Merge branch 'geneve-consolidation'

Pravin B Shelar says:

====================
Geneve: Add support for tunnel metadata mode

Following patches adds support for Geneve tunnel metadata
mode. OVS can make use of Geneve net-device with tunnel
metadata API from kernel.

This also allows us to consolidate Geneve implementation
from two kernel modules geneve_core and geneve to single
geneve module. geneve_core module was targeted to share
Geneve encap and decap code between Geneve netdevice and
OVS Geneve tunnel implementation, Since OVS no longer
needs these API, Geneve code can be consolidated into
single geneve module.

v3-v4:
- Drop NETIF_F_NETNS_LOCAL feature.
- Fix geneve device newlink check

v2-v3:
- make tunnel medata device and regular device mutually exclusive.
- Fix Kconfig dependency for Geneve.
- Fix dst-port netlink encoding.
- drop changelink patch.

v1-v2:
- Replaced per hash table tunnel pointer (metadata enabled) with flag.
- Added support for changelink.
- Improve geneve device route lookup with more parameters.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/Kconfig

@@ -180,8 +180,8 @@ config VXLAN
 	  will be called vxlan.
 
 config GENEVE
-       tristate "Generic Network Virtualization Encapsulation netdev"
-       depends on INET && GENEVE_CORE
+       tristate "Generic Network Virtualization Encapsulation"
+       depends on INET && NET_UDP_TUNNEL
        select NET_IP_TUNNEL
        ---help---
 	  This allows one to create geneve virtual interfaces that provide

drivers/net/geneve.c

@@ -15,8 +15,10 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/hash.h>
+#include <net/dst_metadata.h>
 #include <net/rtnetlink.h>
 #include <net/geneve.h>
+#include <net/protocol.h>
 
 #define GENEVE_NETDEV_VER	"0.6"
 
@@ -32,12 +34,17 @@ static bool log_ecn_error = true;
 module_param(log_ecn_error, bool, 0644);
 MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
 
+#define GENEVE_VER 0
+#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
+
 /* per-network namespace private data for this module */
 struct geneve_net {
 	struct list_head	geneve_list;
-	struct hlist_head vni_list[VNI_HASH_SIZE];
+	struct list_head	sock_list;
 };
 
+static int geneve_net_id;
+
 /* Pseudo network device */
 struct geneve_dev {
 	struct hlist_node  hlist;	/* vni hash table */
@@ -49,9 +56,19 @@ struct geneve_dev {
 	u8                 tos;		/* TOS override */
 	struct sockaddr_in remote;	/* IPv4 address for link partner */
 	struct list_head   next;	/* geneve's per namespace list */
+	__be16		   dst_port;
+	bool		   collect_md;
 };
 
-static int geneve_net_id;
+struct geneve_sock {
+	bool			collect_md;
+	struct list_head	list;
+	struct socket		*sock;
+	struct rcu_head		rcu;
+	int			refcnt;
+	struct udp_offload	udp_offloads;
+	struct hlist_head	vni_list[VNI_HASH_SIZE];
+};
 
 static inline __u32 geneve_net_vni_hash(u8 vni[3])
 {
@@ -61,46 +78,101 @@ static inline __u32 geneve_net_vni_hash(u8 vni[3])
 	return hash_32(vnid, VNI_HASH_BITS);
 }
 
+static __be64 vni_to_tunnel_id(const __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
+#else
+	return (__force __be64)(((__force u64)vni[0] << 40) |
+				((__force u64)vni[1] << 48) |
+				((__force u64)vni[2] << 56));
+#endif
+}
+
+static struct geneve_dev *geneve_lookup(struct geneve_sock *gs,
+					__be32 addr, u8 vni[])
+{
+	struct hlist_head *vni_list_head;
+	struct geneve_dev *geneve;
+	__u32 hash;
+
+	/* Find the device for this VNI */
+	hash = geneve_net_vni_hash(vni);
+	vni_list_head = &gs->vni_list[hash];
+	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
+		if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) &&
+		    addr == geneve->remote.sin_addr.s_addr)
+			return geneve;
+	}
+	return NULL;
+}
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
 /* geneve receive/decap routine */
 static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 {
 	struct genevehdr *gnvh = geneve_hdr(skb);
-	struct geneve_dev *dummy, *geneve = NULL;
-	struct geneve_net *gn;
-	struct iphdr *iph = NULL;
+	struct metadata_dst *tun_dst = NULL;
+	struct geneve_dev *geneve = NULL;
 	struct pcpu_sw_netstats *stats;
-	struct hlist_head *vni_list_head;
-	int err = 0;
-	__u32 hash;
-
-	iph = ip_hdr(skb); /* Still outer IP header... */
+	struct iphdr *iph;
+	u8 *vni;
+	__be32 addr;
+	int err;
 
-	gn = gs->rcv_data;
+	if (gs->collect_md) {
+		static u8 zero_vni[3];
 
-	/* Find the device for this VNI */
-	hash = geneve_net_vni_hash(gnvh->vni);
-	vni_list_head = &gn->vni_list[hash];
-	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
-		if (!memcmp(gnvh->vni, dummy->vni, sizeof(dummy->vni)) &&
-		    iph->saddr == dummy->remote.sin_addr.s_addr) {
-			geneve = dummy;
-			break;
-		}
+		vni = zero_vni;
+		addr = 0;
+	} else {
+		vni = gnvh->vni;
+		iph = ip_hdr(skb); /* Still outer IP header... */
+		addr = iph->saddr;
 	}
+
+	geneve = geneve_lookup(gs, addr, vni);
 	if (!geneve)
 		goto drop;
 
+	if (ip_tunnel_collect_metadata() || gs->collect_md) {
+		__be16 flags;
+		void *opts;
+
+		flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
+			(gnvh->oam ? TUNNEL_OAM : 0) |
+			(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
+
+		tun_dst = udp_tun_rx_dst(skb, AF_INET, flags,
+					 vni_to_tunnel_id(gnvh->vni),
+					 gnvh->opt_len * 4);
+		if (!tun_dst)
+			goto drop;
+
+		/* Update tunnel dst according to Geneve options. */
+		opts = ip_tunnel_info_opts(&tun_dst->u.tun_info,
+					   gnvh->opt_len * 4);
+		memcpy(opts, gnvh->options, gnvh->opt_len * 4);
+	} else {
 		/* Drop packets w/ critical options,
 		 * since we don't support any...
 		 */
 		if (gnvh->critical)
 			goto drop;
+	}
 
 	skb_reset_mac_header(skb);
 	skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
 	skb->protocol = eth_type_trans(skb, geneve->dev);
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
+	if (tun_dst)
+		skb_dst_set(skb, &tun_dst->dst);
+
 	/* Ignore packet loops (and multicast echo) */
 	if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
 		goto drop;
@@ -128,7 +200,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
 	u64_stats_update_end(&stats->syncp);
 
 	netif_rx(skb);
-
 	return;
 drop:
 	/* Consume bad packet */
@@ -141,7 +212,6 @@ static int geneve_init(struct net_device *dev)
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
-
 	return 0;
 }
 
@@ -150,20 +220,281 @@ static void geneve_uninit(struct net_device *dev)
 	free_percpu(dev->tstats);
 }
 
+/* Callback from net/ipv4/udp.c to receive packets */
+static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct genevehdr *geneveh;
+	struct geneve_sock *gs;
+	int opts_len;
+
+	/* Need Geneve and inner Ethernet header to be present */
+	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
+		goto error;
+
+	/* Return packets with reserved bits set */
+	geneveh = geneve_hdr(skb);
+	if (unlikely(geneveh->ver != GENEVE_VER))
+		goto error;
+
+	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
+		goto error;
+
+	opts_len = geneveh->opt_len * 4;
+	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
+				 htons(ETH_P_TEB)))
+		goto drop;
+
+	gs = rcu_dereference_sk_user_data(sk);
+	if (!gs)
+		goto drop;
+
+	geneve_rx(gs, skb);
+	return 0;
+
+drop:
+	/* Consume bad packet */
+	kfree_skb(skb);
+	return 0;
+
+error:
+	/* Let the UDP layer deal with the skb */
+	return 1;
+}
+
+static struct socket *geneve_create_sock(struct net *net, bool ipv6,
+					 __be16 port)
+{
+	struct socket *sock;
+	struct udp_port_cfg udp_conf;
+	int err;
+
+	memset(&udp_conf, 0, sizeof(udp_conf));
+
+	if (ipv6) {
+		udp_conf.family = AF_INET6;
+	} else {
+		udp_conf.family = AF_INET;
+		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+	}
+
+	udp_conf.local_udp_port = port;
+
+	/* Open UDP socket */
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	return sock;
+}
+
+static void geneve_notify_add_rx_port(struct geneve_sock *gs)
+{
+	struct sock *sk = gs->sock->sk;
+	sa_family_t sa_family = sk->sk_family;
+	int err;
+
+	if (sa_family == AF_INET) {
+		err = udp_add_offload(&gs->udp_offloads);
+		if (err)
+			pr_warn("geneve: udp_add_offload failed with status %d\n",
+				err);
+	}
+}
+
+static int geneve_hlen(struct genevehdr *gh)
+{
+	return sizeof(*gh) + gh->opt_len * 4;
+}
+
+static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
+					   struct sk_buff *skb,
+					   struct udp_offload *uoff)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct genevehdr *gh, *gh2;
+	unsigned int hlen, gh_len, off_gnv;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_gnv = skb_gro_offset(skb);
+	hlen = off_gnv + sizeof(*gh);
+	gh = skb_gro_header_fast(skb, off_gnv);
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	if (gh->ver != GENEVE_VER || gh->oam)
+		goto out;
+	gh_len = geneve_hlen(gh);
+
+	hlen = off_gnv + gh_len;
+	if (skb_gro_header_hard(skb, hlen)) {
+		gh = skb_gro_header_slow(skb, hlen, off_gnv);
+		if (unlikely(!gh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		gh2 = (struct genevehdr *)(p->data + off_gnv);
+		if (gh->opt_len != gh2->opt_len ||
+		    memcmp(gh, gh2, gh_len)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, gh_len);
+	skb_gro_postpull_rcsum(skb, gh, gh_len);
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
+			       struct udp_offload *uoff)
+{
+	struct genevehdr *gh;
+	struct packet_offload *ptype;
+	__be16 type;
+	int gh_len;
+	int err = -ENOSYS;
+
+	udp_tunnel_gro_complete(skb, nhoff);
+
+	gh = (struct genevehdr *)(skb->data + nhoff);
+	gh_len = geneve_hlen(gh);
+	type = gh->proto_type;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + gh_len);
+
+	rcu_read_unlock();
+	return err;
+}
+
+/* Create new listen socket if needed */
+static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
+						bool ipv6)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_sock *gs;
+	struct socket *sock;
+	struct udp_tunnel_sock_cfg tunnel_cfg;
+	int h;
+
+	gs = kzalloc(sizeof(*gs), GFP_KERNEL);
+	if (!gs)
+		return ERR_PTR(-ENOMEM);
+
+	sock = geneve_create_sock(net, ipv6, port);
+	if (IS_ERR(sock)) {
+		kfree(gs);
+		return ERR_CAST(sock);
+	}
+
+	gs->sock = sock;
+	gs->refcnt = 1;
+	for (h = 0; h < VNI_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&gs->vni_list[h]);
+
+	/* Initialize the geneve udp offloads structure */
+	gs->udp_offloads.port = port;
+	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
+	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
+	geneve_notify_add_rx_port(gs);
+
+	/* Mark socket as an encapsulation socket */
+	tunnel_cfg.sk_user_data = gs;
+	tunnel_cfg.encap_type = 1;
+	tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
+	tunnel_cfg.encap_destroy = NULL;
+	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
+	list_add(&gs->list, &gn->sock_list);
+	return gs;
+}
+
+static void geneve_notify_del_rx_port(struct geneve_sock *gs)
+{
+	struct sock *sk = gs->sock->sk;
+	sa_family_t sa_family = sk->sk_family;
+
+	if (sa_family == AF_INET)
+		udp_del_offload(&gs->udp_offloads);
+}
+
+static void geneve_sock_release(struct geneve_sock *gs)
+{
+	if (--gs->refcnt)
+		return;
+
+	list_del(&gs->list);
+	geneve_notify_del_rx_port(gs);
+	udp_tunnel_sock_release(gs->sock);
+	kfree_rcu(gs, rcu);
+}
+
+static struct geneve_sock *geneve_find_sock(struct geneve_net *gn,
+					    __be16 dst_port)
+{
+	struct geneve_sock *gs;
+
+	list_for_each_entry(gs, &gn->sock_list, list) {
+		if (inet_sk(gs->sock->sk)->inet_sport == dst_port &&
+		    inet_sk(gs->sock->sk)->sk.sk_family == AF_INET) {
+			return gs;
+		}
+	}
+	return NULL;
+}
+
 static int geneve_open(struct net_device *dev)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct net *net = geneve->net;
-	struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
+	__u32 hash;
+
+	gs = geneve_find_sock(gn, geneve->dst_port);
+	if (gs) {
+		gs->refcnt++;
+		goto out;
+	}
 
-	gs = geneve_sock_add(net, htons(GENEVE_UDP_PORT), geneve_rx, gn,
-	                     false, false);
+	gs = geneve_socket_create(net, geneve->dst_port, false);
 	if (IS_ERR(gs))
 		return PTR_ERR(gs);
 
+out:
+	gs->collect_md = geneve->collect_md;
 	geneve->sock = gs;
 
+	hash = geneve_net_vni_hash(geneve->vni);
+	hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]);
 	return 0;
 }
 
@@ -172,74 +503,189 @@ static int geneve_stop(struct net_device *dev)
 	struct geneve_dev *geneve = netdev_priv(dev);
 	struct geneve_sock *gs = geneve->sock;
 
+	if (!hlist_unhashed(&geneve->hlist))
+		hlist_del_rcu(&geneve->hlist);
 	geneve_sock_release(gs);
-
 	return 0;
 }
 
-static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
+static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb,
+			    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
+			    bool csum)
 {
-	struct geneve_dev *geneve = netdev_priv(dev);
-	struct geneve_sock *gs = geneve->sock;
-	struct rtable *rt = NULL;
-	const struct iphdr *iip; /* interior IP header */
-	struct flowi4 fl4;
+	struct genevehdr *gnvh;
+	int min_headroom;
 	int err;
-	__be16 sport;
-	__u8 tos, ttl;
 
-	iip = ip_hdr(skb);
+	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr);
+	err = skb_cow_head(skb, min_headroom);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		goto free_rt;
+	}
 
-	skb_reset_mac_header(skb);
+	skb = udp_tunnel_handle_offloads(skb, csum);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		goto free_rt;
+	}
+
+	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
+	gnvh->ver = GENEVE_VER;
+	gnvh->opt_len = opt_len / 4;
+	gnvh->oam = !!(tun_flags & TUNNEL_OAM);
+	gnvh->critical = !!(tun_flags & TUNNEL_CRIT_OPT);
+	gnvh->rsvd1 = 0;
+	memcpy(gnvh->vni, vni, 3);
+	gnvh->proto_type = htons(ETH_P_TEB);
+	gnvh->rsvd2 = 0;
+	memcpy(gnvh->options, opt, opt_len);
+
+	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
+	return 0;
+
+free_rt:
+	ip_rt_put(rt);
+	return err;
+}
+
+static struct rtable *geneve_get_rt(struct sk_buff *skb,
+				    struct net_device *dev,
+				    struct flowi4 *fl4,
+				    struct ip_tunnel_info *info)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct rtable *rt = NULL;
+	__u8 tos;
 
-	/* TODO: port min/max limits should be configurable */
-	sport = udp_flow_src_port(dev_net(dev), skb, 0, 0, true);
+	memset(fl4, 0, sizeof(*fl4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_proto = IPPROTO_UDP;
 
+	if (info) {
+		fl4->daddr = info->key.u.ipv4.dst;
+		fl4->saddr = info->key.u.ipv4.src;
+		fl4->flowi4_tos = RT_TOS(info->key.tos);
+	} else {
 		tos = geneve->tos;
-	if (tos == 1)
+		if (tos == 1) {
+			const struct iphdr *iip = ip_hdr(skb);
+
 			tos = ip_tunnel_get_dsfield(iip, skb);
+		}
 
-	memset(&fl4, 0, sizeof(fl4));
-	fl4.flowi4_tos = RT_TOS(tos);
-	fl4.daddr = geneve->remote.sin_addr.s_addr;
-	rt = ip_route_output_key(geneve->net, &fl4);
+		fl4->flowi4_tos = RT_TOS(tos);
+		fl4->daddr = geneve->remote.sin_addr.s_addr;
+	}
+
+	rt = ip_route_output_key(geneve->net, fl4);
 	if (IS_ERR(rt)) {
-		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+		netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr);
 		dev->stats.tx_carrier_errors++;
-		goto tx_error;
+		return rt;
 	}
 	if (rt->dst.dev == dev) { /* is this necessary? */
-		netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
+		netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr);
 		dev->stats.collisions++;
-		goto rt_tx_error;
+		ip_rt_put(rt);
+		return ERR_PTR(-EINVAL);
+	}
+	return rt;
+}
+
+/* Convert 64 bit tunnel ID to 24 bit VNI. */
+static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+	vni[0] = (__force __u8)(tun_id >> 16);
+	vni[1] = (__force __u8)(tun_id >> 8);
+	vni[2] = (__force __u8)tun_id;
+#else
+	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_sock *gs = geneve->sock;
+	struct ip_tunnel_info *info = NULL;
+	struct rtable *rt = NULL;
+	struct flowi4 fl4;
+	__u8 tos, ttl;
+	__be16 sport;
+	bool udp_csum;
+	__be16 df;
+	int err;
+
+	if (geneve->collect_md) {
+		info = skb_tunnel_info(skb);
+		if (unlikely(info && info->mode != IP_TUNNEL_INFO_TX)) {
+			netdev_dbg(dev, "no tunnel metadata\n");
+			goto tx_error;
+		}
+	}
+
+	rt = geneve_get_rt(skb, dev, &fl4, info);
+	if (IS_ERR(rt)) {
+		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+		dev->stats.tx_carrier_errors++;
+		goto tx_error;
 	}
 
-	tos = ip_tunnel_ecn_encap(tos, iip, skb);
+	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	skb_reset_mac_header(skb);
+
+	if (info) {
+		const struct ip_tunnel_key *key = &info->key;
+		u8 *opts = NULL;
+		u8 vni[3];
+
+		tunnel_id_to_vni(key->tun_id, vni);
+		if (key->tun_flags & TUNNEL_GENEVE_OPT)
+			opts = ip_tunnel_info_opts(info, info->options_len);
+
+		udp_csum = !!(key->tun_flags & TUNNEL_CSUM);
+		err = geneve_build_skb(rt, skb, key->tun_flags, vni,
+				       info->options_len, opts, udp_csum);
+		if (unlikely(err))
+			goto err;
+
+		tos = key->tos;
+		ttl = key->ttl;
+		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+	} else {
+		const struct iphdr *iip; /* interior IP header */
 
+		udp_csum = false;
+		err = geneve_build_skb(rt, skb, 0, geneve->vni,
+				       0, NULL, udp_csum);
+		if (unlikely(err))
+			goto err;
+
+		iip = ip_hdr(skb);
+		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);
 		ttl = geneve->ttl;
 		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
 			ttl = 1;
-
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
-
-	/* no need to handle local destination and encap bypass...yet... */
-
-	err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr,
-	                      tos, ttl, 0, sport, htons(GENEVE_UDP_PORT), 0,
-	                      geneve->vni, 0, NULL, false,
-	                      !net_eq(geneve->net, dev_net(geneve->dev)));
-	if (err < 0)
-		ip_rt_put(rt);
+		df = 0;
+	}
+	err = udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, fl4.saddr, fl4.daddr,
+				  tos, ttl, df, sport, geneve->dst_port,
+				  !net_eq(geneve->net, dev_net(geneve->dev)),
+				  !udp_csum);
 
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
-
 	return NETDEV_TX_OK;
 
-rt_tx_error:
-	ip_rt_put(rt);
 tx_error:
-	dev->stats.tx_errors++;
 	dev_kfree_skb(skb);
+err:
+	dev->stats.tx_errors++;
 	return NETDEV_TX_OK;
 }
 
@@ -297,6 +743,7 @@ static void geneve_setup(struct net_device *dev)
 
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
+	eth_hw_addr_random(dev);
 }
 
 static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
@@ -304,6 +751,8 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_REMOTE]		= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
 	[IFLA_GENEVE_TTL]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_TOS]		= { .type = NLA_U8 },
+	[IFLA_GENEVE_PORT]		= { .type = NLA_U16 },
+	[IFLA_GENEVE_COLLECT_METADATA]	= { .type = NLA_FLAG },
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -329,68 +778,117 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
-static int geneve_newlink(struct net *net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[])
+static struct geneve_dev *geneve_find_dev(struct geneve_net *gn,
+					  __be16 dst_port,
+					  __be32 rem_addr,
+					  u8 vni[],
+					  bool *tun_on_same_port,
+					  bool *tun_collect_md)
+{
+	struct geneve_dev *geneve, *t;
+
+	*tun_on_same_port = false;
+	*tun_collect_md = false;
+	t = NULL;
+	list_for_each_entry(geneve, &gn->geneve_list, next) {
+		if (geneve->dst_port == dst_port) {
+			*tun_collect_md = geneve->collect_md;
+			*tun_on_same_port = true;
+		}
+		if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) &&
+		    rem_addr == geneve->remote.sin_addr.s_addr &&
+		    dst_port == geneve->dst_port)
+			t = geneve;
+	}
+	return t;
+}
+
+static int geneve_configure(struct net *net, struct net_device *dev,
+			    __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos,
+			    __u16 dst_port, bool metadata)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	struct geneve_dev *dummy, *geneve = netdev_priv(dev);
-	struct hlist_head *vni_list_head;
-	struct sockaddr_in remote;	/* IPv4 address for link partner */
-	__u32 vni, hash;
+	struct geneve_dev *t, *geneve = netdev_priv(dev);
+	bool tun_collect_md, tun_on_same_port;
 	int err;
 
-	if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
+	if (metadata) {
+		if (rem_addr || vni || tos || ttl)
 			return -EINVAL;
+	}
 
 	geneve->net = net;
 	geneve->dev = dev;
 
-	vni = nla_get_u32(data[IFLA_GENEVE_ID]);
 	geneve->vni[0] = (vni & 0x00ff0000) >> 16;
 	geneve->vni[1] = (vni & 0x0000ff00) >> 8;
 	geneve->vni[2] =  vni & 0x000000ff;
 
-	geneve->remote.sin_addr.s_addr =
-		nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);
+	geneve->remote.sin_addr.s_addr = rem_addr;
 	if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr)))
 		return -EINVAL;
 
-	remote = geneve->remote;
-	hash = geneve_net_vni_hash(geneve->vni);
-	vni_list_head = &gn->vni_list[hash];
-	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
-		if (!memcmp(geneve->vni, dummy->vni, sizeof(dummy->vni)) &&
-		    !memcmp(&remote, &dummy->remote, sizeof(dummy->remote)))
+	geneve->ttl = ttl;
+	geneve->tos = tos;
+	geneve->dst_port = htons(dst_port);
+	geneve->collect_md = metadata;
+
+	t = geneve_find_dev(gn, htons(dst_port), rem_addr, geneve->vni,
+			    &tun_on_same_port, &tun_collect_md);
+	if (t)
 		return -EBUSY;
-	}
 
-	if (tb[IFLA_ADDRESS] == NULL)
-		eth_hw_addr_random(dev);
+	if (metadata) {
+		if (tun_on_same_port)
+			return -EPERM;
+	} else {
+		if (tun_collect_md)
+			return -EPERM;
+	}
 
 	err = register_netdevice(dev);
 	if (err)
 		return err;
 
+	list_add(&geneve->next, &gn->geneve_list);
+	return 0;
+}
+
+static int geneve_newlink(struct net *net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	__u16 dst_port = GENEVE_UDP_PORT;
+	__u8 ttl = 0, tos = 0;
+	bool metadata = false;
+	__be32 rem_addr;
+	__u32 vni;
+
+	if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
+		return -EINVAL;
+
+	vni = nla_get_u32(data[IFLA_GENEVE_ID]);
+	rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);
+
 	if (data[IFLA_GENEVE_TTL])
-		geneve->ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
+		ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
 
 	if (data[IFLA_GENEVE_TOS])
-		geneve->tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
+		tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
 
-	list_add(&geneve->next, &gn->geneve_list);
+	if (data[IFLA_GENEVE_PORT])
+		dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]);
 
-	hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]);
+	if (data[IFLA_GENEVE_COLLECT_METADATA])
+		metadata = true;
 
-	return 0;
+	return geneve_configure(net, dev, rem_addr, vni,
+				ttl, tos, dst_port, metadata);
 }
 
 static void geneve_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct geneve_dev *geneve = netdev_priv(dev);
 
-	if (!hlist_unhashed(&geneve->hlist))
-		hlist_del_rcu(&geneve->hlist);
-
 	list_del(&geneve->next);
 	unregister_netdevice_queue(dev, head);
 }
@@ -401,6 +899,8 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
 		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
+		nla_total_size(sizeof(__u16)) +  /* IFLA_GENEVE_PORT */
+		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
 		0;
 }
 
@@ -421,6 +921,14 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
 		goto nla_put_failure;
 
+	if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port)))
+		goto nla_put_failure;
+
+	if (geneve->collect_md) {
+		if (nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA))
+			goto nla_put_failure;
+	}
+
 	return 0;
 
 nla_put_failure:
@@ -440,16 +948,34 @@ static struct rtnl_link_ops geneve_link_ops __read_mostly = {
 	.fill_info	= geneve_fill_info,
 };
 
+struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
+					u8 name_assign_type, u16 dst_port)
+{
+	struct nlattr *tb[IFLA_MAX + 1];
+	struct net_device *dev;
+	int err;
+
+	memset(tb, 0, sizeof(tb));
+	dev = rtnl_create_link(net, name, name_assign_type,
+			       &geneve_link_ops, tb);
+	if (IS_ERR(dev))
+		return dev;
+
+	err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true);
+	if (err) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
+	return dev;
+}
+EXPORT_SYMBOL_GPL(geneve_dev_create_fb);
+
 static __net_init int geneve_init_net(struct net *net)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	unsigned int h;
 
 	INIT_LIST_HEAD(&gn->geneve_list);
-
-	for (h = 0; h < VNI_HASH_SIZE; ++h)
-		INIT_HLIST_HEAD(&gn->vni_list[h]);
-
+	INIT_LIST_HEAD(&gn->sock_list);
 	return 0;
 }
 

drivers/net/vxlan.c

@@ -1264,36 +1264,13 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	}
 
 	if (vxlan_collect_metadata(vs)) {
-		tun_dst = metadata_dst_alloc(sizeof(*md), GFP_ATOMIC);
+		tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY,
+					 cpu_to_be64(vni >> 8), sizeof(*md));
+
 		if (!tun_dst)
 			goto drop;
 
 		info = &tun_dst->u.tun_info;
-		if (vxlan_get_sk_family(vs) == AF_INET) {
-			const struct iphdr *iph = ip_hdr(skb);
-
-			info->key.u.ipv4.src = iph->saddr;
-			info->key.u.ipv4.dst = iph->daddr;
-			info->key.tos = iph->tos;
-			info->key.ttl = iph->ttl;
-		} else {
-			const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-
-			info->key.u.ipv6.src = ip6h->saddr;
-			info->key.u.ipv6.dst = ip6h->daddr;
-			info->key.tos = ipv6_get_dsfield(ip6h);
-			info->key.ttl = ip6h->hop_limit;
-		}
-
-		info->key.tp_src = udp_hdr(skb)->source;
-		info->key.tp_dst = udp_hdr(skb)->dest;
-
-		info->mode = IP_TUNNEL_INFO_RX;
-		info->key.tun_flags = TUNNEL_KEY;
-		info->key.tun_id = cpu_to_be64(vni >> 8);
-		if (udp_hdr(skb)->check != 0)
-			info->key.tun_flags |= TUNNEL_CSUM;
-
 		md = ip_tunnel_info_opts(info, sizeof(*md));
 	} else {
 		memset(md, 0, sizeof(*md));

include/net/dst_metadata.h

@@ -48,4 +48,65 @@ static inline bool skb_valid_dst(const struct sk_buff *skb)
 struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags);
 struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags);
 
+static inline struct metadata_dst *tun_rx_dst(__be16 flags,
+					      __be64 tunnel_id, int md_size)
+{
+	struct metadata_dst *tun_dst;
+	struct ip_tunnel_info *info;
+
+	tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC);
+	if (!tun_dst)
+		return NULL;
+
+	info = &tun_dst->u.tun_info;
+	info->mode = IP_TUNNEL_INFO_RX;
+	info->key.tun_flags = flags;
+	info->key.tun_id = tunnel_id;
+	info->key.tp_src = 0;
+	info->key.tp_dst = 0;
+	return tun_dst;
+}
+
+static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
+						 __be16 flags,
+						 __be64 tunnel_id,
+						 int md_size)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct metadata_dst *tun_dst;
+	struct ip_tunnel_info *info;
+
+	tun_dst = tun_rx_dst(flags, tunnel_id, md_size);
+	if (!tun_dst)
+		return NULL;
+
+	info = &tun_dst->u.tun_info;
+	info->key.u.ipv4.src = iph->saddr;
+	info->key.u.ipv4.dst = iph->daddr;
+	info->key.tos = iph->tos;
+	info->key.ttl = iph->ttl;
+	return tun_dst;
+}
+
+static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
+						 __be16 flags,
+						 __be64 tunnel_id,
+						 int md_size)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct metadata_dst *tun_dst;
+	struct ip_tunnel_info *info;
+
+	tun_dst = tun_rx_dst(flags, tunnel_id, md_size);
+	if (!tun_dst)
+		return NULL;
+
+	info = &tun_dst->u.tun_info;
+	info->key.u.ipv6.src = ip6h->saddr;
+	info->key.u.ipv6.dst = ip6h->daddr;
+	info->key.tos = ipv6_get_dsfield(ip6h);
+	info->key.ttl = ip6h->hop_limit;
+	return tun_dst;
+}
+
 #endif /* __NET_DST_METADATA_H */

include/net/geneve.h

@@ -62,40 +62,9 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
-static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
-{
-	return (struct genevehdr *)(udp_hdr(skb) + 1);
-}
-
 #ifdef CONFIG_INET
-struct geneve_sock;
-
-typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
-
-struct geneve_sock {
-	struct list_head	list;
-	geneve_rcv_t		*rcv;
-	void			*rcv_data;
-	struct socket		*sock;
-	struct rcu_head		rcu;
-	int			refcnt;
-	struct udp_offload	udp_offloads;
-};
-
-#define GENEVE_VER 0
-#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
-
-struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
-				    geneve_rcv_t *rcv, void *data,
-				    bool no_share, bool ipv6);
-
-void geneve_sock_release(struct geneve_sock *vs);
-
-int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
-		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
-		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
-		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool csum, bool xnet);
+struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
+					u8 name_assign_type, u16 dst_port);
 #endif /*ifdef CONFIG_INET */
 
 #endif /*ifdef__NET_GENEVE_H */

include/net/udp_tunnel.h

@@ -93,6 +93,10 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
 
 void udp_tunnel_sock_release(struct socket *sock);
 
+struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,
+				    __be16 flags, __be64 tunnel_id,
+				    int md_size);
+
 static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb,
 							 bool udp_csum)
 {

include/uapi/linux/if_link.h

@@ -410,6 +410,8 @@ enum {
 	IFLA_GENEVE_REMOTE,
 	IFLA_GENEVE_TTL,
 	IFLA_GENEVE_TOS,
+	IFLA_GENEVE_PORT,	/* destination port */
+	IFLA_GENEVE_COLLECT_METADATA,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)

net/ipv4/Kconfig

@@ -331,20 +331,6 @@ config NET_FOU_IP_TUNNELS
 	  When this option is enabled IP tunnels can be configured to use
 	  FOU or GUE encapsulation.
 
-config GENEVE_CORE
-	tristate "Generic Network Virtualization Encapsulation library"
-	depends on INET
-	select NET_UDP_TUNNEL
-	---help---
-	This allows one to create Geneve virtual interfaces that provide
-	Layer 2 Networks over Layer 3 Networks. Geneve is often used
-	to tunnel virtual network infrastructure in virtualized environments.
-	For more information see:
-	  http://tools.ietf.org/html/draft-gross-geneve-01
-
-	  To compile this driver as a module, choose M here: the module
-
-
 config INET_AH
 	tristate "IP: AH transformation"
 	select XFRM_ALGO

net/ipv4/Makefile

@@ -57,7 +57,6 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
 obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
-obj-$(CONFIG_GENEVE_CORE) += geneve_core.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
 		      xfrm4_output.o xfrm4_protocol.o

net/ipv4/geneve_core.c

-/*
- * Geneve: Generic Network Virtualization Encapsulation
- *
- * Copyright (c) 2014 Nicira, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/slab.h>
-#include <linux/skbuff.h>
-#include <linux/list.h>
-#include <linux/netdevice.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
-#include <linux/igmp.h>
-#include <linux/etherdevice.h>
-#include <linux/if_ether.h>
-#include <linux/if_vlan.h>
-#include <linux/ethtool.h>
-#include <linux/mutex.h>
-#include <net/arp.h>
-#include <net/ndisc.h>
-#include <net/ip.h>
-#include <net/ip_tunnels.h>
-#include <net/icmp.h>
-#include <net/udp.h>
-#include <net/rtnetlink.h>
-#include <net/route.h>
-#include <net/dsfield.h>
-#include <net/inet_ecn.h>
-#include <net/net_namespace.h>
-#include <net/netns/generic.h>
-#include <net/geneve.h>
-#include <net/protocol.h>
-#include <net/udp_tunnel.h>
-#if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/addrconf.h>
-#include <net/ip6_tunnel.h>
-#include <net/ip6_checksum.h>
-#endif
-
-/* Protects sock_list and refcounts. */
-static DEFINE_MUTEX(geneve_mutex);
-
-/* per-network namespace private data for this module */
-struct geneve_net {
-	struct list_head	sock_list;
-};
-
-static int geneve_net_id;
-
-static struct geneve_sock *geneve_find_sock(struct net *net,
-					    sa_family_t family, __be16 port)
-{
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	struct geneve_sock *gs;
-
-	list_for_each_entry(gs, &gn->sock_list, list) {
-		if (inet_sk(gs->sock->sk)->inet_sport == port &&
-		    inet_sk(gs->sock->sk)->sk.sk_family == family)
-			return gs;
-	}
-
-	return NULL;
-}
-
-static void geneve_build_header(struct genevehdr *geneveh,
-				__be16 tun_flags, u8 vni[3],
-				u8 options_len, u8 *options)
-{
-	geneveh->ver = GENEVE_VER;
-	geneveh->opt_len = options_len / 4;
-	geneveh->oam = !!(tun_flags & TUNNEL_OAM);
-	geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT);
-	geneveh->rsvd1 = 0;
-	memcpy(geneveh->vni, vni, 3);
-	geneveh->proto_type = htons(ETH_P_TEB);
-	geneveh->rsvd2 = 0;
-
-	memcpy(geneveh->options, options, options_len);
-}
-
-/* Transmit a fully formatted Geneve frame.
- *
- * When calling this function. The skb->data should point
- * to the geneve header which is fully formed.
- *
- * This function will add other UDP tunnel headers.
- */
-int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
-		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
-		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
-		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool csum, bool xnet)
-{
-	struct genevehdr *gnvh;
-	int min_headroom;
-	int err;
-
-	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
-			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
-			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
-
-	err = skb_cow_head(skb, min_headroom);
-	if (unlikely(err)) {
-		kfree_skb(skb);
-		return err;
-	}
-
-	skb = vlan_hwaccel_push_inside(skb);
-	if (unlikely(!skb))
-		return -ENOMEM;
-
-	skb = udp_tunnel_handle_offloads(skb, csum);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len);
-	geneve_build_header(gnvh, tun_flags, vni, opt_len, opt);
-
-	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
-
-	return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst,
-				   tos, ttl, df, src_port, dst_port, xnet,
-				   !csum);
-}
-EXPORT_SYMBOL_GPL(geneve_xmit_skb);
-
-static int geneve_hlen(struct genevehdr *gh)
-{
-	return sizeof(*gh) + gh->opt_len * 4;
-}
-
-static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
-					   struct sk_buff *skb,
-					   struct udp_offload *uoff)
-{
-	struct sk_buff *p, **pp = NULL;
-	struct genevehdr *gh, *gh2;
-	unsigned int hlen, gh_len, off_gnv;
-	const struct packet_offload *ptype;
-	__be16 type;
-	int flush = 1;
-
-	off_gnv = skb_gro_offset(skb);
-	hlen = off_gnv + sizeof(*gh);
-	gh = skb_gro_header_fast(skb, off_gnv);
-	if (skb_gro_header_hard(skb, hlen)) {
-		gh = skb_gro_header_slow(skb, hlen, off_gnv);
-		if (unlikely(!gh))
-			goto out;
-	}
-
-	if (gh->ver != GENEVE_VER || gh->oam)
-		goto out;
-	gh_len = geneve_hlen(gh);
-
-	hlen = off_gnv + gh_len;
-	if (skb_gro_header_hard(skb, hlen)) {
-		gh = skb_gro_header_slow(skb, hlen, off_gnv);
-		if (unlikely(!gh))
-			goto out;
-	}
-
-	flush = 0;
-
-	for (p = *head; p; p = p->next) {
-		if (!NAPI_GRO_CB(p)->same_flow)
-			continue;
-
-		gh2 = (struct genevehdr *)(p->data + off_gnv);
-		if (gh->opt_len != gh2->opt_len ||
-		    memcmp(gh, gh2, gh_len)) {
-			NAPI_GRO_CB(p)->same_flow = 0;
-			continue;
-		}
-	}
-
-	type = gh->proto_type;
-
-	rcu_read_lock();
-	ptype = gro_find_receive_by_type(type);
-	if (!ptype) {
-		flush = 1;
-		goto out_unlock;
-	}
-
-	skb_gro_pull(skb, gh_len);
-	skb_gro_postpull_rcsum(skb, gh, gh_len);
-	pp = ptype->callbacks.gro_receive(head, skb);
-
-out_unlock:
-	rcu_read_unlock();
-out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-
-	return pp;
-}
-
-static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
-			       struct udp_offload *uoff)
-{
-	struct genevehdr *gh;
-	struct packet_offload *ptype;
-	__be16 type;
-	int gh_len;
-	int err = -ENOSYS;
-
-	udp_tunnel_gro_complete(skb, nhoff);
-
-	gh = (struct genevehdr *)(skb->data + nhoff);
-	gh_len = geneve_hlen(gh);
-	type = gh->proto_type;
-
-	rcu_read_lock();
-	ptype = gro_find_complete_by_type(type);
-	if (ptype)
-		err = ptype->callbacks.gro_complete(skb, nhoff + gh_len);
-
-	rcu_read_unlock();
-	return err;
-}
-
-static void geneve_notify_add_rx_port(struct geneve_sock *gs)
-{
-	struct sock *sk = gs->sock->sk;
-	sa_family_t sa_family = sk->sk_family;
-	int err;
-
-	if (sa_family == AF_INET) {
-		err = udp_add_offload(&gs->udp_offloads);
-		if (err)
-			pr_warn("geneve: udp_add_offload failed with status %d\n",
-				err);
-	}
-}
-
-static void geneve_notify_del_rx_port(struct geneve_sock *gs)
-{
-	struct sock *sk = gs->sock->sk;
-	sa_family_t sa_family = sk->sk_family;
-
-	if (sa_family == AF_INET)
-		udp_del_offload(&gs->udp_offloads);
-}
-
-/* Callback from net/ipv4/udp.c to receive packets */
-static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
-{
-	struct genevehdr *geneveh;
-	struct geneve_sock *gs;
-	int opts_len;
-
-	/* Need Geneve and inner Ethernet header to be present */
-	if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
-		goto error;
-
-	/* Return packets with reserved bits set */
-	geneveh = geneve_hdr(skb);
-
-	if (unlikely(geneveh->ver != GENEVE_VER))
-		goto error;
-
-	if (unlikely(geneveh->proto_type != htons(ETH_P_TEB)))
-		goto error;
-
-	opts_len = geneveh->opt_len * 4;
-	if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len,
-				 htons(ETH_P_TEB)))
-		goto drop;
-
-	gs = rcu_dereference_sk_user_data(sk);
-	if (!gs)
-		goto drop;
-
-	gs->rcv(gs, skb);
-	return 0;
-
-drop:
-	/* Consume bad packet */
-	kfree_skb(skb);
-	return 0;
-
-error:
-	/* Let the UDP layer deal with the skb */
-	return 1;
-}
-
-static struct socket *geneve_create_sock(struct net *net, bool ipv6,
-					 __be16 port)
-{
-	struct socket *sock;
-	struct udp_port_cfg udp_conf;
-	int err;
-
-	memset(&udp_conf, 0, sizeof(udp_conf));
-
-	if (ipv6) {
-		udp_conf.family = AF_INET6;
-	} else {
-		udp_conf.family = AF_INET;
-		udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
-	}
-
-	udp_conf.local_udp_port = port;
-
-	/* Open UDP socket */
-	err = udp_sock_create(net, &udp_conf, &sock);
-	if (err < 0)
-		return ERR_PTR(err);
-
-	return sock;
-}
-
-/* Create new listen socket if needed */
-static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
-						geneve_rcv_t *rcv, void *data,
-						bool ipv6)
-{
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	struct geneve_sock *gs;
-	struct socket *sock;
-	struct udp_tunnel_sock_cfg tunnel_cfg;
-
-	gs = kzalloc(sizeof(*gs), GFP_KERNEL);
-	if (!gs)
-		return ERR_PTR(-ENOMEM);
-
-	sock = geneve_create_sock(net, ipv6, port);
-	if (IS_ERR(sock)) {
-		kfree(gs);
-		return ERR_CAST(sock);
-	}
-
-	gs->sock = sock;
-	gs->refcnt = 1;
-	gs->rcv = rcv;
-	gs->rcv_data = data;
-
-	/* Initialize the geneve udp offloads structure */
-	gs->udp_offloads.port = port;
-	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
-	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
-	geneve_notify_add_rx_port(gs);
-
-	/* Mark socket as an encapsulation socket */
-	tunnel_cfg.sk_user_data = gs;
-	tunnel_cfg.encap_type = 1;
-	tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
-	tunnel_cfg.encap_destroy = NULL;
-	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
-
-	list_add(&gs->list, &gn->sock_list);
-
-	return gs;
-}
-
-struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
-				    geneve_rcv_t *rcv, void *data,
-				    bool no_share, bool ipv6)
-{
-	struct geneve_sock *gs;
-
-	mutex_lock(&geneve_mutex);
-
-	gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
-	if (gs) {
-		if (!no_share && gs->rcv == rcv)
-			gs->refcnt++;
-		else
-			gs = ERR_PTR(-EBUSY);
-	} else {
-		gs = geneve_socket_create(net, port, rcv, data, ipv6);
-	}
-
-	mutex_unlock(&geneve_mutex);
-
-	return gs;
-}
-EXPORT_SYMBOL_GPL(geneve_sock_add);
-
-void geneve_sock_release(struct geneve_sock *gs)
-{
-	mutex_lock(&geneve_mutex);
-
-	if (--gs->refcnt)
-		goto unlock;
-
-	list_del(&gs->list);
-	geneve_notify_del_rx_port(gs);
-	udp_tunnel_sock_release(gs->sock);
-	kfree_rcu(gs, rcu);
-
-unlock:
-	mutex_unlock(&geneve_mutex);
-}
-EXPORT_SYMBOL_GPL(geneve_sock_release);
-
-static __net_init int geneve_init_net(struct net *net)
-{
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
-
-	INIT_LIST_HEAD(&gn->sock_list);
-
-	return 0;
-}
-
-static struct pernet_operations geneve_net_ops = {
-	.init = geneve_init_net,
-	.id   = &geneve_net_id,
-	.size = sizeof(struct geneve_net),
-};
-
-static int __init geneve_init_module(void)
-{
-	int rc;
-
-	rc = register_pernet_subsys(&geneve_net_ops);
-	if (rc)
-		return rc;
-
-	pr_info("Geneve core logic\n");
-
-	return 0;
-}
-module_init(geneve_init_module);
-
-static void __exit geneve_cleanup_module(void)
-{
-	unregister_pernet_subsys(&geneve_net_ops);
-}
-module_exit(geneve_cleanup_module);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>");
-MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic");

net/ipv4/ip_gre.c

@@ -400,25 +400,14 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 	if (tunnel) {
 		skb_pop_mac_header(skb);
 		if (tunnel->collect_md) {
-			struct ip_tunnel_info *info;
+			__be16 flags;
+			__be64 tun_id;
 
-			tun_dst = metadata_dst_alloc(0, GFP_ATOMIC);
+			flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY);
+			tun_id = key_to_tunnel_id(tpi->key);
+			tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0);
 			if (!tun_dst)
 				return PACKET_REJECT;
-
-			info = &tun_dst->u.tun_info;
-			info->key.u.ipv4.src = iph->saddr;
-			info->key.u.ipv4.dst = iph->daddr;
-			info->key.tos = iph->tos;
-			info->key.ttl = iph->ttl;
-
-			info->mode = IP_TUNNEL_INFO_RX;
-			info->key.tun_flags = tpi->flags &
-					      (TUNNEL_CSUM | TUNNEL_KEY);
-			info->key.tun_id = key_to_tunnel_id(tpi->key);
-
-			info->key.tp_src = 0;
-			info->key.tp_dst = 0;
 		}
 
 		ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error);

net/ipv4/udp_tunnel.c

@@ -4,9 +4,10 @@
 #include <linux/udp.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <net/dst_metadata.h>
+#include <net/net_namespace.h>
 #include <net/udp.h>
 #include <net/udp_tunnel.h>
-#include <net/net_namespace.h>
 
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
@@ -103,4 +104,26 @@ void udp_tunnel_sock_release(struct socket *sock)
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_sock_release);
 
+struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb,  unsigned short family,
+				    __be16 flags, __be64 tunnel_id, int md_size)
+{
+	struct metadata_dst *tun_dst;
+	struct ip_tunnel_info *info;
+
+	if (family == AF_INET)
+		tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size);
+	else
+		tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size);
+	if (!tun_dst)
+		return NULL;
+
+	info = &tun_dst->u.tun_info;
+	info->key.tp_src = udp_hdr(skb)->source;
+	info->key.tp_dst = udp_hdr(skb)->dest;
+	if (udp_hdr(skb)->check)
+		info->key.tun_flags |= TUNNEL_CSUM;
+	return tun_dst;
+}
+EXPORT_SYMBOL_GPL(udp_tun_rx_dst);
+
 MODULE_LICENSE("GPL");

net/openvswitch/Kconfig

@@ -70,7 +70,7 @@ config OPENVSWITCH_VXLAN
 config OPENVSWITCH_GENEVE
 	tristate "Open vSwitch Geneve tunneling support"
 	depends on OPENVSWITCH
-	depends on GENEVE_CORE
+	depends on GENEVE
 	default OPENVSWITCH
 	---help---
 	  If you say Y here, then the Open vSwitch will be able create geneve vport.

net/openvswitch/vport-geneve.c

@@ -26,95 +26,44 @@
 
 #include "datapath.h"
 #include "vport.h"
+#include "vport-netdev.h"
 
 static struct vport_ops ovs_geneve_vport_ops;
-
 /**
  * struct geneve_port - Keeps track of open UDP ports
- * @gs: The socket created for this port number.
- * @name: vport name.
+ * @dst_port: destination port.
  */
 struct geneve_port {
-	struct geneve_sock *gs;
-	char name[IFNAMSIZ];
+	u16 port_no;
 };
 
-static LIST_HEAD(geneve_ports);
-
 static inline struct geneve_port *geneve_vport(const struct vport *vport)
 {
 	return vport_priv(vport);
 }
 
-/* Convert 64 bit tunnel ID to 24 bit VNI. */
-static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
-{
-#ifdef __BIG_ENDIAN
-	vni[0] = (__force __u8)(tun_id >> 16);
-	vni[1] = (__force __u8)(tun_id >> 8);
-	vni[2] = (__force __u8)tun_id;
-#else
-	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
-	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
-	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
-#endif
-}
-
-/* Convert 24 bit VNI to 64 bit tunnel ID. */
-static __be64 vni_to_tunnel_id(const __u8 *vni)
-{
-#ifdef __BIG_ENDIAN
-	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
-#else
-	return (__force __be64)(((__force u64)vni[0] << 40) |
-				((__force u64)vni[1] << 48) |
-				((__force u64)vni[2] << 56));
-#endif
-}
-
-static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
-{
-	struct vport *vport = gs->rcv_data;
-	struct genevehdr *geneveh = geneve_hdr(skb);
-	int opts_len;
-	struct ip_tunnel_info tun_info;
-	__be64 key;
-	__be16 flags;
-
-	opts_len = geneveh->opt_len * 4;
-
-	flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
-		(udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
-		(geneveh->oam ? TUNNEL_OAM : 0) |
-		(geneveh->critical ? TUNNEL_CRIT_OPT : 0);
-
-	key = vni_to_tunnel_id(geneveh->vni);
-
-	ip_tunnel_info_init(&tun_info, ip_hdr(skb),
-			    udp_hdr(skb)->source, udp_hdr(skb)->dest,
-			    key, flags, geneveh->options, opts_len);
-
-	ovs_vport_receive(vport, skb, &tun_info);
-}
-
 static int geneve_get_options(const struct vport *vport,
 			      struct sk_buff *skb)
 {
 	struct geneve_port *geneve_port = geneve_vport(vport);
-	struct inet_sock *sk = inet_sk(geneve_port->gs->sock->sk);
 
-	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(sk->inet_sport)))
+	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, geneve_port->port_no))
 		return -EMSGSIZE;
 	return 0;
 }
 
-static void geneve_tnl_destroy(struct vport *vport)
+static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
+				      struct ip_tunnel_info *egress_tun_info)
 {
 	struct geneve_port *geneve_port = geneve_vport(vport);
+	struct net *net = ovs_dp_get_net(vport->dp);
+	__be16 dport = htons(geneve_port->port_no);
+	__be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
 
-	geneve_sock_release(geneve_port->gs);
-
-	ovs_vport_deferred_free(vport);
+	return ovs_tunnel_get_egress_info(egress_tun_info,
+					  ovs_dp_get_net(vport->dp),
+					  OVS_CB(skb)->egress_tun_info,
+					  IPPROTO_UDP, skb->mark, sport, dport);
 }
 
 static struct vport *geneve_tnl_create(const struct vport_parms *parms)
@@ -122,11 +71,11 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms)
 	struct net *net = ovs_dp_get_net(parms->dp);
 	struct nlattr *options = parms->options;
 	struct geneve_port *geneve_port;
-	struct geneve_sock *gs;
+	struct net_device *dev;
 	struct vport *vport;
 	struct nlattr *a;
-	int err;
 	u16 dst_port;
+	int err;
 
 	if (!options) {
 		err = -EINVAL;
@@ -148,104 +97,40 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms)
 		return vport;
 
 	geneve_port = geneve_vport(vport);
-	strncpy(geneve_port->name, parms->name, IFNAMSIZ);
+	geneve_port->port_no = dst_port;
 
-	gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0);
-	if (IS_ERR(gs)) {
+	rtnl_lock();
+	dev = geneve_dev_create_fb(net, parms->name, NET_NAME_USER, dst_port);
+	if (IS_ERR(dev)) {
+		rtnl_unlock();
 		ovs_vport_free(vport);
-		return (void *)gs;
+		return ERR_CAST(dev);
 	}
-	geneve_port->gs = gs;
 
+	dev_change_flags(dev, dev->flags | IFF_UP);
+	rtnl_unlock();
 	return vport;
 error:
 	return ERR_PTR(err);
 }
 
-static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
-{
-	const struct ip_tunnel_key *tun_key;
-	struct ip_tunnel_info *tun_info;
-	struct net *net = ovs_dp_get_net(vport->dp);
-	struct geneve_port *geneve_port = geneve_vport(vport);
-	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
-	__be16 sport;
-	struct rtable *rt;
-	struct flowi4 fl;
-	u8 vni[3], opts_len, *opts;
-	__be16 df;
-	int err;
-
-	tun_info = OVS_CB(skb)->egress_tun_info;
-	if (unlikely(!tun_info)) {
-		err = -EINVAL;
-		goto error;
-	}
-
-	tun_key = &tun_info->key;
-	rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP);
-	if (IS_ERR(rt)) {
-		err = PTR_ERR(rt);
-		goto error;
-	}
-
-	df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
-	sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
-	tunnel_id_to_vni(tun_key->tun_id, vni);
-	skb->ignore_df = 1;
-
-	if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) {
-		opts = (u8 *)tun_info->options;
-		opts_len = tun_info->options_len;
-	} else {
-		opts = NULL;
-		opts_len = 0;
-	}
-
-	err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
-			      tun_key->u.ipv4.dst, tun_key->tos,
-			      tun_key->ttl, df, sport, dport,
-			      tun_key->tun_flags, vni, opts_len, opts,
-			      !!(tun_key->tun_flags & TUNNEL_CSUM), false);
-	if (err < 0)
-		ip_rt_put(rt);
-	return err;
-
-error:
-	kfree_skb(skb);
-	return err;
-}
-
-static const char *geneve_get_name(const struct vport *vport)
+static struct vport *geneve_create(const struct vport_parms *parms)
 {
-	struct geneve_port *geneve_port = geneve_vport(vport);
-
-	return geneve_port->name;
-}
+	struct vport *vport;
 
-static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb,
-				      struct ip_tunnel_info *egress_tun_info)
-{
-	struct geneve_port *geneve_port = geneve_vport(vport);
-	struct net *net = ovs_dp_get_net(vport->dp);
-	__be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
-	__be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+	vport = geneve_tnl_create(parms);
+	if (IS_ERR(vport))
+		return vport;
 
-	/* Get tp_src and tp_dst, refert to geneve_build_header().
-	 */
-	return ovs_tunnel_get_egress_info(egress_tun_info,
-					  ovs_dp_get_net(vport->dp),
-					  OVS_CB(skb)->egress_tun_info,
-					  IPPROTO_UDP, skb->mark, sport, dport);
+	return ovs_netdev_link(vport, parms->name);
 }
 
 static struct vport_ops ovs_geneve_vport_ops = {
 	.type		= OVS_VPORT_TYPE_GENEVE,
-	.create		= geneve_tnl_create,
-	.destroy	= geneve_tnl_destroy,
-	.get_name	= geneve_get_name,
+	.create		= geneve_create,
+	.destroy	= ovs_netdev_tunnel_destroy,
 	.get_options	= geneve_get_options,
-	.send		= geneve_tnl_send,
+	.send		= ovs_netdev_send,
 	.owner          = THIS_MODULE,
 	.get_egress_tun_info	= geneve_get_egress_tun_info,
 };