1 files changed, 100 insertions, 30 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index c36a17aafcf3..1968980f513a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1448,13 +1448,10 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 	if (skb->len > (dev->mtu + dev->hard_header_len))
 		return NET_RX_DROP;
 
-	skb_dst_drop(skb);
+	skb_set_dev(skb, dev);
 	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);
@@ -1614,6 +1611,36 @@ static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
+/**
+ * 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 */
+
 /*
  * Invalidate hardware checksum when packet is to be mangled, and
  * complete checksum manually on outgoing path.
@@ -1853,6 +1880,14 @@ gso:
 
 		skb->next = nskb->next;
 		nskb->next = NULL;
+
+		/*
+		 * If device doesnt need nskb->dst, release it right now while
+		 * its hot in this cpu cache
+		 */
+		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+			skb_dst_drop(nskb);
+
 		rc = ops->ndo_start_xmit(nskb, dev);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -1974,6 +2009,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	return rc;
 }
 
+/*
+ * Returns true if either:
+ *	1. skb has frag_list and the device doesn't support FRAGLIST, or
+ *	2. skb is fragmented and the device does not support SG, or if
+ *	   at least one of fragments is in highmem and device does not
+ *	   support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+				      struct net_device *dev)
+{
+	return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+	       (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+					      illegal_highdma(dev, skb)));
+}
+
 /**
  *	dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
@@ -2010,18 +2060,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 	if (netif_needs_gso(dev, skb))
 		goto gso;
 
-	if (skb_has_frags(skb) &&
-	    !(dev->features & NETIF_F_FRAGLIST) &&
-	    __skb_linearize(skb))
-		goto out_kfree_skb;
-
-	/* Fragmented skb is linearized if device does not support SG,
-	 * or if at least one of fragments is in highmem and device
-	 * does not support DMA from it.
-	 */
-	if (skb_shinfo(skb)->nr_frags &&
-	    (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
-	    __skb_linearize(skb))
+	/* Convert a paged skb to linear, if required */
+	if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
 		goto out_kfree_skb;
 
 	/* If packet is not checksummed and device does not support
@@ -2422,6 +2462,7 @@ int netif_receive_skb(struct sk_buff *skb)
 	struct packet_type *ptype, *pt_prev;
 	struct net_device *orig_dev;
 	struct net_device *null_or_orig;
+	struct net_device *null_or_bond;
 	int ret = NET_RX_DROP;
 	__be16 type;
 
@@ -2487,12 +2528,24 @@ ncls:
 	if (!skb)
 		goto out;
 
+	/*
+	 * Make sure frames received on VLAN interfaces stacked on
+	 * bonding interfaces still make their way to any base bonding
+	 * device that may have registered for a specific ptype.  The
+	 * handler may have to adjust skb->dev and orig_dev.
+	 */
+	null_or_bond = NULL;
+	if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
+	    (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
+		null_or_bond = vlan_dev_real_dev(skb->dev);
+	}
+
 	type = skb->protocol;
 	list_for_each_entry_rcu(ptype,
 			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-		if (ptype->type == type &&
-		    (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
-		     ptype->dev == orig_dev)) {
+		if (ptype->type == type && (ptype->dev == null_or_orig ||
+		     ptype->dev == skb->dev || ptype->dev == orig_dev ||
+		     ptype->dev == null_or_bond)) {
 			if (pt_prev)
 				ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = ptype;
@@ -2561,7 +2614,7 @@ out:
 	return netif_receive_skb(skb);
 }
 
-void napi_gro_flush(struct napi_struct *napi)
+static void napi_gro_flush(struct napi_struct *napi)
 {
 	struct sk_buff *skb, *next;
 
@@ -2574,7 +2627,6 @@ void napi_gro_flush(struct napi_struct *napi)
 	napi->gro_count = 0;
 	napi->gro_list = NULL;
 }
-EXPORT_SYMBOL(napi_gro_flush);
 
 enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -2761,7 +2813,7 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
 	switch (ret) {
 	case GRO_NORMAL:
 	case GRO_HELD:
-		skb->protocol = eth_type_trans(skb, napi->dev);
+		skb->protocol = eth_type_trans(skb, skb->dev);
 
 		if (ret == GRO_HELD)
 			skb_gro_pull(skb, -ETH_HLEN);
@@ -3185,7 +3237,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
 	const struct net_device_stats *stats = dev_get_stats(dev);
 
-	seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+	seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
 		   "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
 		   dev->name, stats->rx_bytes, stats->rx_packets,
 		   stats->rx_errors,
@@ -3640,10 +3692,10 @@ void __dev_set_rx_mode(struct net_device *dev)
 		/* Unicast addresses changes may only happen under the rtnl,
 		 * therefore calling __dev_set_promiscuity here is safe.
 		 */
-		if (dev->uc.count > 0 && !dev->uc_promisc) {
+		if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
 			__dev_set_promiscuity(dev, 1);
 			dev->uc_promisc = 1;
-		} else if (dev->uc.count == 0 && dev->uc_promisc) {
+		} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
 			__dev_set_promiscuity(dev, -1);
 			dev->uc_promisc = 0;
 		}
@@ -4211,7 +4263,7 @@ static void dev_addr_discard(struct net_device *dev)
 	netif_addr_lock_bh(dev);
 
 	__dev_addr_discard(&dev->mc_list);
-	dev->mc_count = 0;
+	netdev_mc_count(dev) = 0;
 
 	netif_addr_unlock_bh(dev);
 }
@@ -4771,21 +4823,23 @@ static void net_set_todo(struct net_device *dev)
 
 static void rollback_registered_many(struct list_head *head)
 {
-	struct net_device *dev;
+	struct net_device *dev, *tmp;
 
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry_safe(dev, tmp, head, unreg_list) {
 		/* Some devices call without registering
-		 * for initialization unwind.
+		 * for initialization unwind. Remove those
+		 * devices and proceed with the remaining.
 		 */
 		if (dev->reg_state == NETREG_UNINITIALIZED) {
 			pr_debug("unregister_netdevice: device %s/%p never "
 				 "was registered\n", dev->name, dev);
 
 			WARN_ON(1);
-			return;
+			list_del(&dev->unreg_list);
+			continue;
 		}
 
 		BUG_ON(dev->reg_state != NETREG_REGISTERED);
@@ -5033,6 +5087,11 @@ int register_netdevice(struct net_device *dev)
 		rollback_registered(dev);
 		dev->reg_state = NETREG_UNREGISTERED;
 	}
+	/*
+	 *	Prevent userspace races by waiting until the network
+	 *	device is fully setup before sending notifications.
+	 */
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
 
 out:
 	return ret;
@@ -5360,6 +5419,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
 
 	netdev_init_queues(dev);
 
+	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);
@@ -5396,6 +5457,9 @@ 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);
 
@@ -5595,6 +5659,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	/* Notify protocols, that a new device appeared. */
 	call_netdevice_notifiers(NETDEV_REGISTER, dev);
 
+	/*
+	 *	Prevent userspace races by waiting until the network
+	 *	device is fully setup before sending notifications.
+	 */
+	rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+
 	synchronize_net();
 	err = 0;
 out: