path: root/drivers/net/geneve.c

/*
 * GENEVE: Generic Network Virtualization Encapsulation
 *
 * Copyright (c) 2015 Red Hat, Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/hash.h>
#include <net/dst_metadata.h>
#include <net/gro_cells.h>
#include <net/rtnetlink.h>
#include <net/geneve.h>
#include <net/protocol.h>

#define GENEVE_NETDEV_VER	"0.6"

#define GENEVE_UDP_PORT		6081

#define GENEVE_N_VID		(1u << 24)
#define GENEVE_VID_MASK		(GENEVE_N_VID - 1)

#define VNI_HASH_BITS		10
#define VNI_HASH_SIZE		(1<<VNI_HASH_BITS)

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 list_head	sock_list;
};

static int geneve_net_id;

union geneve_addr {
	struct sockaddr_in sin;
	struct sockaddr_in6 sin6;
	struct sockaddr sa;
};

static union geneve_addr geneve_remote_unspec = { .sa.sa_family = AF_UNSPEC, };

/* Pseudo network device */
struct geneve_dev {
	struct hlist_node  hlist;	/* vni hash table */
	struct net	   *net;	/* netns for packet i/o */
	struct net_device  *dev;	/* netdev for geneve tunnel */
	struct geneve_sock *sock4;	/* IPv4 socket used for geneve tunnel */
#if IS_ENABLED(CONFIG_IPV6)
	struct geneve_sock *sock6;	/* IPv6 socket used for geneve tunnel */
#endif
	u8                 vni[3];	/* virtual network ID for tunnel */
	u8                 ttl;		/* TTL override */
	u8                 tos;		/* TOS override */
	union geneve_addr  remote;	/* IP address for link partner */
	struct list_head   next;	/* geneve's per namespace list */
	__be16		   dst_port;
	bool		   collect_md;
	struct gro_cells   gro_cells;
	u32		   flags;
};

/* Geneve device flags */
#define GENEVE_F_UDP_CSUM		BIT(0)
#define GENEVE_F_UDP_ZERO_CSUM6_TX	BIT(1)
#define GENEVE_F_UDP_ZERO_CSUM6_RX	BIT(2)

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];
	u32			flags;
};

static inline __u32 geneve_net_vni_hash(u8 vni[3])
{
	__u32 vnid;

	vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
	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.sin_addr.s_addr)
			return geneve;
	}
	return NULL;
}

#if IS_ENABLED(CONFIG_IPV6)
static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs,
					 struct in6_addr addr6, 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)) &&
		    ipv6_addr_equal(&addr6, &geneve->remote.sin6.sin6_addr))
			return geneve;
	}
	return NULL;
}
#endif

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 metadata_dst *tun_dst = NULL;
	struct geneve_dev *geneve = NULL;
	struct pcpu_sw_netstats *stats;
	struct iphdr *iph = NULL;
	__be32 addr;
	static u8 zero_vni[3];
	u8 *vni;
	int err = 0;
	sa_family_t sa_family;
#if IS_ENABLED(CONFIG_IPV6)
	struct ipv6hdr *ip6h = NULL;
	struct in6_addr addr6;
	static struct in6_addr zero_addr6;
#endif

	sa_family = gs->sock->sk->sk_family;

	if (sa_family == AF_INET) {
		iph = ip_hdr(skb); /* outer IP header... */

		if (gs->collect_md) {
			vni = zero_vni;
			addr = 0;
		} else {
			vni = gnvh->vni;

			addr = iph->saddr;
		}

		geneve = geneve_lookup(gs, addr, vni);
#if IS_ENABLED(CONFIG_IPV6)
	} else if (sa_family == AF_INET6) {
		ip6h = ipv6_hdr(skb); /* outer IPv6 header... */

		if (gs->collect_md) {
			vni = zero_vni;
			addr6 = zero_addr6;
		} else {
			vni = gnvh->vni;

			addr6 = ip6h->saddr;
		}

		geneve = geneve6_lookup(gs, addr6, vni);
#endif
	}
	if (!geneve)
		goto drop;

	if (ip_tunnel_collect_metadata() || gs->collect_md) {
		__be16 flags;

		flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
			(gnvh->oam ? TUNNEL_OAM : 0) |
			(gnvh->critical ? TUNNEL_CRIT_OPT : 0);

		tun_dst = udp_tun_rx_dst(skb, sa_family, flags,
					 vni_to_tunnel_id(gnvh->vni),
					 gnvh->opt_len * 4);
		if (!tun_dst)
			goto drop;
		/* Update tunnel dst according to Geneve options. */
		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
					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, &