connection tracking event notifiers
Subsystems (3)
PATCH 1/1 connection tracking event notifiers
Hi Dave,
I'm now starting to send the accumulated netfilter patches. For now there will be three (event notifiers, nfnetlink, nfc_defines). Tomorrow some more (ctnetlink, with some luck nfnetlink_queue and the pptp-helper) will follow.
Please apply to your 2.6.14 tree, thanks!
Signature · 5 lines
- Harald Welte <[email protected]> http://netfilter.org/ ============================================================================ "Fragmentation is like classful addressing -- an interesting early architectural error that shows how much experimentation was going on while IP was being designed." -- Paul Vixie
This adds a notifier chain based event mechanism for ip_conntrack state changes. As opposed to the previous implementations in patch-o-matic, we do no longer need a field in the skb to achieve this.
Thanks to the valuable input from Patrick McHardy and Rusty on the idea of a per_cpu implementation.
---
commit 212c12f0005581d2625a1bd0add59cd8ac5725d0
tree d713bb281f89f966c2d5b26b76b803f83ce40ae7
parent 952afcc6bee0883be51320865d8848dace060603
author laforge <[email protected]> Mi, 20 Jul 2005 08:49:13 -0400 committer laforge <[email protected]> Mi, 20 Jul 2005 08:49:13 -0400
include/linux/netfilter_ipv4/ip_conntrack.h | 144 ++++++++++++++++++++++ include/linux/netfilter_ipv4/ip_conntrack_core.h | 17 ++- net/ipv4/netfilter/Kconfig | 10 ++ net/ipv4/netfilter/ip_conntrack_core.c | 122 ++++++++++++++++++- net/ipv4/netfilter/ip_conntrack_ftp.c | 12 +- net/ipv4/netfilter/ip_conntrack_proto_icmp.c | 1 net/ipv4/netfilter/ip_conntrack_proto_sctp.c | 2 net/ipv4/netfilter/ip_conntrack_proto_tcp.c | 4 + net/ipv4/netfilter/ip_conntrack_proto_udp.c | 3 net/ipv4/netfilter/ip_conntrack_standalone.c | 10 ++ 10 files changed, 311 insertions(+), 14 deletions(-)
include/linux/netfilter_ipv4/ip_conntrack.h +144 -0
@@ -65,6 +65,63 @@ enum ip_conntrack_status {/* Both together */ IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE |IPS_SRC_NAT_DONE ), + +/* Connection is dying (removed from lists), can not be unset. */ +IPS_DYING_BIT =9 , + IPS_DYING = (1 << IPS_DYING_BIT), +}; + +/* Connection tracking event bits */ +enum ip_conntrack_events +{ +/* New conntrack */ +IPCT_NEW_BIT =0 , +IPCT_NEW = (1 <<IPCT_NEW_BIT ), + +/* Expected connection */ +IPCT_RELATED_BIT =1 , +IPCT_RELATED = (1 <<IPCT_RELATED_BIT ), + +/* Destroyed conntrack */ +IPCT_DESTROY_BIT =2 , +IPCT_DESTROY = (1 <<IPCT_DESTROY_BIT ), + +/* Timer has been refreshed */ +IPCT_REFRESH_BIT =3 , +IPCT_REFRESH = (1 <<IPCT_REFRESH_BIT ), + +/* Status has changed */ +IPCT_STATUS_BIT =4 , +IPCT_STATUS = (1 <<IPCT_STATUS_BIT ), + +/* Update of protocol info */ +IPCT_PROTOINFO_BIT =5 , +IPCT_PROTOINFO = (1 <<IPCT_PROTOINFO_BIT ), + +/* Volatile protocol info */ +IPCT_PROTOINFO_VOLATILE_BIT =6 , +IPCT_PROTOINFO_VOLATILE = (1 <<IPCT_PROTOINFO_VOLATILE_BIT ), + +/* New helper for conntrack */ +IPCT_HELPER_BIT =7 , +IPCT_HELPER = (1 <<IPCT_HELPER_BIT ), + +/* Update of helper info */ +IPCT_HELPINFO_BIT =8 , +IPCT_HELPINFO = (1 <<IPCT_HELPINFO_BIT ), + +/* Volatile helper info */ +IPCT_HELPINFO_VOLATILE_BIT =9 , +IPCT_HELPINFO_VOLATILE = (1 <<IPCT_HELPINFO_VOLATILE_BIT ), + +/* NAT info */ +IPCT_NATINFO_BIT =10 , +IPCT_NATINFO = (1 <<IPCT_NATINFO_BIT ), +}; + +enum ip_conntrack_expect_events { +IPEXP_NEW_BIT =0 , +IPEXP_NEW = (1 <<IPEXP_NEW_BIT ), };#ifdef __KERNEL__
@@ -277,6 +334,11 @@ static inline int is_confirmed(struct ipreturn test_bit (IPS_CONFIRMED_BIT , &ct->status); } +static inline int is_dying (struct ip_conntrack *ct) +{ +return test_bit (IPS_DYING_BIT , &ct->status); +} +extern unsigned int ip_conntrack_htable_size;struct ip_conntrack_stat
@@ -300,6 +362,88 @@ struct ip_conntrack_stat#define CONNTRACK_STAT_INC (count) (__get_cpu_var(ip_conntrack_stat).count++) +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +#include <linux/notifier.h> + +struct ip_conntrack_ecache { +struct ip_conntrack *ct; +unsigned int events; +}; +DECLARE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache); + +#define CONNTRACK_ECACHE (x) (__get_cpu_var(ip_conntrack_ecache).x) + +extern struct notifier_block *ip_conntrack_chain; +extern struct notifier_block *ip_conntrack_expect_chain; + +static inline int ip_conntrack_register_notifier (struct notifier_block *nb) +{ +return notifier_chain_register (&ip_conntrack_chain, nb); +} + +static inline int ip_conntrack_unregister_notifier (struct notifier_block *nb) +{ +return notifier_chain_unregister (&ip_conntrack_chain, nb); +} + +static inline int +ip_conntrack_expect_register_notifier (struct notifier_block *nb) +{ +return notifier_chain_register (&ip_conntrack_expect_chain, nb); +} + +static inline int +ip_conntrack_expect_unregister_notifier (struct notifier_block *nb) +{ +return notifier_chain_unregister (&ip_conntrack_expect_chain, nb); +} + +static inline void +ip_conntrack_event_cache (enum ip_conntrack_events event, +const struct sk_buff *skb) +{ +struct ip_conntrack_ecache *ecache = + &__get_cpu_var (ip_conntrack_ecache); + +if (unlikely ((struct ip_conntrack *) skb->nfct != ecache->ct)) { +if (net_ratelimit ()) { +printk (KERN_ERR "ctevent: skb->ct != ecache->ct !!!\n" ); +dump_stack (); + } + } + ecache->events |= event; +} + +extern void +ip_conntrack_deliver_cached_events_for (const struct ip_conntrack *ct); +extern void ip_conntrack_event_cache_init (const struct sk_buff *skb); + +static inline void ip_conntrack_event (enum ip_conntrack_events event, +struct ip_conntrack *ct) +{ +if (is_confirmed (ct) && !is_dying (ct)) +notifier_call_chain (&ip_conntrack_chain, event, ct); +} + +static inline void +ip_conntrack_expect_event (enum ip_conntrack_expect_events event, +struct ip_conntrack_expect *exp) +{ +notifier_call_chain (&ip_conntrack_expect_chain, event, exp); +} +#else /* CONFIG_IP_NF_CONNTRACK_EVENTS */ +static inline void ip_conntrack_event_cache (enum ip_conntrack_events event, +const struct sk_buff *skb) {} +static inline void ip_conntrack_event (enum ip_conntrack_events event, +struct ip_conntrack *ct) {} +static inline void ip_conntrack_deliver_cached_events_for ( +struct ip_conntrack *ct) {} +static inline void ip_conntrack_event_cache_init (const struct sk_buff *skb) {} +static inline void +ip_conntrack_expect_event (enum ip_conntrack_expect_events event, +struct ip_conntrack_expect *exp) {} +#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */ +#ifdef CONFIG_IP_NF_NAT_NEEDED static inline int ip_nat_initialized (struct ip_conntrack *conntrack,enum ip_nat_manip_type manip)
include/linux/netfilter_ipv4/ip_conntrack_core.h +13 -4
@@ -38,12 +38,21 @@ extern int __ip_conntrack_confirm(struct/* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int ip_conntrack_confirm (struct sk_buff **pskb) { -if ((*pskb)->nfct - && !is_confirmed ((struct ip_conntrack *)(*pskb)->nfct)) -return __ip_conntrack_confirm (pskb); -return NF_ACCEPT ; +struct ip_conntrack *ct = (struct ip_conntrack *)(*pskb)->nfct; +int ret =NF_ACCEPT ; + +if (ct && !is_confirmed (ct)) + ret =__ip_conntrack_confirm (pskb); +ip_conntrack_deliver_cached_events_for (ct); + +return ret; } +#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS +struct ip_conntrack_ecache ; +extern void __ip_ct_deliver_cached_events (struct ip_conntrack_ecache *ec); +#endif +extern struct list_head *ip_conntrack_hash;extern struct list_head ip_conntrack_expect_list;extern rwlock_t ip_conntrack_lock;
net/ipv4/netfilter/Kconfig +10 -0
@@ -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
net/ipv4/netfilter/ip_conntrack_core.c +117 -5
201 lines not on this page · raw message
net/ipv4/netfilter/ip_conntrack_ftp.c +8 -4
@@ -262,7 +262,8 @@ static int find_nl_seq(u32 seq, const st }/* 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 +277,13 @@ static void update_nl_seq(u32 nl_seq, st 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 +443,7 @@ 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;
net/ipv4/netfilter/ip_conntrack_proto_icmp.c +1 -0
@@ -102,6 +102,7 @@ static int icmp_packet(struct ip_conntra 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); }
net/ipv4/netfilter/ip_conntrack_proto_sctp.c +2 -0
@@ -404,6 +404,8 @@ static int sctp_packet(struct ip_conntra } conntrack->proto.sctp.state = newconntrack; +if (oldsctpstate != newconntrack) +ip_conntrack_event_cache (IPCT_PROTOINFO , skb);write_unlock_bh (&sctp_lock); }
net/ipv4/netfilter/ip_conntrack_proto_tcp.c +4 -0
@@ -973,6 +973,10 @@ static int tcp_packet(struct ip_conntrac ? 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
net/ipv4/netfilter/ip_conntrack_proto_udp.c +2 -1
@@ -73,7 +73,8 @@ static int udp_packet(struct ip_conntracip_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);
net/ipv4/netfilter/ip_conntrack_standalone.c +10 -0
@@ -402,6 +402,7 @@ static unsigned int ip_confirm(unsigned const struct net_device *out, int (*okfn)(struct sk_buff *)) { + ip_conntrack_event_cache_init(*pskb);/* We've seen it coming out the other side: confirm it */ return ip_conntrack_confirm (pskb); }
@@ -419,6 +420,7 @@ static unsigned int ip_conntrack_help(un ct =ip_conntrack_get (*pskb, &ctinfo);if (ct && ct->helper) {unsigned int ret; +ip_conntrack_event_cache_init (*pskb); ret = ct->helper->help (pskb, ct, ctinfo);if (ret !=NF_ACCEPT )return ret;
@@ -889,6 +891,7 @@ 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 +974,13 @@ 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_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);