// SPDX-License-Identifier: GPL-2.0-or-later/* * NET3: Implementation of the ICMP protocol layer. * * Alan Cox, <alan@lxorguk.ukuu.org.uk> * * 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 <linux/module.h>#include <linux/types.h>#include <linux/jiffies.h>#include <linux/kernel.h>#include <linux/fcntl.h>#include <linux/nospec.h>#include <linux/socket.h>#include <linux/in.h>#include <linux/inet.h>#include <linux/inetdevice.h>#include <linux/netdevice.h>#include <linux/string.h>#include <linux/netfilter_ipv4.h>#include <linux/slab.h>#include <net/flow.h>#include <net/snmp.h>#include <net/ip.h>#include <net/route.h>#include <net/protocol.h>#include <net/icmp.h>#include <net/tcp.h>#include <net/udp.h>#include <net/raw.h>#include <net/ping.h>#include <linux/skbuff.h>#include <net/sock.h>#include <linux/errno.h>#include <linux/timer.h>#include <linux/init.h>#include <linux/uaccess.h>#include <net/checksum.h>#include <net/xfrm.h>#include <net/inet_common.h>#include <net/ip_fib.h>#include <net/l3mdev.h>#include <net/addrconf.h>#include <net/inet_dscp.h>#define CREATE_TRACE_POINTS#include <trace/events/icmp.h> /* * Build xmit assembly blocks */ struct icmp_bxm { struct sk_buff *skb; int offset; int data_len; struct { struct icmphdr icmph; __be32 times[3]; } data; int head_len; /* Must be last as it ends in a flexible-array member. */ struct ip_options_rcu replyopts;}; /* An array of errno for error messages from dest unreach. *//* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */ const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, /* ICMP_NET_UNREACH */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNREACH */ .fatal = 0, }, { .errno = ENOPROTOOPT /* ICMP_PROT_UNREACH */, .fatal = 1, }, { .errno = ECONNREFUSED, /* ICMP_PORT_UNREACH */ .fatal = 1, }, { .errno = EMSGSIZE, /* ICMP_FRAG_NEEDED */ .fatal = 0, }, { .errno = EOPNOTSUPP, /* ICMP_SR_FAILED */ .fatal = 0, }, { .errno = ENETUNREACH, /* ICMP_NET_UNKNOWN */ .fatal = 1, }, { .errno = EHOSTDOWN, /* ICMP_HOST_UNKNOWN */ .fatal = 1, }, { .errno = ENONET, /* ICMP_HOST_ISOLATED */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_ANO */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_ANO */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_PKT_FILTERED */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_VIOLATION */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_CUTOFF */ .fatal = 1, },};EXPORT_SYMBOL(icmp_err_convert); /* * ICMP control array. This specifies what to do with each ICMP. */ struct icmp_control { enum skb_drop_reason (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */}; static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */static inline struct sock *icmp_xmit_lock(struct net *net){ struct sock *sk; sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ return NULL; } sock_net_set(sk, net); return sk;} static inline void icmp_xmit_unlock(struct sock *sk){ sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock);} /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * @net: network namespace * * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Works in tandem with icmp_global_consume(). */bool icmp_global_allow(struct net *net){ u32 delta, now, oldstamp; int incr, new, old; /* Note: many cpus could find this condition true. * Then later icmp_global_consume() could consume more credits, * this is an acceptable race. */ if (atomic_read(&net->ipv4.icmp_global_credit) > 0) return true; now = jiffies; oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp); delta = min_t(u32, now - oldstamp, HZ); if (delta < HZ / 50) return false; incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec); incr = div_u64((u64)incr * delta, HZ); if (!incr) return false; if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) { old = atomic_read(&net->ipv4.icmp_global_credit); do { new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst)); } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new)); } return true;} void icmp_global_consume(struct net *net){ int credits = get_random_u32_below(3); /* Note: this might make icmp_global.credit negative. */ if (credits) atomic_sub(credits, &net->ipv4.icmp_global_credit);} static bool icmpv4_mask_allow(struct net *net, int type, int code){ if (type > NR_ICMP_TYPES) return true; /* Don't limit PMTU discovery. */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) return true; /* Limit if icmp type is enabled in ratemask. */ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false;} static bool icmpv4_global_allow(struct net *net, int type, int code, bool *apply_ratelimit){ if (icmpv4_mask_allow(net, type, code)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false;} /* * Send an ICMP frame. */ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct flowi4 *fl4, int type, int code, bool apply_ratelimit){ struct dst_entry *dst = &rt->dst; struct inet_peer *peer; struct net_device *dev; int peer_timeout; bool rc = true; if (!apply_ratelimit) return true; peer_timeout = READ_ONCE(net->ipv4.sysctl_icmp_ratelimit); if (!peer_timeout) goto out; /* No rate limit on loopback */ rcu_read_lock(); dev = dst_dev_rcu(dst); if (dev && (dev->flags & IFF_LOOPBACK)) goto out_unlock; peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, l3mdev_master_ifindex_rcu(dev)); rc = inet_peer_xrlim_allow(peer, peer_timeout); out_unlock: rcu_read_unlock();out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); else icmp_global_consume(net); return rc;} /* * Maintain the counters used in the SNMP statistics for outgoing ICMP */void icmp_out_count(struct net *net, unsigned char type){ ICMPMSGOUT_INC_STATS(net, type); ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS);} /* * Checksum each fragment, and on the first include the headers and final * checksum. */static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb){ DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); __wsum csum; icmp_param = from; csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_param->data.icmph.type <= NR_ICMP_TYPES && icmp_pointers[array_index_nospec(icmp_param->data.icmph.type, NR_ICMP_TYPES + 1)].error) nf_ct_attach(skb, icmp_param->skb); return 0;} static void icmp_push_reply(struct sock *sk, struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt){ struct sk_buff *skb; 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(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; struct sk_buff *skb1; csum = csum_partial_copy_nocheck((void *)&icmp_param->data, (char *)icmph, icmp_param->head_len); skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); }} /* * Driving logic for building and sending ICMP messages. */ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb){ struct rtable *rt = skb_rtable(skb); struct net *net = dev_net_rcu(rt->dst.dev); bool apply_ratelimit = false; struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; int code = icmp_param->data.icmph.code; if (ip_options_echo(net, &icmp_param->replyopts.opt, skb)) return; /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* is global icmp_msgs_per_sec exhausted ? */ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); ipc.tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); if (icmp_param->replyopts.opt.optlen) { ipc.opt = &icmp_param->replyopts; if (ipc.opt->opt.srr) daddr = icmp_param->replyopts.opt.faddr; } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_dscp = ip4h_dscp(ip_hdr(skb)); fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt);out_unlock: icmp_xmit_unlock(sk);out_bh_enable: local_bh_enable();} /* * The device used for looking up which routing table to use for sending an ICMP * error is preferably the source whenever it is set, which should ensure the * icmp error can be sent to the source host, else lookup using the routing * table of the destination device, else use the main routing table (index 0). */static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb){ struct net_device *dev = skb->dev; const struct dst_entry *dst; if (dev) return dev; dst = skb_dst(skb); return dst ? dst_dev(dst) : NULL;} static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, __be32 saddr, dscp_t dscp, u32 mark, int type, int code, struct icmp_bxm *param){ struct net_device *route_lookup_dev;Lines 1–500 of 1781. Load more
// SPDX-License-Identifier: GPL-2.0-or-later /* * NET3: Implementation of the ICMP protocol layer. * * Alan Cox, <alan@lxorguk.ukuu.org.uk> * * 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 <linux/module.h> #include <linux/types.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/nospec.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/string.h> #include <linux/netfilter_ipv4.h> #include <linux/slab.h> #include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/route.h> #include <net/protocol.h> #include <net/icmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/raw.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/init.h> #include <linux/uaccess.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> #include <net/l3mdev.h> #include <net/addrconf.h> #include <net/inet_dscp.h> #define CREATE_TRACE_POINTS #include <trace/events/icmp.h> /* * Build xmit assembly blocks */ struct icmp_bxm { struct sk_buff *skb; int offset; int data_len; struct { struct icmphdr icmph; __be32 times[3]; } data; int head_len; /* Must be last as it ends in a flexible-array member. */ struct ip_options_rcu replyopts; }; /* An array of errno for error messages from dest unreach. */ /* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */ const struct icmp_err icmp_err_convert[] = { { .errno = ENETUNREACH, /* ICMP_NET_UNREACH */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNREACH */ .fatal = 0, }, { .errno = ENOPROTOOPT /* ICMP_PROT_UNREACH */, .fatal = 1, }, { .errno = ECONNREFUSED, /* ICMP_PORT_UNREACH */ .fatal = 1, }, { .errno = EMSGSIZE, /* ICMP_FRAG_NEEDED */ .fatal = 0, }, { .errno = EOPNOTSUPP, /* ICMP_SR_FAILED */ .fatal = 0, }, { .errno = ENETUNREACH, /* ICMP_NET_UNKNOWN */ .fatal = 1, }, { .errno = EHOSTDOWN, /* ICMP_HOST_UNKNOWN */ .fatal = 1, }, { .errno = ENONET, /* ICMP_HOST_ISOLATED */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_ANO */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_ANO */ .fatal = 1, }, { .errno = ENETUNREACH, /* ICMP_NET_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */ .fatal = 0, }, { .errno = EHOSTUNREACH, /* ICMP_PKT_FILTERED */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_VIOLATION */ .fatal = 1, }, { .errno = EHOSTUNREACH, /* ICMP_PREC_CUTOFF */ .fatal = 1, }, }; EXPORT_SYMBOL(icmp_err_convert); /* * ICMP control array. This specifies what to do with each ICMP. */ struct icmp_control { enum skb_drop_reason (*handler)(struct sk_buff *skb); short error; /* This ICMP is classed as an error message */ }; static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a * dst_link_failure() for an outgoing ICMP packet. */ return NULL; } sock_net_set(sk, net); return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * @net: network namespace * * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Works in tandem with icmp_global_consume(). */ bool icmp_global_allow(struct net *net) { u32 delta, now, oldstamp; int incr, new, old; /* Note: many cpus could find this condition true. * Then later icmp_global_consume() could consume more credits, * this is an acceptable race. */ if (atomic_read(&net->ipv4.icmp_global_credit) > 0) return true; now = jiffies; oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp); delta = min_t(u32, now - oldstamp, HZ); if (delta < HZ / 50) return false; incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec); incr = div_u64((u64)incr * delta, HZ); if (!incr) return false; if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) { old = atomic_read(&net->ipv4.icmp_global_credit); do { new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst)); } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new)); } return true; } void icmp_global_consume(struct net *net) { int credits = get_random_u32_below(3); /* Note: this might make icmp_global.credit negative. */ if (credits) atomic_sub(credits, &net->ipv4.icmp_global_credit); } static bool icmpv4_mask_allow(struct net *net, int type, int code) { if (type > NR_ICMP_TYPES) return true; /* Don't limit PMTU discovery. */ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) return true; /* Limit if icmp type is enabled in ratemask. */ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; } static bool icmpv4_global_allow(struct net *net, int type, int code, bool *apply_ratelimit) { if (icmpv4_mask_allow(net, type, code)) return true; if (icmp_global_allow(net)) { *apply_ratelimit = true; return true; } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } /* * Send an ICMP frame. */ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, struct flowi4 *fl4, int type, int code, bool apply_ratelimit) { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; struct net_device *dev; int peer_timeout; bool rc = true; if (!apply_ratelimit) return true; peer_timeout = READ_ONCE(net->ipv4.sysctl_icmp_ratelimit); if (!peer_timeout) goto out; /* No rate limit on loopback */ rcu_read_lock(); dev = dst_dev_rcu(dst); if (dev && (dev->flags & IFF_LOOPBACK)) goto out_unlock; peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, l3mdev_master_ifindex_rcu(dev)); rc = inet_peer_xrlim_allow(peer, peer_timeout); out_unlock: rcu_read_unlock(); out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); else icmp_global_consume(net); return rc; } /* * Maintain the counters used in the SNMP statistics for outgoing ICMP */ void icmp_out_count(struct net *net, unsigned char type) { ICMPMSGOUT_INC_STATS(net, type); ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS); } /* * Checksum each fragment, and on the first include the headers and final * checksum. */ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { DEFINE_RAW_FLEX(struct icmp_bxm, icmp_param, replyopts.opt.__data, IP_OPTIONS_DATA_FIXED_SIZE); __wsum csum; icmp_param = from; csum = skb_copy_and_csum_bits(icmp_param->skb, icmp_param->offset + offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); if (icmp_param->data.icmph.type <= NR_ICMP_TYPES && icmp_pointers[array_index_nospec(icmp_param->data.icmph.type, NR_ICMP_TYPES + 1)].error) nf_ct_attach(skb, icmp_param->skb); return 0; } static void icmp_push_reply(struct sock *sk, struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { struct sk_buff *skb; 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(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; struct sk_buff *skb1; csum = csum_partial_copy_nocheck((void *)&icmp_param->data, (char *)icmph, icmp_param->head_len); skb_queue_walk(&sk->sk_write_queue, skb1) { csum = csum_add(csum, skb1->csum); } icmph->checksum = csum_fold(csum); skb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, fl4); } } /* * Driving logic for building and sending ICMP messages. */ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net *net = dev_net_rcu(rt->dst.dev); bool apply_ratelimit = false; struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; int code = icmp_param->data.icmph.code; if (ip_options_echo(net, &icmp_param->replyopts.opt, skb)) return; /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* is global icmp_msgs_per_sec exhausted ? */ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); ipc.tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); if (icmp_param->replyopts.opt.optlen) { ipc.opt = &icmp_param->replyopts; if (ipc.opt->opt.srr) daddr = icmp_param->replyopts.opt.faddr; } memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_dscp = ip4h_dscp(ip_hdr(skb)); fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); } /* * The device used for looking up which routing table to use for sending an ICMP * error is preferably the source whenever it is set, which should ensure the * icmp error can be sent to the source host, else lookup using the routing * table of the destination device, else use the main routing table (index 0). */ static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct dst_entry *dst; if (dev) return dev; dst = skb_dst(skb); return dst ? dst_dev(dst) : NULL; } static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, const struct iphdr *iph, __be32 saddr, dscp_t dscp, u32 mark, int type, int code, struct icmp_bxm *param) { struct net_device *route_lookup_dev;