1 files changed, 112 insertions, 137 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 5d59155adf2a..d70e4a3a49f2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -208,7 +208,8 @@ static inline void dev_base_seq_inc(struct net *net)
 
 static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
 {
-	unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+	unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+
 	return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
 }
 
@@ -299,10 +300,9 @@ static const unsigned short netdev_lock_type[] =
 	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
 	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
 	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
-	 ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
-	 ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
-	 ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154,
-	 ARPHRD_VOID, ARPHRD_NONE};
+	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
+	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
+	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
 
 static const char *const netdev_lock_name[] =
 	{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
@@ -317,10 +317,9 @@ static const char *const netdev_lock_name[] =
 	 "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
 	 "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
 	 "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
-	 "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
-	 "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
-	 "_xmit_PHONET_PIPE", "_xmit_IEEE802154",
-	 "_xmit_VOID", "_xmit_NONE"};
+	 "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
+	 "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
+	 "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
 
 static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
 static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
@@ -1137,8 +1136,8 @@ void dev_load(struct net *net, const char *name)
 		no_module = request_module("netdev-%s", name);
 	if (no_module && capable(CAP_SYS_MODULE)) {
 		if (!request_module("%s", name))
-			pr_err("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated).  Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
-			       name);
+			pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated).  Use CAP_NET_ADMIN and alias netdev-%s instead.\n",
+				name);
 	}
 }
 EXPORT_SYMBOL(dev_load);
@@ -1409,14 +1408,34 @@ EXPORT_SYMBOL(register_netdevice_notifier);
  *	register_netdevice_notifier(). The notifier is unlinked into the
  *	kernel structures and may then be reused. A negative errno code
  *	is returned on a failure.
+ *
+ * 	After unregistering unregister and down device events are synthesized
+ *	for all devices on the device list to the removed notifier to remove
+ *	the need for special case cleanup code.
  */
 
 int unregister_netdevice_notifier(struct notifier_block *nb)
 {
+	struct net_device *dev;
+	struct net *net;
 	int err;
 
 	rtnl_lock();
 	err = raw_notifier_chain_unregister(&netdev_chain, nb);
+	if (err)
+		goto unlock;
+
+	for_each_net(net) {
+		for_each_netdev(net, dev) {
+			if (dev->flags & IFF_UP) {
+				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+				nb->notifier_call(nb, NETDEV_DOWN, dev);
+			}
+			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
+		}
+	}
+unlock:
 	rtnl_unlock();
 	return err;
 }
@@ -1596,10 +1615,15 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb_set_dev(skb, dev);
+	skb->skb_iif = 0;
+	skb->dev = dev;
+	skb_dst_drop(skb);
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, dev);
+	skb->mark = 0;
+	secpath_reset(skb);
+	nf_reset(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1651,10 +1675,9 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 
 			if (skb_network_header(skb2) < skb2->data ||
 			    skb2->network_header > skb2->tail) {
-				if (net_ratelimit())
-					pr_crit("protocol %04x is buggy, dev %s\n",
-						ntohs(skb2->protocol),
-						dev->name);
+				net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
+						     ntohs(skb2->protocol),
+						     dev->name);
 				skb_reset_network_header(skb2);
 			}
 
@@ -1668,7 +1691,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_unlock();
 }
 
-/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
+/**
+ * netif_setup_tc - Handle tc mappings on real_num_tx_queues change
  * @dev: Network device
  * @txq: number of queues available
  *
@@ -1770,6 +1794,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
 EXPORT_SYMBOL(netif_set_real_num_rx_queues);
 #endif
 
+/**
+ * netif_get_num_default_rss_queues - default number of RSS queues
+ *
+ * This routine should set an upper limit on the number of RSS queues
+ * used by default by multiqueue devices.
+ */
+int netif_get_num_default_rss_queues(void)
+{
+	return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+}
+EXPORT_SYMBOL(netif_get_num_default_rss_queues);
+
 static inline void __netif_reschedule(struct Qdisc *q)
 {
 	struct softnet_data *sd;
@@ -1848,36 +1884,6 @@ void netif_device_attach(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_device_attach);
 
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
-	skb_dst_drop(skb);
-	if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
-		secpath_reset(skb);
-		nf_reset(skb);
-		skb_init_secmark(skb);
-		skb->mark = 0;
-		skb->priority = 0;
-		skb->nf_trace = 0;
-		skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
-		skb->tc_index = 0;
-#endif
-	}
-	skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
 	static const netdev_features_t null_features = 0;
@@ -2096,25 +2102,6 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 	return 0;
 }
 
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
-	struct sock *sk = skb->sk;
-
-	if (sk && !skb_shinfo(skb)->tx_flags) {
-		/* skb_tx_hash() wont be able to get sk.
-		 * We copy sk_hash into skb->rxhash
-		 */
-		if (!skb->rxhash)
-			skb->rxhash = sk->sk_hash;
-		skb_orphan(skb);
-	}
-}
-
 static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
 {
 	return ((features & NETIF_F_GEN_CSUM) ||
@@ -2200,8 +2187,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 		if (!list_empty(&ptype_all))
 			dev_queue_xmit_nit(skb, dev);
 
-		skb_orphan_try(skb);
-
 		features = netif_skb_features(skb);
 
 		if (vlan_tx_tag_present(skb) &&
@@ -2311,7 +2296,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
 	if (skb->sk && skb->sk->sk_hash)
 		hash = skb->sk->sk_hash;
 	else
-		hash = (__force u16) skb->protocol ^ skb->rxhash;
+		hash = (__force u16) skb->protocol;
 	hash = jhash_1word(hash, hashrnd);
 
 	return (u16) (((u64) hash * qcount) >> 32) + qoffset;
@@ -2321,11 +2306,9 @@ EXPORT_SYMBOL(__skb_tx_hash);
 static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
 {
 	if (unlikely(queue_index >= dev->real_num_tx_queues)) {
-		if (net_ratelimit()) {
-			pr_warn("%s selects TX queue %d, but real number of TX queues is %d\n",
-				dev->name, queue_index,
-				dev->real_num_tx_queues);
-		}
+		net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
+				     dev->name, queue_index,
+				     dev->real_num_tx_queues);
 		return 0;
 	}
 	return queue_index;
@@ -2474,8 +2457,12 @@ static void skb_update_prio(struct sk_buff *skb)
 {
 	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
 
-	if ((!skb->priority) && (skb->sk) && map)
-		skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+	if (!skb->priority && skb->sk && map) {
+		unsigned int prioidx = skb->sk->sk_cgrp_prioidx;
+
+		if (prioidx < map->priomap_len)
+			skb->priority = map->priomap[prioidx];
+	}
 }
 #else
 #define skb_update_prio(skb)
@@ -2485,6 +2472,23 @@ static DEFINE_PER_CPU(int, xmit_recursion);
 #define RECURSION_LIMIT 10
 
 /**
+ *	dev_loopback_xmit - loop back @skb
+ *	@skb: buffer to transmit
+ */
+int dev_loopback_xmit(struct sk_buff *skb)
+{
+	skb_reset_mac_header(skb);
+	__skb_pull(skb, skb_network_offset(skb));
+	skb->pkt_type = PACKET_LOOPBACK;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	WARN_ON(!skb_dst(skb));
+	skb_dst_force(skb);
+	netif_rx_ni(skb);
+	return 0;
+}
+EXPORT_SYMBOL(dev_loopback_xmit);
+
+/**
  *	dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
  *
@@ -2567,17 +2571,15 @@ int dev_queue_xmit(struct sk_buff *skb)
 				}
 			}
 			HARD_TX_UNLOCK(dev, txq);
-			if (net_ratelimit())
-				pr_crit("Virtual device %s asks to queue packet!\n",
-					dev->name);
+			net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
+					     dev->name);
 		} else {
 			/* Recursion is detected! It is possible,
 			 * unfortunately
 			 */
 recursion_alert:
-			if (net_ratelimit())
-				pr_crit("Dead loop on virtual device %s, fix it urgently!\n",
-					dev->name);
+			net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+					     dev->name);
 		}
 	}
 
@@ -3058,9 +3060,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
 	struct Qdisc *q;
 
 	if (unlikely(MAX_RED_LOOP < ttl++)) {
-		if (net_ratelimit())
-			pr_warn("Redir loop detected Dropping packet (%d->%d)\n",
-				skb->skb_iif, dev->ifindex);
+		net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n",
+				     skb->skb_iif, dev->ifindex);
 		return TC_ACT_SHOT;
 	}
 
@@ -3520,10 +3521,16 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 		break;
 
 	case GRO_DROP:
-	case GRO_MERGED_FREE:
 		kfree_skb(skb);
 		break;
 
+	case GRO_MERGED_FREE:
+		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+			kmem_cache_free(skbuff_head_cache, skb);
+		else
+			__kfree_skb(skb);
+		break;
+
 	case GRO_HELD:
 	case GRO_MERGED:
 		break;
@@ -3608,7 +3615,7 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(napi_frags_finish);
 
-struct sk_buff *napi_frags_skb(struct napi_struct *napi)
+static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
 	struct sk_buff *skb = napi->skb;
 	struct ethhdr *eth;
@@ -3643,7 +3650,6 @@ struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 out:
 	return skb;
 }
-EXPORT_SYMBOL(napi_frags_skb);
 
 gro_result_t napi_gro_frags(struct napi_struct *napi)
 {
@@ -4027,54 +4033,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
 
 #ifdef CONFIG_PROC_FS
 
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
-	struct seq_net_private p;
-	unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
 #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
 #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
 
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct net_device *dev;
 	struct hlist_node *p;
 	struct hlist_head *h;
-	unsigned int count, bucket, offset;
+	unsigned int count = 0, offset = get_offset(*pos);
 
-	bucket = get_bucket(state->pos);
-	offset = get_offset(state->pos);
-	h = &net->dev_name_head[bucket];
-	count = 0;
+	h = &net->dev_name_head[get_bucket(*pos)];
 	hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
-		if (count++ == offset) {
-			state->pos = set_bucket_offset(bucket, count);
+		if (++count == offset)
 			return dev;
-		}
 	}
 
 	return NULL;
 }
 
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net_device *dev;
 	unsigned int bucket;
 
-	bucket = get_bucket(state->pos);
 	do {
-		dev = dev_from_same_bucket(seq);
+		dev = dev_from_same_bucket(seq, pos);
 		if (dev)
 			return dev;
 
-		bucket++;
-		state->pos = set_bucket_offset(bucket, 0);
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
 	} while (bucket < NETDEV_HASHENTRIES);
 
 	return NULL;
@@ -4087,33 +4080,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
-	struct dev_iter_state *state = seq->private;
-
 	rcu_read_lock();
 	if (!*pos)
 		return SEQ_START_TOKEN;
 
-	/* check for end of the hash */
-	if (state->pos == 0 && *pos > 1)
+	if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
 		return NULL;
 
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net_device *dev;
-
 	++*pos;
-
-	if (v == SEQ_START_TOKEN)
-		return dev_from_new_bucket(seq);
-
-	dev = dev_from_same_bucket(seq);
-	if (dev)
-		return dev;
-
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4212,13 +4192,7 @@ static const struct seq_operations dev_seq_ops = {
 static int dev_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &dev_seq_ops,
-			    sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
-		     const struct seq_operations *ops)
-{
-	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_seq_fops = {
@@ -4629,9 +4603,9 @@ void dev_set_rx_mode(struct net_device *dev)
  *
  *	Get the combination of flag bits exported through APIs to userspace.
  */
-unsigned dev_get_flags(const struct net_device *dev)
+unsigned int dev_get_flags(const struct net_device *dev)
 {
-	unsigned flags;
+	unsigned int flags;
 
 	flags = (dev->flags & ~(IFF_PROMISC |
 				IFF_ALLMULTI |
@@ -5702,7 +5676,7 @@ int netdev_refcnt_read(const struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_refcnt_read);
 
-/*
+/**
  * netdev_wait_allrefs - wait until all references are gone.
  *
  * This is called when unregistering network devices.
@@ -6339,7 +6313,8 @@ static struct hlist_head *netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
-	INIT_LIST_HEAD(&net->dev_base_head);
+	if (net != &init_net)
+		INIT_LIST_HEAD(&net->dev_base_head);
 
 	net->dev_name_head = netdev_create_hash();
 	if (net->dev_name_head == NULL)