GRE: Refactor GRE tunneling code.

Following patch refactors GRE code into ip tunneling code and GRE
specific code. Common tunneling code is moved to ip_tunnel module.
ip_tunnel module is written as generic library which can be used
by different tunneling implementations.

ip_tunnel module contains following components:
 - packet xmit and rcv generic code. xmit flow looks like
   (gre_xmit/ipip_xmit)->ip_tunnel_xmit->ip_local_out.
 - hash table of all devices.
 - lookup for tunnel devices.
 - control plane operations like device create, destroy, ioctl, netlink
   operations code.
 - registration for tunneling modules, like gre, ipip etc.
 - define single pcpu_tstats dev->tstats.
 - struct tnl_ptk_info added to pass parsed tunnel packet parameters.

ipip.h header is renamed to ip_tunnel.h

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 1361 insertions, 1196 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 7944df768454..2073226a8a63 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -186,9 +186,14 @@ config NET_IPGRE_DEMUX
 	 This is helper module to demultiplex GRE packets on GRE version field criteria.
 	 Required by ip_gre and pptp modules.
 
+config NET_IP_TUNNEL
+	tristate
+	default n
+
 config NET_IPGRE
 	tristate "IP: GRE tunnels over IP"
 	depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX
+	select NET_IP_TUNNEL
 	help
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 15ca63ec604e..089cb9f36387 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -13,6 +13,7 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     fib_frontend.o fib_semantics.o fib_trie.o \
 	     inet_fragment.o ping.o
 
+obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 70b2d4cf5801..93824c57b108 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -111,7 +111,6 @@
 #include <net/sock.h>
 #include <net/raw.h>
 #include <net/icmp.h>
-#include <net/ipip.h>
 #include <net/inet_common.h>
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 7a4c710c4cdd..d2d5a99fba09 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -27,11 +27,6 @@
 
 static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
 static DEFINE_SPINLOCK(gre_proto_lock);
-struct gre_base_hdr {
-	__be16 flags;
-	__be16 protocol;
-};
-#define GRE_HEADER_SECTION 4
 
 int gre_add_protocol(const struct gre_protocol *proto, u8 version)
 {
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2e94289a17e8..ad662e906f7e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -37,7 +37,7 @@
 #include <net/ip.h>
 #include <net/icmp.h>
 #include <net/protocol.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
 #include <net/arp.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
@@ -108,15 +108,6 @@
    fatal route to network, even if it were you who configured
    fatal static route: you are innocent. :-)
 
-
-
-   3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
-   practically identical code. It would be good to glue them
-   together, but it is not very evident, how to make them modular.
-   sit is integral part of IPv6, ipip and gre are naturally modular.
-   We could extract common parts (hash table, ioctl etc)
-   to a separate module (ip_tunnel.c).
-
    Alexey Kuznetsov.
  */
 
@@ -126,400 +117,135 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly;
 static int ipgre_tunnel_init(struct net_device *dev);
-static void ipgre_tunnel_setup(struct net_device *dev);
-static int ipgre_tunnel_bind_dev(struct net_device *dev);
-
-/* Fallback tunnel: no source, no destination, no key, no options */
-
-#define HASH_SIZE  16
 
 static int ipgre_net_id __read_mostly;
-struct ipgre_net {
-	struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
-
-	struct net_device *fb_tunnel_dev;
-};
-
-/* Tunnel hash table */
-
-/*
-   4 hash tables:
-
-   3: (remote,local)
-   2: (remote,*)
-   1: (*,local)
-   0: (*,*)
+static int gre_tap_net_id __read_mostly;
 
-   We require exact key match i.e. if a key is present in packet
-   it will match only tunnel with the same key; if it is not present,
-   it will match only keyless tunnel.
-
-   All keysless packets, if not matched configured keyless tunnels
-   will match fallback tunnel.
- */
+static __sum16 check_checksum(struct sk_buff *skb)
+{
+	__sum16 csum = 0;
 
-#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		csum = csum_fold(skb->csum);
 
-#define tunnels_r_l	tunnels[3]
-#define tunnels_r	tunnels[2]
-#define tunnels_l	tunnels[1]
-#define tunnels_wc	tunnels[0]
+		if (!csum)
+			break;
+		/* Fall through. */
 
-static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
-						   struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
+	case CHECKSUM_NONE:
+		skb->csum = 0;
+		csum = __skb_checksum_complete(skb);
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		break;
 	}
 
-	tot->multicast = dev->stats.multicast;
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_frame_errors = dev->stats.rx_frame_errors;
-	tot->rx_errors = dev->stats.rx_errors;
-
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
-
-	return tot;
+	return csum;
 }
 
-/* Does key in tunnel parameters match packet */
-static bool ipgre_key_match(const struct ip_tunnel_parm *p,
-			    __be16 flags, __be32 key)
+static int ip_gre_calc_hlen(__be16 o_flags)
 {
-	if (p->i_flags & GRE_KEY) {
-		if (flags & GRE_KEY)
-			return key == p->i_key;
-		else
-			return false;	/* key expected, none present */
-	} else
-		return !(flags & GRE_KEY);
-}
+	int addend = 4;
 
-/* Given src, dst and key, find appropriate for input tunnel. */
+	if (o_flags&TUNNEL_CSUM)
+		addend += 4;
+	if (o_flags&TUNNEL_KEY)
+		addend += 4;
+	if (o_flags&TUNNEL_SEQ)
+		addend += 4;
+	return addend;
+}
 
-static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
-					     __be32 remote, __be32 local,
-					     __be16 flags, __be32 key,
-					     __be16 gre_proto)
+static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
+			    bool *csum_err, int *hdr_len)
 {
-	struct net *net = dev_net(dev);
-	int link = dev->ifindex;
-	unsigned int h0 = HASH(remote);
-	unsigned int h1 = HASH(key);
-	struct ip_tunnel *t, *cand = NULL;
-	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-	int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
-		       ARPHRD_ETHER : ARPHRD_IPGRE;
-	int score, cand_score = 4;
-
-	for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) {
-		if (local != t->parms.iph.saddr ||
-		    remote != t->parms.iph.daddr ||
-		    !(t->dev->flags & IFF_UP))
-			continue;
-
-		if (!ipgre_key_match(&t->parms, flags, key))
-			continue;
-
-		if (t->dev->type != ARPHRD_IPGRE &&
-		    t->dev->type != dev_type)
-			continue;
-
-		score = 0;
-		if (t->parms.link != link)
-			score |= 1;
-		if (t->dev->type != dev_type)
-			score |= 2;
-		if (score == 0)
-			return t;
-
-		if (score < cand_score) {
-			cand = t;
-			cand_score = score;
-		}
-	}
-
-	for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) {
-		if (remote != t->parms.iph.daddr ||
-		    !(t->dev->flags & IFF_UP))
-			continue;
-
-		if (!ipgre_key_match(&t->parms, flags, key))
-			continue;
-
-		if (t->dev->type != ARPHRD_IPGRE &&
-		    t->dev->type != dev_type)
-			continue;
-
-		score = 0;
-		if (t->parms.link != link)
-			score |= 1;
-		if (t->dev->type != dev_type)
-			score |= 2;
-		if (score == 0)
-			return t;
-
-		if (score < cand_score) {
-			cand = t;
-			cand_score = score;
-		}
-	}
+	struct iphdr *iph = ip_hdr(skb);
+	struct gre_base_hdr *greh;
+	__be32 *options;
 
-	for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
-			continue;
-
-		if (!ipgre_key_match(&t->parms, flags, key))
-			continue;
-
-		if (t->dev->type != ARPHRD_IPGRE &&
-		    t->dev->type != dev_type)
-			continue;
-
-		score = 0;
-		if (t->parms.link != link)
-			score |= 1;
-		if (t->dev->type != dev_type)
-			score |= 2;
-		if (score == 0)
-			return t;
-
-		if (score < cand_score) {
-			cand = t;
-			cand_score = score;
-		}
-	}
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+		return -EINVAL;
 
-	for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) {
-		if (t->parms.i_key != key ||
-		    !(t->dev->flags & IFF_UP))
-			continue;
-
-		if (t->dev->type != ARPHRD_IPGRE &&
-		    t->dev->type != dev_type)
-			continue;
-
-		score = 0;
-		if (t->parms.link != link)
-			score |= 1;
-		if (t->dev->type != dev_type)
-			score |= 2;
-		if (score == 0)
-			return t;
-
-		if (score < cand_score) {
-			cand = t;
-			cand_score = score;
-		}
-	}
+	greh = (struct gre_base_hdr *)((u8 *)iph + (iph->ihl << 2));
+	if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
+		return -EINVAL;
 
-	if (cand != NULL)
-		return cand;
+	tpi->flags = gre_flags_to_tnl_flags(greh->flags);
+	*hdr_len = ip_gre_calc_hlen(tpi->flags);
 
-	dev = ign->fb_tunnel_dev;
-	if (dev->flags & IFF_UP)
-		return netdev_priv(dev);
+	if (!pskb_may_pull(skb, *hdr_len))
+		return -EINVAL;
 
-	return NULL;
-}
+	tpi->proto = greh->protocol;
 
-static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
-		struct ip_tunnel_parm *parms)
-{
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	__be32 key = parms->i_key;
-	unsigned int h = HASH(key);
-	int prio = 0;
-
-	if (local)
-		prio |= 1;
-	if (remote && !ipv4_is_multicast(remote)) {
-		prio |= 2;
-		h ^= HASH(remote);
+	options = (__be32 *)(greh + 1);
+	if (greh->flags & GRE_CSUM) {
+		if (check_checksum(skb)) {
+			*csum_err = true;
+			return -EINVAL;
+		}
+		options++;
 	}
 
-	return &ign->tunnels[prio][h];
-}
-
-static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
-		struct ip_tunnel *t)
-{
-	return __ipgre_bucket(ign, &t->parms);
-}
-
-static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
+	if (greh->flags & GRE_KEY) {
+		tpi->key = *options;
+		options++;
+	} else
+		tpi->key = 0;
 
-	rcu_assign_pointer(t->next, rtnl_dereference(*tp));
-	rcu_assign_pointer(*tp, t);
-}
+	if (unlikely(greh->flags & GRE_SEQ)) {
+		tpi->seq = *options;
+		options++;
+	} else
+		tpi->seq = 0;
 
-static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
-{
-	struct ip_tunnel __rcu **tp;
-	struct ip_tunnel *iter;
-
-	for (tp = ipgre_bucket(ign, t);
-	     (iter = rtnl_dereference(*tp)) != NULL;
-	     tp = &iter->next) {
-		if (t == iter) {
-			rcu_assign_pointer(*tp, t->next);
-			break;
+	/* WCCP version 1 and 2 protocol decoding.
+	 * - Change protocol to IP
+	 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
+	 */
+	if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) {
+		tpi->proto = htons(ETH_P_IP);
+		if ((*(u8 *)options & 0xF0) != 0x40) {
+			*hdr_len += 4;
+			if (!pskb_may_pull(skb, *hdr_len))
+				return -EINVAL;
 		}
 	}
-}
-
-static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
-					   struct ip_tunnel_parm *parms,
-					   int type)
-{
-	__be32 remote = parms->iph.daddr;
-	__be32 local = parms->iph.saddr;
-	__be32 key = parms->i_key;
-	int link = parms->link;
-	struct ip_tunnel *t;
-	struct ip_tunnel __rcu **tp;
-	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
-	for (tp = __ipgre_bucket(ign, parms);
-	     (t = rtnl_dereference(*tp)) != NULL;
-	     tp = &t->next)
-		if (local == t->parms.iph.saddr &&
-		    remote == t->parms.iph.daddr &&
-		    key == t->parms.i_key &&
-		    link == t->parms.link &&
-		    type == t->dev->type)
-			break;
-
-	return t;
-}
-
-static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
-		struct ip_tunnel_parm *parms, int create)
-{
-	struct ip_tunnel *t, *nt;
-	struct net_device *dev;
-	char name[IFNAMSIZ];
-	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
-	t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
-	if (t || !create)
-		return t;
-
-	if (parms->name[0])
-		strlcpy(name, parms->name, IFNAMSIZ);
-	else
-		strcpy(name, "gre%d");
-
-	dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
-	if (!dev)
-		return NULL;
-
-	dev_net_set(dev, net);
-
-	nt = netdev_priv(dev);
-	nt->parms = *parms;
-	dev->rtnl_link_ops = &ipgre_link_ops;
 
-	dev->mtu = ipgre_tunnel_bind_dev(dev);
-
-	if (register_netdevice(dev) < 0)
-		goto failed_free;
-
-	/* Can use a lockless transmit, unless we generate output sequences */
-	if (!(nt->parms.o_flags & GRE_SEQ))
-		dev->features |= NETIF_F_LLTX;
-
-	dev_hold(dev);
-	ipgre_tunnel_link(ign, nt);
-	return nt;
-
-failed_free:
-	free_netdev(dev);
-	return NULL;
-}
-
-static void ipgre_tunnel_uninit(struct net_device *dev)
-{
-	struct net *net = dev_net(dev);
-	struct ipgre_net *ign = net_generic(net, ipgre_net_id);
-
-	ipgre_tunnel_unlink(ign, netdev_priv(dev));
-	dev_put(dev);
+	return 0;
 }
 
-
 static void ipgre_err(struct sk_buff *skb, u32 info)
 {
 
-/* All the routers (except for Linux) return only
-   8 bytes of packet payload. It means, that precise relaying of
-   ICMP in the real Internet is absolutely infeasible.
+	/* All the routers (except for Linux) return only
+	   8 bytes of packet payload. It means, that precise relaying of
+	   ICMP in the real Internet is absolutely infeasible.
 
-   Moreover, Cisco "wise men" put GRE key to the third word
-   in GRE header. It makes impossible maintaining even soft state for keyed
-   GRE tunnels with enabled checksum. Tell them "thank you".
-
-   Well, I wonder, rfc1812 was written by Cisco employee,
-   what the hell these idiots break standards established
-   by themselves???
- */
+	   Moreover, Cisco "wise men" put GRE key to the third word
+	   in GRE header. It makes impossible maintaining even soft
+	   state for keyed GRE tunnels with enabled checksum. Tell
+	   them "thank you".
 
+	   Well, I wonder, rfc1812 was written by Cisco employee,
+	   what the hell these idiots break standards established
+	   by themselves???
+	   */
+	struct net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn;
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
-	__be16	     *p = (__be16 *)(skb->data+(iph->ihl<<2));
-	int grehlen = (iph->ihl<<2) + 4;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct ip_tunnel *t;
-	__be16 flags;
-	__be32 key = 0;
+	struct tnl_ptk_info tpi;
+	int hdr_len;
+	bool csum_err = false;
 
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
+	if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len)) {
+		if (!csum_err)          /* ignore csum errors. */
 			return;
-		if (flags&GRE_KEY) {
-			grehlen += 4;
-			if (flags&GRE_CSUM)
-				grehlen += 4;
-		}
 	}
 
-	/* If only 8 bytes returned, keyed message will be dropped here */
-	if (skb_headlen(skb) < grehlen)
-		return;
-
-	if (flags & GRE_KEY)
-		key = *(((__be32 *)p) + (grehlen / 4) - 1);
-
 	switch (type) {
 	default:
 	case ICMP_PARAMETERPROB:
@@ -548,8 +274,13 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 		break;
 	}
 
-	t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
-				flags, key, p[1]);
+	if (tpi.proto == htons(ETH_P_TEB))
+		itn = net_generic(net, gre_tap_net_id);
+	else
+		itn = net_generic(net, ipgre_net_id);
+
+	t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+			     iph->daddr, iph->saddr, tpi.key);
 
 	if (t == NULL)
 		return;
@@ -578,158 +309,33 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
 	t->err_time = jiffies;
 }
 
-static inline u8
-ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
-{
-	u8 inner = 0;
-	if (skb->protocol == htons(ETH_P_IP))
-		inner = old_iph->tos;
-	else if (skb->protocol == htons(ETH_P_IPV6))
-		inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
-	return INET_ECN_encapsulate(tos, inner);
-}
-
 static int ipgre_rcv(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn;
 	const struct iphdr *iph;
-	u8     *h;
-	__be16    flags;
-	__sum16   csum = 0;
-	__be32 key = 0;
-	u32    seqno = 0;
 	struct ip_tunnel *tunnel;
-	int    offset = 4;
-	__be16 gre_proto;
-	int    err;
+	struct tnl_ptk_info tpi;
+	int hdr_len;
+	bool csum_err = false;
 
-	if (!pskb_may_pull(skb, 16))
+	if (parse_gre_header(skb, &tpi, &csum_err, &hdr_len) < 0)
 		goto drop;
 
-	iph = ip_hdr(skb);
-	h = skb->data;
-	flags = *(__be16 *)h;
-
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
-		/* - Version must be 0.
-		   - We do not support routing headers.
-		 */
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			goto drop;
-
-		if (flags&GRE_CSUM) {
-			switch (skb->ip_summed) {
-			case CHECKSUM_COMPLETE:
-				csum = csum_fold(skb->csum);
-				if (!csum)
-					break;
-				/* fall through */
-			case CHECKSUM_NONE:
-				skb->csum = 0;
-				csum = __skb_checksum_complete(skb);
-				skb->ip_summed = CHECKSUM_COMPLETE;
-			}
-			offset += 4;
-		}
-		if (flags&GRE_KEY) {
-			key = *(__be32 *)(h + offset);
-			offset += 4;
-		}
-		if (flags&GRE_SEQ) {
-			seqno = ntohl(*(__be32 *)(h + offset));
-			offset += 4;
-		}
-	}
+	if (tpi.proto == htons(ETH_P_TEB))
+		itn = net_generic(net, gre_tap_net_id);
+	else
+		itn = net_generic(net, ipgre_net_id);
 
-	gre_proto = *(__be16 *)(h + 2);
+	iph = ip_hdr(skb);
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi.flags,
+				  iph->saddr, iph->daddr, tpi.key);
 
-	tunnel = ipgre_tunnel_lookup(skb->dev,
-				     iph->saddr, iph->daddr, flags, key,
-				     gre_proto);
 	if (tunnel) {
-		struct pcpu_tstats *tstats;
-
-		secpath_reset(skb);
-
-		skb->protocol = gre_proto;
-		/* WCCP version 1 and 2 protocol decoding.
-		 * - Change protocol to IP
-		 * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
-		 */
-		if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
-			skb->protocol = htons(ETH_P_IP);
-			if ((*(h + offset) & 0xF0) != 0x40)
-				offset += 4;
-		}
-
-		skb->mac_header = skb->network_header;
-		__pskb_pull(skb, offset);
-		skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
-		skb->pkt_type = PACKET_HOST;
-#ifdef CONFIG_NET_IPGRE_BROADCAST
-		if (ipv4_is_multicast(iph->daddr)) {
-			/* Looped back packet, drop it! */
-			if (rt_is_output_route(skb_rtable(skb)))
-				goto drop;
-			tunnel->dev->stats.multicast++;
-			skb->pkt_type = PACKET_BROADCAST;
-		}
-#endif
-
-		if (((flags&GRE_CSUM) && csum) ||
-		    (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
-			tunnel->dev->stats.rx_crc_errors++;
-			tunnel->dev->stats.rx_errors++;
-			goto drop;
-		}
-		if (tunnel->parms.i_flags&GRE_SEQ) {
-			if (!(flags&GRE_SEQ) ||
-			    (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
-				tunnel->dev->stats.rx_fifo_errors++;
-				tunnel->dev->stats.rx_errors++;
-				goto drop;
-			}
-			tunnel->i_seqno = seqno + 1;
-		}
-
-		/* Warning: All skb pointers will be invalidated! */
-		if (tunnel->dev->type == ARPHRD_ETHER) {
-			if (!pskb_may_pull(skb, ETH_HLEN)) {
-				tunnel->dev->stats.rx_length_errors++;
-				tunnel->dev->stats.rx_errors++;
-				goto drop;
-			}
-
-			iph = ip_hdr(skb);
-			skb->protocol = eth_type_trans(skb, tunnel->dev);
-			skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-		}
-
-		__skb_tunnel_rx(skb, tunnel->dev);
-
-		skb_reset_network_header(skb);
-		err = IP_ECN_decapsulate(iph, skb);
-		if (unlikely(err)) {
-			if (log_ecn_error)
-				net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
-						     &iph->saddr, iph->tos);
-			if (err > 1) {
-				++tunnel->dev->stats.rx_frame_errors;
-				++tunnel->dev->stats.rx_errors;
-				goto drop;
-			}
-		}
-
-		tstats = this_cpu_ptr(tunnel->dev->tstats);
-		u64_stats_update_begin(&tstats->syncp);
-		tstats->rx_packets++;
-		tstats->rx_bytes += skb->len;
-		u64_stats_update_end(&tstats->syncp);
-
-		gro_cells_receive(&tunnel->gro_cells, skb);
+		ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
 		return 0;
 	}
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-
 drop:
 	kfree_skb(skb);
 	return 0;
@@ -746,7 +352,7 @@ static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff
 		skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
 		return skb;
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		   tunnel->parms.o_flags&GRE_CSUM) {
+		   tunnel->parms.o_flags&TUNNEL_CSUM) {
 		err = skb_checksum_help(skb);
 		if (unlikely(err))
 			goto error;
@@ -760,480 +366,157 @@ error:
 	return ERR_PTR(err);
 }
 
-static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static struct sk_buff *gre_build_header(struct sk_buff *skb,
+					const struct tnl_ptk_info *tpi,
+					int hdr_len)
 {
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-	const struct iphdr  *old_iph;
-	const struct iphdr  *tiph;
-	struct flowi4 fl4;
-	u8     tos;
-	__be16 df;
-	struct rtable *rt;     			/* Route to the other host */
-	struct net_device *tdev;		/* Device to other host */
-	struct iphdr  *iph;			/* Our new IP header */
-	unsigned int max_headroom;		/* The extra header space needed */
-	int    gre_hlen;
-	__be32 dst;
-	int    mtu;
-	u8     ttl;
-	int    err;
-
-	skb = handle_offloads(tunnel, skb);
-	if (IS_ERR(skb)) {
-		dev->stats.tx_dropped++;
-		return NETDEV_TX_OK;
-	}
+	struct gre_base_hdr *greh;
 
-	if (!skb->encapsulation) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb_push(skb, hdr_len);
 
-	old_iph = ip_hdr(skb);
+	greh = (struct gre_base_hdr *)skb->data;
+	greh->flags = tnl_flags_to_gre_flags(tpi->flags);
+	greh->protocol = tpi->proto;
 
-	if (dev->type == ARPHRD_ETHER)
-		IPCB(skb)->flags = 0;
+	if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) {
+		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
 
-	if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
-		gre_hlen = 0;
-		tiph = (const struct iphdr *)skb->data;
-	} else {
-		gre_hlen = tunnel->hlen;
-		tiph = &tunnel->parms.iph;
-	}
-
-	if ((dst = tiph->daddr) == 0) {
-		/* NBMA tunnel */
-
-		if (skb_dst(skb) == NULL) {
-			dev->stats.tx_fifo_errors++;
-			goto tx_error;
+		if (tpi->flags&TUNNEL_SEQ) {
+			*ptr = tpi->seq;
+			ptr--;
 		}
-
-		if (skb->protocol == htons(ETH_P_IP)) {
-			rt = skb_rtable(skb);
-			dst = rt_nexthop(rt, old_iph->daddr);
+		if (tpi->flags&TUNNEL_KEY) {
+			*ptr = tpi->key;
+			ptr--;
 		}
-#if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6)) {
-			const struct in6_addr *addr6;
-			struct neighbour *neigh;
-			bool do_tx_error_icmp;
-			int addr_type;
-
-			neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
-			if (neigh == NULL)
-				goto tx_error;
-
-			addr6 = (const struct in6_addr *)&neigh->primary_key;
-			addr_type = ipv6_addr_type(addr6);
-
-			if (addr_type == IPV6_ADDR_ANY) {
-				addr6 = &ipv6_hdr(skb)->daddr;
-				addr_type = ipv6_addr_type(addr6);
-			}
-
-			if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
-				do_tx_error_icmp = true;
-			else {
-				do_tx_error_icmp = false;
-				dst = addr6->s6_addr32[3];
-			}
-			neigh_release(neigh);
-			if (do_tx_error_icmp)
-				goto tx_error_icmp;
+		if (tpi->flags&TUNNEL_CSUM &&
+		    !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+			*(__sum16 *)ptr = 0;
+			*(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
+								 skb->len, 0));
 		}
-#endif
-		else
-			goto tx_error;
 	}
 
-	ttl = tiph->ttl;
-	tos = tiph->tos;
-	if (tos & 0x1) {
-		tos &= ~0x1;
-		if (skb->protocol == htons(ETH_P_IP))
-			tos = old_iph->tos;
-		else if (skb->protocol == htons(ETH_P_IPV6))
-			tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
-	}
+	return skb;
+}
 
-	rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
-				 tunnel->parms.o_key, RT_TOS(tos),
-				 tunnel->parms.link);
-	if (IS_ERR(rt)) {
-		dev->stats.tx_carrier_errors++;
-		goto tx_error;
-	}
-	tdev = rt->dst.dev;
+static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
+		       const struct iphdr *tnl_params,
+		       __be16 proto)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	struct tnl_ptk_info tpi;
 
-	if (tdev == dev) {
-		ip_rt_put(rt);
-		dev->stats.collisions++;
-		goto tx_error;
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
 	}
 
-	df = tiph->frag_off;
-	if (df)
-		mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen;
-	else
-		mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-
-	if (skb_dst(skb))
-		skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
-	if (skb->protocol == htons(ETH_P_IP)) {
-		df |= (old_iph->frag_off&htons(IP_DF));
+	tpi.flags = tunnel->parms.o_flags;
+	tpi.proto = proto;
+	tpi.key = tunnel->parms.o_key;
+	if (tunnel->parms.o_flags & TUNNEL_SEQ)
+		tunnel->o_seqno++;
+	tpi.seq = htonl(tunnel->o_seqno);
 
-		if (!skb_is_gso(skb) &&
-		    (old_iph->frag_off&htons(IP_DF)) &&
-		    mtu < ntohs(old_iph->tot_len)) {
-			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
-			ip_rt_put(rt);
-			goto tx_error;
-		}
+	/* Push GRE header. */
+	skb = gre_build_header(skb, &tpi, tunnel->hlen);
+	if (unlikely(!skb)) {
+		dev->stats.tx_dropped++;
+		return;
 	}
-#if IS_ENABLED(CONFIG_IPV6)
-	else if (skb->protocol == htons(ETH_P_IPV6)) {
-		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
-
-		if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
-			if ((tunnel->parms.iph.daddr &&
-			     !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
-			    rt6->rt6i_dst.plen == 128) {
-				rt6->rt6i_flags |= RTF_MODIFIED;
-				dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
-			}
-		}
 
-		if (!skb_is_gso(skb) &&
-		    mtu >= IPV6_MIN_MTU &&
-		    mtu < skb->len - tunnel->hlen + gre_hlen) {
-			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
-			ip_rt_put(rt);
-			goto tx_error;
-		}
-	}
-#endif
+	ip_tunnel_xmit(skb, dev, tnl_params);
+}
 
-	if (tunnel->err_count > 0) {
-		if (time_before(jiffies,
-				tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
-			tunnel->err_count--;
+static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
+			      struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+	const struct iphdr *tnl_params;
 
-			dst_link_failure(skb);
-		} else
-			tunnel->err_count = 0;
-	}
+	skb = handle_offloads(tunnel, skb);
+	if (IS_ERR(skb))
+		goto out;
 
-	max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;
-
-	if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
-	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
-		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
-		if (max_headroom > dev->needed_headroom)
-			dev->needed_headroom = max_headroom;
-		if (!new_skb) {
-			ip_rt_put(rt);
-			dev->stats.tx_dropped++;
-			dev_kfree_skb(skb);
-			return NETDEV_TX_OK;
-		}
-		if (skb->sk)
-			skb_set_owner_w(new_skb, skb->sk);
-		dev_kfree_skb(skb);
-		skb = new_skb;
-		old_iph = ip_hdr(skb);
-		/* Warning : tiph value might point to freed memory */
-	}
+	if (dev->header_ops) {
+		/* Need space for new headers */
+		if (skb_cow_head(skb, dev->needed_headroom -
+				      (tunnel->hlen + sizeof(struct iphdr))));
+			goto free_skb;
 
-	skb_push(skb, gre_hlen);
-	skb_reset_network_header(skb);
-	skb_set_transport_header(skb, sizeof(*iph));
-	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
-	skb_dst_drop(skb);
-	skb_dst_set(skb, &rt->dst);
-
-	/*
-	 *	Push down and install the IPIP header.
-	 */
+		tnl_params = (const struct iphdr *)skb->data;
 
-	iph 			=	ip_hdr(skb);
-	iph->version		=	4;
-	iph->ihl		=	sizeof(struct iphdr) >> 2;
-	iph->frag_off		=	df;
-	iph->protocol		=	IPPROTO_GRE;
-	iph->tos		=	ipgre_ecn_encapsulate(tos, old_iph, skb);
-	iph->daddr		=	fl4.daddr;
-	iph->saddr		=	fl4.saddr;
-	iph->ttl		=	ttl;
-
-	tunnel_ip_select_ident(skb, old_iph, &rt->dst);
-
-	if (ttl == 0) {
-		if (skb->protocol == htons(ETH_P_IP))
-			iph->ttl = old_iph->ttl;
-#if IS_ENABLED(CONFIG_IPV6)
-		else if (skb->protocol == htons(ETH_P_IPV6))
-			iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
-#endif
-		else
-			iph->ttl = ip4_dst_hoplimit(&rt->dst);
-	}
-
-	((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
-	((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
-				   htons(ETH_P_TEB) : skb->protocol;
-
-	if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
-		__be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4);
+		/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
+		 * to gre header.
+		 */
+		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+	} else {
+		if (skb_cow_head(skb, dev->needed_headroom))
+			goto free_skb;
 
-		if (tunnel->parms.o_flags&GRE_SEQ) {
-			++tunnel->o_seqno;
-			*ptr = htonl(tunnel->o_seqno);
-			ptr--;
-		}
-		if (tunnel->parms.o_flags&GRE_KEY) {
-			*ptr = tunnel