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

Pull networking fixes from David Miller:

 1) Fix timeouts with direct mode authentication in mac80211, from
    Stanislaw Gruszka.

 2) Aggregation sessions can deadlock in ath9k, from Felix Fietkau.

 3) Netfilter's xt_addrtype doesn't work with ipv6 due to route lookups
    creating undesirable cache entries, from Florian Westphal.

 4) Fix netfilter's ipt_ULOG from generating non-NULL terminated
    strings.

 5) Fix netdev transmit queue crashes in mac80211, from Johannes Berg.

 6) Fix copy and paste error in 802.11 stack that broke reporting of
    64-bit station tx statistics, from Felix Fietkau.

 7) When qlge_probe fails, it leaks the netdev.  Fix from Wei Yongjun.

 8) SKB control block (where we store the IP options information,
    amongst other things) must be cleared properly otherwise ICMP
    sending can crash for IP tunnels.  Fix from Eric Dumazet.

 9) Verification of Energy Efficient Ether support was coded wrongly,
    the test was inversed.  Fix from Giuseppe CAVALLARO.

10) TCP handles redirects improperly because the wrong flow key is used
    for the route lookup.  From Michal Kubecek.

11) Don't interpret MSG_CMSG_COMPAT from userspace, fix from Andy
    Lutomirski.

12) The new AF_VSOCK was missing from the lockdep string table, fix from
    Federico Vaga.

13) be2net doesn't handle checksumming of IP fragments properly, from
    Somnath Kotur.

14) Fix several bugs in the device address list code that lead to
    crashes and other misbehaviors.  From Jay Vosburgh.

15) Fix ipv6 segmentation handling of fragmented GRE tunnel traffic,
    from Pravin B Shalr.

16) Fix usage of stale policies in IPSEC layer, from Paul Moore.

17) Fix team driver dump of ports when there are a large number of them,
    from Jiri Pirko.

18) Fix softlockups in UDP ipv4 socket lookup causes by and error in the
    hlist_nulls_for_each_entry_rcu() macro.  From Eric Dumazet.

19) Fix several regressions added by the high rate accuracy changes to
    the htb packet scheduler.  From Eric Dumazet.

20) Fix DMA'ing onto the stack in esd_usb2 and peak_usb CAN drivers,
    from Olivier Sobrie and Marc Kleine-Budde.

21) Fix unremovable network devices due to missing route pointer
    installation in the per-device ipv6 address list entries.  From Gao
    feng.

22) Apply the tg3 5719 DMA workaround on 5720 chips as well, otherwise
    we get stalls.  From Nithin Sujir.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (68 commits)
  net_sched: htb: do not mix 1ns and 64ns time units
  net: fix sk_buff head without data area
  tg3: Add read dma workaround for 5720
  net: ethernet: xilinx_emaclite: set protocol selector bits when writing ANAR
  bnx2x: Fix bridged GSO for 57710/57711 chips
  net: fec: add fallback to random MAC address
  bnx2x: fix TCP offload for tunneling ipv4 over ipv6
  ipv6: assign rt6_info to inet6_ifaddr in init_loopback
  net/mlx4_core: Keep VF assigned MAC in the PF admin table
  net/mlx4_en: Handle unassigned VF MAC address correctly
  net/mlx4_core: Return -EPROBE_DEFER when a VF is probed before PF is sufficiently initialized
  net/mlx4_en: Fix adaptive moderation cq update
  net: can: peak_usb: Do not do dma on the stack
  net: can: esd_usb2: Do not do dma on the stack
  net: can: kvaser_usb: fix reception on "USBcan Pro" and "USBcan R" type hardware.
  net_sched: restore "overhead xxx" handling
  net: force a reload of first item in hlist_nulls_for_each_entry_rcu
  hyperv: Fix vlan_proto setting in netvsc_recv_callback()
  team: fix port list dump for big number of ports
  list: introduce list_first_entry_or_null
  ...

5 files changed, 55 insertions, 13 deletions

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 07c865a31a3..857ca9f3517 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -30,6 +30,8 @@ static DEFINE_MUTEX(afinfo_mutex);
 
 const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
 EXPORT_SYMBOL(nf_afinfo);
+const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ipv6_ops);
 
 int nf_register_afinfo(const struct nf_afinfo *afinfo)
 {
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 085b5880ab0..05565d2b3a6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1001,6 +1001,32 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
 	return th->rst;
 }
 
+static inline bool is_new_conn(const struct sk_buff *skb,
+			       struct ip_vs_iphdr *iph)
+{
+	switch (iph->protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			return false;
+		return th->syn;
+	}
+	case IPPROTO_SCTP: {
+		sctp_chunkhdr_t *sch, schunk;
+
+		sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
+					 sizeof(schunk), &schunk);
+		if (sch == NULL)
+			return false;
+		return sch->type == SCTP_CID_INIT;
+	}
+	default:
+		return false;
+	}
+}
+
 /* Handle response packets: rewrite addresses and send away...
  */
 static unsigned int
@@ -1612,6 +1638,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	 * Check if the packet belongs to an existing connection entry
 	 */
 	cp = pp->conn_in_get(af, skb, &iph, 0);
+
+	if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp && cp->dest &&
+	    unlikely(!atomic_read(&cp->dest->weight)) && !iph.fragoffs &&
+	    is_new_conn(skb, &iph)) {
+		ip_vs_conn_expire_now(cp);
+		__ip_vs_conn_put(cp);
+		cp = NULL;
+	}
+
 	if (unlikely(!cp) && !iph.fragoffs) {
 		/* No (second) fragments need to enter here, as nf_defrag_ipv6
 		 * replayed fragment zero will already have created the cp
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 0df269d7c99..a65edfe4b16 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -67,8 +67,8 @@ struct ip_vs_sh_bucket {
 #define IP_VS_SH_TAB_MASK               (IP_VS_SH_TAB_SIZE - 1)
 
 struct ip_vs_sh_state {
-	struct ip_vs_sh_bucket		buckets[IP_VS_SH_TAB_SIZE];
 	struct rcu_head			rcu_head;
+	struct ip_vs_sh_bucket		buckets[IP_VS_SH_TAB_SIZE];
 };
 
 /*
diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c
index 491c7d821a0..5ab24843370 100644
--- a/net/netfilter/xt_LOG.c
+++ b/net/netfilter/xt_LOG.c
@@ -737,7 +737,7 @@ static void dump_ipv6_packet(struct sbuff *m,
 		dump_sk_uid_gid(m, skb->sk);
 
 	/* Max length: 16 "MARK=0xFFFFFFFF " */
-	if (!recurse && skb->mark)
+	if (recurse && skb->mark)
 		sb_add(m, "MARK=0x%x ", skb->mark);
 }
 
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index 49c5ff7f6dd..68ff29f6086 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -22,6 +22,7 @@
 #include <net/ip6_fib.h>
 #endif
 
+#include <linux/netfilter_ipv6.h>
 #include <linux/netfilter/xt_addrtype.h>
 #include <linux/netfilter/x_tables.h>
 
@@ -33,12 +34,12 @@ MODULE_ALIAS("ip6t_addrtype");
 
 #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
-			    const struct in6_addr *addr)
+			    const struct in6_addr *addr, u16 mask)
 {
 	const struct nf_afinfo *afinfo;
 	struct flowi6 flow;
 	struct rt6_info *rt;
-	u32 ret;
+	u32 ret = 0;
 	int route_err;
 
 	memset(&flow, 0, sizeof(flow));
@@ -49,12 +50,19 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 	rcu_read_lock();
 
 	afinfo = nf_get_afinfo(NFPROTO_IPV6);
-	if (afinfo != NULL)
+	if (afinfo != NULL) {
+		const struct nf_ipv6_ops *v6ops;
+
+		if (dev && (mask & XT_ADDRTYPE_LOCAL)) {
+			v6ops = nf_get_ipv6_ops();
+			if (v6ops && v6ops->chk_addr(net, addr, dev, true))
+				ret = XT_ADDRTYPE_LOCAL;
+		}
 		route_err = afinfo->route(net, (struct dst_entry **)&rt,
-					flowi6_to_flowi(&flow), !!dev);
-	else
+					  flowi6_to_flowi(&flow), false);
+	} else {
 		route_err = 1;
-
+	}
 	rcu_read_unlock();
 
 	if (route_err)
@@ -62,15 +70,12 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 
 	if (rt->rt6i_flags & RTF_REJECT)
 		ret = XT_ADDRTYPE_UNREACHABLE;
-	else
-		ret = 0;
 
-	if (rt->rt6i_flags & RTF_LOCAL)
+	if (dev == NULL && rt->rt6i_flags & RTF_LOCAL)
 		ret |= XT_ADDRTYPE_LOCAL;
 	if (rt->rt6i_flags & RTF_ANYCAST)
 		ret |= XT_ADDRTYPE_ANYCAST;
 
-
 	dst_release(&rt->dst);
 	return ret;
 }
@@ -90,7 +95,7 @@ static bool match_type6(struct net *net, const struct net_device *dev,
 
 	if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST |
 	     XT_ADDRTYPE_UNREACHABLE) & mask)
-		return !!(mask & match_lookup_rt6(net, dev, addr));
+		return !!(mask & match_lookup_rt6(net, dev, addr, mask));
 	return true;
 }