Commit dc3d807d authored by David S. Miller's avatar David S. Miller
Browse files

openvswitch: gre tunneling support. 



Pravin B Shelar says:

====================
Following patch series adds support for gre tunneling.
First six patches extend kernel gre and ip_tunnel modules
api so that there is more code sharing between gre modules
and ovs. Rest of patches adds ovs tunneling infrastructre
and gre protocol vport.

V2 fixes two patches according to comments from Jesse.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents ac8025a6 aa310701

drivers/net/vxlan.c

+8 −24
Original line number Diff line number Diff line
@@ -1021,7 +1021,6 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
	struct vxlan_dev *vxlan = netdev_priv(dev);

	struct rtable *rt;

	const struct iphdr *old_iph;

	struct iphdr *iph;

	struct vxlanhdr *vxh;

	struct udphdr *uh;

	struct flowi4 fl4;
@@ -1030,6 +1029,7 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
        u32 vni;

	__be16 df = 0;

	__u8 tos, ttl;

	int err;



	dst_port = rdst->remote_port ? rdst->remote_port : vxlan->dst_port;

	vni = rdst->remote_vni;
@@ -1097,13 +1097,6 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
		vxlan_encap_bypass(skb, vxlan, dst_vxlan);

		return NETDEV_TX_OK;

	}



	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);



	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));

	vxh->vx_flags = htonl(VXLAN_FLAGS);

	vxh->vx_vni = htonl(vni << 8);
@@ -1118,27 +1111,18 @@ static netdev_tx_t vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
	uh->len = htons(skb->len);

	uh->check = 0;



	__skb_push(skb, sizeof(*iph));

	skb_reset_network_header(skb);

	iph		= ip_hdr(skb);

	iph->version	= 4;

	iph->ihl	= sizeof(struct iphdr) >> 2;

	iph->frag_off	= df;

	iph->protocol	= IPPROTO_UDP;

	iph->tos	= ip_tunnel_ecn_encap(tos, old_iph, skb);

	iph->daddr	= dst;

	iph->saddr	= fl4.saddr;

	iph->ttl	= ttl ? : ip4_dst_hoplimit(&rt->dst);

	tunnel_ip_select_ident(skb, old_iph, &rt->dst);



	nf_reset(skb);



	vxlan_set_owner(dev, skb);



	if (handle_offloads(skb))

		goto drop;



	iptunnel_xmit(skb, dev);

	tos = ip_tunnel_ecn_encap(tos, old_iph, skb);

	ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);



	err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, dst,

			    IPPROTO_UDP, tos, ttl, df);

	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);



	return NETDEV_TX_OK;



drop:

include/net/gre.h

+27 −0
Original line number Diff line number Diff line
@@ -7,6 +7,7 @@ 
#define GREPROTO_CISCO		0

#define GREPROTO_PPTP		1

#define GREPROTO_MAX		2

#define GRE_IP_PROTO_MAX	2



struct gre_protocol {

	int  (*handler)(struct sk_buff *skb);
@@ -22,6 +23,32 @@ struct gre_base_hdr { 
int gre_add_protocol(const struct gre_protocol *proto, u8 version);

int gre_del_protocol(const struct gre_protocol *proto, u8 version);



struct gre_cisco_protocol {

	int (*handler)(struct sk_buff *skb, const struct tnl_ptk_info *tpi);

	int (*err_handler)(struct sk_buff *skb, u32 info,

			   const struct tnl_ptk_info *tpi);

	u8 priority;

};



int gre_cisco_register(struct gre_cisco_protocol *proto);

int gre_cisco_unregister(struct gre_cisco_protocol *proto);

void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,

		      int hdr_len);

struct sk_buff *gre_handle_offloads(struct sk_buff *skb, bool gre_csum);



static inline int ip_gre_calc_hlen(__be16 o_flags)

{

	int addend = 4;



	if (o_flags&TUNNEL_CSUM)

		addend += 4;

	if (o_flags&TUNNEL_KEY)

		addend += 4;

	if (o_flags&TUNNEL_SEQ)

		addend += 4;

	return addend;

}



static inline __be16 gre_flags_to_tnl_flags(__be16 flags)

{

	__be16 tflags = 0;

include/net/ip_tunnels.h

+17 −11
Original line number Diff line number Diff line
@@ -73,6 +73,7 @@ struct ip_tunnel { 
#define TUNNEL_REC	__cpu_to_be16(0x20)

#define TUNNEL_VERSION	__cpu_to_be16(0x40)

#define TUNNEL_NO_KEY	__cpu_to_be16(0x80)

#define TUNNEL_DONT_FRAGMENT    __cpu_to_be16(0x0100)



struct tnl_ptk_info {

	__be16 flags;
@@ -155,23 +156,28 @@ static inline void tunnel_ip_select_ident(struct sk_buff *skb, 
				  (skb_shinfo(skb)->gso_segs ?: 1) - 1);

}



static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)

{

	int err;

	int pkt_len = skb->len - skb_transport_offset(skb);

	struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);

int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto);

int iptunnel_xmit(struct net *net, struct rtable *rt,

		  struct sk_buff *skb,

		  __be32 src, __be32 dst, __u8 proto,

		  __u8 tos, __u8 ttl, __be16 df);



	nf_reset(skb);

static inline void iptunnel_xmit_stats(int err,

				       struct net_device_stats *err_stats,

				       struct pcpu_tstats __percpu *stats)

{

	if (err > 0) {

		struct pcpu_tstats *tstats = this_cpu_ptr(stats);



	err = ip_local_out(skb);

	if (likely(net_xmit_eval(err) == 0)) {

		u64_stats_update_begin(&tstats->syncp);

		tstats->tx_bytes += pkt_len;

		tstats->tx_bytes += err;

		tstats->tx_packets++;

		u64_stats_update_end(&tstats->syncp);

	} else if (err < 0) {

		err_stats->tx_errors++;

		err_stats->tx_aborted_errors++;

	} else {

		dev->stats.tx_errors++;

		dev->stats.tx_aborted_errors++;

		err_stats->tx_dropped++;

	}

}

#endif /* __NET_IP_TUNNELS_H */

include/uapi/linux/openvswitch.h

+19 −0
Original line number Diff line number Diff line
@@ -164,6 +164,7 @@ enum ovs_vport_type { 
	OVS_VPORT_TYPE_UNSPEC,

	OVS_VPORT_TYPE_NETDEV,   /* network device */

	OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */

	OVS_VPORT_TYPE_GRE,      /* GRE tunnel. */

	__OVS_VPORT_TYPE_MAX

};
@@ -246,11 +247,29 @@ enum ovs_key_attr { 
	OVS_KEY_ATTR_ARP,       /* struct ovs_key_arp */

	OVS_KEY_ATTR_ND,        /* struct ovs_key_nd */

	OVS_KEY_ATTR_SKB_MARK,  /* u32 skb mark */

	OVS_KEY_ATTR_TUNNEL,    /* Nested set of ovs_tunnel attributes */



#ifdef __KERNEL__

	OVS_KEY_ATTR_IPV4_TUNNEL,  /* struct ovs_key_ipv4_tunnel */

#endif

	__OVS_KEY_ATTR_MAX

};



#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1)



enum ovs_tunnel_key_attr {

	OVS_TUNNEL_KEY_ATTR_ID,                 /* be64 Tunnel ID */

	OVS_TUNNEL_KEY_ATTR_IPV4_SRC,           /* be32 src IP address. */

	OVS_TUNNEL_KEY_ATTR_IPV4_DST,           /* be32 dst IP address. */

	OVS_TUNNEL_KEY_ATTR_TOS,                /* u8 Tunnel IP ToS. */

	OVS_TUNNEL_KEY_ATTR_TTL,                /* u8 Tunnel IP TTL. */

	OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT,      /* No argument, set DF. */

	OVS_TUNNEL_KEY_ATTR_CSUM,               /* No argument. CSUM packet. */

	__OVS_TUNNEL_KEY_ATTR_MAX

};



#define OVS_TUNNEL_KEY_ATTR_MAX (__OVS_TUNNEL_KEY_ATTR_MAX - 1)



/**

 * enum ovs_frag_type - IPv4 and IPv6 fragment type

 * @OVS_FRAG_TYPE_NONE: Packet is not a fragment.

net/ipv4/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -11,7 +11,7 @@ obj-y := route.o inetpeer.o protocol.o \ 
	     tcp_offload.o datagram.o raw.o udp.o udplite.o \

	     udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \

	     fib_frontend.o fib_semantics.o fib_trie.o \

	     inet_fragment.o ping.o

	     inet_fragment.o ping.o ip_tunnel_core.o



obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o

obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o

CRA Git | Maintained and supported by SUSTech CRA and CCSE