diff options
author | Florian Westphal <fw@strlen.de> | 2018-06-29 07:46:51 +0200 |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2018-07-17 15:27:49 +0200 |
commit | a0ae2562c6c4b2721d9fddba63b7286c13517d9f (patch) | |
tree | d57aa096dba122f1b4e6fd83625591c6a7f7f531 /net/netfilter | |
parent | c779e849608a875448f6ffc2a5c2a15523bdcd00 (diff) |
netfilter: conntrack: remove l3proto abstraction
This unifies ipv4 and ipv6 protocol trackers and removes the l3proto
abstraction.
This gets rid of all l3proto indirect calls and the need to do
a lookup on the function to call for l3 demux.
It increases module size by only a small amount (12kbyte), so this reduces
size because nf_conntrack.ko is useless without either nf_conntrack_ipv4
or nf_conntrack_ipv6 module.
before:
text data bss dec hex filename
7357 1088 0 8445 20fd nf_conntrack_ipv4.ko
7405 1084 4 8493 212d nf_conntrack_ipv6.ko
72614 13689 236 86539 1520b nf_conntrack.ko
19K nf_conntrack_ipv4.ko
19K nf_conntrack_ipv6.ko
179K nf_conntrack.ko
after:
text data bss dec hex filename
79277 13937 236 93450 16d0a nf_conntrack.ko
191K nf_conntrack.ko
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/Kconfig | 2 | ||||
-rw-r--r-- | net/netfilter/Makefile | 7 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 11 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto.c | 847 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_icmp.c | 388 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_icmpv6.c | 387 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_standalone.c | 14 | ||||
-rw-r--r-- | net/netfilter/nf_nat_core.c | 8 |
8 files changed, 1408 insertions, 256 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 3ce657fbca67..9eab519b403a 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -49,6 +49,8 @@ config NETFILTER_NETLINK_LOG config NF_CONNTRACK tristate "Netfilter connection tracking support" default m if NETFILTER_ADVANCED=n + select NF_DEFRAG_IPV4 + select NF_DEFRAG_IPV6 if IPV6 != n help Connection tracking keeps a record of what packets have passed through your machine, in order to figure out how they are related diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index f132ea850778..53bd1ed1228a 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,7 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o -nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o +nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o \ + nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o \ + nf_conntrack_proto_icmp.o \ + nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o + +nf_conntrack-$(subst m,y,$(CONFIG_IPV6)) += nf_conntrack_proto_icmpv6.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c069f2faff4c..5123e91b1982 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -291,7 +291,6 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u_int8_t *protonum) { int dataoff = -1; -#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4) const struct iphdr *iph; struct iphdr _iph; @@ -314,15 +313,14 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, nhoff, iph->ihl << 2, skb->len); return -1; } -#endif return dataoff; } +#if IS_ENABLED(CONFIG_IPV6) static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u8 *protonum) { int protoff = -1; -#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6) unsigned int extoff = nhoff + sizeof(struct ipv6hdr); __be16 frag_off; u8 nexthdr; @@ -343,9 +341,9 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, } *protonum = nexthdr; -#endif return protoff; } +#endif static int get_l4proto(const struct sk_buff *skb, unsigned int nhoff, u8 pf, u8 *l4num) @@ -353,8 +351,10 @@ static int get_l4proto(const struct sk_buff *skb, switch (pf) { case NFPROTO_IPV4: return ipv4_get_l4proto(skb, nhoff, l4num); +#if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: return ipv6_get_l4proto(skb, nhoff, l4num); +#endif default: *l4num = 0; break; @@ -2197,9 +2197,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) } EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); -module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, - &nf_conntrack_htable_size, 0600); - static __always_inline unsigned int total_extension_size(void) { /* remember to add new extensions below */ diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 39df72bb9d56..803607a90102 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -1,14 +1,4 @@ -/* L3/L4 protocol support for nf_conntrack. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> - * (C) 2006-2012 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. - */ +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/netfilter.h> @@ -24,22 +14,39 @@ #include <linux/netdevice.h> #include <net/netfilter/nf_conntrack.h> -#include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_log.h> +#include <linux/ip.h> +#include <linux/icmp.h> +#include <linux/sysctl.h> +#include <net/route.h> +#include <net/ip.h> + +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <linux/netfilter_ipv6/ip6_tables.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/ipv4/nf_conntrack_ipv4.h> +#include <net/netfilter/ipv6/nf_conntrack_ipv6.h> +#include <net/netfilter/nf_nat_helper.h> +#include <net/netfilter/ipv4/nf_defrag_ipv4.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> + +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +extern unsigned int nf_conntrack_net_id; + static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; -struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; -EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); -struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { - .l3proto = PF_UNSPEC, -}; -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); - #ifdef CONFIG_SYSCTL static int nf_ct_register_sysctl(struct net *net, @@ -127,137 +134,6 @@ __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) } EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find); -/* this is guaranteed to always return a valid protocol helper, since - * it falls back to generic_protocol */ -const struct nf_conntrack_l3proto * -nf_ct_l3proto_find_get(u_int16_t l3proto) -{ - struct nf_conntrack_l3proto *p; - - rcu_read_lock(); - p = __nf_ct_l3proto_find(l3proto); - if (!try_module_get(p->me)) - p = &nf_conntrack_l3proto_generic; - rcu_read_unlock(); - - return p; -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_find_get); - -int -nf_ct_l3proto_try_module_get(unsigned short l3proto) -{ - const struct nf_conntrack_l3proto *p; - int ret; - -retry: p = nf_ct_l3proto_find_get(l3proto); - if (p == &nf_conntrack_l3proto_generic) { - ret = request_module("nf_conntrack-%d", l3proto); - if (!ret) - goto retry; - - return -EPROTOTYPE; - } - - return 0; -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_try_module_get); - -void nf_ct_l3proto_module_put(unsigned short l3proto) -{ - struct nf_conntrack_l3proto *p; - - /* rcu_read_lock not necessary since the caller holds a reference, but - * taken anyways to avoid lockdep warnings in __nf_ct_l3proto_find() - */ - rcu_read_lock(); - p = __nf_ct_l3proto_find(l3proto); - module_put(p->me); - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put); - -static int nf_ct_netns_do_get(struct net *net, u8 nfproto) -{ - const struct nf_conntrack_l3proto *l3proto; - int ret; - - might_sleep(); - - ret = nf_ct_l3proto_try_module_get(nfproto); - if (ret < 0) - return ret; - - /* we already have a reference, can't fail */ - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(nfproto); - rcu_read_unlock(); - - if (!l3proto->net_ns_get) - return 0; - - ret = l3proto->net_ns_get(net); - if (ret < 0) - nf_ct_l3proto_module_put(nfproto); - - return ret; -} - -int nf_ct_netns_get(struct net *net, u8 nfproto) -{ - int err; - - if (nfproto == NFPROTO_INET) { - err = nf_ct_netns_do_get(net, NFPROTO_IPV4); - if (err < 0) - goto err1; - err = nf_ct_netns_do_get(net, NFPROTO_IPV6); - if (err < 0) - goto err2; - } else { - err = nf_ct_netns_do_get(net, nfproto); - if (err < 0) - goto err1; - } - return 0; - -err2: - nf_ct_netns_put(net, NFPROTO_IPV4); -err1: - return err; -} -EXPORT_SYMBOL_GPL(nf_ct_netns_get); - -static void nf_ct_netns_do_put(struct net *net, u8 nfproto) -{ - const struct nf_conntrack_l3proto *l3proto; - - might_sleep(); - - /* same as nf_conntrack_netns_get(), reference assumed */ - rcu_read_lock(); - l3proto = __nf_ct_l3proto_find(nfproto); - rcu_read_unlock(); - - if (WARN_ON(!l3proto)) - return; - - if (l3proto->net_ns_put) - l3proto->net_ns_put(net); - - nf_ct_l3proto_module_put(nfproto); -} - -void nf_ct_netns_put(struct net *net, uint8_t nfproto) -{ - if (nfproto == NFPROTO_INET) { - nf_ct_netns_do_put(net, NFPROTO_IPV4); - nf_ct_netns_do_put(net, NFPROTO_IPV6); - } else - nf_ct_netns_do_put(net, nfproto); -} -EXPORT_SYMBOL_GPL(nf_ct_netns_put); - const struct nf_conntrack_l4proto * nf_ct_l4proto_find_get(u_int16_t l3num, u_int8_t l4num) { @@ -279,11 +155,6 @@ void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p) } EXPORT_SYMBOL_GPL(nf_ct_l4proto_put); -static int kill_l3proto(struct nf_conn *i, void *data) -{ - return nf_ct_l3num(i) == ((const struct nf_conntrack_l3proto *)data)->l3proto; -} - static int kill_l4proto(struct nf_conn *i, void *data) { const struct nf_conntrack_l4proto *l4proto; @@ -292,49 +163,6 @@ static int kill_l4proto(struct nf_conn *i, void *data) nf_ct_l3num(i) == l4proto->l3proto; } -int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto) -{ - int ret = 0; - struct nf_conntrack_l3proto *old; - - if (proto->l3proto >= NFPROTO_NUMPROTO) - return -EBUSY; - - mutex_lock(&nf_ct_proto_mutex); - old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], - lockdep_is_held(&nf_ct_proto_mutex)); - if (old != &nf_conntrack_l3proto_generic) { - ret = -EBUSY; - goto out_unlock; - } - - rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto); - -out_unlock: - mutex_unlock(&nf_ct_proto_mutex); - return ret; - -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); - -void nf_ct_l3proto_unregister(const struct nf_conntrack_l3proto *proto) -{ - BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO); - - mutex_lock(&nf_ct_proto_mutex); - BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != proto); - rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], - &nf_conntrack_l3proto_generic); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_rcu(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l3proto, (void*)proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); - static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, const struct nf_conntrack_l4proto *l4proto) { @@ -501,8 +329,23 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); -int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) +static void +nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], + unsigned int num_proto) +{ + mutex_lock(&nf_ct_proto_mutex); + while (num_proto-- != 0) + __nf_ct_l4proto_unregister_one(l4proto[num_proto]); + mutex_unlock(&nf_ct_proto_mutex); + + synchronize_net(); + /* Remove all contrack entries for this protocol */ + nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); +} + +static int +nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], + unsigned int num_proto) { int ret = -EINVAL, ver; unsigned int i; @@ -520,7 +363,6 @@ int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], } return ret; } -EXPORT_SYMBOL_GPL(nf_ct_l4proto_register); int nf_ct_l4proto_pernet_register(struct net *net, const struct nf_conntrack_l4proto *const l4proto[], @@ -544,20 +386,6 @@ int nf_ct_l4proto_pernet_register(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - mutex_lock(&nf_ct_proto_mutex); - while (num_proto-- != 0) - __nf_ct_l4proto_unregister_one(l4proto[num_proto]); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); - void nf_ct_l4proto_pernet_unregister(struct net *net, const struct nf_conntrack_l4proto *const l4proto[], unsigned int num_proto) @@ -567,6 +395,563 @@ void nf_ct_l4proto_pernet_unregister(struct net *net, } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); +static unsigned int ipv4_helper(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + + /* This is where we call the helper: as the packet goes out. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + /* rcu_read_lock()ed by nf_hook_thresh */ + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), + ct, ctinfo); +} + +static unsigned int ipv4_confirm(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); +} + +static unsigned int ipv4_conntrack_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); +} + +static unsigned int ipv4_conntrack_local(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */ + enum ip_conntrack_info ctinfo; + struct nf_conn *tmpl; + + tmpl = nf_ct_get(skb, &ctinfo); + if (tmpl && nf_ct_is_template(tmpl)) { + /* when skipping ct, clear templates to avoid fooling + * later targets/matches + */ + skb->_nfct = 0; + nf_ct_put(tmpl); + } + return NF_ACCEPT; + } + + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); +} + +/* Connection tracking may drop packets, but never alters them, so + * make it the first hook. + */ +static const struct nf_hook_ops ipv4_conntrack_ops[] = { + { + .hook = ipv4_conntrack_in, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_conntrack_local, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_helper, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_confirm, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, + { + .hook = ipv4_helper, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_confirm, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, +}; + +/* Fast function for those who don't want to parse /proc (and I don't + * blame them). + * Reversing the socket's dst/src point of view gives us the reply + * mapping. + */ +static int +getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_tuple tuple; + + memset(&tuple, 0, sizeof(tuple)); + + lock_sock(sk); + tuple.src.u3.ip = inet->inet_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.ip = inet->inet_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.src.l3num = PF_INET; + tuple.dst.protonum = sk->sk_protocol; + release_sock(sk); + + /* We only do TCP and SCTP at the moment: is there a better way? */ + if (tuple.dst.protonum != IPPROTO_TCP && + tuple.dst.protonum != IPPROTO_SCTP) { + pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n"); + return -ENOPROTOOPT; + } + + if ((unsigned int)*len < sizeof(struct sockaddr_in)) { + pr_debug("SO_ORIGINAL_DST: len %d not %zu\n", + *len, sizeof(struct sockaddr_in)); + return -EINVAL; + } + + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); + if (h) { + struct sockaddr_in sin; + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + sin.sin_family = AF_INET; + sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.dst.u.tcp.port; + sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.dst.u3.ip; + memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); + + pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", + &sin.sin_addr.s_addr, ntohs(sin.sin_port)); + nf_ct_put(ct); + if (copy_to_user(user, &sin, sizeof(sin)) != 0) + return -EFAULT; + else + return 0; + } + pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", + &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; +} + +static struct nf_sockopt_ops so_getorigdst = { + .pf = PF_INET, + .get_optmin = SO_ORIGINAL_DST, + .get_optmax = SO_ORIGINAL_DST + 1, + .get = getorigdst, + .owner = THIS_MODULE, +}; + +#if IS_ENABLED(CONFIG_IPV6) +static int +ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len) +{ + struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 }; + const struct ipv6_pinfo *inet6 = inet6_sk(sk); + const struct inet_sock *inet = inet_sk(sk); + const struct nf_conntrack_tuple_hash *h; + struct sockaddr_in6 sin6; + struct nf_conn *ct; + __be32 flow_label; + int bound_dev_if; + + lock_sock(sk); + tuple.src.u3.in6 = sk->sk_v6_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.in6 = sk->sk_v6_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; + tuple.dst.protonum = sk->sk_protocol; + bound_dev_if = sk->sk_bound_dev_if; + flow_label = inet6->flow_label; + release_sock(sk); + + if (tuple.dst.protonum != IPPROTO_TCP && + tuple.dst.protonum != IPPROTO_SCTP) + return -ENOPROTOOPT; + + if (*len < 0 || (unsigned int)*len < sizeof(sin6)) + return -EINVAL; + + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); + if (!h) { + pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n", + &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port)); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + sin6.sin6_family = AF_INET6; + sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; + sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK; + memcpy(&sin6.sin6_addr, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6, + sizeof(sin6.sin6_addr)); + + nf_ct_put(ct); + sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if); + return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0; +} + +static struct nf_sockopt_ops so_getorigdst6 = { + .pf = NFPROTO_IPV6, + .get_optmin = IP6T_SO_ORIGINAL_DST, + .get_optmax = IP6T_SO_ORIGINAL_DST + 1, + .get = ipv6_getorigdst, + .owner = THIS_MODULE, +}; + +static unsigned int ipv6_confirm(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned char pnum = ipv6_hdr(skb)->nexthdr; + int protoff; + __be16 frag_off; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + goto out; + + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + goto out; + } + + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } +out: + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); +} + +static unsigned int ipv6_conntrack_in(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); +} + +static unsigned int ipv6_conntrack_local(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); +} + +static unsigned int ipv6_helper(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + const struct nf_conn_help *help; + const struct nf_conntrack_helper *helper; + enum ip_conntrack_info ctinfo; + __be16 frag_off; + int protoff; + u8 nexthdr; + + /* This is where we call the helper: as the packet goes out. */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct || ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + /* rcu_read_lock()ed by nf_hook_thresh */ + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + nexthdr = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + + return helper->help(skb, protoff, ct, ctinfo); +} + +static const struct nf_hook_ops ipv6_conntrack_ops[] = { + { + .hook = ipv6_conntrack_in, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_conntrack_local, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_helper, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_LAST, + }, + { + .hook = ipv6_helper, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv6_confirm, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_LAST - 1, + }, +}; +#endif + +static int nf_ct_netns_do_get(struct net *net, u8 nfproto) +{ + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + int err = 0; + + mutex_lock(&nf_ct_proto_mutex); + + switch (nfproto) { + case NFPROTO_IPV4: + cnet->users4++; + if (cnet->users4 > 1) + goto out_unlock; + err = nf_defrag_ipv4_enable(net); + if (err) { + cnet->users4 = 0; + goto out_unlock; + } + + err = nf_register_net_hooks(net, ipv4_conntrack_ops, + ARRAY_SIZE(ipv4_conntrack_ops)); + if (err) + cnet->users4 = 0; + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: + cnet->users6++; + if (cnet->users6 > 1) + goto out_unlock; + err = nf_defrag_ipv6_enable(net); + if (err < 0) { + cnet->users6 = 0; + goto out_unlock; + } + + err = nf_register_net_hooks(net, ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); + if (err) + cnet->users6 = 0; + break; +#endif + default: + err = -EPROTO; + break; + } + out_unlock: + mutex_unlock(&nf_ct_proto_mutex); + return err; +} + +static void nf_ct_netns_do_put(struct net *net, u8 nfproto) +{ + struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + + mutex_lock(&nf_ct_proto_mutex); + switch (nfproto) { + case NFPROTO_IPV4: + if (cnet->users4 && (--cnet->users4 == 0)) + nf_unregister_net_hooks(net, ipv4_conntrack_ops, + ARRAY_SIZE(ipv4_conntrack_ops)); + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: + if (cnet->users6 && (--cnet->users6 == 0)) + nf_unregister_net_hooks(net, ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); + break; +#endif + } + + mutex_unlock(&nf_ct_proto_mutex); +} + +int nf_ct_netns_get(struct net *net, u8 nfproto) +{ + int err; + + if (nfproto == NFPROTO_INET) { + err = nf_ct_netns_do_get(net, NFPROTO_IPV4); + if (err < 0) + goto err1; + err = nf_ct_netns_do_get(net, NFPROTO_IPV6); + if (err < 0) + goto err2; + } else { + err = nf_ct_netns_do_get(net, nfproto); + if (err < 0) + goto err1; + } + return 0; + +err2: + nf_ct_netns_put(net, NFPROTO_IPV4); +err1: + return err; +} +EXPORT_SYMBOL_GPL(nf_ct_netns_get); + +void nf_ct_netns_put(struct net *net, uint8_t nfproto) +{ + if (nfproto == NFPROTO_INET) { + nf_ct_netns_do_put(net, NFPROTO_IPV4); + nf_ct_netns_do_put(net, NFPROTO_IPV6); + } else { + nf_ct_netns_do_put(net, nfproto); + } +} +EXPORT_SYMBOL_GPL(nf_ct_netns_put); + +static const struct nf_conntrack_l4proto * const builtin_l4proto[] = { + &nf_conntrack_l4proto_tcp4, + &nf_conntrack_l4proto_udp4, + &nf_conntrack_l4proto_icmp, +#ifdef CONFIG_NF_CT_PROTO_DCCP + &nf_conntrack_l4proto_dccp4, +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + &nf_conntrack_l4proto_sctp4, +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + &nf_conntrack_l4proto_udplite4, +#endif +#if IS_ENABLED(CONFIG_IPV6) + &nf_conntrack_l4proto_tcp6, + &nf_conntrack_l4proto_udp6, + &nf_conntrack_l4proto_icmpv6, +#ifdef CONFIG_NF_CT_PROTO_DCCP + &nf_conntrack_l4proto_dccp6, +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + &nf_conntrack_l4proto_sctp6, +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + &nf_conntrack_l4proto_udplite6, +#endif +#endif /* CONFIG_IPV6 */ +}; + +int nf_conntrack_proto_init(void) +{ + int ret = 0; + + ret = nf_register_sockopt(&so_getorigdst); + if (ret < 0) + return ret; + +#if IS_ENABLED(CONFIG_IPV6) + ret = nf_register_sockopt(&so_getorigdst6); + if (ret < 0) + goto cleanup_sockopt; +#endif + ret = nf_ct_l4proto_register(builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + if (ret < 0) + goto cleanup_sockopt2; + + return ret; +cleanup_sockopt2: + nf_unregister_sockopt(&so_getorigdst); +#if IS_ENABLED(CONFIG_IPV6) +cleanup_sockopt: + nf_unregister_sockopt(&so_getorigdst6); +#endif + return ret; +} + +void nf_conntrack_proto_fini(void) +{ + unsigned int i; + + nf_ct_l4proto_unregister(builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + nf_unregister_sockopt(&so_getorigdst); +#if IS_ENABLED(CONFIG_IPV6) + nf_unregister_sockopt(&so_getorigdst6); +#endif + + /* free l3proto protocol tables */ + for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) + kfree(nf_ct_protos[i]); +} + int nf_conntrack_proto_pernet_init(struct net *net) { int err; @@ -583,6 +968,14 @@ int nf_conntrack_proto_pernet_init(struct net *net) if (err < 0) return err; + err = nf_ct_l4proto_pernet_register(net, builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); + if (err < 0) { + nf_ct_l4proto_unregister_sysctl(net, pn, + &nf_conntrack_l4proto_generic); + return err; + } + pn->users++; return 0; } @@ -592,25 +985,19 @@ void nf_conntrack_proto_pernet_fini(struct net *net) struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); + nf_ct_l4proto_pernet_unregister(net, builtin_l4proto, + ARRAY_SIZE(builtin_l4proto)); pn->users--; nf_ct_l4proto_unregister_sysctl(net, pn, &nf_conntrack_l4proto_generic); } -int nf_conntrack_proto_init(void) -{ - unsigned int i; - for (i = 0; i < NFPROTO_NUMPROTO; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); - return 0; -} -void nf_conntrack_proto_fini(void) -{ - unsigned int i; - /* free l3proto protocol tables */ - for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) - kfree(nf_ct_protos[i]); -} +module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, + &nf_conntrack_htable_size, 0600); + +MODULE_ALIAS("ip_conntrack"); +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c new file mode 100644 index 000000000000..036670b38282 --- /dev/null +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -0,0 +1,388 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2006-2010 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/timer.h> +#include <linux/netfilter.h> +#include <linux/in.h> +#include <linux/icmp.h> +#include <linux/seq_file.h> +#include <net/ip.h> +#include <net/checksum.h> +#include <linux/netfilter_ipv4.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_log.h> + +static const unsigned int nf_ct_icmp_timeout = 30*HZ; + +static inline struct nf_icmp_net *icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + +static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) +{ + const struct icmphdr *hp; + struct icmphdr _hdr; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + + tuple->dst.u.icmp.type = hp->type; + tuple->src.u.icmp.id = hp->un.echo.id; + tuple->dst.u.icmp.code = hp->code; + + return true; +} + +/* Add 1; spaces filled with 0. */ +static const u_int8_t invmap[] = { + [ICMP_ECHO] = ICMP_ECHOREPLY + 1, + [ICMP_ECHOREPLY] = ICMP_ECHO + 1, + [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, + [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, + [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, + [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, + [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, + [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 +}; + +static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + if (orig->dst.u.icmp.type >= sizeof(invmap) || + !invmap[orig->dst.u.icmp.type]) + return false; + + tuple->src.u.icmp.id = orig->src.u.icmp.id; + tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; + tuple->dst.u.icmp.code = orig->dst.u.icmp.code; + return true; +} + +static unsigned int *icmp_get_timeouts(struct net *net) +{ + return &icmp_pernet(net)->timeout; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int icmp_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo) +{ + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmp_get_timeouts(nf_ct_net(ct)); + + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff) +{ + static const u_int8_t valid_new[] = { + [ICMP_ECHO] = 1, + [ICMP_TIMESTAMP] = 1, + [ICMP_INFO_REQUEST] = 1, + [ICMP_ADDRESS] = 1 + }; + + if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || + !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { + /* Can't create a new ICMP `conn' with this. */ + pr_debug("icmp: can't create new conn with type %u\n", + ct->tuplehash[0].tuple.dst.u.icmp.type); + nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); + return false; + } + return true; +} + +/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ +static int +icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int hooknum) +{ + struct nf_conntrack_tuple innertuple, origtuple; + const struct nf_conntrack_l4proto *innerproto; + const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_zone *zone; + enum ip_conntrack_info ctinfo; + struct nf_conntrack_zone tmp; + + WARN_ON(skb_nfct(skb)); + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); + + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + ip_hdrlen(skb) + + sizeof(struct icmphdr), + PF_INET, net, &origtuple)) { + pr_debug("icmp_error_message: failed to get tuple\n"); + return -NF_ACCEPT; + } + + /* rcu_read_lock()ed by nf_hook_thresh */ + innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum); + + /* Ordinarily, we'd expect the inverted tupleproto, but it's + been preserved inside the ICMP. */ + if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; + } + + ctinfo = IP_CT_RELATED; + + h = nf_conntrack_find_get(net, zone, &innertuple); + if (!h) { + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; + } + + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo += IP_CT_IS_REPLY; + + /* Update skb to refer to this connection */ + nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + return NF_ACCEPT; +} + +static void icmp_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg); +} + +/* Small and modified version of icmp_rcv */ +static int +icmp_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + const struct icmphdr *icmph; + struct icmphdr _ih; + + /* Not enough header? */ + icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); + if (icmph == NULL) { + icmp_error_log(skb, net, pf, "short packet"); + return -NF_ACCEPT; + } + + /* See ip_conntrack_proto_tcp.c */ + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, dataoff, 0)) { + icmp_error_log(skb, net, pf, "bad hw icmp checksum"); + return -NF_ACCEPT; + } + + /* + * 18 is the highest 'known' ICMP type. Anything else is a mystery + * + * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently + * discarded. + */ + if (icmph->type > NR_ICMP_TYPES) { + icmp_error_log(skb, net, pf, "invalid icmp type"); + return -NF_ACCEPT; + } + + /* Need to track icmp error message? */ + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) + return NF_ACCEPT; + + return icmp_error_message(net, tmpl, skb, hooknum); +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static int icmp_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { + [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, +}; + +static int icmp_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMP_TYPE] || + !tb[CTA_PROTO_ICMP_CODE] || + !tb[CTA_PROTO_ICMP_ID]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); + + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) + return -EINVAL; + + return 0; +} + +static unsigned int icmp_nlattr_tuple_size(void) +{ + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); + + return size; +} +#endif + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) +{ + unsigned int *timeout = data; + struct nf_icmp_net *in = icmp_pernet(net); + + if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { + if (!timeout) + timeout = &in->timeout; + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; + } else if (timeout) { + /* Set default ICMP timeout. */ + *timeout = in->timeout; + } + return 0; +} + +static int +icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { + [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + +#ifdef CONFIG_SYSCTL +static struct ctl_table icmp_sysctl_table[] = { + { + .procname = "nf_conntrack_icmp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; +#endif /* CONFIG_SYSCTL */ + +static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmp_sysctl_table, + sizeof(icmp_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmp_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmp_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmp_timeout; + + return icmp_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmp_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp.pn; +} + +const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = +{ + .l3proto = PF_INET, + .l4proto = IPPROTO_ICMP, + .pkt_to_tuple = icmp_pkt_to_tuple, + .invert_tuple = icmp_invert_tuple, + .packet = icmp_packet, + .new = icmp_new, + .error = icmp_error, + .destroy = NULL, + .me = NULL, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = icmp_tuple_to_nlattr, + .nlattr_tuple_size = icmp_nlattr_tuple_size, + .nlattr_to_tuple = icmp_nlattr_to_tuple, + .nla_policy = icmp_nla_policy, +#endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmp_timeout_nlattr_to_obj, + .obj_to_nlattr = icmp_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmp_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .init_net = icmp_init_net, + .get_net_proto = icmp_get_net_proto, +}; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c new file mode 100644 index 000000000000..bed07b998a10 --- /dev/null +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -0,0 +1,387 @@ +/* + * Copyright (C)2003,2004 USAGI/WIDE Project + * + * 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. + * + * Author: + * Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> + */ + +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/in6.h> +#include <linux/icmpv6.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/ip6_checksum.h> +#include <linux/seq_file.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h> +#include <net/netfilter/nf_log.h> + +static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; + +static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple) +{ + const struct icmp6hdr *hp; + struct icmp6hdr _hdr; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return false; + tuple->dst.u.icmp.type = hp->icmp6_type; + tuple->src.u.icmp.id = hp->icmp6_identifier; + tuple->dst.u.icmp.code = hp->icmp6_code; + + return true; +} + +/* Add 1; spaces filled with 0. */ +static const u_int8_t invmap[] = { + [ICMPV6_ECHO_REQUEST - 128] = ICMPV6_ECHO_REPLY + 1, + [ICMPV6_ECHO_REPLY - 128] = ICMPV6_ECHO_REQUEST + 1, + [ICMPV6_NI_QUERY - 128] = ICMPV6_NI_REPLY + 1, + [ICMPV6_NI_REPLY - 128] = ICMPV6_NI_QUERY + 1 +}; + +static const u_int8_t noct_valid_new[] = { + [ICMPV6_MGM_QUERY - 130] = 1, + [ICMPV6_MGM_REPORT - 130] = 1, + [ICMPV6_MGM_REDUCTION - 130] = 1, + [NDISC_ROUTER_SOLICITATION - 130] = 1, + [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, + [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, + [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, + [ICMPV6_MLD2_REPORT - 130] = 1 +}; + +static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + int type = orig->dst.u.icmp.type - 128; + if (type < 0 || type >= sizeof(invmap) || !invmap[type]) + return false; + + tuple->src.u.icmp.id = orig->src.u.icmp.id; + tuple->dst.u.icmp.type = invmap[type] - 1; + tuple->dst.u.icmp.code = orig->dst.u.icmp.code; + return true; +} + +static unsigned int *icmpv6_get_timeouts(struct net *net) +{ + return &icmpv6_pernet(net)->timeout; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int icmpv6_packet(struct nf_conn *ct, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo) +{ + unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = icmpv6_get_timeouts(nf_ct_net(ct)); + + /* Do not immediately delete the connection after the first + successful reply to avoid excessive conntrackd traffic + and also to handle correctly ICMP echo reply duplicates. */ + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb, + unsigned int dataoff) +{ + static const u_int8_t valid_new[] = { + [ICMPV6_ECHO_REQUEST - 128] = 1, + [ICMPV6_NI_QUERY - 128] = 1 + }; + int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128; + + if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) { + /* Can't create a new ICMPv6 `conn' with this. */ + pr_debug("icmpv6: can't create new conn with type %u\n", + type + 128); + nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple); + return false; + } + return true; +} + +static int +icmpv6_error_message(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, + unsigned int icmp6off) +{ + struct nf_conntrack_tuple intuple, origtuple; + const struct nf_conntrack_tuple_hash *h; + const struct nf_conntrack_l4proto *inproto; + enum ip_conntrack_info ctinfo; + struct nf_conntrack_zone tmp; + + WARN_ON(skb_nfct(skb)); + + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct icmp6hdr), + PF_INET6, net, &origtuple)) { + pr_debug("icmpv6_error: Can't get tuple\n"); + return -NF_ACCEPT; + } + + /* rcu_read_lock()ed by nf_hook_thresh */ + inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum); + + /* Ordinarily, we'd expect the inverted tupleproto, but it's + been preserved inside the ICMP. */ + if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { + pr_debug("icmpv6_error: Can't invert tuple\n"); + return -NF_ACCEPT; + } + + ctinfo = IP_CT_RELATED; + + h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), + &intuple); + if (!h) { + pr_debug("icmpv6_error: no match\n"); + return -NF_ACCEPT; + } else { + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo += IP_CT_IS_REPLY; + } + + /* Update skb to refer to this connection */ + nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + return NF_ACCEPT; +} + +static void icmpv6_error_log(const struct sk_buff *skb, struct net *net, + u8 pf, const char *msg) +{ + nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg); +} + +static int +icmpv6_error(struct net *net, struct nf_conn *tmpl, + struct sk_buff *skb, unsigned int dataoff, + u8 pf, unsigned int hooknum) +{ + const struct icmp6hdr *icmp6h; + struct icmp6hdr _ih; + int type; + + icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); + if (icmp6h == NULL) { + icmpv6_error_log(skb, net, pf, "short packet"); + return -NF_ACCEPT; + } + + if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING && + nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { + icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed"); + return -NF_ACCEPT; + } + + type = icmp6h->icmp6_type - 130; + if (type >= 0 && type < sizeof(noct_valid_new) && + noct_valid_new[type]) { + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + return NF_ACCEPT; + } + + /* is not error message ? */ + if (icmp6h->icmp6_type >= 128) + return NF_ACCEPT; + + return icmpv6_error_message(net, tmpl, skb, dataoff); +} + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> +static int icmpv6_tuple_to_nlattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *t) +{ + if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) || + nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -1; +} + +static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { + [CTA_PROTO_ICMPV6_TYPE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_CODE] = { .type = NLA_U8 }, + [CTA_PROTO_ICMPV6_ID] = { .type = NLA_U16 }, +}; + +static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], + struct nf_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) + return -EINVAL; + + tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); + tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); + tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); + + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) + return -EINVAL; + + return 0; +} + +static unsigned int icmpv6_nlattr_tuple_size(void) +{ + static unsigned int size __read_mostly; + + if (!size) + size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1); + + return size; +} +#endif + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_cttimeout.h> + +static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], + struct net *net, void *data) +{ + unsigned int *timeout = data; + struct nf_icmp_net *in = icmpv6_pernet(net); + + if (!timeout) + timeout = icmpv6_get_timeouts(net); + if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) { + *timeout = + ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ; + } else { + /* Set default ICMPv6 timeout. */ + *timeout = in->timeout; + } + return 0; +} + +static int +icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) +{ + const unsigned int *timeout = data; + + if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -ENOSPC; +} + +static const struct nla_policy +icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { + [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, +}; +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + +#ifdef CONFIG_SYSCTL +static struct ctl_table icmpv6_sysctl_table[] = { + { + .procname = "nf_conntrack_icmpv6_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; +#endif /* CONFIG_SYSCTL */ + +static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, + struct nf_icmp_net *in) +{ +#ifdef CONFIG_SYSCTL + pn->ctl_table = kmemdup(icmpv6_sysctl_table, + sizeof(icmpv6_sysctl_table), + GFP_KERNEL); + if (!pn->ctl_table) + return -ENOMEM; + + pn->ctl_table[0].data = &in->timeout; +#endif + return 0; +} + +static int icmpv6_init_net(struct net *net, u_int16_t proto) +{ + struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_proto_net *pn = &in->pn; + + in->timeout = nf_ct_icmpv6_timeout; + + return icmpv6_kmemdup_sysctl_table(pn, in); +} + +static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6.pn; +} + +const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = +{ + .l3proto = PF_INET6, + .l4proto = IPPROTO_ICMPV6, + .pkt_to_tuple = icmpv6_pkt_to_tuple, + .invert_tuple = icmpv6_invert_tuple, + .packet = icmpv6_packet, + .new = icmpv6_new, + .error = icmpv6_error, +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) + .tuple_to_nlattr = icmpv6_tuple_to_nlattr, + .nlattr_tuple_size = icmpv6_nlattr_tuple_size, + .nlattr_to_tuple = icmpv6_nlattr_to_tuple, + .nla_policy = icmpv6_nla_policy, +#endif +#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) + .ctnl_timeout = { + .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, + .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, + .nlattr_max = CTA_TIMEOUT_ICMP_MAX, + .obj_size = sizeof(unsigned int), + .nla_policy = icmpv6_timeout_nla_policy, + }, +#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ + .init_net = icmpv6_init_net, + .get_net_proto = icmpv6_get_net_proto, +}; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 47b80fd0d2c3..13279f683da9 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1,12 +1,4 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * (C) 2005-2012 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. - */ - +// SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/netfilter.h> #include <linux/slab.h> @@ -32,7 +24,7 @@ #include <net/netfilter/nf_conntrack_timestamp.h> #include <linux/rculist_nulls.h> -MODULE_LICENSE("GPL"); +unsigned int nf_conntrack_net_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_PROCFS void @@ -674,6 +666,8 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) static struct pernet_operations nf_conntrack_net_ops = { .init = nf_conntrack_pernet_init, .exit_batch = nf_conntrack_pernet_exit, + .id = &nf_conntrack_net_id, + .size = sizeof(struct nf_conntrack_net), }; static int __init nf_conntrack_standalone_init(void) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 86df2a1666fd..6366f0c0b8c1 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -28,7 +28,6 @@ #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> -#include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_nat.h> @@ -743,12 +742,6 @@ 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); @@ -781,7 +774,6 @@ void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) synchronize_rcu(); nf_nat_l3proto_clean(l3proto->l3proto); - nf_ct_l3proto_module_put(l3proto->l3proto); } EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); |