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

Pull networking updates from David Miller:

 1) BPF debugger and asm tool by Daniel Borkmann.

 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann.

 3) Correct reciprocal_divide and update users, from Hannes Frederic
    Sowa and Daniel Borkmann.

 4) Currently we only have a "set" operation for the hw timestamp socket
    ioctl, add a "get" operation to match.  From Ben Hutchings.

 5) Add better trace events for debugging driver datapath problems, also
    from Ben Hutchings.

 6) Implement auto corking in TCP, from Eric Dumazet.  Basically, if we
    have a small send and a previous packet is already in the qdisc or
    device queue, defer until TX completion or we get more data.

 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko.

 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel
    Borkmann.

 9) Share IP header compression code between Bluetooth and IEEE802154
    layers, from Jukka Rissanen.

10) Fix ipv6 router reachability probing, from Jiri Benc.

11) Allow packets to be captured on macvtap devices, from Vlad Yasevich.

12) Support tunneling in GRO layer, from Jerry Chu.

13) Allow bonding to be configured fully using netlink, from Scott
    Feldman.

14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can
    already get the TCI.  From Atzm Watanabe.

15) New "Heavy Hitter" qdisc, from Terry Lam.

16) Significantly improve the IPSEC support in pktgen, from Fan Du.

17) Allow ipv4 tunnels to cache routes, just like sockets.  From Tom
    Herbert.

18) Add Proportional Integral Enhanced packet scheduler, from Vijay
    Subramanian.

19) Allow openvswitch to mmap'd netlink, from Thomas Graf.

20) Key TCP metrics blobs also by source address, not just destination
    address.  From Christoph Paasch.

21) Support 10G in generic phylib.  From Andy Fleming.

22) Try to short-circuit GRO flow compares using device provided RX
    hash, if provided.  From Tom Herbert.

The wireless and netfilter folks have been busy little bees too.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits)
  net/cxgb4: Fix referencing freed adapter
  ipv6: reallocate addrconf router for ipv6 address when lo device up
  fib_frontend: fix possible NULL pointer dereference
  rtnetlink: remove IFLA_BOND_SLAVE definition
  rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info
  qlcnic: update version to 5.3.55
  qlcnic: Enhance logic to calculate msix vectors.
  qlcnic: Refactor interrupt coalescing code for all adapters.
  qlcnic: Update poll controller code path
  qlcnic: Interrupt code cleanup
  qlcnic: Enhance Tx timeout debugging.
  qlcnic: Use bool for rx_mac_learn.
  bonding: fix u64 division
  rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC
  sfc: Use the correct maximum TX DMA ring size for SFC9100
  Add Shradha Shah as the sfc driver maintainer.
  net/vxlan: Share RX skb de-marking and checksum checks with ovs
  tulip: cleanup by using ARRAY_SIZE()
  ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called
  net/cxgb4: Don't retrieve stats during recovery
  ...

1 files changed, 169 insertions, 16 deletions

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 2cd02f32f99f..f1d32280cb54 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/skbuff.h>
+#include <linux/init.h>
 #include <net/protocol.h>
 #include <net/gre.h>
 
@@ -26,7 +27,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	netdev_features_t enc_features;
-	int ghl = GRE_HEADER_SECTION;
+	int ghl;
 	struct gre_base_hdr *greh;
 	u16 mac_offset = skb->mac_header;
 	int mac_len = skb->mac_len;
@@ -49,15 +50,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 
 	greh = (struct gre_base_hdr *)skb_transport_header(skb);
 
-	if (greh->flags & GRE_KEY)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_SEQ)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_CSUM) {
-		ghl += GRE_HEADER_SECTION;
-		csum = true;
-	} else
-		csum = false;
+	ghl = skb_inner_network_header(skb) - skb_transport_header(skb);
+	if (unlikely(ghl < sizeof(*greh)))
+		goto out;
+
+	csum = !!(greh->flags & GRE_CSUM);
 
 	if (unlikely(!pskb_may_pull(skb, ghl)))
 		goto out;
@@ -116,19 +113,175 @@ out:
 	return segs;
 }
 
+/* Compute the whole skb csum in s/w and store it, then verify GRO csum
+ * starting from gro_offset.
+ */
+static __sum16 gro_skb_checksum(struct sk_buff *skb)
+{
+	__sum16 sum;
+
+	skb->csum = skb_checksum(skb, 0, skb->len, 0);
+	NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum,
+		csum_partial(skb->data, skb_gro_offset(skb), 0));
+	sum = csum_fold(NAPI_GRO_CB(skb)->csum);
+	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
+		if (unlikely(!sum))
+			netdev_rx_csum_fault(skb->dev);
+	} else
+		skb->ip_summed = CHECKSUM_COMPLETE;
+
+	return sum;
+}
+
+static struct sk_buff **gre_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	struct sk_buff **pp = NULL;
+	struct sk_buff *p;
+	const struct gre_base_hdr *greh;
+	unsigned int hlen, grehlen;
+	unsigned int off;
+	int flush = 1;
+	struct packet_offload *ptype;
+	__be16 type;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*greh);
+	greh = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out;
+	}
+
+	/* Only support version 0 and K (key), C (csum) flags. Note that
+	 * although the support for the S (seq#) flag can be added easily
+	 * for GRO, this is problematic for GSO hence can not be enabled
+	 * here because a GRO pkt may end up in the forwarding path, thus
+	 * requiring GSO support to break it up correctly.
+	 */
+	if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
+		goto out;
+
+	type = greh->protocol;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL)
+		goto out_unlock;
+
+	grehlen = GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	hlen = off + grehlen;
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out_unlock;
+	}
+	if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */
+		__sum16 csum = 0;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			csum = csum_fold(NAPI_GRO_CB(skb)->csum);
+		/* Don't trust csum error calculated/reported by h/w */
+		if (skb->ip_summed == CHECKSUM_NONE || csum != 0)
+			csum = gro_skb_checksum(skb);
+
+		/* GRE CSUM is the 1's complement of the 1's complement sum
+		 * of the GRE hdr plus payload so it should add up to 0xffff
+		 * (and 0 after csum_fold()) just like the IPv4 hdr csum.
+		 */
+		if (csum)
+			goto out_unlock;
+	}
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		const struct gre_base_hdr *greh2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		/* The following checks are needed to ensure only pkts
+		 * from the same tunnel are considered for aggregation.
+		 * The criteria for "the same tunnel" includes:
+		 * 1) same version (we only support version 0 here)
+		 * 2) same protocol (we only support ETH_P_IP for now)
+		 * 3) same set of flags
+		 * 4) same key if the key field is present.
+		 */
+		greh2 = (struct gre_base_hdr *)(p->data + off);
+
+		if (greh2->flags != greh->flags ||
+		    greh2->protocol != greh->protocol) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+		if (greh->flags & GRE_KEY) {
+			/* compare keys */
+			if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
+				NAPI_GRO_CB(p)->same_flow = 0;
+				continue;
+			}
+		}
+	}
+
+	skb_gro_pull(skb, grehlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, greh, grehlen);
+
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int gre_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
+	struct packet_offload *ptype;
+	unsigned int grehlen = sizeof(*greh);
+	int err = -ENOENT;
+	__be16 type;
+
+	type = greh->protocol;
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
+
+	rcu_read_unlock();
+	return err;
+}
+
 static const struct net_offload gre_offload = {
 	.callbacks = {
 		.gso_send_check = gre_gso_send_check,
 		.gso_segment = gre_gso_segment,
+		.gro_receive = gre_gro_receive,
+		.gro_complete = gre_gro_complete,
 	},
 };
 
-int __init gre_offload_init(void)
+static int __init gre_offload_init(void)
 {
 	return inet_add_offload(&gre_offload, IPPROTO_GRE);
 }
-
-void __exit gre_offload_exit(void)
-{
-	inet_del_offload(&gre_offload, IPPROTO_GRE);
-}
+device_initcall(gre_offload_init);