netfilter: conntrack: replace notify chain by function pointer

This patch removes the notify chain infrastructure and replace it
by a simple function pointer. This issue has been mentioned in the
mailing list several times: the use of the notify chain adds
too much overhead for something that is only used by ctnetlink.

This patch also changes nfnetlink_send(). It seems that gfp_any()
returns GFP_KERNEL for user-context request, like those via
ctnetlink, inside the RCU read-side section which is not valid.
Using GFP_KERNEL is also evil since netlink may schedule(),
this leads to "scheduling while atomic" bug reports.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 49 insertions, 21 deletions

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index c600083cbdf..2214e516146 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -75,7 +75,7 @@ extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
 
 extern int nfnetlink_has_listeners(unsigned int group);
 extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, 
-			  int echo);
+			  int echo, gfp_t flags);
 extern void nfnetlink_set_err(u32 pid, u32 group, int error);
 extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags);
 
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 2e17a2d0eb3..1afb907e015 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -6,7 +6,6 @@
 #define _NF_CONNTRACK_ECACHE_H
 #include <net/netfilter/nf_conntrack.h>
 
-#include <linux/notifier.h>
 #include <linux/interrupt.h>
 #include <net/net_namespace.h>
 #include <net/netfilter/nf_conntrack_expect.h>
@@ -69,9 +68,13 @@ struct nf_ct_event {
 	int report;
 };
 
-extern struct atomic_notifier_head nf_conntrack_chain;
-extern int nf_conntrack_register_notifier(struct notifier_block *nb);
-extern int nf_conntrack_unregister_notifier(struct notifier_block *nb);
+struct nf_ct_event_notifier {
+	int (*fcn)(unsigned int events, struct nf_ct_event *item);
+};
+
+extern struct nf_ct_event_notifier *nf_conntrack_event_cb;
+extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
+extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
 
 extern void nf_ct_deliver_cached_events(const struct nf_conn *ct);
 extern void __nf_ct_event_cache_init(struct nf_conn *ct);
@@ -97,13 +100,23 @@ nf_conntrack_event_report(enum ip_conntrack_events event,
 			  u32 pid,
 			  int report)
 {
-	struct nf_ct_event item = {
-		.ct 	= ct,
-		.pid	= pid,
-		.report = report
-	};
-	if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
-		atomic_notifier_call_chain(&nf_conntrack_chain, event, &item);
+	struct nf_ct_event_notifier *notify;
+
+	rcu_read_lock();
+	notify = rcu_dereference(nf_conntrack_event_cb);
+	if (notify == NULL)
+		goto out_unlock;
+
+	if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) {
+		struct nf_ct_event item = {
+			.ct 	= ct,
+			.pid	= pid,
+			.report = report
+		};
+		notify->fcn(event, &item);
+	}
+out_unlock:
+	rcu_read_unlock();
 }
 
 static inline void
@@ -118,9 +131,13 @@ struct nf_exp_event {
 	int report;
 };
 
-extern struct atomic_notifier_head nf_ct_expect_chain;
-extern int nf_ct_expect_register_notifier(struct notifier_block *nb);
-extern int nf_ct_expect_unregister_notifier(struct notifier_block *nb);
+struct nf_exp_event_notifier {
+	int (*fcn)(unsigned int events, struct nf_exp_event *item);
+};
+
+extern struct nf_exp_event_notifier *nf_expect_event_cb;
+extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
+extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
 
 static inline void
 nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
@@ -128,12 +145,23 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			  u32 pid,
 			  int report)
 {
-	struct nf_exp_event item = {
-		.exp	= exp,
-		.pid	= pid,
-		.report = report
-	};
-	atomic_notifier_call_chain(&nf_ct_expect_chain, event, &item);
+	struct nf_exp_event_notifier *notify;
+
+	rcu_read_lock();
+	notify = rcu_dereference(nf_expect_event_cb);
+	if (notify == NULL)
+		goto out_unlock;
+
+	{
+		struct nf_exp_event item = {
+			.exp	= exp,
+			.pid	= pid,
+			.report = report
+		};
+		notify->fcn(event, &item);
+	}
+out_unlock:
+	rcu_read_unlock();
 }
 
 static inline void