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

Pull networking fixes from David Miller:

 1) Fix memory leak in iwlwifi, from Matti Gottlieb.

 2) Add missing registration of netfilter arp_tables into initial
    namespace, from Florian Westphal.

 3) Fix potential NULL deref in DecNET routing code.

 4) Restrict NETLINK_URELEASE to truly bound sockets only, from Dmitry
    Ivanov.

 5) Fix dst ref counting in VRF, from David Ahern.

 6) Fix TSO segmenting limits in i40e driver, from Alexander Duyck.

 7) Fix heap leak in PACKET_DIAG_MCLIST, from Mathias Krause.

 8) Ravalidate IPV6 datagram socket cached routes properly, particularly
    with UDP, from Martin KaFai Lau.

 9) Fix endian bug in RDS dp_ack_seq handling, from Qing Huang.

10) Fix stats typing in bcmgenet driver, from Eric Dumazet.

11) Openvswitch needs to orphan SKBs before ipv6 fragmentation handing,
    from Joe Stringer.

12) SPI device reference leak in spi_ks8895 PHY driver, from Mark Brown.

13) atl2 doesn't actually support scatter-gather, so don't advertise the
    feature.  From Ben Hucthings.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (72 commits)
  openvswitch: use flow protocol when recalculating ipv6 checksums
  Driver: Vmxnet3: set CHECKSUM_UNNECESSARY for IPv6 packets
  atl2: Disable unimplemented scatter/gather feature
  net/mlx4_en: Split SW RX dropped counter per RX ring
  net/mlx4_core: Don't allow to VF change global pause settings
  net/mlx4_core: Avoid repeated calls to pci enable/disable
  net/mlx4_core: Implement pci_resume callback
  net: phy: spi_ks8895: Don't leak references to SPI devices
  net: ethernet: davinci_emac: Fix platform_data overwrite
  net: ethernet: davinci_emac: Fix Unbalanced pm_runtime_enable
  qede: Fix single MTU sized packet from firmware GRO flow
  qede: Fix setting Skb network header
  qede: Fix various memory allocation error flows for fastpath
  tcp: Merge tx_flags and tskey in tcp_shifted_skb
  tcp: Merge tx_flags and tskey in tcp_collapse_retrans
  drivers: net: cpsw: fix wrong regs access in cpsw_ndo_open
  tcp: Fix SOF_TIMESTAMPING_TX_ACK when handling dup acks
  openvswitch: Orphan skbs before IPv6 defrag
  Revert "Prevent NUll pointer dereference with two PHYs on cpsw"
  VSOCK: Only check error on skb_recv_datagram when skb is NULL
  ...

4 files changed, 143 insertions, 68 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 27aed1a..23cec53 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3255,6 +3255,7 @@ 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;
@@ -3413,6 +3414,15 @@ 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 +3448,12 @@ 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 +3511,8 @@ 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;
 				}
@@ -3544,7 +3561,8 @@ restart:
 		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;
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/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,