#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/static_key.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include <net/ip6_checksum.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
#include <net/geneve.h>
#include <net/vxlan.h>
#include <net/erspan.h>
const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(iptun_encaps);
const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(ip6tun_encaps);
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,
u16 ipcb_flags)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) {
if (dev) {
net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
dev->name);
DEV_STATS_INC(dev, tx_errors);
}
ip_rt_put(rt);
kfree_skb(skb);
return;
}
dev_xmit_recursion_inc();
skb_scrub_packet(skb, xnet);
skb_clear_hash_if_not_l4(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
IPCB(skb)->flags = ipcb_flags;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (dev) {
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
dev_xmit_recursion_dec();
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);
int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
__be16 inner_proto, bool raw_proto, bool xnet)
{
if (unlikely(!pskb_may_pull(skb, hdr_len)))
return -ENOMEM;
skb_pull_rcsum(skb, hdr_len);
if (!raw_proto && inner_proto == htons(ETH_P_TEB)) {
struct ethhdr *eh;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
} else {
skb->protocol = inner_proto;
}
skb_clear_hash_if_not_l4(skb);
__vlan_hwaccel_clear_tag(skb);
skb_set_queue_mapping(skb, 0);
skb_scrub_packet(skb, xnet);
return iptunnel_pull_offloads(skb);
}
EXPORT_SYMBOL_GPL(__iptunnel_pull_header);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags)
{
IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { };
struct metadata_dst *res;
struct ip_tunnel_info *dst, *src;
if (!md || md->type != METADATA_IP_TUNNEL ||
md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
return NULL;
src = &md->u.tun_info;
res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
dst = &res->u.tun_info;
dst->key.tun_id = src->key.tun_id;
if (src->mode & IP_TUNNEL_INFO_IPV6)
memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
sizeof(struct in6_addr));
else
dst->key.u.ipv4.dst = src->key.u.ipv4.src;
ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags);
dst->mode = src->mode | IP_TUNNEL_INFO_TX;
ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
src->options_len, tun_flags);
return res;
}
EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);
int iptunnel_handle_offloads(struct sk_buff *skb,
int gso_type_mask)
{
int err;
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
if (skb_is_gso(skb)) {
err = skb_header_unclone(skb, GFP_ATOMIC);
if (unlikely(err))
return err;
skb_shinfo(skb)->gso_type |= gso_type_mask;
return 0;
}
if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_NONE;
skb->encapsulation = 0;
}
return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
{
const struct iphdr *iph = ip_hdr(skb);
struct icmphdr *icmph;
struct iphdr *niph;
struct ethhdr eh;
int len, err;
if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
return -EINVAL;
if (skb_is_gso(skb))
skb_gso_reset(skb);
skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
pskb_pull(skb, ETH_HLEN);
skb_reset_network_header(skb);
err = pskb_trim(skb, 576 - sizeof(*niph) - sizeof(*icmph));
if (err)
return err;
len = skb->len + sizeof(*icmph);
err = skb_cow(skb, sizeof(*niph) + sizeof(*icmph) + ETH_HLEN);
if (err)
return err;
icmph = skb_push(skb, sizeof(*icmph));
*icmph = (struct icmphdr) {
.type = ICMP_DEST_UNREACH,
.code = ICMP_FRAG_NEEDED,
.checksum = 0,
.un.frag.__unused = 0,
.un.frag.mtu = htons(mtu),
};
icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0));
skb_reset_transport_header(skb);
niph = skb_push(skb, sizeof(*niph));
*niph = (struct iphdr) {
.ihl = sizeof(*niph) / 4u,
.version = 4,
.tos = 0,
.tot_len = htons(len + sizeof(*niph)),
.id = 0,
.frag_off = htons(IP_DF),
.ttl = iph->ttl,
.protocol = IPPROTO_ICMP,
.saddr = iph->daddr,
.daddr = iph->saddr,
};
ip_send_check(niph);
skb_reset_network_header(skb);
skb->ip_summed = CHECKSUM_NONE;
eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0);
skb_reset_mac_header(skb);
return skb->len;
}
static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu)
{
const struct icmphdr *icmph = icmp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
if (mtu < 576 || iph->frag_off != htons(IP_DF))
return 0;
if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) ||
ipv4_is_zeronet(iph->saddr) || ipv4_is_loopback(iph->saddr) ||
ipv4_is_lbcast(iph->saddr) || ipv4_is_multicast(iph->saddr))
return 0;
if (iph->protocol == IPPROTO_ICMP && icmp_is_err(icmph->type))
return 0;
return iptunnel_pmtud_build_icmp(skb, mtu);
}
#if IS_ENABLED(CONFIG_IPV6)
static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct icmp6hdr *icmp6h;
struct ipv6hdr *nip6h;
struct ethhdr eh;
int len, err;
__wsum csum;
if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
return -EINVAL;
if (skb_is_gso(skb))
skb_gso_reset(skb);
skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
pskb_pull(skb, ETH_HLEN);
skb_reset_network_header(skb);
err = pskb_trim(skb, IPV6_MIN_MTU - sizeof(*nip6h) - sizeof(*icmp6h));
if (err)
return err;
len = skb->len + sizeof(*icmp6h);
err = skb_cow(skb, sizeof(*nip6h) + sizeof(*icmp6h) + ETH_HLEN);
if (err)
return err;
icmp6h = skb_push(skb, sizeof(*icmp6h));
*icmp6h = (struct icmp6hdr) {
.icmp6_type = ICMPV6_PKT_TOOBIG,
.icmp6_code = 0,
.icmp6_cksum = 0,
.icmp6_mtu = htonl(mtu),
};
skb_reset_transport_header(skb);
nip6h = skb_push(skb, sizeof(*nip6h));
*nip6h = (struct ipv6hdr) {
.priority = 0,
.version = 6,
.flow_lbl = { 0 },
.payload_len = htons(len),
.nexthdr = IPPROTO_ICMPV6,
.hop_limit = ip6h->hop_limit,
.saddr = ip6h->daddr,
.daddr = ip6h->saddr,
};
skb_reset_network_header(skb);
csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
IPPROTO_ICMPV6, csum);
skb->ip_summed = CHECKSUM_NONE;
eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0);
skb_reset_mac_header(skb);
return skb->len;
}
static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
int stype = ipv6_addr_type(&ip6h->saddr);
u8 proto = ip6h->nexthdr;
__be16 frag_off;
int offset;
if (mtu < IPV6_MIN_MTU)
return 0;
if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
stype == IPV6_ADDR_LOOPBACK)
return 0;
offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto,
&frag_off);
if (offset < 0 || (frag_off & htons(~0x7)))
return 0;
if (proto == IPPROTO_ICMPV6) {
struct icmp6hdr *icmp6h;
if (!pskb_may_pull(skb, skb_network_header(skb) +
offset + 1 - skb->data))
return 0;
icmp6h = (struct icmp6hdr *)(skb_network_header(skb) + offset);
if (icmpv6_is_err(icmp6h->icmp6_type) ||
icmp6h->icmp6_type == NDISC_REDIRECT)
return 0;
}
return iptunnel_pmtud_build_icmpv6(skb, mtu);
}
#endif
int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
int headroom, bool reply)
{
u32 mtu = dst_mtu(encap_dst) - headroom;
if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
(!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
return 0;
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (!reply)
return 0;
if (skb->protocol == htons(ETH_P_IP))
return iptunnel_pmtud_check_icmp(skb, mtu);
#if IS_ENABLED(CONFIG_IPV6)
if (skb->protocol == htons(ETH_P_IPV6))
return iptunnel_pmtud_check_icmpv6(skb, mtu);
#endif
return 0;
}
EXPORT_SYMBOL(skb_tunnel_check_pmtu);
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS },
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP_DST] = { .type = NLA_U32 },
[LWTUNNEL_IP_SRC] = { .type = NLA_U32 },
[LWTUNNEL_IP_TTL] = { .type = NLA_U8 },
[LWTUNNEL_IP_TOS] = { .type = NLA_U8 },
[LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 },
[LWTUNNEL_IP_OPTS] = { .type = NLA_NESTED },
};
static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = {
[LWTUNNEL_IP_OPTS_GENEVE] = { .type = NLA_NESTED },
[LWTUNNEL_IP_OPTS_VXLAN] = { .type = NLA_NESTED },
[LWTUNNEL_IP_OPTS_ERSPAN] = { .type = NLA_NESTED },
};
static const struct nla_policy
geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
[LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 },
[LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 },
[LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 },
};
static const struct nla_policy
vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = {
[LWTUNNEL_IP_OPT_VXLAN_GBP] = { .type = NLA_U32 },
};
static const struct nla_policy
erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = {
[LWTUNNEL_IP_OPT_ERSPAN_VER] = { .type = NLA_U8 },
[LWTUNNEL_IP_OPT_ERSPAN_INDEX] = { .type = NLA_U32 },
[LWTUNNEL_IP_OPT_ERSPAN_DIR] = { .type = NLA_U8 },
[LWTUNNEL_IP_OPT_ERSPAN_HWID] = { .type = NLA_U8 },
};
static int ip_tun_parse_opts_geneve(struct nlattr *attr,
struct ip_tunnel_info *info, int opts_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1];
int data_len, err;
err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr,
geneve_opt_policy, extack);
if (err)
return err;
if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] ||
!tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] ||
!tb[LWTUNNEL_IP_OPT_GENEVE_DATA])
return -EINVAL;
attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA];
data_len = nla_len(attr);
if (data_len % 4)
return -EINVAL;
if (info) {
struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len;
memcpy(opt->opt_data, nla_data(attr), data_len);
opt->length = data_len / 4;
attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS];
opt->opt_class = nla_get_be16(attr);
attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
opt->type = nla_get_u8(attr);
__set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags);
}
return sizeof(struct geneve_opt) + data_len;
}
static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
struct ip_tunnel_info *info, int opts_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1];
int err;
err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr,
vxlan_opt_policy, extack);
if (err)
return err;
if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP])
return -EINVAL;
if (info) {
struct vxlan_metadata *md =
ip_tunnel_info_opts(info) + opts_len;
attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
md->gbp = nla_get_u32(attr);
md->gbp &= VXLAN_GBP_MASK;
__set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags);
}
return sizeof(struct vxlan_metadata);
}
static int ip_tun_parse_opts_erspan(struct nlattr *attr,
struct ip_tunnel_info *info, int opts_len,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1];
int err;
u8 ver;
err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr,
erspan_opt_policy, extack);
if (err)
return err;
if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER])
return -EINVAL;
ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]);
if (ver == 1) {
if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX])
return -EINVAL;
} else if (ver == 2) {
if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] ||
!tb[LWTUNNEL_IP_OPT_ERSPAN_HWID])
return -EINVAL;
} else {
return -EINVAL;
}
if (info) {
struct erspan_metadata *md =
ip_tunnel_info_opts(info) + opts_len;
md->version = ver;
if (ver == 1) {
attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX];
md->u.index = nla_get_be32(attr);
} else {
attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR];
md->u.md2.dir = nla_get_u8(attr);
attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID];
set_hwid(&md->u.md2, nla_get_u8(attr));
}
__set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags);
}
return sizeof(struct erspan_metadata);
}
static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
struct netlink_ext_ack *extack)
{
int err, rem, opt_len, opts_len = 0;
struct nlattr *nla;
u32 type = 0;
if (!attr)
return 0;
err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX,
ip_opts_policy, extack);
if (err)
return err;
nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) {
switch (nla_type(nla)) {
case LWTUNNEL_IP_OPTS_GENEVE:
if (type && type != IP_TUNNEL_GENEVE_OPT_BIT)
return -EINVAL;
opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len,
extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
if (opts_len > IP_TUNNEL_OPTS_MAX)
return -EINVAL;
type = IP_TUNNEL_GENEVE_OPT_BIT;
break;
case LWTUNNEL_IP_OPTS_VXLAN:
if (type)
return -EINVAL;
opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len,
extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
type = IP_TUNNEL_VXLAN_OPT_BIT;
break;
case LWTUNNEL_IP_OPTS_ERSPAN:
if (type)
return -EINVAL;
opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len,
extack);
if (opt_len < 0)
return opt_len;
opts_len += opt_len;
type = IP_TUNNEL_ERSPAN_OPT_BIT;
break;
default:
return -EINVAL;
}
}
return opts_len;
}
static int ip_tun_get_optlen(struct nlattr *attr,
struct netlink_ext_ack *extack)
{
return ip_tun_parse_opts(attr, NULL, extack);
}
static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info,
struct netlink_ext_ack *extack)
{
return ip_tun_parse_opts(attr, info, extack);
}
static int ip_tun_build_state(struct net *net, struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
struct lwtunnel_state *new_state;
struct ip_tunnel_info *tun_info;
int err, opt_len;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
ip_tun_policy, extack);
if (err < 0)
return err;
opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack);
if (opt_len < 0)
return opt_len;
new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP;
tun_info = lwt_tun_info(new_state);
err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack);
if (err < 0) {
lwtstate_free(new_state);
return err;
}
#ifdef CONFIG_DST_CACHE
err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
if (err) {
lwtstate_free(new_state);
return err;
}
#endif
if (tb[LWTUNNEL_IP_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]);
if (tb[LWTUNNEL_IP_DST])
tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]);
if (tb[LWTUNNEL_IP_SRC])
tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]);
if (tb[LWTUNNEL_IP_TTL])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]);
if (tb[LWTUNNEL_IP_TOS])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
if (tb[LWTUNNEL_IP_FLAGS]) {
IP_TUNNEL_DECLARE_FLAGS(flags);
ip_tunnel_flags_from_be16(flags,
nla_get_be16(tb[LWTUNNEL_IP_FLAGS]));
ip_tunnel_clear_options_present(flags);
ip_tunnel_flags_or(tun_info->key.tun_flags,
tun_info->key.tun_flags, flags);
}
tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->options_len = opt_len;
*ts = new_state;
return 0;
}
static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
{
#ifdef CONFIG_DST_CACHE
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
dst_cache_destroy(&tun_info->dst_cache);
#endif
}
static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb,
struct ip_tunnel_info *tun_info)
{
struct geneve_opt *opt;
struct nlattr *nest;
int offset = 0;
nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE);
if (!nest)
return -ENOMEM;
while (tun_info->options_len > offset) {
opt = ip_tunnel_info_opts(tun_info) + offset;
if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS,
opt->opt_class) ||
nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) ||
nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4,
opt->opt_data)) {
nla_nest_cancel(skb, nest);
return -ENOMEM;
}
offset += sizeof(*opt) + opt->length * 4;
}
nla_nest_end(skb, nest);
return 0;
}
static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb,
struct ip_tunnel_info *tun_info)
{
struct vxlan_metadata *md;
struct nlattr *nest;
nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN);
if (!nest)
return -ENOMEM;
md = ip_tunnel_info_opts(tun_info);
if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) {
nla_nest_cancel(skb, nest);
return -ENOMEM;
}
nla_nest_end(skb, nest);
return 0;
}
static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb,
struct ip_tunnel_info *tun_info)
{
struct erspan_metadata *md;
struct nlattr *nest;
nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN);
if (!nest)
return -ENOMEM;
md = ip_tunnel_info_opts(tun_info);
if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version))
goto err;
if (md->version == 1 &&
nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index))
goto err;
if (md->version == 2 &&
(nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) ||
nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID,
get_hwid(&md->u.md2))))
goto err;
nla_nest_end(skb, nest);
return 0;
err:
nla_nest_cancel(skb, nest);
return -ENOMEM;
}
static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
struct ip_tunnel_info *tun_info)
{
struct nlattr *nest;
int err = 0;
if (!ip_tunnel_is_options_present(tun_info->key.tun_flags))
return 0;
nest = nla_nest_start_noflag(skb, type);
if (!nest)
return -ENOMEM;
if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags))
err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags))
err = ip_tun_fill_encap_opts_vxlan(skb, tun_info);
else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags))
err = ip_tun_fill_encap_opts_erspan(skb, tun_info);
if (err) {
nla_nest_cancel(skb, nest);
return err;
}
nla_nest_end(skb, nest);
return 0;
}
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id,
LWTUNNEL_IP_PAD) ||
nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) ||
nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP_FLAGS,
ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) ||
ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
return -ENOMEM;
return 0;
}
static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
{
int opt_len;
if (!ip_tunnel_is_options_present(info->key.tun_flags))
return 0;
opt_len = nla_total_size(0);
if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) {
struct geneve_opt *opt;
int offset = 0;
opt_len += nla_total_size(0);
while (info->options_len > offset) {
opt = ip_tunnel_info_opts(info) + offset;
opt_len += nla_total_size(2)
+ nla_total_size(1)
+ nla_total_size(opt->length * 4);
offset += sizeof(*opt) + opt->length * 4;
}
} else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) {
opt_len += nla_total_size(0)
+ nla_total_size(4);
} else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) {
struct erspan_metadata *md = ip_tunnel_info_opts(info);
opt_len += nla_total_size(0)
+ nla_total_size(1)
+ (md->version == 1 ? nla_total_size(4)
: nla_total_size(1) +
nla_total_size(1));
}
return opt_len;
}
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8)
+ nla_total_size(4)
+ nla_total_size(4)
+ nla_total_size(1)
+ nla_total_size(1)
+ nla_total_size(2)
+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
}
static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
struct ip_tunnel_info *info_a = lwt_tun_info(a);
struct ip_tunnel_info *info_b = lwt_tun_info(b);
return memcmp(info_a, info_b, sizeof(info_a->key)) ||
info_a->mode != info_b->mode ||
info_a->options_len != info_b->options_len ||
memcmp(ip_tunnel_info_opts(info_a),
ip_tunnel_info_opts(info_b), info_a->options_len);
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
.build_state = ip_tun_build_state,
.destroy_state = ip_tun_destroy_state,
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
[LWTUNNEL_IP6_UNSPEC] = { .strict_start_type = LWTUNNEL_IP6_OPTS },
[LWTUNNEL_IP6_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 },
[LWTUNNEL_IP6_TC] = { .type = NLA_U8 },
[LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 },
[LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED },
};
static int ip6_tun_build_state(struct net *net, struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
struct lwtunnel_state *new_state;
struct ip_tunnel_info *tun_info;
int err, opt_len;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
ip6_tun_policy, extack);
if (err < 0)
return err;
opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack);
if (opt_len < 0)
return opt_len;
new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len);
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP6;
tun_info = lwt_tun_info(new_state);
err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack);
if (err < 0) {
lwtstate_free(new_state);
return err;
}
if (tb[LWTUNNEL_IP6_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
if (tb[LWTUNNEL_IP6_DST])
tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]);
if (tb[LWTUNNEL_IP6_SRC])
tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]);
if (tb[LWTUNNEL_IP6_HOPLIMIT])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]);
if (tb[LWTUNNEL_IP6_TC])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
if (tb[LWTUNNEL_IP6_FLAGS]) {
IP_TUNNEL_DECLARE_FLAGS(flags);
__be16 data;
data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
ip_tunnel_flags_from_be16(flags, data);
ip_tunnel_clear_options_present(flags);
ip_tunnel_flags_or(tun_info->key.tun_flags,
tun_info->key.tun_flags, flags);
}
tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
tun_info->options_len = opt_len;
*ts = new_state;
return 0;
}
static int ip6_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id,
LWTUNNEL_IP6_PAD) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP6_FLAGS,
ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) ||
ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
return -ENOMEM;
return 0;
}
static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8)
+ nla_total_size(16)
+ nla_total_size(16)
+ nla_total_size(1)
+ nla_total_size(1)
+ nla_total_size(2)
+ ip_tun_opts_nlsize(lwt_tun_info(lwtstate));
}
static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
.build_state = ip6_tun_build_state,
.fill_encap = ip6_tun_fill_encap_info,
.get_encap_size = ip6_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
void __init ip_tunnel_core_init(void)
{
BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255);
lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}
DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
__be16 ip_tunnel_parse_protocol(const struct sk_buff *skb)
{
if (skb_network_header(skb) >= skb->head &&
(skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) &&
ip_hdr(skb)->version == 4)
return htons(ETH_P_IP);
if (skb_network_header(skb) >= skb->head &&
(skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) &&
ipv6_hdr(skb)->version == 6)
return htons(ETH_P_IPV6);
return 0;
}
EXPORT_SYMBOL(ip_tunnel_parse_protocol);
const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol };
EXPORT_SYMBOL(ip_tunnel_header_ops);
bool ip_tunnel_netlink_encap_parms(struct nlattr *data[],
struct ip_tunnel_encap *encap)
{
bool ret = false;
memset(encap, 0, sizeof(*encap));
if (!data)
return ret;
if (data[IFLA_IPTUN_ENCAP_TYPE]) {
ret = true;
encap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
}
if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
ret = true;
encap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
}
if (data[IFLA_IPTUN_ENCAP_SPORT]) {
ret = true;
encap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
}
if (data[IFLA_IPTUN_ENCAP_DPORT]) {
ret = true;
encap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
}
return ret;
}
EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms);
void ip_tunnel_netlink_parms(struct nlattr *data[],
struct ip_tunnel_parm_kern *parms)
{
if (data[IFLA_IPTUN_LINK])
parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
if (data[IFLA_IPTUN_LOCAL])
parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]);
if (data[IFLA_IPTUN_REMOTE])
parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]);
if (data[IFLA_IPTUN_TTL]) {
parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]);
if (parms->iph.ttl)
parms->iph.frag_off = htons(IP_DF);
}
if (data[IFLA_IPTUN_TOS])
parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);
if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
parms->iph.frag_off = htons(IP_DF);
if (data[IFLA_IPTUN_FLAGS]) {
__be16 flags;
flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
ip_tunnel_flags_from_be16(parms->i_flags, flags);
}
if (data[IFLA_IPTUN_PROTO])
parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
}
EXPORT_SYMBOL_GPL(ip_tunnel_netlink_parms);
