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

Pull networking fixes from David S. Miller:

 1) Since we do RCU lookups on ipv4 FIB entries, we have to test if the
    entry is dead before returning it to our caller.

 2) openvswitch locking and packet validation fixes from Ansis Atteka,
    Jesse Gross, and Pravin B Shelar.

 3) Fix PM resume locking in IGB driver, from Benjamin Poirier.

 4) Fix VLAN header handling in vhost-net and macvtap, from Basil Gor.

 5) Revert a bogus network namespace isolation change that was causing
    regressions on S390 networking devices.

 6) If bonding decides to process and handle a LACPDU frame, we
    shouldn't bump the rx_dropped counter.  From Jiri Bohac.

 7) Fix mis-calculation of available TX space in r8169 driver when doing
    TSO, which can lead to crashes and/or hung device.  From Julien
    Ducourthial.

 8) SCTP does not validate cached routes properly in all cases, from
    Nicolas Dichtel.

 9) Link status interrupt needs to be handled in ks8851 driver, from
    Stephen Boyd.

10) Use capable(), not cap_raised(), in connector/userns netlink code.
    From Eric W. Biederman via Andrew Morton.

11) Fix pktgen OOPS on module unload, from Eric Dumazet.

12) iwlwifi under-estimates SKB truesizes, also from Eric Dumazet.

13) Cure division by zero in SFC driver, from Ben Hutchings.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (26 commits)
  ks8851: Update link status during link change interrupt
  macvtap: restore vlan header on user read
  vhost-net: fix handle_rx buffer size
  bonding: don't increase rx_dropped after processing LACPDUs
  connector/userns: replace netlink uses of cap_raised() with capable()
  sctp: check cached dst before using it
  pktgen: fix crash at module unload
  Revert "net: maintain namespace isolation between vlan and real device"
  ehea: fix losing of NEQ events when one event occurred early
  igb: fix rtnl race in PM resume path
  ipv4: Do not use dead fib_info entries.
  r8169: fix unsigned int wraparound with TSO
  sfc: Fix division by zero when using one RX channel and no SR-IOV
  openvswitch: Validation of IPv6 set port action uses IPv4 header
  net: compare_ether_addr[_64bits]() has no ordering
  cdc_ether: Ignore bogus union descriptor for RNDIS devices
  bnx2x: bug fix when loading after SAN boot
  e1000: Silence sparse warnings by correcting type
  igb, ixgbe: netdev_tx_reset_queue incorrectly called from tx init path
  openvswitch: Release rtnl_lock if ovs_vport_cmd_build_info() failed.
  ...

8 files changed, 36 insertions, 65 deletions

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 9988d4abb37..9757c193c86 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -157,7 +157,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 		skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
 	}
 
-	skb_set_dev(skb, vlan_dev_priv(dev)->real_dev);
+	skb->dev = vlan_dev_priv(dev)->real_dev;
 	len = skb->len;
 	if (netpoll_tx_running(dev))
 		return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 9bb8f87c4cd..99e1d759f41 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1617,10 +1617,14 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		return NET_RX_DROP;
 	}
 	skb->skb_iif = 0;
-	skb_set_dev(skb, dev);
+	skb->dev = dev;
+	skb_dst_drop(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb->mark = 0;
+	secpath_reset(skb);
+	nf_reset(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1869,36 +1873,6 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
-	skb_dst_drop(skb);
-	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
-		secpath_reset(skb);
-		nf_reset(skb);
-		skb_init_secmark(skb);
-		skb->mark = 0;
-		skb->priority = 0;
-		skb->nf_trace = 0;
-		skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
-		skb->tc_index = 0;
-#endif
-	}
-	skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
 	static const netdev_features_t null_features = 0;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4d8ce93cd50..77a59980b57 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1931,7 +1931,7 @@ static int pktgen_device_event(struct notifier_block *unused,
 {
 	struct net_device *dev = ptr;
 
-	if (!net_eq(dev_net(dev), &init_net))
+	if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting)
 		return NOTIFY_DONE;
 
 	/* It is OK that we do not hold the group lock right now,
@@ -3755,12 +3755,18 @@ static void __exit pg_cleanup(void)
 {
 	struct pktgen_thread *t;
 	struct list_head *q, *n;
+	struct list_head list;
 
 	/* Stop all interfaces & threads */
 	pktgen_exiting = true;
 
-	list_for_each_safe(q, n, &pktgen_threads) {
+	mutex_lock(&pktgen_thread_lock);
+	list_splice(&list, &pktgen_threads);
+	mutex_unlock(&pktgen_thread_lock);
+
+	list_for_each_safe(q, n, &list) {
 		t = list_entry(q, struct pktgen_thread, th_list);
+		list_del(&t->th_list);
 		kthread_stop(t->tsk);
 		kfree(t);
 	}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index bce36f1a37b..30b88d7b4bd 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1370,6 +1370,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 				continue;
+			if (fi->fib_dead)
+				continue;
 			if (fa->fa_info->fib_scope < flp->flowi4_scope)
 				continue;
 			fib_alias_accessed(fa);
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e44e631ea95..777716bc80f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -421,6 +421,19 @@ static int validate_sample(const struct nlattr *attr,
 	return validate_actions(actions, key, depth + 1);
 }
 
+static int validate_tp_port(const struct sw_flow_key *flow_key)
+{
+	if (flow_key->eth.type == htons(ETH_P_IP)) {
+		if (flow_key->ipv4.tp.src && flow_key->ipv4.tp.dst)
+			return 0;
+	} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
+		if (flow_key->ipv6.tp.src && flow_key->ipv6.tp.dst)
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key)
 {
@@ -462,18 +475,13 @@ static int validate_set(const struct nlattr *a,
 		if (flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;
 
-		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
-			return -EINVAL;
-
-		break;
+		return validate_tp_port(flow_key);
 
 	case OVS_KEY_ATTR_UDP:
 		if (flow_key->ip.proto != IPPROTO_UDP)
 			return -EINVAL;
 
-		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
-			return -EINVAL;
-		break;
+		return validate_tp_port(flow_key);
 
 	default:
 		return -EINVAL;
@@ -1641,10 +1649,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
 					 OVS_VPORT_CMD_NEW);
 	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
 		netlink_set_err(init_net.genl_sock, 0,
-				ovs_dp_vport_multicast_group.id, err);
-		return 0;
+				ovs_dp_vport_multicast_group.id, PTR_ERR(reply));
+		goto exit_unlock;
 	}
 
 	genl_notify(reply, genl_info_net(info), info->snd_pid,
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 1252c3081ef..2a11ec2383e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -183,7 +183,8 @@ void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
 	u8 tcp_flags = 0;
 
 	if (flow->key.eth.type == htons(ETH_P_IP) &&
-	    flow->key.ip.proto == IPPROTO_TCP) {
+	    flow->key.ip.proto == IPPROTO_TCP &&
+	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
 		u8 *tcp = (u8 *)tcp_hdr(skb);
 		tcp_flags = *(tcp + TCP_FLAGS_OFFSET) & TCP_FLAG_MASK;
 	}
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 817174eb5f4..8fc4dcd294a 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -377,9 +377,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 	 */
 	skb_set_owner_w(nskb, sk);
 
-	/* The 'obsolete' field of dst is set to 2 when a dst is freed. */
-	if (!dst || (dst->obsolete > 1)) {
-		dst_release(dst);
+	if (!sctp_transport_dst_check(tp)) {
 		sctp_transport_route(tp, NULL, sctp_sk(sk));
 		if (asoc && (asoc->param_flags & SPP_PMTUD_ENABLE)) {
 			sctp_assoc_sync_pmtu(asoc);
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 3889330b7b0..b026ba0c699 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -226,23 +226,6 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
 		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
 }
 
-/* this is a complete rip-off from __sk_dst_check
- * the cookie is always 0 since this is how it's used in the
- * pmtu code
- */
-static struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
-{
-	struct dst_entry *dst = t->dst;
-
-	if (dst && dst->obsolete && dst->ops->check(dst, 0) == NULL) {
-		dst_release(t->dst);
-		t->dst = NULL;
-		return NULL;
-	}
-
-	return dst;
-}
-
 void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 {
 	struct dst_entry *dst;