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
  ...

5 files changed, 48 insertions, 6 deletions

diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c
index dd8c80dc32a2..8f8713b4388f 100644
--- a/net/ipv4/netfilter/arptable_filter.c
+++ b/net/ipv4/netfilter/arptable_filter.c
@@ -81,6 +81,12 @@ static int __init arptable_filter_init(void)
 		return ret;
 	}
 
+	ret = arptable_filter_table_init(&init_net);
+	if (ret) {
+		unregister_pernet_subsys(&arptable_filter_net_ops);
+		kfree(arpfilter_ops);
+	}
+
 	return ret;
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 02c62299d717..60398a9370e7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1438,9 +1438,9 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #endif
 }
 
-static struct rtable *rt_dst_alloc(struct net_device *dev,
-				   unsigned int flags, u16 type,
-				   bool nopolicy, bool noxfrm, bool will_cache)
+struct rtable *rt_dst_alloc(struct net_device *dev,
+			    unsigned int flags, u16 type,
+			    bool nopolicy, bool noxfrm, bool will_cache)
 {
 	struct rtable *rt;
 
@@ -1468,6 +1468,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev,
 
 	return rt;
 }
+EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
 static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
@@ -2045,6 +2046,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 */
 		if (fi && res->prefixlen < 4)
 			fi = NULL;
+	} else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+		   (orig_oif != dev_out->ifindex)) {
+		/* For local routes that require a particular output interface
+		 * we do not want to cache the result.  Caching the result
+		 * causes incorrect behaviour when there are multiple source
+		 * addresses on the interface, the end result being that if the
+		 * intended recipient is waiting on that interface for the
+		 * packet he won't receive it because it will be delivered on
+		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
+		 * be set to the loopback interface as well.
+		 */
+		fi = NULL;
 	}
 
 	fnhe = NULL;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e6e65f79ade8..c124c3c12f7c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1309,6 +1309,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	if (skb == tcp_highest_sack(sk))
 		tcp_advance_highest_sack(sk, skb);
 
+	tcp_skb_collapse_tstamp(prev, skb);
 	tcp_unlink_write_queue(skb, sk);
 	sk_wmem_free_skb(sk, skb);
 
@@ -3098,7 +3099,8 @@ static void tcp_ack_tstamp(struct sock *sk, struct sk_buff *skb,
 
 	shinfo = skb_shinfo(skb);
 	if ((shinfo->tx_flags & SKBTX_ACK_TSTAMP) &&
-	    between(shinfo->tskey, prior_snd_una, tcp_sk(sk)->snd_una - 1))
+	    !before(shinfo->tskey, prior_snd_una) &&
+	    before(shinfo->tskey, tcp_sk(sk)->snd_una))
 		__skb_tstamp_tx(skb, NULL, sk, SCM_TSTAMP_ACK);
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7d2dc015cd19..441ae9da3a23 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2441,6 +2441,20 @@ u32 __tcp_select_window(struct sock *sk)
 	return window;
 }
 
+void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+			     const struct sk_buff *next_skb)
+{
+	const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb);
+	u8 tsflags = next_shinfo->tx_flags & SKBTX_ANY_TSTAMP;
+
+	if (unlikely(tsflags)) {
+		struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+		shinfo->tx_flags |= tsflags;
+		shinfo->tskey = next_shinfo->tskey;
+	}
+}
+
 /* Collapses two adjacent SKB's during retransmission. */
 static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 {
@@ -2484,6 +2498,8 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 
 	tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
 
+	tcp_skb_collapse_tstamp(skb, next_skb);
+
 	sk_wmem_free_skb(sk, next_skb);
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 08eed5e16df0..a2e7f55a1f61 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -339,8 +339,13 @@ found:
 
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		spin_lock(&hslot2->lock);
-		hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
-					 &hslot2->head);
+		if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+			sk->sk_family == AF_INET6)
+			hlist_nulls_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
+		else
+			hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
+						 &hslot2->head);
 		hslot2->count++;
 		spin_unlock(&hslot2->lock);
 	}