From 5b1158e909ecbe1a052203e0d8df15633f829930 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Sat, 2 Dec 2006 22:07:13 -0800 Subject: [NETFILTER]: Add NAT support for nf_conntrack Add NAT support for nf_conntrack. Joint work of Jozsef Kadlecsik, Yasuyuki Kozakai, Martin Josefsson and myself. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv4/netfilter/Kconfig | 30 +- net/ipv4/netfilter/Makefile | 7 + net/ipv4/netfilter/ip_nat_standalone.c | 6 - net/ipv4/netfilter/ipt_MASQUERADE.c | 29 +- net/ipv4/netfilter/ipt_NETMAP.c | 4 + net/ipv4/netfilter/ipt_REDIRECT.c | 6 +- net/ipv4/netfilter/ipt_SAME.c | 12 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 7 +- net/ipv4/netfilter/nf_nat_core.c | 647 +++++++++++++++++++++++++ net/ipv4/netfilter/nf_nat_helper.c | 433 +++++++++++++++++ net/ipv4/netfilter/nf_nat_proto_icmp.c | 86 ++++ net/ipv4/netfilter/nf_nat_proto_tcp.c | 148 ++++++ net/ipv4/netfilter/nf_nat_proto_udp.c | 138 ++++++ net/ipv4/netfilter/nf_nat_proto_unknown.c | 54 +++ net/ipv4/netfilter/nf_nat_rule.c | 343 +++++++++++++ net/ipv4/netfilter/nf_nat_standalone.c | 406 ++++++++++++++++ 16 files changed, 2337 insertions(+), 19 deletions(-) create mode 100644 net/ipv4/netfilter/nf_nat_core.c create mode 100644 net/ipv4/netfilter/nf_nat_helper.c create mode 100644 net/ipv4/netfilter/nf_nat_proto_icmp.c create mode 100644 net/ipv4/netfilter/nf_nat_proto_tcp.c create mode 100644 net/ipv4/netfilter/nf_nat_proto_udp.c create mode 100644 net/ipv4/netfilter/nf_nat_proto_unknown.c create mode 100644 net/ipv4/netfilter/nf_nat_rule.c create mode 100644 net/ipv4/netfilter/nf_nat_standalone.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 71485276b81..01789aeaeb5 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -6,7 +6,7 @@ menu "IP: Netfilter Configuration" depends on INET && NETFILTER config NF_CONNTRACK_IPV4 - tristate "IPv4 support for new connection tracking (EXPERIMENTAL)" + tristate "IPv4 support for new connection tracking (required for NAT) (EXPERIMENTAL)" depends on EXPERIMENTAL && NF_CONNTRACK ---help--- Connection tracking keeps a record of what packets have passed @@ -387,7 +387,7 @@ config IP_NF_TARGET_TCPMSS To compile it as a module, choose M here. If unsure, say N. -# NAT + specific targets +# NAT + specific targets: ip_conntrack config IP_NF_NAT tristate "Full NAT" depends on IP_NF_IPTABLES && IP_NF_CONNTRACK @@ -398,14 +398,30 @@ config IP_NF_NAT To compile it as a module, choose M here. If unsure, say N. +# NAT + specific targets: nf_conntrack +config NF_NAT + tristate "Full NAT" + depends on IP_NF_IPTABLES && NF_CONNTRACK + help + The Full NAT option allows masquerading, port forwarding and other + forms of full Network Address Port Translation. It is controlled by + the `nat' table in iptables: see the man page for iptables(8). + + To compile it as a module, choose M here. If unsure, say N. + config IP_NF_NAT_NEEDED bool - depends on IP_NF_NAT != n + depends on IP_NF_NAT + default y + +config NF_NAT_NEEDED + bool + depends on NF_NAT default y config IP_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" - depends on IP_NF_NAT + depends on (NF_NAT || IP_NF_NAT) help Masquerading is a special case of NAT: all outgoing connections are changed to seem to come from a particular interface's address, and @@ -417,7 +433,7 @@ config IP_NF_TARGET_MASQUERADE config IP_NF_TARGET_REDIRECT tristate "REDIRECT target support" - depends on IP_NF_NAT + depends on (NF_NAT || IP_NF_NAT) help REDIRECT is a special case of NAT: all incoming connections are mapped onto the incoming interface's address, causing the packets to @@ -428,7 +444,7 @@ config IP_NF_TARGET_REDIRECT config IP_NF_TARGET_NETMAP tristate "NETMAP target support" - depends on IP_NF_NAT + depends on (NF_NAT || IP_NF_NAT) help NETMAP is an implementation of static 1:1 NAT mapping of network addresses. It maps the network address part, while keeping the host @@ -439,7 +455,7 @@ config IP_NF_TARGET_NETMAP config IP_NF_TARGET_SAME tristate "SAME target support" - depends on IP_NF_NAT + depends on (NF_NAT || IP_NF_NAT) help This option adds a `SAME' target, which works like the standard SNAT target, but attempts to give clients the same IP for all connections. diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 21359d83f0c..ec31690764a 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -5,7 +5,12 @@ # objects for the standalone - connection tracking / NAT ip_conntrack-objs := ip_conntrack_standalone.o ip_conntrack_core.o ip_conntrack_proto_generic.o ip_conntrack_proto_tcp.o ip_conntrack_proto_udp.o ip_conntrack_proto_icmp.o ip_nat-objs := ip_nat_core.o ip_nat_helper.o ip_nat_proto_unknown.o ip_nat_proto_tcp.o ip_nat_proto_udp.o ip_nat_proto_icmp.o +nf_nat-objs := nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o +ifneq ($(CONFIG_NF_NAT),) +iptable_nat-objs := nf_nat_rule.o nf_nat_standalone.o +else iptable_nat-objs := ip_nat_rule.o ip_nat_standalone.o +endif ip_conntrack_pptp-objs := ip_conntrack_helper_pptp.o ip_conntrack_proto_gre.o ip_nat_pptp-objs := ip_nat_helper_pptp.o ip_nat_proto_gre.o @@ -16,6 +21,7 @@ ip_nat_h323-objs := ip_nat_helper_h323.o # connection tracking obj-$(CONFIG_IP_NF_CONNTRACK) += ip_conntrack.o obj-$(CONFIG_IP_NF_NAT) += ip_nat.o +obj-$(CONFIG_NF_NAT) += nf_nat.o # conntrack netlink interface obj-$(CONFIG_IP_NF_CONNTRACK_NETLINK) += ip_conntrack_netlink.o @@ -50,6 +56,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o obj-$(CONFIG_IP_NF_NAT) += iptable_nat.o +obj-$(CONFIG_NF_NAT) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o # matches diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index d85d2de5044..ad66328baa5 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -44,12 +44,6 @@ #define DEBUGP(format, args...) #endif -#define HOOKNAME(hooknum) ((hooknum) == NF_IP_POST_ROUTING ? "POST_ROUTING" \ - : ((hooknum) == NF_IP_PRE_ROUTING ? "PRE_ROUTING" \ - : ((hooknum) == NF_IP_LOCAL_OUT ? "LOCAL_OUT" \ - : ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN" \ - : "*ERROR*"))) - #ifdef CONFIG_XFRM static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) { diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 3dbfcfac8a8..28b9233956b 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -2,7 +2,7 @@ (depending on route). */ /* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team + * (C) 2002-2006 Netfilter Core Team * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -20,7 +20,11 @@ #include #include #include +#ifdef CONFIG_NF_NAT_NEEDED +#include +#else #include +#endif #include MODULE_LICENSE("GPL"); @@ -65,23 +69,33 @@ masquerade_target(struct sk_buff **pskb, const struct xt_target *target, const void *targinfo) { +#ifdef CONFIG_NF_NAT_NEEDED + struct nf_conn_nat *nat; +#endif struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; - const struct ip_nat_multi_range_compat *mr; struct ip_nat_range newrange; + const struct ip_nat_multi_range_compat *mr; struct rtable *rt; __be32 newsrc; IP_NF_ASSERT(hooknum == NF_IP_POST_ROUTING); ct = ip_conntrack_get(*pskb, &ctinfo); +#ifdef CONFIG_NF_NAT_NEEDED + nat = nfct_nat(ct); +#endif IP_NF_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. */ +#ifdef CONFIG_NF_NAT_NEEDED + if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0) +#else if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip == 0) +#endif return NF_ACCEPT; mr = targinfo; @@ -93,7 +107,11 @@ masquerade_target(struct sk_buff **pskb, } write_lock_bh(&masq_lock); +#ifdef CONFIG_NF_NAT_NEEDED + nat->masq_index = out->ifindex; +#else ct->nat.masq_index = out->ifindex; +#endif write_unlock_bh(&masq_lock); /* Transfer from original range. */ @@ -109,10 +127,17 @@ masquerade_target(struct sk_buff **pskb, static inline int device_cmp(struct ip_conntrack *i, void *ifindex) { +#ifdef CONFIG_NF_NAT_NEEDED + struct nf_conn_nat *nat = nfct_nat(i); +#endif int ret; read_lock_bh(&masq_lock); +#ifdef CONFIG_NF_NAT_NEEDED + ret = (nat->masq_index == (int)(long)ifindex); +#else ret = (i->nat.masq_index == (int)(long)ifindex); +#endif read_unlock_bh(&masq_lock); return ret; diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 58a88f22710..9390e90f2b2 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -15,7 +15,11 @@ #include #include #include +#ifdef CONFIG_NF_NAT_NEEDED +#include +#else #include +#endif #define MODULENAME "NETMAP" MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index c0dcfe9d610..462eceb3a1b 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -1,6 +1,6 @@ /* Redirect. Simple mapping which alters dst to a local IP address. */ /* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team + * (C) 2002-2006 Netfilter Core Team * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -18,7 +18,11 @@ #include #include #include +#ifdef CONFIG_NF_NAT_NEEDED +#include +#else #include +#endif MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index b38b13328d7..3dcf2941133 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -34,7 +34,11 @@ #include #include #include +#ifdef CONFIG_NF_NAT_NEEDED +#include +#else #include +#endif #include MODULE_LICENSE("GPL"); @@ -152,11 +156,17 @@ same_target(struct sk_buff **pskb, Here we calculate the index in same->iparray which holds the ipaddress we should use */ +#ifdef CONFIG_NF_NAT_NEEDED + tmpip = ntohl(t->src.u3.ip); + + if (!(same->info & IPT_SAME_NODST)) + tmpip += ntohl(t->dst.u3.ip); +#else tmpip = ntohl(t->src.ip); if (!(same->info & IPT_SAME_NODST)) tmpip += ntohl(t->dst.ip); - +#endif aindex = tmpip % same->ipnum; new_ip = htonl(same->iparray[aindex]); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 653f57b8a10..5655109dcaf 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -111,10 +111,10 @@ ipv4_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff, return NF_ACCEPT; } -int nat_module_is_loaded = 0; +int nf_nat_module_is_loaded = 0; static u_int32_t ipv4_get_features(const struct nf_conntrack_tuple *tuple) { - if (nat_module_is_loaded) + if (nf_nat_module_is_loaded) return NF_CT_F_NAT; return NF_CT_F_BASIC; @@ -532,3 +532,6 @@ module_init(nf_conntrack_l3proto_ipv4_init); module_exit(nf_conntrack_l3proto_ipv4_fini); EXPORT_SYMBOL(nf_ct_ipv4_gather_frags); +#ifdef CONFIG_NF_NAT_NEEDED +EXPORT_SYMBOL(nf_nat_module_is_loaded); +#endif diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c new file mode 100644 index 00000000000..86a92272b05 --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -0,0 +1,647 @@ +/* NAT for netfilter; shared with compatibility layer. */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include /* For tcp_prot in getorigdst */ +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +static DEFINE_RWLOCK(nf_nat_lock); + +static struct nf_conntrack_l3proto *l3proto = NULL; + +/* Calculated at init based on memory size */ +static unsigned int nf_nat_htable_size; + +static struct list_head *bysource; + +#define MAX_IP_NAT_PROTO 256 +static struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]; + +static inline struct nf_nat_protocol * +__nf_nat_proto_find(u_int8_t protonum) +{ + return nf_nat_protos[protonum]; +} + +struct nf_nat_protocol * +nf_nat_proto_find_get(u_int8_t protonum) +{ + struct nf_nat_protocol *p; + + /* we need to disable preemption to make sure 'p' doesn't get + * removed until we've grabbed the reference */ + preempt_disable(); + p = __nf_nat_proto_find(protonum); + if (!try_module_get(p->me)) + p = &nf_nat_unknown_protocol; + preempt_enable(); + + return p; +} +EXPORT_SYMBOL_GPL(nf_nat_proto_find_get); + +void +nf_nat_proto_put(struct nf_nat_protocol *p) +{ + module_put(p->me); +} +EXPORT_SYMBOL_GPL(nf_nat_proto_put); + +/* We keep an extra hash for each conntrack, for fast searching. */ +static inline unsigned int +hash_by_src(const struct nf_conntrack_tuple *tuple) +{ + /* Original src, to ensure we map it consistently if poss. */ + return jhash_3words((__force u32)tuple->src.u3.ip, tuple->src.u.all, + tuple->dst.protonum, 0) % nf_nat_htable_size; +} + +/* Noone using conntrack by the time this called. */ +static void nf_nat_cleanup_conntrack(struct nf_conn *conn) +{ + struct nf_conn_nat *nat; + if (!(conn->status & IPS_NAT_DONE_MASK)) + return; + + nat = nfct_nat(conn); + write_lock_bh(&nf_nat_lock); + list_del(&nat->info.bysource); + write_unlock_bh(&nf_nat_lock); +} + +/* Is this tuple already taken? (not by us) */ +int +nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, + const struct nf_conn *ignored_conntrack) +{ + /* Conntrack tracking doesn't keep track of outgoing tuples; only + incoming ones. NAT means they don't have a fixed mapping, + so we invert the tuple and look for the incoming reply. + + We could keep a separate hash if this proves too slow. */ + struct nf_conntrack_tuple reply; + + nf_ct_invert_tuplepr(&reply, tuple); + return nf_conntrack_tuple_taken(&reply, ignored_conntrack); +} +EXPORT_SYMBOL(nf_nat_used_tuple); + +/* If we source map this tuple so reply looks like reply_tuple, will + * that meet the constraints of range. */ +static int +in_range(const struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range) +{ + struct nf_nat_protocol *proto; + + proto = __nf_nat_proto_find(tuple->dst.protonum); + /* If we are supposed to map IPs, then we must be in the + range specified, otherwise let this drag us onto a new src IP. */ + if (range->flags & IP_NAT_RANGE_MAP_IPS) { + if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) || + ntohl(tuple->src.u3.ip) > ntohl(range->max_ip)) + return 0; + } + + if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || + proto->in_range(tuple, IP_NAT_MANIP_SRC, + &range->min, &range->max)) + return 1; + + return 0; +} + +static inline int +same_src(const struct nf_conn *ct, + const struct nf_conntrack_tuple *tuple) +{ + const struct nf_conntrack_tuple *t; + + t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + return (t->dst.protonum == tuple->dst.protonum && + t->src.u3.ip == tuple->src.u3.ip && + t->src.u.all == tuple->src.u.all); +} + +/* Only called for SRC manip */ +static int +find_appropriate_src(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *result, + const struct nf_nat_range *range) +{ + unsigned int h = hash_by_src(tuple); + struct nf_conn_nat *nat; + struct nf_conn *ct; + + read_lock_bh(&nf_nat_lock); + list_for_each_entry(nat, &bysource[h], info.bysource) { + ct = (struct nf_conn *)((char *)nat - offsetof(struct nf_conn, data)); + if (same_src(ct, tuple)) { + /* Copy source part from reply tuple. */ + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + if (in_range(result, range)) { + read_unlock_bh(&nf_nat_lock); + return 1; + } + } + } + read_unlock_bh(&nf_nat_lock); + return 0; +} + +/* For [FUTURE] fragmentation handling, we want the least-used + src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus + if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports + 1-65535, we don't do pro-rata allocation based on ports; we choose + the ip with the lowest src-ip/dst-ip/proto usage. +*/ +static void +find_best_ips_proto(struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + const struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + __be32 *var_ipp; + /* Host order */ + u_int32_t minip, maxip, j; + + /* No IP mapping? Do nothing. */ + if (!(range->flags & IP_NAT_RANGE_MAP_IPS)) + return; + + if (maniptype == IP_NAT_MANIP_SRC) + var_ipp = &tuple->src.u3.ip; + else + var_ipp = &tuple->dst.u3.ip; + + /* Fast path: only one choice. */ + if (range->min_ip == range->max_ip) { + *var_ipp = range->min_ip; + return; + } + + /* Hashing source and destination IPs gives a fairly even + * spread in practice (if there are a small number of IPs + * involved, there usually aren't that many connections + * anyway). The consistency means that servers see the same + * client coming from the same IP (some Internet Banking sites + * like this), even across reboots. */ + minip = ntohl(range->min_ip); + maxip = ntohl(range->max_ip); + j = jhash_2words((__force u32)tuple->src.u3.ip, + (__force u32)tuple->dst.u3.ip, 0); + *var_ipp = htonl(minip + j % (maxip - minip + 1)); +} + +/* Manipulate the tuple into the range given. For NF_IP_POST_ROUTING, + * we change the source to map into the range. For NF_IP_PRE_ROUTING + * and NF_IP_LOCAL_OUT, we change the destination to map into the + * range. It might not be possible to get a unique tuple, but we try. + * At worst (or if we race), we will end up with a final duplicate in + * __ip_conntrack_confirm and drop the packet. */ +static void +get_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig_tuple, + const struct nf_nat_range *range, + struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + struct nf_nat_protocol *proto; + + /* 1) If this srcip/proto/src-proto-part is currently mapped, + and that same mapping gives a unique tuple within the given + range, use that. + + This is only required for source (ie. NAT/masq) mappings. + So far, we don't do local source mappings, so multiple + manips not an issue. */ + if (maniptype == IP_NAT_MANIP_SRC) { + if (find_appropriate_src(orig_tuple, tuple, range)) { + DEBUGP("get_unique_tuple: Found current src map\n"); + if (!nf_nat_used_tuple(tuple, ct)) + return; + } + } + + /* 2) Select the least-used IP/proto combination in the given + range. */ + *tuple = *orig_tuple; + find_best_ips_proto(tuple, range, ct, maniptype); + + /* 3) The per-protocol part of the manip is made to map into + the range to make a unique tuple. */ + + proto = nf_nat_proto_find_get(orig_tuple->dst.protonum); + + /* Only bother mapping if it's not already in range and unique */ + if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || + proto->in_range(tuple, maniptype, &range->min, &range->max)) && + !nf_nat_used_tuple(tuple, ct)) { + nf_nat_proto_put(proto); + return; + } + + /* Last change: get protocol to try to obtain unique tuple. */ + proto->unique_tuple(tuple, range, maniptype, ct); + + nf_nat_proto_put(proto); +} + +unsigned int +nf_nat_setup_info(struct nf_conn *ct, + const struct nf_nat_range *range, + unsigned int hooknum) +{ + struct nf_conntrack_tuple curr_tuple, new_tuple; + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_info *info = &nat->info; + int have_to_hash = !(ct->status & IPS_NAT_DONE_MASK); + enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + + NF_CT_ASSERT(hooknum == NF_IP_PRE_ROUTING || + hooknum == NF_IP_POST_ROUTING || + hooknum == NF_IP_LOCAL_IN || + hooknum == NF_IP_LOCAL_OUT); + BUG_ON(nf_nat_initialized(ct, maniptype)); + + /* What we've got will look like inverse of reply. Normally + this is what is in the conntrack, except for prior + manipulations (future optimization: if num_manips == 0, + orig_tp = + conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */ + nf_ct_invert_tuplepr(&curr_tuple, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); + + if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) { + struct nf_conntrack_tuple reply; + + /* Alter conntrack table so will recognize replies. */ + nf_ct_invert_tuplepr(&reply, &new_tuple); + nf_conntrack_alter_reply(ct, &reply); + + /* Non-atomic: we own this at the moment. */ + if (maniptype == IP_NAT_MANIP_SRC) + ct->status |= IPS_SRC_NAT; + else + ct->status |= IPS_DST_NAT; + } + + /* Place in source hash if this is the first time. */ + if (have_to_hash) { + unsigned int srchash; + + srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + write_lock_bh(&nf_nat_lock); + list_add(&info->bysource, &bysource[srchash]); + write_unlock_bh(&nf_nat_lock); + } + + /* It's done. */ + if (maniptype == IP_NAT_MANIP_DST) + set_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + else + set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + + return NF_ACCEPT; +} +EXPORT_SYMBOL(nf_nat_setup_info); + +/* Returns true if succeeded. */ +static int +manip_pkt(u_int16_t proto, + struct sk_buff **pskb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph; + struct nf_nat_protocol *p; + + if (!skb_make_writable(pskb, iphdroff + sizeof(*iph))) + return 0; + + iph = (void *)(*pskb)->data + iphdroff; + + /* Manipulate protcol part. */ + p = nf_nat_proto_find_get(proto); + if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) { + nf_nat_proto_put(p); + return 0; + } + nf_nat_proto_put(p); + + iph = (void *)(*pskb)->data + iphdroff; + + if (maniptype == IP_NAT_MANIP_SRC) { + nf_csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); + iph->saddr = target->src.u3.ip; + } else { + nf_csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); + iph->daddr = target->dst.u3.ip; + } + return 1; +} + +/* Do packet manipulations according to nf_nat_setup_info. */ +unsigned int nf_nat_packet(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff **pskb) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned long statusbit; + enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); + + if (mtype == IP_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + /* Non-atomic: these bits don't change. */ + if (ct->status & statusbit) { + struct nf_conntrack_tuple target; + + /* We are aiming to look like inverse of other direction. */ + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + + if (!manip_pkt(target.dst.protonum, pskb, 0, &target, mtype)) + return NF_DROP; + } + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_nat_packet); + +/* Dir is direction ICMP is coming from (opposite to packet it contains) */ +int nf_nat_icmp_reply_translation(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff **pskb) +{ + struct { + struct icmphdr icmp; + struct iphdr ip; + } *inside; + struct nf_conntrack_tuple inner, target; + int hdrlen = (*pskb)->nh.iph->ihl * 4; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned long statusbit; + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + + if (!skb_make_writable(pskb, hdrlen + sizeof(*inside))) + return 0; + + inside = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; + + /* We're actually going to mangle it beyond trivial checksum + adjustment, so make sure the current checksum is correct. */ + if (nf_ip_checksum(*pskb, hooknum, hdrlen, 0)) + return 0; + + /* Must be RELATED */ + NF_CT_ASSERT((*pskb)->nfctinfo == IP_CT_RELATED || + (*pskb)->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY); + + /* Redirects on non-null nats must be dropped, else they'll + start talking to each other without our translation, and be + confused... --RR */ + if (inside->icmp.type == ICMP_REDIRECT) { + /* If NAT isn't finished, assume it and drop. */ + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + + if (ct->status & IPS_NAT_MASK) + return 0; + } + + DEBUGP("icmp_reply_translation: translating error %p manp %u dir %s\n", + *pskb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); + + if (!nf_ct_get_tuple(*pskb, + (*pskb)->nh.iph->ihl*4 + sizeof(struct icmphdr), + (*pskb)->nh.iph->ihl*4 + + sizeof(struct icmphdr) + inside->ip.ihl*4, + (u_int16_t)AF_INET, + inside->ip.protocol, + &inner, + l3proto, + __nf_ct_l4proto_find((u_int16_t)PF_INET, + inside->ip.protocol))) + return 0; + + /* Change inner back to look like incoming packet. We do the + opposite manip on this hook to normal, because it might not + pass all hooks (locally-generated ICMP). Consider incoming + packet: PREROUTING (DST manip), routing produces ICMP, goes + through POSTROUTING (which must correct the DST manip). */ + if (!manip_pkt(inside->ip.protocol, pskb, + (*pskb)->nh.iph->ihl*4 + sizeof(inside->icmp), + &ct->tuplehash[!dir].tuple, + !manip)) + return 0; + + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { + /* Reloading "inside" here since manip_pkt inner. */ + inside = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; + inside->icmp.checksum = 0; + inside->icmp.checksum = + csum_fold(skb_checksum(*pskb, hdrlen, + (*pskb)->len - hdrlen, 0)); + } + + /* Change outer to look the reply to an incoming packet + * (proto 0 means don't invert per-proto part). */ + if (manip == IP_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + if (!manip_pkt(0, pskb, 0, &target, manip)) + return 0; + } + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); + +/* Protocol registration. */ +int nf_nat_protocol_register(struct nf_nat_protocol *proto) +{ + int ret = 0; + + write_lock_bh(&nf_nat_lock); + if (nf_nat_protos[proto->protonum] != &nf_nat_unknown_protocol) { + ret = -EBUSY; + goto out; + } + nf_nat_protos[proto->protonum] = proto; + out: + write_unlock_bh(&nf_nat_lock); + return ret; +} +EXPORT_SYMBOL(nf_nat_protocol_register); + +/* Noone stores the protocol anywhere; simply delete it. */ +void nf_nat_protocol_unregister(struct nf_nat_protocol *proto) +{ + write_lock_bh(&nf_nat_lock); + nf_nat_protos[proto->protonum] = &nf_nat_unknown_protocol; + write_unlock_bh(&nf_nat_lock); + + /* Someone could be still looking at the proto in a bh. */ + synchronize_net(); +} +EXPORT_SYMBOL(nf_nat_protocol_unregister); + +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +int +nf_nat_port_range_to_nfattr(struct sk_buff *skb, + const struct nf_nat_range *range) +{ + NFA_PUT(skb, CTA_PROTONAT_PORT_MIN, sizeof(__be16), + &range->min.tcp.port); + NFA_PUT(skb, CTA_PROTONAT_PORT_MAX, sizeof(__be16), + &range->max.tcp.port); + + return 0; + +nfattr_failure: + return -1; +} +EXPORT_SYMBOL_GPL(nf_nat_port_nfattr_to_range); + +int +nf_nat_port_nfattr_to_range(struct nfattr *tb[], struct nf_nat_range *range) +{ + int ret = 0; + + /* we have to return whether we actually parsed something or not */ + + if (tb[CTA_PROTONAT_PORT_MIN-1]) { + ret = 1; + range->min.tcp.port = + *(__be16 *)NFA_DATA(tb[CTA_PROTONAT_PORT_MIN-1]); + } + + if (!tb[CTA_PROTONAT_PORT_MAX-1]) { + if (ret) + range->max.tcp.port = range->min.tcp.port; + } else { + ret = 1; + range->max.tcp.port = + *(__be16 *)NFA_DATA(tb[CTA_PROTONAT_PORT_MAX-1]); + } + + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_port_range_to_nfattr); +#endif + +static int __init nf_nat_init(void) +{ + size_t i; + + /* Leave them the same for the moment. */ + nf_nat_htable_size = nf_conntrack_htable_size; + + /* One vmalloc for both hash tables */ + bysource = vmalloc(sizeof(struct list_head) * nf_nat_htable_size); + if (!bysource) + return -ENOMEM; + + /* Sew in builtin protocols. */ + write_lock_bh(&nf_nat_lock); + for (i = 0; i < MAX_IP_NAT_PROTO; i++) + nf_nat_protos[i] = &nf_nat_unknown_protocol; + nf_nat_protos[IPPROTO_TCP] = &nf_nat_protocol_tcp; + nf_nat_protos[IPPROTO_UDP] = &nf_nat_protocol_udp; + nf_nat_protos[IPPROTO_ICMP] = &nf_nat_protocol_icmp; + write_unlock_bh(&nf_nat_lock); + + for (i = 0; i < nf_nat_htable_size; i++) { + INIT_LIST_HEAD(&bysource[i]); + } + + /* FIXME: Man, this is a hack. */ + NF_CT_ASSERT(nf_conntrack_destroyed == NULL); + nf_conntrack_destroyed = &nf_nat_cleanup_conntrack; + + /* Initialize fake conntrack so that NAT will skip it */ + nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK; + + l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); + return 0; +} + +/* Clear NAT section of all conntracks, in case we're loaded again. */ +static int clean_nat(struct nf_conn *i, void *data) +{ + struct nf_conn_nat *nat = nfct_nat(i); + + if (!nat) + return 0; + memset(nat, 0, sizeof(nat)); + i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | IPS_SEQ_ADJUST); + return 0; +} + +static void __exit nf_nat_cleanup(void) +{ + nf_ct_iterate_cleanup(&clean_nat, NULL); + nf_conntrack_destroyed = NULL; + vfree(bysource); + nf_ct_l3proto_put(l3proto); +} + +MODULE_LICENSE("GPL"); + +module_init(nf_nat_init); +module_exit(nf_nat_cleanup); diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c new file mode 100644 index 00000000000..98fbfc84d18 --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -0,0 +1,433 @@ +/* ip_nat_helper.c - generic support functions for NAT helpers + * + * (C) 2000-2002 Harald Welte + * (C) 2003-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#define DUMP_OFFSET(x) printk("offset_before=%d, offset_after=%d, correction_pos=%u\n", x->offset_before, x->offset_after, x->correction_pos); +#else +#define DEBUGP(format, args...) +#define DUMP_OFFSET(x) +#endif + +static DEFINE_SPINLOCK(nf_nat_seqofs_lock); + +/* Setup TCP sequence correction given this change at this sequence */ +static inline void +adjust_tcp_sequence(u32 seq, + int sizediff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + int dir; + struct nf_nat_seq *this_way, *other_way; + struct nf_conn_nat *nat = nfct_nat(ct); + + DEBUGP("nf_nat_resize_packet: old_size = %u, new_size = %u\n", + (*skb)->len, new_size); + + dir = CTINFO2DIR(ctinfo); + + this_way = &nat->info.seq[dir]; + other_way = &nat->info.seq[!dir]; + + DEBUGP("nf_nat_resize_packet: Seq_offset before: "); + DUMP_OFFSET(this_way); + + spin_lock_bh(&nf_nat_seqofs_lock); + + /* SYN adjust. If it's uninitialized, or this is after last + * correction, record it: we don't handle more than one + * adjustment in the window, but do deal with common case of a + * retransmit */ + if (this_way->offset_before == this_way->offset_after || + before(this_way->correction_pos, seq)) { + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; + } + spin_unlock_bh(&nf_nat_seqofs_lock); + + DEBUGP("nf_nat_resize_packet: Seq_offset after: "); + DUMP_OFFSET(this_way); +} + +/* Frobs data inside this packet, which is linear. */ +static void mangle_contents(struct sk_buff *skb, + unsigned int dataoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + unsigned char *data; + + BUG_ON(skb_is_nonlinear(skb)); + data = (unsigned char *)skb->nh.iph + dataoff; + + /* move post-replacement */ + memmove(data + match_offset + rep_len, + data + match_offset + match_len, + skb->tail - (data + match_offset + match_len)); + + /* insert data from buffer */ + memcpy(data + match_offset, rep_buffer, rep_len); + + /* update skb info */ + if (rep_len > match_len) { + DEBUGP("nf_nat_mangle_packet: Extending packet by " + "%u from %u bytes\n", rep_len - match_len, + skb->len); + skb_put(skb, rep_len - match_len); + } else { + DEBUGP("nf_nat_mangle_packet: Shrinking packet from " + "%u from %u bytes\n", match_len - rep_len, + skb->len); + __skb_trim(skb, skb->len + rep_len - match_len); + } + + /* fix IP hdr checksum information */ + skb->nh.iph->tot_len = htons(skb->len); + ip_send_check(skb->nh.iph); +} + +/* Unusual, but possible case. */ +static int enlarge_skb(struct sk_buff **pskb, unsigned int extra) +{ + struct sk_buff *nskb; + + if ((*pskb)->len + extra > 65535) + return 0; + + nskb = skb_copy_expand(*pskb, skb_headroom(*pskb), extra, GFP_ATOMIC); + if (!nskb) + return 0; + + /* Transfer socket to new skb. */ + if ((*pskb)->sk) + skb_set_owner_w(nskb, (*pskb)->sk); + kfree_skb(*pskb); + *pskb = nskb; + return 1; +} + +/* Generic function for mangling variable-length address changes inside + * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX + * command in FTP). + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * */ +int +nf_nat_mangle_tcp_packet(struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + struct iphdr *iph; + struct tcphdr *tcph; + int oldlen, datalen; + + if (!skb_make_writable(pskb, (*pskb)->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(*pskb) && + !enlarge_skb(pskb, rep_len - match_len)) + return 0; + + SKB_LINEAR_ASSERT(*pskb); + + iph = (*pskb)->nh.iph; + tcph = (void *)iph + iph->ihl*4; + + oldlen = (*pskb)->len - iph->ihl*4; + mangle_contents(*pskb, iph->ihl*4 + tcph->doff*4, + match_offset, match_len, rep_buffer, rep_len); + + datalen = (*pskb)->len - iph->ihl*4; + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { + tcph->check = 0; + tcph->check = tcp_v4_check(tcph, datalen, + iph->saddr, iph->daddr, + csum_partial((char *)tcph, + datalen, 0)); + } else + nf_proto_csum_replace2(&tcph->check, *pskb, + htons(oldlen), htons(datalen), 1); + + if (rep_len != match_len) { + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + adjust_tcp_sequence(ntohl(tcph->seq), + (int)rep_len - (int)match_len, + ct, ctinfo); + /* Tell TCP window tracking about seq change */ + nf_conntrack_tcp_update(*pskb, (*pskb)->nh.iph->ihl*4, + ct, CTINFO2DIR(ctinfo)); + } + return 1; +} +EXPORT_SYMBOL(nf_nat_mangle_tcp_packet); + +/* Generic function for mangling variable-length address changes inside + * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX + * command in the Amanda protocol) + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * XXX - This function could be merged with nf_nat_mangle_tcp_packet which + * should be fairly easy to do. + */ +int +nf_nat_mangle_udp_packet(struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + struct iphdr *iph; + struct udphdr *udph; + int datalen, oldlen; + + /* UDP helpers might accidentally mangle the wrong packet */ + iph = (*pskb)->nh.iph; + if ((*pskb)->len < iph->ihl*4 + sizeof(*udph) + + match_offset + match_len) + return 0; + + if (!skb_make_writable(pskb, (*pskb)->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(*pskb) && + !enlarge_skb(pskb, rep_len - match_len)) + return 0; + + iph = (*pskb)->nh.iph; + udph = (void *)iph + iph->ihl*4; + + oldlen = (*pskb)->len - iph->ihl*4; + mangle_contents(*pskb, iph->ihl*4 + sizeof(*udph), + match_offset, match_len, rep_buffer, rep_len); + + /* update the length of the UDP packet */ + datalen = (*pskb)->len - iph->ihl*4; + udph->len = htons(datalen); + + /* fix udp checksum if udp checksum was previously calculated */ + if (!udph->check && (*pskb)->ip_summed != CHECKSUM_PARTIAL) + return 1; + + if ((*pskb)->ip_summed != CHECKSUM_PARTIAL) { + udph->check = 0; + udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, IPPROTO_UDP, + csum_partial((char *)udph, + datalen, 0)); + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } else + nf_proto_csum_replace2(&udph->check, *pskb, + htons(oldlen), htons(datalen), 1); + + return 1; +} +EXPORT_SYMBOL(nf_nat_mangle_udp_packet); + +/* Adjust one found SACK option including checksum correction */ +static void +sack_adjust(struct sk_buff *skb, + struct tcphdr *tcph, + unsigned int sackoff, + unsigned int sackend, + struct nf_nat_seq *natseq) +{ + while (sackoff < sackend) { + struct tcp_sack_block_wire *sack; + __be32 new_start_seq, new_end_seq; + + sack = (void *)skb->data + sackoff; + if (after(ntohl(sack->start_seq) - natseq->offset_before, + natseq->correction_pos)) + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_after); + else + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_before); + + if (after(ntohl(sack->end_seq) - natseq->offset_before, + natseq->correction_pos)) + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_after); + else + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_before); + + DEBUGP("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", + ntohl(sack->start_seq), new_start_seq, + ntohl(sack->end_seq), new_end_seq); + + nf_proto_csum_replace4(&tcph->check, skb, + sack->start_seq, new_start_seq, 0); + nf_proto_csum_replace4(&tcph->check, skb, + sack->end_seq, new_end_seq, 0); + sack->start_seq = new_start_seq; + sack->end_seq = new_end_seq; + sackoff += sizeof(*sack); + } +} + +/* TCP SACK sequence number adjustment */ +static inline unsigned int +nf_nat_sack_adjust(struct sk_buff **pskb, + struct tcphdr *tcph, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + unsigned int dir, optoff, optend; + struct nf_conn_nat *nat = nfct_nat(ct); + + optoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct tcphdr); + optend = (*pskb)->nh.iph->ihl*4 + tcph->doff*4; + + if (!skb_make_writable(pskb, optend)) + return 0; + + dir = CTINFO2DIR(ctinfo); + + while (optoff < optend) { + /* Usually: option, length. */ + unsigned char *op = (*pskb)->data + optoff; + + switch (op[0]) { + case TCPOPT_EOL: + return 1; + case TCPOPT_NOP: + optoff++; + continue; + default: + /* no partial options */ + if (optoff + 1 == optend || + optoff + op[1] > optend || + op[1] < 2) + return 0; + if (op[0] == TCPOPT_SACK && + op[1] >= 2+TCPOLEN_SACK_PERBLOCK && + ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) + sack_adjust(*pskb, tcph, optoff+2, + optoff+op[1], + &nat->info.seq[!dir]); + optoff += op[1]; + } + } + return 1; +} + +/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ +int +nf_nat_seq_adjust(struct sk_buff **pskb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + struct tcphdr *tcph; + int dir; + __be32 newseq, newack; + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way, *other_way; + + dir = CTINFO2DIR(ctinfo); + + this_way = &nat->info.seq[dir]; + other_way = &nat->info.seq[!dir]; + + if (!skb_make_writable(pskb, (*pskb)->nh.iph->ihl*4+sizeof(*tcph))) + return 0; + + tcph = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; + if (after(ntohl(tcph->seq), this_way->correction_pos)) + newseq = htonl(ntohl(tcph->seq) + this_way->offset_after); + else + newseq = htonl(ntohl(tcph->seq) + this_way->offset_before); + + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, + other_way->correction_pos)) + newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after); + else + newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before); + + nf_proto_csum_replace4(&tcph->check, *pskb, tcph->seq, newseq, 0); + nf_proto_csum_replace4(&tcph->check, *pskb, tcph->ack_seq, newack, 0); + + DEBUGP("Adjusting sequence number from %u->%u, ack from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), + ntohl(newack)); + + tcph->seq = newseq; + tcph->ack_seq = newack; + + if (!nf_nat_sack_adjust(pskb, tcph, ct, ctinfo)) + return 0; + + nf_conntrack_tcp_update(*pskb, (*pskb)->nh.iph->ihl*4, ct, dir); + + return 1; +} +EXPORT_SYMBOL(nf_nat_seq_adjust); + +/* Setup NAT on this expected conntrack so it follows master. */ +/* If we fail to get a free NAT slot, we'll get dropped on confirm */ +void nf_nat_follow_master(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(ct->status & IPS_NAT_DONE_MASK); + + /* Change src to where master sends to */ + range.flags = IP_NAT_RANGE_MAP_IPS; + range.min_ip = range.max_ip + = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; + /* hook doesn't matter, but it has to do source manip */ + nf_nat_setup_info(ct, &range, NF_IP_POST_ROUTING); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.min = range.max = exp->saved_proto; + range.min_ip = range.max_ip + = ct->master->tuplehash[!exp->dir].tuple.src.u3.ip; + /* hook doesn't matter, but it has to do destination manip */ + nf_nat_setup_info(ct, &range, NF_IP_PRE_ROUTING); +} +EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c new file mode 100644 index 00000000000..dcfd772972d --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -0,0 +1,86 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static int +icmp_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) && + ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id); +} + +static int +icmp_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + static u_int16_t id; + unsigned int range_size; + unsigned int i; + + range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1; + /* If no range specified... */ + if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) + range_size = 0xFFFF; + + for (i = 0; i < range_size; i++, id++) { + tuple->src.u.icmp.id = htons(ntohs(range->min.icmp.id) + + (id % range_size)); + if (!nf_nat_used_tuple(tuple, ct)) + return 1; + } + return 0; +} + +static int +icmp_manip_pkt(struct sk_buff **pskb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph = (struct iphdr *)((*pskb)->data + iphdroff); + struct icmphdr *hdr; + unsigned int hdroff = iphdroff + iph->ihl*4; + + if (!skb_make_writable(pskb, hdroff + sizeof(*hdr))) + return 0; + + hdr = (struct icmphdr *)((*pskb)->data + hdroff); + nf_proto_csum_replace2(&hdr->checksum, *pskb, + hdr->un.echo.id, tuple->src.u.icmp.id, 0); + hdr->un.echo.id = tuple->src.u.icmp.id; + return 1; +} + +struct nf_nat_protocol nf_nat_protocol_icmp = { + .name = "ICMP", + .protonum = IPPROTO_ICMP, + .me = THIS_MODULE, + .manip_pkt = icmp_manip_pkt, + .in_range = icmp_in_range, + .unique_tuple = icmp_unique_tuple, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = nf_nat_port_range_to_nfattr, + .nfattr_to_range = nf_nat_port_nfattr_to_range, +#endif +}; diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c new file mode 100644 index 00000000000..7e26a7e9bee --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_proto_tcp.c @@ -0,0 +1,148 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +static int +tcp_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + __be16 port; + + if (maniptype == IP_NAT_MANIP_SRC) + port = tuple->src.u.tcp.port; + else + port = tuple->dst.u.tcp.port; + + return ntohs(port) >= ntohs(min->tcp.port) && + ntohs(port) <= ntohs(max->tcp.port); +} + +static int +tcp_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + static u_int16_t port; + __be16 *portptr; + unsigned int range_size, min, i; + + if (maniptype == IP_NAT_MANIP_SRC) + portptr = &tuple->src.u.tcp.port; + else + portptr = &tuple->dst.u.tcp.port; + + /* If no range specified... */ + if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) { + /* If it's dst rewrite, can't change port */ + if (maniptype == IP_NAT_MANIP_DST) + return 0; + + /* Map privileged onto privileged. */ + if (ntohs(*portptr) < 1024) { + /* Loose convention: >> 512 is credential passing */ + if (ntohs(*portptr)<512) { + min = 1; + range_size = 511 - min + 1; + } else { + min = 600; + range_size = 1023 - min + 1; + } + } else { + min = 1024; + range_size = 65535 - 1024 + 1; + } + } else { + min = ntohs(range->min.tcp.port); + range_size = ntohs(range->max.tcp.port) - min + 1; + } + + for (i = 0; i < range_size; i++, port++) { + *portptr = htons(min + port % range_size); + if (!nf_nat_used_tuple(tuple, ct)) + return 1; + } + return 0; +} + +static int +tcp_manip_pkt(struct sk_buff **pskb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph = (struct iphdr *)((*pskb)->data + iphdroff); + struct tcphdr *hdr; + unsigned int hdroff = iphdroff + iph->ihl*4; + __be32 oldip, newip; + __be16 *portptr, newport, oldport; + int hdrsize = 8; /* TCP connection tracking guarantees this much */ + + /* this could be a inner header returned in icmp packet; in such + cases we cannot update the checksum field since it is outside of + the 8 bytes of transport layer headers we are guaranteed */ + if ((*pskb)->len >= hdroff + sizeof(struct tcphdr)) + hdrsize = sizeof(struct tcphdr); + + if (!skb_make_writable(pskb, hdroff + hdrsize)) + return 0; + + iph = (struct iphdr *)((*pskb)->data + iphdroff); + hdr = (struct tcphdr *)((*pskb)->data + hdroff); + + if (maniptype == IP_NAT_MANIP_SRC) { + /* Get rid of src ip and src pt */ + oldip = iph->saddr; + newip = tuple->src.u3.ip; + newport = tuple->src.u.tcp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst ip and dst pt */ + oldip = iph->daddr; + newip = tuple->dst.u3.ip; + newport = tuple->dst.u.tcp.port; + portptr = &hdr->dest; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return 1; + + nf_proto_csum_replace4(&hdr->check, *pskb, oldip, newip, 1); + nf_proto_csum_replace2(&hdr->check, *pskb, oldport, newport, 0); + return 1; +} + +struct nf_nat_protocol nf_nat_protocol_tcp = { + .name = "TCP", + .protonum = IPPROTO_TCP, + .me = THIS_MODULE, + .manip_pkt = tcp_manip_pkt, + .in_range = tcp_in_range, + .unique_tuple = tcp_unique_tuple, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = nf_nat_port_range_to_nfattr, + .nfattr_to_range = nf_nat_port_nfattr_to_range, +#endif +}; diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c new file mode 100644 index 00000000000..ab0ce4c8699 --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_proto_udp.c @@ -0,0 +1,138 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static int +udp_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + __be16 port; + + if (maniptype == IP_NAT_MANIP_SRC) + port = tuple->src.u.udp.port; + else + port = tuple->dst.u.udp.port; + + return ntohs(port) >= ntohs(min->udp.port) && + ntohs(port) <= ntohs(max->udp.port); +} + +static int +udp_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + static u_int16_t port; + __be16 *portptr; + unsigned int range_size, min, i; + + if (maniptype == IP_NAT_MANIP_SRC) + portptr = &tuple->src.u.udp.port; + else + portptr = &tuple->dst.u.udp.port; + + /* If no range specified... */ + if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) { + /* If it's dst rewrite, can't change port */ + if (maniptype == IP_NAT_MANIP_DST) + return 0; + + if (ntohs(*portptr) < 1024) { + /* Loose convention: >> 512 is credential passing */ + if (ntohs(*portptr)<512) { + min = 1; + range_size = 511 - min + 1; + } else { + min = 600; + range_size = 1023 - min + 1; + } + } else { + min = 1024; + range_size = 65535 - 1024 + 1; + } + } else { + min = ntohs(range->min.udp.port); + range_size = ntohs(range->max.udp.port) - min + 1; + } + + for (i = 0; i < range_size; i++, port++) { + *portptr = htons(min + port % range_size); + if (!nf_nat_used_tuple(tuple, ct)) + return 1; + } + return 0; +} + +static int +udp_manip_pkt(struct sk_buff **pskb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph = (struct iphdr *)((*pskb)->data + iphdroff); + struct udphdr *hdr; + unsigned int hdroff = iphdroff + iph->ihl*4; + __be32 oldip, newip; + __be16 *portptr, newport; + + if (!skb_make_writable(pskb, hdroff + sizeof(*hdr))) + return 0; + + iph = (struct iphdr *)((*pskb)->data + iphdroff); + hdr = (struct udphdr *)((*pskb)->data + hdroff); + + if (maniptype == IP_NAT_MANIP_SRC) { + /* Get rid of src ip and src pt */ + oldip = iph->saddr; + newip = tuple->src.u3.ip; + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst ip and dst pt */ + oldip = iph->daddr; + newip = tuple->dst.u3.ip; + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + if (hdr->check || (*pskb)->ip_summed == CHECKSUM_PARTIAL) { + nf_proto_csum_replace4(&hdr->check, *pskb, oldip, newip, 1); + nf_proto_csum_replace2(&hdr->check, *pskb, *portptr, newport, + 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + } + *portptr = newport; + return 1; +} + +struct nf_nat_protocol nf_nat_protocol_udp = { + .name = "UDP", + .protonum = IPPROTO_UDP, + .me = THIS_MODULE, + .manip_pkt = udp_manip_pkt, + .in_range = udp_in_range, + .unique_tuple = udp_unique_tuple, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = nf_nat_port_range_to_nfattr, + .nfattr_to_range = nf_nat_port_nfattr_to_range, +#endif +}; diff --git a/net/ipv4/netfilter/nf_nat_proto_unknown.c b/net/ipv4/netfilter/nf_nat_proto_unknown.c new file mode 100644 index 00000000000..f50d0203f9c --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_proto_unknown.c @@ -0,0 +1,54 @@ +/* The "unknown" protocol. This is what is used for protocols we + * don't understand. It's returned by ip_ct_find_proto(). + */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include +#include +#include +#include + +static int unknown_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type manip_type, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return 1; +} + +static int unknown_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + /* Sorry: we can't help you; if it's not unique, we can't frob + anything. */ + return 0; +} + +static int +unknown_manip_pkt(struct sk_buff **pskb, + unsigned int iphdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + return 1; +} + +struct nf_nat_protocol nf_nat_unknown_protocol = { + .name = "unknown", + /* .me isn't set: getting a ref to this cannot fail. */ + .manip_pkt = unknown_manip_pkt, + .in_range = unknown_in_range, + .unique_tuple = unknown_unique_tuple, +}; diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c new file mode 100644 index 00000000000..b868ee0195d --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -0,0 +1,343 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Everything about the rules for NAT. */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +#define NAT_VALID_HOOKS ((1<range[0], hooknum); +} + +/* Before 2.6.11 we did implicit source NAT if required. Warn about change. */ +static void warn_if_extra_mangle(__be32 dstip, __be32 srcip) +{ + static int warned = 0; + struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dstip } } }; + struct rtable *rt; + + if (ip_route_output_key(&rt, &fl) != 0) + return; + + if (rt->rt_src != srcip && !warned) { + printk("NAT: no longer support implicit source local NAT\n"); + printk("NAT: packet src %u.%u.%u.%u -> dst %u.%u.%u.%u\n", + NIPQUAD(srcip), NIPQUAD(dstip)); + warned = 1; + } + ip_rt_put(rt); +} + +static unsigned int ipt_dnat_target(struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + unsigned int hooknum, + const struct xt_target *target, + const void *targinfo) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + const struct nf_nat_multi_range_compat *mr = targinfo; + + NF_CT_ASSERT(hooknum == NF_IP_PRE_ROUTING || + hooknum == NF_IP_LOCAL_OUT); + + ct = nf_ct_get(*pskb, &ctinfo); + + /* Connection must be valid and new. */ + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + if (hooknum == NF_IP_LOCAL_OUT && + mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) + warn_if_extra_mangle((*pskb)->nh.iph->daddr, + mr->range[0].min_ip); + + return nf_nat_setup_info(ct, &mr->range[0], hooknum); +} + +static int ipt_snat_checkentry(const char *tablename, + const void *entry, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) +{ + struct nf_nat_multi_range_compat *mr = targinfo; + + /* Must be a valid range */ + if (mr->rangesize != 1) { + printk("SNAT: multiple ranges no longer supported\n"); + return 0; + } + return 1; +} + +static int ipt_dnat_checkentry(const char *tablename, + const void *entry, + const struct xt_target *target, + void *targinfo, + unsigned int hook_mask) +{ + struct nf_nat_multi_range_compat *mr = targinfo; + + /* Must be a valid range */ + if (mr->rangesize != 1) { + printk("DNAT: multiple ranges no longer supported\n"); + return 0; + } + return 1; +} + +inline unsigned int +alloc_null_binding(struct nf_conn *ct, + struct nf_nat_info *info, + unsigned int hooknum) +{ + /* Force range to this IP; let proto decide mapping for + per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). + Use reply in case it's already been mangled (eg local packet). + */ + __be32 ip + = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC + ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip + : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); + struct nf_nat_range range + = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } }; + + DEBUGP("Allocating NULL binding for %p (%u.%u.%u.%u)\n", + ct, NIPQUAD(ip)); + return nf_nat_setup_info(ct, &range, hooknum); +} + +unsigned int +alloc_null_binding_confirmed(struct nf_conn *ct, + struct nf_nat_info *info, + unsigned int hooknum) +{ + __be32 ip + = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC + ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip + : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); + u_int16_t all + = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC + ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all + : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all); + struct nf_nat_range range + = { IP_NAT_RANGE_MAP_IPS, ip, ip, { all }, { all } }; + + DEBUGP("Allocating NULL binding for confirmed %p (%u.%u.%u.%u)\n", + ct, NIPQUAD(ip)); + return nf_nat_setup_info(ct, &range, hooknum); +} + +int nf_nat_rule_find(struct sk_buff **pskb, + unsigned int hooknum, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct, + struct nf_nat_info *info) +{ + int ret; + + ret = ipt_do_table(pskb, hooknum, in, out, &nat_table); + + if (ret == NF_ACCEPT) { + if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) + /* NUL mapping */ + ret = alloc_null_binding(ct, info, hooknum); + } + return ret; +} + +static struct ipt_target ipt_snat_reg = { + .name = "SNAT", + .target = ipt_snat_target, + .targetsize = sizeof(struct nf_nat_multi_range_compat), + .table = "nat", + .hooks = 1 << NF_IP_POST_ROUTING, + .checkentry = ipt_snat_checkentry, + .family = AF_INET, +}; + +static struct xt_target ipt_dnat_reg = { + .name = "DNAT", + .target = ipt_dnat_target, + .targetsize = sizeof(struct nf_nat_multi_range_compat), + .table = "nat", + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT), + .checkentry = ipt_dnat_checkentry, + .family = AF_INET, +}; + +int __init nf_nat_rule_init(void) +{ + int ret; + + ret = ipt_register_table(&nat_table, &nat_initial_table.repl); + if (ret != 0) + return ret; + ret = xt_register_target(&ipt_snat_reg); + if (ret != 0) + goto unregister_table; + + ret = xt_register_target(&ipt_dnat_reg); + if (ret != 0) + goto unregister_snat; + + return ret; + + unregister_snat: + xt_unregister_target(&ipt_snat_reg); + unregister_table: + ipt_unregister_table(&nat_table); + + return ret; +} + +void nf_nat_rule_cleanup(void) +{ + xt_unregister_target(&ipt_dnat_reg); + xt_unregister_target(&ipt_snat_reg); + ipt_unregister_table(&nat_table); +} diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c new file mode 100644 index 00000000000..730a7a44c88 --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -0,0 +1,406 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + +#define HOOKNAME(hooknum) ((hooknum) == NF_IP_POST_ROUTING ? "POST_ROUTING" \ + : ((hooknum) == NF_IP_PRE_ROUTING ? "PRE_ROUTING" \ + : ((hooknum) == NF_IP_LOCAL_OUT ? "LOCAL_OUT" \ + : ((hooknum) == NF_IP_LOCAL_IN ? "LOCAL_IN" \ + : "*ERROR*"))) + +#ifdef CONFIG_XFRM +static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + struct nf_conn *ct; + struct nf_conntrack_tuple *t; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + unsigned long statusbit; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return; + dir = CTINFO2DIR(ctinfo); + t = &ct->tuplehash[dir].tuple; + + if (dir == IP_CT_DIR_ORIGINAL) + statusbit = IPS_DST_NAT; + else + statusbit = IPS_SRC_NAT; + + if (ct->status & statusbit) { + fl->fl4_dst = t->dst.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP) + fl->fl_ip_dport = t->dst.u.tcp.port; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl->fl4_src = t->src.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP) + fl->fl_ip_sport = t->src.u.tcp.port; + } +} +#endif + +static unsigned int +nf_nat_fn(unsigned int hooknum, + struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + struct nf_nat_info *info; + /* maniptype == SRC for postrouting. */ + enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + + /* We never see fragments: conntrack defrags on pre-routing + and local-out, and nf_nat_out protects post-routing. */ + NF_CT_ASSERT(!((*pskb)->nh.iph->frag_off + & htons(IP_MF|IP_OFFSET))); + + ct = nf_ct_get(*pskb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + have dropped it. Hence it's the user's responsibilty to + packet filter it out, or implement conntrack/NAT for that + protocol. 8) --RR */ + if (!ct) { + /* Exception: ICMP redirect to new connection (not in + hash table yet). We must not let this through, in + case we're doing NAT to the same network. */ + if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) { + struct icmphdr _hdr, *hp; + + hp = skb_header_pointer(*pskb, + (*pskb)->nh.iph->ihl*4, + sizeof(_hdr), &_hdr); + if (hp != NULL && + hp->type == ICMP_REDIRECT) + return NF_DROP; + } + return NF_ACCEPT; + } + + /* Don't try to NAT if this packet is not conntracked */ + if (ct == &nf_conntrack_untracked) + return NF_ACCEPT; + + nat = nfct_nat(ct); + if (!nat) + return NF_DROP; + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED+IP_CT_IS_REPLY: + if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(ct, ctinfo, + hooknum, pskb)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + case IP_CT_NEW: + info = &nat->info; + + /* Seen it before? This can happen for loopback, retrans, + or local packets.. */ + if (!nf_nat_initialized(ct, maniptype)) { + unsigned int ret; + + if (unlikely(nf_ct_is_confirmed(ct))) + /* NAT module was loaded late */ + ret = alloc_null_binding_confirmed(ct, info, + hooknum); + else if (hooknum == NF_IP_LOCAL_IN) + /* LOCAL_IN hook doesn't have a chain! */ + ret = alloc_null_binding(ct, info, hooknum); + else + ret = nf_nat_rule_find(pskb, hooknum, in, out, + ct, info); + + if (ret != NF_ACCEPT) { + return ret; + } + } else + DEBUGP("Already setup manip %s for ct %p\n", + maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST", + ct); + break; + + default: + /* ESTABLISHED */ + NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || + ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY)); + info = &nat->info; + } + + NF_CT_ASSERT(info); + return nf_nat_packet(ct, ctinfo, hooknum, pskb); +} + +static unsigned int +nf_nat_in(unsigned int hooknum, + struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + __be32 daddr = (*pskb)->nh.iph->daddr; + + ret = nf_nat_fn(hooknum, pskb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + daddr != (*pskb)->nh.iph->daddr) { + dst_release((*pskb)->dst); + (*pskb)->dst = NULL; + } + return ret; +} + +static unsigned int +nf_nat_out(unsigned int hooknum, + struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ +#ifdef CONFIG_XFRM + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; +#endif + unsigned int ret; + + /* root is playing with raw sockets. */ + if ((*pskb)->len < sizeof(struct iphdr) || + (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) + return NF_ACCEPT; + + ret = nf_nat_fn(hooknum, pskb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(*pskb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip + || ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all + ) + return ip_xfrm_me_harder(pskb) == 0 ? ret : NF_DROP; + } +#endif + return ret; +} + +static unsigned int +nf_nat_local_fn(unsigned int hooknum, + struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + + /* root is playing with raw sockets. */ + if ((*pskb)->len < sizeof(struct iphdr) || + (*pskb)->nh.iph->ihl * 4 < sizeof(struct iphdr)) + return NF_ACCEPT; + + ret = nf_nat_fn(hooknum, pskb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(*pskb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.dst.u3.ip != + ct->tuplehash[!dir].tuple.src.u3.ip +#ifdef CONFIG_XFRM + || ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all +#endif + ) + if (ip_route_me_harder(pskb, RTN_UNSPEC)) + ret = NF_DROP; + } + return ret; +} + +static unsigned int +nf_nat_adjust(unsigned int hooknum, + struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(*pskb, &ctinfo); + if (ct && test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { + DEBUGP("nf_nat_standalone: adjusting sequence number\n"); + if (!nf_nat_seq_adjust(pskb, ct, ctinfo)) + return NF_DROP; + } + return NF_ACCEPT; +} + +/* We must be after connection tracking and before packet filtering. */ + +static struct nf_hook_ops nf_nat_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_in, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_out, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* After conntrack, adjust sequence number */ + { + .hook = nf_nat_adjust, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SEQ_ADJUST, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_local_fn, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_fn, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* After conntrack, adjust sequence number */ + { + .hook = nf_nat_adjust, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SEQ_ADJUST, + }, +}; + +static int __init nf_nat_standalone_init(void) +{ + int size, ret = 0; + + need_conntrack(); + + size = ALIGN(sizeof(struct nf_conn), __alignof__(struct nf_conn_nat)) + + sizeof(struct nf_conn_nat); + ret = nf_conntrack_register_cache(NF_CT_F_NAT, "nf_nat:base", size); + if (ret < 0) { + printk(KERN_ERR "nf_nat_init: Unable to create slab cache\n"); + return ret; + } + + size = ALIGN(size, __alignof__(struct nf_conn_help)) + + sizeof(struct nf_conn_help); + ret = nf_conntrack_register_cache(NF_CT_F_NAT|NF_CT_F_HELP, + "nf_nat:help", size); + if (ret < 0) { + printk(KERN_ERR "nf_nat_init: Unable to create slab cache\n"); + goto cleanup_register_cache; + } +#ifdef CONFIG_XFRM + BUG_ON(ip_nat_decode_session != NULL); + ip_nat_decode_session = nat_decode_session; +#endif + ret = nf_nat_rule_init(); + if (ret < 0) { + printk("nf_nat_init: can't setup rules.\n"); + goto cleanup_decode_session; + } + ret = nf_register_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); + if (ret < 0) { + printk("nf_nat_init: can't register hooks.\n"); + goto cleanup_rule_init; + } + nf_nat_module_is_loaded = 1; + return ret; + + cleanup_rule_init: + nf_nat_rule_cleanup(); + cleanup_decode_session: +#ifdef CONFIG_XFRM + ip_nat_decode_session = NULL; + synchronize_net(); +#endif + nf_conntrack_unregister_cache(NF_CT_F_NAT|NF_CT_F_HELP); + cleanup_register_cache: + nf_conntrack_unregister_cache(NF_CT_F_NAT); + return ret; +} + +static void __exit nf_nat_standalone_fini(void) +{ + nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); + nf_nat_rule_cleanup(); + nf_nat_module_is_loaded = 0; +#ifdef CONFIG_XFRM + ip_nat_decode_session = NULL; + synchronize_net(); +#endif + /* Conntrack caches are unregistered in nf_conntrack_cleanup */ +} + +module_init(nf_nat_standalone_init); +module_exit(nf_nat_standalone_fini); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat"); -- cgit v1.2.3-18-g5258