[NETFILTER]: connection tracking event notifiers

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.

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 157 insertions, 4 deletions

diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index 4ed720f0c4cd..ae1270c97b50 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -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__
@@ -280,6 +337,11 @@ static inline int is_confirmed(struct ip_conntrack *ct)
         return 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
@@ -303,6 +365,88 @@ 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)
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h
index 694aec9b4784..46eeea1e2733 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_core.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h
@@ -38,12 +38,21 @@ extern int __ip_conntrack_confirm(struct sk_buff **pskb);
 /* 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;