Patchwork conntrack: Reduce conntrack count in nf_conntrack_free()

login
register
mail settings
Submitter Eric Dumazet
Date March 25, 2009, 3:53 a.m.
Message ID <49C9AAAC.30607@cosmosbay.com>
Download mbox | patch
Permalink /patch/25043/
State Not Applicable
Delegated to: David Miller
Headers show

Comments

Eric Dumazet - March 25, 2009, 3:53 a.m.
Patrick McHardy a écrit :
> Eric Dumazet wrote:
>> Eric Dumazet a écrit :
>>> Patrick McHardy a écrit :
>>>> Eric Dumazet wrote:
>>
>>>>> Maybe we could use SLAB_DESTROY_BY_RCU thing and no more call_rcu()
>>>>> queueing
>>>>> problem. That would better use CPU caches as well...
>>>> I'm not sure I understand the rules correctly, but we'd still
>>>> have to wait for the grace period before an object can be reused,
>>>> no?
>>> No we dont have to, but we must do additionnal checks after getting
>>> a reference on object found on lookup.
>>> (We must re-check the keys used during search)
>>>
>>> This re-check is not very expensive since everything is hot in cpu
>>> cache.
>>>
>>> Check Documentation/RCU/rculist_nulls.txt for some documentation.
>>>
>>
>> Patrick, I can work on this if you want, since this stuff is fresh
>> in my head, let me know if you already challenged it or not :)
> 
> I'm still looking at the details, if you want to take care of this,
> that would be great .)
> 
> 

I have a litle problem on __nf_conntrack_find() being exported.

Problem is that with SLAB_DESTROY_BY_RCU we must take a reference on object
to recheck it. So ideally  only nf_conntrack_find_get() should be used,
or callers of __nf_conntrack_find() should lock nf_conntrack_lock
(as properly done for example in net/netfilter/nf_conntrack_netlink.c, line 1292)

Here is preliminary patch for review (not tested at all, its 4h50 am here :) )

Could you help me, by checking __nf_conntrack_find() use in net/netfilter/xt_connlimit.c ?
and line 1246 of net/netfilter/nf_conntrack_netlink.c

This part is a litle bit gray for me. :)

Thank you

(Patch against nf-next-2.6 tree of course)

Eric

 include/net/netfilter/nf_conntrack.h                  |   14 -
 include/net/netfilter/nf_conntrack_tuple.h            |    6
 include/net/netns/conntrack.h                         |    5
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c |   16 -
 net/ipv4/netfilter/nf_nat_core.c                      |    2
 net/netfilter/nf_conntrack_core.c                     |  121 +++++-----
 net/netfilter/nf_conntrack_expect.c                   |    2
 net/netfilter/nf_conntrack_helper.c                   |    7
 net/netfilter/nf_conntrack_netlink.c                  |    7
 net/netfilter/nf_conntrack_standalone.c               |   16 -
 10 files changed, 109 insertions(+), 87 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Patrick McHardy - March 25, 2009, 1:39 p.m.
Eric Dumazet wrote:
> I have a litle problem on __nf_conntrack_find() being exported.
> 
> Problem is that with SLAB_DESTROY_BY_RCU we must take a reference on object
> to recheck it. So ideally  only nf_conntrack_find_get() should be used,
> or callers of __nf_conntrack_find() should lock nf_conntrack_lock
> (as properly done for example in net/netfilter/nf_conntrack_netlink.c, line 1292)
> 
> Here is preliminary patch for review (not tested at all, its 4h50 am here :) )
> 
> Could you help me, by checking __nf_conntrack_find() use in net/netfilter/xt_connlimit.c ?
> and line 1246 of net/netfilter/nf_conntrack_netlink.c
> 
> This part is a litle bit gray for me. :)

In case of xt_connlimit, it seems fine to just take a reference.
In case of ctnetlink, keeping the unreferenced lookup under the
lock seems fine. We unfortunately have to export some internals
like nf_conntrack lock for ctnetlink anyways, so I don't think
it would be worth to change it to take references and unexport
the lookup function.

> +/*
> + * Warning :
> + * - Caller must take a reference on returned object
> + *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
> + * OR
> + * - Caller must lock nf_conntrack_lock before calling this function
> + */
>  struct nf_conntrack_tuple_hash *
>  __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
>  {
>  	struct nf_conntrack_tuple_hash *h;
> -	struct hlist_node *n;
> +	struct hlist_nulls_node *n;
>  	unsigned int hash = hash_conntrack(tuple);
>  
>  	/* Disable BHs the entire time since we normally need to disable them
>  	 * at least once for the stats anyway.
>  	 */
>  	local_bh_disable();
> -	hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
> +begin:
> +	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
>  		if (nf_ct_tuple_equal(tuple, &h->tuple)) {
>  			NF_CT_STAT_INC(net, found);
>  			local_bh_enable();
> @@ -261,6 +270,13 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
>  		}
>  		NF_CT_STAT_INC(net, searched);
>  	}
> +	/*
> +	 * if the nulls value we got at the end of this lookup is
> +	 * not the expected one, we must restart lookup.
> +	 * We probably met an item that was moved to another chain.
> +	 */
> +	if (get_nulls_value(n) != hash)
> +		goto begin;

Are you sure this is enough? An entry might have been reused and added
to the same chain I think, so I think we need to recheck the tuple.

>  	local_bh_enable();
>  
>  	return NULL;
> @@ -275,11 +291,18 @@ nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple)
>  	struct nf_conn *ct;
>  
>  	rcu_read_lock();
> +begin:
>  	h = __nf_conntrack_find(net, tuple);
>  	if (h) {
>  		ct = nf_ct_tuplehash_to_ctrack(h);
>  		if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
>  			h = NULL;
> +		else {
> +			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
> +				nf_ct_put(ct);
> +				goto begin;

Ah I see, the hash comparison above is only an optimization?

> +			}
> +		}
>  	}
>  	rcu_read_unlock();
>  
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Eric Dumazet - March 25, 2009, 1:44 p.m.
Patrick McHardy a écrit :
> Eric Dumazet wrote:
>> I have a litle problem on __nf_conntrack_find() being exported.
>>
>> Problem is that with SLAB_DESTROY_BY_RCU we must take a reference on
>> object
>> to recheck it. So ideally  only nf_conntrack_find_get() should be used,
>> or callers of __nf_conntrack_find() should lock nf_conntrack_lock
>> (as properly done for example in net/netfilter/nf_conntrack_netlink.c,
>> line 1292)
>>
>> Here is preliminary patch for review (not tested at all, its 4h50 am
>> here :) )
>>
>> Could you help me, by checking __nf_conntrack_find() use in
>> net/netfilter/xt_connlimit.c ?
>> and line 1246 of net/netfilter/nf_conntrack_netlink.c
>>
>> This part is a litle bit gray for me. :)
> 
> In case of xt_connlimit, it seems fine to just take a reference.
> In case of ctnetlink, keeping the unreferenced lookup under the
> lock seems fine. We unfortunately have to export some internals
> like nf_conntrack lock for ctnetlink anyways, so I don't think
> it would be worth to change it to take references and unexport
> the lookup function.
> 
>> +/*
>> + * Warning :
>> + * - Caller must take a reference on returned object
>> + *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
>> + * OR
>> + * - Caller must lock nf_conntrack_lock before calling this function
>> + */
>>  struct nf_conntrack_tuple_hash *
>>  __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple
>> *tuple)
>>  {
>>      struct nf_conntrack_tuple_hash *h;
>> -    struct hlist_node *n;
>> +    struct hlist_nulls_node *n;
>>      unsigned int hash = hash_conntrack(tuple);
>>  
>>      /* Disable BHs the entire time since we normally need to disable
>> them
>>       * at least once for the stats anyway.
>>       */
>>      local_bh_disable();
>> -    hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
>> +begin:
>> +    hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
>>          if (nf_ct_tuple_equal(tuple, &h->tuple)) {
>>              NF_CT_STAT_INC(net, found);
>>              local_bh_enable();
>> @@ -261,6 +270,13 @@ __nf_conntrack_find(struct net *net, const struct
>> nf_conntrack_tuple *tuple)
>>          }
>>          NF_CT_STAT_INC(net, searched);
>>      }
>> +    /*
>> +     * if the nulls value we got at the end of this lookup is
>> +     * not the expected one, we must restart lookup.
>> +     * We probably met an item that was moved to another chain.
>> +     */
>> +    if (get_nulls_value(n) != hash)
>> +        goto begin;
> 
> Are you sure this is enough? An entry might have been reused and added
> to the same chain I think, so I think we need to recheck the tuple.

Yes, done in caller

> 
>>      local_bh_enable();
>>  
>>      return NULL;
>> @@ -275,11 +291,18 @@ nf_conntrack_find_get(struct net *net, const
>> struct nf_conntrack_tuple *tuple)
>>      struct nf_conn *ct;
>>  
>>      rcu_read_lock();
>> +begin:
>>      h = __nf_conntrack_find(net, tuple);
>>      if (h) {
>>          ct = nf_ct_tuplehash_to_ctrack(h);
>>          if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
>>              h = NULL;
>> +        else {
>> +            if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
>> +                nf_ct_put(ct);
>> +                goto begin;
> 
> Ah I see, the hash comparison above is only an optimization?
> 
>> +            }
>> +        }
>>      }
>>      rcu_read_unlock();
>>  
> 
> 

check net/ipv4/udp.c for an example (__udp4_lib_lookup())

In case of UDP, key check is not returning true/false, but a score.
So UDP case is a litle bit more complex than conntrack case.


        rcu_read_lock();
begin:
        result = NULL;
        badness = -1;
        sk_nulls_for_each_rcu(sk, node, &hslot->head) {
                score = compute_score(sk, net, saddr, hnum, sport,
                                      daddr, dport, dif);
                if (score > badness) {
                        result = sk;
                        badness = score;
                }
        }
        /*
         * if the nulls value we got at the end of this lookup is
         * not the expected one, we must restart lookup.
         * We probably met an item that was moved to another chain.
         */
        if (get_nulls_value(node) != hash)
                goto begin;

        if (result) {
                if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
                        result = NULL;
                else if (unlikely(compute_score(result, net, saddr, hnum, sport,
                                  daddr, dport, dif) < badness)) {
                        sock_put(result);
                        goto begin;
                }
        }
        rcu_read_unlock();
        return result;


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 4dfb793..6c3f964 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -91,8 +91,7 @@  struct nf_conn_help {
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 
-struct nf_conn
-{
+struct nf_conn {
 	/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
            plus 1 for any connection(s) we are `master' for */
 	struct nf_conntrack ct_general;
@@ -126,7 +125,6 @@  struct nf_conn
 #ifdef CONFIG_NET_NS
 	struct net *ct_net;
 #endif
-	struct rcu_head rcu;
 };
 
 static inline struct nf_conn *
@@ -190,9 +188,13 @@  static inline void nf_ct_put(struct nf_conn *ct)
 extern int nf_ct_l3proto_try_module_get(unsigned short l3proto);
 extern void nf_ct_l3proto_module_put(unsigned short l3proto);
 
-extern struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced);
-extern void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced,
-				 unsigned int size);
+/*
+ * Allocate a hashtable of hlist_head (if nulls == 0),
+ * or hlist_nulls_head (if nulls == 1)
+ */
+extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls);
+
+extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size);
 
 extern struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple);
diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h
index f2f6aa7..2628c15 100644
--- a/include/net/netfilter/nf_conntrack_tuple.h
+++ b/include/net/netfilter/nf_conntrack_tuple.h
@@ -12,6 +12,7 @@ 
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
+#include <linux/list_nulls.h>
 
 /* A `tuple' is a structure containing the information to uniquely
   identify a connection.  ie. if two packets have the same tuple, they
@@ -146,9 +147,8 @@  static inline void nf_ct_dump_tuple(const struct nf_conntrack_tuple *t)
 	((enum ip_conntrack_dir)(h)->tuple.dst.dir)
 
 /* Connections have two entries in the hash table: one for each way */
-struct nf_conntrack_tuple_hash
-{
-	struct hlist_node hnode;
+struct nf_conntrack_tuple_hash {
+	struct hlist_nulls_node hnnode;
 	struct nf_conntrack_tuple tuple;
 };
 
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index f4498a6..9dc5840 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -2,6 +2,7 @@ 
 #define __NETNS_CONNTRACK_H
 
 #include <linux/list.h>
+#include <linux/list_nulls.h>
 #include <asm/atomic.h>
 
 struct ctl_table_header;
@@ -10,9 +11,9 @@  struct nf_conntrack_ecache;
 struct netns_ct {
 	atomic_t		count;
 	unsigned int		expect_count;
-	struct hlist_head	*hash;
+	struct hlist_nulls_head	*hash;
 	struct hlist_head	*expect_hash;
-	struct hlist_head	unconfirmed;
+	struct hlist_nulls_head	unconfirmed;
 	struct ip_conntrack_stat *stat;
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	struct nf_conntrack_ecache *ecache;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 6ba5c55..fcbcf62 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -25,30 +25,30 @@  struct ct_iter_state {
 	unsigned int bucket;
 };
 
-static struct hlist_node *ct_get_first(struct seq_file *seq)
+static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 {
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 
 	for (st->bucket = 0;
 	     st->bucket < nf_conntrack_htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(net->ct.hash[st->bucket].first);
-		if (n)
+		if (!is_a_nulls(n))
 			return n;
 	}
 	return NULL;
 }
 
-static struct hlist_node *ct_get_next(struct seq_file *seq,
-				      struct hlist_node *head)
+static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
+				      struct hlist_nulls_node *head)
 {
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
 	head = rcu_dereference(head->next);
-	while (head == NULL) {
+	while (is_a_nulls(head)) {
 		if (++st->bucket >= nf_conntrack_htable_size)
 			return NULL;
 		head = rcu_dereference(net->ct.hash[st->bucket].first);
@@ -56,9 +56,9 @@  static struct hlist_node *ct_get_next(struct seq_file *seq,
 	return head;
 }
 
-static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos)
+static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 {
-	struct hlist_node *head = ct_get_first(seq);
+	struct hlist_nulls_node *head = ct_get_first(seq);
 
 	if (head)
 		while (pos && (head = ct_get_next(seq, head)))
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index a65cf69..fe65187 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -679,7 +679,7 @@  nfnetlink_parse_nat_setup(struct nf_conn *ct,
 static int __net_init nf_nat_net_init(struct net *net)
 {
 	net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size,
-						      &net->ipv4.nat_vmalloced);
+						      &net->ipv4.nat_vmalloced, 0);
 	if (!net->ipv4.nat_bysource)
 		return -ENOMEM;
 	return 0;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 55befe5..9f714e9 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -29,6 +29,7 @@ 
 #include <linux/netdevice.h>
 #include <linux/socket.h>
 #include <linux/mm.h>
+#include <linux/rculist_nulls.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l3proto.h>
@@ -163,8 +164,8 @@  static void
 clean_from_lists(struct nf_conn *ct)
 {
 	pr_debug("clean_from_lists(%p)\n", ct);
-	hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
-	hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode);
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);
 
 	/* Destroy all pending expectations */
 	nf_ct_remove_expectations(ct);
@@ -204,8 +205,8 @@  destroy_conntrack(struct nf_conntrack *nfct)
 
 	/* We overload first tuple to link into unconfirmed list. */
 	if (!nf_ct_is_confirmed(ct)) {
-		BUG_ON(hlist_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode));
-		hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+		BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+		hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 	}
 
 	NF_CT_STAT_INC(net, delete);
@@ -242,18 +243,26 @@  static void death_by_timeout(unsigned long ul_conntrack)
 	nf_ct_put(ct);
 }
 
+/*
+ * Warning :
+ * - Caller must take a reference on returned object
+ *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
+ * OR
+ * - Caller must lock nf_conntrack_lock before calling this function
+ */
 struct nf_conntrack_tuple_hash *
 __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
 {
 	struct nf_conntrack_tuple_hash *h;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 	unsigned int hash = hash_conntrack(tuple);
 
 	/* Disable BHs the entire time since we normally need to disable them
 	 * at least once for the stats anyway.
 	 */
 	local_bh_disable();
-	hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+begin:
+	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
 		if (nf_ct_tuple_equal(tuple, &h->tuple)) {
 			NF_CT_STAT_INC(net, found);
 			local_bh_enable();
@@ -261,6 +270,13 @@  __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
 		}
 		NF_CT_STAT_INC(net, searched);
 	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(n) != hash)
+		goto begin;
 	local_bh_enable();
 
 	return NULL;
@@ -275,11 +291,18 @@  nf_conntrack_find_get(struct net *net, const struct nf_conntrack_tuple *tuple)
 	struct nf_conn *ct;
 
 	rcu_read_lock();
+begin:
 	h = __nf_conntrack_find(net, tuple);
 	if (h) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
 			h = NULL;
+		else {
+			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
+				nf_ct_put(ct);
+				goto begin;
+			}
+		}
 	}
 	rcu_read_unlock();
 
@@ -293,9 +316,9 @@  static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 {
 	struct net *net = nf_ct_net(ct);
 
-	hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
 			   &net->ct.hash[hash]);
-	hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode,
+	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
 			   &net->ct.hash[repl_hash]);
 }
 
@@ -318,7 +341,7 @@  __nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
 	struct nf_conn_help *help;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 	enum ip_conntrack_info ctinfo;
 	struct net *net;
 
@@ -350,17 +373,17 @@  __nf_conntrack_confirm(struct sk_buff *skb)
 	/* See if there's one in the list already, including reverse:
 	   NAT could have grabbed it without realizing, since we're
 	   not in the hash.  If there is, we lost race. */
-	hlist_for_each_entry(h, n, &net->ct.hash[hash], hnode)
+	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				      &h->tuple))
 			goto out;
-	hlist_for_each_entry(h, n, &net->ct.hash[repl_hash], hnode)
+	hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
 		if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				      &h->tuple))
 			goto out;
 
 	/* Remove from unconfirmed list */
-	hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
 
 	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 	/* Timer relative to confirmation time, not original
@@ -399,14 +422,14 @@  nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 {
 	struct net *net = nf_ct_net(ignored_conntrack);
 	struct nf_conntrack_tuple_hash *h;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 	unsigned int hash = hash_conntrack(tuple);
 
 	/* Disable BHs the entire time since we need to disable them at
 	 * least once for the stats anyway.
 	 */
 	rcu_read_lock_bh();
-	hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
 		if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack &&
 		    nf_ct_tuple_equal(tuple, &h->tuple)) {
 			NF_CT_STAT_INC(net, found);
@@ -430,14 +453,14 @@  static noinline int early_drop(struct net *net, unsigned int hash)
 	/* Use oldest entry, which is roughly LRU */
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct = NULL, *tmp;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 	unsigned int i, cnt = 0;
 	int dropped = 0;
 
 	rcu_read_lock();
 	for (i = 0; i < nf_conntrack_htable_size; i++) {
-		hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash],
-					 hnode) {
+		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
+					 hnnode) {
 			tmp = nf_ct_tuplehash_to_ctrack(h);
 			if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
 				ct = tmp;
@@ -508,27 +531,19 @@  struct nf_conn *nf_conntrack_alloc(struct net *net,
 #ifdef CONFIG_NET_NS
 	ct->ct_net = net;
 #endif
-	INIT_RCU_HEAD(&ct->rcu);
 
 	return ct;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
 
-static void nf_conntrack_free_rcu(struct rcu_head *head)
-{
-	struct nf_conn *ct = container_of(head, struct nf_conn, rcu);
-
-	nf_ct_ext_free(ct);
-	kmem_cache_free(nf_conntrack_cachep, ct);
-}
-
 void nf_conntrack_free(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
 	nf_ct_ext_destroy(ct);
 	atomic_dec(&net->ct.count);
-	call_rcu(&ct->rcu, nf_conntrack_free_rcu);
+	nf_ct_ext_free(ct);
+	kmem_cache_free(nf_conntrack_cachep, ct);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_free);
 
@@ -594,7 +609,7 @@  init_conntrack(struct net *net,
 	}
 
 	/* Overload tuple linked list to put us in unconfirmed list. */
-	hlist_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
 		       &net->ct.unconfirmed);
 
 	spin_unlock_bh(&nf_conntrack_lock);
@@ -934,17 +949,17 @@  get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 {
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 
 	spin_lock_bh(&nf_conntrack_lock);
 	for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
-		hlist_for_each_entry(h, n, &net->ct.hash[*bucket], hnode) {
+		hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (iter(ct, data))
 				goto found;
 		}
 	}
-	hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode) {
+	hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
 		ct = nf_ct_tuplehash_to_ctrack(h);
 		if (iter(ct, data))
 			set_bit(IPS_DYING_BIT, &ct->status);
@@ -992,7 +1007,7 @@  static int kill_all(struct nf_conn *i, void *data)
 	return 1;
 }
 
-void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, unsigned int size)
+void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
 {
 	if (vmalloced)
 		vfree(hash);
@@ -1060,26 +1075,28 @@  void nf_conntrack_cleanup(struct net *net)
 	}
 }
 
-struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced)
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls)
 {
-	struct hlist_head *hash;
-	unsigned int size, i;
+	struct hlist_nulls_head *hash;
+	unsigned int nr_slots, i;
+	size_t sz;
 
 	*vmalloced = 0;
 
-	size = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_head));
-	hash = (void*)__get_free_pages(GFP_KERNEL|__GFP_NOWARN,
-				       get_order(sizeof(struct hlist_head)
-						 * size));
+	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
+	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
+	sz = nr_slots * sizeof(struct hlist_nulls_head);
+	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
+					get_order(sz));
 	if (!hash) {
 		*vmalloced = 1;
 		printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
-		hash = vmalloc(sizeof(struct hlist_head) * size);
+		hash = __vmalloc(sz, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
 	}
 
-	if (hash)
-		for (i = 0; i < size; i++)
-			INIT_HLIST_HEAD(&hash[i]);
+	if (hash && nulls)
+		for (i = 0; i < nr_slots; i++)
+			INIT_HLIST_NULLS_HEAD(&hash[i], i);
 
 	return hash;
 }
@@ -1090,7 +1107,7 @@  int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	int i, bucket, vmalloced, old_vmalloced;
 	unsigned int hashsize, old_size;
 	int rnd;
-	struct hlist_head *hash, *old_hash;
+	struct hlist_nulls_head *hash, *old_hash;
 	struct nf_conntrack_tuple_hash *h;
 
 	/* On boot, we can set this without any fancy locking. */
@@ -1101,7 +1118,7 @@  int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	if (!hashsize)
 		return -EINVAL;
 
-	hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced);
+	hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
 	if (!hash)
 		return -ENOMEM;
 
@@ -1116,12 +1133,12 @@  int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	 */
 	spin_lock_bh(&nf_conntrack_lock);
 	for (i = 0; i < nf_conntrack_htable_size; i++) {
-		while (!hlist_empty(&init_net.ct.hash[i])) {
-			h = hlist_entry(init_net.ct.hash[i].first,
-					struct nf_conntrack_tuple_hash, hnode);
-			hlist_del_rcu(&h->hnode);
+		while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
+			h = hlist_nulls_entry(init_net.ct.hash[i].first,
+					struct nf_conntrack_tuple_hash, hnnode);
+			hlist_nulls_del_rcu(&h->hnnode);
 			bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
-			hlist_add_head(&h->hnode, &hash[bucket]);
+			hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
 		}
 	}
 	old_size = nf_conntrack_htable_size;
@@ -1172,7 +1189,7 @@  static int nf_conntrack_init_init_net(void)
 
 	nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
 						sizeof(struct nf_conn),
-						0, 0, NULL);
+						0, SLAB_DESTROY_BY_RCU, NULL);
 	if (!nf_conntrack_cachep) {
 		printk(KERN_ERR "Unable to create nf_conn slab cache\n");
 		ret = -ENOMEM;
@@ -1212,7 +1229,7 @@  static int nf_conntrack_init_net(struct net *net)
 	if (ret < 0)
 		goto err_ecache;
 	net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size,
-						  &net->ct.hash_vmalloc);
+					     &net->ct.hash_vmalloc, 1);
 	if (!net->ct.hash) {
 		ret = -ENOMEM;
 		printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 357ba39..3940f99 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -604,7 +604,7 @@  int nf_conntrack_expect_init(struct net *net)
 
 	net->ct.expect_count = 0;
 	net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize,
-						  &net->ct.expect_vmalloc);
+						  &net->ct.expect_vmalloc, 0);
 	if (net->ct.expect_hash == NULL)
 		goto err1;
 
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a51bdac..6066144 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -158,6 +158,7 @@  static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_expect *exp;
 	const struct hlist_node *n, *next;
+	const struct hlist_nulls_node *nn;
 	unsigned int i;
 
 	/* Get rid of expectations */
@@ -174,10 +175,10 @@  static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 	}
 
 	/* Get rid of expecteds, set helpers to NULL. */
-	hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode)
+	hlist_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode)
 		unhelp(h, me);
 	for (i = 0; i < nf_conntrack_htable_size; i++) {
-		hlist_for_each_entry(h, n, &net->ct.hash[i], hnode)
+		hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
 			unhelp(h, me);
 	}
 }
@@ -217,7 +218,7 @@  int nf_conntrack_helper_init(void)
 
 	nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
 	nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize,
-						  &nf_ct_helper_vmalloc);
+						  &nf_ct_helper_vmalloc, 0);
 	if (!nf_ct_helper_hash)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 1b75c9e..6520c94 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -19,6 +19,7 @@ 
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/rculist.h>
+#include <linux/rculist_nulls.h>
 #include <linux/types.h>
 #include <linux/timer.h>
 #include <linux/skbuff.h>
@@ -536,7 +537,7 @@  ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 	struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 
@@ -544,8 +545,8 @@  ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	last = (struct nf_conn *)cb->args[1];
 	for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
 restart:
-		hlist_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]],
-					 hnode) {
+		hlist_nulls_for_each_entry_rcu(h, n, &init_net.ct.hash[cb->args[0]],
+					 hnnode) {
 			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
 				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 4da54b0..f768368 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -44,30 +44,30 @@  struct ct_iter_state {
 	unsigned int bucket;
 };
 
-static struct hlist_node *ct_get_first(struct seq_file *seq)
+static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 {
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
-	struct hlist_node *n;
+	struct hlist_nulls_node *n;
 
 	for (st->bucket = 0;
 	     st->bucket < nf_conntrack_htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(net->ct.hash[st->bucket].first);
-		if (n)
+		if (!is_a_nulls(n))
 			return n;
 	}
 	return NULL;
 }
 
-static struct hlist_node *ct_get_next(struct seq_file *seq,
-				      struct hlist_node *head)
+static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
+				      struct hlist_nulls_node *head)
 {
 	struct net *net = seq_file_net(seq);
 	struct ct_iter_state *st = seq->private;
 
 	head = rcu_dereference(head->next);
-	while (head == NULL) {
+	while (is_a_nulls(head)) {
 		if (++st->bucket >= nf_conntrack_htable_size)
 			return NULL;
 		head = rcu_dereference(net->ct.hash[st->bucket].first);
@@ -75,9 +75,9 @@  static struct hlist_node *ct_get_next(struct seq_file *seq,
 	return head;
 }
 
-static struct hlist_node *ct_get_idx(struct seq_file *seq, loff_t pos)
+static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
 {
-	struct hlist_node *head = ct_get_first(seq);
+	struct hlist_nulls_node *head = ct_get_first(seq);
 
 	if (head)
 		while (pos && (head = ct_get_next(seq, head)))