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

Pull networking fixes from David Miller:

 1) The per-network-namespace loopback device, and thus its namespace,
    can have its teardown deferred for a long time if a kernel created
    TCP socket closes and the namespace is exiting meanwhile. The kernel
    keeps trying to finish the close sequence until it times out (which
    takes quite some time).

    Fix this by forcing the socket closed in this situation, from Dan
    Streetman.

 2) Fix regression where we're trying to invoke the update_pmtu method
    on route types (in this case metadata tunnel routes) that don't
    implement the dst_ops method. Fix from Nicolas Dichtel.

 3) Fix long standing memory corruption issues in r8169 driver by
    performing the chip statistics DMA programming more correctly. From
    Francois Romieu.

 4) Handle local broadcast sends over VRF routes properly, from David
    Ahern.

 5) Don't refire the DCCP CCID2 timer endlessly, otherwise the socket
    can never be released. From Alexey Kodanev.

 6) Set poll flags properly in VSOCK protocol layer, from Stefan
    Hajnoczi.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  VSOCK: set POLLOUT | POLLWRNORM for TCP_CLOSING
  dccp: don't restart ccid2_hc_tx_rto_expire() if sk in closed state
  net: vrf: Add support for sends to local broadcast address
  r8169: fix memory corruption on retrieval of hardware statistics.
  net: don't call update_pmtu unconditionally
  net: tcp: close sock if net namespace is exiting

9 files changed, 29 insertions, 11 deletions

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 1c75cd1255f6..92d016e87816 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t)
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
+	if (sk->sk_state == DCCP_CLOSED)
+		goto out;
+
 	/* back-off timer */
 	hc->tx_rto <<= 1;
 	if (hc->tx_rto > DCCP_RTO_MAX)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5ddb1cb52bd4..6d21068f9b55 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -520,8 +520,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	else
 		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
-	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 949f432a5f04..51b1669334fe 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -200,7 +200,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f08eebe60446..8e053ad7cae2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2298,6 +2298,9 @@ adjudge_to_death:
 			tcp_send_active_reset(sk, GFP_ATOMIC);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
+		} else if (!check_net(sock_net(sk))) {
+			/* Not possible to send reset; just close */
+			tcp_set_state(sk, TCP_CLOSE);
 		}
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 968fda198376..388158c9d9f6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -48,11 +48,19 @@ static void tcp_write_err(struct sock *sk)
  *  to prevent DoS attacks. It is called when a retransmission timeout
  *  or zero probe timeout occurs on orphaned socket.
  *
+ *  Also close if our net namespace is exiting; in that case there is no
+ *  hope of ever communicating again since all netns interfaces are already
+ *  down (or about to be down), and we need to release our dst references,
+ *  which have been moved to the netns loopback interface, so the namespace
+ *  can finish exiting.  This condition is only possible if we are a kernel
+ *  socket, as those do not hold references to the namespace.
+ *
  *  Criteria is still not confirmed experimentally and may change.
  *  We kill the socket, if:
  *  1. If number of orphaned sockets exceeds an administratively configured
  *     limit.
  *  2. If we have strong memory pressure.
+ *  3. If our net namespace is exiting.
  */
 static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 {
@@ -81,6 +89,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
 	}
+
+	if (!check_net(sock_net(sk))) {
+		/* Not possible to send reset; just close */
+		tcp_done(sk);
+		return 1;
+	}
+
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9a7cf355bc8c..1ee5584c3555 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -642,8 +642,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2,
-						rel_info);
+		skb_dst_update_pmtu(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
@@ -1131,8 +1130,7 @@ route_lookup:
 		mtu = 576;
 	}
 
-	if (skb_dst(skb) && !t->parms.collect_md)
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+	skb_dst_update_pmtu(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index dbb74f3c57a7..8c184f84f353 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -483,7 +483,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	mtu = dst_mtu(dst);
 	if (!skb->ignore_df && skb->len > mtu) {
-		skb_dst(skb)->ops->update_pmtu(dst, NULL, skb, mtu);
+		skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d7dc23c1b2ca..3873d3877135 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -934,8 +934,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			df = 0;
 		}
 
-		if (tunnel->parms.iph.daddr && skb_dst(skb))
-			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+		if (tunnel->parms.iph.daddr)
+			skb_dst_update_pmtu(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 5d28abf87fbf..c9473d698525 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -951,7 +951,7 @@ static unsigned int vsock_poll(struct file *file, struct socket *sock,
 		 * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
 		 * but local send is not shutdown.
 		 */
-		if (sk->sk_state == TCP_CLOSE) {
+		if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) {
 			if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 				mask |= POLLOUT | POLLWRNORM;