Merge branch 'GREoIPV6'

Tom Herbert says:

====================
ipv6: Enable GUEoIPv6 and more fixes for v6 tunneling

This patch set:
  - Fixes GRE6 to process translate flags correctly from configuration
  - Adds support for GSO and GRO for ip6ip6 and ip4ip6
  - Add support for FOU and GUE in IPv6
  - Support GRE, ip6ip6 and ip4ip6 over FOU/GUE
  - Fixes ip6_input to deal with UDP encapsulations
  - Some other minor fixes

v2:
  - Removed a check of GSO types in MPLS
  - Define GSO type SKB_GSO_IPXIP6 and SKB_GSO_IPXIP4 (based on input
    from Alexander)
  - Don't define GSO types specifically for IP6IP6 and IP4IP6, above
    fix makes that unnecessary
  - Don't bother clearing encapsulation flag in UDP tunnel segment
    (another item suggested by Alexander).

v3:
  - Address some minor comments from Alexander

v4:
  - Rebase on changes to fix IP TX tunnels
  - Fix MTU issues in ip4ip6, ip6ip6
  - Add test data for above

v5:
  - Address feedback from Shmulik Ladkani regarding extension header
    code that does not return next header but in instead relies
    on returning value via nhoff. Solution here is to fix EH
    processing to return nexthdr value.
  - Refactored IPv4 encaps so that we won't need to create
    a ip6_tunnel_core.c when adding encap support IPv6.

v6:
  - Fix build issues with regard to new GSO constants
  - FIx MTU calculation issues ip6_tunnel.c pointed out byt ALex
  - Add encap_hlen into headroom for GREv6 to work with FOU/GUE

v7:
  - Added skb_set_inner_ipproto to ip4ip6 and ip6ip6
  - Clarified max_headroom in ip6_tnl_xmit
  - Set features for IPv6 tunnels
  - Other cleanup suggested by Alexander
  - Above fixes throughput performance issues in ip4ip6 and ip6ip6,
    updated test results to reflect that

Tested: Various cases of IP tunnels with netperf TCP_STREAM and TCP_RR.

    - IPv4/GRE/GUE/IPv6 with RCO
      1 TCP_STREAM
      	6616 Mbps
      200 TCP_RR
	1244043 tps
        141/243/446 90/95/99% latencies
	86.61% CPU utilization

    - IPv6/GRE/GUE/IPv6 with RCO
      1 TCP_STREAM
	6940 Mbps
      200 TCP_RR
	1270903 tps
	138/236/440 90/95/99% latencies
	87.51% CPU utilization

     - IP6IP6
      1 TCP_STREAM
	5307 Mbps
      200 TCP_RR
	498981 tps
	388/498/631 90/95/99% latencies
	19.75% CPU utilization (1 CPU saturated)

     - IP6IP6/GUE with RCO
      1 TCP_STREAM
	5575 Mbps
      200 TCP_RR
	1233818 tps
	143/244/451 90/95/99% latencies
	87.57 CPU utilization

     - IP4IP6
      1 TCP_STREAM
	5235 Mbps
      200 TCP_RR
	763774 tps
	250/318/466 90/95/99% latencies
	35.25% CPU utilization (1 CPU saturated)

     - IP4IP6/GUE with RCO
      1 TCP_STREAM
	5337 Mbps
      200 TCP_RR
	1196385 tps
	148/251/460 90/95/99% latencies
	87.56 CPU utilization

     - GRE with keyid
      200 TCP_RR
	744173 tps
	258/332/461 90/95/99% latencies
	34.59% CPU utilization (1 CPU saturated)
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -13259,12 +13259,11 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev,
 		NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX;
 	if (!chip_is_e1x) {
 		dev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL |
-				    NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT;
+				    NETIF_F_GSO_IPXIP4;
 		dev->hw_enc_features =
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
 			NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 |
-			NETIF_F_GSO_IPIP |
-			NETIF_F_GSO_SIT |
+			NETIF_F_GSO_IPXIP4 |
 			NETIF_F_GSO_GRE | NETIF_F_GSO_UDP_TUNNEL;
 	}
 

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -6311,7 +6311,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG |
 			   NETIF_F_TSO | NETIF_F_TSO6 |
 			   NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
-			   NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT |
+			   NETIF_F_GSO_IPXIP4 |
 			   NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
 			   NETIF_F_GSO_PARTIAL | NETIF_F_RXHASH |
 			   NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO;
@@ -6321,8 +6321,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			NETIF_F_TSO | NETIF_F_TSO6 |
 			NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE |
 			NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_GRE_CSUM |
-			NETIF_F_GSO_IPIP | NETIF_F_GSO_SIT |
-			NETIF_F_GSO_PARTIAL;
+			NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_PARTIAL;
 	dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM |
 				    NETIF_F_GSO_GRE_CSUM;
 	dev->vlan_features = dev->hw_features | NETIF_F_HIGHDMA;

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -9083,8 +9083,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 				   NETIF_F_TSO6			|
 				   NETIF_F_GSO_GRE		|
 				   NETIF_F_GSO_GRE_CSUM		|
-				   NETIF_F_GSO_IPIP		|
-				   NETIF_F_GSO_SIT		|
+				   NETIF_F_GSO_IPXIP4		|
 				   NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
 				   NETIF_F_GSO_PARTIAL		|

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2284,8 +2284,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 
 	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
 					 SKB_GSO_GRE_CSUM |
-					 SKB_GSO_IPIP |
-					 SKB_GSO_SIT |
+					 SKB_GSO_IPXIP4 |
 					 SKB_GSO_UDP_TUNNEL |
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
 		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -1559,8 +1559,7 @@ static int i40e_tso(struct sk_buff *skb, u8 *hdr_len, u64 *cd_type_cmd_tso_mss)
 
 	if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE |
 					 SKB_GSO_GRE_CSUM |
-					 SKB_GSO_IPIP |
-					 SKB_GSO_SIT |
+					 SKB_GSO_IPXIP4 |
 					 SKB_GSO_UDP_TUNNEL |
 					 SKB_GSO_UDP_TUNNEL_CSUM)) {
 		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) &&

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -2230,8 +2230,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter)
 				   NETIF_F_TSO6			|
 				   NETIF_F_GSO_GRE		|
 				   NETIF_F_GSO_GRE_CSUM		|
-				   NETIF_F_GSO_IPIP		|
-				   NETIF_F_GSO_SIT		|
+				   NETIF_F_GSO_IPXIP4		|
 				   NETIF_F_GSO_UDP_TUNNEL	|
 				   NETIF_F_GSO_UDP_TUNNEL_CSUM	|
 				   NETIF_F_GSO_PARTIAL		|

drivers/net/ethernet/intel/igb/igb_main.c

@@ -2418,8 +2418,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
 				  NETIF_F_GSO_GRE_CSUM | \
-				  NETIF_F_GSO_IPIP | \
-				  NETIF_F_GSO_SIT | \
+				  NETIF_F_GSO_IPXIP4 | \
 				  NETIF_F_GSO_UDP_TUNNEL | \
 				  NETIF_F_GSO_UDP_TUNNEL_CSUM)
 

drivers/net/ethernet/intel/igbvf/netdev.c

@@ -2763,8 +2763,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #define IGBVF_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
 				    NETIF_F_GSO_GRE_CSUM | \
-				    NETIF_F_GSO_IPIP | \
-				    NETIF_F_GSO_SIT | \
+				    NETIF_F_GSO_IPXIP4 | \
 				    NETIF_F_GSO_UDP_TUNNEL | \
 				    NETIF_F_GSO_UDP_TUNNEL_CSUM)
 

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -9482,8 +9482,7 @@ skip_sriov:
 
 #define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
 				    NETIF_F_GSO_GRE_CSUM | \
-				    NETIF_F_GSO_IPIP | \
-				    NETIF_F_GSO_SIT | \
+				    NETIF_F_GSO_IPXIP4 | \
 				    NETIF_F_GSO_UDP_TUNNEL | \
 				    NETIF_F_GSO_UDP_TUNNEL_CSUM)
 

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -4062,8 +4062,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 #define IXGBEVF_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \
 				      NETIF_F_GSO_GRE_CSUM | \
-				      NETIF_F_GSO_IPIP | \
-				      NETIF_F_GSO_SIT | \
+				      NETIF_F_GSO_IPXIP4 | \
 				      NETIF_F_GSO_UDP_TUNNEL | \
 				      NETIF_F_GSO_UDP_TUNNEL_CSUM)
 

include/linux/netdev_features.h

@@ -44,8 +44,8 @@ enum {
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
 	NETIF_F_GSO_GRE_CSUM_BIT,	/* ... GRE with csum with TSO */
-	NETIF_F_GSO_IPIP_BIT,		/* ... IPIP tunnel with TSO */
-	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
+	NETIF_F_GSO_IPXIP4_BIT,		/* ... IP4 or IP6 over IP4 with TSO */
+	NETIF_F_GSO_IPXIP6_BIT,		/* ... IP4 or IP6 over IP6 with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
 	NETIF_F_GSO_PARTIAL_BIT,	/* ... Only segment inner-most L4
@@ -121,8 +121,8 @@ enum {
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
 #define NETIF_F_GSO_GRE_CSUM	__NETIF_F(GSO_GRE_CSUM)
-#define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
-#define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
+#define NETIF_F_GSO_IPXIP4	__NETIF_F(GSO_IPXIP4)
+#define NETIF_F_GSO_IPXIP6	__NETIF_F(GSO_IPXIP6)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_TSO_MANGLEID	__NETIF_F(TSO_MANGLEID)
@@ -200,8 +200,8 @@ enum {
 
 #define NETIF_F_GSO_ENCAP_ALL	(NETIF_F_GSO_GRE |			\
 				 NETIF_F_GSO_GRE_CSUM |			\
-				 NETIF_F_GSO_IPIP |			\
-				 NETIF_F_GSO_SIT |			\
+				 NETIF_F_GSO_IPXIP4 |			\
+				 NETIF_F_GSO_IPXIP6 |			\
 				 NETIF_F_GSO_UDP_TUNNEL |		\
 				 NETIF_F_GSO_UDP_TUNNEL_CSUM)
 

include/linux/netdevice.h

@@ -4006,8 +4006,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_IPIP    != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_IPXIP4  != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_IPXIP6  != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));

include/linux/skbuff.h

@@ -471,9 +471,9 @@ enum {
 
 	SKB_GSO_GRE_CSUM = 1 << 8,
 
-	SKB_GSO_IPIP = 1 << 9,
+	SKB_GSO_IPXIP4 = 1 << 9,
 
-	SKB_GSO_SIT = 1 << 10,
+	SKB_GSO_IPXIP6 = 1 << 10,
 
 	SKB_GSO_UDP_TUNNEL = 1 << 11,
 

include/net/fou.h

@@ -9,11 +9,11 @@
 #include <net/udp.h>
 
 size_t fou_encap_hlen(struct ip_tunnel_encap *e);
-static size_t gue_encap_hlen(struct ip_tunnel_encap *e);
+size_t gue_encap_hlen(struct ip_tunnel_encap *e);
 
-int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
-		     u8 *protocol, struct flowi4 *fl4);
-int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
-		     u8 *protocol, struct flowi4 *fl4);
+int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		       u8 *protocol, __be16 *sport, int type);
+int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		       u8 *protocol, __be16 *sport, int type);
 
 #endif

include/net/inet_common.h

@@ -39,6 +39,11 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
 
+struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int inet_gro_complete(struct sk_buff *skb, int nhoff);
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features);
+
 static inline void inet_ctl_sock_destroy(struct sock *sk)
 {
 	if (sk)

include/net/ip6_tunnel.h

@@ -52,10 +52,68 @@ struct ip6_tnl {
 	__u32 o_seqno;	/* The last output seqno */
 	int hlen;       /* tun_hlen + encap_hlen */
 	int tun_hlen;	/* Precalculated header length */
+	int encap_hlen; /* Encap header length (FOU,GUE) */
+	struct ip_tunnel_encap encap;
 	int mlink;
+};
 
+struct ip6_tnl_encap_ops {
+	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    u8 *protocol, struct flowi6 *fl6);
 };
 
+extern const struct ip6_tnl_encap_ops __rcu *
+		ip6tun_encaps[MAX_IPTUN_ENCAP_OPS];
+
+int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num);
+int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num);
+int ip6_tnl_encap_setup(struct ip6_tnl *t,
+			struct ip_tunnel_encap *ipencap);
+
+static inline int ip6_encap_hlen(struct ip_tunnel_encap *e)
+{
+	const struct ip6_tnl_encap_ops *ops;
+	int hlen = -EINVAL;
+
+	if (e->type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(ip6tun_encaps[e->type]);
+	if (likely(ops && ops->encap_hlen))
+		hlen = ops->encap_hlen(e);
+	rcu_read_unlock();
+
+	return hlen;
+}
+
+static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
+				u8 *protocol, struct flowi6 *fl6)
+{
+	const struct ip6_tnl_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (t->encap.type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
+	if (likely(ops && ops->build_header))
+		ret = ops->build_header(skb, &t->encap, protocol, fl6);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /* Tunnel encapsulation limit destination sub-option */
 
 struct ipv6_tlv_tnl_enc_lim {

include/net/ip_tunnels.h

@@ -171,22 +171,6 @@ struct ip_tunnel_net {
 	struct ip_tunnel __rcu *collect_md_tun;
 };
 
-struct ip_tunnel_encap_ops {
-	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
-	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
-			    u8 *protocol, struct flowi4 *fl4);
-};
-
-#define MAX_IPTUN_ENCAP_OPS 8
-
-extern const struct ip_tunnel_encap_ops __rcu *
-		iptun_encaps[MAX_IPTUN_ENCAP_OPS];
-
-int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
-			    unsigned int num);
-int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
-			    unsigned int num);
-
 static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 				      __be32 saddr, __be32 daddr,
 				      u8 tos, u8 ttl, __be32 label,
@@ -251,8 +235,6 @@ void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, const u8 protocol);
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
-int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
-		    u8 *protocol, struct flowi4 *fl4);
 int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
@@ -271,9 +253,67 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 		      struct ip_tunnel_parm *p);
 void ip_tunnel_setup(struct net_device *dev, int net_id);
+
+struct ip_tunnel_encap_ops {
+	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
+	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			    u8 *protocol, struct flowi4 *fl4);
+};
+
+#define MAX_IPTUN_ENCAP_OPS 8
+
+extern const struct ip_tunnel_encap_ops __rcu *
+		iptun_encaps[MAX_IPTUN_ENCAP_OPS];
+
+int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
+			    unsigned int num);
+int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
+			    unsigned int num);
+
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
+static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
+{
+	const struct ip_tunnel_encap_ops *ops;
+	int hlen = -EINVAL;
+
+	if (e->type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (e->type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[e->type]);
+	if (likely(ops && ops->encap_hlen))
+		hlen = ops->encap_hlen(e);
+	rcu_read_unlock();
+
+	return hlen;
+}
+
+static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
+				  u8 *protocol, struct flowi4 *fl4)
+{
+	const struct ip_tunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (t->encap.type == TUNNEL_ENCAP_NONE)
+		return 0;
+
+	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
+		return -EINVAL;
+
+	rcu_read_lock();
+	ops = rcu_dereference(iptun_encaps[t->encap.type]);
+	if (likely(ops && ops->build_header))
+		ret = ops->build_header(skb, &t->encap, protocol, fl4);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /* Extract dsfield from inner protocol */
 static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 				       const struct sk_buff *skb)

net/core/ethtool.c

@@ -84,8 +84,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
 	[NETIF_F_GSO_GRE_CSUM_BIT] =	 "tx-gre-csum-segmentation",
-	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
-	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
+	[NETIF_F_GSO_IPXIP4_BIT] =	 "tx-ipxip4-segmentation",
+	[NETIF_F_GSO_IPXIP6_BIT] =	 "tx-ipxip6-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",

net/ipv4/af_inet.c

@@ -1192,8 +1192,8 @@ int inet_sk_rebuild_header(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_sk_rebuild_header);
 
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
-					netdev_features_t features)
+struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+				 netdev_features_t features)
 {
 	bool udpfrag = false, fixedid = false, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
@@ -1205,24 +1205,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	int ihl;
 	int id;
 
-	if (unlikely(skb_shinfo(skb)->gso_type &
-		     ~(SKB_GSO_TCPV4 |
-		       SKB_GSO_UDP |
-		       SKB_GSO_DODGY |
-		       SKB_GSO_TCP_ECN |
-		       SKB_GSO_GRE |
-		       SKB_GSO_GRE_CSUM |
-		       SKB_GSO_IPIP |
-		       SKB_GSO_SIT |
-		       SKB_GSO_TCPV6 |
-		       SKB_GSO_UDP_TUNNEL |
-		       SKB_GSO_UDP_TUNNEL_CSUM |
-		       SKB_GSO_TCP_FIXEDID |
-		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_PARTIAL |
-		       0)))
-		goto out;
-
 	skb_reset_network_header(skb);
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
@@ -1298,9 +1280,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 out:
 	return segs;
 }
+EXPORT_SYMBOL(inet_gso_segment);
 
-static struct sk_buff **inet_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 {
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
@@ -1416,6 +1398,7 @@ out:
 
 	return pp;
 }
+EXPORT_SYMBOL(inet_gro_receive);
 
 static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
@@ -1467,7 +1450,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	return -EINVAL;
 }
 
-static int inet_gro_complete(struct sk_buff *skb, int nhoff)
+int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	__be16 newlen = htons(skb->len - nhoff);
 	struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
@@ -1497,11 +1480,12 @@ out_unlock:
 
 	return err;
 }
+EXPORT_SYMBOL(inet_gro_complete);
 
 static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	skb->encapsulation = 1;
-	skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
 	return inet_gro_complete(skb, nhoff);
 }
 

net/ipv4/fou.c

@@ -21,6 +21,7 @@ struct fou {
 	u8 protocol;
 	u8 flags;
 	__be16 port;
+	u8 family;
 	u16 type;
 	struct list_head list;
 	struct rcu_head rcu;
@@ -47,14 +48,17 @@ static inline struct fou *fou_from_sock(struct sock *sk)
 	return sk->sk_user_data;
 }
 
-static int fou_recv_pull(struct sk_buff *skb, size_t len)
+static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
 {
-	struct iphdr *iph = ip_hdr(skb);
-
 	/* Remove 'len' bytes from the packet (UDP header and
 	 * FOU header if present).
 	 */
-	iph->tot_len = htons(ntohs(iph->tot_len) - len);
+	if (fou->family == AF_INET)
+		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+	else
+		ipv6_hdr(skb)->payload_len =
+		    htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
+
 	__skb_pull(skb, len);
 	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 	skb_reset_transport_header(skb);
@@ -68,7 +72,7 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!fou)
 		return 1;
 
-	if (fou_recv_pull(skb, sizeof(struct udphdr)))
+	if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
 		goto drop;
 
 	return -fou->protocol;
@@ -141,7 +145,11 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 
 	hdrlen = sizeof(struct guehdr) + optlen;
 
-	ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+	if (fou->family == AF_INET)
+		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
+	else
+		ipv6_hdr(skb)->payload_len =
+		    htons(ntohs(ipv6_hdr(skb)->payload_len) - len);
 
 	/* Pull csum through the guehdr now . This can be used if
 	 * there is a remote checksum offload.
@@ -426,7 +434,8 @@ static int fou_add_to_port_list(struct net *net, struct fou *fou)
 
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fout, &fn->fou_list, list) {
-		if (fou->port == fout->port) {
+		if (fou->port == fout->port &&
+		    fou->family == fout->family) {
 			mutex_unlock(&fn->fou_lock);
 			return -EALREADY;
 		}
@@ -448,31 +457,13 @@ static void fou_release(struct fou *fou)
 	kfree_rcu(fou, rcu);
 }
 
-static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-{
-	udp_sk(sk)->encap_rcv = fou_udp_recv;
-	udp_sk(sk)->gro_receive = fou_gro_receive;
-	udp_sk(sk)->gro_complete = fou_gro_complete;
-	fou_from_sock(sk)->protocol = cfg->protocol;
-
-	return 0;
-}
-
-static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
-{
-	udp_sk(sk)->encap_rcv = gue_udp_recv;
-	udp_sk(sk)->gro_receive = gue_gro_receive;
-	udp_sk(sk)->gro_complete = gue_gro_complete;
-
-	return 0;
-}
-
 static int fou_create(struct net *net, struct fou_cfg *cfg,
 		      struct socket **sockp)
 {
 	struct socket *sock = NULL;
 	struct fou *fou = NULL;
 	struct sock *sk;
+	struct udp_tunnel_sock_cfg tunnel_cfg;
 	int err;
 
 	/* Open UDP socket */
@@ -489,35 +480,36 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk = sock->sk;
 
-	fou->flags = cfg->flags;
 	fou->port = cfg->udp_config.local_udp_port;
+	fou->family = cfg->udp_config.family;
+	fou->flags = cfg->flags;
+	fou->type = cfg->type;
+	fou->sock = sock;
+
+	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
+	tunnel_cfg.encap_type = 1;
+	tunnel_cfg.sk_user_data = fou;
+	tunnel_cfg.encap_destroy = NULL;
 
 	/* Initial for fou type */
 	switch (cfg->type) {
 	case FOU_ENCAP_DIRECT:
-		err = fou_encap_init(sk, fou, cfg);
-		if (err)
-			goto error;
+		tunnel_cfg.encap_rcv = fou_udp_recv;
+		tunnel_cfg.gro_receive = fou_gro_receive;
+		tunnel_cfg.gro_complete = fou_gro_complete;
+		fou->protocol = cfg->protocol;
 		break;
 	case FOU_ENCAP_GUE:
-		err = gue_encap_init(sk, fou, cfg);
-		if (err)
-			goto error;
+		tunnel_cfg.encap_rcv = gue_udp_recv;
+		tunnel_cfg.gro_receive = gue_gro_receive;
+		tunnel_cfg.gro_complete = gue_gro_complete;
 		break;
 	default:
 		err = -EINVAL;
 		goto error;
 	}
 
-	fou->type = cfg->type;
-
-	udp_sk(sk)->encap_type = 1;
-	udp_encap_enable();
-
-	sk->sk_user_data = fou;
-	fou->sock = sock;
-
-	inet_inc_convert_csum(sk);
+	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
 	sk->sk_allocation = GFP_ATOMIC;
 
@@ -542,12 +534,13 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg)
 {
 	struct fou_net *fn = net_generic(net, fou_net_id);
 	__be16 port = cfg->udp_config.local_udp_port;
+	u8 family = cfg->udp_config.family;
 	int err = -EINVAL;
 	struct fou *fou;
 
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fou, &fn->fou_list, list) {
-		if (fou->port == port) {
+		if (fou->port == port && fou->family == family) {
 			fou_release(fou);
 			err = 0;
 			break;
@@ -585,8 +578,15 @@ static int parse_nl_config(struct genl_info *info,
 	if (info->attrs[FOU_ATTR_AF]) {
 		u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);
 
-		if (family != AF_INET)
-			return -EINVAL;
+		switch (family) {
+		case AF_INET:
+			break;
+		case AF_INET6:
+			cfg->udp_config.ipv6_v6only = 1;
+			break;
+		default:
+			return -EAFNOSUPPORT;
+		}
 
 		cfg->udp_config.family = family;
 	}
@@ -677,6 +677,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
 	struct fou_cfg cfg;
 	struct fou *fout;
 	__be16 port;
+	u8 family;
 	int ret;
 
 	ret = parse_nl_config(info, &cfg);
@@ -686,6 +687,10 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
 	if (port == 0)
 		return -EINVAL;
 
+	family = cfg.udp_config.family;
+	if (family != AF_INET && family != AF_INET6)
+		return -EINVAL;
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -693,7 +698,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
 	ret = -ESRCH;
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fout, &fn->fou_list, list) {
-		if (port == fout->port) {
+		if (port == fout->port && family == fout->family) {
 			ret = fou_dump_info(fout, info->snd_portid,
 					    info->snd_seq, 0, msg,
 					    info->genlhdr->cmd);
@@ -798,6 +803,22 @@ static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	*protocol = IPPROTO_UDP;
 }
 
+int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		       u8 *protocol, __be16 *sport, int type)
+{
+	int err;
+
+	err = iptunnel_handle_offloads(skb, type);
+	if (err)
+		return err;
+
+	*sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+						skb, 0, 0, false);
+
+	return 0;
+}
+EXPORT_SYMBOL(__fou_build_header);
+
 int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		     u8 *protocol, struct flowi4 *fl4)
 {
@@ -806,26 +827,21 @@ int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 	__be16 sport;
 	int err;
 
-	err = iptunnel_handle_offloads(skb, type);
+	err = __fou_build_header(skb, e, protocol, &sport, type);
 	if (err)
 		return err;
 
-	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
-					       skb, 0, 0, false);
 	fou_build_udp(skb, e, fl4, protocol, sport);
 
 	return 0;
 }
 EXPORT_SYMBOL(fou_build_header);
 
-int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
-		     u8 *protocol, struct flowi4 *fl4)
+int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		       u8 *protocol, __be16 *sport, int type)
 {
-	int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
-						       SKB_GSO_UDP_TUNNEL;
 	struct guehdr *guehdr;
 	size_t hdrlen, optlen = 0;
-	__be16 sport;
 	void *data;
 	bool need_priv = false;
 	int err;
@@ -844,8 +860,8 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 		return err;
 
 	/* Get source port (based on flow hash) before skb_push */
-	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
-					       skb, 0, 0, false);
+	*sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
+						skb, 0, 0, false);
 
 	hdrlen = sizeof(struct guehdr) + optlen;
 
@@ -890,6 +906,22 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
 
 	}
 
+	return 0;
+}
+EXPORT_SYMBOL(__gue_build_header);
+
+int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		     u8 *protocol, struct flowi4 *fl4)
+{
+	int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM :
+						       SKB_GSO_UDP_TUNNEL;
+	__be16 sport;
+	int err;
+
+	err = __gue_build_header(skb, e, protocol, &sport, type);
+	if (err)
+		return err;
+
 	fou_build_udp(skb, e, fl4, protocol, sport);
 
 	return 0;

net/ipv4/gre_offload.c

@@ -26,20 +26,6 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	int gre_offset, outer_hlen;
 	bool need_csum, ufo;
 
-	if (unlikely(skb_shinfo(skb)->gso_type &
-				~(SKB_GSO_TCPV4 |
-				  SKB_GSO_TCPV6 |
-				  SKB_GSO_UDP |
-				  SKB_GSO_DODGY |
-				  SKB_GSO_TCP_ECN |
-				  SKB_GSO_TCP_FIXEDID |
-				  SKB_GSO_GRE |
-				  SKB_GSO_GRE_CSUM |
-				  SKB_GSO_IPIP |
-				  SKB_GSO_SIT |
-				  SKB_GSO_PARTIAL)))
-		goto out;
-
 	if (!skb->encapsulation)
 		goto out;
 

net/ipv4/ip_tunnel.c

@@ -443,29 +443,6 @@ drop:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
 
-static int ip_encap_hlen(struct ip_tunnel_encap *e)
-{
-	const struct ip_tunnel_encap_ops *ops;
-	int hlen = -EINVAL;
-
-	if (e->type == TUNNEL_ENCAP_NONE)
-		return 0;
-
-	if (e->type >= MAX_IPTUN_ENCAP_OPS)
-		return -EINVAL;
-
-	rcu_read_lock();
-	ops = rcu_dereference(iptun_encaps[e->type]);
-	if (likely(ops && ops->encap_hlen))
-		hlen = ops->encap_hlen(e);
-	rcu_read_unlock();
-
-	return hlen;
-}
-
-const struct ip_tunnel_encap_ops __rcu *
-		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
-
 int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *ops,
 			    unsigned int num)
 {
@@ -519,28 +496,6 @@ int ip_tunnel_encap_setup(struct ip_tunnel *t,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup);
 
-int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
-		    u8 *protocol, struct flowi4 *fl4)
-{
-	const struct ip_tunnel_encap_ops *ops;
-	int ret = -EINVAL;
-
-	if (t->encap.type == TUNNEL_ENCAP_NONE)
-		return 0;
-
-	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
-		return -EINVAL;
-
-	rcu_read_lock();
-	ops = rcu_dereference(iptun_encaps[t->encap.type]);
-	if (likely(ops && ops->build_header))
-		ret = ops->build_header(skb, &t->encap, protocol, fl4);
-	rcu_read_unlock();
-
-	return ret;
-}
-EXPORT_SYMBOL(ip_tunnel_encap);
-
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 			    struct rtable *rt, __be16 df,
 			    const struct iphdr *inner_iph)

net/ipv4/ip_tunnel_core.c

@@ -37,6 +37,7 @@
 #include <net/icmp.h>
 #include <net/protocol.h>
 #include <net/ip_tunnels.h>
+#include <net/ip6_tunnel.h>
 #include <net/arp.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
@@ -47,6 +48,14 @@
 #include <net/rtnetlink.h>
 #include <net/dst_metadata.h>
 
+const struct ip_tunnel_encap_ops __rcu *
+		iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
+EXPORT_SYMBOL(iptun_encaps);
+
+const struct ip6_tnl_encap_ops __rcu *
+		ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
+EXPORT_SYMBOL(ip6tun_encaps);
+
 void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 proto,
 		   __u8 tos, __u8 ttl, __be16 df, bool xnet)

net/ipv4/ipip.c

@@ -219,7 +219,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb->protocol != htons(ETH_P_IP)))
 		goto tx_error;
 
-	if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP))
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
 		goto tx_error;
 
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);

net/ipv4/tcp_offload.c

@@ -83,25 +83,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 
 	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
-		int type = skb_shinfo(skb)->gso_type;
-
-		if (unlikely(type &
-			     ~(SKB_GSO_TCPV4 |
-			       SKB_GSO_DODGY |
-			       SKB_GSO_TCP_ECN |
-			       SKB_GSO_TCP_FIXEDID |
-			       SKB_GSO_TCPV6 |
-			       SKB_GSO_GRE |
-			       SKB_GSO_GRE_CSUM |
-			       SKB_GSO_IPIP |
-			       SKB_GSO_SIT |
-			       SKB_GSO_UDP_TUNNEL |
-			       SKB_GSO_UDP_TUNNEL_CSUM |
-			       SKB_GSO_TUNNEL_REMCSUM |
-			       0) ||
-			     !(type & (SKB_GSO_TCPV4 |
-				       SKB_GSO_TCPV6))))
-			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 

net/ipv4/udp_offload.c

@@ -209,16 +209,6 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
-		int type = skb_shinfo(skb)->gso_type;
-
-		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
-				      SKB_GSO_UDP_TUNNEL |
-				      SKB_GSO_UDP_TUNNEL_CSUM |
-				      SKB_GSO_TUNNEL_REMCSUM |
-				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM) ||
-			     !(type & (SKB_GSO_UDP))))
-			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 

net/ipv6/Makefile

@@ -42,6 +42,7 @@ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o
 obj-$(CONFIG_IPV6_SIT) += sit.o
 obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
 obj-$(CONFIG_IPV6_GRE) += ip6_gre.o
+obj-$(CONFIG_NET_FOU) += fou6.o
 
 obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o
 obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload)

net/ipv6/fou6.c

@@ -0,0 +1,140 @@
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <net/fou.h>
+#include <net/ip.h>
+#include <net/ip6_tunnel.h>
+#include <net/ip6_checksum.h>
+#include <net/protocol.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+
+static void fou6_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
+			   struct flowi6 *fl6, u8 *protocol, __be16 sport)
+{
+	struct udphdr *uh;
+
+	skb_push(skb, sizeof(struct udphdr));
+	skb_reset_transport_header(skb);
+
+	uh = udp_hdr(skb);
+
+	uh->dest = e->dport;
+	uh->source = sport;
+	uh->len = htons(skb->len);
+	udp6_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM6), skb,
+		      &fl6->saddr, &fl6->daddr, skb->len);
+
+	*protocol = IPPROTO_UDP;
+}
+
+int fou6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		      u8 *protocol, struct flowi6 *fl6)
+{
+	__be16 sport;
+	int err;
+	int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM6 ?
+		SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	err = __fou_build_header(skb, e, protocol, &sport, type);
+	if (err)
+		return err;
+
+	fou6_build_udp(skb, e, fl6, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(fou6_build_header);
+
+int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
+		      u8 *protocol, struct flowi6 *fl6)
+{
+	__be16 sport;
+	int err;
+	int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM6 ?
+		SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+
+	err = __gue_build_header(skb, e, protocol, &sport, type);
+	if (err)
+		return err;
+
+	fou6_build_udp(skb, e, fl6, protocol, sport);
+
+	return 0;
+}
+EXPORT_SYMBOL(gue6_build_header);
+
+#ifdef CONFIG_NET_FOU_IP_TUNNELS
+
+static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
+	.encap_hlen = fou_encap_hlen,
+	.build_header = fou6_build_header,
+};
+
+static const struct ip6_tnl_encap_ops gue_ip6tun_ops = {
+	.encap_hlen = gue_encap_hlen,
+	.build_header = gue6_build_header,
+};
+
+static int ip6_tnl_encap_add_fou_ops(void)
+{
+	int ret;
+
+	ret = ip6_tnl_encap_add_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+	if (ret < 0) {
+		pr_err("can't add fou6 ops\n");
+		return ret;
+	}
+
+	ret = ip6_tnl_encap_add_ops(&gue_ip6tun_ops, TUNNEL_ENCAP_GUE);
+	if (ret < 0) {
+		pr_err("can't add gue6 ops\n");
+		ip6_tnl_encap_del_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ip6_tnl_encap_del_fou_ops(void)
+{
+	ip6_tnl_encap_del_ops(&fou_ip6tun_ops, TUNNEL_ENCAP_FOU);
+	ip6_tnl_encap_del_ops(&gue_ip6tun_ops, TUNNEL_ENCAP_GUE);
+}
+
+#else
+
+static int ip6_tnl_encap_add_fou_ops(void)
+{
+	return 0;
+}
+
+static void ip6_tnl_encap_del_fou_ops(void)
+{
+}
+
+#endif
+
+static int __init fou6_init(void)
+{
+	int ret;
+
+	ret = ip6_tnl_encap_add_fou_ops();
+
+	return ret;
+}
+
+static void __exit fou6_fini(void)
+{
+	ip6_tnl_encap_del_fou_ops();
+}
+
+module_init(fou6_init);
+module_exit(fou6_fini);
+MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
+MODULE_LICENSE("GPL");

net/ipv6/ip6_gre.c

@@ -729,7 +729,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 
 	t->tun_hlen = gre_calc_hlen(t->parms.o_flags);
 
-	t->hlen = t->tun_hlen;
+	t->hlen = t->encap_hlen + t->tun_hlen;
 
 	t_hlen = t->hlen + sizeof(struct ipv6hdr);
 
@@ -1022,9 +1022,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 	}
 
 	tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
-
-	tunnel->hlen = tunnel->tun_hlen;
-
+	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
 	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
 
 	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
@@ -1290,15 +1288,57 @@ static void ip6gre_tap_setup(struct net_device *dev)
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 }
 
+static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
+				       struct ip_tunnel_encap *ipencap)
+{
+	bool ret = false;
+
+	memset(ipencap, 0, sizeof(*ipencap));
+
+	if (!data)
+		return ret;
+
+	if (data[IFLA_GRE_ENCAP_TYPE]) {
+		ret = true;
+		ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_FLAGS]) {
+		ret = true;
+		ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_SPORT]) {
+		ret = true;
+		ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]);
+	}
+
+	if (data[IFLA_GRE_ENCAP_DPORT]) {
+		ret = true;
+		ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]);
+	}
+
+	return ret;
+}
+
 static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
 	struct nlattr *tb[], struct nlattr *data[])
 {
 	struct ip6_tnl *nt;
 	struct net *net = dev_net(dev);
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct ip_tunnel_encap ipencap;
 	int err;
 
 	nt = netdev_priv(dev);
+
+	if (ip6gre_netlink_encap_parms(data, &ipencap)) {
+		int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
+
 	ip6gre_netlink_parms(data, &nt->parms);
 
 	if (ip6gre_tunnel_find(net, &nt->parms, dev->type))
@@ -1345,10 +1385,18 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct net *net = nt->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
+	struct ip_tunnel_encap ipencap;
 
 	if (dev == ign->fb_tunnel_dev)
 		return -EINVAL;
 
+	if (ip6gre_netlink_encap_parms(data, &ipencap)) {
+		int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
+
 	ip6gre_netlink_parms(data, &p);
 
 	t = ip6gre_tunnel_locate(net, &p, 0);
@@ -1400,6 +1448,14 @@ static size_t ip6gre_get_size(const struct net_device *dev)
 		nla_total_size(4) +
 		/* IFLA_GRE_FLAGS */
 		nla_total_size(4) +
+		/* IFLA_GRE_ENCAP_TYPE */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_FLAGS */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_SPORT */
+		nla_total_size(2) +
+		/* IFLA_GRE_ENCAP_DPORT */
+		nla_total_size(2) +
 		0;
 }
 
@@ -1422,6 +1478,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) ||
 	    nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags))
 		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
+			t->encap.type) ||
+	    nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT,
+			 t->encap.sport) ||
+	    nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT,
+			 t->encap.dport) ||
+	    nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS,
+			t->encap.flags))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1440,6 +1507,10 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 },
 	[IFLA_GRE_FLOWINFO]    = { .type = NLA_U32 },
 	[IFLA_GRE_FLAGS]       = { .type = NLA_U32 },
+	[IFLA_GRE_ENCAP_TYPE]   = { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_FLAGS]  = { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_SPORT]  = { .type = NLA_U16 },
+	[IFLA_GRE_ENCAP_DPORT]  = { .type = NLA_U16 },
 };
 
 static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {

net/ipv6/ip6_input.c

@@ -223,6 +223,7 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
 	unsigned int nhoff;
 	int nexthdr;
 	bool raw;
+	bool have_final = false;
 
 	/*
 	 *	Parse extension headers
@@ -236,14 +237,27 @@ resubmit:
 	nhoff = IP6CB(skb)->nhoff;
 	nexthdr = skb_network_header(skb)[nhoff];
 
+resubmit_final:
 	raw = raw6_local_deliver(skb, nexthdr);
 	ipprot = rcu_dereference(inet6_protos[nexthdr]);
 	if (ipprot) {
 		int ret;
 
-		if (ipprot->flags & INET6_PROTO_FINAL) {
+		if (have_final) {
+			if (!(ipprot->flags & INET6_PROTO_FINAL)) {
+				/* Once we've seen a final protocol don't
+				 * allow encapsulation on any non-final
+				 * ones. This allows foo in UDP encapsulation
+				 * to work.
+				 */
+				goto discard;
+			}
+		} else if (ipprot->flags & INET6_PROTO_FINAL) {
 			const struct ipv6hdr *hdr;
 
+			/* Only do this once for first final protocol */
+			have_final = true;
+
 			/* Free reference early: we don't need it any more,
 			   and it may hold ip_conntrack module loaded
 			   indefinitely. */
@@ -263,10 +277,21 @@ resubmit:
 			goto discard;
 
 		ret = ipprot->handler(skb);
-		if (ret > 0)
-			goto resubmit;
-		else if (ret == 0)
+		if (ret > 0) {
+			if (ipprot->flags & INET6_PROTO_FINAL) {
+				/* Not an extension header, most likely UDP
+				 * encapsulation. Use return value as nexthdr
+				 * protocol not nhoff (which presumably is
+				 * not set by handler).
+				 */
+				nexthdr = ret;
+				goto resubmit_final;
+			} else {
+				goto resubmit;
+			}
+		} else if (ret == 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDELIVERS);
+		}
 	} else {
 		if (!raw) {
 			if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {

net/ipv6/ip6_offload.c

@@ -16,6 +16,7 @@
 
 #include <net/protocol.h>
 #include <net/ipv6.h>
+#include <net/inet_common.h>
 
 #include "ip6_offload.h"
 
@@ -69,24 +70,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	bool encap, udpfrag;
 	int nhoff;
 
-	if (unlikely(skb_shinfo(skb)->gso_type &
-		     ~(SKB_GSO_TCPV4 |
-		       SKB_GSO_UDP |
-		       SKB_GSO_DODGY |
-		       SKB_GSO_TCP_ECN |
-		       SKB_GSO_TCP_FIXEDID |
-		       SKB_GSO_TCPV6 |
-		       SKB_GSO_GRE |
-		       SKB_GSO_GRE_CSUM |
-		       SKB_GSO_IPIP |
-		       SKB_GSO_SIT |
-		       SKB_GSO_UDP_TUNNEL |
-		       SKB_GSO_UDP_TUNNEL_CSUM |
-		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_PARTIAL |
-		       0)))
-		goto out;
-
 	skb_reset_network_header(skb);
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
@@ -104,7 +87,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
 
 	if (skb->encapsulation &&
-	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
+	    skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
 		udpfrag = proto == IPPROTO_UDP && encap;
 	else
 		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
@@ -271,9 +254,11 @@ out:
 	return pp;
 }
 
-static struct sk_buff **sit_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
+					       struct sk_buff *skb)
 {
+	/* Common GRO receive for SIT and IP6IP6 */
+
 	if (NAPI_GRO_CB(skb)->encap_mark) {
 		NAPI_GRO_CB(skb)->flush = 1;
 		return NULL;
@@ -284,6 +269,21 @@ static struct sk_buff **sit_gro_receive(struct sk_buff **head,
 	return ipv6_gro_receive(head, skb);
 }
 
+static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head,
+					   struct sk_buff *skb)
+{
+	/* Common GRO receive for SIT and IP6IP6 */
+
+	if (NAPI_GRO_CB(skb)->encap_mark) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	return inet_gro_receive(head, skb);
+}
+
 static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
@@ -312,10 +312,24 @@ out_unlock:
 static int sit_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	skb->encapsulation = 1;
-	skb_shinfo(skb)->gso_type |= SKB_GSO_SIT;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
 	return ipv6_gro_complete(skb, nhoff);
 }
 
+static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
+	return ipv6_gro_complete(skb, nhoff);
+}
+
+static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
+	return inet_gro_complete(skb, nhoff);
+}
+
 static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.callbacks = {
@@ -328,11 +342,26 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive    = sit_gro_receive,
+		.gro_receive    = sit_ip6ip6_gro_receive,
 		.gro_complete   = sit_gro_complete,
 	},
 };
 
+static const struct net_offload ip4ip6_offload = {
+	.callbacks = {
+		.gso_segment	= inet_gso_segment,
+		.gro_receive    = ip4ip6_gro_receive,
+		.gro_complete   = ip4ip6_gro_complete,
+	},
+};
+
+static const struct net_offload ip6ip6_offload = {
+	.callbacks = {
+		.gso_segment	= ipv6_gso_segment,
+		.gro_receive    = sit_ip6ip6_gro_receive,
+		.gro_complete   = ip6ip6_gro_complete,
+	},
+};
 static int __init ipv6_offload_init(void)
 {
 
@@ -344,6 +373,8 @@ static int __init ipv6_offload_init(void)
 	dev_add_offload(&ipv6_packet_offload);
 
 	inet_add_offload(&sit_offload, IPPROTO_IPV6);
+	inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
+	inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP);
 
 	return 0;
 }

net/ipv6/ip6_tunnel.c

@@ -1010,7 +1010,8 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	struct dst_entry *dst = NULL, *ndst = NULL;
 	struct net_device *tdev;
 	int mtu;
-	unsigned int max_headroom = sizeof(struct ipv6hdr);
+	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
+	unsigned int max_headroom = psh_hlen;
 	int err = -1;
 
 	/* NBMA tunnel */
@@ -1063,7 +1064,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 				     t->parms.name);
 		goto tx_err_dst_release;
 	}
-	mtu = dst_mtu(dst) - sizeof(*ipv6h);
+	mtu = dst_mtu(dst) - psh_hlen;
 	if (encap_limit >= 0) {
 		max_headroom += 8;
 		mtu -= 8;
@@ -1119,16 +1120,18 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 		ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
 	}
 
-	if (likely(!skb->encapsulation)) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
-
+	/* Calculate max headroom for all the headers and adjust
+	 * needed_headroom if necessary.
+	 */
 	max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr)
-			+ dst->header_len;
+			+ dst->header_len + t->hlen;
 	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
 
+	err = ip6_tnl_encap(skb, t, &proto, fl6);
+	if (err)
+		return err;
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
@@ -1180,6 +1183,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
+		return -1;
+
+	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   IPPROTO_IPIP);
 	if (err != 0) {
@@ -1234,6 +1242,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
 		fl6.flowi6_mark = skb->mark;
 
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
+		return -1;
+
+	skb_set_inner_ipproto(skb, IPPROTO_IPV6);
+
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   IPPROTO_IPV6);
 	if (err != 0) {
@@ -1280,6 +1293,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 	struct net_device *dev = t->dev;
 	struct __ip6_tnl_parm *p = &t->parms;
 	struct flowi6 *fl6 = &t->fl.u.ip6;
+	int t_hlen;
 
 	memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
 	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -1303,6 +1317,10 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 	else
 		dev->flags &= ~IFF_POINTOPOINT;
 
+	t->tun_hlen = 0;
+	t->hlen = t->encap_hlen + t->tun_hlen;
+	t_hlen = t->hlen + sizeof(struct ipv6hdr);
+
 	if (p->flags & IP6_TNL_F_CAP_XMIT) {
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
@@ -1316,9 +1334,9 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 
 		if (rt->dst.dev) {
 			dev->hard_header_len = rt->dst.dev->hard_header_len +
-				sizeof(struct ipv6hdr);
+				t_hlen;
 
-			dev->mtu = rt->dst.dev->mtu - sizeof(struct ipv6hdr);
+			dev->mtu = rt->dst.dev->mtu - t_hlen;
 			if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 				dev->mtu -= 8;
 
@@ -1564,6 +1582,59 @@ int ip6_tnl_get_iflink(const struct net_device *dev)
 }
 EXPORT_SYMBOL(ip6_tnl_get_iflink);
 
+int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num)
+{
+	if (num >= MAX_IPTUN_ENCAP_OPS)
+		return -ERANGE;
+
+	return !cmpxchg((const struct ip6_tnl_encap_ops **)
+			&ip6tun_encaps[num],
+			NULL, ops) ? 0 : -1;
+}
+EXPORT_SYMBOL(ip6_tnl_encap_add_ops);
+
+int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
+			  unsigned int num)
+{
+	int ret;
+
+	if (num >= MAX_IPTUN_ENCAP_OPS)
+		return -ERANGE;
+
+	ret = (cmpxchg((const struct ip6_tnl_encap_ops **)
+		       &ip6tun_encaps[num],
+		       ops, NULL) == ops) ? 0 : -1;
+
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL(ip6_tnl_encap_del_ops);
+
+int ip6_tnl_encap_setup(struct ip6_tnl *t,
+			struct ip_tunnel_encap *ipencap)
+{
+	int hlen;
+
+	memset(&t->encap, 0, sizeof(t->encap));
+
+	hlen = ip6_encap_hlen(ipencap);
+	if (hlen < 0)
+		return hlen;
+
+	t->encap.type = ipencap->type;
+	t->encap.sport = ipencap->sport;
+	t->encap.dport = ipencap->dport;
+	t->encap.flags = ipencap->flags;
+
+	t->encap_hlen = hlen;
+	t->hlen = t->encap_hlen + t->tun_hlen;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup);
+
 static const struct net_device_ops ip6_tnl_netdev_ops = {
 	.ndo_init	= ip6_tnl_dev_init,
 	.ndo_uninit	= ip6_tnl_dev_uninit,
@@ -1574,6 +1645,11 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
+#define IPXIPX_FEATURES (NETIF_F_SG |		\
+			 NETIF_F_FRAGLIST |	\
+			 NETIF_F_HIGHDMA |	\
+			 NETIF_F_GSO_SOFTWARE |	\
+			 NETIF_F_HW_CSUM)
 
 /**
  * ip6_tnl_dev_setup - setup virtual tunnel device
@@ -1585,20 +1661,18 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 
 static void ip6_tnl_dev_setup(struct net_device *dev)
 {
-	struct ip6_tnl *t;
-
 	dev->netdev_ops = &ip6_tnl_netdev_ops;
 	dev->destructor = ip6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
-	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
-	dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr);
-	t = netdev_priv(dev);
-	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
-		dev->mtu -= 8;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
+	dev->features |= NETIF_F_LLTX;
 	netif_keep_dst(dev);
+
+	dev->features		|= IPXIPX_FEATURES;
+	dev->hw_features	|= IPXIPX_FEATURES;
+
 	/* This perm addr will be used as interface identifier by IPv6 */
 	dev->addr_assign_type = NET_ADDR_RANDOM;
 	eth_random_addr(dev->perm_addr);
@@ -1615,6 +1689,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
 	int ret;
+	int t_hlen;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
@@ -1630,8 +1705,15 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	if (ret)
 		goto destroy_dst;
 
-	t->hlen = 0;
 	t->tun_hlen = 0;
+	t->hlen = t->encap_hlen + t->tun_hlen;
+	t_hlen = t->hlen + sizeof(struct ipv6hdr);
+
+	dev->type = ARPHRD_TUNNEL6;
+	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	dev->mtu = ETH_DATA_LEN - t_hlen;
+	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+		dev->mtu -= 8;
 
 	return 0;
 
@@ -1729,13 +1811,55 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
 		parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
 }
 
+static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[],
+					struct ip_tunnel_encap *ipencap)
+{
+	bool ret = false;
+
+	memset(ipencap, 0, sizeof(*ipencap));
+
+	if (!data)
+		return ret;
+
+	if (data[IFLA_IPTUN_ENCAP_TYPE]) {
+		ret = true;
+		ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
+		ret = true;
+		ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
+		ret = true;
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
+	}
+
+	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
+		ret = true;
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
+	}
+
+	return ret;
+}
+
 static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
 			   struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net *net = dev_net(dev);
 	struct ip6_tnl *nt, *t;
+	struct ip_tunnel_encap ipencap;
 
 	nt = netdev_priv(dev);
+
+	if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
+		int err = ip6_tnl_encap_setup(nt, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
+
 	ip6_tnl_netlink_parms(data, &nt->parms);
 
 	t = ip6_tnl_locate(net, &nt->parms, 0);
@@ -1752,10 +1876,17 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct __ip6_tnl_parm p;
 	struct net *net = t->net;
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+	struct ip_tunnel_encap ipencap;
 
 	if (dev == ip6n->fb_tnl_dev)
 		return -EINVAL;
 
+	if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
+		int err = ip6_tnl_encap_setup(t, &ipencap);
+
+		if (err < 0)
+			return err;
+	}
 	ip6_tnl_netlink_parms(data, &p);
 
 	t = ip6_tnl_locate(net, &p, 0);
@@ -1796,6 +1927,14 @@ static size_t ip6_tnl_get_size(const struct net_device *dev)
 		nla_total_size(4) +
 		/* IFLA_IPTUN_PROTO */
 		nla_total_size(1) +
+		/* IFLA_IPTUN_ENCAP_TYPE */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_FLAGS */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_SPORT */
+		nla_total_size(2) +
+		/* IFLA_IPTUN_ENCAP_DPORT */
+		nla_total_size(2) +
 		0;
 }
 
@@ -1813,6 +1952,17 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto))
 		goto nla_put_failure;
+
+	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
+			tunnel->encap.type) ||
+	nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
+		     tunnel->encap.sport) ||
+	nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
+		     tunnel->encap.dport) ||
+	nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
+		    tunnel->encap.flags))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1836,6 +1986,10 @@ static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_FLOWINFO]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_FLAGS]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_PROTO]		= { .type = NLA_U8 },
+	[IFLA_IPTUN_ENCAP_TYPE]		= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
 };
 
 static struct rtnl_link_ops ip6_link_ops __read_mostly = {

net/ipv6/sit.c

@@ -913,7 +913,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		goto tx_error;
 	}
 
-	if (iptunnel_handle_offloads(skb, SKB_GSO_SIT)) {
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -1000,7 +1000,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr  *tiph = &tunnel->parms.iph;
 
-	if (iptunnel_handle_offloads(skb, SKB_GSO_IPIP))
+	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
 		goto tx_error;
 
 	skb_set_inner_ipproto(skb, IPPROTO_IPIP);

net/ipv6/udp_offload.c

@@ -36,19 +36,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
 		/* Packet is from an untrusted source, reset gso_segs. */
-		int type = skb_shinfo(skb)->gso_type;
-
-		if (unlikely(type & ~(SKB_GSO_UDP |
-				      SKB_GSO_DODGY |
-				      SKB_GSO_UDP_TUNNEL |
-				      SKB_GSO_UDP_TUNNEL_CSUM |
-				      SKB_GSO_TUNNEL_REMCSUM |
-				      SKB_GSO_GRE |
-				      SKB_GSO_GRE_CSUM |
-				      SKB_GSO_IPIP |
-				      SKB_GSO_SIT) ||
-			     !(type & (SKB_GSO_UDP))))
-			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 

net/mpls/mpls_gso.c

@@ -26,15 +26,6 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 	netdev_features_t mpls_features;
 	__be16 mpls_protocol;
 
-	if (unlikely(skb_shinfo(skb)->gso_type &
-				~(SKB_GSO_TCPV4 |
-				  SKB_GSO_TCPV6 |
-				  SKB_GSO_UDP |
-				  SKB_GSO_DODGY |
-				  SKB_GSO_TCP_FIXEDID |
-				  SKB_GSO_TCP_ECN)))
-		goto out;
-
 	/* Setup inner SKB. */
 	mpls_protocol = skb->protocol;
 	skb->protocol = skb->inner_protocol;
@@ -57,7 +48,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 	 * skb_mac_gso_segment(), an indirect caller of this function.
 	 */
 	__skb_pull(skb, skb->data - skb_mac_header(skb));
-out:
+
 	return segs;
 }
 

net/netfilter/ipvs/ip_vs_xmit.c

@@ -932,17 +932,14 @@ error:
 
 static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
 {
-	if (encaps_af == AF_INET) {
-		if (orig_af == AF_INET)
-			return SKB_GSO_IPIP;
-
-		return SKB_GSO_SIT;
+	switch (encaps_af) {
+	case AF_INET:
+		return SKB_GSO_IPXIP4;
+	case AF_INET6:
+		return SKB_GSO_IPXIP6;
+	default:
+		return 0;
 	}
-
-	/* GSO: we need to provide proper SKB_GSO_ value for IPv6:
-	 * SKB_GSO_SIT/IPV6
-	 */
-	return 0;
 }
 
 /*