/* * IPv6 tunneling device * Linux INET6 implementation * * Authors: * Ville Nuorvala * Yasuyuki Kozakai * * Based on: * linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c * * RFC 2473 * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Changes: * Steven Barth : MAP-E FMR support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #define HASH_SIZE_SHIFT 5 #define HASH_SIZE (1 << HASH_SIZE_SHIFT) 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"); static u32 HASH(const struct in6_addr *addr) { return hash_32(ipv6_addr_hash(addr), HASH_SIZE_SHIFT); } static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static struct rtnl_link_ops ip6_link_ops __read_mostly; static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; }; static struct net_device_stats *ip6_get_stats(struct net_device *dev) { struct pcpu_sw_netstats tmp, sum = { 0 }; int i; for_each_possible_cpu(i) { unsigned int start; const struct pcpu_sw_netstats *tstats = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin_irq(&tstats->syncp); tmp.rx_packets = tstats->rx_packets; tmp.rx_bytes = tstats->rx_bytes; tmp.tx_packets = tstats->tx_packets; tmp.tx_bytes = tstats->tx_bytes; } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); sum.rx_packets += tmp.rx_packets; sum.rx_bytes += tmp.rx_bytes; sum.tx_packets += tmp.tx_packets; sum.tx_bytes += tmp.tx_bytes; } dev->stats.rx_packets = sum.rx_packets; dev->stats.rx_bytes = sum.rx_bytes; dev->stats.tx_packets = sum.tx_packets; dev->stats.tx_bytes = sum.tx_bytes; return &dev->stats; } /* * Update offload stats */ void ip6_update_offload_stats(struct net_device *dev, void *ptr) { struct pcpu_sw_netstats *tstats = per_cpu_ptr(dev->tstats, 0); const struct pcpu_sw_netstats *offload_stats = (struct pcpu_sw_netstats *)ptr; u64_stats_update_begin(&tstats->syncp); tstats->tx_packets += offload_stats->tx_packets; tstats->tx_bytes += offload_stats->tx_bytes; tstats->rx_packets += offload_stats->rx_packets; tstats->rx_bytes += offload_stats->rx_bytes; u64_stats_update_end(&tstats->syncp); } EXPORT_SYMBOL(ip6_update_offload_stats); /* * Locking : hash tables are protected by RCU and RTNL */ static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, struct dst_entry *dst) { write_seqlock_bh(&idst->lock); dst_release(rcu_dereference_protected( idst->dst, lockdep_is_held(&idst->lock.lock))); if (dst) { dst_hold(dst); idst->cookie = rt6_get_cookie((struct rt6_info *)dst); } else { idst->cookie = 0; } rcu_assign_pointer(idst->dst, dst); write_sequnlock_bh(&idst->lock); } struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) { struct ip6_tnl_dst *idst; struct dst_entry *dst; unsigned int seq; u32 cookie; idst = raw_cpu_ptr(t->dst_cache); rcu_read_lock(); do { seq = read_seqbegin(&idst->lock); dst = rcu_dereference(idst->dst); cookie = idst->cookie; } while (read_seqretry(&idst->lock, seq)); if (dst && !atomic_inc_not_zero(&dst->__refcnt)) dst = NULL; rcu_read_unlock(); if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) { ip6_tnl_per_cpu_dst_set(idst, NULL); dst_release(dst); dst = NULL; } return dst; } EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); void ip6_tnl_dst_reset(struct ip6_tnl *t) { int i; for_each_possible_cpu(i) ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) { ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); void ip6_tnl_dst_destroy(struct ip6_tnl *t) { if (!t->dst_cache) return; ip6_tnl_dst_reset(t); free_percpu(t->dst_cache); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy); int ip6_tnl_dst_init(struct ip6_tnl *t) { int i; t->dst_cache = alloc_percpu(struct ip6_tnl_dst); if (!t->dst_cache) return -ENOMEM; for_each_possible_cpu(i) seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock); return 0; } EXPORT_SYMBOL_GPL(ip6_tnl_dst_init); /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ #define for_each_ip6_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip6_tnl * ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(local); struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct in6_addr any; struct __ip6_tnl_fmr *fmr; for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !(t->dev->flags & IFF_UP)) continue; if (ipv6_addr_equal(remote, &t->parms.raddr)) return t; for (fmr = t->parms.fmrs; fmr; fmr = fmr->next) { if (ipv6_prefix_equal(remote, &fmr->ip6_prefix, fmr->ip6_prefix_len)) return t; } } memset(&any, 0, sizeof(any)); hash = HASH(local); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_any(&t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } hash = HASH(&any); for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(remote, &t->parms.raddr) && ipv6_addr_any(&t->parms.laddr) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * ip6_tnl_bucket - get head of list matching given tunnel parameters * @p: parameters containing tunnel end-points * * Description: * ip6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(local); } return &ip6n->tnls[prio][h]; } /** * ip6_tnl_link - add tunnel to hash table * @t: tunnel to be added **/ static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } /** * ip6_tnl_unlink - remove tunnel from hash table * @t: tunnel to be removed **/ static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; for (tp = ip6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ip6_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } static int ip6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; t = netdev_priv(dev); dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); dev_hold(dev); ip6_tnl_link(ip6n, t); return 0; out: return err; } /** * ip6_tnl_create - create a new tunnel * @p: tunnel parameters * @pt: pointer to new tunnel * * Description: * Create tunnel matching given parameters. * * Return: * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err = -ENOMEM; if (p->name[0]) strlcpy(name, p->name, IFNAMSIZ); else sprintf(name, "ip6tnl%%d"); dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: ip6_dev_free(dev); failed: return ERR_PTR(err); } /** * ip6_tnl_locate - find or create tunnel matching given parameters * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * ip6_tnl_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); for (tp = ip6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) return ERR_PTR(-EEXIST); return t; } } if (!create) return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } /** * ip6_tnl_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * ip6_tnl_dev_uninit() removes tunnel from its list **/ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); while (t->parms.fmrs) { struct __ip6_tnl_fmr *next = t->parms.fmrs->next; kfree(t->parms.fmrs); t->parms.fmrs = next; } if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); ip6_tnl_dst_reset(t); dev_put(dev); } /** * parse_tvl_tnl_enc_lim - handle encapsulation limit option * @skb: received socket buffer * * Return: * 0 if none was found, * else index to encapsulation limit **/ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); u8 next, nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; u16 optlen; if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; if (frag_hdr->frag_off) break; optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = (hdr->hdrlen + 2) << 2; } else { optlen = ipv6_optlen(hdr); } /* cache hdr->nexthdr, since pskb_may_pull() might * invalidate hdr */ next = hdr->nexthdr; if (nexthdr == NEXTHDR_DEST) { u16 i = 2; /* Remember : hdr is no longer valid at this point. */ if (!pskb_may_pull(skb, off + optlen)) break; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; /* No more room for encapsulation limit */ if (i + sizeof(*tel) > optlen) break; tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i); /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; else i++; } } nexthdr = next; off += optlen; } return 0; } EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /** * ip6_tnl_err - tunnel error handler * * Description: * ip6_tnl_err() should handle errors in the tunnel according * to the specifications in RFC 2473. **/ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) skb->data; struct ip6_tnl *t; int rel_msg = 0; u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; u8 tproto; __u32 rel_info = 0; __u16 len; int err = -ENOENT; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further processing of the error. */ rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr); if (!t) goto out; tproto = ACCESS_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; err = 0; switch (*type) { __u32 teli; struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } break; case ICMPV6_PARAMPROB: teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } } else { net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } break; case ICMPV6_PKT_TOOBIG: mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; t->dev->mtu = mtu; len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; rel_msg = 1; } break; } *type = rel_type; *code = rel_code; *info = rel_info; *msg = rel_msg; out: rcu_read_unlock(); return err; } static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; u8 rel_type = type; u8 rel_code = code; __u32 rel_info = ntohl(info); int err; struct sk_buff *skb2; const struct iphdr *eiph; struct rtable *rt; struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg == 0) return 0; switch (rel_type) { case ICMPV6_DEST_UNREACH: if (rel_code != ICMPV6_ADDR_UNREACH) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; break; case ICMPV6_PKT_TOOBIG: if (rel_code != 0) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; case NDISC_REDIRECT: rel_type = ICMP_REDIRECT; rel_code = ICMP_REDIR_HOST; default: return 0; } if (!pskb_may_pull(skb, offset + sizeof(struct iphdr))) return 0; skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); rt = NULL; rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { ip_rt_put(rt); if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { if (rel_info > dst_mtu(skb_dst(skb2))) goto out; skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); } if (rel_type == ICMP_REDIRECT) skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); out: kfree_skb(skb2); return 0; } static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { int rel_msg = 0; u8 rel_type = type; u8 rel_code = code; __u32 rel_info = ntohl(info); int err; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); ip6_rt_put(rt); kfree_skb(skb2); } return 0; } static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); return IP6_ECN_decapsulate(ipv6h, skb); } static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); return IP6_ECN_decapsulate(ipv6h, skb); } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ltype = ipv6_addr_type(laddr); int rtype = ipv6_addr_type(raddr); __u32 flags = 0; if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { flags = IP6_TNL_F_CAP_PER_PACKET; } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { if (ltype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_XMIT; if (rtype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_RCV; } return flags; } EXPORT_SYMBOL(ip6_tnl_get_cap); /* called with rcu_read_lock() */ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_RCV) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr(net, laddr, ldev, 0))) && likely(!ipv6_chk_addr(net, raddr, NULL, 0))) ret = 1; } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); /** * ip4ip6_fmr_calc - calculate target / source IPv6-address based on FMR * @dest: destination IPv6 address buffer * @skb: received socket buffer * @fmr: MAP FMR * @xmit: Calculate for xmit or rcv **/ static void ip4ip6_fmr_calc(struct in6_addr *dest, const struct iphdr *iph, const uint8_t *end, const struct __ip6_tnl_fmr *fmr, bool xmit, bool draft03) { int psidlen = fmr->ea_len - (32 - fmr->ip4_prefix_len); u8 *portp = NULL; bool use_dest_addr; const struct iphdr *dsth = iph; if ((u8*)dsth >= end) return; /* find significant IP header */ if (iph->protocol == IPPROTO_ICMP) { struct icmphdr *ih = (struct icmphdr*)(((u8*)dsth) + dsth->ihl * 4); if (ih && ((u8*)&ih[1]) <= end && ( ih->type == ICMP_DEST_UNREACH || ih->type == ICMP_SOURCE_QUENCH || ih->type == ICMP_TIME_EXCEEDED || ih->type == ICMP_PARAMETERPROB || ih->type == ICMP_REDIRECT)) dsth = (const struct iphdr*)&ih[1]; } /* in xmit-path use dest port by default and source port only if this is an ICMP reply to something else; vice versa in rcv-path */ use_dest_addr = (xmit && dsth == iph) || (!xmit && dsth != iph); /* get dst port */ if (((u8 *)&dsth[1]) <= end && ( dsth->protocol == IPPROTO_UDP || dsth->protocol == IPPROTO_TCP || dsth->protocol == IPPROTO_SCTP || dsth->protocol == IPPROTO_DCCP)) { /* for UDP, TCP, SCTP and DCCP source and dest port follow IPv4 header directly */ portp = ((u8*)dsth) + dsth->ihl * 4; if (use_dest_addr) portp += sizeof(u16); } else if (iph->protocol == IPPROTO_ICMP) { struct icmphdr *ih = (struct icmphdr*)(((u8*)dsth) + dsth->ihl * 4); /* use icmp identifier as port */ if (((u8 *)ih) <= end && ( (use_dest_addr && ( ih->type == ICMP_ECHOREPLY || ih->type == ICMP_TIMESTAMPREPLY || ih->type == ICMP_INFO_REPLY || ih->type == ICMP_ADDRESSREPLY)) || (!use_dest_addr && ( ih->type == ICMP_ECHO || ih->type == ICMP_TIMESTAMP || ih->type == ICMP_INFO_REQUEST || ih->type == ICMP_ADDRESS) ))) portp = (u8*)&ih->un.echo.id; } if ((portp && &portp[2] <= end) || psidlen == 0) { int frombyte = fmr->ip6_prefix_len / 8; int fromrem = fmr->ip6_prefix_len % 8; int bytes = sizeof(struct in6_addr) - frombyte; const u32 *addr = (use_dest_addr) ? &iph->daddr : &iph->saddr; u64 eabits = ((u64)ntohl(*addr)) << (32 + fmr->ip4_prefix_len); u64 t = 0; /* extract PSID from port and add it to eabits */ u16 psidbits = 0; if (psidlen > 0) { psidbits = ((u16)portp[0]) << 8 | ((u16)portp[1]); psidbits >>= 16 - psidlen - fmr->offset; psidbits = (u16)(psidbits << (16 - psidlen)); eabits |= ((u64)psidbits) << (48 - (fmr->ea_len - psidlen)); } /* rewrite destination address */ *dest = fmr->ip6_prefix; memcpy(&dest->s6_addr[10], addr, sizeof(*addr)); dest->s6_addr16[7] = htons(psidbits >> (16 - psidlen)); if (bytes > sizeof(u64)) bytes = sizeof(u64); /* insert eabits */ memcpy(&t, &dest->s6_addr[frombyte], bytes); t = be64_to_cpu(t) & ~(((((u64)1) << fmr->ea_len) - 1) << (64 - fmr->ea_len - fromrem)); t = cpu_to_be64(t | (eabits >> fromrem)); memcpy(&dest->s6_addr[frombyte], &t, bytes); if (draft03) { /** * Draft03 IPv6 address format * +--+---+---+---+---+---+---+---+---+ * |PL| 8 16 24 32 40 48 56 | * +--+---+---+---+---+---+---+---+---+ * |64| u | IPv4 address |PSID |0 | * +--+---+---+---+---+---+---+---+---+ * Final specification IPv6 address format * +--+---+---+---+---+---+---+---+---+ * |PL| 8 16 24 32 40 48 56 | * +--+---+---+---+---+---+---+---+---+ * |64| 0 | IPv4 address |PSID | * +--+---+---+---+---+---+---+---+---+ * We need move last six Bytes 1 byte forward */ memmove(&dest->s6_addr[9], &dest->s6_addr[10], 6); } } } /** * ip6_tnl_rcv - decapsulate IPv6 packet and retransmit it locally * @skb: received socket buffer * @protocol: ethernet protocol ID * @dscp_ecn_decapsulate: the function to decapsulate DSCP code and ECN * * Return: 0 **/ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, __u8 ipproto, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); u8 tproto; int err; rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { struct pcpu_sw_netstats *tstats; tproto = ACCESS_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) { rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); goto discard; } if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; } skb->mac_header = skb->network_header; skb_reset_network_header(skb); skb->protocol = htons(protocol); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); if (protocol == ETH_P_IP && !ipv6_addr_equal(&ipv6h->saddr, &t->parms.raddr)) { /* Packet didn't come from BR, so lookup FMR */ struct __ip6_tnl_fmr *fmr; struct in6_addr expected = t->parms.raddr; for (fmr = t->parms.fmrs; fmr; fmr = fmr->next) if (ipv6_prefix_equal(&ipv6h->saddr, &fmr->ip6_prefix, fmr->ip6_prefix_len)) break; /* Check that IPv6 matches IPv4 source to prevent spoofing */ if (fmr) ip4ip6_fmr_calc(&expected, ip_hdr(skb), skb_tail_pointer(skb), fmr, false, t->parms.draft03); if (!ipv6_addr_equal(&ipv6h->saddr, &expected)) { rcu_read_unlock(); goto discard; } } __skb_tunnel_rx(skb, t->dev, t->net); err = dscp_ecn_decapsulate(t, ipv6h, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", &ipv6h->saddr, ipv6_get_dsfield(ipv6h)); if (err > 1) { ++t->dev->stats.rx_frame_errors; ++t->dev->stats.rx_errors; rcu_read_unlock(); goto discard; } } tstats = this_cpu_ptr(t->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); /* Reset the skb_iif to Tunnels interface index */ skb->skb_iif = t->dev->ifindex; netif_rx(skb); rcu_read_unlock(); return 0; } rcu_read_unlock(); return 1; discard: kfree_skb(skb); return 0; } static int ip4ip6_rcv(struct sk_buff *skb) { return ip6_tnl_rcv(skb, ETH_P_IP, IPPROTO_IPIP, ip4ip6_dscp_ecn_decapsulate); } static int ip6ip6_rcv(struct sk_buff *skb) { return ip6_tnl_rcv(skb, ETH_P_IPV6, IPPROTO_IPV6, ip6ip6_dscp_ecn_decapsulate); } struct ipv6_tel_txoption { struct ipv6_txoptions ops; __u8 dst_opt[8]; }; static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) { memset(opt, 0, sizeof(struct ipv6_tel_txoption)); opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; opt->dst_opt[3] = 1; opt->dst_opt[4] = encap_limit; opt->dst_opt[5] = IPV6_TLV_PADN; opt->dst_opt[6] = 1; opt->ops.dst0opt = (struct ipv6_opt_hdr *) opt->dst_opt; opt->ops.opt_nflen = 8; } /** * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_XMIT) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) { struct net_device *ldev = NULL; rcu_read_lock(); if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0))) pr_warn("%s xmit: Local address not yet configured!\n", p->name); else if (!ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr(net, raddr, NULL, 0))) pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", p->name); else ret = 1; rcu_read_unlock(); } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); /** * ip6_tnl_xmit2 - encapsulate packet and send * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @dsfield: dscp code for outer header * @fl: flow of tunneled packet * @encap_limit: encapsulation limit * @pmtu: Path MTU is stored if packet is too big * * Description: * Build new header and do some sanity checks on the packet before sending * it. * * Return: * 0 on success * -1 fail * %-EMSGSIZE message too big. return mtu in this case. **/ static int ip6_tnl_xmit2(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, __u32 *pmtu) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; bool use_cache = false; int mtu; unsigned int max_headroom = sizeof(struct ipv6hdr); u8 proto; int err = -1; /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { struct in6_addr *addr6; struct neighbour *neigh; int addr_type; if (!skb_dst(skb)) goto tx_err_link_failure; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_err_link_failure; addr6 = (struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) addr6 = &ipv6_hdr(skb)->daddr; memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (!(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only only if the routing decision does * not depend on the current inner header value */ use_cache = true; } if (use_cache) dst = ip6_tnl_dst_get(t); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { dst = ip6_route_output(net, NULL, fl6); if (dst->error) goto tx_err_link_failure; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } ndst = dst; } tdev = dst->dev; if (tdev == dev) { stats->collisions++; net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst) - sizeof(*ipv6h); if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; } skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb; new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } if (use_cache && ndst) ip6_tnl_dst_set(t, ndst); skb_dst_set(skb, dst); skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL); } if (likely(!skb->encapsulation)) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; /* Reset the skb_iif to Tunnels interface index */ skb->skb_iif = dev->ifindex; ip6tunnel_xmit(NULL, skb, dev); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static inline int ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); const struct iphdr *iph = ip_hdr(skb); int encap_limit = -1; struct flowi6 fl6; __u8 dsfield; __u32 mtu; u8 tproto; int err; struct __ip6_tnl_fmr *fmr; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_IPIP; dsfield = ipv4_get_dsfield(iph); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT) & IPV6_TCLASS_MASK; if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; /* try to find matching FMR */ for (fmr = t->parms.fmrs; fmr; fmr = fmr->next) { unsigned mshift = 32 - fmr->ip4_prefix_len; if (ntohl(fmr->ip4_prefix.s_addr) >> mshift == ntohl(iph->daddr) >> mshift) break; } /* change dstaddr according to FMR */ if (fmr) ip4ip6_fmr_calc(&fl6.daddr, iph, skb_tail_pointer(skb), fmr, true, t->parms.draft03); err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -1; } return 0; } static inline int ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h = ipv6_hdr(skb); int encap_limit = -1; __u16 offset; struct flowi6 fl6; __u8 dsfield; __u32 mtu; u8 tproto; int err; tproto = ACCESS_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || ip6_tnl_addr_conflict(t, ipv6h)) return -1; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_IPV6; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) fl6.flowlabel |= net_hdr_word(ipv6h) & IPV6_TCLASS_MASK; if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= ip6_flowlabel(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; err = ip6_tnl_xmit2(skb, dev, dsfield, &fl6, encap_limit, &mtu); if (err != 0) { if (err == -EMSGSIZE) icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } return 0; } static netdev_tx_t ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; int ret; switch (skb->protocol) { case htons(ETH_P_IP): ret = ip4ip6_tnl_xmit(skb, dev); break; case htons(ETH_P_IPV6): ret = ip6ip6_tnl_xmit(skb, dev); break; default: goto tx_err; } if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ fl6->saddr = p->laddr; fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, strict); if (!rt) return; if (rt->dst.dev) { dev->hard_header_len = rt->dst.dev->hard_header_len + sizeof(struct ipv6hdr); dev->mtu = rt->dst.dev->mtu - sizeof(struct ipv6hdr); if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } ip6_rt_put(rt); } } /** * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * * Description: * ip6_tnl_change() updates the tunnel parameters **/ static int ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; while (t->parms.fmrs) { struct __ip6_tnl_fmr *next = t->parms.fmrs->next; kfree(t->parms.fmrs); t->parms.fmrs = next; } t->parms.fmrs = p->fmrs; ip6_tnl_dst_reset(t); ip6_tnl_link_config(t); return 0; } static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; ip6_tnl_unlink(ip6n, t); synchronize_net(); err = ip6_tnl_change(t, p); ip6_tnl_link(ip6n, t); netdev_state_change(t->dev); return err; } static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { /* for default tnl0 device allow to change only the proto */ t->parms.proto = p->proto; netdev_state_change(t->dev); return 0; } static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->flags = u->flags; p->hop_limit = u->hop_limit; p->encap_limit = u->encap_limit; p->flowinfo = u->flowinfo; p->link = u->link; p->proto = u->proto; p->fmrs = NULL; memcpy(p->name, u->name, sizeof(u->name)); } static void ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->flags = p->flags; u->hop_limit = p->hop_limit; u->encap_limit = p->encap_limit; u->flowinfo = p->flowinfo; u->link = p->link; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * ip6_tnl_ioctl - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed * * Description: * ip6_tnl_ioctl() is used for managing IPv6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6tnl0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) { err = -EFAULT; } break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && p.proto != 0) break; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) err = ip6_tnl0_update(t, &p1); else err = ip6_tnl_update(t, &p1); } if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; } else { err = PTR_ERR(t); } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } /** * ip6_tnl_change_mtu - change mtu manually for tunnel device * @dev: virtual device associated with tunnel * @new_mtu: the new mtu * * Return: * 0 on success, * %-EINVAL if mtu too small **/ static int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); if (tnl->parms.proto == IPPROTO_IPIP) { if (new_mtu < 68) return -EINVAL; } else { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } if (new_mtu > 0xFFF8 - dev->hard_header_len) return -EINVAL; dev->mtu = new_mtu; return 0; } int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); return t->parms.link; } EXPORT_SYMBOL(ip6_tnl_get_iflink); static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_xmit, .ndo_do_ioctl = ip6_tnl_ioctl, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats = ip6_get_stats, .ndo_get_iflink = ip6_tnl_get_iflink, }; /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void ip6_tnl_dev_setup(struct net_device *dev) { struct ip6_tnl *t; dev->netdev_ops = &ip6_tnl_netdev_ops; dev->destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr); dev->mtu = ETH_DATA_LEN - sizeof(struct ipv6hdr); t = netdev_priv(dev); if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * ip6_tnl_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int ret; t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; ret = ip6_tnl_dst_init(t); if (ret) { free_percpu(dev->tstats); dev->tstats = NULL; return ret; } return 0; } /** * ip6_tnl_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = ip6_tnl_dev_init_gen(dev); if (err) return err; ip6_tnl_link_config(t); return 0; } /** * ip6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); t->parms.proto = IPPROTO_IPV6; dev_hold(dev); rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (proto != IPPROTO_IPV6 && proto != IPPROTO_IPIP && proto != 0) return -EINVAL; return 0; } static const struct nla_policy ip6_tnl_fmr_policy[IFLA_IPTUN_FMR_MAX + 1] = { [IFLA_IPTUN_FMR_IP6_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_FMR_IP4_PREFIX] = { .len = sizeof(struct in_addr) }, [IFLA_IPTUN_FMR_IP6_PREFIX_LEN] = { .type = NLA_U8 }, [IFLA_IPTUN_FMR_IP4_PREFIX_LEN] = { .type = NLA_U8 }, [IFLA_IPTUN_FMR_EA_LEN] = { .type = NLA_U8 }, [IFLA_IPTUN_FMR_OFFSET] = { .type = NLA_U8 } }; static void ip6_tnl_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); if (data[IFLA_IPTUN_ENCAP_LIMIT]) parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); if (data[IFLA_IPTUN_FLOWINFO]) parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); if (data[IFLA_IPTUN_FLAGS]) parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_DRAFT03]) parms->draft03 = nla_get_u8(data[IFLA_IPTUN_DRAFT03]); if (data[IFLA_IPTUN_FMRS]) { unsigned rem; struct nlattr *fmr; nla_for_each_nested(fmr, data[IFLA_IPTUN_FMRS], rem) { struct nlattr *fmrd[IFLA_IPTUN_FMR_MAX + 1], *c; struct __ip6_tnl_fmr *nfmr; nla_parse_nested(fmrd, IFLA_IPTUN_FMR_MAX, fmr, ip6_tnl_fmr_policy); if (!(nfmr = kzalloc(sizeof(*nfmr), GFP_KERNEL))) continue; nfmr->offset = 6; if ((c = fmrd[IFLA_IPTUN_FMR_IP6_PREFIX])) nla_memcpy(&nfmr->ip6_prefix, fmrd[IFLA_IPTUN_FMR_IP6_PREFIX], sizeof(nfmr->ip6_prefix)); if ((c = fmrd[IFLA_IPTUN_FMR_IP4_PREFIX])) nla_memcpy(&nfmr->ip4_prefix, fmrd[IFLA_IPTUN_FMR_IP4_PREFIX], sizeof(nfmr->ip4_prefix)); if ((c = fmrd[IFLA_IPTUN_FMR_IP6_PREFIX_LEN])) nfmr->ip6_prefix_len = nla_get_u8(c); if ((c = fmrd[IFLA_IPTUN_FMR_IP4_PREFIX_LEN])) nfmr->ip4_prefix_len = nla_get_u8(c); if ((c = fmrd[IFLA_IPTUN_FMR_EA_LEN])) nfmr->ea_len = nla_get_u8(c); if ((c = fmrd[IFLA_IPTUN_FMR_OFFSET])) nfmr->offset = nla_get_u8(c); nfmr->next = parms->fmrs; parms->fmrs = nfmr; } } } static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net *net = dev_net(dev); struct ip6_tnl *nt, *t; nt = netdev_priv(dev); ip6_tnl_netlink_parms(data, &nt->parms); t = ip6_tnl_locate(net, &nt->parms, 0); if (!IS_ERR(t)) return -EEXIST; return ip6_tnl_create2(dev); } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) return -EINVAL; ip6_tnl_netlink_parms(data, &p); t = ip6_tnl_locate(net, &p, 0); if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); return ip6_tnl_update(t, &p); } static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static size_t ip6_tnl_get_size(const struct net_device *dev) { const struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_fmr *c; int fmrs = 0; for (c = t->parms.fmrs; c; c = c->next) ++fmrs; return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_LIMIT */ nla_total_size(1) + /* IFLA_IPTUN_FLOWINFO */ nla_total_size(4) + /* IFLA_IPTUN_FLAGS */ nla_total_size(4) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + /* IFLA_IPTUN_FMRS */ nla_total_size(0) + ( /* nest */ nla_total_size(0) + /* IFLA_IPTUN_FMR_IP6_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_FMR_IP4_PREFIX */ nla_total_size(sizeof(struct in_addr)) + /* IFLA_IPTUN_FMR_EA_LEN */ nla_total_size(1) + /* IFLA_IPTUN_FMR_IP6_PREFIX_LEN */ nla_total_size(1) + /* IFLA_IPTUN_FMR_IP4_PREFIX_LEN */ nla_total_size(1) + /* IFLA_IPTUN_FMR_OFFSET */ nla_total_size(1) ) * fmrs + 0; } static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; struct __ip6_tnl_fmr *c; int fmrcnt = 0; struct nlattr *fmrs; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) || !(fmrs = nla_nest_start(skb, IFLA_IPTUN_FMRS))) goto nla_put_failure; for (c = parm->fmrs; c; c = c->next) { struct nlattr *fmr = nla_nest_start(skb, ++fmrcnt); if (!fmr || nla_put(skb, IFLA_IPTUN_FMR_IP6_PREFIX, sizeof(c->ip6_prefix), &c->ip6_prefix) || nla_put(skb, IFLA_IPTUN_FMR_IP4_PREFIX, sizeof(c->ip4_prefix), &c->ip4_prefix) || nla_put_u8(skb, IFLA_IPTUN_FMR_IP6_PREFIX_LEN, c->ip6_prefix_len) || nla_put_u8(skb, IFLA_IPTUN_FMR_IP4_PREFIX_LEN, c->ip4_prefix_len) || nla_put_u8(skb, IFLA_IPTUN_FMR_EA_LEN, c->ea_len) || nla_put_u8(skb, IFLA_IPTUN_FMR_OFFSET, c->offset)) goto nla_put_failure; nla_nest_end(skb, fmr); } nla_nest_end(skb, fmrs); return 0; nla_put_failure: return -EMSGSIZE; } struct net *ip6_tnl_get_link_net(const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); return tunnel->net; } EXPORT_SYMBOL(ip6_tnl_get_link_net); static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, [IFLA_IPTUN_FMRS] = { .type = NLA_NESTED }, }; static struct rtnl_link_ops ip6_link_ops __read_mostly = { .kind = "ip6tnl", .maxtype = IFLA_IPTUN_MAX, .policy = ip6_tnl_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6_tnl_dev_setup, .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, .priority = 1, }; static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, .priority = 1, }; static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; LIST_HEAD(list); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) unregister_netdevice_queue(dev, &list); for (h = 0; h < HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, &list); t = rtnl_dereference(t->next); } } unregister_netdevice_many(&list); } static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: ip6_dev_free(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static void __net_exit ip6_tnl_exit_net(struct net *net) { rtnl_lock(); ip6_tnl_destroy_tunnels(net); rtnl_unlock(); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit = ip6_tnl_exit_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; /** * ip6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init ip6_tunnel_init(void) { int err; err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto out_pernet; err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } err = rtnl_link_register(&ip6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: unregister_pernet_device(&ip6_tnl_net_ops); out_pernet: return err; } /** * ip6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit ip6_tunnel_cleanup(void) { rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) pr_info("%s: can't deregister ip6ip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); module_exit(ip6_tunnel_cleanup);