diff options
Diffstat (limited to 'net/ipv4/netfilter')
44 files changed, 3101 insertions, 409 deletions
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 46d4cb1c06f..e046f552181 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -40,6 +40,16 @@ config IP_NF_CONNTRACK_MARK of packets, but this mark value is kept in the conntrack session instead of the individual packets. +config IP_NF_CONNTRACK_EVENTS + bool "Connection tracking events" + depends on IP_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 + to get notified about changes in the connection tracking state. + + IF unsure, say `N'. + config IP_NF_CT_PROTO_SCTP tristate 'SCTP protocol connection tracking support (EXPERIMENTAL)' depends on IP_NF_CONNTRACK && EXPERIMENTAL @@ -100,11 +110,15 @@ config IP_NF_AMANDA To compile it as a module, choose M here. If unsure, say Y. config IP_NF_QUEUE - tristate "Userspace queueing via NETLINK" + tristate "IP Userspace queueing via NETLINK (OBSOLETE)" help Netfilter has the ability to queue packets to user space: the netlink device can be used to access them using this driver. + This option enables the old IPv4-only "ip_queue" implementation + which has been obsoleted by the new "nfnetlink_queue" code (see + CONFIG_NETFILTER_NETLINK_QUEUE). + To compile it as a module, choose M here. If unsure, say N. config IP_NF_IPTABLES @@ -340,6 +354,17 @@ config IP_NF_MATCH_SCTP If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. +config IP_NF_MATCH_DCCP + tristate 'DCCP protocol match support' + depends on IP_NF_IPTABLES + help + With this option enabled, you will be able to use the iptables + `dccp' match in order to match on DCCP source/destination ports + and DCCP flags. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + config IP_NF_MATCH_COMMENT tristate 'comment match support' depends on IP_NF_IPTABLES @@ -361,6 +386,16 @@ config IP_NF_MATCH_CONNMARK <file:Documentation/modules.txt>. The module will be called ipt_connmark.o. If unsure, say `N'. +config IP_NF_MATCH_CONNBYTES + tristate 'Connection byte/packet counter match support' + depends on IP_NF_CT_ACCT && IP_NF_IPTABLES + help + This option adds a `connbytes' match, which allows you to match the + number of bytes and/or packets for each direction within a connection. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + config IP_NF_MATCH_HASHLIMIT tristate 'hashlimit match support' depends on IP_NF_IPTABLES @@ -375,6 +410,19 @@ config IP_NF_MATCH_HASHLIMIT destination IP' or `500pps from any given source IP' with a single IPtables rule. +config IP_NF_MATCH_STRING + tristate 'string match support' + depends on IP_NF_IPTABLES + select TEXTSEARCH + select TEXTSEARCH_KMP + select TEXTSEARCH_BM + select TEXTSEARCH_FSM + help + This option adds a `string' match, which allows you to look for + pattern matchings in packets. + + To compile it as a module, choose M here. If unsure, say N. + # `filter', generic and specific targets config IP_NF_FILTER tristate "Packet filtering" @@ -616,6 +664,20 @@ config IP_NF_TARGET_CLASSIFY To compile it as a module, choose M here. If unsure, say N. +config IP_NF_TARGET_TTL + tristate 'TTL target support' + depends on IP_NF_MANGLE + help + This option adds a `TTL' target, which enables the user to modify + the TTL value of the IP header. + + While it is safe to decrement/lower the TTL, this target also enables + functionality to increment and set the TTL value of the IP header to + arbitrary values. This is EXTREMELY DANGEROUS since you can easily + create immortal packets that loop forever on the network. + + To compile it as a module, choose M here. If unsure, say N. + config IP_NF_TARGET_CONNMARK tristate 'CONNMARK target support' depends on IP_NF_CONNTRACK_MARK && IP_NF_MANGLE @@ -692,5 +754,11 @@ config IP_NF_ARP_MANGLE Allows altering the ARP packet payload: source and destination hardware and network addresses. +config IP_NF_CONNTRACK_NETLINK + tristate 'Connection tracking netlink interface' + depends on IP_NF_CONNTRACK && NETFILTER_NETLINK + help + This option enables support for a netlink-based userspace interface + endmenu diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 45796d5924d..a7bd38f5052 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -9,6 +9,10 @@ iptable_nat-objs := ip_nat_standalone.o ip_nat_rule.o ip_nat_core.o ip_nat_helpe # connection tracking obj-$(CONFIG_IP_NF_CONNTRACK) += ip_conntrack.o +# conntrack netlink interface +obj-$(CONFIG_IP_NF_CONNTRACK_NETLINK) += ip_conntrack_netlink.o + + # SCTP protocol connection tracking obj-$(CONFIG_IP_NF_CT_PROTO_SCTP) += ip_conntrack_proto_sctp.o @@ -38,6 +42,7 @@ obj-$(CONFIG_IP_NF_MATCH_HELPER) += ipt_helper.o obj-$(CONFIG_IP_NF_MATCH_LIMIT) += ipt_limit.o obj-$(CONFIG_IP_NF_MATCH_HASHLIMIT) += ipt_hashlimit.o obj-$(CONFIG_IP_NF_MATCH_SCTP) += ipt_sctp.o +obj-$(CONFIG_IP_NF_MATCH_DCCP) += ipt_dccp.o obj-$(CONFIG_IP_NF_MATCH_MARK) += ipt_mark.o obj-$(CONFIG_IP_NF_MATCH_MAC) += ipt_mac.o obj-$(CONFIG_IP_NF_MATCH_IPRANGE) += ipt_iprange.o @@ -54,11 +59,13 @@ obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o obj-$(CONFIG_IP_NF_MATCH_STATE) += ipt_state.o obj-$(CONFIG_IP_NF_MATCH_CONNMARK) += ipt_connmark.o obj-$(CONFIG_IP_NF_MATCH_CONNTRACK) += ipt_conntrack.o +obj-$(CONFIG_IP_NF_MATCH_CONNBYTES) += ipt_connbytes.o obj-$(CONFIG_IP_NF_MATCH_TCPMSS) += ipt_tcpmss.o obj-$(CONFIG_IP_NF_MATCH_REALM) += ipt_realm.o obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o obj-$(CONFIG_IP_NF_MATCH_PHYSDEV) += ipt_physdev.o obj-$(CONFIG_IP_NF_MATCH_COMMENT) += ipt_comment.o +obj-$(CONFIG_IP_NF_MATCH_STRING) += ipt_string.o # targets obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o @@ -78,6 +85,7 @@ obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o obj-$(CONFIG_IP_NF_TARGET_TCPMSS) += ipt_TCPMSS.o obj-$(CONFIG_IP_NF_TARGET_NOTRACK) += ipt_NOTRACK.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o +obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o # generic ARP tables obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o @@ -87,3 +95,4 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o +obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += ipt_NFQUEUE.o diff --git a/net/ipv4/netfilter/ip_conntrack_amanda.c b/net/ipv4/netfilter/ip_conntrack_amanda.c index 01e1b58322a..be4c9eb3243 100644 --- a/net/ipv4/netfilter/ip_conntrack_amanda.c +++ b/net/ipv4/netfilter/ip_conntrack_amanda.c @@ -40,7 +40,7 @@ MODULE_PARM_DESC(master_timeout, "timeout for the master connection"); static char *conns[] = { "DATA ", "MESG ", "INDEX " }; /* This is slow, but it's simple. --RR */ -static char amanda_buffer[65536]; +static char *amanda_buffer; static DEFINE_SPINLOCK(amanda_buffer_lock); unsigned int (*ip_nat_amanda_hook)(struct sk_buff **pskb, @@ -153,11 +153,25 @@ static struct ip_conntrack_helper amanda_helper = { static void __exit fini(void) { ip_conntrack_helper_unregister(&amanda_helper); + kfree(amanda_buffer); } static int __init init(void) { - return ip_conntrack_helper_register(&amanda_helper); + int ret; + + amanda_buffer = kmalloc(65536, GFP_KERNEL); + if (!amanda_buffer) + return -ENOMEM; + + ret = ip_conntrack_helper_register(&amanda_helper); + if (ret < 0) { + kfree(amanda_buffer); + return ret; + } + return 0; + + } module_init(init); diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c index a7f0c821a9b..a0648600190 100644 --- a/net/ipv4/netfilter/ip_conntrack_core.c +++ b/net/ipv4/netfilter/ip_conntrack_core.c @@ -37,6 +37,7 @@ #include <linux/err.h> #include <linux/percpu.h> #include <linux/moduleparam.h> +#include <linux/notifier.h> /* ip_conntrack_lock protects the main hash table, protocol/helper/expected registrations, conntrack timers*/ @@ -49,7 +50,7 @@ #include <linux/netfilter_ipv4/ip_conntrack_core.h> #include <linux/netfilter_ipv4/listhelp.h> -#define IP_CONNTRACK_VERSION "2.1" +#define IP_CONNTRACK_VERSION "2.3" #if 0 #define DEBUGP printk @@ -69,22 +70,81 @@ static LIST_HEAD(helpers); unsigned int ip_conntrack_htable_size = 0; int ip_conntrack_max; struct list_head *ip_conntrack_hash; -static kmem_cache_t *ip_conntrack_cachep; -static kmem_cache_t *ip_conntrack_expect_cachep; +static kmem_cache_t *ip_conntrack_cachep __read_mostly; +static kmem_cache_t *ip_conntrack_expect_cachep __read_mostly; struct ip_conntrack ip_conntrack_untracked; unsigned int ip_ct_log_invalid; static LIST_HEAD(unconfirmed); static int ip_conntrack_vmalloc; -DEFINE_PER_CPU(struct ip_conntrack_stat, ip_conntrack_stat); +static unsigned int ip_conntrack_next_id = 1; +static unsigned int ip_conntrack_expect_next_id = 1; +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +struct notifier_block *ip_conntrack_chain; +struct notifier_block *ip_conntrack_expect_chain; + +DEFINE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache); -void -ip_conntrack_put(struct ip_conntrack *ct) +/* deliver cached events and clear cache entry - must be called with locally + * disabled softirqs */ +static inline void +__ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ecache) { - IP_NF_ASSERT(ct); - nf_conntrack_put(&ct->ct_general); + DEBUGP("ecache: delivering events for %p\n", ecache->ct); + if (is_confirmed(ecache->ct) && !is_dying(ecache->ct) && ecache->events) + notifier_call_chain(&ip_conntrack_chain, ecache->events, + ecache->ct); + ecache->events = 0; + ip_conntrack_put(ecache->ct); + ecache->ct = NULL; } +/* Deliver all cached events for a particular conntrack. This is called + * by code prior to async packet handling or freeing the skb */ +void ip_ct_deliver_cached_events(const struct ip_conntrack *ct) +{ + struct ip_conntrack_ecache *ecache; + + local_bh_disable(); + ecache = &__get_cpu_var(ip_conntrack_ecache); + if (ecache->ct == ct) + __ip_ct_deliver_cached_events(ecache); + local_bh_enable(); +} + +void __ip_ct_event_cache_init(struct ip_conntrack *ct) +{ + struct ip_conntrack_ecache *ecache; + + /* take care of delivering potentially old events */ + ecache = &__get_cpu_var(ip_conntrack_ecache); + BUG_ON(ecache->ct == ct); + if (ecache->ct) + __ip_ct_deliver_cached_events(ecache); + /* initialize for this conntrack/packet */ + ecache->ct = ct; + nf_conntrack_get(&ct->ct_general); +} + +/* flush the event cache - touches other CPU's data and must not be called while + * packets are still passing through the code */ +static void ip_ct_event_cache_flush(void) +{ + struct ip_conntrack_ecache *ecache; + int cpu; + + for_each_cpu(cpu) { + ecache = &per_cpu(ip_conntrack_ecache, cpu); + if (ecache->ct) + ip_conntrack_put(ecache->ct); + } +} +#else +static inline void ip_ct_event_cache_flush(void) {} +#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */ + +DEFINE_PER_CPU(struct ip_conntrack_stat, ip_conntrack_stat); + static int ip_conntrack_hash_rnd_initted; static unsigned int ip_conntrack_hash_rnd; @@ -144,6 +204,13 @@ static void unlink_expect(struct ip_conntrack_expect *exp) list_del(&exp->list); CONNTRACK_STAT_INC(expect_delete); exp->master->expecting--; + ip_conntrack_expect_put(exp); +} + +void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp) +{ + unlink_expect(exp); + ip_conntrack_expect_put(exp); } static void expectation_timed_out(unsigned long ul_expect) @@ -156,6 +223,33 @@ static void expectation_timed_out(unsigned long ul_expect) ip_conntrack_expect_put(exp); } +struct ip_conntrack_expect * +__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple) +{ + struct ip_conntrack_expect *i; + + list_for_each_entry(i, &ip_conntrack_expect_list, list) { + if (ip_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 ip_conntrack_expect * +ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple) +{ + struct ip_conntrack_expect *i; + + read_lock_bh(&ip_conntrack_lock); + i = __ip_conntrack_expect_find(tuple); + read_unlock_bh(&ip_conntrack_lock); + + return i; +} + /* If an expectation for this connection is found, it gets delete from * global list then returned. */ static struct ip_conntrack_expect * @@ -180,7 +274,7 @@ find_expectation(const struct ip_conntrack_tuple *tuple) } /* delete all expectations for this conntrack */ -static void remove_expectations(struct ip_conntrack *ct) +void ip_ct_remove_expectations(struct ip_conntrack *ct) { struct ip_conntrack_expect *i, *tmp; @@ -210,7 +304,7 @@ clean_from_lists(struct ip_conntrack *ct) LIST_DELETE(&ip_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]); /* Destroy all pending expectations */ - remove_expectations(ct); + ip_ct_remove_expectations(ct); } static void @@ -223,10 +317,13 @@ destroy_conntrack(struct nf_conntrack *nfct) IP_NF_ASSERT(atomic_read(&nfct->use) == 0); IP_NF_ASSERT(!timer_pending(&ct->timeout)); + ip_conntrack_event(IPCT_DESTROY, ct); + set_bit(IPS_DYING_BIT, &ct->status); + /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to ip_conntrack_lock!!! -HW */ - proto = ip_ct_find_proto(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); + proto = __ip_conntrack_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum); if (proto && proto->destroy) proto->destroy(ct); @@ -238,7 +335,7 @@ 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); + ip_ct_remove_expectations(ct); /* We overload first tuple to link into unconfirmed list. */ if (!is_confirmed(ct)) { @@ -253,8 +350,7 @@ destroy_conntrack(struct nf_conntrack *nfct) ip_conntrack_put(ct->master); DEBUGP("destroy_conntrack: returning ct=%p to slab\n", ct); - kmem_cache_free(ip_conntrack_cachep, ct); - atomic_dec(&ip_conntrack_count); + ip_conntrack_free(ct); } static void death_by_timeout(unsigned long ul_conntrack) @@ -280,7 +376,7 @@ conntrack_tuple_cmp(const struct ip_conntrack_tuple_hash *i, && ip_ct_tuple_equal(tuple, &i->tuple); } -static struct ip_conntrack_tuple_hash * +struct ip_conntrack_tuple_hash * __ip_conntrack_find(const struct ip_conntrack_tuple *tuple, const struct ip_conntrack *ignored_conntrack) { @@ -315,6 +411,29 @@ ip_conntrack_find_get(const struct ip_conntrack_tuple *tuple, return h; } +static void __ip_conntrack_hash_insert(struct ip_conntrack *ct, + unsigned int hash, + unsigned int repl_hash) +{ + ct->id = ++ip_conntrack_next_id; + list_prepend(&ip_conntrack_hash[hash], + &ct->tuplehash[IP_CT_DIR_ORIGINAL].list); + list_prepend(&ip_conntrack_hash[repl_hash], + &ct->tuplehash[IP_CT_DIR_REPLY].list); +} + +void ip_conntrack_hash_insert(struct ip_conntrack *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(&ip_conntrack_lock); + __ip_conntrack_hash_insert(ct, hash, repl_hash); + write_unlock_bh(&ip_conntrack_lock); +} + /* Confirm a connection given skb; places it in hash table */ int __ip_conntrack_confirm(struct sk_buff **pskb) @@ -361,10 +480,7 @@ __ip_conntrack_confirm(struct sk_buff **pskb) /* Remove from unconfirmed list */ list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list); - list_prepend(&ip_conntrack_hash[hash], - &ct->tuplehash[IP_CT_DIR_ORIGINAL]); - list_prepend(&ip_conntrack_hash[repl_hash], - &ct->tuplehash[IP_CT_DIR_REPLY]); + __ip_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. */ @@ -374,6 +490,16 @@ __ip_conntrack_confirm(struct sk_buff **pskb) set_bit(IPS_CONFIRMED_BIT, &ct->status); CONNTRACK_STAT_INC(insert); write_unlock_bh(&ip_conntrack_lock); + if (ct->helper) + ip_conntrack_event_cache(IPCT_HELPER, *pskb); +#ifdef CONFIG_IP_NF_NAT_NEEDED + if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) || + test_bit(IPS_DST_NAT_DONE_BIT, &ct->status)) + ip_conntrack_event_cache(IPCT_NATINFO, *pskb); +#endif + ip_conntrack_event_cache(master_ct(ct) ? + IPCT_RELATED : IPCT_NEW, *pskb); + return NF_ACCEPT; } @@ -438,34 +564,84 @@ static inline int helper_cmp(const struct ip_conntrack_helper *i, return ip_ct_tuple_mask_cmp(rtuple, &i->tuple, &i->mask); } -static struct ip_conntrack_helper *ip_ct_find_helper(const struct ip_conntrack_tuple *tuple) +static struct ip_conntrack_helper * +__ip_conntrack_helper_find( const struct ip_conntrack_tuple *tuple) { return LIST_FIND(&helpers, helper_cmp, struct ip_conntrack_helper *, tuple); } -/* Allocate a new conntrack: we return -ENOMEM if classification - failed due to stress. Otherwise it really is unclassifiable. */ -static struct ip_conntrack_tuple_hash * -init_conntrack(const struct ip_conntrack_tuple *tuple, - struct ip_conntrack_protocol *protocol, - struct sk_buff *skb) +struct ip_conntrack_helper * +ip_conntrack_helper_find_get( const struct ip_conntrack_tuple *tuple) +{ + struct ip_conntrack_helper *helper; + + /* need ip_conntrack_lock to assure that helper exists until + * try_module_get() is called */ + read_lock_bh(&ip_conntrack_lock); + + helper = __ip_conntrack_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(&ip_conntrack_lock); + + return helper; +} + +void ip_conntrack_helper_put(struct ip_conntrack_helper *helper) +{ + module_put(helper->me); +} + +struct ip_conntrack_protocol * +__ip_conntrack_proto_find(u_int8_t protocol) +{ + return ip_ct_protos[protocol]; +} + +/* this is guaranteed to always return a valid protocol helper, since + * it falls back to generic_protocol */ +struct ip_conntrack_protocol * +ip_conntrack_proto_find_get(u_int8_t protocol) +{ + struct ip_conntrack_protocol *p; + + preempt_disable(); + p = __ip_conntrack_proto_find(protocol); + if (p) { + if (!try_module_get(p->me)) + p = &ip_conntrack_generic_protocol; + } + preempt_enable(); + + return p; +} + +void ip_conntrack_proto_put(struct ip_conntrack_protocol *p) +{ + module_put(p->me); +} + +struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig, + struct ip_conntrack_tuple *repl) { struct ip_conntrack *conntrack; - struct ip_conntrack_tuple repl_tuple; - size_t hash; - struct ip_conntrack_expect *exp; if (!ip_conntrack_hash_rnd_initted) { get_random_bytes(&ip_conntrack_hash_rnd, 4); ip_conntrack_hash_rnd_initted = 1; } - hash = hash_conntrack(tuple); - if (ip_conntrack_max && atomic_read(&ip_conntrack_count) >= ip_conntrack_max) { + unsigned int hash = hash_conntrack(orig); /* Try dropping from this hash chain. */ if (!early_drop(&ip_conntrack_hash[hash])) { if (net_ratelimit()) @@ -476,11 +652,6 @@ init_conntrack(const struct ip_conntrack_tuple *tuple, } } - if (!ip_ct_invert_tuple(&repl_tuple, tuple, protocol)) { - DEBUGP("Can't invert tuple.\n"); - return NULL; - } - conntrack = kmem_cache_alloc(ip_conntrack_cachep, GFP_ATOMIC); if (!conntrack) { DEBUGP("Can't allocate conntrack.\n"); @@ -490,17 +661,50 @@ init_conntrack(const struct ip_conntrack_tuple *tuple, memset(conntrack, 0, sizeof(*conntrack)); atomic_set(&conntrack->ct_general.use, 1); conntrack->ct_general.destroy = destroy_conntrack; - conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *tuple; - conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = repl_tuple; - if (!protocol->new(conntrack, skb)) { - kmem_cache_free(ip_conntrack_cachep, conntrack); - return NULL; - } + conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; + conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *repl; /* Don't set timer yet: wait for confirmation */ init_timer(&conntrack->timeout); conntrack->timeout.data = (unsigned long)conntrack; conntrack->timeout.function = death_by_timeout; + atomic_inc(&ip_conntrack_count); + + return conntrack; +} + +void +ip_conntrack_free(struct ip_conntrack *conntrack) +{ + atomic_dec(&ip_conntrack_count); + kmem_cache_free(ip_conntrack_cachep, conntrack); +} + +/* Allocate a new conntrack: we return -ENOMEM if classification + * failed due to stress. Otherwise it really is unclassifiable */ +static struct ip_conntrack_tuple_hash * +init_conntrack(struct ip_conntrack_tuple *tuple, + struct ip_conntrack_protocol *protocol, + struct sk_buff *skb) +{ + struct ip_conntrack *conntrack; + struct ip_conntrack_tuple repl_tuple; + struct ip_conntrack_expect *exp; + + if (!ip_ct_invert_tuple(&repl_tuple, tuple, protocol)) { + DEBUGP("Can't invert tuple.\n"); + return NULL; + } + + conntrack = ip_conntrack_alloc(tuple, &repl_tuple); + if (conntrack == NULL || IS_ERR(conntrack)) + return (struct ip_conntrack_tuple_hash *)conntrack; + + if (!protocol->new(conntrack, skb)) { + ip_conntrack_free(conntrack); + return NULL; + } + write_lock_bh(&ip_conntrack_lock); exp = find_expectation(tuple); @@ -521,7 +725,7 @@ init_conntrack(const struct ip_conntrack_tuple *tuple, nf_conntrack_get(&conntrack->master->ct_general); CONNTRACK_STAT_INC(expect_new); } else { - conntrack->helper = ip_ct_find_helper(&repl_tuple); + conntrack->helper = __ip_conntrack_helper_find(&repl_tuple); CONNTRACK_STAT_INC(new); } @@ -529,7 +733,6 @@ init_conntrack(const struct ip_conntrack_tuple *tuple, /* Overload tuple linked list to put us in unconfirmed list. */ list_add(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL].list, &unconfirmed); - atomic_inc(&ip_conntrack_count); write_unlock_bh(&ip_conntrack_lock); if (exp) { @@ -607,7 +810,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum, struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; struct ip_conntrack_protocol *proto; - int set_reply; + int set_reply = 0; int ret; /* Previously seen (loopback or untracked)? Ignore. */ @@ -625,9 +828,6 @@ unsigned int ip_conntrack_in(unsigned int hooknum, return NF_DROP; } - /* FIXME: Do this right please. --RR */ - (*pskb)->nfcache |= NFC_UNKNOWN; - /* Doesn't cover locally-generated broadcast, so not worth it. */ #if 0 /* Ignore broadcast: no `connection'. */ @@ -643,7 +843,7 @@ unsigned int ip_conntrack_in(unsigned int hooknum, } #endif - proto = ip_ct_find_proto((*pskb)->nh.iph->protocol); + proto = __ip_conntrack_proto_find((*pskb)->nh.iph->protocol); /* It may be an special packet, error, unclean... * inverse of the return code tells to the netfilter @@ -679,8 +879,8 @@ unsigned int ip_conntrack_in(unsigned int hooknum, return -ret; } - if (set_reply) - set_bit(IPS_SEEN_REPLY_BIT, &ct->status); + if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) + ip_conntrack_event_cache(IPCT_STATUS, *pskb); return ret; } @@ -689,7 +889,7 @@ int invert_tuplepr(struct ip_conntrack_tuple *inverse, const struct ip_conntrack_tuple *orig) { return ip_ct_invert_tuple(inverse, orig, - ip_ct_find_proto(orig->dst.protonum)); + __ip_conntrack_proto_find(orig->dst.protonum)); } /* Would two expected things clash? */ @@ -769,6 +969,8 @@ static void ip_conntrack_expect_insert(struct ip_conntrack_expect *exp) exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ; add_timer(&exp->timeout); + exp->id = ++ip_conntrack_expect_next_id; + atomic_inc(&exp->use); CONNTRACK_STAT_INC(expect_create); } @@ -827,6 +1029,7 @@ int ip_conntrack_expect_related(struct ip_conntrack_expect *expect) evict_oldest_expect(expect->master); ip_conntrack_expect_insert(expect); + ip_conntrack_expect_event(IPEXP_NEW, expect); ret = 0; out: write_unlock_bh(&ip_conntrack_lock); @@ -847,7 +1050,7 @@ void ip_conntrack_alter_reply(struct ip_conntrack *conntrack, conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply; if (!conntrack->master && conntrack->expecting == 0) - conntrack->helper = ip_ct_find_helper(newreply); + conntrack->helper = __ip_conntrack_helper_find(newreply); write_unlock_bh(&ip_conntrack_lock); } @@ -861,11 +1064,26 @@ int ip_conntrack_helper_register(struct ip_conntrack_helper *me) return 0; } +struct ip_conntrack_helper * +__ip_conntrack_helper_find_byname(const char *name) +{ + struct ip_conntrack_helper *h; + + list_for_each_entry(h, &helpers, list) { + if (!strcmp(h->name, name)) + return h; + } + + return NULL; +} + static inline int unhelp(struct ip_conntrack_tuple_hash *i, const struct ip_conntrack_helper *me) { - if (tuplehash_to_ctrack(i)->helper == me) + if (tuplehash_to_ctrack(i)->helper == me) { + ip_conntrack_event(IPCT_HELPER, tuplehash_to_ctrack(i)); tuplehash_to_ctrack(i)->helper = NULL; + } return 0; } @@ -927,12 +1145,46 @@ void ip_ct_refresh_acct(struct ip_conntrack *ct, if (del_timer(&ct->timeout)) { ct->timeout.expires = jiffies + extra_jiffies; add_timer(&ct->timeout); + ip_conntrack_event_cache(IPCT_REFRESH, skb); } ct_add_counters(ct, ctinfo, skb); write_unlock_bh(&ip_conntrack_lock); } } +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +/* 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 ip_ct_port_tuple_to_nfattr(struct sk_buff *skb, + const struct ip_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; +} + +int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[], + struct ip_conntrack_tuple *t) +{ + if (!tb[CTA_PROTO_SRC_PORT-1] || !tb[CTA_PROTO_DST_PORT-1]) + 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 + /* Returns new sk_buff, or NULL */ struct sk_buff * ip_ct_gather_frags(struct sk_buff *skb, u_int32_t user) @@ -943,10 +1195,8 @@ ip_ct_gather_frags(struct sk_buff *skb, u_int32_t user) skb = ip_defrag(skb, user); local_bh_enable(); - if (skb) { + if (skb) ip_send_check(skb->nh.iph); - skb->nfcache |= NFC_ALTERED; - } return skb; } @@ -1096,16 +1346,14 @@ static void free_conntrack_hash(void) * ip_conntrack_htable_size)); } -/* Mishearing the voices in his head, our hero wonders how he's - supposed to kill the mall. */ -void ip_conntrack_cleanup(void) +void ip_conntrack_flush() { - ip_ct_attach = NULL; /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module delete... */ synchronize_net(); - + + ip_ct_event_cache_flush(); i_see_dead_people: ip_ct_iterate_cleanup(kill_all, NULL); if (atomic_read(&ip_conntrack_count) != 0) { @@ -1115,7 +1363,14 @@ void ip_conntrack_cleanup(void) /* wait until all references to ip_conntrack_untracked are dropped */ while (atomic_read(&ip_conntrack_untracked.ct_general.use) > 1) schedule(); +} +/* Mishearing the voices in his head, our hero wonders how he's + supposed to kill the mall. */ +void ip_conntrack_cleanup(void) +{ + ip_ct_attach = NULL; + ip_conntrack_flush(); kmem_cache_destroy(ip_conntrack_cachep); kmem_cache_destroy(ip_conntrack_expect_cachep); free_conntrack_hash(); diff --git a/net/ipv4/netfilter/ip_conntrack_ftp.c b/net/ipv4/netfilter/ip_conntrack_ftp.c index 7a3b773be3f..3a2627db172 100644 --- a/net/ipv4/netfilter/ip_conntrack_ftp.c +++ b/net/ipv4/netfilter/ip_conntrack_ftp.c @@ -25,8 +25,7 @@ MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); MODULE_DESCRIPTION("ftp connection tracking helper"); /* This is slow, but it's simple. --RR */ -static char ftp_buffer[65536]; - +static char *ftp_buffer; static DEFINE_SPINLOCK(ip_ftp_lock); #define MAX_PORTS 8 @@ -262,7 +261,8 @@ static int find_nl_seq(u32 seq, const struct ip_ct_ftp_master *info, int dir) } /* We don't update if it's older than what we have. */ -static void update_nl_seq(u32 nl_seq, struct ip_ct_ftp_master *info, int dir) +static void update_nl_seq(u32 nl_seq, struct ip_ct_ftp_master *info, int dir, + struct sk_buff *skb) { unsigned int i, oldest = NUM_SEQ_TO_REMEMBER; @@ -276,10 +276,13 @@ static void update_nl_seq(u32 nl_seq, struct ip_ct_ftp_master *info, int dir) oldest = i; } - if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) + if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) { info->seq_aft_nl[dir][info->seq_aft_nl_num[dir]++] = nl_seq; - else if (oldest != NUM_SEQ_TO_REMEMBER) + ip_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, skb); + } else if (oldest != NUM_SEQ_TO_REMEMBER) { info->seq_aft_nl[dir][oldest] = nl_seq; + ip_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, skb); + } } static int help(struct sk_buff **pskb, @@ -439,7 +442,7 @@ out_update_nl: /* Now if this ends in \n, update ftp info. Seq may have been * adjusted by NAT code. */ if (ends_in_nl) - update_nl_seq(seq, ct_ftp_info,dir); + update_nl_seq(seq, ct_ftp_info,dir, *pskb); out: spin_unlock_bh(&ip_ftp_lock); return ret; @@ -457,6 +460,8 @@ static void fini(void) ports[i]); ip_conntrack_helper_unregister(&ftp[i]); } + + kfree(ftp_buffer); } static int __init init(void) @@ -464,6 +469,10 @@ static int __init init(void) int i, ret; char *tmpname; + ftp_buffer = kmalloc(65536, GFP_KERNEL); + if (!ftp_buffer) + return -ENOMEM; + if (ports_c == 0) ports[ports_c++] = FTP_PORT; diff --git a/net/ipv4/netfilter/ip_conntrack_irc.c b/net/ipv4/netfilter/ip_conntrack_irc.c index 4a28f297d50..25438eec21a 100644 --- a/net/ipv4/netfilter/ip_conntrack_irc.c +++ b/net/ipv4/netfilter/ip_conntrack_irc.c @@ -39,7 +39,7 @@ static int ports_c; static int max_dcc_channels = 8; static unsigned int dcc_timeout = 300; /* This is slow, but it's simple. --RR */ -static char irc_buffer[65536]; +static char *irc_buffer; static DEFINE_SPINLOCK(irc_buffer_lock); unsigned int (*ip_nat_irc_hook)(struct sk_buff **pskb, @@ -257,6 +257,10 @@ static int __init init(void) printk("ip_conntrack_irc: dcc_timeout must be a positive integer\n"); return -EBUSY; } + + irc_buffer = kmalloc(65536, GFP_KERNEL); + if (!irc_buffer) + return -ENOMEM; /* If no port given, default to standard irc port */ if (ports_c == 0) @@ -304,6 +308,7 @@ static void fini(void) ports[i]); ip_conntrack_helper_unregister(&irc_helpers[i]); } + kfree(irc_buffer); } module_init(init); diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c new file mode 100644 index 00000000000..a4e9278db4e --- /dev/null +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -0,0 +1,1579 @@ +/* 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. + */ + +#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/rtnetlink.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ip_conntrack.h> +#include <linux/netfilter_ipv4/ip_conntrack_core.h> +#include <linux/netfilter_ipv4/ip_conntrack_helper.h> +#include <linux/netfilter_ipv4/ip_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[] = "0.90"; + +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(format, args...) +#endif + + +static inline int +ctnetlink_dump_tuples_proto(struct sk_buff *skb, + const struct ip_conntrack_tuple *tuple) +{ + struct ip_conntrack_protocol *proto; + + NFA_PUT(skb, CTA_PROTO_NUM, sizeof(u_int8_t), &tuple->dst.protonum); + + proto = ip_conntrack_proto_find_get(tuple->dst.protonum); + if (proto && proto->tuple_to_nfattr) + return proto->tuple_to_nfattr(skb, tuple); + + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_tuples(struct sk_buff *skb, + const struct ip_conntrack_tuple *tuple) +{ + struct nfattr *nest_parms; + + nest_parms = NFA_NEST(skb, CTA_TUPLE_IP); + NFA_PUT(skb, CTA_IP_V4_SRC, sizeof(u_int32_t), &tuple->src.ip); + NFA_PUT(skb, CTA_IP_V4_DST, sizeof(u_int32_t), &tuple->dst.ip); + NFA_NEST_END(skb, nest_parms); + + nest_parms = NFA_NEST(skb, CTA_TUPLE_PROTO); + ctnetlink_dump_tuples_proto(skb, tuple); + NFA_NEST_END(skb, nest_parms); + + return 0; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_dump_status(struct sk_buff *skb, const struct ip_conntrack *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 ip_conntrack *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 ip_conntrack *ct) +{ + struct ip_conntrack_protocol *proto = ip_conntrack_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum); + + struct nfattr *nest_proto; + int ret; + + if (!proto || !proto->to_nfattr) + return 0; + + nest_proto = NFA_NEST(skb, CTA_PROTOINFO); + + ret = proto->to_nfattr(skb, nest_proto, ct); + + ip_conntrack_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 ip_conntrack *ct) +{ + struct nfattr *nest_helper; + + if (!ct->helper) + return 0; + + nest_helper = NFA_NEST(skb, CTA_HELP); + NFA_PUT(skb, CTA_HELP_NAME, CTA_HELP_MAXNAMESIZE, &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_IP_NF_CT_ACCT +static inline int +ctnetlink_dump_counters(struct sk_buff *skb, const struct ip_conntrack *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_int64_t tmp; + + tmp = cpu_to_be64(ct->counters[dir].packets); + NFA_PUT(skb, CTA_COUNTERS_PACKETS, sizeof(u_int64_t), &tmp); + + tmp = cpu_to_be64(ct->counters[dir].bytes); + NFA_PUT(skb, CTA_COUNTERS_BYTES, sizeof(u_int64_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_IP_NF_CONNTRACK_MARK +static inline int +ctnetlink_dump_mark(struct sk_buff *skb, const struct ip_conntrack *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 ip_conntrack *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 ip_conntrack *ct) +{ + unsigned int 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 ip_conntrack *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 = AF_INET; + 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_IP_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 ip_conntrack *ct = (struct ip_conntrack *)ptr; + struct sk_buff *skb; + unsigned int type; + unsigned char *b; + unsigned int flags = 0, group; + + /* ignore our fake conntrack entry */ + if (ct == &ip_conntrack_untracked) + return NOTIFY_DONE; + + if (events & IPCT_DESTROY) { + type = IPCTNL_MSG_CT_DELETE; + group = NFNLGRP_CONNTRACK_DESTROY; + goto alloc_skb; + } + 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; + goto alloc_skb; + } + if (events & (IPCT_STATUS | + IPCT_PROTOINFO | + IPCT_HELPER | + IPCT_HELPINFO | + IPCT_NATINFO)) { + type = IPCTNL_MSG_CT_NEW; + group = NFNLGRP_CONNTRACK_UPDATE; + goto alloc_skb; + } + + return NOTIFY_DONE; + +alloc_skb: + /* 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 = AF_INET; + 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_IP_NF_CONNTRACK_EVENTS */ + +static int ctnetlink_done(struct netlink_callback *cb) +{ + DEBUGP("entered %s\n", __FUNCTION__); + return 0; +} + +static int +ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ip_conntrack *ct = NULL; + struct ip_conntrack_tuple_hash *h; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[1]; + + DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__, + cb->args[0], *id); + + read_lock_bh(&ip_conntrack_lock); + for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) { + list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) { + h = (struct ip_conntrack_tuple_hash *) i; + if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = tuplehash_to_ctrack(h); + 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(&ip_conntrack_lock); + + DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); + + return skb->len; +} + +#ifdef CONFIG_IP_NF_CT_ACCT +static int +ctnetlink_dump_table_w(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ip_conntrack *ct = NULL; + struct ip_conntrack_tuple_hash *h; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[1]; + + DEBUGP("entered %s, last bucket=%u id=%u\n", __FUNCTION__, + cb->args[0], *id); + + write_lock_bh(&ip_conntrack_lock); + for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++, *id = 0) { + list_for_each_prev(i, &ip_conntrack_hash[cb->args[0]]) { + h = (struct ip_conntrack_tuple_hash *) i; + if (DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = tuplehash_to_ctrack(h); + 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(&ip_conntrack_lock); + + DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id); + + return skb->len; +} +#endif + +static const int cta_min_ip[CTA_IP_MAX] = { + [CTA_IP_V4_SRC-1] = sizeof(u_int32_t), + [CTA_IP_V4_DST-1] = sizeof(u_int32_t), +}; + +static inline int +ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple) +{ + struct nfattr *tb[CTA_IP_MAX]; + + DEBUGP("entered %s\n", __FUNCTION__); + + + if (nfattr_parse_nested(tb, CTA_IP_MAX, attr) < 0) + goto nfattr_failure; + + if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip)) + return -EINVAL; + + if (!tb[CTA_IP_V4_SRC-1]) + return -EINVAL; + tuple->src.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_SRC-1]); + + if (!tb[CTA_IP_V4_DST-1]) + return -EINVAL; + tuple->dst.ip = *(u_int32_t *)NFA_DATA(tb[CTA_IP_V4_DST-1]); + + DEBUGP("leaving\n"); + + return 0; + +nfattr_failure: + return -1; +} + +static const int cta_min_proto[CTA_PROTO_MAX] = { + [CTA_PROTO_NUM-1] = sizeof(u_int16_t), + [CTA_PROTO_SRC_PORT-1] = sizeof(u_int16_t), + [CTA_PROTO_DST_PORT-1] = sizeof(u_int16_t), + [CTA_PROTO_ICMP_TYPE-1] = sizeof(u_int8_t), + [CTA_PROTO_ICMP_CODE-1] = sizeof(u_int8_t), + [CTA_PROTO_ICMP_ID-1] = sizeof(u_int16_t), +}; + +static inline int +ctnetlink_parse_tuple_proto(struct nfattr *attr, + struct ip_conntrack_tuple *tuple) +{ + struct nfattr *tb[CTA_PROTO_MAX]; + struct ip_conntrack_protocol *proto; + int ret = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_parse_nested(tb, CTA_PROTO_MAX, attr) < 0) + goto nfattr_failure; + + 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_int16_t *)NFA_DATA(tb[CTA_PROTO_NUM-1]); + + proto = ip_conntrack_proto_find_get(tuple->dst.protonum); + + if (likely(proto && proto->nfattr_to_tuple)) { + ret = proto->nfattr_to_tuple(tb, tuple); + ip_conntrack_proto_put(proto); + } + + return ret; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple, + enum ctattr_tuple type) +{ + struct nfattr *tb[CTA_TUPLE_MAX]; + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + memset(tuple, 0, sizeof(*tuple)); + + if (nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]) < 0) + goto nfattr_failure; + + if (!tb[CTA_TUPLE_IP-1]) + return -EINVAL; + + 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; + + DUMP_TUPLE(tuple); + + DEBUGP("leaving\n"); + + return 0; + +nfattr_failure: + return -1; +} + +#ifdef CONFIG_IP_NF_NAT_NEEDED +static const int 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 ip_conntrack *ct, + struct ip_nat_range *range) +{ + struct nfattr *tb[CTA_PROTONAT_MAX]; + struct ip_nat_protocol *npt; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr) < 0) + goto nfattr_failure; + + if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat)) + goto nfattr_failure; + + npt = ip_nat_proto_find_get(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum); + if (!npt) + return 0; + + 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; + +nfattr_failure: + return -1; +} + +static inline int +ctnetlink_parse_nat(struct nfattr *cda[], + const struct ip_conntrack *ct, struct ip_nat_range *range) +{ + struct nfattr *tb[CTA_NAT_MAX]; + int err; + + DEBUGP("entered %s\n", __FUNCTION__); + + memset(range, 0, sizeof(*range)); + + if (nfattr_parse_nested(tb, CTA_NAT_MAX, cda[CTA_NAT-1]) < 0) + goto nfattr_failure; + + 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; + +nfattr_failure: + return -1; +} +#endif + +static inline int +ctnetlink_parse_help(struct nfattr *attr, char **helper_name) +{ + struct nfattr *tb[CTA_HELP_MAX]; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nfattr_parse_nested(tb, CTA_HELP_MAX, attr) < 0) + goto nfattr_failure; + + if (!tb[CTA_HELP_NAME-1]) + return -EINVAL; + + *helper_name = NFA_DATA(tb[CTA_HELP_NAME-1]); + + return 0; + +nfattr_failure: + return -1; +} + +static int +ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct ip_conntrack_tuple_hash *h; + struct ip_conntrack_tuple tuple; + struct ip_conntrack *ct; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (cda[CTA_TUPLE_ORIG-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG); + else if (cda[CTA_TUPLE_REPLY-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY); + else { + /* Flush the whole table */ + ip_conntrack_flush(); + return 0; + } + + if (err < 0) + return err; + + h = ip_conntrack_find_get(&tuple, NULL); + if (!h) { + DEBUGP("tuple not found in conntrack hash\n"); + return -ENOENT; + } + + 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) { + ip_conntrack_put(ct); + return -ENOENT; + } + } + if (del_timer(&ct->timeout)) { + ip_conntrack_put(ct); + ct->timeout.function((unsigned long)ct); + return 0; + } + ip_conntrack_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 ip_conntrack_tuple_hash *h; + struct ip_conntrack_tuple tuple; + struct ip_conntrack *ct; + struct sk_buff *skb2 = NULL; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct nfgenmsg *msg = NLMSG_DATA(nlh); + u32 rlen; + + if (msg->nfgen_family != AF_INET) + return -EAFNOSUPPORT; + + if (NFNL_MSG_TYPE(nlh->nlmsg_type) == + IPCTNL_MSG_CT_GET_CTRZERO) { +#ifdef CONFIG_IP_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 (cda[CTA_TUPLE_ORIG-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG); + else if (cda[CTA_TUPLE_REPLY-1]) + err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY); + else + return -EINVAL; + + if (err < 0) + return err; + + h = ip_conntrack_find_get(&tuple, NULL); + if (!h) { + DEBUGP("tuple not found in conntrack hash"); + return -ENOENT; + } + DEBUGP("tuple found\n"); + ct = tuplehash_to_ctrack(h); + + err = -ENOMEM; + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!skb2) { + ip_conntrack_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); + ip_conntrack_put(ct); + if (err <= 0) + goto out; + + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto out; + + DEBUGP("leaving\n"); + return 0; + +out: + if (skb2) + kfree_skb(skb2); + return -1; +} + +static inline int +ctnetlink_change_status(struct ip_conntrack *ct, struct nfattr *cda[]) +{ + unsigned long d, status = *(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, 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 ip_conntrack *ct, struct nfattr *cda[]) +{ + struct ip_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 = __ip_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 ... */ + ip_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 ip_conntrack *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 int +ctnetlink_change_conntrack(struct ip_conntrack *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; + } + + DEBUGP("all done\n"); + return 0; +} + +static int +ctnetlink_create_conntrack(struct nfattr *cda[], + struct ip_conntrack_tuple *otuple, + struct ip_conntrack_tuple *rtuple) +{ + struct ip_conntrack *ct; + int err = -EINVAL; + + DEBUGP("entered %s\n", __FUNCTION__); + + ct = ip_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; + + ct->helper = ip_conntrack_helper_find_get(rtuple); + + add_timer(&ct->timeout); + ip_conntrack_hash_insert(ct); + + if (ct->helper) + ip_conntrack_helper_put(ct->helper); + + DEBUGP("conntrack with id %u inserted\n", ct->id); + return 0; + +err: + ip_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 ip_conntrack_tuple otuple, rtuple; + struct ip_conntrack_tuple_hash *h = NULL; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (cda[CTA_TUPLE_ORIG-1]) { + err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG); + if (err < 0) + return err; + } + + if (cda[CTA_TUPLE_REPLY-1]) { + err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY); + if (err < 0) + return err; + } + + write_lock_bh(&ip_conntrack_lock); + if (cda[CTA_TUPLE_ORIG-1]) + h = __ip_conntrack_find(&otuple, NULL); + else if (cda[CTA_TUPLE_REPLY-1]) + h = __ip_conntrack_find(&rtuple, NULL); + + if (h == NULL) { + write_unlock_bh(&ip_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(tuplehash_to_ctrack(h), cda); + +out_unlock: + write_unlock_bh(&ip_conntrack_lock); + return err; +} + +/*********************************************************************** + * EXPECT + ***********************************************************************/ + +static inline int +ctnetlink_exp_dump_tuple(struct sk_buff *skb, + const struct ip_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 ip_conntrack_expect *exp) +{ + struct ip_conntrack *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 ip_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 = AF_INET; + 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_IP_NF_CONNTRACK_EVENTS +static int ctnetlink_expect_event(struct notifier_block *this, + unsigned long events, void *ptr) +{ + struct nlmsghdr *nlh; + struct nfgenmsg *nfmsg; + struct ip_conntrack_expect *exp = (struct ip_conntrack_expect *)ptr; + struct sk_buff *skb; + unsigned int type; + unsigned char *b; + int flags = 0; + u16 proto; + + 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 = AF_INET; + 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; + proto = exp->tuple.dst.protonum; + 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 ip_conntrack_expect *exp = NULL; + struct list_head *i; + u_int32_t *id = (u_int32_t *) &cb->args[0]; + + DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id); + + read_lock_bh(&ip_conntrack_lock); + list_for_each_prev(i, &ip_conntrack_expect_list) { + exp = (struct ip_conntrack_expect *) i; + 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(&ip_conntrack_lock); + + DEBUGP("leaving, last id=%llu\n", *id); + + return skb->len; +} + +static int +ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct ip_conntrack_tuple tuple; + struct ip_conntrack_expect *exp; + struct sk_buff *skb2; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct nfgenmsg *msg = NLMSG_DATA(nlh); + u32 rlen; + + if (msg->nfgen_family != AF_INET) + return -EAFNOSUPPORT; + + 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); + else + return -EINVAL; + + if (err < 0) + return err; + + exp = ip_conntrack_expect_find_get(&tuple); + if (!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 out; + + ip_conntrack_expect_put(exp); + + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto free; + + return err; + +out: + ip_conntrack_expect_put(exp); +free: + if (skb2) + kfree_skb(skb2); + return err; +} + +static int +ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, + struct nlmsghdr *nlh, struct nfattr *cda[], int *errp) +{ + struct ip_conntrack_expect *exp, *tmp; + struct ip_conntrack_tuple tuple; + struct ip_conntrack_helper *h; + int err; + + if (cda[CTA_EXPECT_TUPLE-1]) { + /* delete a single expect by tuple */ + err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE); + if (err < 0) + return err; + + /* bump usage count to 2 */ + exp = ip_conntrack_expect_find_get(&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)) { + ip_conntrack_expect_put(exp); + return -ENOENT; + } + } + + /* after list removal, usage count == 1 */ + ip_conntrack_unexpect_related(exp); + /* have to put what we 'get' above. + * after this line usage count == 0 */ + ip_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(&ip_conntrack_lock); + h = __ip_conntrack_helper_find_byname(name); + if (!h) { + write_unlock_bh(&ip_conntrack_lock); + return -EINVAL; + } + list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list, + list) { + if (exp->master->helper == h + && del_timer(&exp->timeout)) + __ip_ct_expect_unlink_destroy(exp); + } + write_unlock(&ip_conntrack_lock); + } else { + /* This basically means we have to flush everything*/ + write_lock_bh(&ip_conntrack_lock); + list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list, + list) { + if (del_timer(&exp->timeout)) + __ip_ct_expect_unlink_destroy(exp); + } + write_unlock_bh(&ip_conntrack_lock); + } + + return 0; +} +static int +ctnetlink_change_expect(struct ip_conntrack_expect *x, struct nfattr *cda[]) +{ + return -EOPNOTSUPP; +} + +static int +ctnetlink_create_expect(struct nfattr *cda[]) +{ + struct ip_conntrack_tuple tuple, mask, master_tuple; + struct ip_conntrack_tuple_hash *h = NULL; + struct ip_conntrack_expect *exp; + struct ip_conntrack *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); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK); + if (err < 0) + return err; + err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER); + if (err < 0) + return err; + + /* Look for master conntrack of this expectation */ + h = ip_conntrack_find_get(&master_tuple, NULL); + if (!h) + return -ENOENT; + ct = tuplehash_to_ctrack(h); + + if (!ct->helper) { + /* such conntrack hasn't got any helper, abort */ + err = -EINVAL; + goto out; + } + + exp = ip_conntrack_expect_alloc(ct); + if (!exp) { + err = -ENOMEM; + goto out; + } + + exp->expectfn = NULL; + exp->master = ct; + memcpy(&exp->tuple, &tuple, sizeof(struct ip_conntrack_tuple)); + memcpy(&exp->mask, &mask, sizeof(struct ip_conntrack_tuple)); + + err = ip_conntrack_expect_related(exp); + ip_conntrack_expect_put(exp); + +out: + ip_conntrack_put(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 ip_conntrack_tuple tuple; + struct ip_conntrack_expect *exp; + int err = 0; + + DEBUGP("entered %s\n", __FUNCTION__); + + 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); + if (err < 0) + return err; + + write_lock_bh(&ip_conntrack_lock); + exp = __ip_conntrack_expect_find(&tuple); + + if (!exp) { + write_unlock_bh(&ip_conntrack_lock); + err = -ENOENT; + if (nlh->nlmsg_flags & NLM_F_CREATE) + err = ctnetlink_create_expect(cda); + return err; + } + + err = -EEXIST; + if (!(nlh->nlmsg_flags & NLM_F_EXCL)) + err = ctnetlink_change_expect(exp, cda); + write_unlock_bh(&ip_conntrack_lock); + + DEBUGP("leaving\n"); + + return err; +} + +#ifdef CONFIG_IP_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, + .cap_required = CAP_NET_ADMIN }, + [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, + .attr_count = CTA_MAX, + .cap_required = CAP_NET_ADMIN }, + [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, + .attr_count = CTA_MAX, + .cap_required = CAP_NET_ADMIN }, + [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, + .attr_count = CTA_MAX, + .cap_required = CAP_NET_ADMIN }, +}; + +static struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { + [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, + .attr_count = CTA_EXPECT_MAX, + .cap_required = CAP_NET_ADMIN }, + [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, + .attr_count = CTA_EXPECT_MAX, + .cap_required = CAP_NET_ADMIN }, + [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, + .attr_count = CTA_EXPECT_MAX, + .cap_required = CAP_NET_ADMIN }, +}; + +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, +}; + +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_IP_NF_CONNTRACK_EVENTS + ret = ip_conntrack_register_notifier(&ctnl_notifier); + if (ret < 0) { + printk("ctnetlink_init: cannot register notifier.\n"); + goto err_unreg_exp_subsys; + } + + ret = ip_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_IP_NF_CONNTRACK_EVENTS +err_unreg_notifier: + ip_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_IP_NF_CONNTRACK_EVENTS + ip_conntrack_unregister_notifier(&ctnl_notifier_exp); + ip_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/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index 602c74db325..838d1d69b36 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -102,22 +102,24 @@ static int icmp_packet(struct ip_conntrack *ct, ct->timeout.function((unsigned long)ct); } else { atomic_inc(&ct->proto.icmp.count); + ip_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb); ip_ct_refresh_acct(ct, ctinfo, skb, ip_ct_icmp_timeout); } return NF_ACCEPT; } +static u_int8_t valid_new[] = { + [ICMP_ECHO] = 1, + [ICMP_TIMESTAMP] = 1, + [ICMP_INFO_REQUEST] = 1, + [ICMP_ADDRESS] = 1 +}; + /* Called when a new connection for this protocol found. */ static int icmp_new(struct ip_conntrack *conntrack, const struct sk_buff *skb) { - static u_int8_t valid_new[] - = { [ICMP_ECHO] = 1, - [ICMP_TIMESTAMP] = 1, - [ICMP_INFO_REQUEST] = 1, - [ICMP_ADDRESS] = 1 }; - if (conntrack->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || !valid_new[conntrack->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ @@ -158,11 +160,12 @@ icmp_error_message(struct sk_buff *skb, return NF_ACCEPT; } - innerproto = ip_ct_find_proto(inside->ip.protocol); + innerproto = ip_conntrack_proto_find_get(inside->ip.protocol); dataoff = skb->nh.iph->ihl*4 + sizeof(inside->icmp) + inside->ip.ihl*4; /* Are they talking about one of our connections? */ if (!ip_ct_get_tuple(&inside->ip, skb, dataoff, &origtuple, innerproto)) { DEBUGP("icmp_error: ! get_tuple p=%u", inside->ip.protocol); + ip_conntrack_proto_put(innerproto); return NF_ACCEPT; } @@ -170,8 +173,10 @@ icmp_error_message(struct sk_buff *skb, been preserved inside the ICMP. */ if (!ip_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { DEBUGP("icmp_error_track: Can't invert tuple\n"); + ip_conntrack_proto_put(innerproto); return NF_ACCEPT; } + ip_conntrack_proto_put(innerproto); *ctinfo = IP_CT_RELATED; @@ -212,7 +217,7 @@ icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, icmph = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_ih), &_ih); if (icmph == NULL) { if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_icmp: short packet "); return -NF_ACCEPT; } @@ -226,13 +231,13 @@ icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, if (!(u16)csum_fold(skb->csum)) break; if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_icmp: bad HW ICMP checksum "); return -NF_ACCEPT; case CHECKSUM_NONE: if ((u16)csum_fold(skb_checksum(skb, 0, skb->len, 0))) { if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_icmp: bad ICMP checksum "); return -NF_ACCEPT; } @@ -249,7 +254,7 @@ checksum_skipped: */ if (icmph->type > NR_ICMP_TYPES) { if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_icmp: invalid ICMP type "); return -NF_ACCEPT; } @@ -265,6 +270,47 @@ checksum_skipped: return icmp_error_message(skb, ctinfo, hooknum); } +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +static int icmp_tuple_to_nfattr(struct sk_buff *skb, + const struct ip_conntrack_tuple *t) +{ + NFA_PUT(skb, CTA_PROTO_ICMP_ID, sizeof(u_int16_t), + &t->src.u.icmp.id); + NFA_PUT(skb, CTA_PROTO_ICMP_TYPE, sizeof(u_int8_t), + &t->dst.u.icmp.type); + NFA_PUT(skb, CTA_PROTO_ICMP_CODE, sizeof(u_int8_t), + &t->dst.u.icmp.code); + + if (t->dst.u.icmp.type >= sizeof(valid_new) + || !valid_new[t->dst.u.icmp.type]) + return -EINVAL; + + return 0; + +nfattr_failure: + return -1; +} + +static int icmp_nfattr_to_tuple(struct nfattr *tb[], + struct ip_conntrack_tuple *tuple) +{ + if (!tb[CTA_PROTO_ICMP_TYPE-1] + || !tb[CTA_PROTO_ICMP_CODE-1] + || !tb[CTA_PROTO_ICMP_ID-1]) + return -1; + + tuple->dst.u.icmp.type = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_TYPE-1]); + tuple->dst.u.icmp.code = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_CODE-1]); + tuple->src.u.icmp.id = + *(u_int8_t *)NFA_DATA(tb[CTA_PROTO_ICMP_ID-1]); + + return 0; +} +#endif + struct ip_conntrack_protocol ip_conntrack_protocol_icmp = { .proto = IPPROTO_ICMP, @@ -276,4 +322,9 @@ struct ip_conntrack_protocol ip_conntrack_protocol_icmp = .packet = icmp_packet, .new = icmp_new, .error = icmp_error, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .tuple_to_nfattr = icmp_tuple_to_nfattr, + .nfattr_to_tuple = icmp_nfattr_to_tuple, +#endif }; diff --git a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c index 31d75390bf1..a875f35e576 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_sctp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_sctp.c @@ -404,6 +404,8 @@ static int sctp_packet(struct ip_conntrack *conntrack, } conntrack->proto.sctp.state = newconntrack; + if (oldsctpstate != newconntrack) + ip_conntrack_event_cache(IPCT_PROTOINFO, skb); write_unlock_bh(&sctp_lock); } @@ -503,7 +505,12 @@ static struct ip_conntrack_protocol ip_conntrack_protocol_sctp = { .packet = sctp_packet, .new = sctp_new, .destroy = NULL, - .me = THIS_MODULE + .me = THIS_MODULE, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .tuple_to_nfattr = ip_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = ip_ct_port_nfattr_to_tuple, +#endif }; #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index 809dfed766d..f23ef1f88c4 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -336,6 +336,23 @@ static int tcp_print_conntrack(struct seq_file *s, return seq_printf(s, "%s ", tcp_conntrack_names[state]); } +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa, + const struct ip_conntrack *ct) +{ + read_lock_bh(&tcp_lock); + NFA_PUT(skb, CTA_PROTOINFO_TCP_STATE, sizeof(u_int8_t), + &ct->proto.tcp.state); + read_unlock_bh(&tcp_lock); + + return 0; + +nfattr_failure: + return -1; +} +#endif + static unsigned int get_conntrack_index(const struct tcphdr *tcph) { if (tcph->rst) return TCP_RST_SET; @@ -699,7 +716,7 @@ static int tcp_in_window(struct ip_ct_tcp *state, res = 1; } else { if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: %s ", before(seq, sender->td_maxend + 1) ? after(end, sender->td_end - receiver->td_maxwin - 1) ? @@ -798,7 +815,7 @@ static int tcp_error(struct sk_buff *skb, sizeof(_tcph), &_tcph); if (th == NULL) { if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: short packet "); return -NF_ACCEPT; } @@ -806,7 +823,7 @@ static int tcp_error(struct sk_buff *skb, /* Not whole TCP header or malformed packet */ if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) { if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: truncated/malformed packet "); return -NF_ACCEPT; } @@ -823,7 +840,7 @@ static int tcp_error(struct sk_buff *skb, skb->ip_summed == CHECKSUM_HW ? skb->csum : skb_checksum(skb, iph->ihl*4, tcplen, 0))) { if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: bad TCP checksum "); return -NF_ACCEPT; } @@ -832,7 +849,7 @@ static int tcp_error(struct sk_buff *skb, tcpflags = (((u_int8_t *)th)[13] & ~(TH_ECE|TH_CWR)); if (!tcp_valid_flags[tcpflags]) { if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: invalid TCP flag combination "); return -NF_ACCEPT; } @@ -880,8 +897,9 @@ static int tcp_packet(struct ip_conntrack *conntrack, */ write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, - "ip_ct_tcp: killing out of sync session "); + nf_log_packet(PF_INET, 0, skb, NULL, NULL, + NULL, "ip_ct_tcp: " + "killing out of sync session "); if (del_timer(&conntrack->timeout)) conntrack->timeout.function((unsigned long) conntrack); @@ -895,7 +913,7 @@ static int tcp_packet(struct ip_conntrack *conntrack, write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: invalid packet ignored "); return NF_ACCEPT; case TCP_CONNTRACK_MAX: @@ -905,7 +923,7 @@ static int tcp_packet(struct ip_conntrack *conntrack, old_state); write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: invalid state "); return -NF_ACCEPT; case TCP_CONNTRACK_SYN_SENT: @@ -926,7 +944,7 @@ static int tcp_packet(struct ip_conntrack *conntrack, write_unlock_bh(&tcp_lock); if (LOG_INVALID(IPPROTO_TCP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, - "ip_ct_tcp: invalid SYN"); + NULL, "ip_ct_tcp: invalid SYN"); return -NF_ACCEPT; } case TCP_CONNTRACK_CLOSE: @@ -973,6 +991,10 @@ static int tcp_packet(struct ip_conntrack *conntrack, ? ip_ct_tcp_timeout_max_retrans : *tcp_timeouts[new_state]; write_unlock_bh(&tcp_lock); + ip_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb); + if (new_state != old_state) + ip_conntrack_event_cache(IPCT_PROTOINFO, skb); + if (!test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)) { /* If only reply is a RST, we can consider ourselves not to have an established connection: this is a fairly common @@ -1096,4 +1118,10 @@ struct ip_conntrack_protocol ip_conntrack_protocol_tcp = .packet = tcp_packet, .new = tcp_new, .error = tcp_error, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .to_nfattr = tcp_to_nfattr, + .tuple_to_nfattr = ip_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = ip_ct_port_nfattr_to_tuple, +#endif }; diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 8c1eaba098d..f2dcac7c766 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -73,7 +73,8 @@ static int udp_packet(struct ip_conntrack *conntrack, ip_ct_refresh_acct(conntrack, ctinfo, skb, ip_ct_udp_timeout_stream); /* Also, more likely to be important, and not a probe */ - set_bit(IPS_ASSURED_BIT, &conntrack->status); + if (!test_and_set_bit(IPS_ASSURED_BIT, &conntrack->status)) + ip_conntrack_event_cache(IPCT_STATUS, skb); } else ip_ct_refresh_acct(conntrack, ctinfo, skb, ip_ct_udp_timeout); @@ -97,7 +98,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, hdr = skb_header_pointer(skb, iph->ihl*4, sizeof(_hdr), &_hdr); if (hdr == NULL) { if (LOG_INVALID(IPPROTO_UDP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_udp: short packet "); return -NF_ACCEPT; } @@ -105,7 +106,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, /* Truncated/malformed packets */ if (ntohs(hdr->len) > udplen || ntohs(hdr->len) < sizeof(*hdr)) { if (LOG_INVALID(IPPROTO_UDP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_udp: truncated/malformed packet "); return -NF_ACCEPT; } @@ -125,7 +126,7 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, skb->ip_summed == CHECKSUM_HW ? skb->csum : skb_checksum(skb, iph->ihl*4, udplen, 0))) { if (LOG_INVALID(IPPROTO_UDP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_udp: bad UDP checksum "); return -NF_ACCEPT; } @@ -144,4 +145,9 @@ struct ip_conntrack_protocol ip_conntrack_protocol_udp = .packet = udp_packet, .new = udp_new, .error = udp_error, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .tuple_to_nfattr = ip_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = ip_ct_port_nfattr_to_tuple, +#endif }; diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 61798c46e91..ee5895afd0c 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -5,7 +5,7 @@ */ /* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -147,8 +147,7 @@ static int ct_seq_show(struct seq_file *s, void *v) if (DIRECTION(hash)) return 0; - proto = ip_ct_find_proto(conntrack->tuplehash[IP_CT_DIR_ORIGINAL] - .tuple.dst.protonum); + proto = __ip_conntrack_proto_find(conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum); IP_NF_ASSERT(proto); if (seq_printf(s, "%-8s %u %ld ", @@ -185,7 +184,7 @@ static int ct_seq_show(struct seq_file *s, void *v) return -ENOSPC; #if defined(CONFIG_IP_NF_CONNTRACK_MARK) - if (seq_printf(s, "mark=%lu ", conntrack->mark)) + if (seq_printf(s, "mark=%u ", conntrack->mark)) return -ENOSPC; #endif @@ -283,7 +282,7 @@ static int exp_seq_show(struct seq_file *s, void *v) seq_printf(s, "proto=%u ", expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, - ip_ct_find_proto(expect->tuple.dst.protonum)); + __ip_conntrack_proto_find(expect->tuple.dst.protonum)); return seq_putc(s, '\n'); } @@ -889,6 +888,7 @@ static int init_or_cleanup(int init) return ret; cleanup: + synchronize_net(); #ifdef CONFIG_SYSCTL unregister_sysctl_table(ip_ct_sysctl_header); cleanup_localinops: @@ -971,6 +971,14 @@ void need_ip_conntrack(void) { } +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +EXPORT_SYMBOL_GPL(ip_conntrack_chain); +EXPORT_SYMBOL_GPL(ip_conntrack_expect_chain); +EXPORT_SYMBOL_GPL(ip_conntrack_register_notifier); +EXPORT_SYMBOL_GPL(ip_conntrack_unregister_notifier); +EXPORT_SYMBOL_GPL(__ip_ct_event_cache_init); +EXPORT_PER_CPU_SYMBOL_GPL(ip_conntrack_ecache); +#endif EXPORT_SYMBOL(ip_conntrack_protocol_register); EXPORT_SYMBOL(ip_conntrack_protocol_unregister); EXPORT_SYMBOL(ip_ct_get_tuple); @@ -982,12 +990,16 @@ EXPORT_SYMBOL(ip_conntrack_helper_register); EXPORT_SYMBOL(ip_conntrack_helper_unregister); EXPORT_SYMBOL(ip_ct_iterate_cleanup); EXPORT_SYMBOL(ip_ct_refresh_acct); -EXPORT_SYMBOL(ip_ct_protos); -EXPORT_SYMBOL(ip_ct_find_proto); + EXPORT_SYMBOL(ip_conntrack_expect_alloc); EXPORT_SYMBOL(ip_conntrack_expect_put); +EXPORT_SYMBOL_GPL(ip_conntrack_expect_find_get); EXPORT_SYMBOL(ip_conntrack_expect_related); EXPORT_SYMBOL(ip_conntrack_unexpect_related); +EXPORT_SYMBOL_GPL(ip_conntrack_expect_list); +EXPORT_SYMBOL_GPL(__ip_conntrack_expect_find); +EXPORT_SYMBOL_GPL(__ip_ct_expect_unlink_destroy); + EXPORT_SYMBOL(ip_conntrack_tuple_taken); EXPORT_SYMBOL(ip_ct_gather_frags); EXPORT_SYMBOL(ip_conntrack_htable_size); @@ -995,7 +1007,28 @@ EXPORT_SYMBOL(ip_conntrack_lock); EXPORT_SYMBOL(ip_conntrack_hash); EXPORT_SYMBOL(ip_conntrack_untracked); EXPORT_SYMBOL_GPL(ip_conntrack_find_get); -EXPORT_SYMBOL_GPL(ip_conntrack_put); #ifdef CONFIG_IP_NF_NAT_NEEDED EXPORT_SYMBOL(ip_conntrack_tcp_update); #endif + +EXPORT_SYMBOL_GPL(ip_conntrack_flush); +EXPORT_SYMBOL_GPL(__ip_conntrack_find); + +EXPORT_SYMBOL_GPL(ip_conntrack_alloc); +EXPORT_SYMBOL_GPL(ip_conntrack_free); +EXPORT_SYMBOL_GPL(ip_conntrack_hash_insert); + +EXPORT_SYMBOL_GPL(ip_ct_remove_expectations); + +EXPORT_SYMBOL_GPL(ip_conntrack_helper_find_get); +EXPORT_SYMBOL_GPL(ip_conntrack_helper_put); +EXPORT_SYMBOL_GPL(__ip_conntrack_helper_find_byname); + +EXPORT_SYMBOL_GPL(ip_conntrack_proto_find_get); +EXPORT_SYMBOL_GPL(ip_conntrack_proto_put); +EXPORT_SYMBOL_GPL(__ip_conntrack_proto_find); +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +EXPORT_SYMBOL_GPL(ip_ct_port_tuple_to_nfattr); +EXPORT_SYMBOL_GPL(ip_ct_port_nfattr_to_tuple); +#endif diff --git a/net/ipv4/netfilter/ip_nat_core.c b/net/ipv4/netfilter/ip_nat_core.c index 739b6dde1c8..1adedb743f6 100644 --- a/net/ipv4/netfilter/ip_nat_core.c +++ b/net/ipv4/netfilter/ip_nat_core.c @@ -47,8 +47,39 @@ DEFINE_RWLOCK(ip_nat_lock); static unsigned int ip_nat_htable_size; static struct list_head *bysource; + +#define MAX_IP_NAT_PROTO 256 struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO]; +static inline struct ip_nat_protocol * +__ip_nat_proto_find(u_int8_t protonum) +{ + return ip_nat_protos[protonum]; +} + +struct ip_nat_protocol * +ip_nat_proto_find_get(u_int8_t protonum) +{ + struct ip_nat_protocol *p; + + /* we need to disable preemption to make sure 'p' doesn't get + * removed until we've grabbed the reference */ + preempt_disable(); + p = __ip_nat_proto_find(protonum); + if (p) { + if (!try_module_get(p->me)) + p = &ip_nat_unknown_protocol; + } + preempt_enable(); + + return p; +} + +void +ip_nat_proto_put(struct ip_nat_protocol *p) +{ + module_put(p->me); +} /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int @@ -103,7 +134,8 @@ static int in_range(const struct ip_conntrack_tuple *tuple, const struct ip_nat_range *range) { - struct ip_nat_protocol *proto = ip_nat_find_proto(tuple->dst.protonum); + struct ip_nat_protocol *proto = + __ip_nat_proto_find(tuple->dst.protonum); /* If we are supposed to map IPs, then we must be in the range specified, otherwise let this drag us onto a new src IP. */ @@ -216,8 +248,7 @@ get_unique_tuple(struct ip_conntrack_tuple *tuple, struct ip_conntrack *conntrack, enum ip_nat_manip_type maniptype) { - struct ip_nat_protocol *proto - = ip_nat_find_proto(orig_tuple->dst.protonum); + struct ip_nat_protocol *proto; /* 1) If this srcip/proto/src-proto-part is currently mapped, and that same mapping gives a unique tuple within the given @@ -242,14 +273,20 @@ get_unique_tuple(struct ip_conntrack_tuple *tuple, /* 3) The per-protocol part of the manip is made to map into the range to make a unique tuple. */ + proto = ip_nat_proto_find_get(orig_tuple->dst.protonum); + /* Only bother mapping if it's not already in range and unique */ if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || proto->in_range(tuple, maniptype, &range->min, &range->max)) - && !ip_nat_used_tuple(tuple, conntrack)) + && !ip_nat_used_tuple(tuple, conntrack)) { + ip_nat_proto_put(proto); return; + } /* Last change: get protocol to try to obtain unique tuple. */ proto->unique_tuple(tuple, range, maniptype, conntrack); + + ip_nat_proto_put(proto); } unsigned int @@ -320,17 +357,20 @@ manip_pkt(u_int16_t proto, enum ip_nat_manip_type maniptype) { struct iphdr *iph; + struct ip_nat_protocol *p; - (*pskb)->nfcache |= NFC_ALTERED; - if (!skb_ip_make_writable(pskb, iphdroff + sizeof(*iph))) + if (!skb_make_writable(pskb, iphdroff + sizeof(*iph))) return 0; iph = (void *)(*pskb)->data + iphdroff; /* Manipulate protcol part. */ - if (!ip_nat_find_proto(proto)->manip_pkt(pskb, iphdroff, - target, maniptype)) + p = ip_nat_proto_find_get(proto); + if (!p->manip_pkt(pskb, iphdroff, target, maniptype)) { + ip_nat_proto_put(p); return 0; + } + ip_nat_proto_put(p); iph = (void *)(*pskb)->data + iphdroff; @@ -391,7 +431,7 @@ int icmp_reply_translation(struct sk_buff **pskb, struct ip_conntrack_tuple inner, target; int hdrlen = (*pskb)->nh.iph->ihl * 4; - if (!skb_ip_make_writable(pskb, hdrlen + sizeof(*inside))) + if (!skb_make_writable(pskb, hdrlen + sizeof(*inside))) return 0; inside = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; @@ -426,7 +466,8 @@ int icmp_reply_translation(struct sk_buff **pskb, if (!ip_ct_get_tuple(&inside->ip, *pskb, (*pskb)->nh.iph->ihl*4 + sizeof(struct icmphdr) + inside->ip.ihl*4, - &inner, ip_ct_find_proto(inside->ip.protocol))) + &inner, + __ip_conntrack_proto_find(inside->ip.protocol))) return 0; /* Change inner back to look like incoming packet. We do the @@ -496,6 +537,49 @@ void ip_nat_protocol_unregister(struct ip_nat_protocol *proto) synchronize_net(); } +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) +int +ip_nat_port_range_to_nfattr(struct sk_buff *skb, + const struct ip_nat_range *range) +{ + NFA_PUT(skb, CTA_PROTONAT_PORT_MIN, sizeof(u_int16_t), + &range->min.tcp.port); + NFA_PUT(skb, CTA_PROTONAT_PORT_MAX, sizeof(u_int16_t), + &range->max.tcp.port); + + return 0; + +nfattr_failure: + return -1; +} + +int +ip_nat_port_nfattr_to_range(struct nfattr *tb[], struct ip_nat_range *range) +{ + int ret = 0; + + /* we have to return whether we actually parsed something or not */ + + if (tb[CTA_PROTONAT_PORT_MIN-1]) { + ret = 1; + range->min.tcp.port = + *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MIN-1]); + } + + if (!tb[CTA_PROTONAT_PORT_MAX-1]) { + if (ret) + range->max.tcp.port = range->min.tcp.port; + } else { + ret = 1; + range->max.tcp.port = + *(u_int16_t *)NFA_DATA(tb[CTA_PROTONAT_PORT_MAX-1]); + } + + return ret; +} +#endif + int __init ip_nat_init(void) { size_t i; diff --git a/net/ipv4/netfilter/ip_nat_helper.c b/net/ipv4/netfilter/ip_nat_helper.c index 158f34f32c0..d2dd5d31355 100644 --- a/net/ipv4/netfilter/ip_nat_helper.c +++ b/net/ipv4/netfilter/ip_nat_helper.c @@ -168,7 +168,7 @@ ip_nat_mangle_tcp_packet(struct sk_buff **pskb, struct tcphdr *tcph; int datalen; - if (!skb_ip_make_writable(pskb, (*pskb)->len)) + if (!skb_make_writable(pskb, (*pskb)->len)) return 0; if (rep_len > match_len @@ -228,7 +228,7 @@ ip_nat_mangle_udp_packet(struct sk_buff **pskb, match_offset + match_len) return 0; - if (!skb_ip_make_writable(pskb, (*pskb)->len)) + if (!skb_make_writable(pskb, (*pskb)->len)) return 0; if (rep_len > match_len @@ -315,7 +315,7 @@ ip_nat_sack_adjust(struct sk_buff **pskb, optoff = (*pskb)->nh.iph->ihl*4 + sizeof(struct tcphdr); optend = (*pskb)->nh.iph->ihl*4 + tcph->doff*4; - if (!skb_ip_make_writable(pskb, optend)) + if (!skb_make_writable(pskb, optend)) return 0; dir = CTINFO2DIR(ctinfo); @@ -363,7 +363,7 @@ ip_nat_seq_adjust(struct sk_buff **pskb, this_way = &ct->nat.info.seq[dir]; other_way = &ct->nat.info.seq[!dir]; - if (!skb_ip_make_writable(pskb, (*pskb)->nh.iph->ihl*4+sizeof(*tcph))) + if (!skb_make_writable(pskb, (*pskb)->nh.iph->ihl*4+sizeof(*tcph))) return 0; tcph = (void *)(*pskb)->data + (*pskb)->nh.iph->ihl*4; diff --git a/net/ipv4/netfilter/ip_nat_proto_icmp.c b/net/ipv4/netfilter/ip_nat_proto_icmp.c index 6596c9ee165..93871904399 100644 --- a/net/ipv4/netfilter/ip_nat_proto_icmp.c +++ b/net/ipv4/netfilter/ip_nat_proto_icmp.c @@ -62,7 +62,7 @@ icmp_manip_pkt(struct sk_buff **pskb, struct icmphdr *hdr; unsigned int hdroff = iphdroff + iph->ihl*4; - if (!skb_ip_make_writable(pskb, hdroff + sizeof(*hdr))) + if (!skb_make_writable(pskb, hdroff + sizeof(*hdr))) return 0; hdr = (struct icmphdr *)((*pskb)->data + hdroff); @@ -106,11 +106,18 @@ icmp_print_range(char *buffer, const struct ip_nat_range *range) else return 0; } -struct ip_nat_protocol ip_nat_protocol_icmp -= { "ICMP", IPPROTO_ICMP, - icmp_manip_pkt, - icmp_in_range, - icmp_unique_tuple, - icmp_print, - icmp_print_range +struct ip_nat_protocol ip_nat_protocol_icmp = { + .name = "ICMP", + .protonum = IPPROTO_ICMP, + .me = THIS_MODULE, + .manip_pkt = icmp_manip_pkt, + .in_range = icmp_in_range, + .unique_tuple = icmp_unique_tuple, + .print = icmp_print, + .print_range = icmp_print_range, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = ip_nat_port_range_to_nfattr, + .nfattr_to_range = ip_nat_port_nfattr_to_range, +#endif }; diff --git a/net/ipv4/netfilter/ip_nat_proto_tcp.c b/net/ipv4/netfilter/ip_nat_proto_tcp.c index a98e36d2b3c..1d381bf6857 100644 --- a/net/ipv4/netfilter/ip_nat_proto_tcp.c +++ b/net/ipv4/netfilter/ip_nat_proto_tcp.c @@ -12,6 +12,7 @@ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/if.h> +#include <linux/netfilter/nfnetlink_conntrack.h> #include <linux/netfilter_ipv4/ip_nat.h> #include <linux/netfilter_ipv4/ip_nat_rule.h> #include <linux/netfilter_ipv4/ip_nat_protocol.h> @@ -102,7 +103,7 @@ tcp_manip_pkt(struct sk_buff **pskb, if ((*pskb)->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); - if (!skb_ip_make_writable(pskb, hdroff + hdrsize)) + if (!skb_make_writable(pskb, hdroff + hdrsize)) return 0; iph = (struct iphdr *)((*pskb)->data + iphdroff); @@ -169,11 +170,18 @@ tcp_print_range(char *buffer, const struct ip_nat_range *range) else return 0; } -struct ip_nat_protocol ip_nat_protocol_tcp -= { "TCP", IPPROTO_TCP, - tcp_manip_pkt, - tcp_in_range, - tcp_unique_tuple, - tcp_print, - tcp_print_range +struct ip_nat_protocol ip_nat_protocol_tcp = { + .name = "TCP", + .protonum = IPPROTO_TCP, + .me = THIS_MODULE, + .manip_pkt = tcp_manip_pkt, + .in_range = tcp_in_range, + .unique_tuple = tcp_unique_tuple, + .print = tcp_print, + .print_range = tcp_print_range, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = ip_nat_port_range_to_nfattr, + .nfattr_to_range = ip_nat_port_nfattr_to_range, +#endif }; diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c index 9f66e562566..c4906e1aa24 100644 --- a/net/ipv4/netfilter/ip_nat_proto_udp.c +++ b/net/ipv4/netfilter/ip_nat_proto_udp.c @@ -94,7 +94,7 @@ udp_manip_pkt(struct sk_buff **pskb, u32 oldip, newip; u16 *portptr, newport; - if (!skb_ip_make_writable(pskb, hdroff + sizeof(*hdr))) + if (!skb_make_writable(pskb, hdroff + sizeof(*hdr))) return 0; iph = (struct iphdr *)((*pskb)->data + iphdroff); @@ -156,11 +156,18 @@ udp_print_range(char *buffer, const struct ip_nat_range *range) else return 0; } -struct ip_nat_protocol ip_nat_protocol_udp -= { "UDP", IPPROTO_UDP, - udp_manip_pkt, - udp_in_range, - udp_unique_tuple, - udp_print, - udp_print_range +struct ip_nat_protocol ip_nat_protocol_udp = { + .name = "UDP", + .protonum = IPPROTO_UDP, + .me = THIS_MODULE, + .manip_pkt = udp_manip_pkt, + .in_range = udp_in_range, + .unique_tuple = udp_unique_tuple, + .print = udp_print, + .print_range = udp_print_range, +#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \ + defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE) + .range_to_nfattr = ip_nat_port_range_to_nfattr, + .nfattr_to_range = ip_nat_port_nfattr_to_range, +#endif }; diff --git a/net/ipv4/netfilter/ip_nat_proto_unknown.c b/net/ipv4/netfilter/ip_nat_proto_unknown.c index f5525bd58d1..99bbef56f84 100644 --- a/net/ipv4/netfilter/ip_nat_proto_unknown.c +++ b/net/ipv4/netfilter/ip_nat_proto_unknown.c @@ -61,10 +61,11 @@ unknown_print_range(char *buffer, const struct ip_nat_range *range) } struct ip_nat_protocol ip_nat_unknown_protocol = { - "unknown", 0, - unknown_manip_pkt, - unknown_in_range, - unknown_unique_tuple, - unknown_print, - unknown_print_range + .name = "unknown", + .me = THIS_MODULE, + .manip_pkt = unknown_manip_pkt, + .in_range = unknown_in_range, + .unique_tuple = unknown_unique_tuple, + .print = unknown_print, + .print_range = unknown_print_range }; diff --git a/net/ipv4/netfilter/ip_nat_snmp_basic.c b/net/ipv4/netfilter/ip_nat_snmp_basic.c index 2a48b6e635a..93b2c5111bb 100644 --- a/net/ipv4/netfilter/ip_nat_snmp_basic.c +++ b/net/ipv4/netfilter/ip_nat_snmp_basic.c @@ -1275,7 +1275,7 @@ static int help(struct sk_buff **pskb, return NF_DROP; } - if (!skb_ip_make_writable(pskb, (*pskb)->len)) + if (!skb_make_writable(pskb, (*pskb)->len)) return NF_DROP; spin_lock_bh(&snmp_lock); diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 91d5ea1dbbc..89db052add8 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -73,8 +73,6 @@ ip_nat_fn(unsigned int hooknum, IP_NF_ASSERT(!((*pskb)->nh.iph->frag_off & htons(IP_MF|IP_OFFSET))); - (*pskb)->nfcache |= NFC_UNKNOWN; - /* If we had a hardware checksum before, it's now invalid */ if ((*pskb)->ip_summed == CHECKSUM_HW) if (skb_checksum_help(*pskb, (out == NULL))) @@ -396,6 +394,8 @@ module_exit(fini); EXPORT_SYMBOL(ip_nat_setup_info); EXPORT_SYMBOL(ip_nat_protocol_register); EXPORT_SYMBOL(ip_nat_protocol_unregister); +EXPORT_SYMBOL_GPL(ip_nat_proto_find_get); +EXPORT_SYMBOL_GPL(ip_nat_proto_put); EXPORT_SYMBOL(ip_nat_cheat_check); EXPORT_SYMBOL(ip_nat_mangle_tcp_packet); EXPORT_SYMBOL(ip_nat_mangle_udp_packet); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index c6baa817438..d54f14d926f 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -43,17 +43,10 @@ #define NET_IPQ_QMAX 2088 #define NET_IPQ_QMAX_NAME "ip_queue_maxlen" -struct ipq_rt_info { - __u8 tos; - __u32 daddr; - __u32 saddr; -}; - struct ipq_queue_entry { struct list_head list; struct nf_info *info; struct sk_buff *skb; - struct ipq_rt_info rt_info; }; typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long); @@ -247,8 +240,8 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp) pmsg->packet_id = (unsigned long )entry; pmsg->data_len = data_len; - pmsg->timestamp_sec = entry->skb->stamp.tv_sec; - pmsg->timestamp_usec = entry->skb->stamp.tv_usec; + pmsg->timestamp_sec = skb_tv_base.tv_sec + entry->skb->tstamp.off_sec; + pmsg->timestamp_usec = skb_tv_base.tv_usec + entry->skb->tstamp.off_usec; pmsg->mark = entry->skb->nfmark; pmsg->hook = entry->info->hook; pmsg->hw_protocol = entry->skb->protocol; @@ -287,7 +280,8 @@ nlmsg_failure: } static int -ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info, void *data) +ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info, + unsigned int queuenum, void *data) { int status = -EINVAL; struct sk_buff *nskb; @@ -305,14 +299,6 @@ ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info, void *data) entry->info = info; entry->skb = skb; - if (entry->info->hook == NF_IP_LOCAL_OUT) { - struct iphdr *iph = skb->nh.iph; - - entry->rt_info.tos = iph->tos; - entry->rt_info.daddr = iph->daddr; - entry->rt_info.saddr = iph->saddr; - } - nskb = ipq_build_packet_message(entry, &status); if (nskb == NULL) goto err_out_free; @@ -388,24 +374,11 @@ ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct ipq_queue_entry *e) } skb_put(e->skb, diff); } - if (!skb_ip_make_writable(&e->skb, v->data_len)) + if (!skb_make_writable(&e->skb, v->data_len)) return -ENOMEM; memcpy(e->skb->data, v->payload, v->data_len); e->skb->ip_summed = CHECKSUM_NONE; - e->skb->nfcache |= NFC_ALTERED; - - /* - * Extra routing may needed on local out, as the QUEUE target never - * returns control to the table. - */ - if (e->info->hook == NF_IP_LOCAL_OUT) { - struct iphdr *iph = e->skb->nh.iph; - - if (!(iph->tos == e->rt_info.tos - && iph->daddr == e->rt_info.daddr - && iph->saddr == e->rt_info.saddr)) - return ip_route_me_harder(&e->skb); - } + return 0; } @@ -683,6 +656,11 @@ ipq_get_info(char *buffer, char **start, off_t offset, int length) } #endif /* CONFIG_PROC_FS */ +static struct nf_queue_handler nfqh = { + .name = "ip_queue", + .outfn = &ipq_enqueue_packet, +}; + static int init_or_cleanup(int init) { @@ -693,7 +671,8 @@ init_or_cleanup(int init) goto cleanup; netlink_register_notifier(&ipq_nl_notifier); - ipqnl = netlink_kernel_create(NETLINK_FIREWALL, ipq_rcv_sk); + ipqnl = netlink_kernel_create(NETLINK_FIREWALL, 0, ipq_rcv_sk, + THIS_MODULE); if (ipqnl == NULL) { printk(KERN_ERR "ip_queue: failed to create netlink socket\n"); goto cleanup_netlink_notifier; @@ -710,7 +689,7 @@ init_or_cleanup(int init) register_netdevice_notifier(&ipq_dev_notifier); ipq_sysctl_header = register_sysctl_table(ipq_root_table, 0); - status = nf_register_queue_handler(PF_INET, ipq_enqueue_packet, NULL); + status = nf_register_queue_handler(PF_INET, &nfqh); if (status < 0) { printk(KERN_ERR "ip_queue: failed to register queue handler\n"); goto cleanup_sysctl; @@ -718,7 +697,7 @@ init_or_cleanup(int init) return status; cleanup: - nf_unregister_queue_handler(PF_INET); + nf_unregister_queue_handlers(&nfqh); synchronize_net(); ipq_flush(NF_DROP); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c88dfcd38c5..eef99a1b5de 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -312,7 +312,6 @@ ipt_do_table(struct sk_buff **pskb, do { IP_NF_ASSERT(e); IP_NF_ASSERT(back); - (*pskb)->nfcache |= e->nfcache; if (ip_packet_match(ip, indev, outdev, &e->ip, offset)) { struct ipt_entry_target *t; @@ -341,8 +340,8 @@ ipt_do_table(struct sk_buff **pskb, back->comefrom); continue; } - if (table_base + v - != (void *)e + e->next_offset) { + if (table_base + v != (void *)e + e->next_offset + && !(e->ip.flags & IPT_F_GOTO)) { /* Save old back ptr in next entry */ struct ipt_entry *next = (void *)e + e->next_offset; diff --git a/net/ipv4/netfilter/ipt_CLASSIFY.c b/net/ipv4/netfilter/ipt_CLASSIFY.c index 9842e6e2318..dab78d8bd49 100644 --- a/net/ipv4/netfilter/ipt_CLASSIFY.c +++ b/net/ipv4/netfilter/ipt_CLASSIFY.c @@ -32,10 +32,8 @@ target(struct sk_buff **pskb, { const struct ipt_classify_target_info *clinfo = targinfo; - if((*pskb)->priority != clinfo->priority) { + if((*pskb)->priority != clinfo->priority) (*pskb)->priority = clinfo->priority; - (*pskb)->nfcache |= NFC_ALTERED; - } return IPT_CONTINUE; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 6706d3a1bc4..2d05cafec22 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -367,7 +367,7 @@ target(struct sk_buff **pskb, #ifdef DEBUG_CLUSTERP DUMP_TUPLE(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - DEBUGP("hash=%u ct_hash=%lu ", hash, ct->mark); + DEBUGP("hash=%u ct_hash=%u ", hash, ct->mark); if (!clusterip_responsible(cipinfo->config, hash)) { DEBUGP("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/netfilter/ipt_CONNMARK.c b/net/ipv4/netfilter/ipt_CONNMARK.c index 30ddd3e18eb..13463802133 100644 --- a/net/ipv4/netfilter/ipt_CONNMARK.c +++ b/net/ipv4/netfilter/ipt_CONNMARK.c @@ -40,9 +40,9 @@ target(struct sk_buff **pskb, void *userinfo) { const struct ipt_connmark_target_info *markinfo = targinfo; - unsigned long diff; - unsigned long nfmark; - unsigned long newmark; + u_int32_t diff; + u_int32_t nfmark; + u_int32_t newmark; enum ip_conntrack_info ctinfo; struct ip_conntrack *ct = ip_conntrack_get((*pskb), &ctinfo); @@ -61,10 +61,8 @@ target(struct sk_buff **pskb, case IPT_CONNMARK_RESTORE: nfmark = (*pskb)->nfmark; diff = (ct->mark ^ nfmark) & markinfo->mask; - if (diff != 0) { + if (diff != 0) (*pskb)->nfmark = nfmark ^ diff; - (*pskb)->nfcache |= NFC_ALTERED; - } break; } } @@ -94,6 +92,11 @@ checkentry(const char *tablename, } } + if (matchinfo->mark > 0xffffffff || matchinfo->mask > 0xffffffff) { + printk(KERN_WARNING "CONNMARK: Only supports 32bit mark\n"); + return 0; + } + return 1; } diff --git a/net/ipv4/netfilter/ipt_DSCP.c b/net/ipv4/netfilter/ipt_DSCP.c index 3ea4509099f..6e319570a28 100644 --- a/net/ipv4/netfilter/ipt_DSCP.c +++ b/net/ipv4/netfilter/ipt_DSCP.c @@ -39,7 +39,7 @@ target(struct sk_buff **pskb, if (((*pskb)->nh.iph->tos & IPT_DSCP_MASK) != sh_dscp) { u_int16_t diffs[2]; - if (!skb_ip_make_writable(pskb, sizeof(struct iphdr))) + if (!skb_make_writable(pskb, sizeof(struct iphdr))) return NF_DROP; diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; @@ -51,7 +51,6 @@ target(struct sk_buff **pskb, sizeof(diffs), (*pskb)->nh.iph->check ^ 0xFFFF)); - (*pskb)->nfcache |= NFC_ALTERED; } return IPT_CONTINUE; } diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 94a0ce1c1c9..a1319693f64 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -31,7 +31,7 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) != (einfo->ip_ect & IPT_ECN_IP_MASK)) { u_int16_t diffs[2]; - if (!skb_ip_make_writable(pskb, sizeof(struct iphdr))) + if (!skb_make_writable(pskb, sizeof(struct iphdr))) return 0; diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; @@ -43,7 +43,6 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo) sizeof(diffs), (*pskb)->nh.iph->check ^0xFFFF)); - (*pskb)->nfcache |= NFC_ALTERED; } return 1; } @@ -67,7 +66,7 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) tcph->cwr == einfo->proto.tcp.cwr))) return 1; - if (!skb_ip_make_writable(pskb, (*pskb)->nh.iph->ihl*4+sizeof(*tcph))) + if (!skb_make_writable(pskb, (*pskb)->nh.iph->ihl*4+sizeof(*tcph))) return 0; tcph = (void *)(*pskb)->nh.iph + (*pskb)->nh.iph->ihl*4; @@ -87,7 +86,6 @@ set_ect_tcp(struct sk_buff **pskb, const struct ipt_ECN_info *einfo, int inward) tcph->check = csum_fold(csum_partial((char *)diffs, sizeof(diffs), tcph->check^0xFFFF)); - (*pskb)->nfcache |= NFC_ALTERED; return 1; } diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index ef08733d26d..92ed050fac6 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -27,10 +27,6 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables syslog logging module"); -static unsigned int nflog = 1; -module_param(nflog, int, 0400); -MODULE_PARM_DESC(nflog, "register as internal netfilter logging module"); - #if 0 #define DEBUGP printk #else @@ -41,11 +37,17 @@ MODULE_PARM_DESC(nflog, "register as internal netfilter logging module"); static DEFINE_SPINLOCK(log_lock); /* One level of recursion won't kill us */ -static void dump_packet(const struct ipt_log_info *info, +static void dump_packet(const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { struct iphdr _iph, *ih; + unsigned int logflags; + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_MASK; ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); if (ih == NULL) { @@ -76,7 +78,7 @@ static void dump_packet(const struct ipt_log_info *info, if (ntohs(ih->frag_off) & IP_OFFSET) printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - if ((info->logflags & IPT_LOG_IPOPT) + if ((logflags & IPT_LOG_IPOPT) && ih->ihl * 4 > sizeof(struct iphdr)) { unsigned char _opt[4 * 15 - sizeof(struct iphdr)], *op; unsigned int i, optsize; @@ -119,7 +121,7 @@ static void dump_packet(const struct ipt_log_info *info, printk("SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ - if (info->logflags & IPT_LOG_TCPSEQ) + if (logflags & IPT_LOG_TCPSEQ) printk("SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); /* Max length: 13 "WINDOW=65535 " */ @@ -146,7 +148,7 @@ static void dump_packet(const struct ipt_log_info *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((info->logflags & IPT_LOG_TCPOPT) + if ((logflags & IPT_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; unsigned char *op; @@ -328,7 +330,7 @@ static void dump_packet(const struct ipt_log_info *info, } /* Max length: 15 "UID=4294967295 " */ - if ((info->logflags & IPT_LOG_UID) && !iphoff && skb->sk) { + if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) printk("UID=%u ", skb->sk->sk_socket->file->f_uid); @@ -349,19 +351,31 @@ static void dump_packet(const struct ipt_log_info *info, /* maxlen = 230+ 91 + 230 + 252 = 803 */ } +struct nf_loginfo default_loginfo = { + .type = NF_LOG_TYPE_LOG, + .u = { + .log = { + .level = 0, + .logflags = NF_LOG_MASK, + }, + }, +}; + static void -ipt_log_packet(unsigned int hooknum, +ipt_log_packet(unsigned int pf, + unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, - const struct ipt_log_info *loginfo, - const char *level_string, + const struct nf_loginfo *loginfo, const char *prefix) { + if (!loginfo) + loginfo = &default_loginfo; + spin_lock_bh(&log_lock); - printk(level_string); - printk("%sIN=%s OUT=%s ", - prefix == NULL ? loginfo->prefix : prefix, + printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + prefix, in ? in->name : "", out ? out->name : ""); #ifdef CONFIG_BRIDGE_NETFILTER @@ -405,28 +419,15 @@ ipt_log_target(struct sk_buff **pskb, void *userinfo) { const struct ipt_log_info *loginfo = targinfo; - char level_string[4] = "< >"; + struct nf_loginfo li; - level_string[1] = '0' + (loginfo->level % 8); - ipt_log_packet(hooknum, *pskb, in, out, loginfo, level_string, NULL); + li.type = NF_LOG_TYPE_LOG; + li.u.log.level = loginfo->level; + li.u.log.logflags = loginfo->logflags; - return IPT_CONTINUE; -} + nf_log_packet(PF_INET, hooknum, *pskb, in, out, &li, loginfo->prefix); -static void -ipt_logfn(unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const char *prefix) -{ - struct ipt_log_info loginfo = { - .level = 0, - .logflags = IPT_LOG_MASK, - .prefix = "" - }; - - ipt_log_packet(hooknum, skb, in, out, &loginfo, KERN_WARNING, prefix); + return IPT_CONTINUE; } static int ipt_log_checkentry(const char *tablename, @@ -464,20 +465,29 @@ static struct ipt_target ipt_log_reg = { .me = THIS_MODULE, }; +static struct nf_logger ipt_log_logger ={ + .name = "ipt_LOG", + .logfn = &ipt_log_packet, + .me = THIS_MODULE, +}; + static int __init init(void) { if (ipt_register_target(&ipt_log_reg)) return -EINVAL; - if (nflog) - nf_log_register(PF_INET, &ipt_logfn); + if (nf_log_register(PF_INET, &ipt_log_logger) < 0) { + printk(KERN_WARNING "ipt_LOG: not logging via system console " + "since somebody else already registered for PF_INET\n"); + /* we cannot make module load fail here, since otherwise + * iptables userspace would abort */ + } return 0; } static void __exit fini(void) { - if (nflog) - nf_log_unregister(PF_INET, &ipt_logfn); + nf_log_unregister_logger(&ipt_log_logger); ipt_unregister_target(&ipt_log_reg); } diff --git a/net/ipv4/netfilter/ipt_MARK.c b/net/ipv4/netfilter/ipt_MARK.c index 33c6f9b63b8..52b4f2c296b 100644 --- a/net/ipv4/netfilter/ipt_MARK.c +++ b/net/ipv4/netfilter/ipt_MARK.c @@ -29,10 +29,9 @@ target_v0(struct sk_buff **pskb, { const struct ipt_mark_target_info *markinfo = targinfo; - if((*pskb)->nfmark != markinfo->mark) { + if((*pskb)->nfmark != markinfo->mark) (*pskb)->nfmark = markinfo->mark; - (*pskb)->nfcache |= NFC_ALTERED; - } + return IPT_CONTINUE; } @@ -61,10 +60,9 @@ target_v1(struct sk_buff **pskb, break; } - if((*pskb)->nfmark != mark) { + if((*pskb)->nfmark != mark) (*pskb)->nfmark = mark; - (*pskb)->nfcache |= NFC_ALTERED; - } + return IPT_CONTINUE; } @@ -76,6 +74,8 @@ checkentry_v0(const char *tablename, unsigned int targinfosize, unsigned int hook_mask) { + struct ipt_mark_target_info *markinfo = targinfo; + if (targinfosize != IPT_ALIGN(sizeof(struct ipt_mark_target_info))) { printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", targinfosize, @@ -88,6 +88,11 @@ checkentry_v0(const char *tablename, return 0; } + if (markinfo->mark > 0xffffffff) { + printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); + return 0; + } + return 1; } @@ -120,6 +125,11 @@ checkentry_v1(const char *tablename, return 0; } + if (markinfo->mark > 0xffffffff) { + printk(KERN_WARNING "MARK: Only supports 32bit wide mark\n"); + return 0; + } + return 1; } diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 91e74502c3d..2f3e181c8e9 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -86,11 +86,6 @@ masquerade_target(struct sk_buff **pskb, IP_NF_ASSERT(hooknum == NF_IP_POST_ROUTING); - /* FIXME: For the moment, don't do local packets, breaks - testsuite for 2.3.49 --RR */ - if ((*pskb)->sk) - return NF_ACCEPT; - ct = ip_conntrack_get(*pskb, &ctinfo); IP_NF_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 06254b29d03..e6e7b609536 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -46,7 +46,8 @@ check(const char *tablename, DEBUGP(MODULENAME":check: size %u.\n", targinfosize); return 0; } - if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_POST_ROUTING))) { + if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_POST_ROUTING) | + (1 << NF_IP_LOCAL_OUT))) { DEBUGP(MODULENAME":check: bad hooks %x.\n", hook_mask); return 0; } @@ -76,12 +77,13 @@ target(struct sk_buff **pskb, struct ip_nat_range newrange; IP_NF_ASSERT(hooknum == NF_IP_PRE_ROUTING - || hooknum == NF_IP_POST_ROUTING); + || hooknum == NF_IP_POST_ROUTING + || hooknum == NF_IP_LOCAL_OUT); ct = ip_conntrack_get(*pskb, &ctinfo); netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); - if (hooknum == NF_IP_PRE_ROUTING) + if (hooknum == NF_IP_PRE_ROUTING || hooknum == NF_IP_LOCAL_OUT) new_ip = (*pskb)->nh.iph->daddr & ~netmask; else new_ip = (*pskb)->nh.iph->saddr & ~netmask; diff --git a/net/ipv4/netfilter/ipt_NFQUEUE.c b/net/ipv4/netfilter/ipt_NFQUEUE.c new file mode 100644 index 00000000000..3cedc9be880 --- /dev/null +++ b/net/ipv4/netfilter/ipt_NFQUEUE.c @@ -0,0 +1,70 @@ +/* iptables module for using new netfilter netlink queue + * + * (C) 2005 by Harald Welte <laforge@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/skbuff.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_NFQUEUE.h> + +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("iptables NFQUEUE target"); +MODULE_LICENSE("GPL"); + +static unsigned int +target(struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + unsigned int hooknum, + const void *targinfo, + void *userinfo) +{ + const struct ipt_NFQ_info *tinfo = targinfo; + + return NF_QUEUE_NR(tinfo->queuenum); +} + +static int +checkentry(const char *tablename, + const struct ipt_entry *e, + void *targinfo, + unsigned int targinfosize, + unsigned int hook_mask) +{ + if (targinfosize != IPT_ALIGN(sizeof(struct ipt_NFQ_info))) { + printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", + targinfosize, + IPT_ALIGN(sizeof(struct ipt_NFQ_info))); + return 0; + } + + return 1; +} + +static struct ipt_target ipt_NFQ_reg = { + .name = "NFQUEUE", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + return ipt_register_target(&ipt_NFQ_reg); +} + +static void __exit fini(void) +{ + ipt_unregister_target(&ipt_NFQ_reg); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 91569644602..f115a84a4ac 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -156,7 +156,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* This packet will not be the same as the other: clear nf fields */ nf_reset(nskb); - nskb->nfcache = 0; nskb->nfmark = 0; #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(nskb->nf_bridge); diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index 7b84a254440..8db70d6908c 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -58,7 +58,7 @@ ipt_tcpmss_target(struct sk_buff **pskb, unsigned int i; u_int8_t *opt; - if (!skb_ip_make_writable(pskb, (*pskb)->len)) + if (!skb_make_writable(pskb, (*pskb)->len)) return NF_DROP; if ((*pskb)->ip_summed == CHECKSUM_HW && @@ -190,7 +190,6 @@ ipt_tcpmss_target(struct sk_buff **pskb, newmss); retmodified: - (*pskb)->nfcache |= NFC_UNKNOWN | NFC_ALTERED; return IPT_CONTINUE; } diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index 85c70d240f8..deadb36d442 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -33,7 +33,7 @@ target(struct sk_buff **pskb, if (((*pskb)->nh.iph->tos & IPTOS_TOS_MASK) != tosinfo->tos) { u_int16_t diffs[2]; - if (!skb_ip_make_writable(pskb, sizeof(struct iphdr))) + if (!skb_make_writable(pskb, sizeof(struct iphdr))) return NF_DROP; diffs[0] = htons((*pskb)->nh.iph->tos) ^ 0xFFFF; @@ -46,7 +46,6 @@ target(struct sk_buff **pskb, sizeof(diffs), (*pskb)->nh.iph->check ^0xFFFF)); - (*pskb)->nfcache |= NFC_ALTERED; } return IPT_CONTINUE; } diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c new file mode 100644 index 00000000000..b9ae6a9382f --- /dev/null +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -0,0 +1,119 @@ +/* TTL modification target for IP tables + * (C) 2000,2005 by Harald Welte <laforge@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ip.h> +#include <net/checksum.h> + +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_TTL.h> + +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("IP tables TTL modification module"); +MODULE_LICENSE("GPL"); + +static unsigned int +ipt_ttl_target(struct sk_buff **pskb, const struct net_device *in, + const struct net_device *out, unsigned int hooknum, + const void *targinfo, void *userinfo) +{ + struct iphdr *iph; + const struct ipt_TTL_info *info = targinfo; + u_int16_t diffs[2]; + int new_ttl; + + if (!skb_make_writable(pskb, (*pskb)->len)) + return NF_DROP; + + iph = (*pskb)->nh.iph; + + switch (info->mode) { + case IPT_TTL_SET: + new_ttl = info->ttl; + break; + case IPT_TTL_INC: + new_ttl = iph->ttl + info->ttl; + if (new_ttl > 255) + new_ttl = 255; + break; + case IPT_TTL_DEC: + new_ttl = iph->ttl - info->ttl; + if (new_ttl < 0) + new_ttl = 0; + break; + default: + new_ttl = iph->ttl; + break; + } + + if (new_ttl != iph->ttl) { + diffs[0] = htons(((unsigned)iph->ttl) << 8) ^ 0xFFFF; + iph->ttl = new_ttl; + diffs[1] = htons(((unsigned)iph->ttl) << 8); + iph->check = csum_fold(csum_partial((char *)diffs, + sizeof(diffs), + iph->check^0xFFFF)); + } + + return IPT_CONTINUE; +} + +static int ipt_ttl_checkentry(const char *tablename, + const struct ipt_entry *e, + void *targinfo, + unsigned int targinfosize, + unsigned int hook_mask) +{ + struct ipt_TTL_info *info = targinfo; + + if (targinfosize != IPT_ALIGN(sizeof(struct ipt_TTL_info))) { + printk(KERN_WARNING "ipt_TTL: targinfosize %u != %Zu\n", + targinfosize, + IPT_ALIGN(sizeof(struct ipt_TTL_info))); + return 0; + } + + if (strcmp(tablename, "mangle")) { + printk(KERN_WARNING "ipt_TTL: can only be called from " + "\"mangle\" table, not \"%s\"\n", tablename); + return 0; + } + + if (info->mode > IPT_TTL_MAXMODE) { + printk(KERN_WARNING "ipt_TTL: invalid or unknown Mode %u\n", + info->mode); + return 0; + } + + if ((info->mode != IPT_TTL_SET) && (info->ttl == 0)) + return 0; + + return 1; +} + +static struct ipt_target ipt_TTL = { + .name = "TTL", + .target = ipt_ttl_target, + .checkentry = ipt_ttl_checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + return ipt_register_target(&ipt_TTL); +} + +static void __exit fini(void) +{ + ipt_unregister_target(&ipt_TTL); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 52a0076302a..e2c14f3cb2f 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -62,6 +62,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>"); MODULE_DESCRIPTION("iptables userspace logging module"); +MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); #define ULOG_NL_EVENT 111 /* Harald's favorite number */ #define ULOG_MAXNLGROUPS 32 /* numer of nlgroups */ @@ -115,10 +116,10 @@ static void ulog_send(unsigned int nlgroupnum) if (ub->qlen > 1) ub->lastnlh->nlmsg_type = NLMSG_DONE; - NETLINK_CB(ub->skb).dst_groups = (1 << nlgroupnum); - DEBUGP("ipt_ULOG: throwing %d packets to netlink mask %u\n", - ub->qlen, nlgroupnum); - netlink_broadcast(nflognl, ub->skb, 0, (1 << nlgroupnum), GFP_ATOMIC); + NETLINK_CB(ub->skb).dst_group = nlgroupnum + 1; + DEBUGP("ipt_ULOG: throwing %d packets to netlink group %u\n", + ub->qlen, nlgroupnum + 1); + netlink_broadcast(nflognl, ub->skb, 0, nlgroupnum + 1, GFP_ATOMIC); ub->qlen = 0; ub->skb = NULL; @@ -219,13 +220,13 @@ static void ipt_ulog_packet(unsigned int hooknum, pm = NLMSG_DATA(nlh); /* We might not have a timestamp, get one */ - if (skb->stamp.tv_sec == 0) - do_gettimeofday((struct timeval *)&skb->stamp); + if (skb->tstamp.off_sec == 0) + __net_timestamp((struct sk_buff *)skb); /* copy hook, prefix, timestamp, payload, etc. */ pm->data_len = copy_len; - pm->timestamp_sec = skb->stamp.tv_sec; - pm->timestamp_usec = skb->stamp.tv_usec; + pm->timestamp_sec = skb_tv_base.tv_sec + skb->tstamp.off_sec; + pm->timestamp_usec = skb_tv_base.tv_usec + skb->tstamp.off_usec; pm->mark = skb->nfmark; pm->hook = hooknum; if (prefix != NULL) @@ -303,18 +304,27 @@ static unsigned int ipt_ulog_target(struct sk_buff **pskb, return IPT_CONTINUE; } -static void ipt_logfn(unsigned int hooknum, +static void ipt_logfn(unsigned int pf, + unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, + const struct nf_loginfo *li, const char *prefix) { - struct ipt_ulog_info loginfo = { - .nl_group = ULOG_DEFAULT_NLGROUP, - .copy_range = 0, - .qthreshold = ULOG_DEFAULT_QTHRESHOLD, - .prefix = "" - }; + struct ipt_ulog_info loginfo; + + if (!li || li->type != NF_LOG_TYPE_ULOG) { + loginfo.nl_group = ULOG_DEFAULT_NLGROUP; + loginfo.copy_range = 0; + loginfo.qthreshold = ULOG_DEFAULT_QTHRESHOLD; + loginfo.prefix[0] = '\0'; + } else { + loginfo.nl_group = li->u.ulog.group; + loginfo.copy_range = li->u.ulog.copy_len; + loginfo.qthreshold = li->u.ulog.qthreshold; + strlcpy(loginfo.prefix, prefix, sizeof(loginfo.prefix)); + } ipt_ulog_packet(hooknum, skb, in, out, &loginfo, prefix); } @@ -354,6 +364,12 @@ static struct ipt_target ipt_ulog_reg = { .me = THIS_MODULE, }; +static struct nf_logger ipt_ulog_logger = { + .name = "ipt_ULOG", + .logfn = &ipt_logfn, + .me = THIS_MODULE, +}; + static int __init init(void) { int i; @@ -372,7 +388,8 @@ static int __init init(void) ulog_buffers[i].timer.data = i; } - nflognl = netlink_kernel_create(NETLINK_NFLOG, NULL); + nflognl = netlink_kernel_create(NETLINK_NFLOG, ULOG_MAXNLGROUPS, NULL, + THIS_MODULE); if (!nflognl) return -ENOMEM; @@ -381,7 +398,7 @@ static int __init init(void) return -EINVAL; } if (nflog) - nf_log_register(PF_INET, &ipt_logfn); + nf_log_register(PF_INET, &ipt_ulog_logger); return 0; } @@ -394,7 +411,7 @@ static void __exit fini(void) DEBUGP("ipt_ULOG: cleanup_module\n"); if (nflog) - nf_log_unregister(PF_INET, &ipt_logfn); + nf_log_unregister_logger(&ipt_ulog_logger); ipt_unregister_target(&ipt_ulog_reg); sock_release(nflognl->sk_socket); diff --git a/net/ipv4/netfilter/ipt_connbytes.c b/net/ipv4/netfilter/ipt_connbytes.c new file mode 100644 index 00000000000..df4a42c6da2 --- /dev/null +++ b/net/ipv4/netfilter/ipt_connbytes.c @@ -0,0 +1,162 @@ +/* Kernel module to match connection tracking byte counter. + * GPL (C) 2002 Martin Devera (devik@cdi.cz). + * + * 2004-07-20 Harald Welte <laforge@netfilter.org> + * - reimplemented to use per-connection accounting counters + * - add functionality to match number of packets + * - add functionality to match average packet size + * - add support to match directions seperately + * + */ +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netfilter_ipv4/ip_conntrack.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_connbytes.h> + +#include <asm/div64.h> +#include <asm/bitops.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("iptables match for matching number of pkts/bytes per connection"); + +/* 64bit divisor, dividend and result. dynamic precision */ +static u_int64_t div64_64(u_int64_t dividend, u_int64_t divisor) +{ + u_int32_t d = divisor; + + if (divisor > 0xffffffffULL) { + unsigned int shift = fls(divisor >> 32); + + d = divisor >> shift; + dividend >>= shift; + } + + do_div(dividend, d); + return dividend; +} + +static int +match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + int *hotdrop) +{ + const struct ipt_connbytes_info *sinfo = matchinfo; + enum ip_conntrack_info ctinfo; + struct ip_conntrack *ct; + u_int64_t what = 0; /* initialize to make gcc happy */ + + if (!(ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo))) + return 0; /* no match */ + + switch (sinfo->what) { + case IPT_CONNBYTES_PKTS: + switch (sinfo->direction) { + case IPT_CONNBYTES_DIR_ORIGINAL: + what = ct->counters[IP_CT_DIR_ORIGINAL].packets; + break; + case IPT_CONNBYTES_DIR_REPLY: + what = ct->counters[IP_CT_DIR_REPLY].packets; + break; + case IPT_CONNBYTES_DIR_BOTH: + what = ct->counters[IP_CT_DIR_ORIGINAL].packets; + what += ct->counters[IP_CT_DIR_REPLY].packets; + break; + } + break; + case IPT_CONNBYTES_BYTES: + switch (sinfo->direction) { + case IPT_CONNBYTES_DIR_ORIGINAL: + what = ct->counters[IP_CT_DIR_ORIGINAL].bytes; + break; + case IPT_CONNBYTES_DIR_REPLY: + what = ct->counters[IP_CT_DIR_REPLY].bytes; + break; + case IPT_CONNBYTES_DIR_BOTH: + what = ct->counters[IP_CT_DIR_ORIGINAL].bytes; + what += ct->counters[IP_CT_DIR_REPLY].bytes; + break; + } + break; + case IPT_CONNBYTES_AVGPKT: + switch (sinfo->direction) { + case IPT_CONNBYTES_DIR_ORIGINAL: + what = div64_64(ct->counters[IP_CT_DIR_ORIGINAL].bytes, + ct->counters[IP_CT_DIR_ORIGINAL].packets); + break; + case IPT_CONNBYTES_DIR_REPLY: + what = div64_64(ct->counters[IP_CT_DIR_REPLY].bytes, + ct->counters[IP_CT_DIR_REPLY].packets); + break; + case IPT_CONNBYTES_DIR_BOTH: + { + u_int64_t bytes; + u_int64_t pkts; + bytes = ct->counters[IP_CT_DIR_ORIGINAL].bytes + + ct->counters[IP_CT_DIR_REPLY].bytes; + pkts = ct->counters[IP_CT_DIR_ORIGINAL].packets+ + ct->counters[IP_CT_DIR_REPLY].packets; + + /* FIXME_THEORETICAL: what to do if sum + * overflows ? */ + + what = div64_64(bytes, pkts); + } + break; + } + break; + } + + if (sinfo->count.to) + return (what <= sinfo->count.to && what >= sinfo->count.from); + else + return (what >= sinfo->count.from); +} + +static int check(const char *tablename, + const struct ipt_ip *ip, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ipt_connbytes_info *sinfo = matchinfo; + + if (matchsize != IPT_ALIGN(sizeof(struct ipt_connbytes_info))) + return 0; + + if (sinfo->what != IPT_CONNBYTES_PKTS && + sinfo->what != IPT_CONNBYTES_BYTES && + sinfo->what != IPT_CONNBYTES_AVGPKT) + return 0; + + if (sinfo->direction != IPT_CONNBYTES_DIR_ORIGINAL && + sinfo->direction != IPT_CONNBYTES_DIR_REPLY && + sinfo->direction != IPT_CONNBYTES_DIR_BOTH) + return 0; + + return 1; +} + +static struct ipt_match state_match = { + .name = "connbytes", + .match = &match, + .checkentry = &check, + .me = THIS_MODULE +}; + +static int __init init(void) +{ + return ipt_register_match(&state_match); +} + +static void __exit fini(void) +{ + ipt_unregister_match(&state_match); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_connmark.c b/net/ipv4/netfilter/ipt_connmark.c index 2706f96cea5..bf8de47ce00 100644 --- a/net/ipv4/netfilter/ipt_connmark.c +++ b/net/ipv4/netfilter/ipt_connmark.c @@ -54,9 +54,16 @@ checkentry(const char *tablename, unsigned int matchsize, unsigned int hook_mask) { + struct ipt_connmark_info *cm = + (struct ipt_connmark_info *)matchinfo; if (matchsize != IPT_ALIGN(sizeof(struct ipt_connmark_info))) return 0; + if (cm->mark > 0xffffffff || cm->mask > 0xffffffff) { + printk(KERN_WARNING "connmark: only support 32bit mark\n"); + return 0; + } + return 1; } diff --git a/net/ipv4/netfilter/ipt_dccp.c b/net/ipv4/netfilter/ipt_dccp.c new file mode 100644 index 00000000000..ad3278bba6c --- /dev/null +++ b/net/ipv4/netfilter/ipt_dccp.c @@ -0,0 +1,176 @@ +/* + * iptables module for DCCP protocol header matching + * + * (C) 2005 by Harald Welte <laforge@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <net/ip.h> +#include <linux/dccp.h> + +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_dccp.h> + +#define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ + || (!!((invflag) & (option)) ^ (cond))) + +static unsigned char *dccp_optbuf; +static DEFINE_SPINLOCK(dccp_buflock); + +static inline int +dccp_find_option(u_int8_t option, + const struct sk_buff *skb, + const struct dccp_hdr *dh, + int *hotdrop) +{ + /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ + unsigned char *op; + unsigned int optoff = __dccp_hdr_len(dh); + unsigned int optlen = dh->dccph_doff*4 - __dccp_hdr_len(dh); + unsigned int i; + + if (dh->dccph_doff * 4 < __dccp_hdr_len(dh)) { + *hotdrop = 1; + return 0; + } + + if (!optlen) + return 0; + + spin_lock_bh(&dccp_buflock); + op = skb_header_pointer(skb, + skb->nh.iph->ihl*4 + optoff, + optlen, dccp_optbuf); + if (op == NULL) { + /* If we don't have the whole header, drop packet. */ + spin_unlock_bh(&dccp_buflock); + *hotdrop = 1; + return 0; + } + + for (i = 0; i < optlen; ) { + if (op[i] == option) { + spin_unlock_bh(&dccp_buflock); + return 1; + } + + if (op[i] < 2) + i++; + else + i += op[i+1]?:1; + } + + spin_unlock_bh(&dccp_buflock); + return 0; +} + + +static inline int +match_types(const struct dccp_hdr *dh, u_int16_t typemask) +{ + return (typemask & (1 << dh->dccph_type)); +} + +static inline int +match_option(u_int8_t option, const struct sk_buff *skb, + const struct dccp_hdr *dh, int *hotdrop) +{ + return dccp_find_option(option, skb, dh, hotdrop); +} + +static int +match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + int *hotdrop) +{ + const struct ipt_dccp_info *info = + (const struct ipt_dccp_info *)matchinfo; + struct dccp_hdr _dh, *dh; + + if (offset) + return 0; + + dh = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_dh), &_dh); + if (dh == NULL) { + *hotdrop = 1; + return 0; + } + + return DCCHECK(((ntohs(dh->dccph_sport) >= info->spts[0]) + && (ntohs(dh->dccph_sport) <= info->spts[1])), + IPT_DCCP_SRC_PORTS, info->flags, info->invflags) + && DCCHECK(((ntohs(dh->dccph_dport) >= info->dpts[0]) + && (ntohs(dh->dccph_dport) <= info->dpts[1])), + IPT_DCCP_DEST_PORTS, info->flags, info->invflags) + && DCCHECK(match_types(dh, info->typemask), + IPT_DCCP_TYPE, info->flags, info->invflags) + && DCCHECK(match_option(info->option, skb, dh, hotdrop), + IPT_DCCP_OPTION, info->flags, info->invflags); +} + +static int +checkentry(const char *tablename, + const struct ipt_ip *ip, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ipt_dccp_info *info; + + info = (const struct ipt_dccp_info *)matchinfo; + + return ip->proto == IPPROTO_DCCP + && !(ip->invflags & IPT_INV_PROTO) + && matchsize == IPT_ALIGN(sizeof(struct ipt_dccp_info)) + && !(info->flags & ~IPT_DCCP_VALID_FLAGS) + && !(info->invflags & ~IPT_DCCP_VALID_FLAGS) + && !(info->invflags & ~info->flags); +} + +static struct ipt_match dccp_match = +{ + .name = "dccp", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + int ret; + + /* doff is 8 bits, so the maximum option size is (4*256). Don't put + * this in BSS since DaveM is worried about locked TLB's for kernel + * BSS. */ + dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); + if (!dccp_optbuf) + return -ENOMEM; + ret = ipt_register_match(&dccp_match); + if (ret) + kfree(dccp_optbuf); + + return ret; +} + +static void __exit fini(void) +{ + ipt_unregister_match(&dccp_match); + kfree(dccp_optbuf); +} + +module_init(init); +module_exit(fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("Match for DCCP protocol packets"); + diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 564b49bfebc..2dd1cccbdab 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -94,7 +94,7 @@ struct ipt_hashlimit_htable { static DEFINE_SPINLOCK(hashlimit_lock); /* protects htables list */ static DECLARE_MUTEX(hlimit_mutex); /* additional checkentry protection */ static HLIST_HEAD(hashlimit_htables); -static kmem_cache_t *hashlimit_cachep; +static kmem_cache_t *hashlimit_cachep __read_mostly; static inline int dst_cmp(const struct dsthash_ent *ent, struct dsthash_dst *b) { diff --git a/net/ipv4/netfilter/ipt_mark.c b/net/ipv4/netfilter/ipt_mark.c index 8955728127b..00bef6cdd3f 100644 --- a/net/ipv4/netfilter/ipt_mark.c +++ b/net/ipv4/netfilter/ipt_mark.c @@ -37,9 +37,16 @@ checkentry(const char *tablename, unsigned int matchsize, unsigned int hook_mask) { + struct ipt_mark_info *minfo = (struct ipt_mark_info *) matchinfo; + if (matchsize != IPT_ALIGN(sizeof(struct ipt_mark_info))) return 0; + if (minfo->mark > 0xffffffff || minfo->mask > 0xffffffff) { + printk(KERN_WARNING "mark: only supports 32bit mark\n"); + return 0; + } + return 1; } diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 3b9065e0638..c1889f88262 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -21,106 +21,6 @@ MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables owner match"); static int -match_comm(const struct sk_buff *skb, const char *comm) -{ - struct task_struct *g, *p; - struct files_struct *files; - int i; - - read_lock(&tasklist_lock); - do_each_thread(g, p) { - if(strncmp(p->comm, comm, sizeof(p->comm))) - continue; - - task_lock(p); - files = p->files; - if(files) { - spin_lock(&files->file_lock); - for (i=0; i < files->max_fds; i++) { - if (fcheck_files(files, i) == - skb->sk->sk_socket->file) { - spin_unlock(&files->file_lock); - task_unlock(p); - read_unlock(&tasklist_lock); - return 1; - } - } - spin_unlock(&files->file_lock); - } - task_unlock(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); - return 0; -} - -static int -match_pid(const struct sk_buff *skb, pid_t pid) -{ - struct task_struct *p; - struct files_struct *files; - int i; - - read_lock(&tasklist_lock); - p = find_task_by_pid(pid); - if (!p) - goto out; - task_lock(p); - files = p->files; - if(files) { - spin_lock(&files->file_lock); - for (i=0; i < files->max_fds; i++) { - if (fcheck_files(files, i) == - skb->sk->sk_socket->file) { - spin_unlock(&files->file_lock); - task_unlock(p); - read_unlock(&tasklist_lock); - return 1; - } - } - spin_unlock(&files->file_lock); - } - task_unlock(p); -out: - read_unlock(&tasklist_lock); - return 0; -} - -static int -match_sid(const struct sk_buff *skb, pid_t sid) -{ - struct task_struct *g, *p; - struct file *file = skb->sk->sk_socket->file; - int i, found=0; - - read_lock(&tasklist_lock); - do_each_thread(g, p) { - struct files_struct *files; - if (p->signal->session != sid) - continue; - - task_lock(p); - files = p->files; - if (files) { - spin_lock(&files->file_lock); - for (i=0; i < files->max_fds; i++) { - if (fcheck_files(files, i) == file) { - found = 1; - break; - } - } - spin_unlock(&files->file_lock); - } - task_unlock(p); - if (found) - goto out; - } while_each_thread(g, p); -out: - read_unlock(&tasklist_lock); - - return found; -} - -static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, @@ -145,24 +45,6 @@ match(const struct sk_buff *skb, return 0; } - if(info->match & IPT_OWNER_PID) { - if (!match_pid(skb, info->pid) ^ - !!(info->invert & IPT_OWNER_PID)) - return 0; - } - - if(info->match & IPT_OWNER_SID) { - if (!match_sid(skb, info->sid) ^ - !!(info->invert & IPT_OWNER_SID)) - return 0; - } - - if(info->match & IPT_OWNER_COMM) { - if (!match_comm(skb, info->comm) ^ - !!(info->invert & IPT_OWNER_COMM)) - return 0; - } - return 1; } @@ -173,6 +55,8 @@ checkentry(const char *tablename, unsigned int matchsize, unsigned int hook_mask) { + const struct ipt_owner_info *info = matchinfo; + if (hook_mask & ~((1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_POST_ROUTING))) { printk("ipt_owner: only valid for LOCAL_OUT or POST_ROUTING.\n"); @@ -184,15 +68,13 @@ checkentry(const char *tablename, IPT_ALIGN(sizeof(struct ipt_owner_info))); return 0; } -#ifdef CONFIG_SMP - /* files->file_lock can not be used in a BH */ - if (((struct ipt_owner_info *)matchinfo)->match - & (IPT_OWNER_PID|IPT_OWNER_SID|IPT_OWNER_COMM)) { - printk("ipt_owner: pid, sid and command matching is broken " - "on SMP.\n"); + + if (info->match & (IPT_OWNER_PID|IPT_OWNER_SID|IPT_OWNER_COMM)) { + printk("ipt_owner: pid, sid and command matching " + "not supported anymore\n"); return 0; } -#endif + return 1; } diff --git a/net/ipv4/netfilter/ipt_string.c b/net/ipv4/netfilter/ipt_string.c new file mode 100644 index 00000000000..b5def204d79 --- /dev/null +++ b/net/ipv4/netfilter/ipt_string.c @@ -0,0 +1,91 @@ +/* String matching match for iptables + * + * (C) 2005 Pablo Neira Ayuso <pablo@eurodev.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/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4/ipt_string.h> +#include <linux/textsearch.h> + +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@eurodev.net>"); +MODULE_DESCRIPTION("IP tables string match module"); +MODULE_LICENSE("GPL"); + +static int match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + int *hotdrop) +{ + struct ts_state state; + struct ipt_string_info *conf = (struct ipt_string_info *) matchinfo; + + memset(&state, 0, sizeof(struct ts_state)); + + return (skb_find_text((struct sk_buff *)skb, conf->from_offset, + conf->to_offset, conf->config, &state) + != UINT_MAX) && !conf->invert; +} + +#define STRING_TEXT_PRIV(m) ((struct ipt_string_info *) m) + +static int checkentry(const char *tablename, + const struct ipt_ip *ip, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + struct ipt_string_info *conf = matchinfo; + struct ts_config *ts_conf; + + if (matchsize != IPT_ALIGN(sizeof(struct ipt_string_info))) + return 0; + + /* Damn, can't handle this case properly with iptables... */ + if (conf->from_offset > conf->to_offset) + return 0; + + ts_conf = textsearch_prepare(conf->algo, conf->pattern, conf->patlen, + GFP_KERNEL, TS_AUTOLOAD); + if (IS_ERR(ts_conf)) + return 0; + + conf->config = ts_conf; + + return 1; +} + +static void destroy(void *matchinfo, unsigned int matchsize) +{ + textsearch_destroy(STRING_TEXT_PRIV(matchinfo)->config); +} + +static struct ipt_match string_match = { + .name = "string", + .match = match, + .checkentry = checkentry, + .destroy = destroy, + .me = THIS_MODULE +}; + +static int __init init(void) +{ + return ipt_register_match(&string_match); +} + +static void __exit fini(void) +{ + ipt_unregister_match(&string_match); +} + +module_init(init); +module_exit(fini); |