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
  ...

10 files changed, 74 insertions, 4 deletions

diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8541a913f6a3..d1f904c8b2cb 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -828,6 +828,11 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
+enum mlx4_pci_status {
+	MLX4_PCI_STATUS_DISABLED,
+	MLX4_PCI_STATUS_ENABLED,
+};
+
 struct mlx4_dev_persistent {
 	struct pci_dev	       *pdev;
 	struct mlx4_dev	       *dev;
@@ -841,6 +846,8 @@ struct mlx4_dev_persistent {
 	u8		state;
 	struct mutex	interface_state_mutex; /* protect SW state */
 	u8	interface_state;
+	struct mutex		pci_status_mutex; /* sync pci state */
+	enum mlx4_pci_status	pci_status;
 };
 
 struct mlx4_dev {
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index 1c33dd7da4a7..4ae95f7e8597 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -98,6 +98,45 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 	if (!is_a_nulls(first))
 		first->pprev = &n->next;
 }
+
+/**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the end of the specified hlist_nulls,
+ * while permitting racing traversals.  NOTE: tail insertion requires
+ * list traversal.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	for (i = hlist_nulls_first_rcu(h); !is_a_nulls(i);
+	     i = hlist_nulls_next_rcu(i))
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_nulls_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
 /**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index c0a92e2c286d..74c9693d4941 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -17,6 +17,7 @@
 #include <linux/hardirq.h>
 #include <linux/rcupdate.h>
 #include <net/sock.h>
+#include <net/inet_sock.h>
 
 #ifdef CONFIG_CGROUP_NET_CLASSID
 struct cgroup_cls_state {
@@ -63,11 +64,13 @@ static inline u32 task_get_classid(const struct sk_buff *skb)
 	 * softirqs always disables bh.
 	 */
 	if (in_serving_softirq()) {
+		struct sock *sk = skb_to_full_sk(skb);
+
 		/* If there is an sock_cgroup_classid we'll use that. */
-		if (!skb->sk)
+		if (!sk || !sk_fullsock(sk))
 			return 0;
 
-		classid = sock_cgroup_classid(&skb->sk->sk_cgrp_data);
+		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 	}
 
 	return classid;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 295d291269e2..54c779416eec 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -101,6 +101,9 @@ void fib6_force_start_gc(struct net *net);
 struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr, bool anycast);
 
+struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
+			       int flags);
+
 /*
  *	support functions for ND
  *
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d0aeb97aec5d..1be050ada8c5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -959,6 +959,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len);
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr,
 				 int addr_len);
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr);
+void ip6_datagram_release_cb(struct sock *sk);
 
 int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
diff --git a/include/net/route.h b/include/net/route.h
index 9b0a523bb428..6de665bf1750 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -209,6 +209,9 @@ unsigned int inet_addr_type_dev_table(struct net *net,
 void ip_rt_multicast_event(struct in_device *);
 int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
 void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
+struct rtable *rt_dst_alloc(struct net_device *dev,
+			     unsigned int flags, u16 type,
+			     bool nopolicy, bool noxfrm, bool will_cache);
 
 struct in_ifaddr;
 void fib_add_ifaddr(struct in_ifaddr *);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 6df1ce7a411c..5a404c354f4c 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -847,6 +847,11 @@ struct sctp_transport {
 	 */
 	ktime_t last_time_heard;
 
+	/* When was the last time that we sent a chunk using this
+	 * transport? We use this to check for idle transports
+	 */
+	unsigned long last_time_sent;
+
 	/* Last time(in jiffies) when cwnd is reduced due to the congestion
 	 * indication based on ECNE chunk.
 	 */
@@ -952,7 +957,8 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *,
 			  struct sctp_sock *);
 void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk);
 void sctp_transport_free(struct sctp_transport *);
-void sctp_transport_reset_timers(struct sctp_transport *);
+void sctp_transport_reset_t3_rtx(struct sctp_transport *);
+void sctp_transport_reset_hb_timer(struct sctp_transport *);
 int sctp_transport_hold(struct sctp_transport *);
 void sctp_transport_put(struct sctp_transport *);
 void sctp_transport_update_rto(struct sctp_transport *, __u32);
diff --git a/include/net/sock.h b/include/net/sock.h
index 255d3e03727b..121ffc115c4f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -630,7 +630,11 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
+	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+	    sk->sk_family == AF_INET6)
+		hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+	else
+		hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b91370f61be6..6db10228113f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -552,6 +552,8 @@ void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
 bool tcp_schedule_loss_probe(struct sock *sk);
+void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+			     const struct sk_buff *next_skb);
 
 /* tcp_input.c */
 void tcp_resume_early_retransmit(struct sock *sk);
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index b71fd0b5cbad..813ffb2e22c9 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -96,6 +96,7 @@ header-y += cyclades.h
 header-y += cycx_cfm.h
 header-y += dcbnl.h
 header-y += dccp.h
+header-y += devlink.h
 header-y += dlmconstants.h
 header-y += dlm_device.h
 header-y += dlm.h