[NETFILTER]: nf_conntrack: split out expectation handling

This patch splits out expectation handling into its own file
nf_conntrack_expect.c

Signed-off-by: Martin Josefsson <gandalf@wlug.westbo.se>
Signed-off-by: Patrick McHardy <kaber@trash.net>

10 files changed, 452 insertions, 401 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 1fbd8193d5f1..9d2581fc04be 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -124,44 +124,6 @@ struct nf_conn
         char data[0];
 };
 
-struct nf_conntrack_expect
-{
-        /* Internal linked list (global expectation list) */
-        struct list_head list;
-
-        /* We expect this tuple, with the following mask */
-        struct nf_conntrack_tuple tuple, mask;
- 
-        /* Function to call after setup and insertion */
-        void (*expectfn)(struct nf_conn *new,
-                         struct nf_conntrack_expect *this);
-
-        /* The conntrack of the master connection */
-        struct nf_conn *master;
-
-        /* Timer function; deletes the expectation. */
-        struct timer_list timeout;
-
-        /* Usage count. */
-        atomic_t use;
-
-        /* Unique ID */
-        unsigned int id;
-
-        /* Flags */
-        unsigned int flags;
-
-#ifdef CONFIG_NF_NAT_NEEDED
-        /* This is the original per-proto part, used to map the
-         * expected connection the way the recipient expects. */
-        union nf_conntrack_manip_proto saved_proto;
-        /* Direction relative to the master connection. */
-        enum ip_conntrack_dir dir;
-#endif
-};
-
-#define NF_CT_EXPECT_PERMANENT 0x1
-
 static inline struct nf_conn *
 nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash)
 {
@@ -208,16 +170,6 @@ __nf_conntrack_find(const struct nf_conntrack_tuple *tuple,
 
 extern void nf_conntrack_hash_insert(struct nf_conn *ct);
 
-extern struct nf_conntrack_expect *
-__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
-
-extern struct nf_conntrack_expect *
-nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
-
-extern void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
-
-extern void nf_ct_remove_expectations(struct nf_conn *ct);
-
 extern void nf_conntrack_flush(void);
 
 extern struct nf_conntrack_helper *
@@ -295,6 +247,7 @@ extern int nf_conntrack_checksum;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 #include <linux/notifier.h>
 #include <linux/interrupt.h>
+#include <net/netfilter/nf_conntrack_expect.h>
 
 struct nf_conntrack_ecache {
         struct nf_conn *ct;
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index da254525a4ce..84a8e01941fb 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -13,6 +13,8 @@
 #define _NF_CONNTRACK_CORE_H
 
 #include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_protocol.h>
 
 /* This header is used to share core functionality between the
    standalone connection tracking module, and the compatibility layer's use
@@ -70,6 +72,11 @@ static inline int nf_conntrack_confirm(struct sk_buff **pskb)
 
 extern void __nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb);
 
+int
+print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
+            struct nf_conntrack_l3proto *l3proto,
+            struct nf_conntrack_protocol *proto);
+
 extern struct list_head *nf_conntrack_hash;
 extern struct list_head nf_conntrack_expect_list;
 extern rwlock_t nf_conntrack_lock ;
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
new file mode 100644
index 000000000000..5aa483e03455
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -0,0 +1,72 @@
+/*
+ * connection tracking expectations.
+ */
+
+#ifndef _NF_CONNTRACK_EXPECT_H
+#define _NF_CONNTRACK_EXPECT_H
+#include <net/netfilter/nf_conntrack.h>
+
+extern struct list_head nf_conntrack_expect_list;
+extern kmem_cache_t *nf_conntrack_expect_cachep;
+extern struct file_operations exp_file_ops;
+
+struct nf_conntrack_expect
+{
+        /* Internal linked list (global expectation list) */
+        struct list_head list;
+
+        /* We expect this tuple, with the following mask */
+        struct nf_conntrack_tuple tuple, mask;
+
+        /* Function to call after setup and insertion */
+        void (*expectfn)(struct nf_conn *new,
+                         struct nf_conntrack_expect *this);
+
+        /* The conntrack of the master connection */
+        struct nf_conn *master;
+
+        /* Timer function; deletes the expectation. */
+        struct timer_list timeout;
+
+        /* Usage count. */
+        atomic_t use;
+
+        /* Unique ID */
+        unsigned int id;
+
+        /* Flags */
+        unsigned int flags;
+
+#ifdef CONFIG_NF_NAT_NEEDED
+        /* This is the original per-proto part, used to map the
+         * expected connection the way the recipient expects. */
+        union nf_conntrack_manip_proto saved_proto;
+        /* Direction relative to the master connection. */
+        enum ip_conntrack_dir dir;
+#endif
+};
+
+#define NF_CT_EXPECT_PERMANENT 0x1
+
+
+struct nf_conntrack_expect *
+__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
+
+struct nf_conntrack_expect *
+nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple);
+
+struct nf_conntrack_expect *
+find_expectation(const struct nf_conntrack_tuple *tuple);
+
+void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
+void nf_ct_remove_expectations(struct nf_conn *ct);
+void nf_conntrack_unexpect_related(struct nf_conntrack_expect *exp);
+
+/* Allocate space for an expectation: this is mandatory before calling
+   nf_conntrack_expect_related.  You will have to call put afterwards. */
+struct nf_conntrack_expect *nf_conntrack_expect_alloc(struct nf_conn *me);
+void nf_conntrack_expect_put(struct nf_conntrack_expect *exp);
+int nf_conntrack_expect_related(struct nf_conntrack_expect *expect);
+
+#endif /*_NF_CONNTRACK_EXPECT_H*/
+
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 86ec8174ad02..3cbd13e22160 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -40,14 +40,4 @@ struct nf_conntrack_helper
 extern int nf_conntrack_helper_register(struct nf_conntrack_helper *);
 extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
 
-/* Allocate space for an expectation: this is mandatory before calling
-   nf_conntrack_expect_related.  You will have to call put afterwards. */
-extern struct nf_conntrack_expect *
-nf_conntrack_expect_alloc(struct nf_conn *master);
-extern void nf_conntrack_expect_put(struct nf_conntrack_expect *exp);
-
-/* Add an expected connection: can have more than one per connection */
-extern int nf_conntrack_expect_related(struct nf_conntrack_expect *exp);
-extern void nf_conntrack_unexpect_related(struct nf_conntrack_expect *exp);
-
 #endif /*_NF_CONNTRACK_HELPER_H*/
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a74be492fd0a..d33b9ac01aa7 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,5 +1,5 @@
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
-nf_conntrack-objs       := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o
+nf_conntrack-objs       := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o
 
 obj-$(CONFIG_NETFILTER) = netfilter.o
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index de0567b1f422..72fbae4e594c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -55,6 +55,7 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_protocol.h>
+#include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>
 
@@ -72,21 +73,19 @@ DEFINE_RWLOCK(nf_conntrack_lock);
 atomic_t nf_conntrack_count = ATOMIC_INIT(0);
 
 void (*nf_conntrack_destroyed)(struct nf_conn *conntrack) = NULL;
-LIST_HEAD(nf_conntrack_expect_list);
 struct nf_conntrack_protocol **nf_ct_protos[PF_MAX] __read_mostly;
 struct nf_conntrack_l3proto *nf_ct_l3protos[PF_MAX] __read_mostly;
 static LIST_HEAD(helpers);
 unsigned int nf_conntrack_htable_size __read_mostly = 0;
 int nf_conntrack_max __read_mostly;
 struct list_head *nf_conntrack_hash __read_mostly;
-static kmem_cache_t *nf_conntrack_expect_cachep __read_mostly;
 struct nf_conn nf_conntrack_untracked;
 unsigned int nf_ct_log_invalid __read_mostly;
 static LIST_HEAD(unconfirmed);
 static int nf_conntrack_vmalloc __read_mostly;
 
 static unsigned int nf_conntrack_next_id;
-static unsigned int nf_conntrack_expect_next_id;
+
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 ATOMIC_NOTIFIER_HEAD(nf_conntrack_chain);
 ATOMIC_NOTIFIER_HEAD(nf_conntrack_expect_chain);
@@ -438,103 +437,6 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
         return protocol->invert_tuple(inverse, orig);
 }
 
-/* nf_conntrack_expect helper functions */
-void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
-{
-        struct nf_conn_help *master_help = nfct_help(exp->master);
-
-        NF_CT_ASSERT(master_help);
-        ASSERT_WRITE_LOCK(&nf_conntrack_lock);
-        NF_CT_ASSERT(!timer_pending(&exp->timeout));
-
-        list_del(&exp->list);
-        NF_CT_STAT_INC(expect_delete);
-        master_help->expecting--;
-        nf_conntrack_expect_put(exp);
-}
-
-static void expectation_timed_out(unsigned long ul_expect)
-{
-        struct nf_conntrack_expect *exp = (void *)ul_expect;
-
-        write_lock_bh(&nf_conntrack_lock);
-        nf_ct_unlink_expect(exp);
-        write_unlock_bh(&nf_conntrack_lock);
-        nf_conntrack_expect_put(exp);
-}
-
-struct nf_conntrack_expect *
-__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
-{
-        struct nf_conntrack_expect *i;
-        
-        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
-                if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask))
-                        return i;
-        }
-        return NULL;
-}
-
-/* Just find a expectation corresponding to a tuple. */
-struct nf_conntrack_expect *
-nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
-{
-        struct nf_conntrack_expect *i;
-        
-        read_lock_bh(&nf_conntrack_lock);
-        i = __nf_conntrack_expect_find(tuple);
-        if (i)
-                atomic_inc(&i->use);
-        read_unlock_bh(&nf_conntrack_lock);
-
-        return i;
-}
-
-/* If an expectation for this connection is found, it gets delete from
- * global list then returned. */
-static struct nf_conntrack_expect *
-find_expectation(const struct nf_conntrack_tuple *tuple)
-{
-        struct nf_conntrack_expect *i;
-
-        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
-        /* If master is not in hash table yet (ie. packet hasn't left
-           this machine yet), how can other end know about expected?
-           Hence these are not the droids you are looking for (if
-           master ct never got confirmed, we'd hold a reference to it
-           and weird things would happen to future packets). */
-                if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)
-                    && nf_ct_is_confirmed(i->master)) {
-                        if (i->flags & NF_CT_EXPECT_PERMANENT) {
-                                atomic_inc(&i->use);
-                                return i;
-                        } else if (del_timer(&i->timeout)) {
-                                nf_ct_unlink_expect(i);
-                                return i;
-                        }
-                }
-        }
-        return NULL;
-}
-
-/* delete all expectations for this conntrack */
-void nf_ct_remove_expectations(struct nf_conn *ct)
-{
-        struct nf_conntrack_expect *i, *tmp;
-        struct nf_conn_help *help = nfct_help(ct);
-
-        /* Optimization: most connection never expect any others. */
-        if (!help || help->expecting == 0)
-                return;
-
-        list_for_each_entry_safe(i, tmp, &nf_conntrack_expect_list, list) {
-                if (i->master == ct && del_timer(&i->timeout)) {
-                        nf_ct_unlink_expect(i);
-                        nf_conntrack_expect_put(i);
-                }
-        }
-}
-
 static void
 clean_from_lists(struct nf_conn *ct)
 {
@@ -1133,169 +1035,6 @@ int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
                                                      orig->dst.protonum));
 }
 
-/* Would two expected things clash? */
-static inline int expect_clash(const struct nf_conntrack_expect *a,
-                               const struct nf_conntrack_expect *b)
-{
-        /* Part covered by intersection of masks must be unequal,
-           otherwise they clash */
-        struct nf_conntrack_tuple intersect_mask;
-        int count;
-
-        intersect_mask.src.l3num = a->mask.src.l3num & b->mask.src.l3num;
-        intersect_mask.src.u.all = a->mask.src.u.all & b->mask.src.u.all;
-        intersect_mask.dst.u.all = a->mask.dst.u.all & b->mask.dst.u.all;
-        intersect_mask.dst.protonum = a->mask.dst.protonum
-                                        & b->mask.dst.protonum;
-
-        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
-                intersect_mask.src.u3.all[count] =
-                        a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
-        }
-
-        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
-                intersect_mask.dst.u3.all[count] =
-                        a->mask.dst.u3.all[count] & b->mask.dst.u3.all[count];
-        }
-
-        return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
-}
-
-static inline int expect_matches(const struct nf_conntrack_expect *a,
-                                 const struct nf_conntrack_expect *b)
-{
-        return a->master == b->master
-                && nf_ct_tuple_equal(&a->tuple, &b->tuple)
-                && nf_ct_tuple_equal(&a->mask, &b->mask);
-}
-
-/* Generally a bad idea to call this: could have matched already. */
-void nf_conntrack_unexpect_related(struct nf_conntrack_expect *exp)
-{
-        struct nf_conntrack_expect *i;
-
-        write_lock_bh(&nf_conntrack_lock);
-        /* choose the the oldest expectation to evict */
-        list_for_each_entry_reverse(i, &nf_conntrack_expect_list, list) {
-                if (expect_matches(i, exp) && del_timer(&i->timeout)) {
-                        nf_ct_unlink_expect(i);
-                        write_unlock_bh(&nf_conntrack_lock);
-                        nf_conntrack_expect_put(i);
-                        return;
-                }
-        }
-        write_unlock_bh(&nf_conntrack_lock);
-}
-
-/* We don't increase the master conntrack refcount for non-fulfilled
- * conntracks. During the conntrack destruction, the expectations are
- * always killed before the conntrack itself */
-struct nf_conntrack_expect *nf_conntrack_expect_alloc(struct nf_conn *me)
-{
-        struct nf_conntrack_expect *new;
-
-        new = kmem_cache_alloc(nf_conntrack_expect_cachep, GFP_ATOMIC);
-        if (!new) {
-                DEBUGP("expect_related: OOM allocating expect\n");
-                return NULL;
-        }
-        new->master = me;
-        atomic_set(&new->use, 1);
-        return new;
-}
-
-void nf_conntrack_expect_put(struct nf_conntrack_expect *exp)
-{
-        if (atomic_dec_and_test(&exp->use))
-                kmem_cache_free(nf_conntrack_expect_cachep, exp);
-}
-
-static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp)
-{
-        struct nf_conn_help *master_help = nfct_help(exp->master);
-
-        atomic_inc(&exp->use);
-        master_help->expecting++;
-        list_add(&exp->list, &nf_conntrack_expect_list);
-
-        init_timer(&exp->timeout);
-        exp->timeout.data = (unsigned long)exp;
-        exp->timeout.function = expectation_timed_out;
-        exp->timeout.expires = jiffies + master_help->helper->timeout * HZ;
-        add_timer(&exp->timeout);
-
-        exp->id = ++nf_conntrack_expect_next_id;
-        atomic_inc(&exp->use);
-        NF_CT_STAT_INC(expect_create);
-}
-
-/* Race with expectations being used means we could have none to find; OK. */
-static void evict_oldest_expect(struct nf_conn *master)
-{
-        struct nf_conntrack_expect *i;
-
-        list_for_each_entry_reverse(i, &nf_conntrack_expect_list, list) {
-                if (i->master == master) {
-                        if (del_timer(&i->timeout)) {
-                                nf_ct_unlink_expect(i);
-                                nf_conntrack_expect_put(i);
-                        }
-                        break;
-                }
-        }
-}
-
-static inline int refresh_timer(struct nf_conntrack_expect *i)
-{
-        struct nf_conn_help *master_help = nfct_help(i->master);
-
-        if (!del_timer(&i->timeout))
-                return 0;
-
-        i->timeout.expires = jiffies + master_help->helper->timeout*HZ;
-        add_timer(&i->timeout);
-        return 1;
-}
-
-int nf_conntrack_expect_related(struct nf_conntrack_expect *expect)
-{
-        struct nf_conntrack_expect *i;
-        struct nf_conn *master = expect->master;
-        struct nf_conn_help *master_help = nfct_help(master);
-        int ret;
-
-        NF_CT_ASSERT(master_help);
-
-        DEBUGP("nf_conntrack_expect_related %p\n", related_to);
-        DEBUGP("tuple: "); NF_CT_DUMP_TUPLE(&expect->tuple);
-        DEBUGP("mask:  "); NF_CT_DUMP_TUPLE(&expect->mask);
-
-        write_lock_bh(&nf_conntrack_lock);
-        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
-                if (expect_matches(i, expect)) {
-                        /* Refresh timer: if it's dying, ignore.. */
-                        if (refresh_timer(i)) {
-                                ret = 0;
-                                goto out;
-                        }
-                } else if (expect_clash(i, expect)) {
-                        ret = -EBUSY;
-                        goto out;
-                }
-        }
-        /* Will be over limit? */
-        if (master_help->helper->max_expected &&
-            master_help->expecting >= master_help->helper->max_expected)
-                evict_oldest_expect(master);
-
-        nf_conntrack_expect_insert(expect);
-        nf_conntrack_expect_event(IPEXP_NEW, expect);
-        ret = 0;
-out:
-        write_unlock_bh(&nf_conntrack_lock);
-        return ret;
-}
-
 int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 {
         int ret;
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
new file mode 100644
index 000000000000..076e678b3188
--- /dev/null
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -0,0 +1,365 @@
+/* Expectation handling for nf_conntrack. */
+
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.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/types.h>
+#include <linux/netfilter.h>
+#include <linux/skbuff.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/stddef.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/percpu.h>
+#include <linux/kernel.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+
+LIST_HEAD(nf_conntrack_expect_list);
+kmem_cache_t *nf_conntrack_expect_cachep __read_mostly;
+DECLARE_PER_CPU(struct ip_conntrack_stat, nf_conntrack_stat);
+static unsigned int nf_conntrack_expect_next_id;
+
+/* nf_conntrack_expect helper functions */
+void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
+{
+        struct nf_conn_help *master_help = nfct_help(exp->master);
+
+        NF_CT_ASSERT(master_help);
+        NF_CT_ASSERT(!timer_pending(&exp->timeout));
+
+        list_del(&exp->list);
+        NF_CT_STAT_INC(expect_delete);
+        master_help->expecting--;
+        nf_conntrack_expect_put(exp);
+}
+
+static void expectation_timed_out(unsigned long ul_expect)
+{
+        struct nf_conntrack_expect *exp = (void *)ul_expect;
+
+        write_lock_bh(&nf_conntrack_lock);
+        nf_ct_unlink_expect(exp);
+        write_unlock_bh(&nf_conntrack_lock);
+        nf_conntrack_expect_put(exp);
+}
+
+struct nf_conntrack_expect *
+__nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
+{
+        struct nf_conntrack_expect *i;
+
+        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
+                if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask))
+                        return i;
+        }
+        return NULL;
+}
+
+/* Just find a expectation corresponding to a tuple. */
+struct nf_conntrack_expect *
+nf_conntrack_expect_find(const struct nf_conntrack_tuple *tuple)
+{
+        struct nf_conntrack_expect *i;
+
+        read_lock_bh(&nf_conntrack_lock);
+        i = __nf_conntrack_expect_find(tuple);
+        if (i)
+                atomic_inc(&i->use);
+        read_unlock_bh(&nf_conntrack_lock);
+
+        return i;
+}
+
+/* If an expectation for this connection is found, it gets delete from
+ * global list then returned. */
+struct nf_conntrack_expect *
+find_expectation(const struct nf_conntrack_tuple *tuple)
+{
+        struct nf_conntrack_expect *i;
+
+        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
+        /* If master is not in hash table yet (ie. packet hasn't left
+           this machine yet), how can other end know about expected?
+           Hence these are not the droids you are looking for (if
+           master ct never got confirmed, we'd hold a reference to it
+           and weird things would happen to future packets). */
+                if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)
+                    && nf_ct_is_confirmed(i->master)) {
+                        if (i->flags & NF_CT_EXPECT_PERMANENT) {
+                                atomic_inc(&i->use);
+                                return i;
+                        } else if (del_timer(&i->timeout)) {
+                                nf_ct_unlink_expect(i);
+                                return i;
+                        }
+                }
+        }
+        return NULL;
+}
+
+/* delete all expectations for this conntrack */
+void nf_ct_remove_expectations(struct nf_conn *ct)
+{
+        struct nf_conntrack_expect *i, *tmp;
+        struct nf_conn_help *help = nfct_help(ct);
+
+        /* Optimization: most connection never expect any others. */
+        if (!help || help->expecting == 0)
+                return;
+
+        list_for_each_entry_safe(i, tmp, &nf_conntrack_expect_list, list) {
+                if (i->master == ct && del_timer(&i->timeout)) {
+                        nf_ct_unlink_expect(i);
+                        nf_conntrack_expect_put(i);
+                }
+        }
+}
+
+/* Would two expected things clash? */
+static inline int expect_clash(const struct nf_conntrack_expect *a,
+                               const struct nf_conntrack_expect *b)
+{
+        /* Part covered by intersection of masks must be unequal,
+           otherwise they clash */
+        struct nf_conntrack_tuple intersect_mask;
+        int count;
+
+        intersect_mask.src.l3num = a->mask.src.l3num & b->mask.src.l3num;
+        intersect_mask.src.u.all = a->mask.src.u.all & b->mask.src.u.all;
+        intersect_mask.dst.u.all = a->mask.dst.u.all & b->mask.dst.u.all;
+        intersect_mask.dst.protonum = a->mask.dst.protonum
+                                        & b->mask.dst.protonum;
+
+        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
+                intersect_mask.src.u3.all[count] =
+                        a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
+        }
+
+        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
+                intersect_mask.dst.u3.all[count] =
+                        a->mask.dst.u3.all[count] & b->mask.dst.u3.all[count];
+        }
+
+        return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
+}
+
+static inline int expect_matches(const struct nf_conntrack_expect *a,
+                                 const struct nf_conntrack_expect *b)
+{
+        return a->master == b->master
+                && nf_ct_tuple_equal(&a->tuple, &b->tuple)
+                && nf_ct_tuple_equal(&a->mask, &b->mask);
+}
+
+/* Generally a bad idea to call this: could have matched already. */
+void nf_conntrack_unexpect_related(struct nf_conntrack_expect *exp)
+{
+        struct nf_conntrack_expect *i;
+
+        write_lock_bh(&nf_conntrack_lock);
+        /* choose the the oldest expectation to evict */
+        list_for_each_entry_reverse(i, &nf_conntrack_expect_list, list) {
+                if (expect_matches(i, exp) && del_timer(&i->timeout)) {
+                        nf_ct_unlink_expect(i);
+                        write_unlock_bh(&nf_conntrack_lock);
+                        nf_conntrack_expect_put(i);
+                        return;
+                }
+        }
+        write_unlock_bh(&nf_conntrack_lock);
+}
+
+/* We don't increase the master conntrack refcount for non-fulfilled
+ * conntracks. During the conntrack destruction, the expectations are
+ * always killed before the conntrack itself */
+struct nf_conntrack_expect *nf_conntrack_expect_alloc(struct nf_conn *me)
+{
+        struct nf_conntrack_expect *new;
+
+        new = kmem_cache_alloc(nf_conntrack_expect_cachep, GFP_ATOMIC);
+        if (!new)
+                return NULL;
+
+        new->master = me;
+        atomic_set(&new->use, 1);
+        return new;
+}
+
+void nf_conntrack_expect_put(struct nf_conntrack_expect *exp)
+{
+        if (atomic_dec_and_test(&exp->use))
+                kmem_cache_free(nf_conntrack_expect_cachep, exp);
+}
+
+static void nf_conntrack_expect_insert(struct nf_conntrack_expect *exp)
+{
+        struct nf_conn_help *master_help = nfct_help(exp->master);
+
+        atomic_inc(&exp->use);
+        master_help->expecting++;
+        list_add(&exp->list, &nf_conntrack_expect_list);
+
+        init_timer(&exp->timeout);
+        exp->timeout.data = (unsigned long)exp;
+        exp->timeout.function = expectation_timed_out;
+        exp->timeout.expires = jiffies + master_help->helper->timeout * HZ;
+        add_timer(&exp->timeout);
+
+        exp->id = ++nf_conntrack_expect_next_id;
+        atomic_inc(&exp->use);
+        NF_CT_STAT_INC(expect_create);
+}
+
+/* Race with expectations being used means we could have none to find; OK. */
+static void evict_oldest_expect(struct nf_conn *master)
+{
+        struct nf_conntrack_expect *i;
+
+        list_for_each_entry_reverse(i, &nf_conntrack_expect_list, list) {
+                if (i->master == master) {
+                        if (del_timer(&i->timeout)) {
+                                nf_ct_unlink_expect(i);
+                                nf_conntrack_expect_put(i);
+                        }
+                        break;
+                }
+        }
+}
+
+static inline int refresh_timer(struct nf_conntrack_expect *i)
+{
+        struct nf_conn_help *master_help = nfct_help(i->master);
+
+        if (!del_timer(&i->timeout))
+                return 0;
+
+        i->timeout.expires = jiffies + master_help->helper->timeout*HZ;
+        add_timer(&i->timeout);
+        return 1;
+}
+
+int nf_conntrack_expect_related(struct nf_conntrack_expect *expect)
+{
+        struct nf_conntrack_expect *i;
+        struct nf_conn *master = expect->master;
+        struct nf_conn_help *master_help = nfct_help(master);
+        int ret;
+
+        NF_CT_ASSERT(master_help);
+
+        write_lock_bh(&nf_conntrack_lock);
+        list_for_each_entry(i, &nf_conntrack_expect_list, list) {
+                if (expect_matches(i, expect)) {
+                        /* Refresh timer: if it's dying, ignore.. */
+                        if (refresh_timer(i)) {
+                                ret = 0;
+                                goto out;
+                        }
+                } else if (expect_clash(i, expect)) {
+                        ret = -EBUSY;
+                        goto out;
+                }
+        }
+        /* Will be over limit? */
+        if (master_help->helper->max_expected &&
+            master_help->expecting >= master_help->helper->max_expected)
+                evict_oldest_expect(master);
+
+        nf_conntrack_expect_insert(expect);
+        nf_conntrack_expect_event(IPEXP_NEW, expect);
+        ret = 0;
+out:
+        write_unlock_bh(&nf_conntrack_lock);
+        return ret;
+}
+
+#ifdef CONFIG_PROC_FS
+static void *exp_seq_start(struct seq_file *s, loff_t *pos)
+{
+        struct list_head *e = &nf_conntrack_expect_list;
+        loff_t i;
+
+        /* strange seq_file api calls stop even if we fail,
+         * thus we need to grab lock since stop unlocks */
+        read_lock_bh(&nf_conntrack_lock);
+
+        if (list_empty(e))
+                return NULL;
+
+        for (i = 0; i <= *pos; i++) {
+                e = e->next;
+                if (e == &nf_conntrack_expect_list)
+                        return NULL;
+        }
+        return e;
+}
+
+static void *exp_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+        struct list_head *e = v;
+
+        ++*pos;
+        e = e->next;
+
+        if (e == &nf_conntrack_expect_list)
+                return NULL;
+
+        return e;
+}
+
+static void exp_seq_stop(struct seq_file *s, void *v)
+{
+        read_unlock_bh(&nf_conntrack_lock);
+}
+
+static int exp_seq_show(struct seq_file *s, void *v)
+{
+        struct nf_conntrack_expect *expect = v;
+
+        if (expect->timeout.function)
+                seq_printf(s, "%ld ", timer_pending(&expect->timeout)
+                           ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
+        else
+                seq_printf(s, "- ");
+        seq_printf(s, "l3proto = %u proto=%u ",
+                   expect->tuple.src.l3num,
+                   expect->tuple.dst.protonum);
+        print_tuple(s, &expect->tuple,
+                    __nf_ct_l3proto_find(expect->tuple.src.l3num),
+                    __nf_ct_proto_find(expect->tuple.src.l3num,
+                                       expect->tuple.dst.protonum));
+        return seq_putc(s, '\n');
+}
+
+static struct seq_operations exp_seq_ops = {
+        .start = exp_seq_start,
+        .next = exp_seq_next,
+        .stop = exp_seq_stop,
+        .show = exp_seq_show
+};
+
+static int exp_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &exp_seq_ops);
+}
+
+struct file_operations exp_file_ops = {
+        .owner   = THIS_MODULE,
+        .open    = exp_open,
+        .read    = seq_read,
+        .llseek  = seq_lseek,
+        .release = seq_release
+};
+#endif /* CONFIG_PROC_FS */
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 0c17a5bd112b..503fabf18843 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -26,6 +26,7 @@
 #include <net/tcp.h>
 
 #include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <linux/netfilter/nf_conntrack_ftp.h>
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index cfb35fd8d9b9..c3d53d91929f 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -35,6 +35,7 @@
 #include <linux/netfilter.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_protocol.h>
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 5954f6773810..72643d32cab3 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -36,6 +36,7 @@
 #include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_protocol.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 
 #if 0
@@ -66,7 +67,7 @@ static int kill_proto(struct nf_conn *i, void *data)
 }
 
 #ifdef CONFIG_PROC_FS
-static int
+int
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             struct nf_conntrack_l3proto *l3proto,
             struct nf_conntrack_protocol *proto)
@@ -258,84 +259,6 @@ static struct file_operations ct_file_ops = {
         .release = seq_release_private,
 };
 
-/* expects */
-static void *exp_seq_start(struct seq_file *s, loff_t *pos)
-{
-        struct list_head *e = &nf_conntrack_expect_list;
-        loff_t i;
-
-        /* strange seq_file api calls stop even if we fail,
-         * thus we need to grab lock since stop unlocks */
-        read_lock_bh(&nf_conntrack_lock);
-
-        if (list_empty(e))
-                return NULL;
-
-        for (i = 0; i <= *pos; i++) {
-                e = e->next;
-                if (e == &nf_conntrack_expect_list)
-                        return NULL;
-        }
-        return e;
-}
-
-static void *exp_seq_next(struct seq_file *s, void *v, loff_t *pos)
-{
-        struct list_head *e = v;
-
-        ++*pos;
-        e = e->next;
-
-        if (e == &nf_conntrack_expect_list)
-                return NULL;
-
-        return e;
-}
-
-static void exp_seq_stop(struct seq_file *s, void *v)
-{
-        read_unlock_bh(&nf_conntrack_lock);
-}
-
-static int exp_seq_show(struct seq_file *s, void *v)
-{
-        struct nf_conntrack_expect *expect = v;
-
-        if (expect->timeout.function)
-                seq_printf(s, "%ld ", timer_pending(&expect->timeout)
-                           ? (long)(expect->timeout.expires - jiffies)/HZ : 0);
-        else
-                seq_printf(s, "- ");
-        seq_printf(s, "l3proto = %u proto=%u ",
-                   expect->tuple.src.l3num,
-                   expect->tuple.dst.protonum);
-        print_tuple(s, &expect->tuple,
-                    __nf_ct_l3proto_find(expect->tuple.src.l3num),
-                    __nf_ct_proto_find(expect->tuple.src.l3num,
-                                       expect->tuple.dst.protonum));
-        return seq_putc(s, '\n');
-}
-
-static struct seq_operations exp_seq_ops = {
-        .start = exp_seq_start,
-        .next = exp_seq_next,
-        .stop = exp_seq_stop,
-        .show = exp_seq_show
-};
-
-static int exp_open(struct inode *inode, struct file *file)
-{
-        return seq_open(file, &exp_seq_ops);
-}
-
-static struct file_operations exp_file_ops = {
-        .owner   = THIS_MODULE,
-        .open    = exp_open,
-        .read    = seq_read,
-        .llseek  = seq_lseek,
-        .release = seq_release
-};
-
 static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos)
 {
         int cpu;