int iptunnel_xmit(struct net *net, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df) { int pkt_len = skb->len; struct iphdr *iph; int err; nf_reset(skb); secpath_reset(skb); skb_clear_rxhash(skb); skb_dst_drop(skb); skb_dst_set(skb, &rt_dst(rt)); #if 0 /* Do not clear ovs_skb_cb. It will be done in gso code. */ memset(IPCB(skb), 0, sizeof(*IPCB(skb))); #endif /* Push down and install the IP header. */ __skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; __ip_select_ident(iph, &rt_dst(rt), (skb_shinfo(skb)->gso_segs ?: 1) - 1); err = ip_local_out(skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; return pkt_len; }
static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4, struct net_device *vrf_dev) { struct rtable *rt; int err = 1; rt = ip_route_output_flow(dev_net(vrf_dev), fl4, NULL); if (IS_ERR(rt)) goto out; /* TO-DO: what about broadcast ? */ if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out; } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); err = 0; out: return err; }
static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, __u8 proto, __u8 prio, __u8 ttl) { struct ipv6hdr *ip6h; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst_clone(dst)); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = proto; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6h->payload_len = htons(skb->len - sizeof(*ip6h)); }
int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, htonl(0)); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev); return 0; }
/* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(netif_rx(skb) == NET_RX_SUCCESS)) vrf_rx_stats(dev, len); else this_cpu_inc(dev->dstats->rx_drps); return NETDEV_TX_OK; }
int nat64_send_packet_ipv6(struct sk_buff *skb) { // Function based on Ecdysis's nat64_output_ipv4 struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi fl; struct dst_entry *dst; skb->protocol = htons(ETH_P_IPV6); memset(&fl, 0, sizeof(fl)); if(!&(fl.fl6_src)) { return -EINVAL; } fl.fl6_src = iph->saddr; fl.fl6_dst = iph->daddr; fl.fl6_flowlabel = 0; fl.proto = skb->protocol; dst = ip6_route_output(&init_net, NULL, &fl); if (!dst) { pr_warning("error: ip6_route_output failed"); return -EINVAL; } skb->dev = dst->dev; skb_dst_set(skb, dst); if(ip6_local_out(skb)) { pr_warning("nf_NAT64: ip6_local_out failed."); return -EINVAL; } return 0; }
// this method will send the message to the destination machine using ipv4 static int cse536_sendmsg(char *data, size_t len) { struct sk_buff *skb; struct iphdr *iph; struct rtable *rt; struct net *net = &init_net; unsigned char *skbdata; // create and setup an sk_buff skb = alloc_skb(sizeof(struct iphdr) + 4096, GFP_ATOMIC); skb_reserve(skb, sizeof(struct iphdr) + 1500); skbdata = skb_put(skb, len); // skb->csum = csum_and_copy_from_user(data, skbdata, len, 0, &err); memcpy(skbdata, data, len); // setup and add the ip header skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = 0; iph->frag_off = 0; iph->ttl = 64; iph->daddr = cse536_daddr; iph->saddr = cse536_saddr; iph->protocol = IPPROTO_CSE536; // my protocol number iph->id = htons(1); iph->tot_len = htons(skb->len); // get the route. this seems to be necessary, does not work without rt = ip_route_output(net, cse536_daddr, cse536_saddr, 0,0); skb_dst_set(skb, &rt->dst); //printk("skb data: %s", skbdata); return ip_local_out(skb); }
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; struct iphdr *iph; int err; skb_scrub_packet(skb, xnet); skb_clear_hash(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; iph->frag_off = df; iph->protocol = proto; iph->tos = tos; iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; __ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out(net, sk, skb); if (unlikely(net_xmit_eval(err))) pkt_len = 0; iptunnel_xmit_stats(dev, pkt_len); }
static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, unsigned short reason, gfp_t gfp, struct dst_entry *dst, int ddl, unsigned char *dd, __le16 rem, __le16 loc) { struct sk_buff *skb = NULL; int size = 7 + ddl + ((msgflg == NSP_DISCINIT) ? 1 : 0); unsigned char *msg; if ((dst == NULL) || (rem == 0)) { if (net_ratelimit()) printk(KERN_DEBUG "DECnet: dn_nsp_do_disc: BUG! Please report this to [email protected] rem=%u dst=%p\n", le16_to_cpu(rem), dst); return; } if ((skb = dn_alloc_skb(sk, size, gfp)) == NULL) return; msg = skb_put(skb, size); *msg++ = msgflg; *(__le16 *)msg = rem; msg += 2; *(__le16 *)msg = loc; msg += 2; *(__le16 *)msg = cpu_to_le16(reason); msg += 2; if (msgflg == NSP_DISCINIT) *msg++ = ddl; if (ddl) { memcpy(msg, dd, ddl); } skb_dst_set(skb, dst_clone(dst)); dst_output(skb); }
int skb_route(struct sk_buff *skb, void *pkt) { struct dst_entry *dst; switch (get_l3_proto(pkt)) { case 6: dst = route_ipv6(pkt); break; case 4: dst = route_ipv4(pkt); break; default: log_err("Invalid mode: %u", get_l3_proto(pkt)); return -EINVAL; } if (!dst) return -EINVAL; (skb)->dev = dst->dev; skb_dst_set(skb, dst); return 0; }
/* Reroute packet to local IPv4 stack after DNAT */ static int __ip_vs_reroute_locally(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; struct net *net = dev_net(dev); struct iphdr *iph = ip_hdr(skb); if (rt_is_input_route(rt)) { unsigned long orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, skb->dev)) return 0; refdst_drop(orefdst); } else { struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = RT_TOS(iph->tos), .flowi4_mark = skb->mark, }; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return 0; if (!(rt->rt_flags & RTCF_LOCAL)) { ip_rt_put(rt); return 0; } /* Drop old route. */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } return 1; } #ifdef CONFIG_IP_VS_IPV6 static inline int __ip_vs_is_local_route6(struct rt6_info *rt) { return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK; } static struct dst_entry * __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, struct in6_addr *ret_saddr, int do_xfrm) { struct dst_entry *dst; struct flowi6 fl6 = { .daddr = *daddr, }; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) goto out_err; if (!ret_saddr) return dst; if (ipv6_addr_any(&fl6.saddr) && ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, &fl6.daddr, 0, &fl6.saddr) < 0) goto out_err; if (do_xfrm) { dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) { dst = NULL; goto out_err; } } ipv6_addr_copy(ret_saddr, &fl6.saddr); return dst; out_err: dst_release(dst); IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr); return NULL; } /* * Get route to destination or remote server * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest, * &4=Allow redirect from remote daddr to local */ static struct rt6_info * __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, struct in6_addr *daddr, struct in6_addr *ret_saddr, int do_xfrm, int rt_mode) { struct net *net = dev_net(skb_dst(skb)->dev); struct rt6_info *rt; /* Route to the other host */ struct rt6_info *ort; /* Original route */ struct dst_entry *dst; int local; if (dest) { spin_lock(&dest->dst_lock); rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0); if (!rt) { u32 cookie; dst = __ip_vs_route_output_v6(net, &dest->addr.in6, &dest->dst_saddr, do_xfrm); if (!dst) { spin_unlock(&dest->dst_lock); return NULL; } rt = (struct rt6_info *) dst; cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie); IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n", &dest->addr.in6, &dest->dst_saddr, atomic_read(&rt->dst.__refcnt)); } if (ret_saddr) ipv6_addr_copy(ret_saddr, &dest->dst_saddr); spin_unlock(&dest->dst_lock); } else { dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); if (!dst) return NULL; rt = (struct rt6_info *) dst; } local = __ip_vs_is_local_route6(rt); if (!((local ? 1 : 2) & rt_mode)) { IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n", local ? "local":"non-local", daddr); dst_release(&rt->dst); return NULL; } if (local && !(rt_mode & 4) && !((ort = (struct rt6_info *) skb_dst(skb)) && __ip_vs_is_local_route6(ort))) { IP_VS_DBG_RL("Redirect from non-local address %pI6 to local " "requires NAT method, dest: %pI6\n", &ipv6_hdr(skb)->daddr, daddr); dst_release(&rt->dst); return NULL; } if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LOOPBACK)) { IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 " "to non-local address, dest: %pI6\n", &ipv6_hdr(skb)->saddr, daddr); dst_release(&rt->dst); return NULL; } return rt; } #endif /* * Release dest->dst_cache before a dest is removed */ void ip_vs_dst_reset(struct ip_vs_dest *dest) { struct dst_entry *old_dst; old_dst = dest->dst_cache; dest->dst_cache = NULL; dst_release(old_dst); } #define IP_VS_XMIT_TUNNEL(skb, cp) \ ({ \ int __ret = NF_ACCEPT; \ \ (skb)->ipvs_property = 1; \ if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \ __ret = ip_vs_confirm_conntrack(skb, cp); \ if (__ret == NF_ACCEPT) { \ nf_reset(skb); \ skb_forward_csum(skb); \ } \ __ret; \ }) #define IP_VS_XMIT_NAT(pf, skb, cp, local) \ do { \ (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ ip_vs_notrack(skb); \ else \ ip_vs_update_conntrack(skb, cp, 1); \ if (local) \ return NF_ACCEPT; \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ skb_dst(skb)->dev, dst_output); \ } while (0) #define IP_VS_XMIT(pf, skb, cp, local) \ do { \ (skb)->ipvs_property = 1; \ if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \ ip_vs_notrack(skb); \ if (local) \ return NF_ACCEPT; \ skb_forward_csum(skb); \ NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \ skb_dst(skb)->dev, dst_output); \ } while (0) /* * NULL transmitter (do nothing except return NF_ACCEPT) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { /* we do not touch skb and do not need pskb ptr */ IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); }
int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset) { struct rt6_info *rt; /* Route to the other host */ int mtu; int rc; int local; EnterFunction(10); /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) rc = cp->packet_xmit(skb, cp, pp); else rc = NF_ACCEPT; /* do not touch skb anymore */ atomic_inc_unchecked(&cp->in_pkts); goto out; } /* * mangle and send the packet here (only for VS/NAT) */ if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, 0, 1|2|4))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG(10, "%s(): " "stopping DNAT to local address %pI6\n", __func__, &cp->daddr.in6); goto tx_error_put; } } #endif /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI6\n", __func__, &cp->daddr.in6); goto tx_error_put; } /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); skb->dev = net->loopback_dev; } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, offset)) goto tx_error_put; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; ip_vs_nat_icmp_v6(skb, pp, cp, 0); if (!local || !skb->dev) { /* drop the old route when skb is not shared */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } else { /* destined to loopback, do we need to change route? */ dst_release(&rt->dst); } /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local); rc = NF_STOLEN; goto out; tx_error_icmp: dst_link_failure(skb); tx_error: dev_kfree_skb(skb); rc = NF_STOLEN; out: LeaveFunction(10); return rc; tx_error_put: dst_release(&rt->dst); goto tx_error; }
/* * ICMP packet transmitter * called by the ip_vs_in_icmp */ int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset) { struct rtable *rt; /* Route to the other host */ int mtu; int rc; int local; EnterFunction(10); /* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be forwarded directly here, because there is no need to translate address/port back */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) { if (cp->packet_xmit) rc = cp->packet_xmit(skb, cp, pp); else rc = NF_ACCEPT; /* do not touch skb anymore */ atomic_inc_unchecked(&cp->in_pkts); goto out; } /* * mangle and send the packet here (only for VS/NAT) */ if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(ip_hdr(skb)->tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG(10, "%s(): " "stopping DNAT to local address %pI4\n", __func__, &cp->daddr.ip); goto tx_error_put; } } #endif /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(rt->rt_dst) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", __func__, &cp->daddr.ip); goto tx_error_put; } /* MTU checking */ mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) && !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, offset)) goto tx_error_put; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; ip_vs_nat_icmp(skb, pp, cp, 0); if (!local) { /* drop the old route when skb is not shared */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } else { ip_rt_put(rt); /* * Some IPv4 replies get local address from routes, * not from iph, so while we DNAT after routing * we need this second input/output route. */ if (!__ip_vs_reroute_locally(skb)) goto tx_error; } /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local); rc = NF_STOLEN; goto out; tx_error_icmp: dst_link_failure(skb); tx_error: dev_kfree_skb(skb); rc = NF_STOLEN; out: LeaveFunction(10); return rc; tx_error_put: ip_rt_put(rt); goto tx_error; }
int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = np->cork.opt; struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst; struct flowi6 *fl6 = &inet->cork.fl.u.ip6; unsigned char proto = fl6->flowi6_proto; int err = 0; if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ if (np->pmtudisc < IPV6_PMTUDISC_DO) skb->local_df = 1; ipv6_addr_copy(final_dst, &fl6->daddr); __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); *(__be32*)hdr = fl6->flowlabel | htonl(0x60000000 | ((int)np->cork.tclass << 20)); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; ipv6_addr_copy(&hdr->saddr, &fl6->saddr); ipv6_addr_copy(&hdr->daddr, final_dst); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, dst_clone(&rt->dst)); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) goto error; } out: ip6_cork_release(inet, np); return err; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); goto out; }
static int xfrm_output_one(struct sk_buff *skb, int err) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; struct net *net = xs_net(x); if (err <= 0) goto resume; do { err = xfrm_state_check_space(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); goto error_nolock; } err = x->outer_mode->output(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error_nolock; } spin_lock_bh(&x->lock); err = xfrm_state_check_expire(x); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); goto error; } if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output = ++x->replay.oseq; if (unlikely(x->replay.oseq == 0)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; goto error; } if (xfrm_aevent_is_on(net)) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } x->curlft.bytes += skb->len; x->curlft.packets++; spin_unlock_bh(&x->lock); err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out_exit; resume: if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error_nolock; } dst = dst_pop(dst); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); err = 0; out_exit: return err; error: spin_unlock_bh(&x->lock); error_nolock: kfree_skb(skb); goto out_exit; }
/* Send RST reply */ static void send_reset(struct net *net, struct sk_buff *oldskb) { struct sk_buff *nskb; struct tcphdr otcph, *tcph; unsigned int otcplen, hh_len; int tcphoff, needs_ack; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); struct ipv6hdr *ip6h; #define DEFAULT_TOS_VALUE 0x0U const __u8 tclass = DEFAULT_TOS_VALUE; struct dst_entry *dst = NULL; u8 proto; struct flowi fl; if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) { pr_debug("addr is not unicast.\n"); return; } proto = oip6h->nexthdr; tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto); if ((tcphoff < 0) || (tcphoff > oldskb->len)) { pr_debug("Cannot get TCP header.\n"); return; } otcplen = oldskb->len - tcphoff; /* IP header checks: fragment, too short. */ if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) { pr_debug("proto(%d) != IPPROTO_TCP, " "or too short. otcplen = %d\n", proto, otcplen); return; } if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr))) BUG(); /* No RST for RST. */ if (otcph.rst) { pr_debug("RST is set\n"); return; } /* Check checksum. */ if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP, skb_checksum(oldskb, tcphoff, otcplen, 0))) { pr_debug("TCP checksum is invalid\n"); return; } memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr); ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr); fl.fl_ip_sport = otcph.dest; fl.fl_ip_dport = otcph.source; security_skb_classify_flow(oldskb, &fl); dst = ip6_route_output(net, NULL, &fl); if (dst == NULL || dst->error) { dst_release(dst); return; } if (xfrm_lookup(net, &dst, &fl, NULL, 0)) return; hh_len = (dst->dev->hard_header_len + 15)&~15; nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) + sizeof(struct tcphdr) + dst->trailer_len, GFP_ATOMIC); if (!nskb) { if (net_ratelimit()) pr_debug("cannot alloc skb\n"); dst_release(dst); return; } skb_dst_set(nskb, dst); skb_reserve(nskb, hh_len + dst->header_len); skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = dst_metric(dst, RTAX_HOPLIMIT); ip6h->nexthdr = IPPROTO_TCP; ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr); tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; tcph->source = otcph.dest; tcph->dest = otcph.source; if (otcph.ack) { needs_ack = 0; tcph->seq = otcph.ack_seq; tcph->ack_seq = 0; } else { needs_ack = 1; tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin + otcplen - (otcph.doff<<2)); tcph->seq = 0; } /* Reset flags */ ((u_int8_t *)tcph)[13] = 0; tcph->rst = 1; tcph->ack = needs_ack; tcph->window = 0; tcph->urg_ptr = 0; tcph->check = 0; /* Adjust TCP checksum */ tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr, &ipv6_hdr(nskb)->daddr, sizeof(struct tcphdr), IPPROTO_TCP, csum_partial(tcph, sizeof(struct tcphdr), 0)); nf_ct_attach(nskb, oldskb); ip6_local_out(nskb); }
static int xfrm_output_one(struct sk_buff *skb, int err) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; struct net *net = xs_net(x); if (err <= 0) goto resume; do { err = xfrm_skb_check_space(skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); goto error_nolock; } err = x->outer_mode->output(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error_nolock; } spin_lock_bh(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID); err = -EINVAL; goto error; } err = xfrm_state_check_expire(x); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); goto error; } err = x->repl->overflow(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); goto error; } x->curlft.bytes += skb->len; x->curlft.packets++; spin_unlock_bh(&x->lock); skb_dst_force(skb); err = x->type->output(x, skb); if (err == -EINPROGRESS) goto out; resume: if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error_nolock; } dst = skb_dst_pop(skb); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } skb_dst_set(skb, dst); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); return 0; error: spin_unlock_bh(&x->lock); error_nolock: kfree_skb(skb); out: return err; }
/* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge * port group as it was received on. We can still bridge * the packet. * 2. The packet was DNAT'ed to a different device, either * a non-bridged device or another bridge port group. * The packet will need to be routed. * * The correct way of distinguishing between these two cases is to * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * * Let's first consider the case that ip_route_input() succeeds: * * If the output device equals the logical bridge device the packet * came in on, we can consider this bridging. The corresponding MAC * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will * later be passed up to the IP stack to be routed. For a redirected * packet, ip_route_input() will give back the localhost as output device, * which differs from the bridge device. * * Let's now consider the case that ip_route_input() fails: * * This can be because the destination address is martian, in which case * the packet will be dropped. * If IP forwarding is disabled, ip_route_input() will fail, while * ip_route_output_key() can return success. The source * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care * if IP forwarding is enabled. If the output device equals the logical bridge * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; int err; nf_bridge->frag_max_size = IPCB(skb)->frag_max_size; if (nf_bridge->pkt_otherhost) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a * martian destination or due to the fact that * forwarding is disabled. For most martian packets, * ip_route_output_key() will fail. It won't fail for 2 types of * martian destinations: loopback destinations and destination * 0.0.0.0. In both cases the packet will be dropped because the * destination is the loopback device and not the bridge. */ if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) goto free_skb; rt = ip_route_output(net, iph->daddr, 0, RT_TOS(iph->tos), 0); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (rt->dst.dev == dev) { skb_dst_set(skb, &rt->dst); goto bridged_dnat; } ip_rt_put(rt); } free_skb: kfree_skb(skb); return 0; } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge); return 0; } ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { rt = bridge_parent_rtable(nf_bridge->physindev); if (!rt) { kfree_skb(skb); return 0; } skb_dst_set_noref(skb, &rt->dst); } skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_handle_frame_finish); return 0; }
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, void *from, size_t length, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct iphdr *iph; struct sk_buff *skb; unsigned int iphlen; int err; struct rtable *rt = *rtp; int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, rt->dst.dev->mtu); return -EMSGSIZE; } if (flags&MSG_PROBE) goto out; hlen = LL_RESERVED_SPACE(rt->dst.dev); tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, &rt->dst); *rtp = NULL; skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb,sizeof(*iph)); skb->ip_summed = CHECKSUM_NONE; skb->transport_header = skb->network_header; err = -EFAULT; if (!memcpy_fromiovecend2((void *)iph, from, 0, length)) goto error_free; iphlen = iph->ihl * 4; /* * We don't want to modify the ip header, but we do need to * be sure that it won't cause problems later along the network * stack. Specifically we want to make sure that iph->ihl is a * sane value. If ihl points beyond the length of the buffer passed * in, reject the frame as invalid */ err = -EINVAL; if (iphlen > length) goto error_free; if (iphlen >= sizeof(*iph)) { if (!iph->saddr) iph->saddr = fl4->saddr; iph->check = 0; iph->tot_len = htons(length); if (!iph->id) ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) goto error; out: return 0; error_free: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); if (err == -ENOBUFS && !inet->recverr) err = 0; return err; }
int ip6_route_me_harder(struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct ipv6hdr *iph = ipv6_hdr(skb); struct dst_entry *dst; struct flowi fl = { .oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, .mark = skb->mark, .fl6_dst = iph->daddr, .fl6_src = iph->saddr, }; dst = ip6_route_output(net, skb->sk, &fl); if (dst->error) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n"); dst_release(dst); return -EINVAL; } /* Drop old route. */ skb_dst_drop(skb); skb_dst_set(skb, dst); #ifdef CONFIG_XFRM if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, &fl, AF_INET6) == 0) { skb_dst_set(skb, NULL); if (xfrm_lookup(net, &dst, &fl, skb->sk, 0)) return -1; skb_dst_set(skb, dst); } #endif return 0; } EXPORT_SYMBOL(ip6_route_me_harder); /* * Extra routing may needed on local out, as the QUEUE target never * returns control to the table. */ struct ip6_rt_info { struct in6_addr daddr; struct in6_addr saddr; u_int32_t mark; }; static void nf_ip6_saveroute(const struct sk_buff *skb, struct nf_queue_entry *entry) { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->hook == NF_INET_LOCAL_OUT) { struct ipv6hdr *iph = ipv6_hdr(skb); rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; rt_info->mark = skb->mark; } } static int nf_ip6_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->hook == NF_INET_LOCAL_OUT) { struct ipv6hdr *iph = ipv6_hdr(skb); if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) return ip6_route_me_harder(skb); } return 0; } static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl) { *dst = ip6_route_output(&init_net, NULL, fl); return (*dst)->error; }
/* * IP Tunneling transmitter * * This function encapsulates the packet in a new IP packet, its * destination will be set to cp->daddr. Most code of this function * is taken from ipip.c. * * It is used in VS/TUN cluster. The load balancer selects a real * server from a cluster based on a scheduling algorithm, * encapsulates the request packet and forwards it to the selected * server. For example, all real servers are configured with * "ifconfig tunl0 <Virtual IP Address> up". When the server receives * the encapsulated packet, it will decapsulate the packet, processe * the request and return the response packets directly to the client * without passing the load balancer. This can greatly increase the * scalability of virtual server. * * Used for ANY protocol */ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); u8 tos = old_iph->tos; __be16 df = old_iph->frag_off; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; int ret; EnterFunction(10); if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL))) goto tx_error_icmp; if (rt->rt_flags & RTCF_LOCAL) { ip_rt_put(rt); IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1); } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__); goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); df |= (old_iph->frag_off & htons(IP_DF)); if ((old_iph->frag_off & htons(IP_DF) && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); kfree_skb(skb); IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); } skb->transport_header = skb->network_header; /* fix old IP header checksum */ ip_send_check(old_iph); skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. */ iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; iph->frag_off = df; iph->protocol = IPPROTO_IPIP; iph->tos = tos; iph->daddr = rt->rt_dst; iph->saddr = rt->rt_src; iph->ttl = old_iph->ttl; ip_select_ident(iph, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; ret = IP_VS_XMIT_TUNNEL(skb, cp); if (ret == NF_ACCEPT) ip_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_put: ip_rt_put(rt); goto tx_error; }
//----------------------------------------------------------------------------- static bool _gtpurh_route_packet(struct sk_buff *skb_pP, const struct xt_gtpurh_target_info *info_pP) //----------------------------------------------------------------------------- { int err = 0; struct rtable *rt = NULL; struct iphdr *iph_p = ip_hdr(skb_pP); int daddr = iph_p->daddr; struct flowi fl = { .u = { .ip4 = { .daddr = daddr, .flowi4_tos = RT_TOS(iph_p->tos), .flowi4_scope = RT_SCOPE_UNIVERSE, } } }; //skb_pP->pkt_type = PACKET_OTHERHOST; skb_pP->pkt_type = PACKET_OUTGOING; #if 0 pr_info("GTPURH(%d): Routing packet: %d.%d.%d.%d --> %d.%d.%d.%d Proto: %d, Len: %d Mark: %u Packet type: %u\n", info_pP->action, iph_p->saddr & 0xFF, (iph_p->saddr & 0x0000FF00) >> 8, (iph_p->saddr & 0x00FF0000) >> 16, iph_p->saddr >> 24, iph_p->daddr & 0xFF, (iph_p->daddr & 0x0000FF00) >> 8, (iph_p->daddr & 0x00FF0000) >> 16, iph_p->daddr >> 24, iph_p->protocol, ntohs(iph_p->tot_len), skb_pP->mark, skb_pP->pkt_type); #endif rt = ip_route_output_key(&init_net, &fl.u.ip4); if (rt == null) { pr_info("GTPURH: Failed to route packet to dst 0x%x. Error: (%d)\n", fl.u.ip4.daddr, err); return GTPURH_FAILURE; } #if 0 if (rt->dst.dev) { pr_info("GTPURH: dst dev name %s\n", rt->dst.dev->name); } else { pr_info("GTPURH: dst dev NULL\n"); } #endif skb_pP->priority = rt_tos2priority(iph_p->tos); skb_dst_drop(skb_pP); skb_dst_set(skb_pP, &rt->dst); skb_pP->dev = skb_dst(skb_pP)->dev; // Send the GTPu message out ip_local_out(skb_pP); if (err == 0) { return GTPURH_SUCCESS; } else { return GTPURH_FAILURE; } }
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; }
/* * NAT transmitter (only for outside-to-inside nat forwarding) * Not used for related ICMP */ int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rtable *rt; /* Route to the other host */ int mtu; struct iphdr *iph = ip_hdr(skb); int local; EnterFunction(10); /* check if it is a connection of no-client-port */ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { __be16 _pt, *p; p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt); if (p == NULL) goto tx_error; ip_vs_conn_fill_cport(cp, *p); IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(iph->tos), IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR))) goto tx_error_icmp; local = rt->rt_flags & RTCF_LOCAL; /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to local address"); goto tx_error_put; } } #endif /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(rt->rt_dst) && rt_is_input_route(skb_rtable(skb))) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); goto tx_error_put; } /* MTU checking */ mtu = dst_mtu(&rt->dst); if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) && !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for"); goto tx_error_put; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, sizeof(struct iphdr))) goto tx_error_put; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) goto tx_error_put; ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); if (!local) { /* drop old route */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } else { ip_rt_put(rt); /* * Some IPv4 replies get local address from routes, * not from iph, so while we DNAT after routing * we need this second input/output route. */ if (!__ip_vs_reroute_locally(skb)) goto tx_error; } IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still MTU problem. */ /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_put: ip_rt_put(rt); goto tx_error; }
/* Send RST reply */ static void send_reset(struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; const struct iphdr *oiph; struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _otcph, *tcph; unsigned int addr_type; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) return; oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb), sizeof(_otcph), &_otcph); if (oth == NULL) return; /* No RST for RST. */ if (oth->rst) return; /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return; oiph = ip_hdr(oldskb); nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + LL_MAX_HEADER, GFP_ATOMIC); if (!nskb) return; skb_reserve(nskb, LL_MAX_HEADER); skb_reset_network_header(nskb); niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; niph->id = 0; niph->frag_off = htons(IP_DF); niph->protocol = IPPROTO_TCP; niph->check = 0; niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); memset(tcph, 0, sizeof(*tcph)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; if (oth->ack) tcph->seq = oth->ack_seq; else { tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + oldskb->len - ip_hdrlen(oldskb) - (oth->doff << 2)); tcph->ack = 1; } tcph->rst = 1; tcph->check = tcp_v4_check(sizeof(struct tcphdr), niph->saddr, niph->daddr, csum_partial(tcph, sizeof(struct tcphdr), 0)); addr_type = RTN_UNSPEC; if (hook != NF_INET_FORWARD #ifdef CONFIG_BRIDGE_NETFILTER || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED) #endif ) addr_type = RTN_LOCAL; /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set(nskb, dst_clone(skb_dst(oldskb))); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT); nskb->ip_summed = CHECKSUM_NONE; /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; nf_ct_attach(nskb, oldskb); ip_local_out(nskb); return; free_nskb: kfree_skb(nskb); }
int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rt6_info *rt; /* Route to the other host */ int mtu; int local; EnterFunction(10); /* check if it is a connection of no-client-port */ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) { __be16 _pt, *p; p = skb_header_pointer(skb, sizeof(struct ipv6hdr), sizeof(_pt), &_pt); if (p == NULL) goto tx_error; ip_vs_conn_fill_cport(cp, *p); IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL, 0, 1|2|4))) goto tx_error_icmp; local = __ip_vs_is_local_route6(rt); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to local address"); goto tx_error_put; } } #endif /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) { IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); goto tx_error_put; } /* MTU checking */ mtu = dst_mtu(&rt->dst); if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); skb->dev = net->loopback_dev; } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0, "ip_vs_nat_xmit_v6(): frag needed for"); goto tx_error_put; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, sizeof(struct ipv6hdr))) goto tx_error_put; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error_put; /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) goto tx_error; ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6); if (!local || !skb->dev) { /* drop the old route when skb is not shared */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } else { /* destined to loopback, do we need to change route? */ dst_release(&rt->dst); } IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still MTU problem. */ /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: LeaveFunction(10); kfree_skb(skb); return NF_STOLEN; tx_error_put: dst_release(&rt->dst); goto tx_error; }
/* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge * port group as it was received on. We can still bridge * the packet. * 2. The packet was DNAT'ed to a different device, either * a non-bridged device or another bridge port group. * The packet will need to be routed. * * The correct way of distinguishing between these two cases is to * call ip_route_input() and to look at skb->dst->dev, which is * changed to the destination device if ip_route_input() succeeds. * * Let's first consider the case that ip_route_input() succeeds: * * If the output device equals the logical bridge device the packet * came in on, we can consider this bridging. The corresponding MAC * address will be obtained in br_nf_pre_routing_finish_bridge. * Otherwise, the packet is considered to be routed and we just * change the destination MAC address so that the packet will * later be passed up to the IP stack to be routed. For a redirected * packet, ip_route_input() will give back the localhost as output device, * which differs from the bridge device. * * Let's now consider the case that ip_route_input() fails: * * This can be because the destination address is martian, in which case * the packet will be dropped. * If IP forwarding is disabled, ip_route_input() will fail, while * ip_route_output_key() can return success. The source * address for ip_route_output_key() is set to zero, so ip_route_output_key() * thinks we're handling a locally generated packet and won't care * if IP forwarding is enabled. If the output device equals the logical bridge * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ static int br_nf_pre_routing_finish(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); struct nf_bridge_info *nf_bridge = skb->nf_bridge; struct rtable *rt; int err; if (nf_bridge->mask & BRNF_PKT_TYPE) { skb->pkt_type = PACKET_OTHERHOST; nf_bridge->mask ^= BRNF_PKT_TYPE; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; if (dnat_took_place(skb)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a * martian destination or due to the fact that * forwarding is disabled. For most martian packets, * ip_route_output_key() will fail. It won't fail for 2 types of * martian destinations: loopback destinations and destination * 0.0.0.0. In both cases the packet will be dropped because the * destination is the loopback device and not the bridge. */ if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) goto free_skb; rt = ip_route_output(dev_net(dev), iph->daddr, 0, RT_TOS(iph->tos), 0); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (rt->dst.dev == dev) { skb_dst_set(skb, &rt->dst); goto bridged_dnat; } ip_rt_put(rt); } free_skb: kfree_skb(skb); return 0; } else { if (skb_dst(skb)->dev == dev) { bridged_dnat: skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; } memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); skb->pkt_type = PACKET_HOST; } } else { rt = bridge_parent_rtable(nf_bridge->physindev); if (!rt) { kfree_skb(skb); return 0; } skb_dst_set_noref(skb, &rt->dst); } skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); return 0; }
int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { struct rt6_info *rt; /* Route to the other host */ struct in6_addr saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ struct ipv6hdr *old_iph = ipv6_hdr(skb); struct ipv6hdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int mtu; int ret; EnterFunction(10); if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, &saddr, 1, 1|2))) goto tx_error_icmp; if (__ip_vs_is_local_route6(rt)) { dst_release(&rt->dst); IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1); } tdev = rt->dst.dev; mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr); if (mtu < IPV6_MIN_MTU) { IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__, IPV6_MIN_MTU); goto tx_error_put; } if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); skb->dev = net->loopback_dev; } icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr); if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { dst_release(&rt->dst); kfree_skb(skb); IP_VS_ERR_RL("%s(): no memory\n", __func__); return NF_STOLEN; } kfree_skb(skb); skb = new_skb; old_iph = ipv6_hdr(skb); } skb->transport_header = skb->network_header; skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); /* drop old route */ skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); /* * Push down and install the IPIP header. */ iph = ipv6_hdr(skb); iph->version = 6; iph->nexthdr = IPPROTO_IPV6; iph->payload_len = old_iph->payload_len; be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); ipv6_addr_copy(&iph->daddr, &cp->daddr.in6); ipv6_addr_copy(&iph->saddr, &saddr); iph->hop_limit = old_iph->hop_limit; /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; ret = IP_VS_XMIT_TUNNEL(skb, cp); if (ret == NF_ACCEPT) ip6_local_out(skb); else if (ret == NF_DROP) kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); LeaveFunction(10); return NF_STOLEN; tx_error_put: dst_release(&rt->dst); goto tx_error; }
struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; struct rt6_info *rt = (struct rt6_info *)cork->base.dst; struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, np->autoflowlabel, fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_dst_set(skb, dst_clone(&rt->dst)); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } ip6_cork_release(cork, v6_cork); out: return skb; }