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/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/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,
 };