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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 120 insertions, 51 deletions

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 59035bc3008d..507310ef4b56 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -25,30 +25,11 @@ struct udp_offload_priv {
 	struct udp_offload_priv __rcu *next;
 };
 
-static int udp4_ufo_send_check(struct sk_buff *skb)
-{
-	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
-		return -EINVAL;
-
-	if (likely(!skb->encapsulation)) {
-		const struct iphdr *iph;
-		struct udphdr *uh;
-
-		iph = ip_hdr(skb);
-		uh = udp_hdr(skb);
-
-		uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				IPPROTO_UDP, 0);
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		skb->ip_summed = CHECKSUM_PARTIAL;
-	}
-
-	return 0;
-}
-
-struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
-				       netdev_features_t features)
+static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
+	netdev_features_t features,
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features),
+	__be16 new_protocol)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
@@ -70,7 +51,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
-	skb->protocol = htons(ETH_P_TEB);
+	skb->protocol = new_protocol;
 
 	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
 	if (need_csum)
@@ -78,7 +59,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
-	segs = skb_mac_gso_segment(skb, enc_features);
+	segs = gso_inner_segment(skb, enc_features);
 	if (IS_ERR_OR_NULL(segs)) {
 		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
 				     mac_len);
@@ -123,21 +104,63 @@ out:
 	return segs;
 }
 
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+				       netdev_features_t features,
+				       bool is_ipv6)
+{
+	__be16 protocol = skb->protocol;
+	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
+					     netdev_features_t features);
+
+	rcu_read_lock();
+
+	switch (skb->inner_protocol_type) {
+	case ENCAP_TYPE_ETHER:
+		protocol = skb->inner_protocol;
+		gso_inner_segment = skb_mac_gso_segment;
+		break;
+	case ENCAP_TYPE_IPPROTO:
+		offloads = is_ipv6 ? inet6_offloads : inet_offloads;
+		ops = rcu_dereference(offloads[skb->inner_ipproto]);
+		if (!ops || !ops->callbacks.gso_segment)
+			goto out_unlock;
+		gso_inner_segment = ops->callbacks.gso_segment;
+		break;
+	default:
+		goto out_unlock;
+	}
+
+	segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment,
+					protocol);
+
+out_unlock:
+	rcu_read_unlock();
+
+	return segs;
+}
+
 static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 					 netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
-	int offset;
 	__wsum csum;
+	struct udphdr *uh;
+	struct iphdr *iph;
 
 	if (skb->encapsulation &&
 	    (skb_shinfo(skb)->gso_type &
 	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
-		segs = skb_udp_tunnel_segment(skb, features);
+		segs = skb_udp_tunnel_segment(skb, features, false);
 		goto out;
 	}
 
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+		goto out;
+
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
 		goto out;
@@ -165,10 +188,16 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	 * HW cannot do checksum of UDP packets sent as multiple
 	 * IP fragments.
 	 */
-	offset = skb_checksum_start_offset(skb);
-	csum = skb_checksum(skb, offset, skb->len - offset, 0);
-	offset += skb->csum_offset;
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+
+	uh = udp_hdr(skb);
+	iph = ip_hdr(skb);
+
+	uh->check = 0;
+	csum = skb_checksum(skb, 0, skb->len, 0);
+	uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum);
+	if (uh->check == 0)
+		uh->check = CSUM_MANGLED_0;
+
 	skb->ip_summed = CHECKSUM_NONE;
 
 	/* Fragment the skb. IP headers of the fragments are updated in
@@ -228,30 +257,24 @@ unlock:
 }
 EXPORT_SYMBOL(udp_del_offload);
 
-static struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
+				 struct udphdr *uh)
 {
 	struct udp_offload_priv *uo_priv;
 	struct sk_buff *p, **pp = NULL;
-	struct udphdr *uh, *uh2;
-	unsigned int hlen, off;
+	struct udphdr *uh2;
+	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
 	if (NAPI_GRO_CB(skb)->udp_mark ||
-	    (!skb->encapsulation && skb->ip_summed != CHECKSUM_COMPLETE))
+	    (skb->ip_summed != CHECKSUM_PARTIAL &&
+	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the udp gro layer */
 	NAPI_GRO_CB(skb)->udp_mark = 1;
 
-	off  = skb_gro_offset(skb);
-	hlen = off + sizeof(*uh);
-	uh   = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen)) {
-		uh = skb_gro_header_slow(skb, hlen, off);
-		if (unlikely(!uh))
-			goto out;
-	}
-
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
 	for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
@@ -269,7 +292,12 @@ unflush:
 			continue;
 
 		uh2 = (struct udphdr   *)(p->data + off);
-		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) {
+
+		/* Match ports and either checksums are either both zero
+		 * or nonzero.
+		 */
+		if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) ||
+		    (!uh->check ^ !uh2->check)) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
@@ -277,6 +305,7 @@ unflush:
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
+	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
 	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
 
 out_unlock:
@@ -286,7 +315,34 @@ out:
 	return pp;
 }
 
-static int udp_gro_complete(struct sk_buff *skb, int nhoff)
+static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_gro_udphdr(skb);
+
+	if (unlikely(!uh))
+		goto flush;
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if (NAPI_GRO_CB(skb)->flush)
+		goto skip;
+
+	if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check,
+						 inet_gro_compute_pseudo))
+		goto flush;
+	else if (uh->check)
+		skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
+					     inet_gro_compute_pseudo);
+skip:
+	NAPI_GRO_CB(skb)->is_ipv6 = 0;
+	return udp_gro_receive(head, skb, uh);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
+}
+
+int udp_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	struct udp_offload_priv *uo_priv;
 	__be16 newlen = htons(skb->len - nhoff);
@@ -304,19 +360,32 @@ static int udp_gro_complete(struct sk_buff *skb, int nhoff)
 			break;
 	}
 
-	if (uo_priv != NULL)
+	if (uo_priv != NULL) {
+		NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
 		err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr));
+	}
 
 	rcu_read_unlock();
 	return err;
 }
 
+static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
+
+	if (uh->check)
+		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
+					  iph->daddr, 0);
+
+	return udp_gro_complete(skb, nhoff);
+}
+
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
-		.gso_send_check = udp4_ufo_send_check,
 		.gso_segment = udp4_ufo_fragment,
-		.gro_receive  =	udp_gro_receive,
-		.gro_complete =	udp_gro_complete,
+		.gro_receive  =	udp4_gro_receive,
+		.gro_complete =	udp4_gro_complete,
 	},
 };