1 files changed, 194 insertions, 75 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index d2c8a06b3a9..7990984ca36 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -148,6 +148,9 @@ struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = 0;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
@@ -1326,7 +1333,7 @@ static int __dev_close_many(struct list_head *head)
 		 * dev->stop() will invoke napi_disable() on all of it's
 		 * napi_struct instances on this device.
 		 */
-		smp_mb__after_clear_bit(); /* Commit netif_running(). */
+		smp_mb__after_atomic(); /* Commit netif_running(). */
 	}
 
 	dev_deactivate_many(head);
@@ -1661,6 +1668,29 @@ bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
+			atomic_long_inc(&dev->rx_dropped);
+			kfree_skb(skb);
+			return NET_RX_DROP;
+		}
+	}
+
+	if (unlikely(!is_skb_forwardable(dev, skb))) {
+		atomic_long_inc(&dev->rx_dropped);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb_scrub_packet(skb, true);
+	skb->protocol = eth_type_trans(skb, dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__dev_forward_skb);
+
 /**
  * dev_forward_skb - loopback an skb to another netif
  *
@@ -1681,24 +1711,7 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable);
  */
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
-			atomic_long_inc(&dev->rx_dropped);
-			kfree_skb(skb);
-			return NET_RX_DROP;
-		}
-	}
-
-	if (unlikely(!is_skb_forwardable(dev, skb))) {
-		atomic_long_inc(&dev->rx_dropped);
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	skb_scrub_packet(skb, true);
-	skb->protocol = eth_type_trans(skb, dev);
-
-	return netif_rx_internal(skb);
+	return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
@@ -2283,8 +2296,8 @@ EXPORT_SYMBOL(skb_checksum_help);
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
+	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
-	int vlan_depth = skb->mac_len;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
 	if (type == htons(ETH_P_TEB)) {
@@ -2297,15 +2310,30 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		struct vlan_hdr *vh;
+	/* if skb->protocol is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN)))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
 
-		if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
-			return 0;
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
 
-		vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-		type = vh->h_vlan_encapsulated_proto;
-		vlan_depth += VLAN_HLEN;
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
 	*depth = vlan_depth;
@@ -2418,7 +2446,7 @@ 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;
@@ -2492,39 +2520,63 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 	return 0;
 }
 
+/* If MPLS offload request, verify we are testing hardware MPLS features
+ * instead of standard features for the netdev.
+ */
+#ifdef CONFIG_NET_MPLS_GSO
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+		features &= skb->dev->mpls_features;
+
+	return features;
+}
+#else
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	return features;
+}
+#endif
+
 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;
+	__be16 type;
+
+	type = skb_network_protocol(skb, &tmp);
+	features = net_mpls_features(skb, features, type);
 
 	if (skb->ip_summed != CHECKSUM_NONE &&
-	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
+	    !can_checksum_protocol(features, type)) {
 		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 +2584,9 @@ 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)
@@ -3343,7 +3395,7 @@ static void net_tx_action(struct softirq_action *h)
 
 			root_lock = qdisc_lock(q);
 			if (spin_trylock(root_lock)) {
-				smp_mb__before_clear_bit();
+				smp_mb__before_atomic();
 				clear_bit(__QDISC_STATE_SCHED,
 					  &q->state);
 				qdisc_run(q);
@@ -3353,7 +3405,7 @@ static void net_tx_action(struct softirq_action *h)
 					      &q->state)) {
 					__netif_reschedule(q);
 				} else {
-					smp_mb__before_clear_bit();
+					smp_mb__before_atomic();
 					clear_bit(__QDISC_STATE_SCHED,
 						  &q->state);
 				}
@@ -3953,6 +4005,7 @@ 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;
@@ -4181,9 +4234,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
 #endif
 	napi->weight = weight_p;
 	local_irq_disable();
-	while (work < quota) {
+	while (1) {
 		struct sk_buff *skb;
-		unsigned int qlen;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
 			local_irq_enable();
@@ -4197,24 +4249,24 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		}
 
 		rps_lock(sd);
-		qlen = skb_queue_len(&sd->input_pkt_queue);
-		if (qlen)
-			skb_queue_splice_tail_init(&sd->input_pkt_queue,
-						   &sd->process_queue);
-
-		if (qlen < quota - work) {
+		if (skb_queue_empty(&sd->input_pkt_queue)) {
 			/*
 			 * Inline a custom version of __napi_complete().
 			 * only current cpu owns and manipulates this napi,
-			 * and NAPI_STATE_SCHED is the only possible flag set on backlog.
-			 * we can use a plain write instead of clear_bit(),
+			 * and NAPI_STATE_SCHED is the only possible flag set
+			 * on backlog.
+			 * We can use a plain write instead of clear_bit(),
 			 * and we dont need an smp_mb() memory barrier.
 			 */
 			list_del(&napi->poll_list);
 			napi->state = 0;
+			rps_unlock(sd);
 
-			quota = work + qlen;
+			break;
 		}
+
+		skb_queue_splice_tail_init(&sd->input_pkt_queue,
+					   &sd->process_queue);
 		rps_unlock(sd);
 	}
 	local_irq_enable();
@@ -4244,7 +4296,7 @@ void __napi_complete(struct napi_struct *n)
 	BUG_ON(n->gro_list);
 
 	list_del(&n->poll_list);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
 }
 EXPORT_SYMBOL(__napi_complete);
@@ -4543,6 +4595,32 @@ 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
  * @iter: list_head ** of the current position
@@ -4624,6 +4702,32 @@ 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
  *				       variant
@@ -5073,6 +5177,30 @@ 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 +5366,6 @@ 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 +5670,7 @@ 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)
 {
@@ -5600,10 +5727,6 @@ static void rollback_registered_many(struct list_head *head)
 		*/
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
-
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5613,6 +5736,10 @@ static void rollback_registered_many(struct list_head *head)
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
+		if (!dev->rtnl_link_ops ||
+		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
 
@@ -5838,10 +5965,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 
 static void netif_free_tx_queues(struct net_device *dev)
 {
-	if (is_vmalloc_addr(dev->_tx))
-		vfree(dev->_tx);
-	else
-		kfree(dev->_tx);
+	kvfree(dev->_tx);
 }
 
 static int netif_alloc_netdev_queues(struct net_device *dev)
@@ -6315,10 +6439,7 @@ void netdev_freemem(struct net_device *dev)
 {
 	char *addr = (char *)dev - dev->padded;
 
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 /**
@@ -6423,11 +6544,6 @@ free_all:
 
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
-	netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
-	kfree(dev->_rx);
-#endif
-
 free_dev:
 	netdev_freemem(dev);
 	return NULL;
@@ -6524,6 +6640,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -6533,6 +6652,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -6988,7 +7108,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }