diff options
Diffstat (limited to 'net/netfilter')
-rw-r--r-- | net/netfilter/Kconfig | 11 | ||||
-rw-r--r-- | net/netfilter/Makefile | 3 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 242 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_ftp.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_netlink.c | 1653 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_tcp.c | 71 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_udp.c | 10 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_standalone.c | 42 | ||||
-rw-r--r-- | net/netfilter/nfnetlink.c | 5 | ||||
-rw-r--r-- | net/netfilter/nfnetlink_log.c | 2 | ||||
-rw-r--r-- | net/netfilter/nfnetlink_queue.c | 81 |
11 files changed, 2042 insertions, 80 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index a84f922..7d55f9c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -61,8 +61,8 @@ config NF_CONNTRACK_MARK instead of the individual packets. config NF_CONNTRACK_EVENTS - bool "Connection tracking events" - depends on NF_CONNTRACK + bool "Connection tracking events (EXPERIMENTAL)" + depends on EXPERIMENTAL && NF_CONNTRACK help If this option is enabled, the connection tracking code will provide a notifier chain that can be used by other kernel code @@ -95,4 +95,11 @@ config NF_CONNTRACK_FTP To compile it as a module, choose M here. If unsure, say N. +config NF_CT_NETLINK + tristate 'Connection tracking netlink interface (EXPERIMENTAL)' + depends on EXPERIMENTAL && NF_CONNTRACK && NETFILTER_NETLINK + depends on NF_CONNTRACK!=y || NETFILTER_NETLINK!=m + help + This option enables support for a netlink-based userspace interface + endmenu diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 55f019a..cb21831 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -13,3 +13,6 @@ obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o # SCTP protocol connection tracking obj-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o + +# netlink interface for nf_conntrack +obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 1da6783..62bb509 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -82,6 +82,8 @@ unsigned int nf_ct_log_invalid; static LIST_HEAD(unconfirmed); static int nf_conntrack_vmalloc; +static unsigned int nf_conntrack_next_id = 1; +static unsigned int nf_conntrack_expect_next_id = 1; #ifdef CONFIG_NF_CONNTRACK_EVENTS struct notifier_block *nf_conntrack_chain; struct notifier_block *nf_conntrack_expect_chain; @@ -184,7 +186,7 @@ DECLARE_MUTEX(nf_ct_cache_mutex); extern struct nf_conntrack_protocol nf_conntrack_generic_protocol; struct nf_conntrack_protocol * -nf_ct_find_proto(u_int16_t l3proto, u_int8_t protocol) +__nf_ct_proto_find(u_int16_t l3proto, u_int8_t protocol) { if (unlikely(nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_generic_protocol; @@ -192,6 +194,50 @@ nf_ct_find_proto(u_int16_t l3proto, u_int8_t protocol) return nf_ct_protos[l3proto][protocol]; } +/* this is guaranteed to always return a valid protocol helper, since + * it falls back to generic_protocol */ +struct nf_conntrack_protocol * +nf_ct_proto_find_get(u_int16_t l3proto, u_int8_t protocol) +{ + struct nf_conntrack_protocol *p; + + preempt_disable(); + p = __nf_ct_proto_find(l3proto, protocol); + if (p) { + if (!try_module_get(p->me)) + p = &nf_conntrack_generic_protocol; + } + preempt_enable(); + + return p; +} + +void nf_ct_proto_put(struct nf_conntrack_protocol *p) +{ + module_put(p->me); +} + +struct nf_conntrack_l3proto * +nf_ct_l3proto_find_get(u_int16_t l3proto) +{ + struct nf_conntrack_l3proto *p; + + preempt_disable(); + p = __nf_ct_l3proto_find(l3proto); + if (p) { + if (!try_module_get(p->me)) + p = &nf_conntrack_generic_l3proto; + } + preempt_enable(); + + return p; +} + +void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p) +{ + module_put(p->me); +} + static int nf_conntrack_hash_rnd_initted; static unsigned int nf_conntrack_hash_rnd; @@ -384,7 +430,7 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, } /* nf_conntrack_expect helper functions */ -static void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) +void nf_ct_unlink_expect(struct nf_conntrack_expect *exp) { ASSERT_WRITE_LOCK(&nf_conntrack_lock); NF_CT_ASSERT(!timer_pending(&exp->timeout)); @@ -404,6 +450,33 @@ static void expectation_timed_out(unsigned long ul_expect) nf_conntrack_expect_put(exp); } +struct nf_conntrack_expect * +__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_expect *i; + + list_for_each_entry(i, &nf_conntrack_expect_list, list) { + if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) { + atomic_inc(&i->use); + return i; + } + } + return NULL; +} + +/* Just find a expectation corresponding to a tuple. */ +struct nf_conntrack_expect * +nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_expect *i; + + read_lock_bh(&nf_conntrack_lock); + i = __nf_conntrack_expect_find(tuple); + read_unlock_bh(&nf_conntrack_lock); + + return i; +} + /* If an expectation for this connection is found, it gets delete from * global list then returned. */ static struct nf_conntrack_expect * @@ -432,7 +505,7 @@ find_expectation(const struct nf_conntrack_tuple *tuple) } /* delete all expectations for this conntrack */ -static void remove_expectations(struct nf_conn *ct) +void nf_ct_remove_expectations(struct nf_conn *ct) { struct nf_conntrack_expect *i, *tmp; @@ -462,7 +535,7 @@ clean_from_lists(struct nf_conn *ct) LIST_DELETE(&nf_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]); /* Destroy all pending expectations */ - remove_expectations(ct); + nf_ct_remove_expectations(ct); } static void @@ -482,12 +555,11 @@ destroy_conntrack(struct nf_conntrack *nfct) /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to nf_conntrack_lock!!! -HW */ - l3proto = nf_ct_find_l3proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num); + l3proto = __nf_ct_l3proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num); if (l3proto && l3proto->destroy) l3proto->destroy(ct); - proto = nf_ct_find_proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num, - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); + proto = __nf_ct_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); if (proto && proto->destroy) proto->destroy(ct); @@ -499,7 +571,7 @@ destroy_conntrack(struct nf_conntrack *nfct) * except TFTP can create an expectation on the first packet, * before connection is in the list, so we need to clean here, * too. */ - remove_expectations(ct); + nf_ct_remove_expectations(ct); /* We overload first tuple to link into unconfirmed list. */ if (!nf_ct_is_confirmed(ct)) { @@ -540,7 +612,7 @@ conntrack_tuple_cmp(const struct nf_conntrack_tuple_hash *i, && nf_ct_tuple_equal(tuple, &i->tuple); } -static struct nf_conntrack_tuple_hash * +struct nf_conntrack_tuple_hash * __nf_conntrack_find(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { @@ -575,6 +647,29 @@ nf_conntrack_find_get(const struct nf_conntrack_tuple *tuple, return h; } +static void __nf_conntrack_hash_insert(struct nf_conn *ct, + unsigned int hash, + unsigned int repl_hash) +{ + ct->id = ++nf_conntrack_next_id; + list_prepend(&nf_conntrack_hash[hash], + &ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + list_prepend(&nf_conntrack_hash[repl_hash], + &ct->tuplehash[IP_CT_DIR_REPLY].list); +} + +void nf_conntrack_hash_insert(struct nf_conn *ct) +{ + unsigned int hash, repl_hash; + + hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + write_lock_bh(&nf_conntrack_lock); + __nf_conntrack_hash_insert(ct, hash, repl_hash); + write_unlock_bh(&nf_conntrack_lock); +} + /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff **pskb) @@ -621,10 +716,7 @@ __nf_conntrack_confirm(struct sk_buff **pskb) /* Remove from unconfirmed list */ list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); - list_prepend(&nf_conntrack_hash[hash], - &ct->tuplehash[IP_CT_DIR_ORIGINAL]); - list_prepend(&nf_conntrack_hash[repl_hash], - &ct->tuplehash[IP_CT_DIR_REPLY]); + __nf_conntrack_hash_insert(ct, hash, repl_hash); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ @@ -708,13 +800,41 @@ static inline int helper_cmp(const struct nf_conntrack_helper *i, } static struct nf_conntrack_helper * -nf_ct_find_helper(const struct nf_conntrack_tuple *tuple) +__nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) { return LIST_FIND(&helpers, helper_cmp, struct nf_conntrack_helper *, tuple); } +struct nf_conntrack_helper * +nf_ct_helper_find_get( const struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_helper *helper; + + /* need nf_conntrack_lock to assure that helper exists until + * try_module_get() is called */ + read_lock_bh(&nf_conntrack_lock); + + helper = __nf_ct_helper_find(tuple); + if (helper) { + /* need to increase module usage count to assure helper will + * not go away while the caller is e.g. busy putting a + * conntrack in the hash that uses the helper */ + if (!try_module_get(helper->me)) + helper = NULL; + } + + read_unlock_bh(&nf_conntrack_lock); + + return helper; +} + +void nf_ct_helper_put(struct nf_conntrack_helper *helper) +{ + module_put(helper->me); +} + static struct nf_conn * __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, @@ -744,7 +864,7 @@ __nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, /* find features needed by this conntrack. */ features = l3proto->get_features(orig); read_lock_bh(&nf_conntrack_lock); - if (nf_ct_find_helper(repl) != NULL) + if (__nf_ct_helper_find(repl) != NULL) features |= NF_CT_F_HELP; read_unlock_bh(&nf_conntrack_lock); @@ -794,7 +914,7 @@ struct nf_conn *nf_conntrack_alloc(const struct nf_conntrack_tuple *orig, { struct nf_conntrack_l3proto *l3proto; - l3proto = nf_ct_find_l3proto(orig->src.l3num); + l3proto = __nf_ct_l3proto_find(orig->src.l3num); return __nf_conntrack_alloc(orig, repl, l3proto); } @@ -853,7 +973,7 @@ init_conntrack(const struct nf_conntrack_tuple *tuple, nf_conntrack_get(&conntrack->master->ct_general); NF_CT_STAT_INC(expect_new); } else { - conntrack->helper = nf_ct_find_helper(&repl_tuple); + conntrack->helper = __nf_ct_helper_find(&repl_tuple); NF_CT_STAT_INC(new); } @@ -947,13 +1067,13 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) return NF_ACCEPT; } - l3proto = nf_ct_find_l3proto((u_int16_t)pf); + l3proto = __nf_ct_l3proto_find((u_int16_t)pf); if ((ret = l3proto->prepare(pskb, hooknum, &dataoff, &protonum)) <= 0) { DEBUGP("not prepared to track yet or error occured\n"); return -ret; } - proto = nf_ct_find_proto((u_int16_t)pf, protonum); + proto = __nf_ct_proto_find((u_int16_t)pf, protonum); /* It may be an special packet, error, unclean... * inverse of the return code tells to the netfilter @@ -1002,9 +1122,9 @@ int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig) { return nf_ct_invert_tuple(inverse, orig, - nf_ct_find_l3proto(orig->src.l3num), - nf_ct_find_proto(orig->src.l3num, - orig->dst.protonum)); + __nf_ct_l3proto_find(orig->src.l3num), + __nf_ct_proto_find(orig->src.l3num, + orig->dst.protonum)); } /* Would two expected things clash? */ @@ -1096,6 +1216,7 @@ static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp) exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ; add_timer(&exp->timeout); + exp->id = ++nf_conntrack_expect_next_id; atomic_inc(&exp->use); NF_CT_STAT_INC(expect_create); } @@ -1129,6 +1250,7 @@ static inline int refresh_timer(struct nf_conntrack_expect *i) int nf_conntrack_expect_related(struct nf_conntrack_expect *expect) { struct nf_conntrack_expect *i; + struct nf_conn *master = expect->master; int ret; DEBUGP("nf_conntrack_expect_related %p\n", related_to); @@ -1149,9 +1271,9 @@ int nf_conntrack_expect_related(struct nf_conntrack_expect *expect) } } /* Will be over limit? */ - if (expect->master->helper->max_expected && - expect->master->expecting >= expect->master->helper->max_expected) - evict_oldest_expect(expect->master); + if (master->helper->max_expected && + master->expecting >= master->helper->max_expected) + evict_oldest_expect(master); nf_conntrack_expect_insert(expect); nf_conntrack_expect_event(IPEXP_NEW, expect); @@ -1175,7 +1297,7 @@ void nf_conntrack_alter_reply(struct nf_conn *conntrack, conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply; if (!conntrack->master && conntrack->expecting == 0) - conntrack->helper = nf_ct_find_helper(newreply); + conntrack->helper = __nf_ct_helper_find(newreply); write_unlock_bh(&nf_conntrack_lock); } @@ -1200,6 +1322,19 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) return 0; } +struct nf_conntrack_helper * +__nf_conntrack_helper_find_byname(const char *name) +{ + struct nf_conntrack_helper *h; + + list_for_each_entry(h, &helpers, list) { + if (!strcmp(h->name, name)) + return h; + } + + return NULL; +} + static inline int unhelp(struct nf_conntrack_tuple_hash *i, const struct nf_conntrack_helper *me) { @@ -1283,6 +1418,51 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, nf_conntrack_event_cache(event, skb); } +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be + * in ip_conntrack_core, since we don't want the protocols to autoload + * or depend on ctnetlink */ +int nf_ct_port_tuple_to_nfattr(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + NFA_PUT(skb, CTA_PROTO_SRC_PORT, sizeof(u_int16_t), + &tuple->src.u.tcp.port); + NFA_PUT(skb, CTA_PROTO_DST_PORT, sizeof(u_int16_t), + &tuple->dst.u.tcp.port); + return 0; + +nfattr_failure: + return -1; +} + +static const size_t cta_min_proto[CTA_PROTO_MAX] = { + [CTA_PROTO_SRC_PORT-1] = sizeof(u_int16_t), + [CTA_PROTO_DST_PORT-1] = sizeof(u_int16_t) +}; + +int nf_ct_port_nfattr_to_tuple(struct nfattr *tb[], + struct nf_conntrack_tuple *t) +{ + if (!tb[CTA_PROTO_SRC_PORT-1] || !tb[CTA_PROTO_DST_PORT-1]) + return -EINVAL; + + if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto)) + return -EINVAL; + + t->src.u.tcp.port = + *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_SRC_PORT-1]); + t->dst.u.tcp.port = + *(u_int16_t *)NFA_DATA(tb[CTA_PROTO_DST_PORT-1]); + + return 0; +} +#endif + /* Used by ipt_REJECT and ip6t_REJECT. */ void __nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) { @@ -1365,6 +1545,11 @@ static void free_conntrack_hash(struct list_head *hash, int vmalloced, int size) get_order(sizeof(struct list_head) * size)); } +void nf_conntrack_flush() +{ + nf_ct_iterate_cleanup(kill_all, NULL); +} + /* Mishearing the voices in his head, our hero wonders how he's supposed to kill the mall. */ void nf_conntrack_cleanup(void) @@ -1378,11 +1563,14 @@ void nf_conntrack_cleanup(void) nf_ct_event_cache_flush(); i_see_dead_people: - nf_ct_iterate_cleanup(kill_all, NULL); + nf_conntrack_flush(); if (atomic_read(&nf_conntrack_count) != 0) { schedule(); goto i_see_dead_people; } + /* wait until all references to nf_conntrack_untracked are dropped */ + while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1) + schedule(); for (i = 0; i < NF_CT_F_NUM; i++) { if (nf_ct_cache[i].use == 0) diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 65080e26..d5a6eaf 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -44,7 +44,7 @@ static unsigned int ports_c; module_param_array(ports, ushort, &ports_c, 0400); static int loose; -module_param(loose, int, 0600); +module_param(loose, bool, 0600); unsigned int (*nf_nat_ftp_hook)(struct sk_buff **pskb, enum ip_conntrack_info ctinfo, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c new file mode 100644 index 0000000..73ab16b --- /dev/null +++ b/net/netfilter/nf_conntrack_netlink.c @@ -0,0 +1,1653 @@ +/* Connection tracking via netlink socket. Allows for user space + * protocol helpers and general trouble making from userspace. + * + * (C) 2001 by Jay Schulist <jschlst@samba.org> + * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> + * (C) 2003 by Patrick Mchardy <kaber@trash.net> + * (C) 2005 by Pablo Neira Ayuso <pablo@eurodev.net> + * + * I've reworked this stuff to use attributes instead of conntrack + * structures. 5.44 am. I need more tea. --pablo 05/07/11. + * + * Initial connection tracking via netlink development funded and + * generally made possible by Network Robots, Inc. (www.networkrobots.com) + * + * Further development of this code funded by Astaro AG (http://www.astaro.com) + * + * This software may be used and distributed according to the terms + * of the GNU General Public License, incorporated herein by reference. + * + * Derived from ip_conntrack_netlink.c: Port by Pablo Neira Ayuso (05/11/14) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/netlink.h> +#include <linux/spinlock.h> +#include <linux/notifier.h> + +#include <linux/netfilter.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_l3proto.h> +#include <net/netfilter/nf_conntrack_protocol.h> +#include <linux/netfilter_ipv4/ip_nat_protocol.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +MODULE_LICENSE("GPL"); + +static char __initdata version[] = "0.92"; + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + + +static inline int +ctnetlink_dump_tuples_proto(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_protocol *proto; + int ret = 0; + + NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum); + + /* If no protocol helper is found, this function will return the + * generic protocol helper, so proto won't *ever* be NULL */ + proto = nf_ct_proto_find_get(tuple->src.l3num, tuple->dst.protonum); + if (likely(proto->tuple_to_nfattr)) + ret = proto->tuple_to_nfattr(skb, tuple); + + nf_ct_proto_put(proto); + + return ret; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_tuples(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple) +{ + struct nfattr *nest_parms; + struct nf_conntrack_l3proto *l3proto; + int ret = 0; + + l3proto = nf_ct_l3proto_find_get(tuple->src.l3num); + + nest_parms = NFA_NEST(skb, CTA_TUPLE_IP); + if (likely(l3proto->tuple_to_nfattr)) + ret = l3proto->tuple_to_nfattr(skb, tuple); + NFA_NEST_END(skb, nest_parms); + + nf_ct_l3proto_put(l3proto); + + if (unlikely(ret < 0)) + return ret; + + nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO); + ret = ctnetlink_dump_tuples_proto(skb, tuple); + NFA_NEST_END(skb, nest_parms); + + return ret; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) +{ + u_int32_t status = htonl((u_int32_t) ct->status); + NFA_PUT(skb, CTA_STATUS, sizeof(status), &status); + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) +{ + long timeout_l = ct->timeout.expires - jiffies; + u_int32_t timeout; + + if (timeout_l < 0) + timeout = 0; + else + timeout = htonl(timeout_l / HZ); + + NFA_PUT(skb, CTA_TIMEOUT, sizeof(timeout), &timeout); + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nf_conntrack_protocol *proto = nf_ct_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num, ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum); + struct nfattr *nest_proto; + int ret; + + if (!proto->to_nfattr) { + nf_ct_proto_put(proto); + return 0; + } + + nest_proto = NFA_NEST(skb, CTA_PROTOINFO); + + ret = proto->to_nfattr(skb, nest_proto, ct); + + nf_ct_proto_put(proto); + + NFA_NEST_END(skb, nest_proto); + + return ret; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nfattr *nest_helper; + + if (!ct->helper) + return 0; + + nest_helper = NFA_NEST(skb, CTA_HELP); + NFA_PUT(skb, CTA_HELP_NAME, strlen(ct->helper->name), ct->helper->name); + + if (ct->helper->to_nfattr) + ct->helper->to_nfattr(skb, ct); + + NFA_NEST_END(skb, nest_helper); + + return 0; + +nfattr_failure: + return -1; +} + +#ifdef CONFIG_NF_CT_ACCT +static inline int +ctnetlink_dump_counters(struct sk_buff *skb, const struct nf_conn *ct, + enum ip_conntrack_dir dir) +{ + enum ctattr_type type = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; + struct nfattr *nest_count = NFA_NEST(skb, type); + u_int32_t tmp; + + tmp = htonl(ct->counters[dir].packets); + NFA_PUT(skb, CTA_COUNTERS32_PACKETS, sizeof(u_int32_t), &tmp); + + tmp = htonl(ct->counters[dir].bytes); + NFA_PUT(skb, CTA_COUNTERS32_BYTES, sizeof(u_int32_t), &tmp); + + NFA_NEST_END(skb, nest_count); + + return 0; + +nfattr_failure: + return -1; +} +#else +#define ctnetlink_dump_counters(a, b, c) (0) +#endif + +#ifdef CONFIG_NF_CONNTRACK_MARK +static inline int +ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +{ + u_int32_t mark = htonl(ct->mark); + + NFA_PUT(skb, CTA_MARK, sizeof(u_int32_t), &mark); + return 0; + +nfattr_failure: + return -1; +} +#else +#define ctnetlink_dump_mark(a, b) (0) +#endif + +static inline int +ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) +{ + u_int32_t id = htonl(ct->id); + NFA_PUT(skb, CTA_ID, sizeof(u_int32_t), &id); + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) +{ + u_int32_t use = htonl(atomic_read(&ct->ct_general.use)); + + NFA_PUT(skb, CTA_USE, sizeof(u_int32_t), &use); + return 0; + +nfattr_failure: + return -1; +} + +#define tuple(ct, dir) (&(ct)->tuplehash[dir].tuple) + +static int +ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, + int event, int nowait, + const struct nf_conn *ct) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + struct nfattr *nest_parms; + unsigned char *b; + + b = skb->tail; + + event |= NFNL_SUBSYS_CTNETLINK << 8; + nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg)); + nfmsg = NLMSG_DATA(nlh); + + nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; + nfmsg->nfgen_family = + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG); + if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + goto nfattr_failure; + NFA_NEST_END(skb, nest_parms); + + nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY); + if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) + goto nfattr_failure; + NFA_NEST_END(skb, nest_parms); + + if (ctnetlink_dump_status(skb, ct) < 0 || + ctnetlink_dump_timeout(skb, ct) < 0 || + ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || + ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 || + ctnetlink_dump_protoinfo(skb, ct) < 0 || + ctnetlink_dump_helpinfo(skb, ct) < 0 || + ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_id(skb, ct) < 0 || + ctnetlink_dump_use(skb, ct) < 0) + goto nfattr_failure; + + nlh->nlmsg_len = skb->tail - b; + return skb->len; + +nlmsg_failure: +nfattr_failure: + skb_trim(skb, b - skb->data); + return -1; +} + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +static int ctnetlink_conntrack_event(struct notifier_block *this, + unsigned long events, void *ptr) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + struct nfattr *nest_parms; + struct nf_conn *ct = (struct nf_conn *)ptr; + struct sk_buff *skb; + unsigned int type; + unsigned char *b; + unsigned int flags = 0, group; + + /* ignore our fake conntrack entry */ + if (ct == &nf_conntrack_untracked) + return NOTIFY_DONE; + + if (events & IPCT_DESTROY) { + type = IPCTNL_MSG_CT_DELETE; + group = NFNLGRP_CONNTRACK_DESTROY; + } else if (events & (IPCT_NEW | IPCT_RELATED)) { + type = IPCTNL_MSG_CT_NEW; + flags = NLM_F_CREATE|NLM_F_EXCL; + /* dump everything */ + events = ~0UL; + group = NFNLGRP_CONNTRACK_NEW; + } else if (events & (IPCT_STATUS | + IPCT_PROTOINFO | + IPCT_HELPER | + IPCT_HELPINFO | + IPCT_NATINFO)) { + type = IPCTNL_MSG_CT_NEW; + group = NFNLGRP_CONNTRACK_UPDATE; + } else + return NOTIFY_DONE; + + /* FIXME: Check if there are any listeners before, don't hurt performance */ + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!skb) + return NOTIFY_DONE; + + b = skb->tail; + + type |= NFNL_SUBSYS_CTNETLINK << 8; + nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); + nfmsg = NLMSG_DATA(nlh); + + nlh->nlmsg_flags = flags; + nfmsg->nfgen_family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + nest_parms = NFA_NEST(skb, CTA_TUPLE_ORIG); + if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) + goto nfattr_failure; + NFA_NEST_END(skb, nest_parms); + + nest_parms = NFA_NEST(skb, CTA_TUPLE_REPLY); + if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0) + goto nfattr_failure; + NFA_NEST_END(skb, nest_parms); + + /* NAT stuff is now a status flag */ + if ((events & IPCT_STATUS || events & IPCT_NATINFO) + && ctnetlink_dump_status(skb, ct) < 0) + goto nfattr_failure; + if (events & IPCT_REFRESH + && ctnetlink_dump_timeout(skb, ct) < 0) + goto nfattr_failure; + if (events & IPCT_PROTOINFO + && ctnetlink_dump_protoinfo(skb, ct) < 0) + goto nfattr_failure; + if (events & IPCT_HELPINFO + && ctnetlink_dump_helpinfo(skb, ct) < 0) + goto nfattr_failure; + + if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || + ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) + goto nfattr_failure; + + nlh->nlmsg_len = skb->tail - b; + nfnetlink_send(skb, 0, group, 0); + return NOTIFY_DONE; + +nlmsg_failure: +nfattr_failure: + kfree_skb(skb); + return NOTIFY_DONE; +} +#endif /* CONFIG_NF_CONNTRACK_EVENTS */ + +static int ctnetlink_done(struct netlink_callback *cb) +{ + DEBUGP("entered %s\n", __FUNCTION__); + return 0; +} + +#define L3PROTO(ct) ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num + +static int +ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nf_conn *ct = NULL; + struct nf_conntrack_tuple_hash *h; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[1]; + struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); + u_int8_t l3proto = nfmsg->nfgen_family; + + DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, + cb->args[0], *id); + + read_lock_bh(&nf_conntrack_lock); + for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++, *id = 0) { + list_for_each_prev(i, &nf_conntrack_hash[cb->args[0]]) { + h = (struct nf_conntrack_tuple_hash *) i; + if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = nf_ct_tuplehash_to_ctrack(h); + /* Dump entries of a given L3 protocol number. + * If it is not specified, ie. l3proto == 0, + * then dump everything. */ + if (l3proto && L3PROTO(ct) != l3proto) + continue; + if (ct->id <= *id) + continue; + if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + IPCTNL_MSG_CT_NEW, + 1, ct) < 0) + goto out; + *id = ct->id; + } + } +out: + read_unlock_bh(&nf_conntrack_lock); + + DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); + + return skb->len; +} + +#ifdef CONFIG_NF_CT_ACCT +static int +ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nf_conn *ct = NULL; + struct nf_conntrack_tuple_hash *h; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[1]; + struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); + u_int8_t l3proto = nfmsg->nfgen_family; + + DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, + cb->args[0], *id); + + write_lock_bh(&nf_conntrack_lock); + for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++, *id = 0) { + list_for_each_prev(i, &nf_conntrack_hash[cb->args[0]]) { + h = (struct nf_conntrack_tuple_hash *) i; + if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = nf_ct_tuplehash_to_ctrack(h); + if (l3proto && L3PROTO(ct) != l3proto) + continue; + if (ct->id <= *id) + continue; + if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + IPCTNL_MSG_CT_NEW, + 1, ct) < 0) + goto out; + *id = ct->id; + + memset(&ct->counters, 0, sizeof(ct->counters)); + } + } +out: + write_unlock_bh(&nf_conntrack_lock); + + DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); + + return skb->len; +} +#endif + +static inline int +ctnetlink_parse_tuple_ip(struct nfattr *attr, struct nf_conntrack_tuple *tuple) +{ + struct nfattr *tb[CTA_IP_MAX]; + struct nf_conntrack_l3proto *l3proto; + int ret = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + nfattr_parse_nested(tb, CTA_IP_MAX, attr); + + l3proto = nf_ct_l3proto_find_get(tuple->src.l3num); + + if (likely(l3proto->nfattr_to_tuple)) + ret = l3proto->nfattr_to_tuple(tb, tuple); + + nf_ct_l3proto_put(l3proto); + + DEBUGP("leaving\n"); + + return ret; +} + +static const size_t cta_min_proto[CTA_PROTO_MAX] = { + [CTA_PROTO_NUM-1] = sizeof(u_int8_t), +}; + +static inline int +ctnetlink_parse_tuple_proto(struct nfattr *attr, + struct nf_conntrack_tuple *tuple) +{ + struct nfattr *tb[CTA_PROTO_MAX]; + struct nf_conntrack_protocol *proto; + int ret = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + nfattr_parse_nested(tb, CTA_PROTO_MAX, attr); + + if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto)) + return -EINVAL; + + if (!tb[CTA_PROTO_NUM-1]) + return -EINVAL; + tuple->dst.protonum = *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_NUM-1]); + + proto = nf_ct_proto_find_get(tuple->src.l3num, tuple->dst.protonum); + + if (likely(proto->nfattr_to_tuple)) + ret = proto->nfattr_to_tuple(tb, tuple); + + nf_ct_proto_put(proto); + + return ret; +} + +static inline int +ctnetlink_parse_tuple(struct nfattr *cda[], struct nf_conntrack_tuple *tuple, + enum ctattr_tuple type, u_int8_t l3num) +{ + struct nfattr *tb[CTA_TUPLE_MAX]; + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + memset(tuple, 0, sizeof(*tuple)); + + nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]); + + if (!tb[CTA_TUPLE_IP-1]) + return -EINVAL; + + tuple->src.l3num = l3num; + + err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP-1], tuple); + if (err < 0) + return err; + + if (!tb[CTA_TUPLE_PROTO-1]) + return -EINVAL; + + err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO-1], tuple); + if (err < 0) + return err; + + /* orig and expect tuples get DIR_ORIGINAL */ + if (type == CTA_TUPLE_REPLY) + tuple->dst.dir = IP_CT_DIR_REPLY; + else + tuple->dst.dir = IP_CT_DIR_ORIGINAL; + + NF_CT_DUMP_TUPLE(tuple); + + DEBUGP("leaving\n"); + + return 0; +} + +#ifdef CONFIG_IP_NF_NAT_NEEDED +static const size_t cta_min_protonat[CTA_PROTONAT_MAX] = { + [CTA_PROTONAT_PORT_MIN-1] = sizeof(u_int16_t), + [CTA_PROTONAT_PORT_MAX-1] = sizeof(u_int16_t), +}; + +static int ctnetlink_parse_nat_proto(struct nfattr *attr, + const struct nf_conn *ct, + struct ip_nat_range *range) +{ + struct nfattr *tb[CTA_PROTONAT_MAX]; + struct ip_nat_protocol *npt; + + DEBUGP("entered %s\n", __FUNCTION__); + + nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr); + + if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat)) + return -EINVAL; + + npt = ip_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum); + + if (!npt->nfattr_to_range) { + ip_nat_proto_put(npt); + return 0; + } + + /* nfattr_to_range returns 1 if it parsed, 0 if not, neg. on error */ + if (npt->nfattr_to_range(tb, range) > 0) + range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED; + + ip_nat_proto_put(npt); + + DEBUGP("leaving\n"); + return 0; +} + +static const size_t cta_min_nat[CTA_NAT_MAX] = { + [CTA_NAT_MINIP-1] = sizeof(u_int32_t), + [CTA_NAT_MAXIP-1] = sizeof(u_int32_t), +}; + +static inline int +ctnetlink_parse_nat(struct nfattr *cda[], + const struct nf_conn *ct, struct ip_nat_range *range) +{ + struct nfattr *tb[CTA_NAT_MAX]; + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + memset(range, 0, sizeof(*range)); + + nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]); + + if (nfattr_bad_size(tb, CTA_NAT_MAX, cta_min_nat)) + return -EINVAL; + + if (tb[CTA_NAT_MINIP-1]) + range->min_ip = *(u_int32_t *)NFA_DATA(tb[CTA_NAT_MINIP-1]); + + if (!tb[CTA_NAT_MAXIP-1]) + range->max_ip = range->min_ip; + else + range->max_ip = *(u_int32_t *)NFA_DATA(tb[CTA_NAT_MAXIP-1]); + + if (range->min_ip) + range->flags |= IP_NAT_RANGE_MAP_IPS; + + if (!tb[CTA_NAT_PROTO-1]) + return 0; + + err = ctnetlink_parse_nat_proto(tb[CTA_NAT_PROTO-1], ct, range); + if (err < 0) + return err; + + DEBUGP("leaving\n"); + return 0; +} +#endif + +static inline int +ctnetlink_parse_help(struct nfattr *attr, char **helper_name) +{ + struct nfattr *tb[CTA_HELP_MAX]; + + DEBUGP("entered %s\n", __FUNCTION__); + + nfattr_parse_nested(tb, CTA_HELP_MAX, attr); + + if (!tb[CTA_HELP_NAME-1]) + return -EINVAL; + + *helper_name = NFA_DATA(tb[CTA_HELP_NAME-1]); + + return 0; +} + +static const size_t cta_min[CTA_MAX] = { + [CTA_STATUS-1] = sizeof(u_int32_t), + [CTA_TIMEOUT-1] = sizeof(u_int32_t), + [CTA_MARK-1] = sizeof(u_int32_t), + [CTA_USE-1] = sizeof(u_int32_t), + [CTA_ID-1] = sizeof(u_int32_t) +}; + +static int +ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_tuple tuple; + struct nf_conn *ct; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_bad_size(cda, CTA_MAX, cta_min)) + return -EINVAL; + + if (cda[CTA_TUPLE_ORIG-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); + else if (cda[CTA_TUPLE_REPLY-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); + else { + /* Flush the whole table */ + nf_conntrack_flush(); + return 0; + } + + if (err < 0) + return err; + + h = nf_conntrack_find_get(&tuple, NULL); + if (!h) { + DEBUGP("tuple not found in conntrack hash\n"); + return -ENOENT; + } + + ct = nf_ct_tuplehash_to_ctrack(h); + + if (cda[CTA_ID-1]) { + u_int32_t id = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_ID-1])); + if (ct->id != id) { + nf_ct_put(ct); + return -ENOENT; + } + } + if (del_timer(&ct->timeout)) + ct->timeout.function((unsigned long)ct); + + nf_ct_put(ct); + DEBUGP("leaving\n"); + + return 0; +} + +static int +ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_tuple tuple; + struct nf_conn *ct; + struct sk_buff *skb2 = NULL; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + u32 rlen; + + if (NFNL_MSG_TYPE(nlh->nlmsg_type) == + IPCTNL_MSG_CT_GET_CTRZERO) { +#ifdef CONFIG_NF_CT_ACCT + if ((*errp = netlink_dump_start(ctnl, skb, nlh, + ctnetlink_dump_table_w, + ctnetlink_done)) != 0) + return -EINVAL; +#else + return -ENOTSUPP; +#endif + } else { + if ((*errp = netlink_dump_start(ctnl, skb, nlh, + ctnetlink_dump_table, + ctnetlink_done)) != 0) + return -EINVAL; + } + + rlen = NLMSG_ALIGN(nlh->nlmsg_len); + if (rlen > skb->len) + rlen = skb->len; + skb_pull(skb, rlen); + return 0; + } + + if (nfattr_bad_size(cda, CTA_MAX, cta_min)) + return -EINVAL; + + if (cda[CTA_TUPLE_ORIG-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3); + else if (cda[CTA_TUPLE_REPLY-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3); + else + return -EINVAL; + + if (err < 0) + return err; + + h = nf_conntrack_find_get(&tuple, NULL); + if (!h) { + DEBUGP("tuple not found in conntrack hash"); + return -ENOENT; + } + DEBUGP("tuple found\n"); + ct = nf_ct_tuplehash_to_ctrack(h); + + err = -ENOMEM; + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb2) { + nf_ct_put(ct); + return -ENOMEM; + } + NETLINK_CB(skb2).dst_pid = NETLINK_CB(skb).pid; + + err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, + IPCTNL_MSG_CT_NEW, 1, ct); + nf_ct_put(ct); + if (err <= 0) + goto free; + + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto out; + + DEBUGP("leaving\n"); + return 0; + +free: + kfree_skb(skb2); +out: + return err; +} + +static inline int +ctnetlink_change_status(struct nf_conn *ct, struct nfattr *cda[]) +{ + unsigned long d; + unsigned status = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_STATUS-1])); + d = ct->status ^ status; + + if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) + /* unchangeable */ + return -EINVAL; + + if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) + /* SEEN_REPLY bit can only be set */ + return -EINVAL; + + + if (d & IPS_ASSURED && !(status & IPS_ASSURED)) + /* ASSURED bit can only be set */ + return -EINVAL; + + if (cda[CTA_NAT-1]) { +#ifndef CONFIG_IP_NF_NAT_NEEDED + return -EINVAL; +#else + unsigned int hooknum; + struct ip_nat_range range; + + if (ctnetlink_parse_nat(cda, ct, &range) < 0) + return -EINVAL; + + DEBUGP("NAT: %u.%u.%u.%u-%u.%u.%u.%u:%u-%u\n", + NIPQUAD(range.min_ip), NIPQUAD(range.max_ip), + htons(range.min.all), htons(range.max.all)); + + /* This is tricky but it works. ip_nat_setup_info needs the + * hook number as parameter, so let's do the correct + * conversion and run away */ + if (status & IPS_SRC_NAT_DONE) + hooknum = NF_IP_POST_ROUTING; /* IP_NAT_MANIP_SRC */ + else if (status & IPS_DST_NAT_DONE) + hooknum = NF_IP_PRE_ROUTING; /* IP_NAT_MANIP_DST */ + else + return -EINVAL; /* Missing NAT flags */ + + DEBUGP("NAT status: %lu\n", + status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK)); + + if (ip_nat_initialized(ct, HOOK2MANIP(hooknum))) + return -EEXIST; + ip_nat_setup_info(ct, &range, hooknum); + + DEBUGP("NAT status after setup_info: %lu\n", + ct->status & (IPS_NAT_MASK | IPS_NAT_DONE_MASK)); +#endif + } + + /* Be careful here, modifying NAT bits can screw up things, + * so don't let users modify them directly if they don't pass + * ip_nat_range. */ + ct->status |= status & ~(IPS_NAT_DONE_MASK | IPS_NAT_MASK); + return 0; +} + + +static inline int +ctnetlink_change_helper(struct nf_conn *ct, struct nfattr *cda[]) +{ + struct nf_conntrack_helper *helper; + char *helpname; + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + /* don't change helper of sibling connections */ + if (ct->master) + return -EINVAL; + + err = ctnetlink_parse_help(cda[CTA_HELP-1], &helpname); + if (err < 0) + return err; + + helper = __nf_conntrack_helper_find_byname(helpname); + if (!helper) { + if (!strcmp(helpname, "")) + helper = NULL; + else + return -EINVAL; + } + + if (ct->helper) { + if (!helper) { + /* we had a helper before ... */ + nf_ct_remove_expectations(ct); + ct->helper = NULL; + } else { + /* need to zero data of old helper */ + memset(&ct->help, 0, sizeof(ct->help)); + } + } + + ct->helper = helper; + + return 0; +} + +static inline int +ctnetlink_change_timeout(struct nf_conn *ct, struct nfattr *cda[]) +{ + u_int32_t timeout = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_TIMEOUT-1])); + + if (!del_timer(&ct->timeout)) + return -ETIME; + + ct->timeout.expires = jiffies + timeout * HZ; + add_timer(&ct->timeout); + + return 0; +} + +static inline int +ctnetlink_change_protoinfo(struct nf_conn *ct, struct nfattr *cda[]) +{ + struct nfattr *tb[CTA_PROTOINFO_MAX], *attr = cda[CTA_PROTOINFO-1]; + struct nf_conntrack_protocol *proto; + u_int16_t npt = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum; + u_int16_t l3num = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + int err = 0; + + nfattr_parse_nested(tb, CTA_PROTOINFO_MAX, attr); + + proto = nf_ct_proto_find_get(l3num, npt); + + if (proto->from_nfattr) + err = proto->from_nfattr(tb, ct); + nf_ct_proto_put(proto); + + return err; +} + +static int +ctnetlink_change_conntrack(struct nf_conn *ct, struct nfattr *cda[]) +{ + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (cda[CTA_HELP-1]) { + err = ctnetlink_change_helper(ct, cda); + if (err < 0) + return err; + } + + if (cda[CTA_TIMEOUT-1]) { + err = ctnetlink_change_timeout(ct, cda); + if (err < 0) + return err; + } + + if (cda[CTA_STATUS-1]) { + err = ctnetlink_change_status(ct, cda); + if (err < 0) + return err; + } + + if (cda[CTA_PROTOINFO-1]) { + err = ctnetlink_change_protoinfo(ct, cda); + if (err < 0) + return err; + } + +#if defined(CONFIG_IP_NF_CONNTRACK_MARK) + if (cda[CTA_MARK-1]) + ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); +#endif + + DEBUGP("all done\n"); + return 0; +} + +static int +ctnetlink_create_conntrack(struct nfattr *cda[], + struct nf_conntrack_tuple *otuple, + struct nf_conntrack_tuple *rtuple) +{ + struct nf_conn *ct; + int err = -EINVAL; + + DEBUGP("entered %s\n", __FUNCTION__); + + ct = nf_conntrack_alloc(otuple, rtuple); + if (ct == NULL || IS_ERR(ct)) + return -ENOMEM; + + if (!cda[CTA_TIMEOUT-1]) + goto err; + ct->timeout.expires = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_TIMEOUT-1])); + + ct->timeout.expires = jiffies + ct->timeout.expires * HZ; + ct->status |= IPS_CONFIRMED; + + err = ctnetlink_change_status(ct, cda); + if (err < 0) + goto err; + + if (cda[CTA_PROTOINFO-1]) { + err = ctnetlink_change_protoinfo(ct, cda); + if (err < 0) + return err; + } + +#if defined(CONFIG_IP_NF_CONNTRACK_MARK) + if (cda[CTA_MARK-1]) + ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1])); +#endif + + ct->helper = nf_ct_helper_find_get(rtuple); + + add_timer(&ct->timeout); + nf_conntrack_hash_insert(ct); + + if (ct->helper) + nf_ct_helper_put(ct->helper); + + DEBUGP("conntrack with id %u inserted\n", ct->id); + return 0; + +err: + nf_conntrack_free(ct); + return err; +} + +static int +ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_tuple otuple, rtuple; + struct nf_conntrack_tuple_hash *h = NULL; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_bad_size(cda, CTA_MAX, cta_min)) + return -EINVAL; + + if (cda[CTA_TUPLE_ORIG-1]) { + err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3); + if (err < 0) + return err; + } + + if (cda[CTA_TUPLE_REPLY-1]) { + err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3); + if (err < 0) + return err; + } + + write_lock_bh(&nf_conntrack_lock); + if (cda[CTA_TUPLE_ORIG-1]) + h = __nf_conntrack_find(&otuple, NULL); + else if (cda[CTA_TUPLE_REPLY-1]) + h = __nf_conntrack_find(&rtuple, NULL); + + if (h == NULL) { + write_unlock_bh(&nf_conntrack_lock); + DEBUGP("no such conntrack, create new\n"); + err = -ENOENT; + if (nlh->nlmsg_flags & NLM_F_CREATE) + err = ctnetlink_create_conntrack(cda, &otuple, &rtuple); + return err; + } + /* implicit 'else' */ + + /* we only allow nat config for new conntracks */ + if (cda[CTA_NAT-1]) { + err = -EINVAL; + goto out_unlock; + } + + /* We manipulate the conntrack inside the global conntrack table lock, + * so there's no need to increase the refcount */ + DEBUGP("conntrack found\n"); + err = -EEXIST; + if (!(nlh->nlmsg_flags & NLM_F_EXCL)) + err = ctnetlink_change_conntrack(nf_ct_tuplehash_to_ctrack(h), cda); + +out_unlock: + write_unlock_bh(&nf_conntrack_lock); + return err; +} + +/*********************************************************************** + * EXPECT + ***********************************************************************/ + +static inline int +ctnetlink_exp_dump_tuple(struct sk_buff *skb, + const struct nf_conntrack_tuple *tuple, + enum ctattr_expect type) +{ + struct nfattr *nest_parms = NFA_NEST(skb, type); + + if (ctnetlink_dump_tuples(skb, tuple) < 0) + goto nfattr_failure; + + NFA_NEST_END(skb, nest_parms); + + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_exp_dump_expect(struct sk_buff *skb, + const struct nf_conntrack_expect *exp) +{ + struct nf_conn *master = exp->master; + u_int32_t timeout = htonl((exp->timeout.expires - jiffies) / HZ); + u_int32_t id = htonl(exp->id); + + if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) + goto nfattr_failure; + if (ctnetlink_exp_dump_tuple(skb, &exp->mask, CTA_EXPECT_MASK) < 0) + goto nfattr_failure; + if (ctnetlink_exp_dump_tuple(skb, + &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + CTA_EXPECT_MASTER) < 0) + goto nfattr_failure; + + NFA_PUT(skb, CTA_EXPECT_TIMEOUT, sizeof(timeout), &timeout); + NFA_PUT(skb, CTA_EXPECT_ID, sizeof(u_int32_t), &id); + + return 0; + +nfattr_failure: + return -1; +} + +static int +ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, + int event, + int nowait, + const struct nf_conntrack_expect *exp) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + unsigned char *b; + + b = skb->tail; + + event |= NFNL_SUBSYS_CTNETLINK_EXP << 8; + nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg)); + nfmsg = NLMSG_DATA(nlh); + + nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0; + nfmsg->nfgen_family = exp->tuple.src.l3num; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (ctnetlink_exp_dump_expect(skb, exp) < 0) + goto nfattr_failure; + + nlh->nlmsg_len = skb->tail - b; + return skb->len; + +nlmsg_failure: +nfattr_failure: + skb_trim(skb, b - skb->data); + return -1; +} + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +static int ctnetlink_expect_event(struct notifier_block *this, + unsigned long events, void *ptr) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + struct nf_conntrack_expect *exp = (struct nf_conntrack_expect *)ptr; + struct sk_buff *skb; + unsigned int type; + unsigned char *b; + int flags = 0; + + if (events & IPEXP_NEW) { + type = IPCTNL_MSG_EXP_NEW; + flags = NLM_F_CREATE|NLM_F_EXCL; + } else + return NOTIFY_DONE; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!skb) + return NOTIFY_DONE; + + b = skb->tail; + + type |= NFNL_SUBSYS_CTNETLINK << 8; + nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); + nfmsg = NLMSG_DATA(nlh); + + nlh->nlmsg_flags = flags; + nfmsg->nfgen_family = exp->tuple.src.l3num; + nfmsg->version = NFNETLINK_V0; + nfmsg->res_id = 0; + + if (ctnetlink_exp_dump_expect(skb, exp) < 0) + goto nfattr_failure; + + nlh->nlmsg_len = skb->tail - b; + nfnetlink_send(skb, 0, NFNLGRP_CONNTRACK_EXP_NEW, 0); + return NOTIFY_DONE; + +nlmsg_failure: +nfattr_failure: + kfree_skb(skb); + return NOTIFY_DONE; +} +#endif + +static int +ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct nf_conntrack_expect *exp = NULL; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[0]; + struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh); + u_int8_t l3proto = nfmsg->nfgen_family; + + DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id); + + read_lock_bh(&nf_conntrack_lock); + list_for_each_prev(i, &nf_conntrack_expect_list) { + exp = (struct nf_conntrack_expect *) i; + if (l3proto && exp->tuple.src.l3num != l3proto) + continue; + if (exp->id <= *id) + continue; + if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + IPCTNL_MSG_EXP_NEW, + 1, exp) < 0) + goto out; + *id = exp->id; + } +out: + read_unlock_bh(&nf_conntrack_lock); + + DEBUGP("leaving, last id=%llu\n", *id); + + return skb->len; +} + +static const size_t cta_min_exp[CTA_EXPECT_MAX] = { + [CTA_EXPECT_TIMEOUT-1] = sizeof(u_int32_t), + [CTA_EXPECT_ID-1] = sizeof(u_int32_t) +}; + +static int +ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_tuple tuple; + struct nf_conntrack_expect *exp; + struct sk_buff *skb2; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) + return -EINVAL; + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + u32 rlen; + + if ((*errp = netlink_dump_start(ctnl, skb, nlh, + ctnetlink_exp_dump_table, + ctnetlink_done)) != 0) + return -EINVAL; + rlen = NLMSG_ALIGN(nlh->nlmsg_len); + if (rlen > skb->len) + rlen = skb->len; + skb_pull(skb, rlen); + return 0; + } + + if (cda[CTA_EXPECT_MASTER-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3); + else + return -EINVAL; + + if (err < 0) + return err; + + exp = nf_conntrack_expect_find(&tuple); + if (!exp) + return -ENOENT; + + if (cda[CTA_EXPECT_ID-1]) { + u_int32_t id = *(u_int32_t *)NFA_DATA(cda[CTA_EXPECT_ID-1]); + if (exp->id != ntohl(id)) { + nf_conntrack_expect_put(exp); + return -ENOENT; + } + } + + err = -ENOMEM; + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb2) + goto out; + NETLINK_CB(skb2).dst_pid = NETLINK_CB(skb).pid; + + err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, + nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, + 1, exp); + if (err <= 0) + goto free; + + nf_conntrack_expect_put(exp); + + return netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + +free: + kfree_skb(skb2); +out: + nf_conntrack_expect_put(exp); + return err; +} + +static int +ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_expect *exp, *tmp; + struct nf_conntrack_tuple tuple; + struct nf_conntrack_helper *h; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err; + + if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) + return -EINVAL; + + if (cda[CTA_EXPECT_TUPLE-1]) { + /* delete a single expect by tuple */ + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + if (err < 0) + return err; + + /* bump usage count to 2 */ + exp = nf_conntrack_expect_find(&tuple); + if (!exp) + return -ENOENT; + + if (cda[CTA_EXPECT_ID-1]) { + u_int32_t id = + *(u_int32_t *)NFA_DATA(cda[CTA_EXPECT_ID-1]); + if (exp->id != ntohl(id)) { + nf_conntrack_expect_put(exp); + return -ENOENT; + } + } + + /* after list removal, usage count == 1 */ + nf_conntrack_unexpect_related(exp); + /* have to put what we 'get' above. + * after this line usage count == 0 */ + nf_conntrack_expect_put(exp); + } else if (cda[CTA_EXPECT_HELP_NAME-1]) { + char *name = NFA_DATA(cda[CTA_EXPECT_HELP_NAME-1]); + + /* delete all expectations for this helper */ + write_lock_bh(&nf_conntrack_lock); + h = __nf_conntrack_helper_find_byname(name); + if (!h) { + write_unlock_bh(&nf_conntrack_lock); + return -EINVAL; + } + list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, + list) { + if (exp->master->helper == h + && del_timer(&exp->timeout)) { + nf_ct_unlink_expect(exp); + nf_conntrack_expect_put(exp); + } + } + write_unlock_bh(&nf_conntrack_lock); + } else { + /* This basically means we have to flush everything*/ + write_lock_bh(&nf_conntrack_lock); + list_for_each_entry_safe(exp, tmp, &nf_conntrack_expect_list, + list) { + if (del_timer(&exp->timeout)) { + nf_ct_unlink_expect(exp); + nf_conntrack_expect_put(exp); + } + } + write_unlock_bh(&nf_conntrack_lock); + } + + return 0; +} +static int +ctnetlink_change_expect(struct nf_conntrack_expect *x, struct nfattr *cda[]) +{ + return -EOPNOTSUPP; +} + +static int +ctnetlink_create_expect(struct nfattr *cda[], u_int8_t u3) +{ + struct nf_conntrack_tuple tuple, mask, master_tuple; + struct nf_conntrack_tuple_hash *h = NULL; + struct nf_conntrack_expect *exp; + struct nf_conn *ct; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + /* caller guarantees that those three CTA_EXPECT_* exist */ + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3); + if (err < 0) + return err; + + /* Look for master conntrack of this expectation */ + h = nf_conntrack_find_get(&master_tuple, NULL); + if (!h) + return -ENOENT; + ct = nf_ct_tuplehash_to_ctrack(h); + + if (!ct->helper) { + /* such conntrack hasn't got any helper, abort */ + err = -EINVAL; + goto out; + } + + exp = nf_conntrack_expect_alloc(ct); + if (!exp) { + err = -ENOMEM; + goto out; + } + + exp->expectfn = NULL; + exp->flags = 0; + exp->master = ct; + memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple)); + memcpy(&exp->mask, &mask, sizeof(struct nf_conntrack_tuple)); + + err = nf_conntrack_expect_related(exp); + nf_conntrack_expect_put(exp); + +out: + nf_ct_put(nf_ct_tuplehash_to_ctrack(h)); + return err; +} + +static int +ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct nf_conntrack_tuple tuple; + struct nf_conntrack_expect *exp; + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + u_int8_t u3 = nfmsg->nfgen_family; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp)) + return -EINVAL; + + if (!cda[CTA_EXPECT_TUPLE-1] + || !cda[CTA_EXPECT_MASK-1] + || !cda[CTA_EXPECT_MASTER-1]) + return -EINVAL; + + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3); + if (err < 0) + return err; + + write_lock_bh(&nf_conntrack_lock); + exp = __nf_conntrack_expect_find(&tuple); + + if (!exp) { + write_unlock_bh(&nf_conntrack_lock); + err = -ENOENT; + if (nlh->nlmsg_flags & NLM_F_CREATE) + err = ctnetlink_create_expect(cda, u3); + return err; + } + + err = -EEXIST; + if (!(nlh->nlmsg_flags & NLM_F_EXCL)) + err = ctnetlink_change_expect(exp, cda); + write_unlock_bh(&nf_conntrack_lock); + + DEBUGP("leaving\n"); + + return err; +} + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +static struct notifier_block ctnl_notifier = { + .notifier_call = ctnetlink_conntrack_event, +}; + +static struct notifier_block ctnl_notifier_exp = { + .notifier_call = ctnetlink_expect_event, +}; +#endif + +static struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { + [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, + .attr_count = CTA_MAX, }, + [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, + .attr_count = CTA_MAX, }, + [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, + .attr_count = CTA_MAX, }, + [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, + .attr_count = CTA_MAX, }, +}; + +static struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { + [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, + .attr_count = CTA_EXPECT_MAX, }, + [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, + .attr_count = CTA_EXPECT_MAX, }, + [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, + .attr_count = CTA_EXPECT_MAX, }, +}; + +static struct nfnetlink_subsystem ctnl_subsys = { + .name = "conntrack", + .subsys_id = NFNL_SUBSYS_CTNETLINK, + .cb_count = IPCTNL_MSG_MAX, + .cb = ctnl_cb, +}; + +static struct nfnetlink_subsystem ctnl_exp_subsys = { + .name = "conntrack_expect", + .subsys_id = NFNL_SUBSYS_CTNETLINK_EXP, + .cb_count = IPCTNL_MSG_EXP_MAX, + .cb = ctnl_exp_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); + +static int __init ctnetlink_init(void) +{ + int ret; + + printk("ctnetlink v%s: registering with nfnetlink.\n", version); + ret = nfnetlink_subsys_register(&ctnl_subsys); + if (ret < 0) { + printk("ctnetlink_init: cannot register with nfnetlink.\n"); + goto err_out; + } + + ret = nfnetlink_subsys_register(&ctnl_exp_subsys); + if (ret < 0) { + printk("ctnetlink_init: cannot register exp with nfnetlink.\n"); + goto err_unreg_subsys; + } + +#ifdef CONFIG_NF_CONNTRACK_EVENTS + ret = nf_conntrack_register_notifier(&ctnl_notifier); + if (ret < 0) { + printk("ctnetlink_init: cannot register notifier.\n"); + goto err_unreg_exp_subsys; + } + + ret = nf_conntrack_expect_register_notifier(&ctnl_notifier_exp); + if (ret < 0) { + printk("ctnetlink_init: cannot expect register notifier.\n"); + goto err_unreg_notifier; + } +#endif + + return 0; + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +err_unreg_notifier: + nf_conntrack_unregister_notifier(&ctnl_notifier); +err_unreg_exp_subsys: + nfnetlink_subsys_unregister(&ctnl_exp_subsys); +#endif +err_unreg_subsys: + nfnetlink_subsys_unregister(&ctnl_subsys); +err_out: + return ret; +} + +static void __exit ctnetlink_exit(void) +{ + printk("ctnetlink: unregistering from nfnetlink.\n"); + +#ifdef CONFIG_NF_CONNTRACK_EVENTS + nf_conntrack_unregister_notifier(&ctnl_notifier_exp); + nf_conntrack_unregister_notifier(&ctnl_notifier); +#endif + + nfnetlink_subsys_unregister(&ctnl_exp_subsys); + nfnetlink_subsys_unregister(&ctnl_subsys); + return; +} + +module_init(ctnetlink_init); +module_exit(ctnetlink_exit); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 6035633..6167137 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1147,6 +1147,63 @@ static int tcp_new(struct nf_conn *conntrack, receiver->td_scale); return 1; } + +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_conntrack.h> + +static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa, + const struct nf_conn *ct) +{ + struct nfattr *nest_parms; + + read_lock_bh(&tcp_lock); + nest_parms = NFA_NEST(skb, CTA_PROTOINFO_TCP); + NFA_PUT(skb, CTA_PROTOINFO_TCP_STATE, sizeof(u_int8_t), + &ct->proto.tcp.state); + read_unlock_bh(&tcp_lock); + + NFA_NEST_END(skb, nest_parms); + + return 0; + +nfattr_failure: + read_unlock_bh(&tcp_lock); + return -1; +} + +static const size_t cta_min_tcp[CTA_PROTOINFO_TCP_MAX] = { + [CTA_PROTOINFO_TCP_STATE-1] = sizeof(u_int8_t), +}; + +static int nfattr_to_tcp(struct nfattr *cda[], struct nf_conn *ct) +{ + struct nfattr *attr = cda[CTA_PROTOINFO_TCP-1]; + struct nfattr *tb[CTA_PROTOINFO_TCP_MAX]; + + /* updates could not contain anything about the private + * protocol info, in that case skip the parsing */ + if (!attr) + return 0; + + nfattr_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, attr); + + if (nfattr_bad_size(tb, CTA_PROTOINFO_TCP_MAX, cta_min_tcp)) + return -EINVAL; + + if (!tb[CTA_PROTOINFO_TCP_STATE-1]) + return -EINVAL; + + write_lock_bh(&tcp_lock); + ct->proto.tcp.state = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTOINFO_TCP_STATE-1]); + write_unlock_bh(&tcp_lock); + + return 0; +} +#endif struct nf_conntrack_protocol nf_conntrack_protocol_tcp4 = { @@ -1160,6 +1217,13 @@ struct nf_conntrack_protocol nf_conntrack_protocol_tcp4 = .packet = tcp_packet, .new = tcp_new, .error = tcp_error4, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .to_nfattr = tcp_to_nfattr, + .from_nfattr = nfattr_to_tcp, + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif }; struct nf_conntrack_protocol nf_conntrack_protocol_tcp6 = @@ -1174,6 +1238,13 @@ struct nf_conntrack_protocol nf_conntrack_protocol_tcp6 = .packet = tcp_packet, .new = tcp_new, .error = tcp_error6, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .to_nfattr = tcp_to_nfattr, + .from_nfattr = nfattr_to_tcp, + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif }; EXPORT_SYMBOL(nf_conntrack_protocol_tcp4); diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 3cae7ce..1a592a5 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -196,6 +196,11 @@ struct nf_conntrack_protocol nf_conntrack_protocol_udp4 = .packet = udp_packet, .new = udp_new, .error = udp_error4, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif }; struct nf_conntrack_protocol nf_conntrack_protocol_udp6 = @@ -210,6 +215,11 @@ struct nf_conntrack_protocol nf_conntrack_protocol_udp6 = .packet = udp_packet, .new = udp_new, .error = udp_error6, +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif }; EXPORT_SYMBOL(nf_conntrack_protocol_udp4); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 5af381f..d17e42b 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -161,14 +161,14 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) return 0; - l3proto = nf_ct_find_l3proto(conntrack->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.src.l3num); + l3proto = __nf_ct_l3proto_find(conntrack->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.src.l3num); NF_CT_ASSERT(l3proto); - proto = nf_ct_find_proto(conntrack->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.src.l3num, - conntrack->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.dst.protonum); + proto = __nf_ct_proto_find(conntrack->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.src.l3num, + conntrack->tuplehash[IP_CT_DIR_ORIGINAL] + .tuple.dst.protonum); NF_CT_ASSERT(proto); if (seq_printf(s, "%-8s %u %-8s %u %ld ", @@ -307,9 +307,9 @@ static int exp_seq_show(struct seq_file *s, void *v) expect->tuple.src.l3num, expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, - nf_ct_find_l3proto(expect->tuple.src.l3num), - nf_ct_find_proto(expect->tuple.src.l3num, - expect->tuple.dst.protonum)); + __nf_ct_l3proto_find(expect->tuple.src.l3num), + __nf_ct_proto_find(expect->tuple.src.l3num, + expect->tuple.dst.protonum)); return seq_putc(s, '\n'); } @@ -847,7 +847,11 @@ EXPORT_SYMBOL(nf_conntrack_helper_unregister); EXPORT_SYMBOL(nf_ct_iterate_cleanup); EXPORT_SYMBOL(__nf_ct_refresh_acct); EXPORT_SYMBOL(nf_ct_protos); -EXPORT_SYMBOL(nf_ct_find_proto); +EXPORT_SYMBOL(__nf_ct_proto_find); +EXPORT_SYMBOL(nf_ct_proto_find_get); +EXPORT_SYMBOL(nf_ct_proto_put); +EXPORT_SYMBOL(nf_ct_l3proto_find_get); +EXPORT_SYMBOL(nf_ct_l3proto_put); EXPORT_SYMBOL(nf_ct_l3protos); EXPORT_SYMBOL(nf_conntrack_expect_alloc); EXPORT_SYMBOL(nf_conntrack_expect_put); @@ -867,3 +871,21 @@ EXPORT_SYMBOL(nf_ct_get_tuple); EXPORT_SYMBOL(nf_ct_invert_tuple); EXPORT_SYMBOL(nf_conntrack_in); EXPORT_SYMBOL(__nf_conntrack_attach); +EXPORT_SYMBOL(nf_conntrack_alloc); +EXPORT_SYMBOL(nf_conntrack_free); +EXPORT_SYMBOL(nf_conntrack_flush); +EXPORT_SYMBOL(nf_ct_remove_expectations); +EXPORT_SYMBOL(nf_ct_helper_find_get); +EXPORT_SYMBOL(nf_ct_helper_put); +EXPORT_SYMBOL(__nf_conntrack_helper_find_byname); +EXPORT_SYMBOL(__nf_conntrack_find); +EXPORT_SYMBOL(nf_ct_unlink_expect); +EXPORT_SYMBOL(nf_conntrack_hash_insert); +EXPORT_SYMBOL(__nf_conntrack_expect_find); +EXPORT_SYMBOL(nf_conntrack_expect_find); +EXPORT_SYMBOL(nf_conntrack_expect_list); +#if defined(CONFIG_NF_CT_NETLINK) || \ + defined(CONFIG_NF_CT_NETLINK_MODULE) +EXPORT_SYMBOL(nf_ct_port_tuple_to_nfattr); +EXPORT_SYMBOL(nf_ct_port_nfattr_to_tuple); +#endif diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a60c59b..95fdf04 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -162,7 +162,7 @@ nfnetlink_check_attributes(struct nfnetlink_subsystem *subsys, return -EINVAL; } - min_len = NLMSG_ALIGN(sizeof(struct nfgenmsg)); + min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); if (unlikely(nlh->nlmsg_len < min_len)) return -EINVAL; @@ -236,8 +236,7 @@ static inline int nfnetlink_rcv_msg(struct sk_buff *skb, } /* All the messages must at least contain nfgenmsg */ - if (nlh->nlmsg_len < - NLMSG_LENGTH(NLMSG_ALIGN(sizeof(struct nfgenmsg)))) { + if (nlh->nlmsg_len < NLMSG_SPACE(sizeof(struct nfgenmsg))) { DEBUGP("received message was too short\n"); return 0; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cba6372..e10512e 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -151,7 +151,7 @@ instance_create(u_int16_t group_num, int pid) goto out_unlock; INIT_HLIST_NODE(&inst->hlist); - inst->lock = SPIN_LOCK_UNLOCKED; + spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ atomic_set(&inst->use, 2); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f28460b6..18ed9c5 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -148,7 +148,7 @@ instance_create(u_int16_t queue_num, int pid) atomic_set(&inst->id_sequence, 0); /* needs to be two, since we _put() after creation */ atomic_set(&inst->use, 2); - inst->lock = SPIN_LOCK_UNLOCKED; + spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); if (!try_module_get(THIS_MODULE)) @@ -345,6 +345,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, struct nfqnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; + struct nf_info *entinf = entry->info; + struct sk_buff *entskb = entry->skb; + struct net_device *indev; + struct net_device *outdev; unsigned int tmp_uint; QDEBUG("entered\n"); @@ -361,6 +365,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, + NLMSG_SPACE(sizeof(struct nfqnl_msg_packet_hw)) + NLMSG_SPACE(sizeof(struct nfqnl_msg_packet_timestamp)); + outdev = entinf->outdev; + spin_lock_bh(&queue->lock); switch (queue->copy_mode) { @@ -370,15 +376,15 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, break; case NFQNL_COPY_PACKET: - if (entry->skb->ip_summed == CHECKSUM_HW && - (*errp = skb_checksum_help(entry->skb, - entry->info->outdev == NULL))) { + if (entskb->ip_summed == CHECKSUM_HW && + (*errp = skb_checksum_help(entskb, + outdev == NULL))) { spin_unlock_bh(&queue->lock); return NULL; } if (queue->copy_range == 0 - || queue->copy_range > entry->skb->len) - data_len = entry->skb->len; + || queue->copy_range > entskb->len) + data_len = entskb->len; else data_len = queue->copy_range; @@ -402,29 +408,30 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); - nfmsg->nfgen_family = entry->info->pf; + nfmsg->nfgen_family = entinf->pf; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(queue->queue_num); pmsg.packet_id = htonl(entry->id); - pmsg.hw_protocol = htons(entry->skb->protocol); - pmsg.hook = entry->info->hook; + pmsg.hw_protocol = htons(entskb->protocol); + pmsg.hook = entinf->hook; NFA_PUT(skb, NFQA_PACKET_HDR, sizeof(pmsg), &pmsg); - if (entry->info->indev) { - tmp_uint = htonl(entry->info->indev->ifindex); + indev = entinf->indev; + if (indev) { + tmp_uint = htonl(indev->ifindex); #ifndef CONFIG_BRIDGE_NETFILTER NFA_PUT(skb, NFQA_IFINDEX_INDEV, sizeof(tmp_uint), &tmp_uint); #else - if (entry->info->pf == PF_BRIDGE) { + if (entinf->pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ NFA_PUT(skb, NFQA_IFINDEX_PHYSINDEV, sizeof(tmp_uint), &tmp_uint); /* this is the bridge group "brX" */ - tmp_uint = htonl(entry->info->indev->br_port->br->dev->ifindex); + tmp_uint = htonl(indev->br_port->br->dev->ifindex); NFA_PUT(skb, NFQA_IFINDEX_INDEV, sizeof(tmp_uint), &tmp_uint); } else { @@ -432,9 +439,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, * physical device (when called from ipv4) */ NFA_PUT(skb, NFQA_IFINDEX_INDEV, sizeof(tmp_uint), &tmp_uint); - if (entry->skb->nf_bridge - && entry->skb->nf_bridge->physindev) { - tmp_uint = htonl(entry->skb->nf_bridge->physindev->ifindex); + if (entskb->nf_bridge + && entskb->nf_bridge->physindev) { + tmp_uint = htonl(entskb->nf_bridge->physindev->ifindex); NFA_PUT(skb, NFQA_IFINDEX_PHYSINDEV, sizeof(tmp_uint), &tmp_uint); } @@ -442,19 +449,19 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, #endif } - if (entry->info->outdev) { - tmp_uint = htonl(entry->info->outdev->ifindex); + if (outdev) { + tmp_uint = htonl(outdev->ifindex); #ifndef CONFIG_BRIDGE_NETFILTER NFA_PUT(skb, NFQA_IFINDEX_OUTDEV, sizeof(tmp_uint), &tmp_uint); #else - if (entry->info->pf == PF_BRIDGE) { + if (entinf->pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ NFA_PUT(skb, NFQA_IFINDEX_PHYSOUTDEV, sizeof(tmp_uint), &tmp_uint); /* this is the bridge group "brX" */ - tmp_uint = htonl(entry->info->outdev->br_port->br->dev->ifindex); + tmp_uint = htonl(outdev->br_port->br->dev->ifindex); NFA_PUT(skb, NFQA_IFINDEX_OUTDEV, sizeof(tmp_uint), &tmp_uint); } else { @@ -462,9 +469,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, * physical output device (when called from ipv4) */ NFA_PUT(skb, NFQA_IFINDEX_OUTDEV, sizeof(tmp_uint), &tmp_uint); - if (entry->skb->nf_bridge - && entry->skb->nf_bridge->physoutdev) { - tmp_uint = htonl(entry->skb->nf_bridge->physoutdev->ifindex); + if (entskb->nf_bridge + && entskb->nf_bridge->physoutdev) { + tmp_uint = htonl(entskb->nf_bridge->physoutdev->ifindex); NFA_PUT(skb, NFQA_IFINDEX_PHYSOUTDEV, sizeof(tmp_uint), &tmp_uint); } @@ -472,27 +479,27 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, #endif } - if (entry->skb->nfmark) { - tmp_uint = htonl(entry->skb->nfmark); + if (entskb->nfmark) { + tmp_uint = htonl(entskb->nfmark); NFA_PUT(skb, NFQA_MARK, sizeof(u_int32_t), &tmp_uint); } - if (entry->info->indev && entry->skb->dev - && entry->skb->dev->hard_header_parse) { + if (indev && entskb->dev + && entskb->dev->hard_header_parse) { struct nfqnl_msg_packet_hw phw; phw.hw_addrlen = - entry->skb->dev->hard_header_parse(entry->skb, + entskb->dev->hard_header_parse(entskb, phw.hw_addr); phw.hw_addrlen = htons(phw.hw_addrlen); NFA_PUT(skb, NFQA_HWADDR, sizeof(phw), &phw); } - if (entry->skb->tstamp.off_sec) { + if (entskb->tstamp.off_sec) { struct nfqnl_msg_packet_timestamp ts; - ts.sec = cpu_to_be64(entry->skb->tstamp.off_sec); - ts.usec = cpu_to_be64(entry->skb->tstamp.off_usec); + ts.sec = cpu_to_be64(entskb->tstamp.off_sec); + ts.usec = cpu_to_be64(entskb->tstamp.off_usec); NFA_PUT(skb, NFQA_TIMESTAMP, sizeof(ts), &ts); } @@ -510,7 +517,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, nfa->nfa_type = NFQA_PAYLOAD; nfa->nfa_len = size; - if (skb_copy_bits(entry->skb, 0, NFA_DATA(nfa), data_len)) + if (skb_copy_bits(entskb, 0, NFA_DATA(nfa), data_len)) BUG(); } @@ -667,12 +674,14 @@ nfqnl_set_mode(struct nfqnl_instance *queue, static int dev_cmp(struct nfqnl_queue_entry *entry, unsigned long ifindex) { - if (entry->info->indev) - if (entry->info->indev->ifindex == ifindex) + struct nf_info *entinf = entry->info; + + if (entinf->indev) + if (entinf->indev->ifindex == ifindex) return 1; - if (entry->info->outdev) - if (entry->info->outdev->ifindex == ifindex) + if (entinf->outdev) + if (entinf->outdev->ifindex == ifindex) return 1; return 0; |