/* * NET3: Implementation of the ICMP protocol layer. * * Alan Cox, * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Some of the function names and the icmp unreach table for this * module were derived from [icmp.c 1.0.11 06/02/93] by * Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting. * Other than that this module is a complete rewrite. * * Fixes: * Clemens Fruhwirth : introduce global icmp rate limiting * with icmp type masking ability instead * of broken per type icmp timeouts. * Mike Shaver : RFC1122 checks. * Alan Cox : Multicast ping reply as self. * Alan Cox : Fix atomicity lockup in ip_build_xmit * call. * Alan Cox : Added 216,128 byte paths to the MTU * code. * Martin Mares : RFC1812 checks. * Martin Mares : Can be configured to follow redirects * if acting as a router _without_ a * routing protocol (RFC 1812). * Martin Mares : Echo requests may be configured to * be ignored (RFC 1812). * Martin Mares : Limitation of ICMP error message * transmit rate (RFC 1812). * Martin Mares : TOS and Precedence set correctly * (RFC 1812). * Martin Mares : Now copying as much data from the * original packet as we can without * exceeding 576 bytes (RFC 1812). * Willy Konynenberg : Transparent proxying support. * Keith Owens : RFC1191 correction for 4.2BSD based * path MTU bug. * Thomas Quinot : ICMP Dest Unreach codes up to 15 are * valid (RFC 1812). * Andi Kleen : Check all packet lengths properly * and moved all kfree_skb() up to * icmp_rcv. * Andi Kleen : Move the rate limit bookkeeping * into the dest entry and use a token * bucket filter (thanks to ANK). Make * the rates sysctl configurable. * Yu Tianli : Fixed two ugly bugs in icmp_send * - IP option length was accounted wrongly * - ICMP header length was not accounted * at all. * Tristan Greaves : Added sysctl option to ignore bogus * broadcast responses from broken routers. * * To Fix: * * - Should use skb_pull() instead of all the manual checking. * This would also greatly simply some upper layer error handlers. --AK * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include struct icmp_bxm { struct sk_buff *skb; int offset; int data_len; struct { struct icmphdr icmph; __be32 times[3]; } data; int head_len; struct ip_options_data replyopts; }; const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, .fatal = 0, }, { .errno = EHOSTUNREACH, .fatal = 0, }, { .errno = ENOPROTOOPT , .fatal = 1, }, { .errno = ECONNREFUSED, .fatal = 1, }, { .errno = EMSGSIZE, .fatal = 0, }, { .errno = EOPNOTSUPP, .fatal = 0, }, { .errno = ENETUNREACH, .fatal = 1, }, { .errno = EHOSTDOWN, .fatal = 1, }, { .errno = ENONET, .fatal = 1, }, { .errno = ENETUNREACH, .fatal = 1, }, { .errno = EHOSTUNREACH, .fatal = 1, }, { .errno = ENETUNREACH, .fatal = 0, }, { .errno = EHOSTUNREACH, .fatal = 0, }, { .errno = EHOSTUNREACH, .fatal = 1, }, { .errno = EHOSTUNREACH, .fatal = 1, }, { .errno = EHOSTUNREACH, .fatal = 1, }, }; EXPORT_SYMBOL(icmp_err_convert); struct icmp_control { void (*handler)(struct sk_buff *skb); short error; }; static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; static struct sock *icmp_sk(struct net *net) { return net->ipv4.icmp_sk[smp_processor_id()]; } static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; local_bh_disable(); sk = icmp_sk(net); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { local_bh_enable(); return NULL; } return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { spin_unlock_bh(&sk->sk_lock.slock); } static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct flowi4 *fl4, int type, int code) { struct dst_entry *dst = &rt->dst; bool rc = true; if (type > NR_ICMP_TYPES) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) goto out; if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) goto out; if ((1 << type) & net->ipv4.sysctl_icmp_ratemask) { if (!rt->peer) rt_bind_peer(rt, fl4->daddr, 1); rc = inet_peer_xrlim_allow(rt->peer, net->ipv4.sysctl_icmp_ratelimit); } out: return rc; } void icmp_out_count(struct net *net, unsigned char type) { ICMPMSGOUT_INC_STATS(net, type); ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS); } static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct icmp_bxm *icmp_param = (struct icmp_bxm *)from; __wsum csum; csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, to, len, 0); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_pointers[icmp_param->data.icmph.type].error) nf_ct_attach(skb, icmp_param->skb); return 0; } static void icmp_push_reply(struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { struct sock *sk; struct sk_buff *skb; sk = icmp_sk(dev_net((*rt)->dst.dev)); if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, ipc, rt, MSG_DONTWAIT) < 0) { ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_OUTERRORS); ip_flush_pending_frames(sk); } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { struct icmphdr *icmph = icmp_hdr(skb); __wsum csum = 0; struct sk_buff *skb1; skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } csum = csum_partial_copy_nocheck((void *)&icmp_param->data, (char *)icmph, icmp_param->head_len, csum); icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); } } static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; __be32 daddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb)) return; sk = icmp_xmit_lock(net); if (sk == NULL) return; inet = inet_sk(sk); icmp_param->data.icmph.checksum = 0; inet->tos = ip_hdr(skb)->tos; sk->sk_mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; ipc.opt = NULL; ipc.tx_flags = 0; if (icmp_param->replyopts.opt.opt.optlen) { ipc.opt = &icmp_param->replyopts.opt; if (ipc.opt->opt.srr) daddr = icmp_param->replyopts.opt.opt.faddr; } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = rt->rt_spec_dst; fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, icmp_param->data.icmph.type, icmp_param->data.icmph.code)) icmp_push_reply(icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, __be32 saddr, u8 tos, u32 mark, int type, int code, struct icmp_bxm *param) { struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = (param->replyopts.opt.opt.srr ? param->replyopts.opt.opt.faddr : iph->saddr); fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_tos = RT_TOS(tos); fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; rt2 = rt; rt = (struct rtable *) xfrm_lookup(net, &rt->dst, flowi4_to_flowi(fl4), NULL, 0); if (!IS_ERR(rt)) { if (rt != rt2) return rt; } else if (PTR_ERR(rt) == -EPERM) { rt = NULL; } else return rt; err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; fl4_2.daddr = fl4_dec.saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); goto relookup_failed; } orefdst = skb_in->_skb_refdst; err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); skb_in->_skb_refdst = orefdst; } if (err) goto relookup_failed; rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, flowi4_to_flowi(&fl4_dec), NULL, XFRM_LOOKUP_ICMP); if (!IS_ERR(rt2)) { dst_release(&rt->dst); memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; } else if (PTR_ERR(rt2) == -EPERM) { if (rt) dst_release(&rt->dst); return rt2; } else { err = PTR_ERR(rt2); goto relookup_failed; } return rt; relookup_failed: if (rt) return rt; return ERR_PTR(err); } void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct iphdr *iph; int room; struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; #ifdef CONFIG_HTC_NETWORK_DEBUG __be32 src_addr, dst_addr; #endif u8 tos; u32 mark; struct net *net; struct sock *sk; if (!rt) goto out; net = dev_net(rt->dst.dev); iph = ip_hdr(skb_in); if ((u8 *)iph < skb_in->head || (skb_in->network_header + sizeof(*iph)) > skb_in->tail) goto out; if (skb_in->pkt_type != PACKET_HOST) goto out; if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto out; if (iph->frag_off & htons(IP_OFFSET)) goto out; if (icmp_pointers[type].error) { if (iph->protocol == IPPROTO_ICMP) { u8 _inner_type, *itp; itp = skb_header_pointer(skb_in, skb_network_header(skb_in) + (iph->ihl << 2) + offsetof(struct icmphdr, type) - skb_in->data, sizeof(_inner_type), &_inner_type); if (itp == NULL) goto out; if (*itp > NR_ICMP_TYPES || icmp_pointers[*itp].error) goto out; } } sk = icmp_xmit_lock(net); if (sk == NULL) return; #ifdef CONFIG_HTC_NETWORK_DEBUG src_addr = iph->saddr; dst_addr = iph->daddr; if ( (!ipv4_is_zeronet(src_addr) && !ipv4_is_loopback(src_addr)) && (!ipv4_is_zeronet(dst_addr) && !ipv4_is_loopback(dst_addr))) { if ((type == ICMP_DEST_UNREACH) && ((code == ICMP_PORT_UNREACH) || (code == ICMP_HOST_UNREACH))) { NET_LOG("[ICMP] Dest unreachable(%s): src:%pI4 dst: %pI4", code == ICMP_PORT_UNREACH ? "PORT_UNREACH" : "HOST_UNREACH", &src_addr, &dst_addr ); } } #endif saddr = iph->daddr; if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); if (rt_is_input_route(rt) && net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) dev = dev_get_by_index_rcu(net, rt->rt_iif); if (dev) saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK); else saddr = 0; rcu_read_unlock(); } tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL) : iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in)) goto out_unlock; icmp_param.data.icmph.type = type; icmp_param.data.icmph.code = code; icmp_param.data.icmph.un.gateway = info; icmp_param.data.icmph.checksum = 0; icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); inet_sk(sk)->tos = tos; sk->sk_mark = mark; ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; ipc.tx_flags = 0; rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark, type, code, &icmp_param); if (IS_ERR(rt)) goto out_unlock; if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code)) goto ende; room = dst_mtu(&rt->dst); if (room > 576) room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out:; } EXPORT_SYMBOL(icmp_send); static void icmp_unreach(struct sk_buff *skb) { const struct iphdr *iph; struct icmphdr *icmph; int hash, protocol; const struct net_protocol *ipprot; u32 info = 0; struct net *net; net = dev_net(skb_dst(skb)->dev); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out_err; icmph = icmp_hdr(skb); iph = (const struct iphdr *)skb->data; if (iph->ihl < 5) goto out_err; if (icmph->type == ICMP_DEST_UNREACH) { switch (icmph->code & 15) { case ICMP_NET_UNREACH: case ICMP_HOST_UNREACH: case ICMP_PROT_UNREACH: case ICMP_PORT_UNREACH: break; case ICMP_FRAG_NEEDED: if (ipv4_config.no_pmtu_disc) { LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: fragmentation needed and DF set\n"), &iph->daddr); } else { info = ip_rt_frag_needed(net, iph, ntohs(icmph->un.frag.mtu), skb->dev); if (!info) goto out; } break; case ICMP_SR_FAILED: LIMIT_NETDEBUG(KERN_INFO pr_fmt("%pI4: Source Route Failed\n"), &iph->daddr); break; default: break; } if (icmph->code > NR_ICMP_UNREACH) goto out; } else if (icmph->type == ICMP_PARAMETERPROB) info = ntohl(icmph->un.gateway) >> 24; if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { if (net_ratelimit()) pr_warn("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, &iph->daddr, skb->dev->name); goto out; } if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) goto out; iph = (const struct iphdr *)skb->data; protocol = iph->protocol; raw_icmp_error(skb, protocol, info); hash = protocol & (MAX_INET_PROTOS - 1); rcu_read_lock(); ipprot = rcu_dereference(inet_protos[hash]); if (ipprot && ipprot->err_handler) ipprot->err_handler(skb, info); rcu_read_unlock(); out: return; out_err: ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); goto out; } static void icmp_redirect(struct sk_buff *skb) { const struct iphdr *iph; if (skb->len < sizeof(struct iphdr)) goto out_err; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; iph = (const struct iphdr *)skb->data; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: ip_rt_redirect(ip_hdr(skb)->saddr, iph->daddr, icmp_hdr(skb)->un.gateway, iph->saddr, skb->dev); break; } if (iph->protocol == IPPROTO_ICMP && iph->ihl >= 5 && pskb_may_pull(skb, (iph->ihl<<2)+8)) { ping_v4_err(skb, icmp_hdr(skb)->un.gateway); } out: return; out_err: ICMP_INC_STATS_BH(dev_net(skb->dev), ICMP_MIB_INERRORS); goto out; } static void icmp_echo(struct sk_buff *skb) { struct net *net; net = dev_net(skb_dst(skb)->dev); if (!net->ipv4.sysctl_icmp_echo_ignore_all) { struct icmp_bxm icmp_param; icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.data.icmph.type = ICMP_ECHOREPLY; icmp_param.skb = skb; icmp_param.offset = 0; icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); icmp_reply(&icmp_param, skb); } } static void icmp_timestamp(struct sk_buff *skb) { struct timespec tv; struct icmp_bxm icmp_param; if (skb->len < 4) goto out_err; getnstimeofday(&tv); icmp_param.data.times[1] = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC); icmp_param.data.times[2] = icmp_param.data.times[1]; if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4)) BUG(); icmp_param.data.icmph = *icmp_hdr(skb); icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY; icmp_param.data.icmph.code = 0; icmp_param.skb = skb; icmp_param.offset = 0; icmp_param.data_len = 0; icmp_param.head_len = sizeof(struct icmphdr) + 12; icmp_reply(&icmp_param, skb); out: return; out_err: ICMP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); goto out; } static void icmp_address(struct sk_buff *skb) { #if 0 if (net_ratelimit()) printk(KERN_DEBUG "a guy asks for address mask. Who is it?\n"); #endif } static void icmp_address_reply(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct in_ifaddr *ifa; if (skb->len < 4 || !(rt->rt_flags&RTCF_DIRECTSRC)) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; if (in_dev->ifa_list && IN_DEV_LOG_MARTIANS(in_dev) && IN_DEV_FORWARD(in_dev)) { __be32 _mask, *mp; mp = skb_header_pointer(skb, 0, sizeof(_mask), &_mask); BUG_ON(mp == NULL); for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (*mp == ifa->ifa_mask && inet_ifa_match(ip_hdr(skb)->saddr, ifa)) break; } if (!ifa && net_ratelimit()) { pr_info("Wrong address mask %pI4 from %s/%pI4\n", mp, dev->name, &ip_hdr(skb)->saddr); } } } static void icmp_discard(struct sk_buff *skb) { } int icmp_rcv(struct sk_buff *skb) { struct icmphdr *icmph; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { struct sec_path *sp = skb_sec_path(skb); int nh; if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) goto drop; if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr))) goto drop; nh = skb_network_offset(skb); skb_set_network_header(skb, sizeof(*icmph)); if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN, skb)) goto drop; skb_set_network_header(skb, nh); } ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS); switch (skb->ip_summed) { case CHECKSUM_COMPLETE: if (!csum_fold(skb->csum)) break; case CHECKSUM_NONE: skb->csum = 0; if (__skb_checksum_complete(skb)) goto error; } if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); ICMPMSGIN_INC_STATS_BH(net, icmph->type); if (icmph->type > NR_ICMP_TYPES) goto error; if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && net->ipv4.sysctl_icmp_echo_ignore_broadcasts) { goto error; } if (icmph->type != ICMP_ECHO && icmph->type != ICMP_TIMESTAMP && icmph->type != ICMP_ADDRESS && icmph->type != ICMP_ADDRESSREPLY) { goto error; } } icmp_pointers[icmph->type].handler(skb); drop: kfree_skb(skb); return 0; error: ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); goto drop; } static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { [ICMP_ECHOREPLY] = { .handler = ping_rcv, }, [1] = { .handler = icmp_discard, .error = 1, }, [2] = { .handler = icmp_discard, .error = 1, }, [ICMP_DEST_UNREACH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_SOURCE_QUENCH] = { .handler = icmp_unreach, .error = 1, }, [ICMP_REDIRECT] = { .handler = icmp_redirect, .error = 1, }, [6] = { .handler = icmp_discard, .error = 1, }, [7] = { .handler = icmp_discard, .error = 1, }, [ICMP_ECHO] = { .handler = icmp_echo, }, [9] = { .handler = icmp_discard, .error = 1, }, [10] = { .handler = icmp_discard, .error = 1, }, [ICMP_TIME_EXCEEDED] = { .handler = icmp_unreach, .error = 1, }, [ICMP_PARAMETERPROB] = { .handler = icmp_unreach, .error = 1, }, [ICMP_TIMESTAMP] = { .handler = icmp_timestamp, }, [ICMP_TIMESTAMPREPLY] = { .handler = icmp_discard, }, [ICMP_INFO_REQUEST] = { .handler = icmp_discard, }, [ICMP_INFO_REPLY] = { .handler = icmp_discard, }, [ICMP_ADDRESS] = { .handler = icmp_address, }, [ICMP_ADDRESSREPLY] = { .handler = icmp_address_reply, }, }; static void __net_exit icmp_sk_exit(struct net *net) { int i; for_each_possible_cpu(i) inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]); kfree(net->ipv4.icmp_sk); net->ipv4.icmp_sk = NULL; } static int __net_init icmp_sk_init(struct net *net) { int i, err; net->ipv4.icmp_sk = kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL); if (net->ipv4.icmp_sk == NULL) return -ENOMEM; for_each_possible_cpu(i) { struct sock *sk; err = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_ICMP, net); if (err < 0) goto fail; net->ipv4.icmp_sk[i] = sk; sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; } net->ipv4.sysctl_icmp_echo_ignore_all = 0; net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1; net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1; net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; return 0; fail: for_each_possible_cpu(i) inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]); kfree(net->ipv4.icmp_sk); return err; } static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, .exit = icmp_sk_exit, }; int __init icmp_init(void) { return register_pernet_subsys(&icmp_sk_ops); }