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

Pull networking updates from David Miller:
 "Here is my initial pull request for the networking subsystem during
  this merge window:

   1) Support for ESN in AH (RFC 4302) from Fan Du.

   2) Add full kernel doc for ethtool command structures, from Ben
      Hutchings.

   3) Add BCM7xxx PHY driver, from Florian Fainelli.

   4) Export computed TCP rate information in netlink socket dumps, from
      Eric Dumazet.

   5) Allow IPSEC SA to be dumped partially using a filter, from Nicolas
      Dichtel.

   6) Convert many drivers to pci_enable_msix_range(), from Alexander
      Gordeev.

   7) Record SKB timestamps more efficiently, from Eric Dumazet.

   8) Switch to microsecond resolution for TCP round trip times, also
      from Eric Dumazet.

   9) Clean up and fix 6lowpan fragmentation handling by making use of
      the existing inet_frag api for it's implementation.

  10) Add TX grant mapping to xen-netback driver, from Zoltan Kiss.

  11) Auto size SKB lengths when composing netlink messages based upon
      past message sizes used, from Eric Dumazet.

  12) qdisc dumps can take a long time, add a cond_resched(), From Eric
      Dumazet.

  13) Sanitize netpoll core and drivers wrt.  SKB handling semantics.
      Get rid of never-used-in-tree netpoll RX handling.  From Eric W
      Biederman.

  14) Support inter-address-family and namespace changing in VTI tunnel
      driver(s).  From Steffen Klassert.

  15) Add Altera TSE driver, from Vince Bridgers.

  16) Optimizing csum_replace2() so that it doesn't adjust the checksum
      by checksumming the entire header, from Eric Dumazet.

  17) Expand BPF internal implementation for faster interpreting, more
      direct translations into JIT'd code, and much cleaner uses of BPF
      filtering in non-socket ocntexts.  From Daniel Borkmann and Alexei
      Starovoitov"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1976 commits)
  netpoll: Use skb_irq_freeable to make zap_completion_queue safe.
  net: Add a test to see if a skb is freeable in irq context
  qlcnic: Fix build failure due to undefined reference to `vxlan_get_rx_port'
  net: ptp: move PTP classifier in its own file
  net: sxgbe: make "core_ops" static
  net: sxgbe: fix logical vs bitwise operation
  net: sxgbe: sxgbe_mdio_register() frees the bus
  Call efx_set_channels() before efx->type->dimension_resources()
  xen-netback: disable rogue vif in kthread context
  net/mlx4: Set proper build dependancy with vxlan
  be2net: fix build dependency on VxLAN
  mac802154: make csma/cca parameters per-wpan
  mac802154: allow only one WPAN to be up at any given time
  net: filter: minor: fix kdoc in __sk_run_filter
  netlink: don't compare the nul-termination in nla_strcmp
  can: c_can: Avoid led toggling for every packet.
  can: c_can: Simplify TX interrupt cleanup
  can: c_can: Store dlc private
  can: c_can: Reduce register access
  can: c_can: Make the code readable
  ...

1 files changed, 87 insertions, 66 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 4a91591b30a6..757063420ce0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1245,7 +1245,7 @@ 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
 	 */
-	netpoll_rx_disable(dev);
+	netpoll_poll_disable(dev);
 
 	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
 	ret = notifier_to_errno(ret);
@@ -1260,7 +1260,7 @@ static int __dev_open(struct net_device *dev)
 	if (!ret && ops->ndo_open)
 		ret = ops->ndo_open(dev);
 
-	netpoll_rx_enable(dev);
+	netpoll_poll_enable(dev);
 
 	if (ret)
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1313,6 +1313,9 @@ static int __dev_close_many(struct list_head *head)
 	might_sleep();
 
 	list_for_each_entry(dev, head, close_list) {
+		/* Temporarily disable netpoll until the interface is down */
+		netpoll_poll_disable(dev);
+
 		call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
 
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1343,6 +1346,7 @@ static int __dev_close_many(struct list_head *head)
 
 		dev->flags &= ~IFF_UP;
 		net_dmaengine_put();
+		netpoll_poll_enable(dev);
 	}
 
 	return 0;
@@ -1353,14 +1357,10 @@ static int __dev_close(struct net_device *dev)
 	int retval;
 	LIST_HEAD(single);
 
-	/* Temporarily disable netpoll until the interface is down */
-	netpoll_rx_disable(dev);
-
 	list_add(&dev->close_list, &single);
 	retval = __dev_close_many(&single);
 	list_del(&single);
 
-	netpoll_rx_enable(dev);
 	return retval;
 }
 
@@ -1398,14 +1398,9 @@ int dev_close(struct net_device *dev)
 	if (dev->flags & IFF_UP) {
 		LIST_HEAD(single);
 
-		/* Block netpoll rx while the interface is going down */
-		netpoll_rx_disable(dev);
-
 		list_add(&dev->close_list, &single);
 		dev_close_many(&single);
 		list_del(&single);
-
-		netpoll_rx_enable(dev);
 	}
 	return 0;
 }
@@ -1645,8 +1640,7 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 			__net_timestamp(SKB);		\
 	}						\
 
-static inline bool is_skb_forwardable(struct net_device *dev,
-				      struct sk_buff *skb)
+bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
 {
 	unsigned int len;
 
@@ -1665,6 +1659,7 @@ static inline bool is_skb_forwardable(struct net_device *dev,
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
 /**
  * dev_forward_skb - loopback an skb to another netif
@@ -2885,6 +2880,7 @@ recursion_alert:
 	rc = -ENETDOWN;
 	rcu_read_unlock_bh();
 
+	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb(skb);
 	return rc;
 out:
@@ -2957,7 +2953,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		flow_table = rcu_dereference(rxqueue->rps_flow_table);
 		if (!flow_table)
 			goto out;
-		flow_id = skb->rxhash & flow_table->mask;
+		flow_id = skb_get_hash(skb) & flow_table->mask;
 		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
 							rxq_index, flow_id);
 		if (rc < 0)
@@ -2991,6 +2987,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_sock_flow_table *sock_flow_table;
 	int cpu = -1;
 	u16 tcpu;
+	u32 hash;
 
 	if (skb_rx_queue_recorded(skb)) {
 		u16 index = skb_get_rx_queue(skb);
@@ -3019,7 +3016,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	skb_reset_network_header(skb);
-	if (!skb_get_hash(skb))
+	hash = skb_get_hash(skb);
+	if (!hash)
 		goto done;
 
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3028,11 +3026,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		u16 next_cpu;
 		struct rps_dev_flow *rflow;
 
-		rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+		rflow = &flow_table->flows[hash & flow_table->mask];
 		tcpu = rflow->cpu;
 
-		next_cpu = sock_flow_table->ents[skb->rxhash &
-		    sock_flow_table->mask];
+		next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
 
 		/*
 		 * If the desired CPU (where last recvmsg was done) is
@@ -3061,7 +3058,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	if (map) {
-		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+		tcpu = map->cpus[((u64) hash * map->len) >> 32];
 
 		if (cpu_online(tcpu)) {
 			cpu = tcpu;
@@ -3236,10 +3233,6 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	/* if netpoll wants it, pretend we never saw it */
-	if (netpoll_rx(skb))
-		return NET_RX_DROP;
-
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	trace_netif_rx(skb);
@@ -3500,11 +3493,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
 {
 	switch (skb->protocol) {
-	case __constant_htons(ETH_P_ARP):
-	case __constant_htons(ETH_P_IP):
-	case __constant_htons(ETH_P_IPV6):
-	case __constant_htons(ETH_P_8021Q):
-	case __constant_htons(ETH_P_8021AD):
+	case htons(ETH_P_ARP):
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+	case htons(ETH_P_8021Q):
+	case htons(ETH_P_8021AD):
 		return true;
 	default:
 		return false;
@@ -3525,10 +3518,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	trace_netif_receive_skb(skb);
 
-	/* if we've gotten here through NAPI, check netpoll */
-	if (netpoll_receive_skb(skb))
-		goto out;
-
 	orig_dev = skb->dev;
 
 	skb_reset_network_header(skb);
@@ -3655,7 +3644,6 @@ drop:
 
 unlock:
 	rcu_read_unlock();
-out:
 	return ret;
 }
 
@@ -3845,10 +3833,10 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
-						      skb_gro_mac_header(skb));
+						      skb_mac_header(skb));
 		else if (!diffs)
 			diffs = memcmp(skb_mac_header(p),
-				       skb_gro_mac_header(skb),
+				       skb_mac_header(skb),
 				       maclen);
 		NAPI_GRO_CB(p)->same_flow = !diffs;
 	}
@@ -3871,6 +3859,27 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	}
 }
 
+static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
+{
+	struct skb_shared_info *pinfo = skb_shinfo(skb);
+
+	BUG_ON(skb->end - skb->tail < grow);
+
+	memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+	skb->data_len -= grow;
+	skb->tail += grow;
+
+	pinfo->frags[0].page_offset += grow;
+	skb_frag_size_sub(&pinfo->frags[0], grow);
+
+	if (unlikely(!skb_frag_size(&pinfo->frags[0]))) {
+		skb_frag_unref(skb, 0);
+		memmove(pinfo->frags, pinfo->frags + 1,
+			--pinfo->nr_frags * sizeof(pinfo->frags[0]));
+	}
+}
+
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
@@ -3879,14 +3888,14 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	struct list_head *head = &offload_base;
 	int same_flow;
 	enum gro_result ret;
+	int grow;
 
-	if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
 
 	if (skb_is_gso(skb) || skb_has_frag_list(skb))
 		goto normal;
 
-	skb_gro_reset_offset(skb);
 	gro_list_prepare(napi, skb);
 	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
 
@@ -3950,27 +3959,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = GRO_HELD;
 
 pull:
-	if (skb_headlen(skb) < skb_gro_offset(skb)) {
-		int grow = skb_gro_offset(skb) - skb_headlen(skb);
-
-		BUG_ON(skb->end - skb->tail < grow);
-
-		memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
-
-		skb->tail += grow;
-		skb->data_len -= grow;
-
-		skb_shinfo(skb)->frags[0].page_offset += grow;
-		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
-
-		if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
-			skb_frag_unref(skb, 0);
-			memmove(skb_shinfo(skb)->frags,
-				skb_shinfo(skb)->frags + 1,
-				--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
-		}
-	}
-
+	grow = skb_gro_offset(skb) - skb_headlen(skb);
+	if (grow > 0)
+		gro_pull_from_frag0(skb, grow);
 ok:
 	return ret;
 
@@ -4038,6 +4029,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	trace_napi_gro_receive_entry(skb);
 
+	skb_gro_reset_offset(skb);
+
 	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
 }
 EXPORT_SYMBOL(napi_gro_receive);
@@ -4066,12 +4059,16 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
-			       gro_result_t ret)
+static gro_result_t napi_frags_finish(struct napi_struct *napi,
+				      struct sk_buff *skb,
+				      gro_result_t ret)
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		if (netif_receive_skb_internal(skb))
+	case GRO_HELD:
+		__skb_push(skb, ETH_HLEN);
+		skb->protocol = eth_type_trans(skb, skb->dev);
+		if (ret == GRO_NORMAL && netif_receive_skb_internal(skb))
 			ret = GRO_DROP;
 		break;
 
@@ -4080,7 +4077,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 		napi_reuse_skb(napi, skb);
 		break;
 
-	case GRO_HELD:
 	case GRO_MERGED:
 		break;
 	}
@@ -4088,17 +4084,41 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 	return ret;
 }
 
+/* Upper GRO stack assumes network header starts at gro_offset=0
+ * Drivers could call both napi_gro_frags() and napi_gro_receive()
+ * We copy ethernet header into skb->data to have a common layout.
+ */
 static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
 	struct sk_buff *skb = napi->skb;
+	const struct ethhdr *eth;
+	unsigned int hlen = sizeof(*eth);
 
 	napi->skb = NULL;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
-		napi_reuse_skb(napi, skb);
-		return NULL;
+	skb_reset_mac_header(skb);
+	skb_gro_reset_offset(skb);
+
+	eth = skb_gro_header_fast(skb, 0);
+	if (unlikely(skb_gro_header_hard(skb, hlen))) {
+		eth = skb_gro_header_slow(skb, hlen, 0);
+		if (unlikely(!eth)) {
+			napi_reuse_skb(napi, skb);
+			return NULL;
+		}
+	} else {
+		gro_pull_from_frag0(skb, hlen);
+		NAPI_GRO_CB(skb)->frag0 += hlen;
+		NAPI_GRO_CB(skb)->frag0_len -= hlen;
 	}
-	skb->protocol = eth_type_trans(skb, skb->dev);
+	__skb_pull(skb, hlen);
+
+	/*
+	 * This works because the only protocols we care about don't require
+	 * special handling.
+	 * We'll fix it up properly in napi_frags_finish()
+	 */
+	skb->protocol = eth->h_proto;
 
 	return skb;
 }
@@ -6251,6 +6271,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
 	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);