Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "This is a re-do of the net-next pull request for the current merge
  window.  The only difference from the one I made the other day is that
  this has Eliezer's interface renames and the timeout handling changes
  made based upon your feedback, as well as a few bug fixes that have
  trickeled in.

  Highlights:

   1) Low latency device polling, eliminating the cost of interrupt
      handling and context switches.  Allows direct polling of a network
      device from socket operations, such as recvmsg() and poll().

      Currently ixgbe, mlx4, and bnx2x support this feature.

      Full high level description, performance numbers, and design in
      commit 0a4db187a999 ("Merge branch 'll_poll'")

      From Eliezer Tamir.

   2) With the routing cache removed, ip_check_mc_rcu() gets exercised
      more than ever before in the case where we have lots of multicast
      addresses.  Use a hash table instead of a simple linked list, from
      Eric Dumazet.

   3) Add driver for Atheros CQA98xx 802.11ac wireless devices, from
      Bartosz Markowski, Janusz Dziedzic, Kalle Valo, Marek Kwaczynski,
      Marek Puzyniak, Michal Kazior, and Sujith Manoharan.

   4) Support reporting the TUN device persist flag to userspace, from
      Pavel Emelyanov.

   5) Allow controlling network device VF link state using netlink, from
      Rony Efraim.

   6) Support GRE tunneling in openvswitch, from Pravin B Shelar.

   7) Adjust SOCK_MIN_RCVBUF and SOCK_MIN_SNDBUF for modern times, from
      Daniel Borkmann and Eric Dumazet.

   8) Allow controlling of TCP quickack behavior on a per-route basis,
      from Cong Wang.

   9) Several bug fixes and improvements to vxlan from Stephen
      Hemminger, Pravin B Shelar, and Mike Rapoport.  In particular,
      support receiving on multiple UDP ports.

  10) Major cleanups, particular in the area of debugging and cookie
      lifetime handline, to the SCTP protocol code.  From Daniel
      Borkmann.

  11) Allow packets to cross network namespaces when traversing tunnel
      devices.  From Nicolas Dichtel.

  12) Allow monitoring netlink traffic via AF_PACKET sockets, in a
      manner akin to how we monitor real network traffic via ptype_all.
      From Daniel Borkmann.

  13) Several bug fixes and improvements for the new alx device driver,
      from Johannes Berg.

  14) Fix scalability issues in the netem packet scheduler's time queue,
      by using an rbtree.  From Eric Dumazet.

  15) Several bug fixes in TCP loss recovery handling, from Yuchung
      Cheng.

  16) Add support for GSO segmentation of MPLS packets, from Simon
      Horman.

  17) Make network notifiers have a real data type for the opaque
      pointer that's passed into them.  Use this to properly handle
      network device flag changes in arp_netdev_event().  From Jiri
      Pirko and Timo Teräs.

  18) Convert several drivers over to module_pci_driver(), from Peter
      Huewe.

  19) tcp_fixup_rcvbuf() can loop 500 times over loopback, just use a
      O(1) calculation instead.  From Eric Dumazet.

  20) Support setting of explicit tunnel peer addresses in ipv6, just
      like ipv4.  From Nicolas Dichtel.

  21) Protect x86 BPF JIT against spraying attacks, from Eric Dumazet.

  22) Prevent a single high rate flow from overruning an individual cpu
      during RX packet processing via selective flow shedding.  From
      Willem de Bruijn.

  23) Don't use spinlocks in TCP md5 signing fast paths, from Eric
      Dumazet.

  24) Don't just drop GSO packets which are above the TBF scheduler's
      burst limit, chop them up so they are in-bounds instead.  Also
      from Eric Dumazet.

  25) VLAN offloads are missed when configured on top of a bridge, fix
      from Vlad Yasevich.

  26) Support IPV6 in ping sockets.  From Lorenzo Colitti.

  27) Receive flow steering targets should be updated at poll() time
      too, from David Majnemer.

  28) Fix several corner case regressions in PMTU/redirect handling due
      to the routing cache removal, from Timo Teräs.

  29) We have to be mindful of ipv4 mapped ipv6 sockets in
      upd_v6_push_pending_frames().  From Hannes Frederic Sowa.

  30) Fix L2TP sequence number handling bugs, from James Chapman."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1214 commits)
  drivers/net: caif: fix wrong rtnl_is_locked() usage
  drivers/net: enic: release rtnl_lock on error-path
  vhost-net: fix use-after-free in vhost_net_flush
  net: mv643xx_eth: do not use port number as platform device id
  net: sctp: confirm route during forward progress
  virtio_net: fix race in RX VQ processing
  virtio: support unlocked queue poll
  net/cadence/macb: fix bug/typo in extracting gem_irq_read_clear bit
  Documentation: Fix references to defunct linux-net@vger.kernel.org
  net/fs: change busy poll time accounting
  net: rename low latency sockets functions to busy poll
  bridge: fix some kernel warning in multicast timer
  sfc: Fix memory leak when discarding scattered packets
  sit: fix tunnel update via netlink
  dt:net:stmmac: Add dt specific phy reset callback support.
  dt:net:stmmac: Add support to dwmac version 3.610 and 3.710
  dt:net:stmmac: Allocate platform data only if its NULL.
  net:stmmac: fix memleak in the open method
  ipv6: rt6_check_neigh should successfully verify neigh if no NUD information are available
  net: ipv6: fix wrong ping_v6_sendmsg return value
  ...

1 files changed, 192 insertions, 46 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index faebb398fb4..560dafd83ad 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -129,6 +129,8 @@
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
 #include <linux/static_key.h>
+#include <linux/hashtable.h>
+#include <linux/vmalloc.h>
 
 #include "net-sysfs.h"
 
@@ -166,6 +168,12 @@ static struct list_head offload_base __read_mostly;
 DEFINE_RWLOCK(dev_base_lock);
 EXPORT_SYMBOL(dev_base_lock);
 
+/* protects napi_hash addition/deletion and napi_gen_id */
+static DEFINE_SPINLOCK(napi_hash_lock);
+
+static unsigned int napi_gen_id;
+static DEFINE_HASHTABLE(napi_hash, 8);
+
 seqcount_t devnet_rename_seq;
 
 static inline void dev_base_seq_inc(struct net *net)
@@ -1232,9 +1240,7 @@ static int __dev_open(struct net_device *dev)
 	 * If we don't do this there is a chance ndo_poll_controller
 	 * or ndo_poll may be running while we open the device
 	 */
-	ret = netpoll_rx_disable(dev);
-	if (ret)
-		return ret;
+	netpoll_rx_disable(dev);
 
 	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
 	ret = notifier_to_errno(ret);
@@ -1343,9 +1349,7 @@ static int __dev_close(struct net_device *dev)
 	LIST_HEAD(single);
 
 	/* Temporarily disable netpoll until the interface is down */
-	retval = netpoll_rx_disable(dev);
-	if (retval)
-		return retval;
+	netpoll_rx_disable(dev);
 
 	list_add(&dev->unreg_list, &single);
 	retval = __dev_close_many(&single);
@@ -1387,14 +1391,11 @@ static int dev_close_many(struct list_head *head)
  */
 int dev_close(struct net_device *dev)
 {
-	int ret = 0;
 	if (dev->flags & IFF_UP) {
 		LIST_HEAD(single);
 
 		/* Block netpoll rx while the interface is going down */
-		ret = netpoll_rx_disable(dev);
-		if (ret)
-			return ret;
+		netpoll_rx_disable(dev);
 
 		list_add(&dev->unreg_list, &single);
 		dev_close_many(&single);
@@ -1402,7 +1403,7 @@ int dev_close(struct net_device *dev)
 
 		netpoll_rx_enable(dev);
 	}
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(dev_close);
 
@@ -1432,6 +1433,14 @@ void dev_disable_lro(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_disable_lro);
 
+static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
+				   struct net_device *dev)
+{
+	struct netdev_notifier_info info;
+
+	netdev_notifier_info_init(&info, dev);
+	return nb->notifier_call(nb, val, &info);
+}
 
 static int dev_boot_phase = 1;
 
@@ -1464,7 +1473,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
 		goto unlock;
 	for_each_net(net) {
 		for_each_netdev(net, dev) {
-			err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+			err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
 			err = notifier_to_errno(err);
 			if (err)
 				goto rollback;
@@ -1472,7 +1481,7 @@ int register_netdevice_notifier(struct notifier_block *nb)
 			if (!(dev->flags & IFF_UP))
 				continue;
 
-			nb->notifier_call(nb, NETDEV_UP, dev);
+			call_netdevice_notifier(nb, NETDEV_UP, dev);
 		}
 	}
 
@@ -1488,10 +1497,11 @@ rollback:
 				goto outroll;
 
 			if (dev->flags & IFF_UP) {
-				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
-				nb->notifier_call(nb, NETDEV_DOWN, dev);
+				call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+							dev);
+				call_netdevice_notifier(nb, NETDEV_DOWN, dev);
 			}
-			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
 		}
 	}
 
@@ -1529,10 +1539,11 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
 	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);
+				call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+							dev);
+				call_netdevice_notifier(nb, NETDEV_DOWN, dev);
 			}
-			nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+			call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
 		}
 	}
 unlock:
@@ -1542,6 +1553,25 @@ unlock:
 EXPORT_SYMBOL(unregister_netdevice_notifier);
 
 /**
+ *	call_netdevice_notifiers_info - call all network notifier blocks
+ *	@val: value passed unmodified to notifier function
+ *	@dev: net_device pointer passed unmodified to notifier function
+ *	@info: notifier information data
+ *
+ *	Call all network notifier blocks.  Parameters and return value
+ *	are as for raw_notifier_call_chain().
+ */
+
+int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
+				  struct netdev_notifier_info *info)
+{
+	ASSERT_RTNL();
+	netdev_notifier_info_init(info, dev);
+	return raw_notifier_call_chain(&netdev_chain, val, info);
+}
+EXPORT_SYMBOL(call_netdevice_notifiers_info);
+
+/**
  *	call_netdevice_notifiers - call all network notifier blocks
  *      @val: value passed unmodified to notifier function
  *      @dev: net_device pointer passed unmodified to notifier function
@@ -1552,8 +1582,9 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
 
 int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 {
-	ASSERT_RTNL();
-	return raw_notifier_call_chain(&netdev_chain, val, dev);
+	struct netdev_notifier_info info;
+
+	return call_netdevice_notifiers_info(val, dev, &info);
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
@@ -1655,23 +1686,19 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 		}
 	}
 
-	skb_orphan(skb);
-
 	if (unlikely(!is_skb_forwardable(dev, skb))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	skb->skb_iif = 0;
-	skb->dev = dev;
-	skb_dst_drop(skb);
-	skb->tstamp.tv64 = 0;
-	skb->pkt_type = PACKET_HOST;
+	skb_scrub_packet(skb);
 	skb->protocol = eth_type_trans(skb, dev);
-	skb->mark = 0;
-	secpath_reset(skb);
-	nf_reset(skb);
-	nf_reset_trace(skb);
+
+	/* eth_type_trans() can set pkt_type.
+	 * clear pkt_type _after_ calling eth_type_trans()
+	 */
+	skb->pkt_type = PACKET_HOST;
+
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -1736,7 +1763,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 			skb_reset_mac_header(skb2);
 
 			if (skb_network_header(skb2) < skb2->data ||
-			    skb2->network_header > skb2->tail) {
+			    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
 				net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
 						     ntohs(skb2->protocol),
 						     dev->name);
@@ -3099,6 +3126,46 @@ static int rps_ipi_queued(struct softnet_data *sd)
 	return 0;
 }
 
+#ifdef CONFIG_NET_FLOW_LIMIT
+int netdev_flow_limit_table_len __read_mostly = (1 << 12);
+#endif
+
+static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
+{
+#ifdef CONFIG_NET_FLOW_LIMIT
+	struct sd_flow_limit *fl;
+	struct softnet_data *sd;
+	unsigned int old_flow, new_flow;
+
+	if (qlen < (netdev_max_backlog >> 1))
+		return false;
+
+	sd = &__get_cpu_var(softnet_data);
+
+	rcu_read_lock();
+	fl = rcu_dereference(sd->flow_limit);
+	if (fl) {
+		new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+		old_flow = fl->history[fl->history_head];
+		fl->history[fl->history_head] = new_flow;
+
+		fl->history_head++;
+		fl->history_head &= FLOW_LIMIT_HISTORY - 1;
+
+		if (likely(fl->buckets[old_flow]))
+			fl->buckets[old_flow]--;
+
+		if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
+			fl->count++;
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+#endif
+	return false;
+}
+
 /*
  * enqueue_to_backlog is called to queue an skb to a per CPU backlog
  * queue (may be a remote CPU queue).
@@ -3108,13 +3175,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
 {
 	struct softnet_data *sd;
 	unsigned long flags;
+	unsigned int qlen;
 
 	sd = &per_cpu(softnet_data, cpu);
 
 	local_irq_save(flags);
 
 	rps_lock(sd);
-	if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+	qlen = skb_queue_len(&sd->input_pkt_queue);
+	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (skb_queue_len(&sd->input_pkt_queue)) {
 enqueue:
 			__skb_queue_tail(&sd->input_pkt_queue, skb);
@@ -3862,7 +3931,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	NAPI_GRO_CB(skb)->frag0 = NULL;
 	NAPI_GRO_CB(skb)->frag0_len = 0;
 
-	if (skb->mac_header == skb->tail &&
+	if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
 	    pinfo->nr_frags &&
 	    !PageHighMem(skb_frag_page(frag0))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
@@ -4106,6 +4175,58 @@ void napi_complete(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_complete);
 
+/* must be called under rcu_read_lock(), as we dont take a reference */
+struct napi_struct *napi_by_id(unsigned int napi_id)
+{
+	unsigned int hash = napi_id % HASH_SIZE(napi_hash);
+	struct napi_struct *napi;
+
+	hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node)
+		if (napi->napi_id == napi_id)
+			return napi;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(napi_by_id);
+
+void napi_hash_add(struct napi_struct *napi)
+{
+	if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+
+		spin_lock(&napi_hash_lock);
+
+		/* 0 is not a valid id, we also skip an id that is taken
+		 * we expect both events to be extremely rare
+		 */
+		napi->napi_id = 0;
+		while (!napi->napi_id) {
+			napi->napi_id = ++napi_gen_id;
+			if (napi_by_id(napi->napi_id))
+				napi->napi_id = 0;
+		}
+
+		hlist_add_head_rcu(&napi->napi_hash_node,
+			&napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+
+		spin_unlock(&napi_hash_lock);
+	}
+}
+EXPORT_SYMBOL_GPL(napi_hash_add);
+
+/* Warning : caller is responsible to make sure rcu grace period
+ * is respected before freeing memory containing @napi
+ */
+void napi_hash_del(struct napi_struct *napi)
+{
+	spin_lock(&napi_hash_lock);
+
+	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
+		hlist_del_rcu(&napi->napi_hash_node);
+
+	spin_unlock(&napi_hash_lock);
+}
+EXPORT_SYMBOL_GPL(napi_hash_del);
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
@@ -4404,7 +4525,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	else
 		list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
 	dev_hold(upper_dev);
-
+	call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
 	return 0;
 }
 
@@ -4464,6 +4585,7 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 	list_del_rcu(&upper->list);
 	dev_put(upper_dev);
 	kfree_rcu(upper, rcu);
+	call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
@@ -4734,8 +4856,13 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
 	}
 
 	if (dev->flags & IFF_UP &&
-	    (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE)))
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+	    (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = changes;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
+	}
 }
 
 /**
@@ -5158,17 +5285,28 @@ static void netdev_init_one_queue(struct net_device *dev,
 #endif
 }
 
+static void netif_free_tx_queues(struct net_device *dev)
+{
+	if (is_vmalloc_addr(dev->_tx))
+		vfree(dev->_tx);
+	else
+		kfree(dev->_tx);
+}
+
 static int netif_alloc_netdev_queues(struct net_device *dev)
 {
 	unsigned int count = dev->num_tx_queues;
 	struct netdev_queue *tx;
+	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1);
-
-	tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
-	if (!tx)
-		return -ENOMEM;
+	BUG_ON(count < 1 || count > 0xffff);
 
+	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!tx) {
+		tx = vzalloc(sz);
+		if (!tx)
+			return -ENOMEM;
+	}
 	dev->_tx = tx;
 
 	netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
@@ -5269,6 +5407,10 @@ int register_netdevice(struct net_device *dev)
 	 */
 	dev->hw_enc_features |= NETIF_F_SG;
 
+	/* Make NETIF_F_SG inheritable to MPLS.
+	 */
+	dev->mpls_features |= NETIF_F_SG;
+
 	ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
 	ret = notifier_to_errno(ret);
 	if (ret)
@@ -5712,7 +5854,7 @@ free_all:
 
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
-	kfree(dev->_tx);
+	netif_free_tx_queues(dev);
 #ifdef CONFIG_RPS
 	kfree(dev->_rx);
 #endif
@@ -5737,7 +5879,7 @@ void free_netdev(struct net_device *dev)
 
 	release_net(dev_net(dev));
 
-	kfree(dev->_tx);
+	netif_free_tx_queues(dev);
 #ifdef CONFIG_RPS
 	kfree(dev->_rx);
 #endif
@@ -6048,7 +6190,7 @@ netdev_features_t netdev_increment_features(netdev_features_t all,
 }
 EXPORT_SYMBOL(netdev_increment_features);
 
-static struct hlist_head *netdev_create_hash(void)
+static struct hlist_head * __net_init netdev_create_hash(void)
 {
 	int i;
 	struct hlist_head *hash;
@@ -6304,6 +6446,10 @@ static int __init net_dev_init(void)
 		sd->backlog.weight = weight_p;
 		sd->backlog.gro_list = NULL;
 		sd->backlog.gro_count = 0;
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+		sd->flow_limit = NULL;
+#endif
 	}
 
 	dev_boot_phase = 0;