/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) { struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi fl = {}; unsigned long orefdst; unsigned int hh_len; unsigned int type; type = inet_addr_type(net, iph->saddr); if (skb->sk && inet_sk(skb->sk)->transparent) type = RTN_LOCAL; if (addr_type == RTN_UNSPEC) addr_type = type; /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. */ if (addr_type == RTN_LOCAL) { fl.nl_u.ip4_u.daddr = iph->daddr; if (type == RTN_LOCAL) fl.nl_u.ip4_u.saddr = iph->saddr; fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; fl.mark = skb->mark; fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; if (ip_route_output_key(net, &rt, &fl) != 0) return -1; /* Drop old route. */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } else { /* non-local src, find valid iif to satisfy * rp-filter when calling ip_route_input. */ fl.nl_u.ip4_u.daddr = iph->saddr; if (ip_route_output_key(net, &rt, &fl) != 0) return -1; orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, RT_TOS(iph->tos), rt->dst.dev) != 0) { dst_release(&rt->dst); return -1; } dst_release(&rt->dst); refdst_drop(orefdst); } if (skb_dst(skb)->error) return -1; #ifdef CONFIG_XFRM if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, &fl, AF_INET) == 0) { struct dst_entry *dst = skb_dst(skb); skb_dst_set(skb, NULL); if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) return -1; skb_dst_set(skb, dst); } #endif /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -1; return 0; }
int ip6_mc_input(struct sk_buff *skb) { struct ipv6hdr *hdr; int deliver; IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INMCASTPKTS); hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); #ifdef CONFIG_IPV6_MROUTE /* * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate * packets. */ struct sk_buff *skb2; struct inet6_skb_parm *opt = IP6CB(skb); /* Check for MLD */ if (unlikely(opt->ra)) { /* Check if this is a mld message */ u8 *ptr = skb_network_header(skb) + opt->ra; struct icmp6hdr *icmp6; u8 nexthdr = hdr->nexthdr; int offset; /* Check if the value of Router Alert * is for MLD (0x0000). */ if ((ptr[2] | ptr[3]) == 0) { deliver = 0; if (!ipv6_ext_hdr(nexthdr)) { /* BUG */ goto out; } offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr); if (offset < 0) goto out; if (nexthdr != IPPROTO_ICMPV6) goto out; if (!pskb_may_pull(skb, (skb_network_header(skb) + offset + 1 - skb->data))) goto out; icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case ICMPV6_MGM_QUERY: case ICMPV6_MGM_REPORT: case ICMPV6_MGM_REDUCTION: case ICMPV6_MLD2_REPORT: deliver = 1; break; } goto out; } /* unknown RA - process it normally */ } if (deliver) skb2 = skb_clone(skb, GFP_ATOMIC); else { skb2 = skb; skb = NULL; } if (skb2) { skb2->dev = skb2->dst->dev; ip6_mr_input(skb2); } } out: #endif if (likely(deliver)) ip6_input(skb); else { /* discard */ kfree_skb(skb); } return 0; }
struct sk_buff *ndisc_build_skb(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *saddr, struct icmp6hdr *icmp6h, const struct in6_addr *target, int llinfo) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int len; u8 *opt; if (!dev->addr_len) llinfo = 0; len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0); if (llinfo) len += ndisc_opt_addr_space(dev); skb = alloc_skb((MAX_HEADER + sizeof(struct ipv6hdr) + len + hlen + tlen), GFP_ATOMIC); if (!skb) { ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __func__); return NULL; } skb_reserve(skb, hlen); ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); skb->transport_header = skb->tail; skb_put(skb, len); hdr = (struct icmp6hdr *)skb_transport_header(skb); memcpy(hdr, icmp6h, sizeof(*hdr)); opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); if (target) { *(struct in6_addr *)opt = *target; opt += sizeof(*target); } if (llinfo) ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, dev->addr_len, dev->type); hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ skb_set_owner_w(skb, sk); return skb; }
static bool socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) { struct ipv6hdr *iph = ipv6_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; struct in6_addr *daddr, *saddr; __be16 dport, sport; int thoff, tproto; const struct xt_socket_mtinfo1 *info = (struct xt_socket_mtinfo1 *) par->matchinfo; tproto = ipv6_find_hdr(skb, &thoff, -1, NULL); if (tproto < 0) { pr_debug("unable to find transport header in IPv6 packet, dropping\n"); return NF_DROP; } if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) { hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; saddr = &iph->saddr; sport = hp->source; daddr = &iph->daddr; dport = hp->dest; } else if (tproto == IPPROTO_ICMPV6) { if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport)) return false; } else { return false; } sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); if (sk != NULL) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY */ wildcard = (sk->sk_state != TCP_TIME_WAIT && ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info && info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; } pr_debug("proto %hhd %pI6:%hu -> %pI6:%hu " "(orig %pI6:%hu) sock %p\n", tproto, saddr, ntohs(sport), daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); }
void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; struct rtable *rt; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto tx_error; key = &tun_info->key; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); inner_iph = (const struct iphdr *)skb_inner_network_header(skb); tos = key->tos; if (tos == 1) { if (skb->protocol == htons(ETH_P_IP)) tos = inner_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, RT_TOS(tos), tunnel->parms.link); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error; } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; else ttl = ip4_dst_hoplimit(&rt->dst); } if (key->tun_flags & TUNNEL_DONT_FRAGMENT) df = htons(IP_DF); else if (skb->protocol == htons(ETH_P_IP)) df = inner_iph->frag_off & htons(IP_DF); headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; if (skb_cow_head(skb, dev->needed_headroom)) { ip_rt_put(rt); goto tx_dropped; } iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, key->tos, key->ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: dev->stats.tx_errors++; goto kfree; tx_dropped: dev->stats.tx_dropped++; kfree: kfree_skb(skb); }
static int ip6_input_finish(struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; struct inet6_dev *idev; unsigned int nhoff; int nexthdr; bool raw; /* * Parse extension headers */ rcu_read_lock(); resubmit: idev = ip6_dst_idev(skb_dst(skb)); if (!pskb_pull(skb, skb_transport_offset(skb))) goto discard; nhoff = IP6CB(skb)->nhoff; nexthdr = skb_network_header(skb)[nhoff]; raw = raw6_local_deliver(skb, nexthdr); if ((ipprot = rcu_dereference(inet6_protos[nexthdr])) != NULL) { int ret; if (ipprot->flags & INET6_PROTO_FINAL) { const struct ipv6hdr *hdr; /* Free reference early: we don't need it any more, and it may hold ip_conntrack module loaded indefinitely. */ nf_reset(skb); skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); hdr = ipv6_hdr(skb); if (ipv6_addr_is_multicast(&hdr->daddr) && !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, &hdr->saddr) && !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) goto discard; } if (!(ipprot->flags & INET6_PROTO_NOPOLICY) && !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; ret = ipprot->handler(skb); if (ret > 0) goto resubmit; else if (ret == 0) IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); } else { if (!raw) { if (xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INUNKNOWNPROTOS); icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_UNK_NEXTHDR, nhoff); } } else IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); kfree_skb(skb); } rcu_read_unlock(); return 0; discard: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); rcu_read_unlock(); kfree_skb(skb); return 0; }
int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { const struct ipv6hdr *hdr; u32 pkt_len; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); if (skb->pkt_type == PACKET_OTHERHOST) { kfree_skb(skb); return NET_RX_DROP; } rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_IN, skb->len); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || !idev || unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); /* * Store incoming device index. When the packet will * be queued, we cannot refer to skb->dev anymore. * * BTW, when we send a packet for our own local address on a * non-loopback interface (e.g. ethX), it is being delivered * via the loopback interface (lo) here; skb->dev = loopback_dev. * It, however, should be considered as if it is being * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; hdr = ipv6_hdr(skb); if (hdr->version != 6) goto err; /* * RFC4291 2.5.3 * A packet received on an interface with a destination address * of loopback must be dropped. */ if (!(dev->flags & IFF_LOOPBACK) && ipv6_addr_loopback(&hdr->daddr)) goto err; /* RFC4291 2.7 * Nodes must not originate a packet to a multicast address whose scope * field contains the reserved value 0; if such a packet is received, it * must be silently dropped. */ if (ipv6_addr_is_multicast(&hdr->daddr) && IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0) goto err; /* * RFC4291 2.7 * Multicast addresses must not be used as source addresses in IPv6 * packets or appear in any Routing header. */ if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); pkt_len = ntohs(hdr->payload_len); /* pkt_len may be zero if Jumbo payload option is present */ if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + sizeof(struct ipv6hdr) > skb->len) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); goto drop; } hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP) { if (ipv6_parse_hopopts(skb) < 0) { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); rcu_read_unlock(); return NET_RX_DROP; } } rcu_read_unlock(); /* Must drop socket now because of tproxy. */ skb_orphan(skb); return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, dev, NULL, ip6_rcv_finish); err: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); drop: rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; }
static int arp_process(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); struct arphdr *arp; unsigned char *arp_ptr; struct rtable *rt; unsigned char *sha; __be32 sip, tip; u16 dev_type = dev->type; int addr_type; struct neighbour *n; struct net *net = dev_net(dev); bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device * is ARP'able. */ if (in_dev == NULL) goto out; arp = arp_hdr(skb); switch (dev_type) { default: if (arp->ar_pro != htons(ETH_P_IP) || htons(dev_type) != arp->ar_hrd) goto out; break; case ARPHRD_ETHER: case ARPHRD_IEEE802_TR: case ARPHRD_FDDI: case ARPHRD_IEEE802: /* * ETHERNET, Token Ring and Fibre Channel (which are IEEE 802 * devices, according to RFC 2625) devices will accept ARP * hardware types of either 1 (Ethernet) or 6 (IEEE 802.2). * This is the case also of FDDI, where the RFC 1390 says that * FDDI devices should accept ARP hardware of (1) Ethernet, * however, to be more robust, we'll accept both 1 (Ethernet) * or 6 (IEEE 802.2) */ if ((arp->ar_hrd != htons(ARPHRD_ETHER) && arp->ar_hrd != htons(ARPHRD_IEEE802)) || arp->ar_pro != htons(ETH_P_IP)) goto out; break; case ARPHRD_AX25: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_AX25)) goto out; break; case ARPHRD_NETROM: if (arp->ar_pro != htons(AX25_P_IP) || arp->ar_hrd != htons(ARPHRD_NETROM)) goto out; break; } /* Understand only these message types */ if (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST)) goto out; /* * Extract fields */ arp_ptr = (unsigned char *)(arp + 1); sha = arp_ptr; arp_ptr += dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; arp_ptr += dev->addr_len; memcpy(&tip, arp_ptr, 4); /* * Check for bad requests for 127.x.x.x and requests for multicast * addresses. If this is one such, delete it. */ if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; /* * Special case: We must set Frame Relay source Q.922 address */ if (dev_type == ARPHRD_DLCI) sha = dev->broadcast; /* * Process entry. The idea here is we want to send a reply if it is a * request for us or if it is a request for someone else that we hold * a proxy for. We want to add an entry to our cache if it is a reply * to us or if it is a request for our address. * (The assumption for this last is that if someone is requesting our * address, they are probably intending to talk to us, so it saves time * if we cache their address. Their address is also probably not in * our cache, since ours is not in their cache.) * * Putting this another way, we only care about replies if they are to * us, in which case we add them to the cache. For requests, we care * about those for us and those for our proxies. We reply to both, * and in the case of requests for us we add the requester to the arp * cache. */ /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type(net, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); goto out; } if (arp->ar_op == htons(ARPOP_REQUEST) && ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { int dont_send; dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); neigh_release(n); } } goto out; } else if (IN_DEV_FORWARD(in_dev)) { if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || in_dev->arp_parms->proxy_delay == 0) { arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); return 0; } goto out; } } } /* Update our ARP tables */ n = __neigh_lookup(&arp_tbl, &sip, dev, 0); if (IN_DEV_ARP_ACCEPT(in_dev)) { /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && inet_addr_type(net, sip) == RTN_UNICAST; if (n == NULL && ((arp->ar_op == htons(ARPOP_REPLY) && inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { int state = NUD_REACHABLE; int override; /* If several different ARP replies follows back-to-back, use the FIRST one. It is possible, if several proxy agents are active. Taking the first reply prevents arp trashing and chooses the fastest router. */ override = time_after(jiffies, n->updated + n->parms->locktime) || is_garp; /* Broadcast replies and request packets do not assert neighbour reachability. */ if (arp->ar_op != htons(ARPOP_REPLY) || skb->pkt_type != PACKET_HOST) state = NUD_STALE; neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0); neigh_release(n); }
struct sock* xt_socket_get4_sk(const struct sk_buff *skb, struct xt_action_param *par) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; __be32 daddr = 0, saddr = 0; __be16 dport = 0, sport = 0; u8 protocol = 0; #ifdef XT_SOCKET_HAVE_CONNTRACK struct nf_conn const *ct; enum ip_conntrack_info ctinfo; #endif if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) return NULL; protocol = iph->protocol; saddr = iph->saddr; sport = hp->source; daddr = iph->daddr; dport = hp->dest; } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) return NULL; } else { return NULL; } #ifdef XT_SOCKET_HAVE_CONNTRACK ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; dport = (iph->protocol == IPPROTO_TCP) ? ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port : ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; } #endif sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", protocol, &saddr, ntohs(sport), &daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return sk; }
static int arp_constructor(struct neighbour *neigh) { __be32 addr = *(__be32 *)neigh->primary_key; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev == NULL) { rcu_read_unlock(); return -EINVAL; } neigh->type = inet_addr_type(dev_net(dev), addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); rcu_read_unlock(); if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) ARPHRD_ETHER: (ethernet, apfddi) ARPHRD_FDDI: (fddi) ARPHRD_IEEE802: (tr) ARPHRD_METRICOM: (strip) ARPHRD_ARCNET: etc. etc. etc. ARPHRD_IPDDP will also work, if author repairs it. I did not it, because this driver does not work even in old paradigm. */ #if 1 /* So... these "amateur" devices are hopeless. The only thing, that I can say now: It is very sad that we need to keep ugly obsolete code to make them happy. They should be moved to more reasonable state, now they use rebuild_header INSTEAD OF hard_start_xmit!!! Besides that, they are sort of out of date (a lot of redundant clones/copies, useless in 2.1), I wonder why people believe that they work. */ switch (dev->type) { default: break; case ARPHRD_ROSE: #if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: #if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: #endif neigh->ops = &arp_broken_ops; neigh->output = neigh->ops->output; return 0; #else break; #endif } #endif if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); } else if (neigh->type == RTN_BROADCAST || (dev->flags & IFF_POINTOPOINT)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &arp_hh_ops; else neigh->ops = &arp_generic_ops; if (neigh->nud_state & NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } return 0; }
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; u8 *dst_ha = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { rcu_read_unlock(); return; } switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ if (skb && inet_addr_type(dev_net(dev), ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ if (!skb) break; saddr = ip_hdr(skb)->saddr; if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; } saddr = 0; break; case 2: /* Avoid secondary IPs, get a primary/preferred one */ break; } rcu_read_unlock(); if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); probes -= neigh->parms->ucast_probes; if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) printk(KERN_DEBUG "trying to ucast probe in NUD_INVALID\n"); dst_ha = neigh->ha; read_lock_bh(&neigh->lock); } else { probes -= neigh->parms->app_probes; if (probes < 0) { #ifdef CONFIG_ARPD neigh_app_ns(neigh); #endif return; } } arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_ha, dev->dev_addr, NULL); if (dst_ha) read_unlock_bh(&neigh->lock); }
static int vti4_err(struct sk_buff *skb, u32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip_tunnel *tunnel; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; mark = be32_to_cpu(tunnel->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; }
static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; int err; int mtu; if (!dst) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } dst_hold(dst); dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; dst_release(dst); goto tx_error_icmp; } tdev = dst->dev; if (tdev == dev) { dst_release(dst); dev->stats.collisions++; goto tx_error; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); goto tx_error; } skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: dev->stats.tx_errors++; kfree_skb(skb); return NETDEV_TX_OK; }
int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) { const struct ip_options *sopt; unsigned char *sptr, *dptr; int soffset, doffset; int optlen; __be32 daddr; memset(dopt, 0, sizeof(struct ip_options)); sopt = &(IPCB(skb)->opt); if (sopt->optlen == 0) return 0; sptr = skb_network_header(skb); dptr = dopt->__data; daddr = skb_rtable(skb)->rt_spec_dst; if (sopt->rr) { optlen = sptr[sopt->rr+1]; soffset = sptr[sopt->rr+2]; dopt->rr = dopt->optlen + sizeof(struct iphdr); memcpy(dptr, sptr+sopt->rr, optlen); if (sopt->rr_needaddr && soffset <= optlen) { if (soffset + 3 > optlen) return -EINVAL; dptr[2] = soffset + 4; dopt->rr_needaddr = 1; } dptr += optlen; dopt->optlen += optlen; } if (sopt->ts) { optlen = sptr[sopt->ts+1]; soffset = sptr[sopt->ts+2]; dopt->ts = dopt->optlen + sizeof(struct iphdr); memcpy(dptr, sptr+sopt->ts, optlen); if (soffset <= optlen) { if (sopt->ts_needaddr) { if (soffset + 3 > optlen) return -EINVAL; dopt->ts_needaddr = 1; soffset += 4; } if (sopt->ts_needtime) { if (soffset + 3 > optlen) return -EINVAL; if ((dptr[3]&0xF) != IPOPT_TS_PRESPEC) { dopt->ts_needtime = 1; soffset += 4; } else { dopt->ts_needtime = 0; if (soffset + 7 <= optlen) { __be32 addr; memcpy(&addr, dptr+soffset-1, 4); if (inet_addr_type(dev_net(skb_dst(skb)->dev), addr) != RTN_UNICAST) { dopt->ts_needtime = 1; soffset += 8; } } } } dptr[2] = soffset; } dptr += optlen; dopt->optlen += optlen; } if (sopt->srr) { unsigned char *start = sptr+sopt->srr; __be32 faddr; optlen = start[1]; soffset = start[2]; doffset = 0; if (soffset > optlen) soffset = optlen + 1; soffset -= 4; if (soffset > 3) { memcpy(&faddr, &start[soffset-1], 4); for (soffset-=4, doffset=4; soffset > 3; soffset-=4, doffset+=4) memcpy(&dptr[doffset-1], &start[soffset-1], 4); /* * RFC1812 requires to fix illegal source routes. */ if (memcmp(&ip_hdr(skb)->saddr, &start[soffset + 3], 4) == 0) doffset -= 4; } if (doffset > 3) { memcpy(&start[doffset-1], &daddr, 4); dopt->faddr = faddr; dptr[0] = start[0]; dptr[1] = doffset+3; dptr[2] = 4; dptr += doffset+3; dopt->srr = dopt->optlen + sizeof(struct iphdr); dopt->optlen += doffset+3; dopt->is_strictroute = sopt->is_strictroute; } } if (sopt->cipso) { optlen = sptr[sopt->cipso+1]; dopt->cipso = dopt->optlen+sizeof(struct iphdr); memcpy(dptr, sptr+sopt->cipso, optlen); dptr += optlen; dopt->optlen += optlen; } while (dopt->optlen & 3) { *dptr++ = IPOPT_END; dopt->optlen++; } return 0; }
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; int hroom, troom; __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; struct net *net = dev_net(skb_dst(skb)->dev); hlen = ip6_find_1stfragopt(skb, &prevhdr); nexthdr = *prevhdr; mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (!skb->local_df && skb->len > mtu) { skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (np && np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } mtu -= hlen + sizeof(struct frag_hdr); if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb)) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = 0; offset = 0; frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!tmp_hdr) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); return -ENOMEM; } __skb_pull(skb, hlen); fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); ipv6_select_ident(fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); frag_id = fh->identification; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); dst_hold(&rt->dst); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (frag) { frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), tmp_hdr, hlen); offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(offset); if (frag->next != NULL) fh->frag_off |= htons(IP6_MF); fh->identification = frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } err = output(skb); if(!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; skb = frag; frag = skb->next; skb->next = NULL; } kfree(tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); dst_release(&rt->dst); return 0; } while (frag) { skb = frag->next; kfree_skb(frag); frag = skb; } IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); dst_release(&rt->dst); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ /* * Fragment the datagram. */ *prevhdr = NEXTHDR_FRAGMENT; hroom = LL_RESERVED_SPACE(rt->dst.dev); troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. */ while(left > 0) { len = left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > mtu) len = mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < left) { len &= ~7; } /* * Allocate buffer. */ if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + hroom + troom, GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); err = -ENOMEM; goto fail; } /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, hroom); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); frag->transport_header = (frag->network_header + hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), hlen); /* * Build fragment header. */ fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { ipv6_select_ident(fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len)) BUG(); left -= len; fh->frag_off = htons(offset); if (left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ptr += len; offset += len; /* * Put this fragment into the sending queue. */ err = output(frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); kfree_skb(skb); return err; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; }
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } sk = inet6_lookup(net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); if (sk == NULL) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = inet6_sk(sk); if (type == NDISC_REDIRECT) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); goto out; } if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; dst = inet6_csk_update_pmtu(sk, ntohl(info)); if (!dst) goto out; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); goto out; } icmpv6_err_convert(type, code, &err); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (req == NULL) goto out; /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ WARN_ON(req->sk != NULL); if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: /* Cannot happen. It can, it SYNs are crossed. --ANK */ if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; /* * Wake people up to see the error * (see connect in sock.c) */ sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
/* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; new_dev->priv_flags |= (real_dev->priv_flags & IFF_UNICAST_FLT); vlan_dev_priv(new_dev)->vlan_proto = htons(ETH_P_8021Q); vlan_dev_priv(new_dev)->vlan_id = vlan_id; vlan_dev_priv(new_dev)->real_dev = real_dev; vlan_dev_priv(new_dev)->dent = NULL; vlan_dev_priv(new_dev)->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: free_netdev(new_dev); return err; }
/* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error * returned to the user. If err > 0 it's just the icmp type << 8 | icmp code. * After adjustment header points to the first 8 bytes of the tcp header. We * need to find the appropriate port. * * The locking strategy used here is very "optimistic". When someone else * accesses the socket the ICMP is just dropped and for some paths there is no * check at all. A more general error queue to queue errors for later handling * is probably better. */ static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; __u64 seq; int err; struct net *net = dev_net(skb->dev); if (skb->len < offset + sizeof(*dh) || skb->len < offset + __dccp_basic_hdr_len(dh)) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } sk = inet_lookup(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, dh->dccph_sport, inet_iif(skb)); if (sk == NULL) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ if (!sock_owned_by_user(sk)) dccp_do_pmtu_discovery(sk, iph, info); goto out; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { struct request_sock *req , **prev; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; req = inet_csk_search_req(sk, &prev, dh->dccph_dport, iph->daddr, iph->saddr); if (!req) goto out; /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ WARN_ON(req->sk); if (seq != dccp_rsk(req)->dreq_iss) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } /* * Still in RESPOND, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); goto out; case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk->sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else /* Only an error on timeout */ sk->sk_err_soft = err; out: bh_unlock_sock(sk); sock_put(sk); }
int ip6_mc_input(struct sk_buff *skb) { const struct ipv6hdr *hdr; bool deliver; IP6_UPD_PO_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, skb->len); hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); #ifdef CONFIG_IPV6_MROUTE /* * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate * packets. */ struct sk_buff *skb2; struct inet6_skb_parm *opt = IP6CB(skb); /* Check for MLD */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { /* Check if this is a mld message */ u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; /* Check if the value of Router Alert * is for MLD (0x0000). */ if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) { deliver = false; if (!ipv6_ext_hdr(nexthdr)) { /* BUG */ goto out; } offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) goto out; if (!ipv6_is_mld(skb, nexthdr, offset)) goto out; deliver = true; } /* unknown RA - process it normally */ } if (deliver) skb2 = skb_clone(skb, GFP_ATOMIC); else { skb2 = skb; skb = NULL; } if (skb2) { ip6_mr_input(skb2); } } out: #endif if (likely(deliver)) ip6_input(skb); else { /* discard */ kfree_skb(skb); } return 0; }
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff) { struct sk_buff *prev, *next; struct net_device *dev; int offset, end; struct net *net = dev_net(skb->dst->dev); if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((u8 *)&fhdr->frag_off - skb_network_header(skb))); return -1; } if (skb->ip_summed == CHECKSUM_COMPLETE) { const unsigned char *nh = skb_network_header(skb); skb->csum = csum_sub(skb->csum, csum_partial(nh, (u8 *)(fhdr + 1) - nh, 0)); } /* Is this the final fragment? */ if (!(fhdr->frag_off & htons(IP6_MF))) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; fq->q.last_in |= INET_FRAG_LAST_IN; fq->q.len = end; } else { /* Check if the fragment is rounded to 8 bytes. * Required by the RFC. */ if (end & 0x7) { /* RFC2460 says always send parameter problem in * this case. -DaveM */ IP6_INC_STATS_BH(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, offsetof(struct ipv6hdr, payload_len)); return -1; } if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.last_in & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } } if (end == offset) goto err; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) goto err; if (pskb_trim_rcsum(skb, end - offset)) goto err; /* Find out which fragments are in front and at the back of us * in the chain of fragments so far. We must know where to put * this fragment, right? */ prev = NULL; for(next = fq->q.fragments; next != NULL; next = next->next) { if (FRAG6_CB(next)->offset >= offset) break; /* bingo! */ prev = next; } /* We found where to put this one. Check for overlap with * preceding fragment, and, if needed, align things so that * any overlaps are eliminated. */ if (prev) { int i = (FRAG6_CB(prev)->offset + prev->len) - offset; if (i > 0) { offset += i; if (end <= offset) goto err; if (!pskb_pull(skb, i)) goto err; if (skb->ip_summed != CHECKSUM_UNNECESSARY) skb->ip_summed = CHECKSUM_NONE; } } /* Look for overlap with succeeding segments. * If we can merge fragments, do it. */ while (next && FRAG6_CB(next)->offset < end) { int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */ if (i < next->len) { /* Eat head of the next overlapped fragment * and leave the loop. The next ones cannot overlap. */ if (!pskb_pull(next, i)) goto err; FRAG6_CB(next)->offset += i; /* next fragment */ fq->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) next->ip_summed = CHECKSUM_NONE; break; } else { struct sk_buff *free_it = next; /* Old fragment is completely overridden with * new one drop it. */ next = next->next; if (prev) prev->next = next; else fq->q.fragments = next; fq->q.meat -= free_it->len; frag_kfree_skb(fq->q.net, free_it, NULL); } } FRAG6_CB(skb)->offset = offset; /* Insert this fragment in the chain of fragments. */ skb->next = next; if (prev) prev->next = skb; else fq->q.fragments = skb; dev = skb->dev; if (dev) { fq->iif = dev->ifindex; skb->dev = NULL; } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; atomic_add(skb->truesize, &fq->q.net->mem); /* The first fragment. * nhoffset is obtained from the first fragment, of course. */ if (offset == 0) { fq->nhoffset = nhoff; fq->q.last_in |= INET_FRAG_FIRST_IN; } if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) return ip6_frag_reasm(fq, prev, dev); write_lock(&ip6_frags.lock); list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); write_unlock(&ip6_frags.lock); return -1; err: IP6_INC_STATS(net, ip6_dst_idev(skb->dst), IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -1; }
static bool socket_match(const struct sk_buff *skb, struct xt_action_param *par, const struct xt_socket_mtinfo1 *info) { const struct iphdr *iph = ip_hdr(skb); struct udphdr _hdr, *hp = NULL; struct sock *sk; __be32 daddr, saddr; __be16 dport, sport; u8 protocol; #ifdef XT_SOCKET_HAVE_CONNTRACK struct nf_conn const *ct; enum ip_conntrack_info ctinfo; #endif if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) { hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (hp == NULL) return false; protocol = iph->protocol; saddr = iph->saddr; sport = hp->source; daddr = iph->daddr; dport = hp->dest; } else if (iph->protocol == IPPROTO_ICMP) { if (extract_icmp4_fields(skb, &protocol, &saddr, &daddr, &sport, &dport)) return false; } else { return false; } #ifdef XT_SOCKET_HAVE_CONNTRACK /* Do the lookup with the original socket address in case this is a * reply packet of an established SNAT-ted connection. */ ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; dport = (iph->protocol == IPPROTO_TCP) ? ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port : ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; } #endif sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, sport, dport, par->in, NFT_LOOKUP_ANY); if (sk != NULL) { bool wildcard; bool transparent = true; /* Ignore sockets listening on INADDR_ANY */ wildcard = (sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->inet_rcv_saddr == 0); /* Ignore non-transparent sockets, if XT_SOCKET_TRANSPARENT is used */ if (info && info->flags & XT_SOCKET_TRANSPARENT) transparent = ((sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->transparent) || (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; } pr_debug("proto %hhu %pI4:%hu -> %pI4:%hu (orig %pI4:%hu) sock %p\n", protocol, &saddr, ntohs(sport), &daddr, ntohs(dport), &iph->daddr, hp ? ntohs(hp->dest) : 0, sk); return (sk != NULL); }
static void ifb_ri_tasklet(unsigned long _txp) { struct ifb_q_private *txp = (struct ifb_q_private *)_txp; struct netdev_queue *txq; struct sk_buff *skb; txq = netdev_get_tx_queue(txp->dev, txp->txqnum); skb = skb_peek(&txp->tq); if (!skb) { if (!__netif_tx_trylock(txq)) goto resched; skb_queue_splice_tail_init(&txp->rq, &txp->tq); __netif_tx_unlock(txq); } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { skb->tc_redirected = 0; skb->tc_skip_classify = 1; u64_stats_update_begin(&txp->tsync); txp->tx_packets++; txp->tx_bytes += skb->len; u64_stats_update_end(&txp->tsync); rcu_read_lock(); skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif); if (!skb->dev) { rcu_read_unlock(); dev_kfree_skb(skb); txp->dev->stats.tx_dropped++; if (skb_queue_len(&txp->tq) != 0) goto resched; break; } rcu_read_unlock(); skb->skb_iif = txp->dev->ifindex; if (!skb->tc_from_ingress) { dev_queue_xmit(skb); } else { skb_pull_rcsum(skb, skb->mac_len); netif_receive_skb(skb); } } if (__netif_tx_trylock(txq)) { skb = skb_peek(&txp->rq); if (!skb) { txp->tasklet_pending = 0; if (netif_tx_queue_stopped(txq)) netif_tx_wake_queue(txq); } else { __netif_tx_unlock(txq); goto resched; } __netif_tx_unlock(txq); } else { resched: txp->tasklet_pending = 1; tasklet_schedule(&txp->ifb_tasklet); } }
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) { struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); int err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } #endif if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { tunnel->dev->stats.rx_crc_errors++; tunnel->dev->stats.rx_errors++; goto drop; } if (tunnel->parms.i_flags&TUNNEL_SEQ) { if (!(tpi->flags&TUNNEL_SEQ) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { tunnel->dev->stats.rx_fifo_errors++; tunnel->dev->stats.rx_errors++; goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } skb_reset_network_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { ++tunnel->dev->stats.rx_frame_errors; ++tunnel->dev->stats.rx_errors; goto drop; } } tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tunnel->dev->type == ARPHRD_ETHER) { skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: kfree_skb(skb); return 0; }
static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; struct in6_addr *nexthop; int ret; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && ((mroute6_socket(dev_net(dev), skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, newskb, NULL, newskb->dev, dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { IP6_INC_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; } } rcu_read_lock_bh(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { ret = dst_neigh_output(dst, neigh, skb); rcu_read_unlock_bh(); return ret; } rcu_read_unlock_bh(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; }
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; __be16 df; struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; bool connected; inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { const struct in6_addr *addr6; struct neighbour *neigh; bool do_tx_error_icmp; int addr_type; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) do_tx_error_icmp = true; else { do_tx_error_icmp = false; dst = addr6->s6_addr32[3]; } neigh_release(neigh); if (do_tx_error_icmp) goto tx_error_icmp; } #endif else goto tx_error; connected = false; } tos = tnl_params->tos; if (tos & 0x1) { tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) { tos = inner_iph->tos; connected = false; } else if (skb->protocol == htons(ETH_P_IPV6)) { tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); connected = false; } } init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; rt = connected ? dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error; } if (connected) dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) { ip_rt_put(rt); goto tx_error; } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = tnl_params->ttl; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) ttl = inner_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit; #endif else ttl = ip4_dst_hoplimit(&rt->dst); } df = tnl_params->frag_off; if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) df |= (inner_iph->frag_off&htons(IP_DF)); max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; if (skb_cow_head(skb, dev->needed_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; #if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); #endif tx_error: dev->stats.tx_errors++; kfree_skb(skb); }
static void ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; <<<<<<< HEAD
} static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, int router, int solicited, int override, int inc_opt) { struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct icmp6hdr icmp6h = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, }; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = 0; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } icmp6h.icmp6_router = router;
int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); u32 mtu; if (net->ipv6.devconf_all->forwarding == 0) goto error; if (skb_warn_if_lro(skb)) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } if (skb->pkt_type != PACKET_HOST) goto drop; skb_forward_csum(skb); /* * We DO NOT make any processing on * RA packets, pushing them to user level AS IS * without ane WARRANTY that application will be able * to interpret them. The reason is that we * cannot make anything clever here. * * We are not end-node, so that if packet contains * AH/ESP, we cannot make anything. * Defragmentation also would be mistake, RA packets * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ if (opt->ra) { u8 *ptr = skb_network_header(skb) + opt->ra; if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3])) return 0; } /* * check and decrement ttl */ if (hdr->hop_limit <= 1) { /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; } /* XXX: idev->cnf.proxy_ndp? */ if ((net->ipv6.devconf_all->proxy_ndp == 1 && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) || net->ipv6.devconf_all->proxy_ndp >= 2) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; /* * incoming and outgoing devices are the same * send a redirect. */ rt = (struct rt6_info *) dst; if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else target = &hdr->daddr; if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) ndisc_send_redirect(skb, target); } else { int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ if (addrtype == IPV6_ADDR_ANY || addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } mtu = dst_mtu(dst); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb->len > mtu && !skb_is_gso(skb)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS); IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ hdr->hop_limit--; IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); error: IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; }
/* * Stuff received packets to associated sockets. * On error, returns non-zero and releases the skb. */ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pkttype, struct net_device *orig_dev) { struct net *net = dev_net(dev); struct phonethdr *ph; struct sockaddr_pn sa; u16 len; /* check we have at least a full Phonet header */ if (!pskb_pull(skb, sizeof(struct phonethdr))) goto out; /* check that the advertised length is correct */ ph = pn_hdr(skb); len = get_unaligned_be16(&ph->pn_length); if (len < 2) goto out; len -= 2; if ((len > skb->len) || pskb_trim(skb, len)) goto out; skb_reset_transport_header(skb); pn_skb_get_dst_sockaddr(skb, &sa); /* check if this is broadcasted */ if (pn_sockaddr_get_addr(&sa) == PNADDR_BROADCAST) { pn_deliver_sock_broadcast(net, skb); goto out; } /* resource routing */ if (pn_sockaddr_get_object(&sa) == 0) { struct sock *sk = pn_find_sock_by_res(net, sa.spn_resource); if (sk) return sk_receive_skb(sk, skb, 0); } /* check if we are the destination */ if (phonet_address_lookup(net, pn_sockaddr_get_addr(&sa)) == 0) { /* Phonet packet input */ struct sock *sk = pn_find_sock_by_sa(net, &sa); if (sk) return sk_receive_skb(sk, skb, 0); if (can_respond(skb)) { send_obj_unreachable(skb); send_reset_indications(skb); } } else if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) goto out; /* Race between address deletion and loopback */ else { /* Phonet packet routing */ struct net_device *out_dev; out_dev = phonet_route_output(net, pn_sockaddr_get_addr(&sa)); if (!out_dev) { LIMIT_NETDEBUG(KERN_WARNING"No Phonet route to %02X\n", pn_sockaddr_get_addr(&sa)); goto out; } __skb_push(skb, sizeof(struct phonethdr)); skb->dev = out_dev; if (out_dev == dev) { LIMIT_NETDEBUG(KERN_ERR"Phonet loop to %02X on %s\n", pn_sockaddr_get_addr(&sa), dev->name); goto out_dev; } /* Some drivers (e.g. TUN) do not allocate HW header space */ if (skb_cow_head(skb, out_dev->hard_header_len)) goto out_dev; if (dev_hard_header(skb, out_dev, ETH_P_PHONET, NULL, NULL, skb->len) < 0) goto out_dev; dev_queue_xmit(skb); dev_put(out_dev); return NET_RX_SUCCESS; out_dev: dev_put(out_dev); } out: kfree_skb(skb); return NET_RX_DROP; }
/* * Return NULL if skb is handled * note: already called with rcu_read_lock */ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) { struct net_bridge_port *p; struct sk_buff *skb = *pskb; const unsigned char *dest = eth_hdr(skb)->h_dest; br_should_route_hook_t *rhook; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return RX_HANDLER_CONSUMED; p = br_port_get_rcu(skb->dev); if (p->flags & BR_VLAN_TUNNEL) { if (br_handle_ingress_vlan_tunnel(skb, p, nbp_vlan_group_rcu(p))) goto drop; } if (unlikely(is_link_local_ether_addr(dest))) { u16 fwd_mask = p->br->group_fwd_mask_required; /* * See IEEE 802.1D Table 7-10 Reserved addresses * * Assignment Value * Bridge Group Address 01-80-C2-00-00-00 * (MAC Control) 802.3 01-80-C2-00-00-01 * (Link Aggregation) 802.3 01-80-C2-00-00-02 * 802.1X PAE address 01-80-C2-00-00-03 * * 802.1AB LLDP 01-80-C2-00-00-0E * * Others reserved for future standardization */ switch (dest[5]) { case 0x00: /* Bridge Group Address */ /* If STP is turned off, then must forward to keep loop detection */ if (p->br->stp_enabled == BR_NO_STP || fwd_mask & (1u << dest[5])) goto forward; *pskb = skb; __br_handle_local_finish(skb); return RX_HANDLER_PASS; case 0x01: /* IEEE MAC (Pause) */ goto drop; case 0x0E: /* 802.1AB LLDP */ fwd_mask |= p->br->group_fwd_mask; if (fwd_mask & (1u << dest[5])) goto forward; *pskb = skb; __br_handle_local_finish(skb); return RX_HANDLER_PASS; default: /* Allow selective forwarding for most other protocols */ fwd_mask |= p->br->group_fwd_mask; if (fwd_mask & (1u << dest[5])) goto forward; } /* Deliver packet to local host only */ NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), NULL, skb, skb->dev, NULL, br_handle_local_finish); return RX_HANDLER_CONSUMED; } forward: switch (p->state) { case BR_STATE_FORWARDING: rhook = rcu_dereference(br_should_route_hook); if (rhook) { if ((*rhook)(skb)) { *pskb = skb; return RX_HANDLER_PASS; } dest = eth_hdr(skb)->h_dest; } /* fall through */ case BR_STATE_LEARNING: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, dev_net(skb->dev), NULL, skb, skb->dev, NULL, br_handle_frame_finish); break; default: drop: kfree_skb(skb); } return RX_HANDLER_CONSUMED; }