[mirror_ubuntu-bionic-kernel.git] / include / net / ip_tunnels.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __NET_IP_TUNNELS_H
#define __NET_IP_TUNNELS_H 1

#include <linux/if_tunnel.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/types.h>
#include <linux/u64_stats_sync.h>
#include <linux/bitops.h>

#include <net/dsfield.h>
#include <net/gro_cells.h>
#include <net/inet_ecn.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/lwtunnel.h>
#include <net/dst_cache.h>

#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif

/* Keep error state on tunnel for 30 sec */
#define IPTUNNEL_ERR_TIMEO	(30*HZ)

/* Used to memset ip_tunnel padding. */
#define IP_TUNNEL_KEY_SIZE	offsetofend(struct ip_tunnel_key, tp_dst)

/* Used to memset ipv4 address padding. */
#define IP_TUNNEL_KEY_IPV4_PAD	offsetofend(struct ip_tunnel_key, u.ipv4.dst)
#define IP_TUNNEL_KEY_IPV4_PAD_LEN				\
	(FIELD_SIZEOF(struct ip_tunnel_key, u) -		\
	 FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))

struct ip_tunnel_key {
	__be64			tun_id;
	union {
		struct {
			__be32	src;
			__be32	dst;
		} ipv4;
		struct {
			struct in6_addr src;
			struct in6_addr dst;
		} ipv6;
	} u;
	__be16			tun_flags;
	u8			tos;		/* TOS for IPv4, TC for IPv6 */
	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
	__be32			label;		/* Flow Label for IPv6 */
	__be16			tp_src;
	__be16			tp_dst;
};

/* Flags for ip_tunnel_info mode. */
#define IP_TUNNEL_INFO_TX	0x01	/* represents tx tunnel parameters */
#define IP_TUNNEL_INFO_IPV6	0x02	/* key contains IPv6 addresses */
#define IP_TUNNEL_INFO_BRIDGE	0x04	/* represents a bridged tunnel id */

/* Maximum tunnel options length. */
#define IP_TUNNEL_OPTS_MAX					\
	GENMASK((FIELD_SIZEOF(struct ip_tunnel_info,		\
			      options_len) * BITS_PER_BYTE) - 1, 0)

struct ip_tunnel_info {
	struct ip_tunnel_key	key;
#ifdef CONFIG_DST_CACHE
	struct dst_cache	dst_cache;
#endif
	u8			options_len;
	u8			mode;
};

/* 6rd prefix/relay information */
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd_parm {
	struct in6_addr		prefix;
	__be32			relay_prefix;
	u16			prefixlen;
	u16			relay_prefixlen;
};
#endif

struct ip_tunnel_encap {
	u16			type;
	u16			flags;
	__be16			sport;
	__be16			dport;
};

struct ip_tunnel_prl_entry {
	struct ip_tunnel_prl_entry __rcu *next;
	__be32				addr;
	u16				flags;
	struct rcu_head			rcu_head;
};

struct metadata_dst;
/* A fan overlay /8 (250.0.0.0/8, for example) maps to exactly one /16
 * underlay (10.88.0.0/16, for example).  Multiple local addresses within
 * the /16 may be used, but a particular overlay may not span
 * multiple underlay subnets.
 *
 * We store one underlay, indexed by the overlay's high order octet.
 */
#define FAN_OVERLAY_CNT		256

struct ip_fan_map {
	__be32			underlay;
	__be32			overlay;
	u16			underlay_prefix;
	u16			overlay_prefix;
	u32			overlay_mask;
	struct list_head	list;
	struct rcu_head		rcu;
};

struct ip_tunnel_fan {
	struct list_head	fan_maps;
};

struct ip_tunnel {
	struct ip_tunnel __rcu	*next;
	struct hlist_node hash_node;
	struct net_device	*dev;
	struct net		*net;	/* netns for packet i/o */

	unsigned long	err_time;	/* Time when the last ICMP error
					 * arrived */
	int		err_count;	/* Number of arrived ICMP errors */

	/* These four fields used only by GRE */
	u32		i_seqno;	/* The last seen seqno	*/
	u32		o_seqno;	/* The last output seqno */
	int		tun_hlen;	/* Precalculated header length */

	/* This field used only by ERSPAN */
	u32		index;		/* ERSPAN type II index */

	struct dst_cache dst_cache;

	struct ip_tunnel_parm parms;

	int		mlink;
	int		encap_hlen;	/* Encap header length (FOU,GUE) */
	int		hlen;		/* tun_hlen + encap_hlen */
	struct ip_tunnel_encap encap;

	/* for SIT */
#ifdef CONFIG_IPV6_SIT_6RD
	struct ip_tunnel_6rd_parm ip6rd;
#endif
	struct ip_tunnel_prl_entry __rcu *prl;	/* potential router list */
	unsigned int		prl_count;	/* # of entries in PRL */
	struct ip_tunnel_fan	fan;
	unsigned int		ip_tnl_net_id;
	struct gro_cells	gro_cells;
	__u32			fwmark;
	bool			collect_md;
	bool			ignore_df;
};

#define TUNNEL_CSUM		__cpu_to_be16(0x01)
#define TUNNEL_ROUTING		__cpu_to_be16(0x02)
#define TUNNEL_KEY		__cpu_to_be16(0x04)
#define TUNNEL_SEQ		__cpu_to_be16(0x08)
#define TUNNEL_STRICT		__cpu_to_be16(0x10)
#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)
#define TUNNEL_OAM		__cpu_to_be16(0x0200)
#define TUNNEL_CRIT_OPT		__cpu_to_be16(0x0400)
#define TUNNEL_GENEVE_OPT	__cpu_to_be16(0x0800)
#define TUNNEL_VXLAN_OPT	__cpu_to_be16(0x1000)
#define TUNNEL_NOCACHE		__cpu_to_be16(0x2000)
#define TUNNEL_ERSPAN_OPT	__cpu_to_be16(0x4000)

#define TUNNEL_OPTIONS_PRESENT \
		(TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT)

static inline int fan_has_map(const struct ip_tunnel_fan *fan)
{
	return !list_empty(&fan->fan_maps);
}

struct tnl_ptk_info {
	__be16 flags;
	__be16 proto;
	__be32 key;
	__be32 seq;
	int hdr_len;
};

#define PACKET_RCVD	0
#define PACKET_REJECT	1
#define PACKET_NEXT	2

#define IP_TNL_HASH_BITS   7
#define IP_TNL_HASH_SIZE   (1 << IP_TNL_HASH_BITS)

struct ip_tunnel_net {
	struct net_device *fb_tunnel_dev;
	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
	struct ip_tunnel __rcu *collect_md_tun;
};

static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
				      __be32 saddr, __be32 daddr,
				      u8 tos, u8 ttl, __be32 label,
				      __be16 tp_src, __be16 tp_dst,
				      __be64 tun_id, __be16 tun_flags)
{
	key->tun_id = tun_id;
	key->u.ipv4.src = saddr;
	key->u.ipv4.dst = daddr;
	memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD,
	       0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
	key->tos = tos;
	key->ttl = ttl;
	key->label = label;
	key->tun_flags = tun_flags;

	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
	 * the upper tunnel are used.
	 * E.g: GRE over IPSEC, the tp_src and tp_port are zero.
	 */
	key->tp_src = tp_src;
	key->tp_dst = tp_dst;

	/* Clear struct padding. */
	if (sizeof(*key) != IP_TUNNEL_KEY_SIZE)
		memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE,
		       0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
}

static inline bool
ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
			   const struct ip_tunnel_info *info)
{
	if (skb->mark)
		return false;
	if (!info)
		return true;
	if (info->key.tun_flags & TUNNEL_NOCACHE)
		return false;

	return true;
}

static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
					       *tun_info)
{
	return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET;
}

static inline __be64 key32_to_tunnel_id(__be32 key)
{
#ifdef __BIG_ENDIAN
	return (__force __be64)key;
#else
	return (__force __be64)((__force u64)key << 32);
#endif
}

/* Returns the least-significant 32 bits of a __be64. */
static inline __be32 tunnel_id_to_key32(__be64 tun_id)
{
#ifdef __BIG_ENDIAN
	return (__force __be32)tun_id;
#else
	return (__force __be32)((__force u64)tun_id >> 32);
#endif
}

#ifdef CONFIG_INET

int ip_tunnel_init(struct net_device *dev);
void ip_tunnel_uninit(struct net_device *dev);
void  ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
struct net *ip_tunnel_get_link_net(const struct net_device *dev);
int ip_tunnel_get_iflink(const struct net_device *dev);
int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
		       struct rtnl_link_ops *ops, char *devname);

void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
			   struct rtnl_link_ops *ops);

void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
		    const struct iphdr *tnl_params, const u8 protocol);
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
		       const u8 proto);
int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);

void ip_tunnel_get_stats64(struct net_device *dev,
			   struct rtnl_link_stats64 *tot);
struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
				   int link, __be16 flags,
				   __be32 remote, __be32 local,
				   __be32 key);

int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
		  bool log_ecn_error);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
			 struct ip_tunnel_parm *p, __u32 fwmark);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
		      struct ip_tunnel_parm *p, __u32 fwmark);
void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);

struct ip_tunnel_encap_ops {
	size_t (*encap_hlen)(struct ip_tunnel_encap *e);
	int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
			    u8 *protocol, struct flowi4 *fl4);
};

#define MAX_IPTUN_ENCAP_OPS 8

extern const struct ip_tunnel_encap_ops __rcu *
		iptun_encaps[MAX_IPTUN_ENCAP_OPS];

int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
			    unsigned int num);
int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
			    unsigned int num);

int ip_tunnel_encap_setup(struct ip_tunnel *t,
			  struct ip_tunnel_encap *ipencap);

static inline bool pskb_inet_may_pull(struct sk_buff *skb)
{
	int nhlen;

	switch (skb->protocol) {
#if IS_ENABLED(CONFIG_IPV6)
	case htons(ETH_P_IPV6):
		nhlen = sizeof(struct ipv6hdr);
		break;
#endif
	case htons(ETH_P_IP):
		nhlen = sizeof(struct iphdr);
		break;
	default:
		nhlen = 0;
	}

	return pskb_network_may_pull(skb, nhlen);
}

static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
{
	const struct ip_tunnel_encap_ops *ops;
	int hlen = -EINVAL;

	if (e->type == TUNNEL_ENCAP_NONE)
		return 0;

	if (e->type >= MAX_IPTUN_ENCAP_OPS)
		return -EINVAL;

	rcu_read_lock();
	ops = rcu_dereference(iptun_encaps[e->type]);
	if (likely(ops && ops->encap_hlen))
		hlen = ops->encap_hlen(e);
	rcu_read_unlock();

	return hlen;
}

static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
				  u8 *protocol, struct flowi4 *fl4)
{
	const struct ip_tunnel_encap_ops *ops;
	int ret = -EINVAL;

	if (t->encap.type == TUNNEL_ENCAP_NONE)
		return 0;

	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
		return -EINVAL;

	rcu_read_lock();
	ops = rcu_dereference(iptun_encaps[t->encap.type]);
	if (likely(ops && ops->build_header))
		ret = ops->build_header(skb, &t->encap, protocol, fl4);
	rcu_read_unlock();

	return ret;
}

/* Extract dsfield from inner protocol */
static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
				       const struct sk_buff *skb)
{
	if (skb->protocol == htons(ETH_P_IP))
		return iph->tos;
	else if (skb->protocol == htons(ETH_P_IPV6))
		return ipv6_get_dsfield((const struct ipv6hdr *)iph);
	else
		return 0;
}

/* Propogate ECN bits out */
static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
				     const struct sk_buff *skb)
{
	u8 inner = ip_tunnel_get_dsfield(iph, skb);

	return INET_ECN_encapsulate(tos, inner);
}

int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
			   __be16 inner_proto, bool raw_proto, bool xnet);

static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
				       __be16 inner_proto, bool xnet)
{
	return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet);
}

void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
		   __be32 src, __be32 dst, u8 proto,
		   u8 tos, u8 ttl, __be16 df, bool xnet);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
					     gfp_t flags);

int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);

static inline int iptunnel_pull_offloads(struct sk_buff *skb)
{
	if (skb_is_gso(skb)) {
		int err;

		err = skb_unclone(skb, GFP_ATOMIC);
		if (unlikely(err))
			return err;
		skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >>
					       NETIF_F_GSO_SHIFT);
	}

	skb->encapsulation = 0;
	return 0;
}

static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
{
	if (pkt_len > 0) {
		struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);

		u64_stats_update_begin(&tstats->syncp);
		tstats->tx_bytes += pkt_len;
		tstats->tx_packets++;
		u64_stats_update_end(&tstats->syncp);
		put_cpu_ptr(tstats);
	} else {
		struct net_device_stats *err_stats = &dev->stats;

		if (pkt_len < 0) {
			err_stats->tx_errors++;
			err_stats->tx_aborted_errors++;
		} else {
			err_stats->tx_dropped++;
		}
	}
}

static inline void *ip_tunnel_info_opts(struct ip_tunnel_info *info)
{
	return info + 1;
}

static inline void ip_tunnel_info_opts_get(void *to,
					   const struct ip_tunnel_info *info)
{
	memcpy(to, info + 1, info->options_len);
}

static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
					   const void *from, int len)
{
	memcpy(ip_tunnel_info_opts(info), from, len);
	info->options_len = len;
}

static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
{
	return (struct ip_tunnel_info *)lwtstate->data;
}

extern struct static_key ip_tunnel_metadata_cnt;

/* Returns > 0 if metadata should be collected */
static inline int ip_tunnel_collect_metadata(void)
{
	return static_key_false(&ip_tunnel_metadata_cnt);
}

void __init ip_tunnel_core_init(void);

void ip_tunnel_need_metadata(void);
void ip_tunnel_unneed_metadata(void);

#else /* CONFIG_INET */

static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
{
	return NULL;
}

static inline void ip_tunnel_need_metadata(void)
{
}

static inline void ip_tunnel_unneed_metadata(void)
{
}

static inline void ip_tunnel_info_opts_get(void *to,
					   const struct ip_tunnel_info *info)
{
}

static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
					   const void *from, int len)
{
	info->options_len = 0;
}

#endif /* CONFIG_INET */

#endif /* __NET_IP_TUNNELS_H */
Commit	Line	Data
b2441318	1	/* SPDX-License-Identifier: GPL-2.0 */
c5441932 PS	2	#ifndef __NET_IP_TUNNELS_H
	3	#define __NET_IP_TUNNELS_H 1
	4
	5	#include <linux/if_tunnel.h>
	6	#include <linux/netdevice.h>
	7	#include <linux/skbuff.h>
7f9562a1	8	#include <linux/socket.h>
c5441932 PS	9	#include <linux/types.h>
c5441932 PS	10	#include <linux/u64_stats_sync.h>
fca5fdf6 DB	11	#include <linux/bitops.h>
fca5fdf6 DB	12
c5441932 PS	13	#include <net/dsfield.h>
	14	#include <net/gro_cells.h>
	15	#include <net/inet_ecn.h>
56328486	16	#include <net/netns/generic.h>
c5441932	17	#include <net/rtnetlink.h>
3093fbe7	18	#include <net/lwtunnel.h>
e09acddf	19	#include <net/dst_cache.h>
c5441932 PS	20
	21	#if IS_ENABLED(CONFIG_IPV6)
	22	#include <net/ipv6.h>
	23	#include <net/ip6_fib.h>
	24	#include <net/ip6_route.h>
	25	#endif
	26
	27	/* Keep error state on tunnel for 30 sec */
	28	#define IPTUNNEL_ERR_TIMEO (30*HZ)
	29
1d8fff90	30	/* Used to memset ip_tunnel padding. */
376534a3	31	#define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst)
1d8fff90	32
c1ea5d67 JB	33	/* Used to memset ipv4 address padding. */
	34	#define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst)
	35	#define IP_TUNNEL_KEY_IPV4_PAD_LEN \
	36	(FIELD_SIZEOF(struct ip_tunnel_key, u) - \
	37	FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4))
	38
1d8fff90 TG	39	struct ip_tunnel_key {
1d8fff90 TG	40	__be64 tun_id;
c1ea5d67 JB	41	union {
	42	struct {
	43	__be32 src;
	44	__be32 dst;
	45	} ipv4;
	46	struct {
	47	struct in6_addr src;
	48	struct in6_addr dst;
	49	} ipv6;
	50	} u;
1d8fff90	51	__be16 tun_flags;
7c383fb2 JB	52	u8 tos; /* TOS for IPv4, TC for IPv6 */
7c383fb2 JB	53	u8 ttl; /* TTL for IPv4, HL for IPv6 */
13461144	54	__be32 label; /* Flow Label for IPv6 */
1d8fff90 TG	55	__be16 tp_src;
1d8fff90 TG	56	__be16 tp_dst;
ac1cf399	57	};
1d8fff90	58
46fa062a JB	59	/* Flags for ip_tunnel_info mode. */
46fa062a JB	60	#define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */
7f9562a1	61	#define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */
f35581d6	62	#define IP_TUNNEL_INFO_BRIDGE 0x04 /* represents a bridged tunnel id */
ee122c79	63
fca5fdf6 DB	64	/* Maximum tunnel options length. */
	65	#define IP_TUNNEL_OPTS_MAX \
	66	GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \
	67	options_len) * BITS_PER_BYTE) - 1, 0)
	68
1d8fff90 TG	69	struct ip_tunnel_info {
1d8fff90 TG	70	struct ip_tunnel_key key;
d71785ff PA	71	#ifdef CONFIG_DST_CACHE
	72	struct dst_cache dst_cache;
	73	#endif
1d8fff90	74	u8 options_len;
ee122c79	75	u8 mode;
1d8fff90 TG	76	};
1d8fff90 TG	77
c5441932 PS	78	/* 6rd prefix/relay information */
	79	#ifdef CONFIG_IPV6_SIT_6RD
	80	struct ip_tunnel_6rd_parm {
	81	struct in6_addr prefix;
	82	__be32 relay_prefix;
	83	u16 prefixlen;
	84	u16 relay_prefixlen;
	85	};
	86	#endif
	87
56328486	88	struct ip_tunnel_encap {
6b8847c5 JB	89	u16 type;
6b8847c5 JB	90	u16 flags;
56328486 TH	91	__be16 sport;
	92	__be16 dport;
	93	};
	94
c5441932 PS	95	struct ip_tunnel_prl_entry {
	96	struct ip_tunnel_prl_entry __rcu *next;
	97	__be32 addr;
	98	u16 flags;
	99	struct rcu_head rcu_head;
	100	};
	101
2e15ea39	102	struct metadata_dst;
55ff02b2 JV	103	/* A fan overlay /8 (250.0.0.0/8, for example) maps to exactly one /16
	104	* underlay (10.88.0.0/16, for example). Multiple local addresses within
	105	* the /16 may be used, but a particular overlay may not span
	106	* multiple underlay subnets.
	107	*
	108	* We store one underlay, indexed by the overlay's high order octet.
	109	*/
	110	#define FAN_OVERLAY_CNT 256
	111
d57420a1 JV	112	struct ip_fan_map {
	113	__be32 underlay;
	114	__be32 overlay;
	115	u16 underlay_prefix;
	116	u16 overlay_prefix;
	117	u32 overlay_mask;
	118	struct list_head list;
	119	struct rcu_head rcu;
	120	};
	121
55ff02b2	122	struct ip_tunnel_fan {
d57420a1	123	struct list_head fan_maps;
55ff02b2	124	};
2e15ea39	125
c5441932 PS	126	struct ip_tunnel {
	127	struct ip_tunnel __rcu *next;
	128	struct hlist_node hash_node;
	129	struct net_device *dev;
5e6700b3	130	struct net net; / netns for packet i/o */
c5441932	131
c5441932 PS	132	unsigned long err_time; /* Time when the last ICMP error
c5441932 PS	133	* arrived */
f38ba953	134	int err_count; /* Number of arrived ICMP errors */
c5441932 PS	135
c5441932 PS	136	/* These four fields used only by GRE */
6b8847c5 JB	137	u32 i_seqno; /* The last seen seqno */
6b8847c5 JB	138	u32 o_seqno; /* The last output seqno */
56328486	139	int tun_hlen; /* Precalculated header length */
c5441932	140
84e54fe0 WT	141	/* This field used only by ERSPAN */
	142	u32 index; /* ERSPAN type II index */
	143
e09acddf	144	struct dst_cache dst_cache;
7d442fab	145
c5441932 PS	146	struct ip_tunnel_parm parms;
c5441932 PS	147
f38ba953	148	int mlink;
56328486	149	int encap_hlen; /* Encap header length (FOU,GUE) */
56328486	150	int hlen; /* tun_hlen + encap_hlen */
f38ba953	151	struct ip_tunnel_encap encap;
56328486	152
c5441932 PS	153	/* for SIT */
	154	#ifdef CONFIG_IPV6_SIT_6RD
	155	struct ip_tunnel_6rd_parm ip6rd;
	156	#endif
	157	struct ip_tunnel_prl_entry __rcu prl; / potential router list */
	158	unsigned int prl_count; /* # of entries in PRL */
55ff02b2	159	struct ip_tunnel_fan fan;
c7d03a00	160	unsigned int ip_tnl_net_id;
c5441932	161	struct gro_cells gro_cells;
9830ad4c	162	__u32 fwmark;
2e15ea39	163	bool collect_md;
22a59be8	164	bool ignore_df;
c5441932 PS	165	};
c5441932 PS	166
f5796684 JG	167	#define TUNNEL_CSUM __cpu_to_be16(0x01)
	168	#define TUNNEL_ROUTING __cpu_to_be16(0x02)
	169	#define TUNNEL_KEY __cpu_to_be16(0x04)
	170	#define TUNNEL_SEQ __cpu_to_be16(0x08)
	171	#define TUNNEL_STRICT __cpu_to_be16(0x10)
	172	#define TUNNEL_REC __cpu_to_be16(0x20)
	173	#define TUNNEL_VERSION __cpu_to_be16(0x40)
	174	#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
9a628224	175	#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100)
f5796684 JG	176	#define TUNNEL_OAM __cpu_to_be16(0x0200)
f5796684 JG	177	#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
1dd144cf TG	178	#define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800)
1dd144cf TG	179	#define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000)
db3c6139	180	#define TUNNEL_NOCACHE __cpu_to_be16(0x2000)
1a66a836	181	#define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000)
1dd144cf	182
1a66a836 WT	183	#define TUNNEL_OPTIONS_PRESENT \
1a66a836 WT	184	(TUNNEL_GENEVE_OPT \| TUNNEL_VXLAN_OPT \| TUNNEL_ERSPAN_OPT)
d57420a1 JV	185
	186	static inline int fan_has_map(const struct ip_tunnel_fan *fan)
	187	{
	188	return !list_empty(&fan->fan_maps);
	189	}
c5441932 PS	190
	191	struct tnl_ptk_info {
	192	__be16 flags;
	193	__be16 proto;
	194	__be32 key;
	195	__be32 seq;
9b8c6d7b	196	int hdr_len;
c5441932 PS	197	};
	198
	199	#define PACKET_RCVD 0
	200	#define PACKET_REJECT 1
125372fa	201	#define PACKET_NEXT 2
c5441932	202
6261d983	203	#define IP_TNL_HASH_BITS 7
c5441932 PS	204	#define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS)
	205
	206	struct ip_tunnel_net {
c5441932	207	struct net_device *fb_tunnel_dev;
6261d983	208	struct hlist_head tunnels[IP_TNL_HASH_SIZE];
2e15ea39	209	struct ip_tunnel __rcu *collect_md_tun;
c5441932 PS	210	};
c5441932 PS	211
4c222798 PS	212	static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
4c222798 PS	213	__be32 saddr, __be32 daddr,
13461144	214	u8 tos, u8 ttl, __be32 label,
4c222798 PS	215	__be16 tp_src, __be16 tp_dst,
4c222798 PS	216	__be64 tun_id, __be16 tun_flags)
1d8fff90	217	{
4c222798 PS	218	key->tun_id = tun_id;
	219	key->u.ipv4.src = saddr;
	220	key->u.ipv4.dst = daddr;
	221	memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD,
c1ea5d67	222	0, IP_TUNNEL_KEY_IPV4_PAD_LEN);
4c222798 PS	223	key->tos = tos;
4c222798 PS	224	key->ttl = ttl;
13461144	225	key->label = label;
4c222798	226	key->tun_flags = tun_flags;
1d8fff90 TG	227
	228	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
	229	* the upper tunnel are used.
	230	* E.g: GRE over IPSEC, the tp_src and tp_port are zero.
	231	*/
4c222798 PS	232	key->tp_src = tp_src;
4c222798 PS	233	key->tp_dst = tp_dst;
1d8fff90 TG	234
1d8fff90 TG	235	/* Clear struct padding. */
4c222798 PS	236	if (sizeof(*key) != IP_TUNNEL_KEY_SIZE)
	237	memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE,
	238	0, sizeof(*key) - IP_TUNNEL_KEY_SIZE);
1d8fff90 TG	239	}
1d8fff90 TG	240
db3c6139 DB	241	static inline bool
	242	ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
	243	const struct ip_tunnel_info *info)
	244	{
	245	if (skb->mark)
	246	return false;
	247	if (!info)
	248	return true;
	249	if (info->key.tun_flags & TUNNEL_NOCACHE)
	250	return false;
	251
	252	return true;
	253	}
	254
7f9562a1 JB	255	static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
	256	*tun_info)
	257	{
	258	return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET;
	259	}
	260
d817f432 AV	261	static inline __be64 key32_to_tunnel_id(__be32 key)
	262	{
	263	#ifdef __BIG_ENDIAN
	264	return (__force __be64)key;
	265	#else
	266	return (__force __be64)((__force u64)key << 32);
	267	#endif
	268	}
	269
	270	/* Returns the least-significant 32 bits of a __be64. */
	271	static inline __be32 tunnel_id_to_key32(__be64 tun_id)
	272	{
	273	#ifdef __BIG_ENDIAN
	274	return (__force __be32)tun_id;
	275	#else
	276	return (__force __be32)((__force u64)tun_id >> 32);
	277	#endif
	278	}
	279
5243b6ac JG	280	#ifdef CONFIG_INET
5243b6ac JG	281
c5441932 PS	282	int ip_tunnel_init(struct net_device *dev);
	283	void ip_tunnel_uninit(struct net_device *dev);
	284	void ip_tunnel_dellink(struct net_device dev, struct list_head head);
1728d4fa	285	struct net ip_tunnel_get_link_net(const struct net_device dev);
1e99584b	286	int ip_tunnel_get_iflink(const struct net_device *dev);
c7d03a00	287	int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
d3b6f614	288	struct rtnl_link_ops ops, char devname);
c5441932	289
64bc1781 ED	290	void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
64bc1781 ED	291	struct rtnl_link_ops *ops);
c5441932 PS	292
c5441932 PS	293	void ip_tunnel_xmit(struct sk_buff skb, struct net_device dev,
bf3d6a8f	294	const struct iphdr *tnl_params, const u8 protocol);
cfc7381b AS	295	void ip_md_tunnel_xmit(struct sk_buff skb, struct net_device dev,
cfc7381b AS	296	const u8 proto);
c5441932	297	int ip_tunnel_ioctl(struct net_device dev, struct ip_tunnel_parm p, int cmd);
7e059158	298	int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
c5441932 PS	299	int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
c5441932 PS	300
bc1f4470	301	void ip_tunnel_get_stats64(struct net_device *dev,
bc1f4470	302	struct rtnl_link_stats64 *tot);
c5441932 PS	303	struct ip_tunnel ip_tunnel_lookup(struct ip_tunnel_net itn,
	304	int link, __be16 flags,
	305	__be32 remote, __be32 local,
	306	__be32 key);
	307
	308	int ip_tunnel_rcv(struct ip_tunnel tunnel, struct sk_buff skb,
2e15ea39 PS	309	const struct tnl_ptk_info tpi, struct metadata_dst tun_dst,
2e15ea39 PS	310	bool log_ecn_error);
c5441932	311	int ip_tunnel_changelink(struct net_device dev, struct nlattr tb[],
9830ad4c	312	struct ip_tunnel_parm *p, __u32 fwmark);
c5441932	313	int ip_tunnel_newlink(struct net_device dev, struct nlattr tb[],
9830ad4c	314	struct ip_tunnel_parm *p, __u32 fwmark);
c7d03a00	315	void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
55c2bc14 TH	316
	317	struct ip_tunnel_encap_ops {
	318	size_t (encap_hlen)(struct ip_tunnel_encap e);
	319	int (build_header)(struct sk_buff skb, struct ip_tunnel_encap *e,
	320	u8 protocol, struct flowi4 fl4);
	321	};
	322
	323	#define MAX_IPTUN_ENCAP_OPS 8
	324
	325	extern const struct ip_tunnel_encap_ops __rcu *
	326	iptun_encaps[MAX_IPTUN_ENCAP_OPS];
	327
	328	int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op,
	329	unsigned int num);
	330	int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
	331	unsigned int num);
	332
56328486 TH	333	int ip_tunnel_encap_setup(struct ip_tunnel *t,
56328486 TH	334	struct ip_tunnel_encap *ipencap);
c5441932	335
78afc98e WB	336	static inline bool pskb_inet_may_pull(struct sk_buff *skb)
	337	{
	338	int nhlen;
	339
	340	switch (skb->protocol) {
	341	#if IS_ENABLED(CONFIG_IPV6)
	342	case htons(ETH_P_IPV6):
	343	nhlen = sizeof(struct ipv6hdr);
	344	break;
	345	#endif
	346	case htons(ETH_P_IP):
	347	nhlen = sizeof(struct iphdr);
	348	break;
	349	default:
	350	nhlen = 0;
	351	}
	352
	353	return pskb_network_may_pull(skb, nhlen);
	354	}
	355
55c2bc14 TH	356	static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
	357	{
	358	const struct ip_tunnel_encap_ops *ops;
	359	int hlen = -EINVAL;
	360
	361	if (e->type == TUNNEL_ENCAP_NONE)
	362	return 0;
	363
	364	if (e->type >= MAX_IPTUN_ENCAP_OPS)
	365	return -EINVAL;
	366
	367	rcu_read_lock();
	368	ops = rcu_dereference(iptun_encaps[e->type]);
	369	if (likely(ops && ops->encap_hlen))
	370	hlen = ops->encap_hlen(e);
	371	rcu_read_unlock();
	372
	373	return hlen;
	374	}
	375
	376	static inline int ip_tunnel_encap(struct sk_buff skb, struct ip_tunnel t,
	377	u8 protocol, struct flowi4 fl4)
	378	{
	379	const struct ip_tunnel_encap_ops *ops;
	380	int ret = -EINVAL;
	381
	382	if (t->encap.type == TUNNEL_ENCAP_NONE)
	383	return 0;
	384
	385	if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
	386	return -EINVAL;
	387
	388	rcu_read_lock();
	389	ops = rcu_dereference(iptun_encaps[t->encap.type]);
	390	if (likely(ops && ops->build_header))
	391	ret = ops->build_header(skb, &t->encap, protocol, fl4);
	392	rcu_read_unlock();
	393
	394	return ret;
	395	}
	396
c5441932 PS	397	/* Extract dsfield from inner protocol */
	398	static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
	399	const struct sk_buff *skb)
	400	{
	401	if (skb->protocol == htons(ETH_P_IP))
	402	return iph->tos;
	403	else if (skb->protocol == htons(ETH_P_IPV6))
	404	return ipv6_get_dsfield((const struct ipv6hdr *)iph);
	405	else
	406	return 0;
	407	}
	408
	409	/* Propogate ECN bits out */
	410	static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
	411	const struct sk_buff *skb)
	412	{
	413	u8 inner = ip_tunnel_get_dsfield(iph, skb);
	414
	415	return INET_ECN_encapsulate(tos, inner);
	416	}
	417
a6d5bbf3 JB	418	int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
	419	__be16 inner_proto, bool raw_proto, bool xnet);
	420
	421	static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
	422	__be16 inner_proto, bool xnet)
	423	{
	424	return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet);
	425	}
	426
039f5062 PS	427	void iptunnel_xmit(struct sock sk, struct rtable rt, struct sk_buff *skb,
	428	__be32 src, __be32 dst, u8 proto,
	429	u8 tos, u8 ttl, __be16 df, bool xnet);
63d008a4 JB	430	struct metadata_dst iptunnel_metadata_reply(struct metadata_dst md,
63d008a4 JB	431	gfp_t flags);
0e6fbc5b	432
aed069df	433	int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
2d26f0a3	434
a09a4c8d JG	435	static inline int iptunnel_pull_offloads(struct sk_buff *skb)
	436	{
	437	if (skb_is_gso(skb)) {
	438	int err;
	439
	440	err = skb_unclone(skb, GFP_ATOMIC);
	441	if (unlikely(err))
	442	return err;
	443	skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >>
	444	NETIF_F_GSO_SHIFT);
	445	}
	446
	447	skb->encapsulation = 0;
	448	return 0;
	449	}
	450
039f5062	451	static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
c5441932	452	{
039f5062 PS	453	if (pkt_len > 0) {
039f5062 PS	454	struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
c5441932	455
c5441932	456	u64_stats_update_begin(&tstats->syncp);
039f5062	457	tstats->tx_bytes += pkt_len;
c5441932 PS	458	tstats->tx_packets++;
c5441932 PS	459	u64_stats_update_end(&tstats->syncp);
b4fe85f9	460	put_cpu_ptr(tstats);
c5441932	461	} else {
039f5062 PS	462	struct net_device_stats *err_stats = &dev->stats;
	463
	464	if (pkt_len < 0) {
	465	err_stats->tx_errors++;
	466	err_stats->tx_aborted_errors++;
	467	} else {
	468	err_stats->tx_dropped++;
	469	}
c5441932 PS	470	}
c5441932 PS	471	}
5243b6ac	472
4c222798	473	static inline void ip_tunnel_info_opts(struct ip_tunnel_info info)
ee122c79 TG	474	{
	475	return info + 1;
	476	}
	477
4c222798 PS	478	static inline void ip_tunnel_info_opts_get(void *to,
	479	const struct ip_tunnel_info *info)
	480	{
	481	memcpy(to, info + 1, info->options_len);
	482	}
	483
	484	static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
	485	const void *from, int len)
	486	{
	487	memcpy(ip_tunnel_info_opts(info), from, len);
	488	info->options_len = len;
	489	}
	490
3093fbe7 TG	491	static inline struct ip_tunnel_info lwt_tun_info(struct lwtunnel_state lwtstate)
	492	{
	493	return (struct ip_tunnel_info *)lwtstate->data;
	494	}
	495
e7030878 TG	496	extern struct static_key ip_tunnel_metadata_cnt;
	497
	498	/* Returns > 0 if metadata should be collected */
	499	static inline int ip_tunnel_collect_metadata(void)
	500	{
	501	return static_key_false(&ip_tunnel_metadata_cnt);
	502	}
	503
045a0fa0 TG	504	void __init ip_tunnel_core_init(void);
045a0fa0 TG	505
e7030878 TG	506	void ip_tunnel_need_metadata(void);
	507	void ip_tunnel_unneed_metadata(void);
	508
05283187 TG	509	#else /* CONFIG_INET */
	510
	511	static inline struct ip_tunnel_info lwt_tun_info(struct lwtunnel_state lwtstate)
	512	{
	513	return NULL;
	514	}
	515
	516	static inline void ip_tunnel_need_metadata(void)
	517	{
	518	}
	519
	520	static inline void ip_tunnel_unneed_metadata(void)
	521	{
	522	}
	523
e28e87ed DB	524	static inline void ip_tunnel_info_opts_get(void *to,
	525	const struct ip_tunnel_info *info)
	526	{
	527	}
	528
	529	static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
	530	const void *from, int len)
	531	{
	532	info->options_len = 0;
	533	}
	534
5243b6ac JG	535	#endif /* CONFIG_INET */
5243b6ac JG	536
c5441932	537	#endif /* __NET_IP_TUNNELS_H */