diff options
author | Patrick McHardy <kaber@trash.net> | 2012-08-26 19:14:06 +0200 |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2012-08-30 03:00:14 +0200 |
commit | c7232c9979cba684c50b64c513c4a83c9aa70563 (patch) | |
tree | dbe0fdac62191d85935f5a3dfe815c1b1add60f9 /net/netfilter | |
parent | 051966c0c644a1c96092d4206e00704ade813c9a (diff) | |
download | op-kernel-dev-c7232c9979cba684c50b64c513c4a83c9aa70563.zip op-kernel-dev-c7232c9979cba684c50b64c513c4a83c9aa70563.tar.gz |
netfilter: add protocol independent NAT core
Convert the IPv4 NAT implementation to a protocol independent core and
address family specific modules.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/Kconfig | 24 | ||||
-rw-r--r-- | net/netfilter/Makefile | 11 | ||||
-rw-r--r-- | net/netfilter/core.c | 5 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 6 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_netlink.c | 35 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_tcp.c | 8 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_sip.c | 6 | ||||
-rw-r--r-- | net/netfilter/nf_nat_core.c | 854 | ||||
-rw-r--r-- | net/netfilter/nf_nat_helper.c | 435 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_common.c | 112 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_dccp.c | 116 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_sctp.c | 103 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_tcp.c | 85 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_udp.c | 76 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_udplite.c | 106 | ||||
-rw-r--r-- | net/netfilter/nf_nat_proto_unknown.c | 54 | ||||
-rw-r--r-- | net/netfilter/xt_nat.c | 167 |
17 files changed, 2190 insertions, 13 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c19b214..91addda 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -356,6 +356,30 @@ config NETFILTER_NETLINK_QUEUE_CT If this option is enabled, NFQUEUE can include Connection Tracking information together with the packet is the enqueued via NFNETLINK. +config NF_NAT + tristate + +config NF_NAT_NEEDED + bool + depends on NF_NAT + default y + +config NF_NAT_PROTO_DCCP + tristate + depends on NF_NAT && NF_CT_PROTO_DCCP + default NF_NAT && NF_CT_PROTO_DCCP + +config NF_NAT_PROTO_UDPLITE + tristate + depends on NF_NAT && NF_CT_PROTO_UDPLITE + default NF_NAT && NF_CT_PROTO_UDPLITE + +config NF_NAT_PROTO_SCTP + tristate + default NF_NAT && NF_CT_PROTO_SCTP + depends on NF_NAT && NF_CT_PROTO_SCTP + select LIBCRC32C + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1c5160f..09c9451 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -43,6 +43,17 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o +nf_nat-y := nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \ + nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o + +obj-$(CONFIG_NF_NAT) += nf_nat.o +obj-$(CONFIG_NF_NAT) += xt_nat.o + +# NAT protocols (nf_nat) +obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o +obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o +obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o + # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8f4b0b2..e61b3ac 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -275,6 +275,11 @@ EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); #endif /* CONFIG_NF_CONNTRACK */ +#ifdef CONFIG_NF_NAT_NEEDED +void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); +EXPORT_SYMBOL(nf_nat_decode_session_hook); +#endif + #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_net_netfilter; EXPORT_SYMBOL(proc_net_netfilter); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index cf48755..f83e79d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,6 +55,12 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); +int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff); +EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); + DEFINE_SPINLOCK(nf_conntrack_lock); EXPORT_SYMBOL_GPL(nf_conntrack_lock); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index da4fc37..966f513 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,7 @@ #include <net/netfilter/nf_conntrack_timestamp.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> -#include <net/netfilter/nf_nat_protocol.h> +#include <net/netfilter/nf_nat_l4proto.h> #include <net/netfilter/nf_nat_helper.h> #endif @@ -1096,13 +1096,14 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, const struct nlattr *attr) { typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup; + int err; parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook); if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(); - if (request_module("nf-nat-ipv4") < 0) { + if (request_module("nf-nat") < 0) { nfnl_lock(); rcu_read_lock(); return -EOPNOTSUPP; @@ -1115,7 +1116,26 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, return -EOPNOTSUPP; } - return parse_nat_setup(ct, manip, attr); + err = parse_nat_setup(ct, manip, attr); + if (err == -EAGAIN) { +#ifdef CONFIG_MODULES + rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); + nfnl_unlock(); + if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { + nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); + rcu_read_lock(); + return -EOPNOTSUPP; + } + nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); + rcu_read_lock(); +#else + err = -EOPNOTSUPP; +#endif + } + return err; } #endif @@ -1979,6 +1999,8 @@ nla_put_failure: return -1; } +static const union nf_inet_addr any_addr; + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2005,7 +2027,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; #ifdef CONFIG_NF_NAT_NEEDED - if (exp->saved_ip || exp->saved_proto.all) { + if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || + exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -2014,7 +2037,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); - nat_tuple.src.u3.ip = exp->saved_ip; + nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; @@ -2410,7 +2433,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, if (err < 0) return err; - exp->saved_ip = nat_tuple.src.u3.ip; + exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a5ac11e..9c2cc71 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -505,10 +505,10 @@ static inline s16 nat_offset(const struct nf_conn *ct, return get_offset != NULL ? get_offset(ct, dir, seq) : 0; } -#define NAT_OFFSET(pf, ct, dir, seq) \ - (pf == NFPROTO_IPV4 ? nat_offset(ct, dir, seq) : 0) +#define NAT_OFFSET(ct, dir, seq) \ + (nat_offset(ct, dir, seq)) #else -#define NAT_OFFSET(pf, ct, dir, seq) 0 +#define NAT_OFFSET(ct, dir, seq) 0 #endif static bool tcp_in_window(const struct nf_conn *ct, @@ -541,7 +541,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ - receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1); + receiver_offset = NAT_OFFSET(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 590f0ab..d517490 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -946,11 +946,11 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, break; #ifdef CONFIG_NF_NAT_NEEDED if (exp->tuple.src.l3num == AF_INET && !direct_rtp && - (exp->saved_ip != exp->tuple.dst.u3.ip || + (exp->saved_addr.ip != exp->tuple.dst.u3.ip || exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) && ct->status & IPS_NAT_MASK) { - daddr->ip = exp->saved_ip; - tuple.dst.u3.ip = exp->saved_ip; + daddr->ip = exp->saved_addr.ip; + tuple.dst.u3.ip = exp->saved_addr.ip; tuple.dst.u.udp.port = exp->saved_proto.udp.port; direct_rtp = 1; } else diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c new file mode 100644 index 0000000..c577b75 --- /dev/null +++ b/net/netfilter/nf_nat_core.c @@ -0,0 +1,854 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2011 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/module.h> +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/gfp.h> +#include <net/xfrm.h> +#include <linux/jhash.h> +#include <linux/rtnetlink.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <linux/netfilter/nf_nat.h> + +static DEFINE_SPINLOCK(nf_nat_lock); + +static DEFINE_MUTEX(nf_nat_proto_mutex); +static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] + __read_mostly; +static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] + __read_mostly; + + +inline const struct nf_nat_l3proto * +__nf_nat_l3proto_find(u8 family) +{ + return rcu_dereference(nf_nat_l3protos[family]); +} + +inline const struct nf_nat_l4proto * +__nf_nat_l4proto_find(u8 family, u8 protonum) +{ + return rcu_dereference(nf_nat_l4protos[family][protonum]); +} +EXPORT_SYMBOL_GPL(__nf_nat_l4proto_find); + +#ifdef CONFIG_XFRM +static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + unsigned long statusbit; + u8 family; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return; + + family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(family); + if (l3proto == NULL) + goto out; + + dir = CTINFO2DIR(ctinfo); + if (dir == IP_CT_DIR_ORIGINAL) + statusbit = IPS_DST_NAT; + else + statusbit = IPS_SRC_NAT; + + l3proto->decode_session(skb, ct, dir, statusbit, fl); +out: + rcu_read_unlock(); +} + +int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) +{ + struct flowi fl; + unsigned int hh_len; + struct dst_entry *dst; + + if (xfrm_decode_session(skb, &fl, family) < 0) + return -1; + + dst = skb_dst(skb); + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + dst_hold(dst); + + dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); + if (IS_ERR(dst)) + return -1; + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + return -1; + return 0; +} +EXPORT_SYMBOL(nf_xfrm_me_harder); +#endif /* CONFIG_XFRM */ + +/* We keep an extra hash for each conntrack, for fast searching. */ +static inline unsigned int +hash_by_src(const struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) +{ + unsigned int hash; + + /* Original src, to ensure we map it consistently if poss. */ + hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), + tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd); + return ((u64)hash * net->ct.nat_htable_size) >> 32; +} + +/* 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_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range) +{ + /* 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 & NF_NAT_RANGE_MAP_IPS && + !l3proto->in_range(tuple, range)) + return 0; + + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) || + l4proto->in_range(tuple, NF_NAT_MANIP_SRC, + &range->min_proto, &range->max_proto)) + 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 && + nf_inet_addr_cmp(&t->src.u3, &tuple->src.u3) && + t->src.u.all == tuple->src.u.all); +} + +/* Only called for SRC manip */ +static int +find_appropriate_src(struct net *net, u16 zone, + const struct nf_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *result, + const struct nf_nat_range *range) +{ + unsigned int h = hash_by_src(net, zone, tuple); + const struct nf_conn_nat *nat; + const struct nf_conn *ct; + const struct hlist_node *n; + + hlist_for_each_entry_rcu(nat, n, &net->ct.nat_bysource[h], bysource) { + ct = nat->ct; + if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { + /* 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(l3proto, l4proto, result, range)) { + rcu_read_unlock(); + return 1; + } + } + } + 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(u16 zone, struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + const struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + union nf_inet_addr *var_ipp; + unsigned int i, max; + /* Host order */ + u32 minip, maxip, j, dist; + bool full_range; + + /* No IP mapping? Do nothing. */ + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) + return; + + if (maniptype == NF_NAT_MANIP_SRC) + var_ipp = &tuple->src.u3; + else + var_ipp = &tuple->dst.u3; + + /* Fast path: only one choice. */ + if (nf_inet_addr_cmp(&range->min_addr, &range->max_addr)) { + *var_ipp = range->min_addr; + return; + } + + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + max = sizeof(var_ipp->ip) / sizeof(u32) - 1; + else + max = sizeof(var_ipp->ip6) / sizeof(u32) - 1; + + /* 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. + */ + j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3), + range->flags & NF_NAT_RANGE_PERSISTENT ? + 0 : (__force u32)tuple->dst.u3.all[max] ^ zone); + + full_range = false; + for (i = 0; i <= max; i++) { + /* If first bytes of the address are at the maximum, use the + * distance. Otherwise use the full range. + */ + if (!full_range) { + minip = ntohl((__force __be32)range->min_addr.all[i]); + maxip = ntohl((__force __be32)range->max_addr.all[i]); + dist = maxip - minip + 1; + } else { + minip = 0; + dist = ~0; + } + + var_ipp->all[i] = (__force __u32) + htonl(minip + (((u64)j * dist) >> 32)); + if (var_ipp->all[i] != range->max_addr.all[i]) + full_range = true; + + if (!(range->flags & NF_NAT_RANGE_PERSISTENT)) + j ^= (__force u32)tuple->dst.u3.all[i]; + } +} + +/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, + * we change the source to map into the range. For NF_INET_PRE_ROUTING + * and NF_INET_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) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + struct net *net = nf_ct_net(ct); + u16 zone = nf_ct_zone(ct); + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num); + l4proto = __nf_nat_l4proto_find(orig_tuple->src.l3num, + orig_tuple->dst.protonum); + + /* 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 == NF_NAT_MANIP_SRC && + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + /* try the original tuple first */ + if (in_range(l3proto, l4proto, orig_tuple, range)) { + if (!nf_nat_used_tuple(orig_tuple, ct)) { + *tuple = *orig_tuple; + goto out; + } + } else if (find_appropriate_src(net, zone, l3proto, l4proto, + orig_tuple, tuple, range)) { + pr_debug("get_unique_tuple: Found current src map\n"); + if (!nf_nat_used_tuple(tuple, ct)) + goto out; + } + } + + /* 2) Select the least-used IP/proto combination in the given range */ + *tuple = *orig_tuple; + find_best_ips_proto(zone, tuple, range, ct, maniptype); + + /* 3) The per-protocol part of the manip is made to map into + * the range to make a unique tuple. + */ + + /* Only bother mapping if it's not already in range and unique */ + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { + if (l4proto->in_range(tuple, maniptype, + &range->min_proto, + &range->max_proto) && + (range->min_proto.all == range->max_proto.all || + !nf_nat_used_tuple(tuple, ct))) + goto out; + } else if (!nf_nat_used_tuple(tuple, ct)) { + goto out; + } + } + + /* Last change: get protocol to try to obtain unique tuple. */ + l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct); +out: + rcu_read_unlock(); +} + +unsigned int +nf_nat_setup_info(struct nf_conn *ct, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype) +{ + struct net *net = nf_ct_net(ct); + struct nf_conntrack_tuple curr_tuple, new_tuple; + struct nf_conn_nat *nat; + + /* nat helper or nfctnetlink also setup binding */ + nat = nfct_nat(ct); + if (!nat) { + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + + NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || + maniptype == NF_NAT_MANIP_DST); + 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 = ct->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 == NF_NAT_MANIP_SRC) + ct->status |= IPS_SRC_NAT; + else + ct->status |= IPS_DST_NAT; + } + + if (maniptype == NF_NAT_MANIP_SRC) { + unsigned int srchash; + + srchash = hash_by_src(net, nf_ct_zone(ct), + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + spin_lock_bh(&nf_nat_lock); + /* nf_conntrack_alter_reply might re-allocate extension aera */ + nat = nfct_nat(ct); + nat->ct = ct; + hlist_add_head_rcu(&nat->bysource, + &net->ct.nat_bysource[srchash]); + spin_unlock_bh(&nf_nat_lock); + } + + /* It's done. */ + if (maniptype == NF_NAT_MANIP_DST) + ct->status |= IPS_DST_NAT_DONE; + else + ct->status |= IPS_SRC_NAT_DONE; + + return NF_ACCEPT; +} +EXPORT_SYMBOL(nf_nat_setup_info); + +/* 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 *skb) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned long statusbit; + enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); + + if (mtype == NF_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); + + l3proto = __nf_nat_l3proto_find(target.src.l3num); + l4proto = __nf_nat_l4proto_find(target.src.l3num, + target.dst.protonum); + if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype)) + return NF_DROP; + } + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_nat_packet); + +struct nf_nat_proto_clean { + u8 l3proto; + u8 l4proto; + bool hash; +}; + +/* Clear NAT section of all conntracks, in case we're loaded again. */ +static int nf_nat_proto_clean(struct nf_conn *i, void *data) +{ + const struct nf_nat_proto_clean *clean = data; + struct nf_conn_nat *nat = nfct_nat(i); + + if (!nat) + return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || + (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) + return 0; + + if (clean->hash) { + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); + } else { + memset(nat, 0, sizeof(*nat)); + i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | + IPS_SEQ_ADJUST); + } + return 0; +} + +static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + .l4proto = l4proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +static void nf_nat_l3proto_clean(u8 l3proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +/* Protocol registration. */ +int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + const struct nf_nat_l4proto **l4protos; + unsigned int i; + int ret = 0; + + mutex_lock(&nf_nat_proto_mutex); + if (nf_nat_l4protos[l3proto] == NULL) { + l4protos = kmalloc(IPPROTO_MAX * sizeof(struct nf_nat_l4proto *), + GFP_KERNEL); + if (l4protos == NULL) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < IPPROTO_MAX; i++) + RCU_INIT_POINTER(l4protos[i], &nf_nat_l4proto_unknown); + + /* Before making proto_array visible to lockless readers, + * we must make sure its content is committed to memory. + */ + smp_wmb(); + + nf_nat_l4protos[l3proto] = l4protos; + } + + if (rcu_dereference_protected( + nf_nat_l4protos[l3proto][l4proto->l4proto], + lockdep_is_held(&nf_nat_proto_mutex) + ) != &nf_nat_l4proto_unknown) { + ret = -EBUSY; + goto out; + } + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], l4proto); + out: + mutex_unlock(&nf_nat_proto_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_register); + +/* No one stores the protocol anywhere; simply delete it. */ +void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], + &nf_nat_l4proto_unknown); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l4proto_clean(l3proto, l4proto->l4proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister); + +int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto) +{ + int err; + + err = nf_ct_l3proto_try_module_get(l3proto->l3proto); + if (err < 0) + return err; + + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP], + &nf_nat_l4proto_tcp); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_UDP], + &nf_nat_l4proto_udp); + mutex_unlock(&nf_nat_proto_mutex); + + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], l3proto); + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_register); + +void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], NULL); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l3proto_clean(l3proto->l3proto); + nf_ct_l3proto_module_put(l3proto->l3proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); + +/* No one using conntrack by the time this called. */ +static void nf_nat_cleanup_conntrack(struct nf_conn *ct) +{ + struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); + + if (nat == NULL || nat->ct == NULL) + return; + + NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static void nf_nat_move_storage(void *new, void *old) +{ + struct nf_conn_nat *new_nat = new; + struct nf_conn_nat *old_nat = old; + struct nf_conn *ct = old_nat->ct; + + if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) + return; + + spin_lock_bh(&nf_nat_lock); + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static struct nf_ct_ext_type nat_extend __read_mostly = { + .len = sizeof(struct nf_conn_nat), + .align = __alignof__(struct nf_conn_nat), + .destroy = nf_nat_cleanup_conntrack, + .move = nf_nat_move_storage, + .id = NF_CT_EXT_NAT, + .flags = NF_CT_EXT_F_PREALLOC, +}; + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { + [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, + [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, +}; + +static int nfnetlink_parse_nat_proto(struct nlattr *attr, + const struct nf_conn *ct, + struct nf_nat_range *range) +{ + struct nlattr *tb[CTA_PROTONAT_MAX+1]; + const struct nf_nat_l4proto *l4proto; + int err; + + err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy); + if (err < 0) + return err; + + l4proto = __nf_nat_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); + if (l4proto->nlattr_to_range) + err = l4proto->nlattr_to_range(tb, range); + + return err; +} + +static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { + [CTA_NAT_V4_MINIP] = { .type = NLA_U32 }, + [CTA_NAT_V4_MAXIP] = { .type = NLA_U32 }, + [CTA_NAT_PROTO] = { .type = NLA_NESTED }, +}; + +static int +nfnetlink_parse_nat(const struct nlattr *nat, + const struct nf_conn *ct, struct nf_nat_range *range) +{ + const struct nf_nat_l3proto *l3proto; + struct nlattr *tb[CTA_NAT_MAX+1]; + int err; + + memset(range, 0, sizeof(*range)); + + err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy); + if (err < 0) + return err; + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) { + err = -EAGAIN; + goto out; + } + err = l3proto->nlattr_to_range(tb, range); + if (err < 0) + goto out; + + if (!tb[CTA_NAT_PROTO]) + goto out; + + err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); +out: + rcu_read_unlock(); + return err; +} + +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + struct nf_nat_range range; + int err; + + err = nfnetlink_parse_nat(attr, ct, &range); + if (err < 0) + return err; + if (nf_nat_initialized(ct, manip)) + return -EEXIST; + + return nf_nat_setup_info(ct, &range, manip); +} +#else +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +static int __net_init nf_nat_net_init(struct net *net) +{ + /* Leave them the same for the moment. */ + net->ct.nat_htable_size = net->ct.htable_size; + net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0); + if (!net->ct.nat_bysource) + return -ENOMEM; + return 0; +} + +static void __net_exit nf_nat_net_exit(struct net *net) +{ + struct nf_nat_proto_clean clean = {}; + + nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + synchronize_rcu(); + nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); +} + +static struct pernet_operations nf_nat_net_ops = { + .init = nf_nat_net_init, + .exit = nf_nat_net_exit, +}; + +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + +static struct nfq_ct_nat_hook nfq_ct_nat = { + .seq_adjust = nf_nat_tcp_seq_adjust, +}; + +static int __init nf_nat_init(void) +{ + int ret; + + ret = nf_ct_extend_register(&nat_extend); + if (ret < 0) { + printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); + return ret; + } + + ret = register_pernet_subsys(&nf_nat_net_ops); + if (ret < 0) + goto cleanup_extend; + + nf_ct_helper_expectfn_register(&follow_master_nat); + + /* Initialize fake conntrack so that NAT will skip it */ + nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); + + BUG_ON(nf_nat_seq_adjust_hook != NULL); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); + BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, + nfnetlink_parse_nat_setup); + BUG_ON(nf_ct_nat_offset != NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); +#ifdef CONFIG_XFRM + BUG_ON(nf_nat_decode_session_hook != NULL); + RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); +#endif + return 0; + + cleanup_extend: + nf_ct_extend_unregister(&nat_extend); + return ret; +} + +static void __exit nf_nat_cleanup(void) +{ + unsigned int i; + + unregister_pernet_subsys(&nf_nat_net_ops); + nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); +#ifdef CONFIG_XFRM + RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); +#endif + for (i = 0; i < NFPROTO_NUMPROTO; i++) + kfree(nf_nat_l4protos[i]); + synchronize_net(); +} + +MODULE_LICENSE("GPL"); + +module_init(nf_nat_init); +module_exit(nf_nat_cleanup); diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c new file mode 100644 index 0000000..23c2b38 --- /dev/null +++ b/net/netfilter/nf_nat_helper.c @@ -0,0 +1,435 @@ +/* nf_nat_helper.c - generic support functions for NAT helpers + * + * (C) 2000-2002 Harald Welte <laforge@netfilter.org> + * (C) 2003-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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 <linux/module.h> +#include <linux/gfp.h> +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <net/tcp.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_helper.h> + +#define DUMP_OFFSET(x) \ + pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ + x->offset_before, x->offset_after, x->correction_pos); + +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) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; + + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); + + pr_debug("adjust_tcp_sequence: 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); + + pr_debug("adjust_tcp_sequence: Seq_offset after: "); + DUMP_OFFSET(this_way); +} + +/* Get the offset value, for conntrack */ +s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way; + s16 offset; + + if (!nat) + return 0; + + this_way = &nat->seq[dir]; + spin_lock_bh(&nf_nat_seqofs_lock); + offset = after(seq, this_way->correction_pos) + ? this_way->offset_after : this_way->offset_before; + spin_unlock_bh(&nf_nat_seqofs_lock); + + return offset; +} + +/* 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 = skb_network_header(skb) + dataoff; + + /* move post-replacement */ + memmove(data + match_offset + rep_len, + data + match_offset + match_len, + skb->tail - (skb->network_header + dataoff + + match_offset + match_len)); + + /* insert data from buffer */ + memcpy(data + match_offset, rep_buffer, rep_len); + + /* update skb info */ + if (rep_len > match_len) { + pr_debug("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 { + pr_debug("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); + } + + if (nf_ct_l3num((struct nf_conn *)skb->nfct) == NFPROTO_IPV4) { + /* fix IP hdr checksum information */ + ip_hdr(skb)->tot_len = htons(skb->len); + ip_send_check(ip_hdr(skb)); + } else + ipv6_hdr(skb)->payload_len = + htons(skb->len - sizeof(struct ipv6hdr)); +} + +/* Unusual, but possible case. */ +static int enlarge_skb(struct sk_buff *skb, unsigned int extra) +{ + if (skb->len + extra > 65535) + return 0; + + if (pskb_expand_head(skb, 0, extra - skb_tailroom(skb), GFP_ATOMIC)) + return 0; + + return 1; +} + +void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s16 off) +{ + if (!off) + return; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); + nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); +} +EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); + +void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); + +/* 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 *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len, bool adjust) +{ + const struct nf_nat_l3proto *l3proto; + struct tcphdr *tcph; + int oldlen, datalen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + SKB_LINEAR_ASSERT(skb); + + tcph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + tcph->doff*4, + match_offset, match_len, rep_buffer, rep_len); + + datalen = skb->len - protoff; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_TCP, tcph, &tcph->check, + datalen, oldlen); + + if (adjust && rep_len != match_len) + nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, + (int)rep_len - (int)match_len); + + 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 *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + const struct nf_nat_l3proto *l3proto; + struct udphdr *udph; + int datalen, oldlen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + udph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + sizeof(*udph), + match_offset, match_len, rep_buffer, rep_len); + + /* update the length of the UDP packet */ + datalen = skb->len - protoff; + udph->len = htons(datalen); + + /* fix udp checksum if udp checksum was previously calculated */ + if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) + return 1; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_UDP, udph, &udph->check, + datalen, oldlen); + + 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); + + pr_debug("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); + + inet_proto_csum_replace4(&tcph->check, skb, + sack->start_seq, new_start_seq, 0); + inet_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 *skb, + unsigned int protoff, + 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 = protoff + sizeof(struct tcphdr); + optend = protoff + tcph->doff * 4; + + if (!skb_make_writable(skb, optend)) + return 0; + + dir = CTINFO2DIR(ctinfo); + + while (optoff < optend) { + /* Usually: option, length. */ + unsigned char *op = skb->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(skb, tcph, optoff+2, + optoff+op[1], &nat->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 *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff) +{ + struct tcphdr *tcph; + int dir; + __be32 newseq, newack; + s16 seqoff, ackoff; + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way, *other_way; + + dir = CTINFO2DIR(ctinfo); + + this_way = &nat->seq[dir]; + other_way = &nat->seq[!dir]; + + if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + return 0; + + tcph = (void *)skb->data + protoff; + if (after(ntohl(tcph->seq), this_way->correction_pos)) + seqoff = this_way->offset_after; + else + seqoff = this_way->offset_before; + + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, + other_way->correction_pos)) + ackoff = other_way->offset_after; + else + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); + + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); + inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); + + pr_debug("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; + + return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); +} + +/* 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 = NF_NAT_RANGE_MAP_IPS; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.src.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} +EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c new file mode 100644 index 0000000..9baaf73 --- /dev/null +++ b/net/netfilter/nf_nat_proto_common.c @@ -0,0 +1,112 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2008 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/types.h> +#include <linux/random.h> +#include <linux/netfilter.h> +#include <linux/export.h> + +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +bool nf_nat_l4proto_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 == NF_NAT_MANIP_SRC) + port = tuple->src.u.all; + else + port = tuple->dst.u.all; + + return ntohs(port) >= ntohs(min->all) && + ntohs(port) <= ntohs(max->all); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range); + +void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct, + u16 *rover) +{ + unsigned int range_size, min, i; + __be16 *portptr; + u_int16_t off; + + if (maniptype == NF_NAT_MANIP_SRC) + portptr = &tuple->src.u.all; + else + portptr = &tuple->dst.u.all; + + /* If no range specified... */ + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + /* If it's dst rewrite, can't change port */ + if (maniptype == NF_NAT_MANIP_DST) + return; + + 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_proto.all); + range_size = ntohs(range->max_proto.all) - min + 1; + } + + if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) + off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC + ? tuple->dst.u.all + : tuple->src.u.all); + else + off = *rover; + + for (i = 0; ; ++off) { + *portptr = htons(min + off % range_size); + if (++i != range_size && nf_nat_used_tuple(tuple, ct)) + continue; + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) + *rover = off; + return; + } + return; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_PROTONAT_PORT_MIN]) { + range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); + range->max_proto.all = range->min_proto.all; + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + if (tb[CTA_PROTONAT_PORT_MAX]) { + range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_nlattr_to_range); +#endif diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c new file mode 100644 index 0000000..c8be2cd --- /dev/null +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -0,0 +1,116 @@ +/* + * DCCP NAT protocol helper + * + * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/skbuff.h> +#include <linux/dccp.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u_int16_t dccp_port_rover; + +static void +dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &dccp_port_rover); +} + +static bool +dccp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct dccp_hdr *hdr; + __be16 *portptr, oldport, newport; + int hdrsize = 8; /* DCCP connection tracking guarantees this much */ + + if (skb->len >= hdroff + sizeof(struct dccp_hdr)) + hdrsize = sizeof(struct dccp_hdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct dccp_hdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + newport = tuple->src.u.dccp.port; + portptr = &hdr->dccph_sport; + } else { + newport = tuple->dst.u.dccp.port; + portptr = &hdr->dccph_dport; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, + 0); + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_dccp = { + .l4proto = IPPROTO_DCCP, + .manip_pkt = dccp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = dccp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_dccp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); +err1: + return err; +} + +static void __exit nf_nat_proto_dccp_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + +} + +module_init(nf_nat_proto_dccp_init); +module_exit(nf_nat_proto_dccp_fini); + +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_DESCRIPTION("DCCP NAT protocol helper"); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c new file mode 100644 index 0000000..e64faa5 --- /dev/null +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -0,0 +1,103 @@ +/* + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/types.h> +#include <linux/init.h> +#include <linux/sctp.h> +#include <linux/module.h> +#include <net/sctp/checksum.h> + +#include <net/netfilter/nf_nat_l4proto.h> + +static u_int16_t nf_sctp_port_rover; + +static void +sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &nf_sctp_port_rover); +} + +static bool +sctp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct sk_buff *frag; + sctp_sctphdr_t *hdr; + __be32 crc32; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct sctphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + hdr->source = tuple->src.u.sctp.port; + } else { + /* Get rid of dst port */ + hdr->dest = tuple->dst.u.sctp.port; + } + + crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); + skb_walk_frags(skb, frag) + crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), + crc32); + crc32 = sctp_end_cksum(crc32); + hdr->checksum = crc32; + + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_sctp = { + .l4proto = IPPROTO_SCTP, + .manip_pkt = sctp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = sctp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_sctp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_sctp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +err1: + return err; +} + +static void __exit nf_nat_proto_sctp_exit(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +} + +module_init(nf_nat_proto_sctp_init); +module_exit(nf_nat_proto_sctp_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SCTP NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c new file mode 100644 index 0000000..83ec8a6 --- /dev/null +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -0,0 +1,85 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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 <linux/types.h> +#include <linux/init.h> +#include <linux/export.h> +#include <linux/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> +#include <net/netfilter/nf_nat_core.h> + +static u16 tcp_port_rover; + +static void +tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &tcp_port_rover); +} + +static bool +tcp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct tcphdr *hdr; + __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 (skb->len >= hdroff + sizeof(struct tcphdr)) + hdrsize = sizeof(struct tcphdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct tcphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.tcp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.tcp.port; + portptr = &hdr->dest; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0); + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_tcp = { + .l4proto = IPPROTO_TCP, + .manip_pkt = tcp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = tcp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c new file mode 100644 index 0000000..7df613f --- /dev/null +++ b/net/netfilter/nf_nat_proto_udp.c @@ -0,0 +1,76 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * + * 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 <linux/types.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/udp.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_core.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u16 udp_port_rover; + +static void +udp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udp_port_rover); +} + +static bool +udp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) { + l3proto->csum_update(skb, iphdroff, &hdr->check, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, + 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + } + *portptr = newport; + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_udp = { + .l4proto = IPPROTO_UDP, + .manip_pkt = udp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c new file mode 100644 index 0000000..776a0d1 --- /dev/null +++ b/net/netfilter/nf_nat_proto_udplite.c @@ -0,0 +1,106 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2008 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/types.h> +#include <linux/init.h> +#include <linux/udp.h> + +#include <linux/netfilter.h> +#include <linux/module.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l3proto.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static u16 udplite_port_rover; + +static void +udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udplite_port_rover); +} + +static bool +udplite_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of source port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + + *portptr = newport; + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_udplite = { + .l4proto = IPPROTO_UDPLITE, + .manip_pkt = udplite_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udplite_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_udplite_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_udplite); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +err1: + return err; +} + +static void __exit nf_nat_proto_udplite_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +} + +module_init(nf_nat_proto_udplite_init); +module_exit(nf_nat_proto_udplite_fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UDP-Lite NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c new file mode 100644 index 0000000..6e494d5 --- /dev/null +++ b/net/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 <coreteam@netfilter.org> + * + * 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 <linux/types.h> +#include <linux/init.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_nat.h> +#include <net/netfilter/nf_nat_l4proto.h> + +static bool 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 true; +} + +static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto, + 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; +} + +static bool +unknown_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_unknown = { + .manip_pkt = unknown_manip_pkt, + .in_range = unknown_in_range, + .unique_tuple = unknown_unique_tuple, +}; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c new file mode 100644 index 0000000..7521368 --- /dev/null +++ b/net/netfilter/xt_nat.c @@ -0,0 +1,167 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2011 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_nat_core.h> + +static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (mr->rangesize != 1) { + pr_info("%s: multiple ranges no longer supported\n", + par->target->name); + return -EINVAL; + } + return 0; +} + +static void xt_nat_convert_range(struct nf_nat_range *dst, + const struct nf_nat_ipv4_range *src) +{ + memset(&dst->min_addr, 0, sizeof(dst->min_addr)); + memset(&dst->max_addr, 0, sizeof(dst->max_addr)); + + dst->flags = src->flags; + dst->min_addr.ip = src->min_ip; + dst->max_addr.ip = src->max_ip; + dst->min_proto = src->min; + dst->max_proto = src->max; +} + +static unsigned int +xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} + +static unsigned int +xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_DST); +} + +static struct xt_target xt_nat_target_reg[] __read_mostly = { + { + .name = "SNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_snat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_dnat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "SNAT", + .revision = 1, + .target = xt_snat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 1, + .target = xt_dnat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +}; + +static int __init xt_nat_init(void) +{ + return xt_register_targets(xt_nat_target_reg, + ARRAY_SIZE(xt_nat_target_reg)); +} + +static void __exit xt_nat_exit(void) +{ + xt_unregister_targets(xt_nat_target_reg, ARRAY_SIZE(xt_nat_target_reg)); +} + +module_init(xt_nat_init); +module_exit(xt_nat_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_SNAT"); +MODULE_ALIAS("ipt_DNAT"); |