6 files changed, 163 insertions, 106 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 27aed1a..8ec4b30 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3176,35 +3176,9 @@ static void addrconf_gre_config(struct net_device *dev)
 }
 #endif
 
-#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-/* If the host route is cached on the addr struct make sure it is associated
- * with the proper table. e.g., enslavement can change and if so the cached
- * host route needs to move to the new table.
- */
-static void l3mdev_check_host_rt(struct inet6_dev *idev,
-				  struct inet6_ifaddr *ifp)
-{
-	if (ifp->rt) {
-		u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
-
-		if (tb_id != ifp->rt->rt6i_table->tb6_id) {
-			ip6_del_rt(ifp->rt);
-			ifp->rt = NULL;
-		}
-	}
-}
-#else
-static void l3mdev_check_host_rt(struct inet6_dev *idev,
-				  struct inet6_ifaddr *ifp)
-{
-}
-#endif
-
 static int fixup_permanent_addr(struct inet6_dev *idev,
 				struct inet6_ifaddr *ifp)
 {
-	l3mdev_check_host_rt(idev, ifp);
-
 	if (!ifp->rt) {
 		struct rt6_info *rt;
 
@@ -3255,6 +3229,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			   void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changeupper_info *info;
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	int run_pending = 0;
 	int err;
@@ -3303,6 +3278,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			break;
 
 		if (event == NETDEV_UP) {
+			/* restore routes for permanent addresses */
+			addrconf_permanent_addr(dev);
+
 			if (!addrconf_qdisc_ok(dev)) {
 				/* device is not ready yet. */
 				pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n",
@@ -3336,9 +3314,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			run_pending = 1;
 		}
 
-		/* restore routes for permanent addresses */
-		addrconf_permanent_addr(dev);
-
 		switch (dev->type) {
 #if IS_ENABLED(CONFIG_IPV6_SIT)
 		case ARPHRD_SIT:
@@ -3413,6 +3388,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 		if (idev)
 			addrconf_type_change(dev, event);
 		break;
+
+	case NETDEV_CHANGEUPPER:
+		info = ptr;
+
+		/* flush all routes if dev is linked to or unlinked from
+		 * an L3 master device (e.g., VRF)
+		 */
+		if (info->upper_dev && netif_is_l3_master(info->upper_dev))
+			addrconf_ifdown(dev, 0);
 	}
 
 	return NOTIFY_OK;
@@ -3438,6 +3422,12 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event)
 		ipv6_mc_unmap(idev);
 }
 
+static bool addr_is_local(const struct in6_addr *addr)
+{
+	return ipv6_addr_type(addr) &
+		(IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
+}
+
 static int addrconf_ifdown(struct net_device *dev, int how)
 {
 	struct net *net = dev_net(dev);
@@ -3495,7 +3485,8 @@ restart:
 				 * address is retained on a down event
 				 */
 				if (!keep_addr ||
-				    !(ifa->flags & IFA_F_PERMANENT)) {
+				    !(ifa->flags & IFA_F_PERMANENT) ||
+				    addr_is_local(&ifa->addr)) {
 					hlist_del_init_rcu(&ifa->addr_lst);
 					goto restart;
 				}
@@ -3539,17 +3530,23 @@ restart:
 
 	INIT_LIST_HEAD(&del_list);
 	list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
+		struct rt6_info *rt = NULL;
+
 		addrconf_del_dad_work(ifa);
 
 		write_unlock_bh(&idev->lock);
 		spin_lock_bh(&ifa->lock);
 
-		if (keep_addr && (ifa->flags & IFA_F_PERMANENT)) {
+		if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+		    !addr_is_local(&ifa->addr)) {
 			/* set state to skip the notifier below */
 			state = INET6_IFADDR_STATE_DEAD;
 			ifa->state = 0;
 			if (!(ifa->flags & IFA_F_NODAD))
 				ifa->flags |= IFA_F_TENTATIVE;
+
+			rt = ifa->rt;
+			ifa->rt = NULL;
 		} else {
 			state = ifa->state;
 			ifa->state = INET6_IFADDR_STATE_DEAD;
@@ -3560,6 +3557,9 @@ restart:
 
 		spin_unlock_bh(&ifa->lock);
 
+		if (rt)
+			ip6_del_rt(rt);
+
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
 			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
@@ -5325,10 +5325,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 			if (rt)
 				ip6_del_rt(rt);
 		}
-		dst_hold(&ifp->rt->dst);
-
-		ip6_del_rt(ifp->rt);
-
+		if (ifp->rt) {
+			dst_hold(&ifp->rt->dst);
+			ip6_del_rt(ifp->rt);
+		}
 		rt_genid_bump_ipv6(net);
 		break;
 	}
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4281621..9dd3882 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,18 +40,114 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
+static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	memset(fl6, 0, sizeof(*fl6));
+	fl6->flowi6_proto = sk->sk_protocol;
+	fl6->daddr = sk->sk_v6_daddr;
+	fl6->saddr = np->saddr;
+	fl6->flowi6_oif = sk->sk_bound_dev_if;
+	fl6->flowi6_mark = sk->sk_mark;
+	fl6->fl6_dport = inet->inet_dport;
+	fl6->fl6_sport = inet->inet_sport;
+	fl6->flowlabel = np->flow_label;
+
+	if (!fl6->flowi6_oif)
+		fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
+	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr))
+		fl6->flowi6_oif = np->mcast_oif;
+
+	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+}
+
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
+{
+	struct ip6_flowlabel *flowlabel = NULL;
+	struct in6_addr *final_p, final;
+	struct ipv6_txoptions *opt;
+	struct dst_entry *dst;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct flowi6 fl6;
+	int err = 0;
+
+	if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) {
+		flowlabel = fl6_sock_lookup(sk, np->flow_label);
+		if (!flowlabel)
+			return -EINVAL;
+	}
+	ip6_datagram_flow_key_init(&fl6, sk);
+
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
+	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
+
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		goto out;
+	}
+
+	if (fix_sk_saddr) {
+		if (ipv6_addr_any(&np->saddr))
+			np->saddr = fl6.saddr;
+
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			sk->sk_v6_rcv_saddr = fl6.saddr;
+			inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+			if (sk->sk_prot->rehash)
+				sk->sk_prot->rehash(sk);
+		}
+	}
+
+	ip6_dst_store(sk, dst,
+		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+		      &sk->sk_v6_daddr : NULL,
+#ifdef CONFIG_IPV6_SUBTREES
+		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
+		      &np->saddr :
+#endif
+		      NULL);
+
+out:
+	fl6_sock_release(flowlabel);
+	return err;
+}
+
+void ip6_datagram_release_cb(struct sock *sk)
+{
+	struct dst_entry *dst;
+
+	if (ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		return;
+
+	rcu_read_lock();
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete ||
+	    dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	ip6_datagram_dst_update(sk, false);
+}
+EXPORT_SYMBOL_GPL(ip6_datagram_release_cb);
+
 static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
 	struct ipv6_pinfo	*np = inet6_sk(sk);
-	struct in6_addr	*daddr, *final_p, final;
-	struct dst_entry	*dst;
-	struct flowi6		fl6;
-	struct ip6_flowlabel	*flowlabel = NULL;
-	struct ipv6_txoptions	*opt;
+	struct in6_addr		*daddr;
 	int			addr_type;
 	int			err;
+	__be32			fl6_flowlabel = 0;
 
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
@@ -66,15 +162,8 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl6, 0, sizeof(fl6));
-	if (np->sndflow) {
-		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
-			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (!flowlabel)
-				return -EINVAL;
-		}
-	}
+	if (np->sndflow)
+		fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
@@ -145,7 +234,7 @@ ipv4_connected:
 	}
 
 	sk->sk_v6_daddr = *daddr;
-	np->flow_label = fl6.flowlabel;
+	np->flow_label = fl6_flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
 
@@ -154,59 +243,13 @@ ipv4_connected:
 	 *	destination cache for it.
 	 */
 
-	fl6.flowi6_proto = sk->sk_protocol;
-	fl6.daddr = sk->sk_v6_daddr;
-	fl6.saddr = np->saddr;
-	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	fl6.flowi6_mark = sk->sk_mark;
-	fl6.fl6_dport = inet->inet_dport;
-	fl6.fl6_sport = inet->inet_sport;
-
-	if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
-
-	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
-		fl6.flowi6_oif = np->mcast_oif;
-
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
-
-	rcu_read_lock();
-	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
-	final_p = fl6_update_dst(&fl6, opt, &final);
-	rcu_read_unlock();
-
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
-	err = 0;
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
+	err = ip6_datagram_dst_update(sk, true);
+	if (err)
 		goto out;
-	}
-
-	/* source address lookup done in ip6_dst_lookup */
-
-	if (ipv6_addr_any(&np->saddr))
-		np->saddr = fl6.saddr;
-
-	if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-		sk->sk_v6_rcv_saddr = fl6.saddr;
-		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
-		if (sk->sk_prot->rehash)
-			sk->sk_prot->rehash(sk);
-	}
-
-	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
-		      &sk->sk_v6_daddr : NULL,
-#ifdef CONFIG_IPV6_SUBTREES
-		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
-		      &np->saddr :
-#endif
-		      NULL);
 
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 out:
-	fl6_sock_release(flowlabel);
 	return err;
 }
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 9428345..bc972e7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1090,8 +1090,8 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 			int getfrag(void *from, char *to, int offset, int len,
 			int odd, struct sk_buff *skb),
 			void *from, int length, int hh_len, int fragheaderlen,
-			int transhdrlen, int mtu, unsigned int flags,
-			const struct flowi6 *fl6)
+			int exthdrlen, int transhdrlen, int mtu,
+			unsigned int flags, const struct flowi6 *fl6)
 
 {
 	struct sk_buff *skb;
@@ -1116,7 +1116,7 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		skb_put(skb, fragheaderlen + transhdrlen);
 
 		/* initialize network header pointer */
-		skb_reset_network_header(skb);
+		skb_set_network_header(skb, exthdrlen);
 
 		/* initialize protocol header pointer */
 		skb->transport_header = skb->network_header + fragheaderlen;
@@ -1358,7 +1358,7 @@ emsgsize:
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
-					  hh_len, fragheaderlen,
+					  hh_len, fragheaderlen, exthdrlen,
 					  transhdrlen, mtu, flags, fl6);
 		if (err)
 			goto error;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index eb2ac4b..1f20345 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -252,12 +252,12 @@ static int ip6_tnl_create2(struct net_device *dev)
 
 	t = netdev_priv(dev);
 
+	dev->rtnl_link_ops = &ip6_link_ops;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out;
 
 	strcpy(t->parms.name, dev->name);
-	dev->rtnl_link_ops = &ip6_link_ops;
 
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ed44663..d916d6a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -338,9 +338,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
 	return rt;
 }
 
-static struct rt6_info *ip6_dst_alloc(struct net *net,
-				      struct net_device *dev,
-				      int flags)
+struct rt6_info *ip6_dst_alloc(struct net *net,
+			       struct net_device *dev,
+			       int flags)
 {
 	struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
 
@@ -364,6 +364,7 @@ static struct rt6_info *ip6_dst_alloc(struct net *net,
 
 	return rt;
 }
+EXPORT_SYMBOL(ip6_dst_alloc);
 
 static void ip6_dst_destroy(struct dst_entry *dst)
 {
@@ -1417,8 +1418,20 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	struct dst_entry *dst;
+
 	ip6_update_pmtu(skb, sock_net(sk), mtu,
 			sk->sk_bound_dev_if, sk->sk_mark);
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete ||
+	    dst->ops->check(dst, inet6_sk(sk)->dst_cookie))
+		return;
+
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		ip6_datagram_dst_update(sk, false);
+	bh_unlock_sock(sk);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8125931..6bc5c66 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1539,6 +1539,7 @@ struct proto udpv6_prot = {
 	.sendmsg	   = udpv6_sendmsg,
 	.recvmsg	   = udpv6_recvmsg,
 	.backlog_rcv	   = __udpv6_queue_rcv_skb,
+	.release_cb	   = ip6_datagram_release_cb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.rehash		   = udp_v6_rehash,