head
+	 * DCCP doesn't use sk_write_queue, just sk_send_head
 	 * for retransmissions
 	 */
 	if (sk->sk_send_head != NULL) {
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 058c48e258fc..d0a447e520a2 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -12,6 +12,7 @@ ip_nat_pptp-objs	:= ip_nat_helper_pptp.o ip_nat_proto_gre.o
 
 # connection tracking
 obj-$(CONFIG_IP_NF_CONNTRACK) += ip_conntrack.o
+obj-$(CONFIG_IP_NF_NAT) += ip_nat.o
 
 # conntrack netlink interface
 obj-$(CONFIG_IP_NF_CONNTRACK_NETLINK) += ip_conntrack_netlink.o
@@ -41,7 +42,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o
 # the three instances of ip_tables
 obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o
 obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o
-obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o ip_nat.o
+obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o
 obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
 
 # matches
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index b2b60f3e9cdd..42196ba3b0b9 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -182,6 +182,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl)
 		case IPPROTO_UDP:
 		case IPPROTO_TCP:
 		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
 			if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				u16 *ports = (u16 *)xprth;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 73a23b4130a5..a60585fd85ad 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -137,6 +137,7 @@ static int addrconf_ifdown(struct net_device *dev, int how);
 static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags);
 static void addrconf_dad_timer(unsigned long data);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp);
+static void addrconf_dad_run(struct inet6_dev *idev);
 static void addrconf_rs_timer(unsigned long data);
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
 static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -388,6 +389,9 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
 		}
 #endif
 
+		if (netif_carrier_ok(dev))
+			ndev->if_flags |= IF_READY;
+
 		write_lock_bh(&addrconf_lock);
 		dev->ip6_ptr = ndev;
 		write_unlock_bh(&addrconf_lock);
@@ -415,6 +419,7 @@ static struct inet6_dev * ipv6_find_idev(struct net_device *dev)
 		if ((idev = ipv6_add_dev(dev)) == NULL)
 			return NULL;
 	}
+
 	if (dev->flags&IFF_UP)
 		ipv6_mc_up(idev);
 	return idev;
@@ -634,8 +639,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 	}
 #endif
 
-	for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;
-	     ifap = &ifa->if_next) {
+	for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) {
 		if (ifa == ifp) {
 			*ifap = ifa->if_next;
 			__in6_ifa_put(ifp);
@@ -643,6 +647,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 			if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0)
 				break;
 			deleted = 1;
+			continue;
 		} else if (ifp->flags & IFA_F_PERMANENT) {
 			if (ipv6_prefix_equal(&ifa->addr, &ifp->addr,
 					      ifp->prefix_len)) {
@@ -666,6 +671,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 				}
 			}
 		}
+		ifap = &ifa->if_next;
 	}
 	write_unlock_bh(&idev->lock);
 
@@ -903,11 +909,18 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev,
 
 			score.addr_type = __ipv6_addr_type(&ifa->addr);
 
-			/* Rule 0: Candidate Source Address (section 4)
+			/* Rule 0:
+			 * - Tentative Address (RFC2462 section 5.4)
+			 *  - A tentative address is not considered
+			 *    "assigned to an interface" in the traditional
+			 *    sense.
+			 * - Candidate Source Address (section 4)
 			 *  - In any case, anycast addresses, multicast
 			 *    addresses, and the unspecified address MUST
 			 *    NOT be included in a candidate set.
 			 */
+			if (ifa->flags & IFA_F_TENTATIVE)
+				continue;
 			if (unlikely(score.addr_type == IPV6_ADDR_ANY ||
 				     score.addr_type & IPV6_ADDR_MULTICAST)) {
 				LIMIT_NETDEBUG(KERN_DEBUG
@@ -1215,10 +1228,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 
 /* Gets referenced address, destroys ifaddr */
 
-void addrconf_dad_failure(struct inet6_ifaddr *ifp)
+void addrconf_dad_stop(struct inet6_ifaddr *ifp)
 {
-	if (net_ratelimit())
-		printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name);
 	if (ifp->flags&IFA_F_PERMANENT) {
 		spin_lock_bh(&ifp->lock);
 		addrconf_del_timer(ifp);
@@ -1244,6 +1255,12 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 		ipv6_del_addr(ifp);
 }
 
+void addrconf_dad_failure(struct inet6_ifaddr *ifp)
+{
+	if (net_ratelimit())
+		printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name);
+	addrconf_dad_stop(ifp);
+}
 
 /* Join to solicited addr multicast group. */
 
@@ -1596,9 +1613,17 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
 	   not good.
 	 */
 	if (valid_lft >= 0x7FFFFFFF/HZ)
-		rt_expires = 0;
+		rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ);
 	else
-		rt_expires = jiffies + valid_lft * HZ;
+		rt_expires = valid_lft * HZ;
+
+	/*
+	 * We convert this (in jiffies) to clock_t later.
+	 * Avoid arithmetic overflow there as well.
+	 * Overflow can happen only if HZ < USER_HZ.
+	 */
+	if (HZ < USER_HZ && rt_expires > 0x7FFFFFFF / USER_HZ)
+		rt_expires = 0x7FFFFFFF / USER_HZ;
 
 	if (pinfo->onlink) {
 		struct rt6_info *rt;
@@ -1610,12 +1635,12 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len)
 					ip6_del_rt(rt, NULL, NULL, NULL);
 					rt = NULL;
 				} else {
-					rt->rt6i_expires = rt_expires;
+					rt->rt6i_expires = jiffies + rt_expires;
 				}
 			}
 		} else if (valid_lft) {
 			addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
-					      dev, rt_expires, RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT);
+					      dev, jiffies_to_clock_t(rt_expires), RTF_ADDRCONF|RTF_EXPIRES|RTF_PREFIX_RT);
 		}
 		if (rt)
 			dst_release(&rt->u.dst);
@@ -2125,9 +2150,42 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = (struct net_device *) data;
 	struct inet6_dev *idev = __in6_dev_get(dev);
+	int run_pending = 0;
 
 	switch(event) {
 	case NETDEV_UP:
+	case NETDEV_CHANGE:
+		if (event == NETDEV_UP) {
+			if (!netif_carrier_ok(dev)) {
+				/* device is not ready yet. */
+				printk(KERN_INFO
+					"ADDRCONF(NETDEV_UP): %s: "
+					"link is not ready\n",
+					dev->name);
+				break;
+			}
+		} else {
+			if (!netif_carrier_ok(dev)) {
+				/* device is still not ready. */
+				break;
+			}
+
+			if (idev) {
+				if (idev->if_flags & IF_READY) {
+					/* device is already configured. */
+					break;
+				}
+				idev->if_flags |= IF_READY;
+			}
+
+			printk(KERN_INFO
+					"ADDRCONF(NETDEV_CHANGE): %s: "
+					"link becomes ready\n",
+					dev->name);
+
+			run_pending = 1;
+		}
+
 		switch(dev->type) {
 		case ARPHRD_SIT:
 			addrconf_sit_config(dev);
@@ -2144,6 +2202,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			break;
 		};
 		if (idev) {
+			if (run_pending)
+				addrconf_dad_run(idev);
+
 			/* If the MTU changed during the interface down, when the
 			   interface up, the changed MTU must be reflected in the
 			   idev as well as routers.
@@ -2178,8 +2239,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		 */
 		addrconf_ifdown(dev, event != NETDEV_DOWN);
 		break;
-	case NETDEV_CHANGE:
-		break;
+
 	case NETDEV_CHANGENAME:
 #ifdef CONFIG_SYSCTL
 		if (idev) {
@@ -2260,7 +2320,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 	/* Step 3: clear flags for stateless addrconf */
 	if (how != 1)
-		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD);
+		idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY);
 
 	/* Step 4: clear address list */
 #ifdef CONFIG_IPV6_PRIVACY
@@ -2369,11 +2429,20 @@ out:
 /*
  *	Duplicate Address Detection
  */
+static void addrconf_dad_kick(struct inet6_ifaddr *ifp)
+{
+	unsigned long rand_num;
+	struct inet6_dev *idev = ifp->idev;
+
+	rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1);
+	ifp->probes = idev->cnf.dad_transmits;
+	addrconf_mod_timer(ifp, AC_DAD, rand_num);
+}
+
 static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
 {
 	struct inet6_dev *idev = ifp->idev;
 	struct net_device *dev = idev->dev;
-	unsigned long rand_num;
 
 	addrconf_join_solict(dev, &ifp->addr);
 
@@ -2382,7 +2451,6 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
 					flags);
 
 	net_srandom(ifp->addr.s6_addr32[3]);
-	rand_num = net_random() % (idev->cnf.rtr_solicit_delay ? : 1);
 
 	read_lock_bh(&idev->lock);
 	if (ifp->dead)
@@ -2399,9 +2467,19 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
 		return;
 	}
 
-	ifp->probes = idev->cnf.dad_transmits;
-	addrconf_mod_timer(ifp, AC_DAD, rand_num);
-
+	if (!(idev->if_flags & IF_READY)) {
+		spin_unlock_bh(&ifp->lock);
+		read_unlock_bh(&idev->lock);
+		/*
+		 * If the defice is not ready:
+		 * - keep it tentative if it is a permanent address.
+		 * - otherwise, kill it.
+		 */
+		in6_ifa_hold(ifp);
+		addrconf_dad_stop(ifp);
+		return;
+	}
+	addrconf_dad_kick(ifp);
 	spin_unlock_bh(&ifp->lock);
 out:
 	read_unlock_bh(&idev->lock);
@@ -2484,6 +2562,22 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	}
 }
 
+static void addrconf_dad_run(struct inet6_dev *idev) {
+	struct inet6_ifaddr *ifp;
+
+	read_lock_bh(&idev->lock);
+	for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) {
+		spin_lock_bh(&ifp->lock);
+		if (!(ifp->flags & IFA_F_TENTATIVE)) {
+			spin_unlock_bh(&ifp->lock);
+			continue;
+		}
+		spin_unlock_bh(&ifp->lock);
+		addrconf_dad_kick(ifp);
+	}
+	read_unlock_bh(&idev->lock);
+}
+
 #ifdef CONFIG_PROC_FS
 struct if6_iter_state {
 	int bucket;
@@ -2689,6 +2783,9 @@ restart:
 						in6_ifa_hold(ifpub);
 						spin_unlock(&ifp->lock);
 						read_unlock(&addrconf_hash_lock);
+						spin_lock(&ifpub->lock);
+						ifpub->regen_count = 0;
+						spin_unlock(&ifpub->lock);
 						ipv6_create_tempaddr(ifpub, ifp);
 						in6_ifa_put(ifpub);
 						in6_ifa_put(ifp);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 34a332225c17..6ec6a2b549bb 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -328,8 +328,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 		iif = skb->dev->ifindex;
 
 	/*
-	 *	Must not send if we know that source is Anycast also.
-	 *	for now we don't know that.
+	 *	Must not send error if the source does not uniquely
+	 *	identify a single node (RFC2463 Section 2.4).
+	 *	We check unspecified / multicast addresses here,
+	 *	and anycast addresses will be checked later.
 	 */
 	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
 		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n");
@@ -373,6 +375,16 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	err = ip6_dst_lookup(sk, &dst, &fl);
 	if (err)
 		goto out;
+
+	/*
+	 * We won't send icmp if the destination is known
+	 * anycast.
+	 */
+	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n");
+		goto out_dst_release;
+	}
+
 	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
 		goto out;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index fd939da090c4..f829a4ad3ccc 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -170,7 +170,7 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 #define MLDV2_QQIC(value) MLDV2_EXP(0x80, 4, 3, value)
 #define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value)
 
-#define IPV6_MLD_MAX_MSF	10
+#define IPV6_MLD_MAX_MSF	64
 
 int sysctl_mld_max_msf = IPV6_MLD_MAX_MSF;
 
@@ -224,6 +224,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr)
 
 	mc_lst->ifindex = dev->ifindex;
 	mc_lst->sfmode = MCAST_EXCLUDE;
+	mc_lst->sflock = RW_LOCK_UNLOCKED;
 	mc_lst->sflist = NULL;
 
 	/*
@@ -360,6 +361,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 	struct ip6_sf_socklist *psl;
 	int i, j, rv;
 	int leavegroup = 0;
+	int pmclocked = 0;
 	int err;
 
 	if (pgsr->gsr_group.ss_family != AF_INET6 ||
@@ -403,6 +405,9 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 		pmc->sfmode = omode;
 	}
 
+	write_lock_bh(&pmc->sflock);
+	pmclocked = 1;
+
 	psl = pmc->sflist;
 	if (!add) {
 		if (!psl)
@@ -475,6 +480,8 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 	/* update the interface list */
 	ip6_mc_add_src(idev, group, omode, 1, source, 1);
 done:
+	if (pmclocked)
+		write_unlock_bh(&pmc->sflock);
 	read_unlock_bh(&ipv6_sk_mc_lock);
 	read_unlock_bh(&idev->lock);
 	in6_dev_put(idev);
@@ -510,6 +517,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
 	dev = idev->dev;
 
 	err = 0;
+	read_lock_bh(&ipv6_sk_mc_lock);
+
 	if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) {
 		leavegroup = 1;
 		goto done;
@@ -549,6 +558,8 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
 		newpsl = NULL;
 		(void) ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0);
 	}
+
+	write_lock_bh(&pmc->sflock);
 	psl = pmc->sflist;
 	if (psl) {
 		(void) ip6_mc_del_src(idev, group, pmc->sfmode,
@@ -558,8 +569,10 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
 		(void) ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0);
 	pmc->sflist = newpsl;
 	pmc->sfmode = gsf->gf_fmode;
+	write_unlock_bh(&pmc->sflock);
 	err = 0;
 done:
+	read_unlock_bh(&ipv6_sk_mc_lock);
 	read_unlock_bh(&idev->lock);
 	in6_dev_put(idev);
 	dev_put(dev);
@@ -592,6 +605,11 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	dev = idev->dev;
 
 	err = -EADDRNOTAVAIL;
+	/*
+	 * changes to the ipv6_mc_list require the socket lock and
+	 * a read lock on ip6_sk_mc_lock. We have the socket lock,
+	 * so reading the list is safe.
+	 */
 
 	for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) {
 		if (pmc->ifindex != gsf->gf_interface)
@@ -614,6 +632,10 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	    copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) {
 		return -EFAULT;
 	}
+	/* changes to psl require the socket lock, a read lock on
+	 * on ipv6_sk_mc_lock and a write lock on pmc->sflock. We
+	 * have the socket lock, so reading here is safe.
+	 */
 	for (i=0; i<copycount; i++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
@@ -650,6 +672,7 @@ int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr,
 		read_unlock(&ipv6_sk_mc_lock);
 		return 1;
 	}
+	read_lock(&mc->sflock);
 	psl = mc->sflist;
 	if (!psl) {
 		rv = mc->sfmode == MCAST_EXCLUDE;
@@ -665,6 +688,7 @@ int inet6_mc_check(struct sock *sk, struct in6_addr *mc_addr,
 		if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count)
 			rv = 0;
 	}
+	read_unlock(&mc->sflock);
 	read_unlock(&ipv6_sk_mc_lock);
 
 	return rv;
@@ -1068,7 +1092,8 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime)
 	ma->mca_flags |= MAF_TIMER_RUNNING;
 }
 
-static void mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
+/* mark EXCLUDE-mode sources */
+static int mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs,
 	struct in6_addr *srcs)
 {
 	struct ip6_sf_list *psf;
@@ -1078,13 +1103,53 @@ static void mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
 	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
 		if (scount == nsrcs)
 			break;
-		for (i=0; i<nsrcs; i++)
+		for (i=0; i<nsrcs; i++) {
+			/* skip inactive filters */
+			if (pmc->mca_sfcount[MCAST_INCLUDE] ||
+			    pmc->mca_sfcount[MCAST_EXCLUDE] !=
+			    psf->sf_count[MCAST_EXCLUDE])
+				continue;
+			if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) {
+				scount++;
+				break;
+			}
+		}
+	}
+	pmc->mca_flags &= ~MAF_GSQUERY;
+	if (scount == nsrcs)	/* all sources excluded */
+		return 0;
+	return 1;
+}
+
+static int mld_marksources(struct ifmcaddr6 *pmc, int nsrcs,
+	struct in6_addr *srcs)
+{
+	struct ip6_sf_list *psf;
+	int i, scount;
+
+	if (pmc->mca_sfmode == MCAST_EXCLUDE)
+		return mld_xmarksources(pmc, nsrcs, srcs);
+
+	/* mark INCLUDE-mode sources */
+
+	scount = 0;
+	for (psf=pmc->mca_sources; psf; psf=psf->sf_next) {
+		if (scount == nsrcs)
+			break;
+		for (i=0; i<nsrcs; i++) {
 			if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) {
 				psf->sf_gsresp = 1;
 				scount++;
 				break;
 			}
+		}
+	}
+	if (!scount) {
+		pmc->mca_flags &= ~MAF_GSQUERY;
+		return 0;
 	}
+	pmc->mca_flags |= MAF_GSQUERY;
+	return 1;
 }
 
 int igmp6_event_query(struct sk_buff *skb)
@@ -1167,7 +1232,7 @@ int igmp6_event_query(struct sk_buff *skb)
 		/* mark sources to include, if group & source-specific */
 		if (mlh2->nsrcs != 0) {
 			if (!pskb_may_pull(skb, srcs_offset + 
-				mlh2->nsrcs * sizeof(struct in6_addr))) {
+			    ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) {
 				in6_dev_put(idev);
 				return -EINVAL;
 			}
@@ -1203,10 +1268,9 @@ int igmp6_event_query(struct sk_buff *skb)
 				else
 					ma->mca_flags &= ~MAF_GSQUERY;
 			}
-			if (ma->mca_flags & MAF_GSQUERY)
-				mld_marksources(ma, ntohs(mlh2->nsrcs),
-					mlh2->srcs);
-			igmp6_group_queried(ma, max_delay);
+			if (!(ma->mca_flags & MAF_GSQUERY) ||
+			   mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs))
+				igmp6_group_queried(ma, max_delay);
 			spin_unlock_bh(&ma->mca_lock);
 			if (group_type != IPV6_ADDR_ANY)
 				break;
@@ -1281,7 +1345,18 @@ static int is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
 	case MLD2_MODE_IS_EXCLUDE:
 		if (gdeleted || sdeleted)
 			return 0;
-		return !((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp);
+		if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) {
+			if (pmc->mca_sfmode == MCAST_INCLUDE)
+				return 1;
+			/* don't include if this source is excluded
+			 * in all filters
+			 */
+			if (psf->sf_count[MCAST_INCLUDE])
+				return 0;
+			return pmc->mca_sfcount[MCAST_EXCLUDE] ==
+				psf->sf_count[MCAST_EXCLUDE];
+		}
+		return 0;
 	case MLD2_CHANGE_TO_INCLUDE:
 		if (gdeleted || sdeleted)
 			return 0;
@@ -1450,7 +1525,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	struct mld2_report *pmr;
 	struct mld2_grec *pgr = NULL;
 	struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
-	int scount, first, isquery, truncate;
+	int scount, stotal, first, isquery, truncate;
 
 	if (pmc->mca_flags & MAF_NOREPORT)
 		return skb;
@@ -1460,25 +1535,13 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 	truncate = type == MLD2_MODE_IS_EXCLUDE ||
 		    type == MLD2_CHANGE_TO_EXCLUDE;
 
+	stotal = scount = 0;
+
 	psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources;
 
-	if (!*psf_list) {
-		if (type == MLD2_ALLOW_NEW_SOURCES ||
-		    type == MLD2_BLOCK_OLD_SOURCES)
-			return skb;
-		if (pmc->mca_crcount || isquery) {
-			/* make sure we have room for group header and at
-			 * least one source.
-			 */
-			if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)+
-			    sizeof(struct in6_addr)) {
-				mld_sendpack(skb);
-				skb = NULL; /* add_grhead will get a new one */
-			}
-			skb = add_grhead(skb, pmc, type, &pgr);
-		}
-		return skb;
-	}
+	if (!*psf_list)
+		goto empty_source;
+
 	pmr = skb ? (struct mld2_report *)skb->h.raw : NULL;
 
 	/* EX and TO_EX get a fresh packet, if needed */
@@ -1491,7 +1554,6 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 		}
 	}
 	first = 1;
-	scount = 0;
 	psf_prev = NULL;
 	for (psf=*psf_list; psf; psf=psf_next) {
 		struct in6_addr *psrc;
@@ -1525,7 +1587,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 		}
 		psrc = (struct in6_addr *)skb_put(skb, sizeof(*psrc));
 		*psrc = psf->sf_addr;
-		scount++;
+		scount++; stotal++;
 		if ((type == MLD2_ALLOW_NEW_SOURCES ||
 		     type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) {
 			psf->sf_crcount--;
@@ -1540,6 +1602,21 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 		}
 		psf_prev = psf;
 	}
+
+empty_source:
+	if (!stotal) {
+		if (type == MLD2_ALLOW_NEW_SOURCES ||
+		    type == MLD2_BLOCK_OLD_SOURCES)
+			return skb;
+		if (pmc->mca_crcount || isquery) {
+			/* make sure we have room for group header */
+			if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) {
+				mld_sendpack(skb);
+				skb = NULL; /* add_grhead will get a new one */
+			}
+			skb = add_grhead(skb, pmc, type, &pgr);
+		}
+	}
 	if (pgr)
 		pgr->grec_nsrcs = htons(scount);
 
@@ -1621,11 +1698,11 @@ static void mld_send_cr(struct inet6_dev *idev)
 			skb = add_grec(skb, pmc, dtype, 1, 1);
 		}
 		if (pmc->mca_crcount) {
-			pmc->mca_crcount--;
 			if (pmc->mca_sfmode == MCAST_EXCLUDE) {
 				type = MLD2_CHANGE_TO_INCLUDE;
 				skb = add_grec(skb, pmc, type, 1, 0);
 			}
+			pmc->mca_crcount--;
 			if (pmc->mca_crcount == 0) {
 				mld_clear_zeros(&pmc->mca_tomb);
 				mld_clear_zeros(&pmc->mca_sources);
@@ -1659,12 +1736,12 @@ static void mld_send_cr(struct inet6_dev *idev)
 
 		/* filter mode changes */
 		if (pmc->mca_crcount) {
-			pmc->mca_crcount--;
 			if (pmc->mca_sfmode == MCAST_EXCLUDE)
 				type = MLD2_CHANGE_TO_EXCLUDE;
 			else
 				type = MLD2_CHANGE_TO_INCLUDE;
 			skb = add_grec(skb, pmc, type, 0, 0);
+			pmc->mca_crcount--;
 		}
 		spin_unlock_bh(&pmc->mca_lock);
 	}
@@ -2023,6 +2100,9 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 {
 	int err;
 
+	/* callers have the socket lock and a write lock on ipv6_sk_mc_lock,
+	 * so no other readers or writers of iml or its sflist
+	 */
 	if (iml->sflist == 0) {
 		/* any-source empty exclude case */
 		return ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0);
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 060d61202412..04912f9b35c3 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -211,7 +211,7 @@ config IP6_NF_TARGET_REJECT
 
 config IP6_NF_TARGET_NFQUEUE
 	tristate "NFQUEUE Target Support"
-	depends on IP_NF_IPTABLES
+	depends on IP6_NF_IPTABLES
 	help
 	  This Target replaced the old obsolete QUEUE target.
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a7a537b50595..66140f13d119 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -413,11 +413,14 @@ static struct rt6_info *rt6_cow(struct rt6_info *ort, struct in6_addr *daddr,
 	rt = ip6_rt_copy(ort);
 
 	if (rt) {
-		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
-
-		if (!(rt->rt6i_flags&RTF_GATEWAY))
+		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
+			if (rt->rt6i_dst.plen != 128 &&
+			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
+				rt->rt6i_flags |= RTF_ANYCAST;
 			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
+		}
 
+		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
 		rt->rt6i_dst.plen = 128;
 		rt->rt6i_flags |= RTF_CACHE;
 		rt->u.dst.flags |= DST_HOST;
@@ -829,7 +832,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh,
 	}
 
 	rt->u.dst.obsolete = -1;
-	rt->rt6i_expires = clock_t_to_jiffies(rtmsg->rtmsg_info);
+	rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info);
 	if (nlh && (r = NLMSG_DATA(nlh))) {
 		rt->rt6i_protocol = r->rtm_protocol;
 	} else {
@@ -1413,7 +1416,9 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	rt->u.dst.obsolete = -1;
 
 	rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
-	if (!anycast)
+	if (anycast)
+		rt->rt6i_flags |= RTF_ANYCAST;
+	else
 		rt->rt6i_flags |= RTF_LOCAL;
 	rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
 	if (rt->rt6i_nexthop == NULL) {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index cf1d91e74c82..69bd957380e7 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -214,6 +214,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl)
 		case IPPROTO_UDP:
 		case IPPROTO_TCP:
 		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
 			if (pskb_may_pull(skb, skb->nh.raw + offset + 4 - skb->data)) {
 				u16 *ports = (u16 *)exthdr;
 
diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c
index 004e8599b8fe..a7d88b5ad756 100644
--- a/net/netrom/nr_in.c
+++ b/net/netrom/nr_in.c
@@ -99,7 +99,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit);
+		if (sysctl_netrom_reset_circuit)
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -130,7 +130,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb,
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit);
+		if (sysctl_netrom_reset_circuit)
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
@@ -265,7 +265,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype
 		break;
 
 	case NR_RESET:
-		if (sysctl_netrom_reset_circuit);
+		if (sysctl_netrom_reset_circuit)
 			nr_disconnect(sk, ECONNRESET);
 		break;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1f7f244806b7..9df888e932c5 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -156,10 +156,6 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)
 				sizeof(struct sk_buff) +
 				sizeof(struct sctp_chunk);
 
-	sk->sk_wmem_queued += SCTP_DATA_SNDSIZE(chunk) +
-				sizeof(struct sk_buff) +
-				sizeof(struct sctp_chunk);
-
 	atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
 }
 
@@ -4426,7 +4422,7 @@ cleanup:
  * tcp_poll().  Note that, based on these implementations, we don't
  * lock the socket in this function, even though it seems that,
  * ideally, locking or some other mechanisms can be used to ensure
- * the integrity of the counters (sndbuf and wmem_queued) used
+ * the integrity of the counters (sndbuf and wmem_alloc) used
  * in this place.  We assume that we don't need locks either until proven
  * otherwise.
  *
@@ -4833,10 +4829,6 @@ static void sctp_wfree(struct sk_buff *skb)
 				sizeof(struct sk_buff) +
 				sizeof(struct sctp_chunk);
 
-	sk->sk_wmem_queued -= SCTP_DATA_SNDSIZE(chunk) +
-				sizeof(struct sk_buff) +
-				sizeof(struct sctp_chunk);
-
 	atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
 
 	sock_wfree(skb);
@@ -4920,7 +4912,7 @@ void sctp_write_space(struct sock *sk)
 
 /* Is there any sndbuf space available on the socket?
  *
- * Note that wmem_queued is the sum of the send buffers on all of the
+ * Note that sk_wmem_alloc is the sum of the send buffers on all of the
  * associations on the same socket.  For a UDP-style socket with
  * multiple associations, it is possible for it to be "unwriteable"
  * prematurely.  I assume that this is acceptable because
@@ -4933,7 +4925,7 @@ static int sctp_writeable(struct sock *sk)
 {
 	int amt = 0;
 
-	amt = sk->sk_sndbuf - sk->sk_wmem_queued;
+	amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
 	if (amt < 0)
 		amt = 0;
 	return amt;
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index f44f46f1d8e0..8d782282ec19 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -638,7 +638,7 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 				gss_msg);
 		atomic_inc(&gss_msg->count);
 		gss_unhash_msg(gss_msg);
-		if (msg->errno == -ETIMEDOUT || msg->errno == -EPIPE) {
+		if (msg->errno == -ETIMEDOUT) {
 			unsigned long now = jiffies;
 			if (time_after(now, ratelimit)) {
 				printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n"
@@ -786,7 +786,9 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int taskflags)
 	cred->gc_flags = 0;
 	cred->gc_base.cr_ops = &gss_credops;
 	cred->gc_service = gss_auth->service;
-	err = gss_create_upcall(gss_auth, cred);
+	do {
+		err = gss_create_upcall(gss_auth, cred);
+	} while (err == -EAGAIN);
 	if (err < 0)
 		goto out_err;
 
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index c76ea221798c..16a2458f38f7 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -174,7 +174,7 @@ rpc_pipe_release(struct inode *inode, struct file *filp)
 		goto out;
 	msg = (struct rpc_pipe_msg *)filp->private_data;
 	if (msg != NULL) {
-		msg->errno = -EPIPE;
+		msg->errno = -EAGAIN;
 		list_del_init(&msg->list);
 		rpci->ops->destroy_msg(msg);
 	}
@@ -183,7 +183,7 @@ rpc_pipe_release(struct inode *inode, struct file *filp)
 	if (filp->f_mode & FMODE_READ)
 		rpci->nreaders --;
 	if (!rpci->nreaders)
-		__rpc_purge_upcall(inode, -EPIPE);
+		__rpc_purge_upcall(inode, -EAGAIN);
 	if (rpci->ops->release_pipe)
 		rpci->ops->release_pipe(inode);
 out:
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0a51fd46a848..77e8800d4127 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -990,6 +990,7 @@ static void xs_udp_connect_worker(void *args)
 		sk->sk_data_ready = xs_udp_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
 		sk->sk_no_check = UDP_CSUM_NORCV;
+		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_set_connected(xprt);
 
@@ -1074,6 +1075,7 @@ static void xs_tcp_connect_worker(void *args)
 		sk->sk_data_ready = xs_tcp_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
+		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */
 		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 0db9e57013fd..d19e274b9c4a 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -346,6 +346,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	struct xfrm_policy *pol, **p;
 	struct xfrm_policy *delpol = NULL;
 	struct xfrm_policy **newpos = NULL;
+	struct dst_entry *gc_list;
 
 	write_lock_bh(&xfrm_policy_lock);
 	for (p = &xfrm_policy_list[dir]; (pol=*p)!=NULL;) {
@@ -381,9 +382,36 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 		xfrm_pol_hold(policy);
 	write_unlock_bh(&xfrm_policy_lock);
 
-	if (delpol) {
+	if (delpol)
 		xfrm_policy_kill(delpol);
+
+	read_lock_bh(&xfrm_policy_lock);
+	gc_list = NULL;
+	for (policy = policy->next; policy; policy = policy->next) {
+		struct dst_entry *dst;
+
+		write_lock(&policy->lock);
+		dst = policy->bundles;
+		if (dst) {
+			struct dst_entry *tail = dst;
+			while (tail->next)
+				tail = tail->next;
+			tail->next = gc_list;
+			gc_list = dst;
+
+			policy->bundles = NULL;
+		}
+		write_unlock(&policy->lock);
+	}
+	read_unlock_bh(&xfrm_policy_lock);
+
+	while (gc_list) {
+		struct dst_entry *dst = gc_list;
+
+		gc_list = dst->next;
+		dst_free(dst);
 	}
+
 	return 0;
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
@@ -1014,13 +1042,12 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
 }
 EXPORT_SYMBOL(__xfrm_route_forward);
 
-/* Optimize later using cookies and generation ids. */
-
 static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
 {
-	if (!stale_bundle(dst))
-		return dst;
-
+	/* If it is marked obsolete, which is how we even get here,
+	 * then we have purged it from the policy bundle list and we
+	 * did that for a good reason.
+	 */
 	return NULL;
 }
 
@@ -1104,6 +1131,16 @@ int xfrm_flush_bundles(void)
 	return 0;
 }
 
+static int always_true(struct dst_entry *dst)
+{
+	return 1;
+}
+
+void xfrm_flush_all_bundles(void)
+{
+	xfrm_prune_bundles(always_true);
+}
+
 void xfrm_init_pmtu(struct dst_entry *dst)
 {
 	do {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 7cf48aa6c95b..479effc97666 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -431,6 +431,8 @@ void xfrm_state_insert(struct xfrm_state *x)
 	spin_lock_bh(&xfrm_state_lock);
 	__xfrm_state_insert(x);
 	spin_unlock_bh(&xfrm_state_lock);
+
+	xfrm_flush_all_bundles();
 }
 EXPORT_SYMBOL(xfrm_state_insert);
 
@@ -478,6 +480,9 @@ out:
 	spin_unlock_bh(&xfrm_state_lock);
 	xfrm_state_put_afinfo(afinfo);
 
+	if (!err)
+		xfrm_flush_all_bundles();
+
 	if (x1) {
 		xfrm_state_delete(x1);
 		xfrm_state_put(x1);