/* * 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, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct rtable *rt; /* Route to the other host */ int rc; int local; int rt_mode, was_input; 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, iph); else rc = NF_ACCEPT; /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); goto out; } /* * mangle and send the packet here (only for VS/NAT) */ was_input = rt_is_input_route(skb_rtable(skb)); /* LOCALNODE from FORWARD hook is not supported */ rt_mode = (hooknum != NF_INET_FORWARD) ? IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; rcu_read_lock(); local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, NULL, iph); if (local < 0) goto tx_error; rt = skb_rtable(skb); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *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; } } #endif /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) { IP_VS_DBG(1, "%s(): " "stopping DNAT to loopback %pI4\n", __func__, &cp->daddr.ip); goto tx_error; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, offset)) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; ip_vs_nat_icmp(skb, pp, cp, 0); /* Another hack: avoid icmp_send in ip_fragment */ skb->ignore_df = 1; rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); rcu_read_unlock(); goto out; tx_error: kfree_skb(skb); rcu_read_unlock(); rc = NF_STOLEN; out: LeaveFunction(10); return rc; }
/* * 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, NULL))) 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 IS_ENABLED(CONFIG_NF_CONNTRACK) 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(cp->daddr.ip) && 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; }
/* * 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, unsigned int hooknum) { struct rtable *rt; /* Route to the other host */ int mtu; int rc; int local; int rt_mode; 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(&cp->in_pkts); goto out; } /* * mangle and send the packet here (only for VS/NAT) */ /* LOCALNODE from FORWARD hook is not supported */ rt_mode = (hooknum != NF_INET_FORWARD) ? IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, RT_TOS(ip_hdr(skb)->tos), rt_mode, NULL))) 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 IS_ENABLED(CONFIG_NF_CONNTRACK) 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(cp->daddr.ip) && 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; }
/* 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->dst.dev && rt->dst.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; } } *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 */ 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.in6, 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.in6, atomic_read(&rt->dst.__refcnt)); } if (ret_saddr) *ret_saddr = dest->dst_saddr.in6; 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 ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) & 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 & IP_VS_RT_MODE_RDR) && !((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); \ 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); }
/* * 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 ip_vs_iphdr *ipvsh) { struct rtable *rt; /* Route to the other host */ int local, rc, was_input; EnterFunction(10); rcu_read_lock(); /* 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, ipvsh->len, 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)); } was_input = rt_is_input_route(skb_rtable(skb)); local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR, NULL); if (local < 0) goto tx_error; rt = skb_rtable(skb); /* * Avoid duplicate tuple in reply direction for NAT traffic * to local address when connection is sync-ed */ #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (cp->flags & IP_VS_CONN_F_SYNC && local) { enum ip_conntrack_info ctinfo; struct nf_conn *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; } } #endif /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) { IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " "stopping DNAT to loopback address"); goto tx_error; } /* copy-on-write the packet before mangling it */ if (!skb_make_writable(skb, sizeof(struct iphdr))) goto tx_error; if (skb_cow(skb, rt->dst.dev->hard_header_len)) goto tx_error; /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh)) goto tx_error; ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); 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; rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local); rcu_read_unlock(); LeaveFunction(10); return rc; tx_error: kfree_skb(skb); rcu_read_unlock(); LeaveFunction(10); return NF_STOLEN; }