[NETFILTER]: Fix multiple problems with the conntrack event cache

refcnt underflow: the reference count is decremented when a conntrack
entry is removed from the hash but it is not incremented when entering
new entries.

missing protection of process context against softirq context: all
cache operations need to locally disable softirqs to avoid races.
Additionally the event cache can't be initialized when a packet
enteres the conntrack code but needs to be initialized whenever we
cache an event and the stored conntrack entry doesn't match the
current one.

incorrect flushing of the event cache in ip_ct_iterate_cleanup:
without real locking we can't flush the cache for different CPUs
without incurring races. The cache for different CPUs can only be
flushed when no packets are going through the
code. ip_ct_iterate_cleanup doesn't need to drop all references, so
flushing is moved to the cleanup path.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 18 insertions, 25 deletions

diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index ff2c1c6001f9..088742befe49 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -411,6 +411,7 @@ struct ip_conntrack_stat
 
 #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
 #include <linux/notifier.h>
+#include <linux/interrupt.h>
 
 struct ip_conntrack_ecache {
         struct ip_conntrack *ct;
@@ -445,26 +446,24 @@ ip_conntrack_expect_unregister_notifier(struct notifier_block *nb)
         return notifier_chain_unregister(&ip_conntrack_expect_chain, nb);
 }
 
+extern void ip_ct_deliver_cached_events(const struct ip_conntrack *ct);
+extern void __ip_ct_event_cache_init(struct ip_conntrack *ct);
+
 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();
-                }
-        }
+        struct ip_conntrack *ct = (struct ip_conntrack *)skb->nfct;
+        struct ip_conntrack_ecache *ecache;
+        
+        local_bh_disable();
+        ecache = &__get_cpu_var(ip_conntrack_ecache);
+        if (ct != ecache->ct)
+                __ip_ct_event_cache_init(ct);
         ecache->events |= event;
+        local_bh_enable();
 }
 
-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)
 {
@@ -483,9 +482,7 @@ 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_ct_deliver_cached_events(const struct ip_conntrack *ct) {}
 static inline void 
 ip_conntrack_expect_event(enum ip_conntrack_expect_events event, 
                           struct ip_conntrack_expect *exp) {}
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h
index fbf6c3e41647..dc4d2a0575de 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_core.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h
@@ -44,18 +44,14 @@ static inline int ip_conntrack_confirm(struct sk_buff **pskb)
         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);
-
+        if (ct) {
+                if (!is_confirmed(ct))
+                        ret = __ip_conntrack_confirm(pskb);
+                ip_ct_deliver_cached_events(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 void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp);
 
 extern struct list_head *ip_conntrack_hash;