13 files changed, 351 insertions, 521 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index c7e305d13b7..9444c5cb413 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -199,6 +199,11 @@ static struct list_head ptype_all __read_mostly;	/* Taps */
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
+static inline void dev_base_seq_inc(struct net *net)
+{
+	while (++net->dev_base_seq == 0);
+}
+
 static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
 {
 	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
@@ -237,6 +242,9 @@ static int list_netdevice(struct net_device *dev)
 	hlist_add_head_rcu(&dev->index_hlist,
 			   dev_index_hash(net, dev->ifindex));
 	write_unlock_bh(&dev_base_lock);
+
+	dev_base_seq_inc(net);
+
 	return 0;
 }
 
@@ -253,6 +261,8 @@ static void unlist_netdevice(struct net_device *dev)
 	hlist_del_rcu(&dev->name_hlist);
 	hlist_del_rcu(&dev->index_hlist);
 	write_unlock_bh(&dev_base_lock);
+
+	dev_base_seq_inc(dev_net(dev));
 }
 
 /*
@@ -2096,6 +2106,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
+	unsigned int skb_len;
 
 	if (likely(!skb->next)) {
 		u32 features;
@@ -2146,8 +2157,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			}
 		}
 
+		skb_len = skb->len;
 		rc = ops->ndo_start_xmit(skb, dev);
-		trace_net_dev_xmit(skb, rc);
+		trace_net_dev_xmit(skb, rc, dev, skb_len);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
@@ -2167,8 +2179,9 @@ gso:
 		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
 			skb_dst_drop(nskb);
 
+		skb_len = nskb->len;
 		rc = ops->ndo_start_xmit(nskb, dev);
-		trace_net_dev_xmit(nskb, rc);
+		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
 				goto out_kfree_gso_skb;
@@ -2529,7 +2542,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb)
 			goto done;
 
 		ip = (const struct iphdr *) (skb->data + nhoff);
-		if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+		if (ip_is_fragment(ip))
 			ip_proto = 0;
 		else
 			ip_proto = ip->protocol;
@@ -3111,7 +3124,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 
 	skb_reset_network_header(skb);
 	skb_reset_transport_header(skb);
-	skb->mac_len = skb->network_header - skb->mac_header;
+	skb_reset_mac_len(skb);
 
 	pt_prev = NULL;
 
@@ -5196,7 +5209,7 @@ static void rollback_registered(struct net_device *dev)
 	list_del(&single);
 }
 
-u32 netdev_fix_features(struct net_device *dev, u32 features)
+static u32 netdev_fix_features(struct net_device *dev, u32 features)
 {
 	/* Fix illegal checksum combinations */
 	if ((features & NETIF_F_HW_CSUM) &&
@@ -5255,7 +5268,6 @@ u32 netdev_fix_features(struct net_device *dev, u32 features)
 
 	return features;
 }
-EXPORT_SYMBOL(netdev_fix_features);
 
 int __netdev_update_features(struct net_device *dev)
 {
@@ -5475,11 +5487,9 @@ int register_netdevice(struct net_device *dev)
 		dev->features |= NETIF_F_NOCACHE_COPY;
 	}
 
-	/* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
-	 * vlan_dev_init() will do the dev->features check, so these features
-	 * are enabled only if supported by underlying device.
+	/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
 	 */
-	dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA);
+	dev->vlan_features |= NETIF_F_HIGHDMA;
 
 	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
 	ret = notifier_to_errno(ret);
@@ -5864,8 +5874,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->gso_max_size = GSO_MAX_SIZE;
 
-	INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
-	dev->ethtool_ntuple_list.count = 0;
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
 	INIT_LIST_HEAD(&dev->link_watch_list);
@@ -5929,9 +5937,6 @@ void free_netdev(struct net_device *dev)
 	/* Flush device addresses */
 	dev_addr_flush(dev);
 
-	/* Clear ethtool n-tuple list */
-	ethtool_ntuple_flush(dev);
-
 	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
 		netif_napi_del(p);
 
@@ -6175,6 +6180,11 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		oldsd->output_queue = NULL;
 		oldsd->output_queue_tailp = &oldsd->output_queue;
 	}
+	/* Append NAPI poll list from offline CPU. */
+	if (!list_empty(&oldsd->poll_list)) {
+		list_splice_init(&oldsd->poll_list, &sd->poll_list);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	}
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_enable();
@@ -6261,29 +6271,23 @@ err_name:
 /**
  *	netdev_drivername - network driver for the device
  *	@dev: network device
- *	@buffer: buffer for resulting name
- *	@len: size of buffer
  *
  *	Determine network driver for device.
  */
-char *netdev_drivername(const struct net_device *dev, char *buffer, int len)
+const char *netdev_drivername(const struct net_device *dev)
 {
 	const struct device_driver *driver;
 	const struct device *parent;
-
-	if (len <= 0 || !buffer)
-		return buffer;
-	buffer[0] = 0;
+	const char *empty = "";
 
 	parent = dev->dev.parent;
-
 	if (!parent)
-		return buffer;
+		return empty;
 
 	driver = parent->driver;
 	if (driver && driver->name)
-		strlcpy(buffer, driver->name, len);
-	return buffer;
+		return driver->name;
+	return empty;
 }
 
 static int __netdev_printk(const char *level, const struct net_device *dev,
diff --git a/net/core/dst.c b/net/core/dst.c
index 9ccca038444..14b33baf073 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -171,8 +171,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 	dst_init_metrics(dst, dst_default_metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
-	dst->neighbour = NULL;
-	dst->hh = NULL;
+	dst->_neighbour = NULL;
 #ifdef CONFIG_XFRM
 	dst->xfrm = NULL;
 #endif
@@ -190,7 +189,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
 	dst->lastuse = jiffies;
 	dst->flags = flags;
 	dst->next = NULL;
-	dst_entries_add(ops, 1);
+	if (!(flags & DST_NOCOUNT))
+		dst_entries_add(ops, 1);
 	return dst;
 }
 EXPORT_SYMBOL(dst_alloc);
@@ -225,25 +225,20 @@ struct dst_entry *dst_destroy(struct dst_entry * dst)
 {
 	struct dst_entry *child;
 	struct neighbour *neigh;
-	struct hh_cache *hh;
 
 	smp_rmb();
 
 again:
-	neigh = dst->neighbour;
-	hh = dst->hh;
+	neigh = dst->_neighbour;
 	child = dst->child;
 
-	dst->hh = NULL;
-	if (hh)
-		hh_cache_put(hh);
-
 	if (neigh) {
-		dst->neighbour = NULL;
+		dst->_neighbour = NULL;
 		neigh_release(neigh);
 	}
 
-	dst_entries_add(dst->ops, -1);
+	if (!(dst->flags & DST_NOCOUNT))
+		dst_entries_add(dst->ops, -1);
 
 	if (dst->ops->destroy)
 		dst->ops->destroy(dst);
@@ -368,8 +363,8 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 		dst->dev = dev_net(dst->dev)->loopback_dev;
 		dev_hold(dst->dev);
 		dev_put(dev);
-		if (dst->neighbour && dst->neighbour->dev == dev) {
-			dst->neighbour->dev = dst->dev;
+		if (dst->_neighbour && dst->_neighbour->dev == dev) {
+			dst->_neighbour->dev = dst->dev;
 			dev_hold(dst->dev);
 			dev_put(dev);
 		}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index fd14116ad7f..6cdba5fc2be 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -169,18 +169,6 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported)
 }
 EXPORT_SYMBOL(ethtool_op_set_flags);
 
-void ethtool_ntuple_flush(struct net_device *dev)
-{
-	struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
-
-	list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) {
-		list_del(&fsc->list);
-		kfree(fsc);
-	}
-	dev->ethtool_ntuple_list.count = 0;
-}
-EXPORT_SYMBOL(ethtool_ntuple_flush);
-
 /* Handlers for each ethtool command */
 
 #define ETHTOOL_DEV_FEATURE_WORDS	1
@@ -865,34 +853,6 @@ out:
 	return ret;
 }
 
-static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list,
-			struct ethtool_rx_ntuple_flow_spec *spec,
-			struct ethtool_rx_ntuple_flow_spec_container *fsc)
-{
-
-	/* don't add filters forever */
-	if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) {
-		/* free the container */
-		kfree(fsc);
-		return;
-	}
-
-	/* Copy the whole filter over */
-	fsc->fs.flow_type = spec->flow_type;
-	memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u));
-	memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u));
-
-	fsc->fs.vlan_tag = spec->vlan_tag;
-	fsc->fs.vlan_tag_mask = spec->vlan_tag_mask;
-	fsc->fs.data = spec->data;
-	fsc->fs.data_mask = spec->data_mask;
-	fsc->fs.action = spec->action;
-
-	/* add to the list */
-	list_add_tail_rcu(&fsc->list, &list->list);
-	list->count++;
-}
-
 /*
  * ethtool does not (or did not) set masks for flow parameters that are
  * not specified, so if both value and mask are 0 then this must be
@@ -930,8 +890,6 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev,
 {
 	struct ethtool_rx_ntuple cmd;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
-	struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL;
-	int ret;
 
 	if (!ops->set_rx_ntuple)
 		return -EOPNOTSUPP;
@@ -944,269 +902,7 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev,
 
 	rx_ntuple_fix_masks(&cmd.fs);
 
-	/*
-	 * Cache filter in dev struct for GET operation only if
-	 * the underlying driver doesn't have its own GET operation, and
-	 * only if the filter was added successfully.  First make sure we
-	 * can allocate the filter, then continue if successful.
-	 */
-	if (!ops->get_rx_ntuple) {
-		fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC);
-		if (!fsc)
-			return -ENOMEM;
-	}
-
-	ret = ops->set_rx_ntuple(dev, &cmd);
-	if (ret) {
-		kfree(fsc);
-		return ret;
-	}
-
-	if (!ops->get_rx_ntuple)
-		__rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc);
-
-	return ret;
-}
-
-static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr)
-{
-	struct ethtool_gstrings gstrings;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-	struct ethtool_rx_ntuple_flow_spec_container *fsc;
-	u8 *data;
-	char *p;
-	int ret, i, num_strings = 0;
-
-	if (!ops->get_sset_count)
-		return -EOPNOTSUPP;
-
-	if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
-		return -EFAULT;
-
-	ret = ops->get_sset_count(dev, gstrings.string_set);
-	if (ret < 0)
-		return ret;
-
-	gstrings.len = ret;
-
-	data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
-	if (!data)
-		return -ENOMEM;
-
-	if (ops->get_rx_ntuple) {
-		/* driver-specific filter grab */
-		ret = ops->get_rx_ntuple(dev, gstrings.string_set, data);
-		goto copy;
-	}
-
-	/* default ethtool filter grab */
-	i = 0;
-	p = (char *)data;
-	list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) {
-		sprintf(p, "Filter %d:\n", i);
-		p += ETH_GSTRING_LEN;
-		num_strings++;
-
-		switch (fsc->fs.flow_type) {
-		case TCP_V4_FLOW:
-			sprintf(p, "\tFlow Type: TCP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case UDP_V4_FLOW:
-			sprintf(p, "\tFlow Type: UDP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case SCTP_V4_FLOW:
-			sprintf(p, "\tFlow Type: SCTP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case AH_ESP_V4_FLOW:
-			sprintf(p, "\tFlow Type: AH ESP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case ESP_V4_FLOW:
-			sprintf(p, "\tFlow Type: ESP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case IP_USER_FLOW:
-			sprintf(p, "\tFlow Type: Raw IP\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case IPV4_FLOW:
-			sprintf(p, "\tFlow Type: IPv4\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		default:
-			sprintf(p, "\tFlow Type: Unknown\n");
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			goto unknown_filter;
-		}
-
-		/* now the rest of the filters */
-		switch (fsc->fs.flow_type) {
-		case TCP_V4_FLOW:
-		case UDP_V4_FLOW:
-		case SCTP_V4_FLOW:
-			sprintf(p, "\tSrc IP addr: 0x%x\n",
-				fsc->fs.h_u.tcp_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSrc IP mask: 0x%x\n",
-				fsc->fs.m_u.tcp_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP addr: 0x%x\n",
-				fsc->fs.h_u.tcp_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP mask: 0x%x\n",
-				fsc->fs.m_u.tcp_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSrc Port: %d, mask: 0x%x\n",
-				fsc->fs.h_u.tcp_ip4_spec.psrc,
-				fsc->fs.m_u.tcp_ip4_spec.psrc);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest Port: %d, mask: 0x%x\n",
-				fsc->fs.h_u.tcp_ip4_spec.pdst,
-				fsc->fs.m_u.tcp_ip4_spec.pdst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
-				fsc->fs.h_u.tcp_ip4_spec.tos,
-				fsc->fs.m_u.tcp_ip4_spec.tos);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case AH_ESP_V4_FLOW:
-		case ESP_V4_FLOW:
-			sprintf(p, "\tSrc IP addr: 0x%x\n",
-				fsc->fs.h_u.ah_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSrc IP mask: 0x%x\n",
-				fsc->fs.m_u.ah_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP addr: 0x%x\n",
-				fsc->fs.h_u.ah_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP mask: 0x%x\n",
-				fsc->fs.m_u.ah_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSPI: %d, mask: 0x%x\n",
-				fsc->fs.h_u.ah_ip4_spec.spi,
-				fsc->fs.m_u.ah_ip4_spec.spi);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
-				fsc->fs.h_u.ah_ip4_spec.tos,
-				fsc->fs.m_u.ah_ip4_spec.tos);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case IP_USER_FLOW:
-			sprintf(p, "\tSrc IP addr: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSrc IP mask: 0x%x\n",
-				fsc->fs.m_u.usr_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP addr: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP mask: 0x%x\n",
-				fsc->fs.m_u.usr_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		case IPV4_FLOW:
-			sprintf(p, "\tSrc IP addr: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tSrc IP mask: 0x%x\n",
-				fsc->fs.m_u.usr_ip4_spec.ip4src);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP addr: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tDest IP mask: 0x%x\n",
-				fsc->fs.m_u.usr_ip4_spec.ip4dst);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.l4_4_bytes,
-				fsc->fs.m_u.usr_ip4_spec.l4_4_bytes);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.tos,
-				fsc->fs.m_u.usr_ip4_spec.tos);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tIP Version: %d, mask: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.ip_ver,
-				fsc->fs.m_u.usr_ip4_spec.ip_ver);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			sprintf(p, "\tProtocol: %d, mask: 0x%x\n",
-				fsc->fs.h_u.usr_ip4_spec.proto,
-				fsc->fs.m_u.usr_ip4_spec.proto);
-			p += ETH_GSTRING_LEN;
-			num_strings++;
-			break;
-		}
-		sprintf(p, "\tVLAN: %d, mask: 0x%x\n",
-			fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask);
-		p += ETH_GSTRING_LEN;
-		num_strings++;
-		sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data);
-		p += ETH_GSTRING_LEN;
-		num_strings++;
-		sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask);
-		p += ETH_GSTRING_LEN;
-		num_strings++;
-		if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP)
-			sprintf(p, "\tAction: Drop\n");
-		else
-			sprintf(p, "\tAction: Direct to queue %d\n",
-				fsc->fs.action);
-		p += ETH_GSTRING_LEN;
-		num_strings++;
-unknown_filter:
-		i++;
-	}
-copy:
-	/* indicate to userspace how many strings we actually have */
-	gstrings.len = num_strings;
-	ret = -EFAULT;
-	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
-		goto out;
-	useraddr += sizeof(gstrings);
-	if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
-		goto out;
-	ret = 0;
-
-out:
-	kfree(data);
-	return ret;
+	return ops->set_rx_ntuple(dev, &cmd);
 }
 
 static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
@@ -1227,7 +923,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 		regs.len = reglen;
 
 	regbuf = vzalloc(reglen);
-	if (!regbuf)
+	if (reglen && !regbuf)
 		return -ENOMEM;
 
 	ops->get_regs(dev, &regs, regbuf);
@@ -1236,7 +932,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 	if (copy_to_user(useraddr, &regs, sizeof(regs)))
 		goto out;
 	useraddr += offsetof(struct ethtool_regs, data);
-	if (copy_to_user(useraddr, regbuf, regs.len))
+	if (regbuf && copy_to_user(useraddr, regbuf, regs.len))
 		goto out;
 	ret = 0;
 
@@ -2101,9 +1797,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXNTUPLE:
 		rc = ethtool_set_rx_ntuple(dev, useraddr);
 		break;
-	case ETHTOOL_GRXNTUPLE:
-		rc = ethtool_get_rx_ntuple(dev, useraddr);
-		break;
 	case ETHTOOL_GSSET_INFO:
 		rc = ethtool_get_sset_info(dev, useraddr);
 		break;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 008dc70b064..e7ab0c0285b 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -740,9 +740,9 @@ static struct pernet_operations fib_rules_net_ops = {
 static int __init fib_rules_init(void)
 {
 	int err;
-	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
 
 	err = register_pernet_subsys(&fib_rules_net_ops);
 	if (err < 0)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 799f06e03a2..8fab9b0bb20 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -98,7 +98,7 @@ static const struct file_operations neigh_stat_seq_fops;
 
 static DEFINE_RWLOCK(neigh_tbl_lock);
 
-static int neigh_blackhole(struct sk_buff *skb)
+static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb)
 {
 	kfree_skb(skb);
 	return -ENETDOWN;
@@ -137,7 +137,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 	write_lock_bh(&tbl->lock);
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
-	for (i = 0; i <= nht->hash_mask; i++) {
+	for (i = 0; i < (1 << nht->hash_shift); i++) {
 		struct neighbour *n;
 		struct neighbour __rcu **np;
 
@@ -210,7 +210,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	for (i = 0; i <= nht->hash_mask; i++) {
+	for (i = 0; i < (1 << nht->hash_shift); i++) {
 		struct neighbour *n;
 		struct neighbour __rcu **np = &nht->hash_buckets[i];
 
@@ -297,6 +297,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl)
 	n->updated	  = n->used = now;
 	n->nud_state	  = NUD_NONE;
 	n->output	  = neigh_blackhole;
+	seqlock_init(&n->hh.hh_lock);
 	n->parms	  = neigh_parms_clone(&tbl->parms);
 	setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n);
 
@@ -312,9 +313,9 @@ out_entries:
 	goto out;
 }
 
-static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries)
+static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
 {
-	size_t size = entries * sizeof(struct neighbour *);
+	size_t size = (1 << shift) * sizeof(struct neighbour *);
 	struct neigh_hash_table *ret;
 	struct neighbour __rcu **buckets;
 
@@ -332,8 +333,9 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries)
 		return NULL;
 	}
 	ret->hash_buckets = buckets;
-	ret->hash_mask = entries - 1;
+	ret->hash_shift = shift;
 	get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd));
+	ret->hash_rnd |= 1;
 	return ret;
 }
 
@@ -342,7 +344,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
 	struct neigh_hash_table *nht = container_of(head,
 						    struct neigh_hash_table,
 						    rcu);
-	size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *);
+	size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *);
 	struct neighbour __rcu **buckets = nht->hash_buckets;
 
 	if (size <= PAGE_SIZE)
@@ -353,21 +355,20 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
 }
 
 static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl,
-						unsigned long new_entries)
+						unsigned long new_shift)
 {
 	unsigned int i, hash;
 	struct neigh_hash_table *new_nht, *old_nht;
 
 	NEIGH_CACHE_STAT_INC(tbl, hash_grows);
 
-	BUG_ON(!is_power_of_2(new_entries));
 	old_nht = rcu_dereference_protected(tbl->nht,
 					    lockdep_is_held(&tbl->lock));
-	new_nht = neigh_hash_alloc(new_entries);
+	new_nht = neigh_hash_alloc(new_shift);
 	if (!new_nht)
 		return old_nht;
 
-	for (i = 0; i <= old_nht->hash_mask; i++) {
+	for (i = 0; i < (1 << old_nht->hash_shift); i++) {
 		struct neighbour *n, *next;
 
 		for (n = rcu_dereference_protected(old_nht->hash_buckets[i],
@@ -377,7 +378,7 @@ static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl,
 			hash = tbl->hash(n->primary_key, n->dev,
 					 new_nht->hash_rnd);
 
-			hash &= new_nht->hash_mask;
+			hash >>= (32 - new_nht->hash_shift);
 			next = rcu_dereference_protected(n->next,
 						lockdep_is_held(&tbl->lock));
 
@@ -406,7 +407,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey,
 
 	rcu_read_lock_bh();
 	nht = rcu_dereference_bh(tbl->nht);
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask;
+	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
 
 	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
 	     n != NULL;
@@ -436,7 +437,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
 
 	rcu_read_lock_bh();
 	nht = rcu_dereference_bh(tbl->nht);
-	hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask;
+	hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift);
 
 	for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]);
 	     n != NULL;
@@ -492,10 +493,10 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
 	nht = rcu_dereference_protected(tbl->nht,
 					lockdep_is_held(&tbl->lock));
 
-	if (atomic_read(&tbl->entries) > (nht->hash_mask + 1))
-		nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1);
+	if (atomic_read(&tbl->entries) > (1 << nht->hash_shift))
+		nht = neigh_hash_grow(tbl, nht->hash_shift + 1);
 
-	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask;
+	hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift);
 
 	if (n->parms->dead) {
 		rc = ERR_PTR(-EINVAL);
@@ -688,8 +689,6 @@ static void neigh_destroy_rcu(struct rcu_head *head)
  */
 void neigh_destroy(struct neighbour *neigh)
 {
-	struct hh_cache *hh;
-
 	NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);
 
 	if (!neigh->dead) {
@@ -702,16 +701,6 @@ void neigh_destroy(struct neighbour *neigh)
 	if (neigh_del_timer(neigh))
 		printk(KERN_WARNING "Impossible event.\n");
 
-	while ((hh = neigh->hh) != NULL) {
-		neigh->hh = hh->hh_next;
-		hh->hh_next = NULL;
-
-		write_seqlock_bh(&hh->hh_lock);
-		hh->hh_output = neigh_blackhole;
-		write_sequnlock_bh(&hh->hh_lock);
-		hh_cache_put(hh);
-	}
-
 	skb_queue_purge(&neigh->arp_queue);
 
 	dev_put(neigh->dev);
@@ -731,14 +720,9 @@ EXPORT_SYMBOL(neigh_destroy);
  */
 static void neigh_suspect(struct neighbour *neigh)
 {
-	struct hh_cache *hh;
-
 	NEIGH_PRINTK2("neigh %p is suspected.\n", neigh);
 
 	neigh->output = neigh->ops->output;
-
-	for (hh = neigh->hh; hh; hh = hh->hh_next)
-		hh->hh_output = neigh->ops->output;
 }
 
 /* Neighbour state is OK;
@@ -748,14 +732,9 @@ static void neigh_suspect(struct neighbour *neigh)
  */
 static void neigh_connect(struct neighbour *neigh)
 {
-	struct hh_cache *hh;
-
 	NEIGH_PRINTK2("neigh %p is connected.\n", neigh);
 
 	neigh->output = neigh->ops->connected_output;
-
-	for (hh = neigh->hh; hh; hh = hh->hh_next)
-		hh->hh_output = neigh->ops->hh_output;
 }
 
 static void neigh_periodic_work(struct work_struct *work)
@@ -784,7 +763,7 @@ static void neigh_periodic_work(struct work_struct *work)
 				neigh_rand_reach_time(p->base_reachable_time);
 	}
 
-	for (i = 0 ; i <= nht->hash_mask; i++) {
+	for (i = 0 ; i < (1 << nht->hash_shift); i++) {
 		np = &nht->hash_buckets[i];
 
 		while ((n = rcu_dereference_protected(*np,
@@ -1015,7 +994,7 @@ out_unlock_bh:
 }
 EXPORT_SYMBOL(__neigh_event_send);
 
-static void neigh_update_hhs(const struct neighbour *neigh)
+static void neigh_update_hhs(struct neighbour *neigh)
 {
 	struct hh_cache *hh;
 	void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *)
@@ -1025,7 +1004,8 @@ static void neigh_update_hhs(const struct neighbour *neigh)
 		update = neigh->dev->header_ops->cache_update;
 
 	if (update) {
-		for (hh = neigh->hh; hh; hh = hh->hh_next) {
+		hh = &neigh->hh;
+		if (hh->hh_len) {
 			write_seqlock_bh(&hh->hh_lock);
 			update(hh, neigh->dev, neigh->ha);
 			write_sequnlock_bh(&hh->hh_lock);
@@ -1173,12 +1153,13 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 
 		while (neigh->nud_state & NUD_VALID &&
 		       (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) {
-			struct neighbour *n1 = neigh;
+			struct dst_entry *dst = skb_dst(skb);
+			struct neighbour *n2, *n1 = neigh;
 			write_unlock_bh(&neigh->lock);
 			/* On shaper/eql skb->dst->neighbour != neigh :( */
-			if (skb_dst(skb) && skb_dst(skb)->neighbour)
-				n1 = skb_dst(skb)->neighbour;
-			n1->output(skb);
+			if (dst && (n2 = dst_get_neighbour(dst)) != NULL)
+				n1 = n2;
+			n1->output(n1, skb);
 			write_lock_bh(&neigh->lock);
 		}
 		skb_queue_purge(&neigh->arp_queue);
@@ -1211,67 +1192,21 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl,
 }
 EXPORT_SYMBOL(neigh_event_ns);
 
-static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst,
-				   __be16 protocol)
-{
-	struct hh_cache *hh;
-
-	smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */
-	for (hh = n->hh; hh; hh = hh->hh_next) {
-		if (hh->hh_type == protocol) {
-			atomic_inc(&hh->hh_refcnt);
-			if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL))
-				hh_cache_put(hh);
-			return true;
-		}
-	}
-	return false;
-}
-
 /* called with read_lock_bh(&n->lock); */
-static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst,
-			  __be16 protocol)
+static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst)
 {
-	struct hh_cache	*hh;
 	struct net_device *dev = dst->dev;
-
-	if (likely(neigh_hh_lookup(n, dst, protocol)))
-		return;
-
-	/* slow path */
-	hh = kzalloc(sizeof(*hh), GFP_ATOMIC);
-	if (!hh)
-		return;
-
-	seqlock_init(&hh->hh_lock);
-	hh->hh_type = protocol;
-	atomic_set(&hh->hh_refcnt, 2);
-
-	if (dev->header_ops->cache(n, hh)) {
-		kfree(hh);
-		return;
-	}
+	__be16 prot = dst->ops->protocol;
+	struct hh_cache	*hh = &n->hh;
 
 	write_lock_bh(&n->lock);
 
-	/* must check if another thread already did the insert */
-	if (neigh_hh_lookup(n, dst, protocol)) {
-		kfree(hh);
-		goto end;
-	}
-
-	if (n->nud_state & NUD_CONNECTED)
-		hh->hh_output = n->ops->hh_output;
-	else
-		hh->hh_output = n->ops->output;
-
-	hh->hh_next = n->hh;
-	smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */
-	n->hh	    = hh;
+	/* Only one thread can come in here and initialize the
+	 * hh_cache entry.
+	 */
+	if (!hh->hh_len)
+		dev->header_ops->cache(n, hh, prot);
 
-	if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL))
-		hh_cache_put(hh);
-end:
 	write_unlock_bh(&n->lock);
 }
 
@@ -1280,7 +1215,7 @@ end:
  * but resolution is not made yet.
  */
 
-int neigh_compat_output(struct sk_buff *skb)
+int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 
@@ -1297,13 +1232,12 @@ EXPORT_SYMBOL(neigh_compat_output);
 
 /* Slow and careful. */
 
-int neigh_resolve_output(struct sk_buff *skb)
+int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	struct neighbour *neigh;
 	int rc = 0;
 
-	if (!dst || !(neigh = dst->neighbour))
+	if (!dst)
 		goto discard;
 
 	__skb_pull(skb, skb_network_offset(skb));
@@ -1313,10 +1247,8 @@ int neigh_resolve_output(struct sk_buff *skb)
 		struct net_device *dev = neigh->dev;
 		unsigned int seq;
 
-		if (dev->header_ops->cache &&
-		    !dst->hh &&
-		    !(dst->flags & DST_NOCACHE))
-			neigh_hh_init(neigh, dst, dst->ops->protocol);
+		if (dev->header_ops->cache && !neigh->hh.hh_len)
+			neigh_hh_init(neigh, dst);
 
 		do {
 			seq = read_seqbegin(&neigh->ha_lock);
@@ -1325,7 +1257,7 @@ int neigh_resolve_output(struct sk_buff *skb)
 		} while (read_seqretry(&neigh->ha_lock, seq));
 
 		if (err >= 0)
-			rc = neigh->ops->queue_xmit(skb);
+			rc = dev_queue_xmit(skb);
 		else
 			goto out_kfree_skb;
 	}
@@ -1333,7 +1265,7 @@ out:
 	return rc;
 discard:
 	NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n",
-		      dst, dst ? dst->neighbour : NULL);
+		      dst, neigh);
 out_kfree_skb:
 	rc = -EINVAL;
 	kfree_skb(skb);
@@ -1343,13 +1275,11 @@ EXPORT_SYMBOL(neigh_resolve_output);
 
 /* As fast as possible without hh cache */
 
-int neigh_connected_output(struct sk_buff *skb)
+int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
 {
-	int err;
-	struct dst_entry *dst = skb_dst(skb);
-	struct neighbour *neigh = dst->neighbour;
 	struct net_device *dev = neigh->dev;
 	unsigned int seq;
+	int err;