Merge commit '9f12600fe425bc28f0ccba034a77783c09c15af4' into for-linus

Backmerge of dcache.c changes from mainline.  It's that, or complete
rebase...

Conflicts:
	fs/splice.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

net/8021q/vlan.c

@@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
+	vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_uninit_mvrp;

net/8021q/vlan_dev.c

@@ -493,48 +493,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 	}
 }
 
-static int vlan_calculate_locking_subclass(struct net_device *real_dev)
-{
-	int subclass = 0;
-
-	while (is_vlan_dev(real_dev)) {
-		subclass++;
-		real_dev = vlan_dev_priv(real_dev)->real_dev;
-	}
-
-	return subclass;
-}
-
-static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
-{
-	int err = 0, subclass;
-
-	subclass = vlan_calculate_locking_subclass(to);
-
-	spin_lock_nested(&to->addr_list_lock, subclass);
-	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
-	if (!err)
-		__dev_set_rx_mode(to);
-	spin_unlock(&to->addr_list_lock);
-}
-
-static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
-{
-	int err = 0, subclass;
-
-	subclass = vlan_calculate_locking_subclass(to);
-
-	spin_lock_nested(&to->addr_list_lock, subclass);
-	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
-	if (!err)
-		__dev_set_rx_mode(to);
-	spin_unlock(&to->addr_list_lock);
-}
-
 static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 {
-	vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
-	vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
 /*
@@ -562,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
 }
 
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->nest_level;
+}
+
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.rebuild = vlan_dev_rebuild_header,
@@ -597,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0;
 
 	netif_carrier_off(dev);
 
@@ -646,8 +612,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	subclass = vlan_calculate_locking_subclass(dev);
-	vlan_dev_set_lockdep_class(dev, subclass);
+	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
 
 	vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
@@ -819,6 +784,7 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 };
 
 void vlan_setup(struct net_device *dev)

net/batman-adv/bat_iv_ogm.c

@@ -1545,6 +1545,8 @@ out_neigh:
 	if ((orig_neigh_node) && (!is_single_hop_neigh))
 		batadv_orig_node_free_ref(orig_neigh_node);
 out:
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 	if (router)
 		batadv_neigh_node_free_ref(router);
 	if (router_router)

net/batman-adv/distributed-arp-table.c

@@ -940,8 +940,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		 * additional DAT answer may trigger kernel warnings about
 		 * a packet coming from the wrong port.
 		 */
-		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr,
-					BATADV_NO_FLAGS)) {
+		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) {
 			ret = true;
 			goto out;
 		}

net/batman-adv/fragmentation.c

@@ -418,12 +418,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			     struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_priv *bat_priv;
-	struct batadv_hard_iface *primary_if;
+	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_frag_packet frag_header;
 	struct sk_buff *skb_fragment;
 	unsigned mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned header_size = sizeof(frag_header);
 	unsigned max_fragment_size, max_packet_size;
+	bool ret = false;
 
 	/* To avoid merge and refragmentation at next-hops we never send
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -483,7 +484,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			   skb->len + ETH_HLEN);
 	batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
 
-	return true;
+	ret = true;
+
 out_err:
-	return false;
+	if (primary_if)
+		batadv_hardif_free_ref(primary_if);
+
+	return ret;
 }

net/batman-adv/gateway_client.c

@@ -42,8 +42,10 @@
 
 static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node)
 {
-	if (atomic_dec_and_test(&gw_node->refcount))
+	if (atomic_dec_and_test(&gw_node->refcount)) {
+		batadv_orig_node_free_ref(gw_node->orig_node);
 		kfree_rcu(gw_node, rcu);
+	}
 }
 
 static struct batadv_gw_node *
@@ -406,10 +408,15 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 	if (gateway->bandwidth_down == 0)
 		return;
 
-	gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
-	if (!gw_node)
+	if (!atomic_inc_not_zero(&orig_node->refcount))
 		return;
 
+	gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
+	if (!gw_node) {
+		batadv_orig_node_free_ref(orig_node);
+		return;
+	}
+
 	INIT_HLIST_NODE(&gw_node->list);
 	gw_node->orig_node = orig_node;
 	atomic_set(&gw_node->refcount, 1);

net/batman-adv/hard-interface.c

@@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 		return true;
 
 	/* no more parents..stop recursion */
-	if (net_dev->iflink == net_dev->ifindex)
+	if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
 		return false;
 
 	/* recurse over the parent device */

net/batman-adv/originator.c

@@ -501,12 +501,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
 static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 {
 	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_neigh_node *router;
 
 	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
 
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
 		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
 
+	/* this is the last reference to this object */
+	router = rcu_dereference_protected(orig_ifinfo->router, true);
+	if (router)
+		batadv_neigh_node_free_ref_now(router);
 	kfree(orig_ifinfo);
 }
 
@@ -701,6 +706,47 @@ free_orig_node:
 	return NULL;
 }
 
+/**
+ * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor
+ * @bat_priv: the bat priv with all the soft interface information
+ * @neigh: orig node which is to be checked
+ */
+static void
+batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
+			  struct batadv_neigh_node *neigh)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+	struct batadv_hard_iface *if_outgoing;
+	struct hlist_node *node_tmp;
+
+	spin_lock_bh(&neigh->ifinfo_lock);
+
+	/* for all ifinfo objects for this neighinator */
+	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+				  &neigh->ifinfo_list, list) {
+		if_outgoing = neigh_ifinfo->if_outgoing;
+
+		/* always keep the default interface */
+		if (if_outgoing == BATADV_IF_DEFAULT)
+			continue;
+
+		/* don't purge if the interface is not (going) down */
+		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+			continue;
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "neighbor/ifinfo purge: neighbor %pM, iface: %s\n",
+			   neigh->addr, if_outgoing->net_dev->name);
+
+		hlist_del_rcu(&neigh_ifinfo->list);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	}
+
+	spin_unlock_bh(&neigh->ifinfo_lock);
+}
+
 /**
  * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator
  * @bat_priv: the bat priv with all the soft interface information
@@ -800,6 +846,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 
 			hlist_del_rcu(&neigh_node->list);
 			batadv_neigh_node_free_ref(neigh_node);
+		} else {
+			/* only necessary if not the whole neighbor is to be
+			 * deleted, but some interface has been removed.
+			 */
+			batadv_purge_neigh_ifinfo(bat_priv, neigh_node);
 		}
 	}
 
@@ -857,7 +908,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 {
 	struct batadv_neigh_node *best_neigh_node;
 	struct batadv_hard_iface *hard_iface;
-	bool changed;
+	bool changed_ifinfo, changed_neigh;
 
 	if (batadv_has_timed_out(orig_node->last_seen,
 				 2 * BATADV_PURGE_TIMEOUT)) {
@@ -867,10 +918,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 			   jiffies_to_msecs(orig_node->last_seen));
 		return true;
 	}
-	changed = batadv_purge_orig_ifinfo(bat_priv, orig_node);
-	changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node);
+	changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node);
+	changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node);
 
-	if (!changed)
+	if (!changed_ifinfo && !changed_neigh)
 		return false;
 
 	/* first for NULL ... */
@@ -1028,7 +1079,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
 	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
 
 out:
-	batadv_hardif_free_ref(hard_iface);
+	if (hard_iface)
+		batadv_hardif_free_ref(hard_iface);
 	return 0;
 }
 

net/bridge/br_netfilter.c

@@ -859,12 +859,12 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 	return NF_STOLEN;
 }
 
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
 
-	if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
+	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
 	    !skb_is_gso(skb)) {
 		if (br_parse_ip_options(skb))

net/ceph/messenger.c

@@ -557,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
 	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -570,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	return ret;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, bool more)
+{
+	int ret;
+	struct kvec iov;
+
+	/* sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fallback to sendmsg if that's the case */
+	if (page_count(page) >= 1)
+		return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+	iov.iov_base = kmap(page) + offset;
+	iov.iov_len = size;
+	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+	kunmap(page);
+
+	return ret;
+}
 
 /*
  * Shutdown/close the socket for the given connection.

net/ceph/osdmap.c

@@ -329,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_descend_once = %d",
 	     c->chooseleaf_descend_once);
 
+	ceph_decode_need(p, end, sizeof(u8), done);
+	c->chooseleaf_vary_r = ceph_decode_8(p);
+	dout("crush decode tunable chooseleaf_vary_r = %d",
+	     c->chooseleaf_vary_r);
+
 done:
 	dout("crush_decode success\n");
 	return c;

net/core/dev.c

@@ -2418,7 +2418,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
 	int i;
@@ -2493,38 +2493,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-					    const struct net_device *dev,
-					    netdev_features_t features)
+	netdev_features_t features)
 {
 	int tmp;
 
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(dev, skb)) {
+	} else if (illegal_highdma(skb->dev, skb)) {
 		features &= ~NETIF_F_SG;
 	}
 
 	return features;
 }
 
-netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
-					 const struct net_device *dev)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = dev->features;
+	netdev_features_t features = skb->dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
+	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, dev, features);
+		return harmonize_features(skb, features);
 	}
 
-	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
 					       NETIF_F_HW_VLAN_STAG_TX);
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2532,9 +2530,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
 				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_STAG_TX;
 
-	return harmonize_features(skb, dev, features);
+	return harmonize_features(skb, features);
 }
-EXPORT_SYMBOL(netif_skb_dev_features);
+EXPORT_SYMBOL(netif_skb_features);
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
@@ -3953,6 +3951,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
+	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -4542,6 +4541,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
 }
 EXPORT_SYMBOL(netdev_adjacent_get_private);
 
+/**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
 /**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
@@ -4623,6 +4648,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
+/**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
 /**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
@@ -5073,6 +5124,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev))
+{
+	struct net_device *lower = NULL;
+	struct list_head *iter;
+	int max_nest = -1;
+	int nest;
+
+	ASSERT_RTNL();
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		nest = dev_get_nest_level(lower, type_check);
+		if (max_nest < nest)
+			max_nest = nest;
+	}
+
+	if (type_check(dev))
+		max_nest++;
+
+	return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -5238,7 +5313,6 @@ void __dev_set_rx_mode(struct net_device *dev)
 	if (ops->ndo_set_rx_mode)
 		ops->ndo_set_rx_mode(dev);
 }
-EXPORT_SYMBOL(__dev_set_rx_mode);
 
 void dev_set_rx_mode(struct net_device *dev)
 {
@@ -5543,7 +5617,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {

net/core/neighbour.c

@@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-	neigh->nud_state = NUD_PROBE;
-	atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+	neigh->nud_state = NUD_INCOMPLETE;
+	atomic_set(&neigh->probes, neigh_max_probes(neigh));
 	neigh_add_timer(neigh,
 			jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
 }

net/core/net_namespace.c

@@ -24,7 +24,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);

net/core/rtnetlink.c

@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
 
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+	struct net *net;
+	bool unregistering;
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&netdev_unregistering_wq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		unregistering = false;
+		rtnl_lock();
+		for_each_net(net) {
+			if (net->dev_unreg_count > 0) {
+				unregistering = true;
+				break;
+			}
+		}
+		if (!unregistering)
+			break;
+		__rtnl_unlock();
+		schedule();
+	}
+	finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 /**
  * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-	rtnl_lock();
+	/* Close the race with cleanup_net() */
+	mutex_lock(&net_mutex);
+	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
 	rtnl_unlock();
+	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 

net/core/skbuff.c

@@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
 
-	lp = NAPI_GRO_CB(p)->last ?: p;
+	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
 	if (headlen <= offset) {
@@ -3192,7 +3192,7 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	if (!NAPI_GRO_CB(p)->last)
+	if (NAPI_GRO_CB(p)->last == p)
 		skb_shinfo(p)->frag_list = skb;
 	else
 		NAPI_GRO_CB(p)->last->next = skb;

net/core/utils.c

@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
 {
 	struct __net_random_once_work *work =
 		container_of(w, struct __net_random_once_work, work);
-	if (!static_key_enabled(work->key))
-		static_key_slow_inc(work->key);
+	BUG_ON(!static_key_enabled(work->key));
+	static_key_slow_dec(work->key);
 	kfree(work);
 }
 
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
 }
 
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
-			   struct static_key *done_key)
+			   struct static_key *once_key)
 {
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 	*done = true;
 	spin_unlock_irqrestore(&lock, flags);
 
-	__net_random_once_disable_jump(done_key);
+	__net_random_once_disable_jump(once_key);
 
 	return true;
 }

net/dsa/dsa.c

@@ -406,8 +406,9 @@ static int dsa_of_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	chip_index = 0;
+	chip_index = -1;
 	for_each_available_child_of_node(np, child) {
+		chip_index++;
 		cd = &pd->chip[chip_index];
 
 		cd->mii_bus = &mdio_bus->dev;

net/ipv4/af_inet.c

@@ -1650,6 +1650,39 @@ static int __init init_ipv4_mibs(void)
 	return register_pernet_subsys(&ipv4_mib_ops);
 }
 
+static __net_init int inet_init_net(struct net *net)
+{
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] =  32768;
+	net->ipv4.ip_local_ports.range[1] =  61000;
+
+	seqlock_init(&net->ipv4.ping_group_range.lock);
+	/*
+	 * Sane defaults - nobody may create ping sockets.
+	 * Boot scripts should set this to distro-specific group.
+	 */
+	net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+	net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+	return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+	.init = inet_init_net,
+	.exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+	return register_pernet_subsys(&af_inet_ops);
+}
+
 static int ipv4_proc_init(void);
 
 /*
@@ -1794,6 +1827,9 @@ static int __init inet_init(void)
 	if (ip_mr_init())
 		pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
 #endif
+
+	if (init_inet_pernet_ops())
+		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
 	/*
 	 *	Initialise per-cpu ipv4 mibs
 	 */

net/ipv4/fib_semantics.c

@@ -821,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;

net/ipv4/inet_connection_sock.c

@@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
-		*low = net->ipv4.sysctl_local_ports.range[0];
-		*high = net->ipv4.sysctl_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+		*low = net->ipv4.ip_local_ports.range[0];
+		*high = net->ipv4.ip_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 

net/ipv4/ip_forward.c

@@ -42,12 +42,12 @@
 static bool ip_may_fragment(const struct sk_buff *skb)
 {
 	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-	       !skb->local_df;
+		skb->local_df;
 }
 
 static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
@@ -56,53 +56,6 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
-{
-	unsigned int mtu;
-
-	if (skb->local_df || !skb_is_gso(skb))
-		return false;
-
-	mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
-
-	/* if seglen > mtu, do software segmentation for IP fragmentation on
-	 * output.  DF bit cannot be set since ip_forward would have sent
-	 * icmp error.
-	 */
-	return skb_gso_network_seglen(skb) > mtu;
-}
-
-/* called if GSO skb needs to be fragmented on forward */
-static int ip_forward_finish_gso(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	netdev_features_t features;
-	struct sk_buff *segs;
-	int ret = 0;
-
-	features = netif_skb_dev_features(skb, dst->dev);
-	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
-	if (IS_ERR(segs)) {
-		kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	consume_skb(skb);
-
-	do {
-		struct sk_buff *nskb = segs->next;
-		int err;
-
-		segs->next = NULL;
-		err = dst_output(segs);
-
-		if (err && ret == 0)
-			ret = err;
-		segs = nskb;
-	} while (segs);
-
-	return ret;
-}
 
 static int ip_forward_finish(struct sk_buff *skb)
 {
@@ -114,9 +67,6 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	if (ip_gso_exceeds_dst_mtu(skb))
-		return ip_forward_finish_gso(skb);
-
 	return dst_output(skb);
 }
 

net/ipv4/ip_fragment.c

@@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg)
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (qp->user == IP_DEFRAG_AF_PACKET ||
-		    (qp->user == IP_DEFRAG_CONNTRACK_IN &&
-		     skb_rtable(head)->rt_type != RTN_LOCAL))
+		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
 			goto out_rcu_unlock;
 
 

net/ipv4/ip_output.c

@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_finish_output(struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,10 +262,13 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)

net/ipv4/ip_tunnel.c

@@ -540,9 +540,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
-	bool connected = true;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -882,6 +883,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();

net/ipv4/ip_vti.c

@@ -239,6 +239,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 static int vti4_err(struct sk_buff *skb, u32 info)
 {
 	__be32 spi;
+	__u32 mark;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel;
 	struct ip_esp_hdr *esph;
@@ -254,6 +255,8 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 	if (!tunnel)
 		return -1;
 
+	mark = be32_to_cpu(tunnel->parms.o_key);
+
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
@@ -281,7 +284,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 		return 0;
 	}
 
-	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, protocol, AF_INET);
 	if (!x)
 		return 0;

net/ipv4/netfilter/nf_defrag_ipv4.c

@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->local_df = 1;
+	}
 
 	return err;
 }

net/ipv4/ping.c

@@ -236,15 +236,15 @@ exit:
 static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 					  kgid_t *high)
 {
-	kgid_t *data = net->ipv4.sysctl_ping_group_range;
+	kgid_t *data = net->ipv4.ping_group_range.range;
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 

net/ipv4/route.c

@@ -1519,7 +1519,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));

net/ipv4/sysctl_net_ipv4.c

@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] = range[0];
-	net->ipv4.sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] = range[0];
+	net->ipv4.ip_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 size_t *lenp, loff_t *ppos)
 {
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
+		container_of(table->data, struct net, ipv4.ip_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ping_group_range",
-		.data		= &init_net.ipv4.sysctl_ping_group_range,
+		.data		= &init_net.ipv4.ping_group_range.range,
 		.maxlen		= sizeof(gid_t)*2,
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
@@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
-		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
+		.data		= &init_net.ipv4.ip_local_ports.range,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
@@ -858,20 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			table[i].data += (void *)net - (void *)&init_net;
 	}
 
-	/*
-	 * Sane defaults - nobody may create ping sockets.
-	 * Boot scripts should set this to distro-specific group.
-	 */
-	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
-	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
-	/*
-	 * Set defaults for local port range
-	 */
-	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] =  32768;
-	net->ipv4.sysctl_local_ports.range[1] =  61000;
-
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;

net/ipv4/xfrm4_output.c

@@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED;
-
-	skb->protocol = htons(ETH_P_IP);
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
 
 int xfrm4_output_finish(struct sk_buff *skb)
 {
-#ifdef CONFIG_NETFILTER
-	if (!skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
-		return dst_output(skb);
-	}
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	skb->protocol = htons(ETH_P_IP);
 
+#ifdef CONFIG_NETFILTER
 	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IP);
 	return xfrm_output(skb);
 }
 
+static int __xfrm4_output(struct sk_buff *skb)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IPCB(skb)->flags |= IPSKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
+
+	return x->outer_mode->afinfo->output_finish(skb);
+}
+
 int xfrm4_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct xfrm_state *x = dst->xfrm;
-
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-			    NULL, dst->dev,
-			    x->outer_mode->afinfo->output_finish,
+			    NULL, skb_dst(skb)->dev, __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 

net/ipv4/xfrm4_protocol.c

@@ -50,8 +50,12 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(protocol);
 
-	for_each_protocol_rcu(*proto_handlers(protocol), handler)
+	if (!head)
+		return 0;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->cb_handler(skb, err)) <= 0)
 			return ret;
 
@@ -64,15 +68,20 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
 
 	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
 	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
 	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
 
-	for_each_protocol_rcu(*proto_handlers(nexthdr), handler)
+	if (!head)
+		goto out;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
 			return ret;
 
+out:
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 	kfree_skb(skb);
@@ -208,6 +217,9 @@ int xfrm4_protocol_register(struct xfrm4_protocol *handler,
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -250,6 +262,9 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
 	struct xfrm4_protocol *t;
 	int ret = -ENOENT;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	for (pprev = proto_handlers(protocol);

net/ipv6/ip6_offload.c

@@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	unsigned int off;
 	u16 flush = 1;
 	int proto;
-	__wsum csum;
 
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*iph);
@@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	NAPI_GRO_CB(skb)->flush |= flush;
 
-	csum = skb->csum;
-	skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
+	skb_gro_postpull_rcsum(skb, iph, nlen);
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
-	skb->csum = csum;
-
 out_unlock:
 	rcu_read_unlock();
 

net/ipv6/ip6_output.c

@@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 
 static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
+	/* ipv6 conntrack defrag sets max_frag_size + local_df */
 	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
 		return true;
 
+	if (skb->local_df)
+		return false;
+
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
 		return false;
 
@@ -1225,7 +1229,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		unsigned int maxnonfragsize, headersize;
 
 		headersize = sizeof(struct ipv6hdr) +
-			     (opt ? opt->tot_len : 0) +
+			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
 			     (dst_allfrag(&rt->dst) ?
 			      sizeof(struct frag_hdr) : 0) +
 			     rt->rt6i_nfheader_len;

net/ipv6/ip6_tunnel.c

@@ -1557,7 +1557,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	u8 proto;
 
-	if (!data)
+	if (!data || !data[IFLA_IPTUN_PROTO])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);

net/ipv6/ip6_vti.c

@@ -511,6 +511,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    u8 type, u8 code, int offset, __be32 info)
 {
 	__be32 spi;
+	__u32 mark;
 	struct xfrm_state *x;
 	struct ip6_tnl *t;
 	struct ip_esp_hdr *esph;
@@ -524,6 +525,8 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!t)
 		return -1;
 
+	mark = be32_to_cpu(t->parms.o_key);
+
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data + offset);
@@ -545,7 +548,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	    type != NDISC_REDIRECT)
 		return 0;
 
-	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, protocol, AF_INET6);
 	if (!x)
 		return 0;
@@ -1097,7 +1100,6 @@ static int __init vti6_tunnel_init(void)
 
 	err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
 	if (err < 0) {
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;
@@ -1106,7 +1108,6 @@ static int __init vti6_tunnel_init(void)
 	err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
 	if (err < 0) {
 		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;
@@ -1116,7 +1117,6 @@ static int __init vti6_tunnel_init(void)
 	if (err < 0) {
 		xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
 		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;

net/ipv6/ndisc.c

@@ -851,7 +851,7 @@ out:
 static void ndisc_recv_na(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
-	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
 	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
 	u8 *lladdr = NULL;
 	u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
@@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 			/*
 			 * Change: router to host
 			 */
-			struct rt6_info *rt;
-			rt = rt6_get_dflt_router(saddr, dev);
-			if (rt)
-				ip6_del_rt(rt);
+			rt6_clean_tohost(dev_net(dev),  saddr);
 		}
 
 out:

net/ipv6/netfilter.c

@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */

net/ipv6/route.c

@@ -2234,6 +2234,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
 }
 
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+/* Remove routers and update dst entries when gateway turn into host. */
+static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+{
+	struct in6_addr *gateway = (struct in6_addr *)arg;
+
+	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
+	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
+	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+		return -1;
+	}
+	return 0;
+}
+
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
+{
+	fib6_clean_all(net, fib6_clean_tohost, gateway);
+}
+
 struct arg_dev_net {
 	struct net_device *dev;
 	struct net *net;
@@ -2709,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 	if (tb[RTA_OIF])
 		oif = nla_get_u32(tb[RTA_OIF]);
 
+	if (tb[RTA_MARK])
+		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
 	if (iif) {
 		struct net_device *dev;
 		int flags = 0;

net/ipv6/tcpv6_offload.c

@@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:

net/ipv6/xfrm6_output.c

@@ -114,12 +114,6 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-#ifdef CONFIG_NETFILTER
-	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
-
-	skb->protocol = htons(ETH_P_IPV6);
 	skb->local_df = 1;
 
 	return x->outer_mode->output2(x, skb);
@@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output);
 
 int xfrm6_output_finish(struct sk_buff *skb)
 {
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+	skb->protocol = htons(ETH_P_IPV6);
+
 #ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IPV6);
 	return xfrm_output(skb);
 }
 
@@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb)
 	struct xfrm_state *x = dst->xfrm;
 	int mtu;
 
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
+
 	if (skb->protocol == htons(ETH_P_IPV6))
 		mtu = ip6_skb_dst_mtu(skb);
 	else
@@ -165,6 +168,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 
 int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL,
-		       skb_dst(skb)->dev, __xfrm6_output);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+			    NULL, skb_dst(skb)->dev, __xfrm6_output,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }

net/ipv6/xfrm6_protocol.c

@@ -50,6 +50,10 @@ int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm6_protocol *handler;
+	struct xfrm6_protocol __rcu **head = proto_handlers(protocol);
+
+	if (!head)
+		return 0;
 
 	for_each_protocol_rcu(*proto_handlers(protocol), handler)
 		if ((ret = handler->cb_handler(skb, err)) <= 0)
@@ -184,10 +188,12 @@ int xfrm6_protocol_register(struct xfrm6_protocol *handler,
 	struct xfrm6_protocol __rcu **pprev;
 	struct xfrm6_protocol *t;
 	bool add_netproto = false;
-
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm6_protocol_mutex);
 
 	if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -230,6 +236,9 @@ int xfrm6_protocol_deregister(struct xfrm6_protocol *handler,
 	struct xfrm6_protocol *t;
 	int ret = -ENOENT;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm6_protocol_mutex);
 
 	for (pprev = proto_handlers(protocol);

net/iucv/af_iucv.c

@@ -1830,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}

net/mac80211/ieee80211_i.h

@@ -317,6 +317,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 

net/mac80211/mlme.c

@@ -3598,18 +3598,24 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 
 	sdata_lock(sdata);
 
-	if (ifmgd->auth_data) {
+	if (ifmgd->auth_data || ifmgd->assoc_data) {
+		const u8 *bssid = ifmgd->auth_data ?
+				ifmgd->auth_data->bss->bssid :
+				ifmgd->assoc_data->bss->bssid;
+
 		/*
-		 * If we are trying to authenticate while suspending, cfg80211
-		 * won't know and won't actually abort those attempts, thus we
-		 * need to do that ourselves.
+		 * If we are trying to authenticate / associate while suspending,
+		 * cfg80211 won't know and won't actually abort those attempts,
+		 * thus we need to do that ourselves.
 		 */
-		ieee80211_send_deauth_disassoc(sdata,
-					       ifmgd->auth_data->bss->bssid,
+		ieee80211_send_deauth_disassoc(sdata, bssid,
 					       IEEE80211_STYPE_DEAUTH,
 					       WLAN_REASON_DEAUTH_LEAVING,
 					       false, frame_buf);
-		ieee80211_destroy_auth_data(sdata, false);
+		if (ifmgd->assoc_data)
+			ieee80211_destroy_assoc_data(sdata, false);
+		if (ifmgd->auth_data)
+			ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 				      IEEE80211_DEAUTH_FRAME_LEN);
 	}

net/mac80211/offchannel.c

@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 
@@ -354,14 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
-		ieee80211_offchannel_stop_vifs(local);
+		WARN_ON(local->use_chanctx);
 
-		/* switch channel etc */
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
+
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);
@@ -380,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;

net/mac80211/rx.c

@@ -1231,7 +1231,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) &&
 		    test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
 			sta->last_rx = jiffies;
-			if (ieee80211_is_data(hdr->frame_control)) {
+			if (ieee80211_is_data(hdr->frame_control) &&
+			    !is_multicast_ether_addr(hdr->addr1)) {
 				sta->last_rx_rate_idx = status->rate_idx;
 				sta->last_rx_rate_flag = status->flag;
 				sta->last_rx_rate_vht_flag = status->vht_flag;

net/mac80211/sta_info.c

@@ -1148,7 +1148,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	atomic_dec(&ps->num_sta_ps);
 
 	/* This station just woke up and isn't aware of our SMPS state */
-	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
+	if (!ieee80211_vif_is_mesh(&sdata->vif) &&
+	    !ieee80211_smps_is_restrictive(sta->known_smps_mode,
 					   sdata->smps_mode) &&
 	    sta->known_smps_mode != sdata->bss->req_smps &&
 	    sta_info_tx_streams(sta) != 1) {

net/mac80211/status.c

@@ -314,10 +314,9 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
 	    !is_multicast_ether_addr(hdr->addr1))
 		txflags |= IEEE80211_RADIOTAP_F_TX_FAIL;
 
-	if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) ||
-	    (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT))
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
 		txflags |= IEEE80211_RADIOTAP_F_TX_CTS;
-	else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
 		txflags |= IEEE80211_RADIOTAP_F_TX_RTS;
 
 	put_unaligned_le16(txflags, pos);

net/mac80211/trace.h

@@ -21,10 +21,10 @@
 
 #define VIF_ENTRY	__field(enum nl80211_iftype, vif_type) __field(void *, sdata)	\
 			__field(bool, p2p)						\
-			__string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>")
+			__string(vif_name, sdata->name)
 #define VIF_ASSIGN	__entry->vif_type = sdata->vif.type; __entry->sdata = sdata;	\
 			__entry->p2p = sdata->vif.p2p;					\
-			__assign_str(vif_name, sdata->dev ? sdata->dev->name : sdata->name)
+			__assign_str(vif_name, sdata->name)
 #define VIF_PR_FMT	" vif:%s(%d%s)"
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 

net/mac80211/util.c

@@ -1780,7 +1780,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mutex_unlock(&local->mtx);
 
 	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped(local->hw.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
 
 	/*
 	 * If this is for hw restart things are still running.

net/mac80211/vht.c

@@ -129,9 +129,12 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	if (!vht_cap_ie || !sband->vht_cap.vht_supported)
 		return;
 
-	/* A VHT STA must support 40 MHz */
-	if (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
-		return;
+	/*
+	 * A VHT STA must support 40 MHz, but if we verify that here
+	 * then we break a few things - some APs (e.g. Netgear R6300v2
+	 * and others based on the BCM4360 chipset) will unset this
+	 * capability bit when operating in 20 MHz.
+	 */
 
 	vht_cap->vht_supported = true;
 

net/netfilter/nf_conntrack_netlink.c

@@ -1336,6 +1336,9 @@ ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 #ifdef CONFIG_NF_NAT_NEEDED
 	int ret;
 
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
+
 	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
 					cda[CTA_NAT_DST]);
 	if (ret < 0)

net/netfilter/nf_tables_core.c

@@ -66,20 +66,6 @@ struct nft_jumpstack {
 	int			rulenum;
 };
 
-static inline void
-nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
-		struct nft_jumpstack *jumpstack, unsigned int stackptr)
-{
-	struct nft_stats __percpu *stats;
-	const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this;
-
-	rcu_read_lock_bh();
-	stats = rcu_dereference(nft_base_chain(chain)->stats);
-	__this_cpu_inc(stats->pkts);
-	__this_cpu_add(stats->bytes, pkt->skb->len);
-	rcu_read_unlock_bh();
-}
-
 enum nft_trace {
 	NFT_TRACE_RULE,
 	NFT_TRACE_RETURN,
@@ -117,13 +103,14 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt,
 unsigned int
 nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
-	const struct nft_chain *chain = ops->priv;
+	const struct nft_chain *chain = ops->priv, *basechain = chain;
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
-	int rulenum = 0;
+	struct nft_stats __percpu *stats;
+	int rulenum;
 	/*
 	 * Cache cursor to avoid problems in case that the cursor is updated
 	 * while traversing the ruleset.
@@ -131,6 +118,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
 
 do_chain:
+	rulenum = 0;
 	rule = list_entry(&chain->rules, struct nft_rule, list);
 next_rule:
 	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
@@ -156,8 +144,10 @@ next_rule:
 		switch (data[NFT_REG_VERDICT].verdict) {
 		case NFT_BREAK:
 			data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
-			/* fall through */
+			continue;
 		case NFT_CONTINUE:
+			if (unlikely(pkt->skb->nf_trace))
+				nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 			continue;
 		}
 		break;
@@ -183,37 +173,44 @@ next_rule:
 		jumpstack[stackptr].rule  = rule;
 		jumpstack[stackptr].rulenum = rulenum;
 		stackptr++;
-		/* fall through */
+		chain = data[NFT_REG_VERDICT].chain;
+		goto do_chain;
 	case NFT_GOTO:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
 		chain = data[NFT_REG_VERDICT].chain;
 		goto do_chain;
 	case NFT_RETURN:
 		if (unlikely(pkt->skb->nf_trace))
 			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
-
-		/* fall through */
+		break;
 	case NFT_CONTINUE:
+		if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN)))
+			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
 	}
 
 	if (stackptr > 0) {
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
-
 		stackptr--;
 		chain = jumpstack[stackptr].chain;
 		rule  = jumpstack[stackptr].rule;
 		rulenum = jumpstack[stackptr].rulenum;
 		goto next_rule;
 	}
-	nft_chain_stats(chain, pkt, jumpstack, stackptr);
 
 	if (unlikely(pkt->skb->nf_trace))
-		nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY);
+		nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
 
-	return nft_base_chain(chain)->policy;
+	rcu_read_lock_bh();
+	stats = rcu_dereference(nft_base_chain(basechain)->stats);
+	__this_cpu_inc(stats->pkts);
+	__this_cpu_add(stats->bytes, pkt->skb->len);
+	rcu_read_unlock_bh();
+
+	return nft_base_chain(basechain)->policy;
 }
 EXPORT_SYMBOL_GPL(nft_do_chain);
 

net/netfilter/nfnetlink.c

@@ -256,15 +256,15 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			kfree_skb(nskb);
-			return netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			return kfree_skb(nskb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		kfree_skb(nskb);
-		return netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		return kfree_skb(skb);
 	}
 
 	while (skb->len >= nlmsg_total_size(0)) {

net/rxrpc/ar-key.c

@@ -99,7 +99,7 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr,
 	_debug("tktlen: %x", tktlen);
 	if (tktlen > AFSTOKEN_RK_TIX_MAX)
 		return -EKEYREJECTED;
-	if (8 * 4 + tktlen != toklen)
+	if (toklen < 8 * 4 + tktlen)
 		return -EKEYREJECTED;
 
 	plen = sizeof(*token) + sizeof(*token->kad) + tktlen;

net/sched/cls_tcindex.c

@@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
 };
 
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+	memset(r, 0, sizeof(*r));
+	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
@@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		return err;
 
 	memcpy(&cp, p, sizeof(cp));
-	memset(&new_filter_result, 0, sizeof(new_filter_result));
-	tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+	tcindex_filter_result_init(&new_filter_result);
 
+	tcindex_filter_result_init(&cr);
 	if (old_r)
-		memcpy(&cr, r, sizeof(cr));
-	else {
-		memset(&cr, 0, sizeof(cr));
-		tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	}
+		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp.perfect && !cp.h) {
 		if (valid_perfect_hash(&cp)) {
+			int i;
+
 			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
 			if (!cp.perfect)
 				goto errout;
+			for (i = 0; i < cp.hash; i++)
+				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
 			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	tcf_exts_change(tp, &cr.exts, &e);
+	if (old_r)
+		tcf_exts_change(tp, &r->exts, &e);
+	else
+		tcf_exts_change(tp, &cr.exts, &e);
 
 	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
-		memset(old_r, 0, sizeof(*old_r));
+		tcindex_filter_result_init(old_r);
 
 	memcpy(p, &cp, sizeof(cp));
-	memcpy(r, &cr, sizeof(cr));
+	r->res = cr.res;
 
 	if (r == &new_filter_result) {
 		struct tcindex_filter **fp;

net/wireless/scan.c

@@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
+	ASSERT_RTNL();
+
 	trace_cfg80211_sched_scan_stopped(wiphy);
 
-	rtnl_lock();
 	__cfg80211_stop_sched_scan(rdev, true);
+}
+EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
+
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+{
+	rtnl_lock();
+	cfg80211_sched_scan_stopped_rtnl(wiphy);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped);

net/wireless/sme.c

@@ -234,7 +234,6 @@ void cfg80211_conn_work(struct work_struct *work)
 					NULL, 0, NULL, 0,
 					WLAN_STATUS_UNSPECIFIED_FAILURE,
 					false, NULL);
-			cfg80211_sme_free(wdev);
 		}
 		wdev_unlock(wdev);
 	}
@@ -648,6 +647,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wdev->wiphy, bss);
 		}
+		cfg80211_sme_free(wdev);
 		return;
 	}