netfilter: conntrack: use a single hashtable for all namespaces

We already include netns address in the hash and compare the netns pointers
during lookup, so even if namespaces have overlapping addresses entries
will be spread across the table.

Assuming 64k bucket size, this change saves 0.5 mbyte per namespace on a
64bit system.

NAT bysrc and expectation hash is still per namespace, those will
changed too soon.

Future patch will also make conntrack object slab cache global again.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/netfilter/nf_conntrack_core.h

@@ -81,6 +81,7 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
 
 #define CONNTRACK_LOCKS 1024
 
+extern struct hlist_nulls_head *nf_conntrack_hash;
 extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
 void nf_conntrack_lock(spinlock_t *lock);
 

include/net/netns/conntrack.h

@@ -93,9 +93,7 @@ struct netns_ct {
 	int			sysctl_tstamp;
 	int			sysctl_checksum;
 
-	unsigned int		htable_size;
 	struct kmem_cache	*nf_conntrack_cachep;
-	struct hlist_nulls_head	*hash;
 	struct hlist_head	*expect_hash;
 	struct ct_pcpu __percpu *pcpu_lists;
 	struct ip_conntrack_stat __percpu *stat;

net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c

@@ -360,7 +360,7 @@ static int ipv4_init_net(struct net *net)
 
 	in->ctl_table[0].data = &nf_conntrack_max;
 	in->ctl_table[1].data = &net->ct.count;
-	in->ctl_table[2].data = &net->ct.htable_size;
+	in->ctl_table[2].data = &nf_conntrack_htable_size;
 	in->ctl_table[3].data = &net->ct.sysctl_checksum;
 	in->ctl_table[4].data = &net->ct.sysctl_log_invalid;
 #endif

net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c

@@ -31,15 +31,14 @@ struct ct_iter_state {
 
 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_nulls_node *n;
 
 	for (st->bucket = 0;
-	     st->bucket < net->ct.htable_size;
+	     st->bucket < nf_conntrack_htable_size;
 	     st->bucket++) {
 		n = rcu_dereference(
-			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+			hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -49,17 +48,16 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 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(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= net->ct.htable_size)
+			if (++st->bucket >= nf_conntrack_htable_size)
 				return NULL;
 		}
 		head = rcu_dereference(
-			hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+			hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
 	}
 	return head;
 }

net/netfilter/nf_conntrack_core.c

@@ -69,6 +69,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks);
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
 EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
 
+struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
+EXPORT_SYMBOL_GPL(nf_conntrack_hash);
+
 static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
 static __read_mostly seqcount_t nf_conntrack_generation;
 static __read_mostly bool nf_conntrack_locks_all;
@@ -164,9 +167,9 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
 		      tuple->dst.protonum));
 }
 
-static u32 hash_bucket(u32 hash, const struct net *net)
+static u32 scale_hash(u32 hash)
 {
-	return reciprocal_scale(hash, net->ct.htable_size);
+	return reciprocal_scale(hash, nf_conntrack_htable_size);
 }
 
 static u32 __hash_conntrack(const struct net *net,
@@ -179,7 +182,7 @@ static u32 __hash_conntrack(const struct net *net,
 static u32 hash_conntrack(const struct net *net,
 			  const struct nf_conntrack_tuple *tuple)
 {
-	return __hash_conntrack(net, tuple, net->ct.htable_size);
+	return scale_hash(hash_conntrack_raw(tuple, net));
 }
 
 bool
@@ -478,8 +481,8 @@ ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
 begin:
 	do {
 		sequence = read_seqcount_begin(&nf_conntrack_generation);
-		bucket = hash_bucket(hash, net);
-		ct_hash = net->ct.hash;
+		bucket = scale_hash(hash);
+		ct_hash = nf_conntrack_hash;
 	} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
 
 	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
@@ -543,12 +546,10 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct,
 				       unsigned int hash,
 				       unsigned int reply_hash)
 {
-	struct net *net = nf_ct_net(ct);
-
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-			   &net->ct.hash[hash]);
+			   &nf_conntrack_hash[hash]);
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
-			   &net->ct.hash[reply_hash]);
+			   &nf_conntrack_hash[reply_hash]);
 }
 
 int
@@ -573,12 +574,12 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
 
 	/* See if there's one in the list already, including reverse */
-	hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
 		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				    zone, net))
 			goto out;
 
-	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
 		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				    zone, net))
 			goto out;
@@ -633,7 +634,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		sequence = read_seqcount_begin(&nf_conntrack_generation);
 		/* reuse the hash saved before */
 		hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
-		hash = hash_bucket(hash, net);
+		hash = scale_hash(hash);
 		reply_hash = hash_conntrack(net,
 					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
 
@@ -663,12 +664,12 @@ __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_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
 		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
 				    zone, net))
 			goto out;
 
-	hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
+	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
 		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
 				    zone, net))
 			goto out;
@@ -736,7 +737,7 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 	do {
 		sequence = read_seqcount_begin(&nf_conntrack_generation);
 		hash = hash_conntrack(net, tuple);
-		ct_hash = net->ct.hash;
+		ct_hash = nf_conntrack_hash;
 	} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
 
 	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
@@ -773,16 +774,16 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 	local_bh_disable();
 restart:
 	sequence = read_seqcount_begin(&nf_conntrack_generation);
-	hash = hash_bucket(_hash, net);
-	for (; i < net->ct.htable_size; i++) {
+	hash = scale_hash(_hash);
+	for (; i < nf_conntrack_htable_size; i++) {
 		lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
 		nf_conntrack_lock(lockp);
 		if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
 			spin_unlock(lockp);
 			goto restart;
 		}
-		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
-					 hnnode) {
+		hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash],
+					       hnnode) {
 			tmp = nf_ct_tuplehash_to_ctrack(h);
 			if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
 			    !nf_ct_is_dying(tmp) &&
@@ -793,7 +794,7 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 			cnt++;
 		}
 
-		hash = (hash + 1) % net->ct.htable_size;
+		hash = (hash + 1) % nf_conntrack_htable_size;
 		spin_unlock(lockp);
 
 		if (ct || cnt >= NF_CT_EVICTION_RANGE)
@@ -1376,12 +1377,12 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 	int cpu;
 	spinlock_t *lockp;
 
-	for (; *bucket < net->ct.htable_size; (*bucket)++) {
+	for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
 		lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
 		local_bh_disable();
 		nf_conntrack_lock(lockp);
-		if (*bucket < net->ct.htable_size) {
-			hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
+		if (*bucket < nf_conntrack_htable_size) {
+			hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
 				if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
 					continue;
 				ct = nf_ct_tuplehash_to_ctrack(h);
@@ -1478,6 +1479,8 @@ void nf_conntrack_cleanup_end(void)
 	while (untrack_refs() > 0)
 		schedule();
 
+	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
+
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 	nf_ct_extend_unregister(&nf_ct_zone_extend);
 #endif
@@ -1528,7 +1531,6 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 	}
 
 	list_for_each_entry(net, net_exit_list, exit_list) {
-		nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 		nf_conntrack_proto_pernet_fini(net);
 		nf_conntrack_helper_pernet_fini(net);
 		nf_conntrack_ecache_pernet_fini(net);
@@ -1599,10 +1601,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 	 * though since that required taking the locks.
 	 */
 
-	for (i = 0; i < init_net.ct.htable_size; i++) {
-		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);
+	for (i = 0; i < nf_conntrack_htable_size; i++) {
+		while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
+			h = hlist_nulls_entry(nf_conntrack_hash[i].first,
+					      struct nf_conntrack_tuple_hash, hnnode);
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			hlist_nulls_del_rcu(&h->hnnode);
 			bucket = __hash_conntrack(nf_ct_net(ct),
@@ -1610,11 +1612,11 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 			hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
 		}
 	}
-	old_size = init_net.ct.htable_size;
-	old_hash = init_net.ct.hash;
+	old_size = nf_conntrack_htable_size;
+	old_hash = nf_conntrack_hash;
 
-	init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
-	init_net.ct.hash = hash;
+	nf_conntrack_hash = hash;
+	nf_conntrack_htable_size = hashsize;
 
 	write_seqcount_end(&nf_conntrack_generation);
 	nf_conntrack_all_unlock();
@@ -1670,6 +1672,11 @@ int nf_conntrack_init_start(void)
 		 * entries. */
 		max_factor = 4;
 	}
+
+	nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
+	if (!nf_conntrack_hash)
+		return -ENOMEM;
+
 	nf_conntrack_max = max_factor * nf_conntrack_htable_size;
 
 	printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
@@ -1748,6 +1755,7 @@ int nf_conntrack_init_start(void)
 err_acct:
 	nf_conntrack_expect_fini();
 err_expect:
+	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
 	return ret;
 }
 
@@ -1800,12 +1808,6 @@ int nf_conntrack_init_net(struct net *net)
 		goto err_cache;
 	}
 
-	net->ct.htable_size = nf_conntrack_htable_size;
-	net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
-	if (!net->ct.hash) {
-		printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
-		goto err_hash;
-	}
 	ret = nf_conntrack_expect_pernet_init(net);
 	if (ret < 0)
 		goto err_expect;
@@ -1837,8 +1839,6 @@ int nf_conntrack_init_net(struct net *net)
 err_acct:
 	nf_conntrack_expect_pernet_fini(net);
 err_expect:
-	nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
-err_hash:
 	kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 err_cache:
 	kfree(net->ct.slabname);

net/netfilter/nf_conntrack_helper.c

@@ -424,10 +424,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me,
 		spin_unlock_bh(&pcpu->lock);
 	}
 	local_bh_disable();
-	for (i = 0; i < net->ct.htable_size; i++) {
+	for (i = 0; i < nf_conntrack_htable_size; i++) {
 		nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
-		if (i < net->ct.htable_size) {
-			hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+		if (i < nf_conntrack_htable_size) {
+			hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
 				unhelp(h, me);
 		}
 		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);

net/netfilter/nf_conntrack_netlink.c

@@ -824,16 +824,16 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	last = (struct nf_conn *)cb->args[1];
 
 	local_bh_disable();
-	for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
+	for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
 restart:
 		lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS];
 		nf_conntrack_lock(lockp);
-		if (cb->args[0] >= net->ct.htable_size) {
+		if (cb->args[0] >= nf_conntrack_htable_size) {
 			spin_unlock(lockp);
 			goto out;
 		}
-		hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
-					 hnnode) {
+		hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]],
+					   hnnode) {
 			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
 				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);

net/netfilter/nf_conntrack_standalone.c

@@ -54,14 +54,13 @@ struct ct_iter_state {
 
 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_nulls_node *n;
 
 	for (st->bucket = 0;
-	     st->bucket < net->ct.htable_size;
+	     st->bucket < nf_conntrack_htable_size;
 	     st->bucket++) {
-		n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket]));
+		n = rcu_dereference(hlist_nulls_first_rcu(&nf_conntrack_hash[st->bucket]));
 		if (!is_a_nulls(n))
 			return n;
 	}
@@ -71,18 +70,17 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
 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(hlist_nulls_next_rcu(head));
 	while (is_a_nulls(head)) {
 		if (likely(get_nulls_value(head) == st->bucket)) {
-			if (++st->bucket >= net->ct.htable_size)
+			if (++st->bucket >= nf_conntrack_htable_size)
 				return NULL;
 		}
 		head = rcu_dereference(
 				hlist_nulls_first_rcu(
-					&net->ct.hash[st->bucket]));
+					&nf_conntrack_hash[st->bucket]));
 	}
 	return head;
 }
@@ -458,7 +456,7 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 	},
 	{
 		.procname       = "nf_conntrack_buckets",
-		.data           = &init_net.ct.htable_size,
+		.data           = &nf_conntrack_htable_size,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0444,
 		.proc_handler   = proc_dointvec,
@@ -512,7 +510,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 		goto out_kmemdup;
 
 	table[1].data = &net->ct.count;
-	table[2].data = &net->ct.htable_size;
 	table[3].data = &net->ct.sysctl_checksum;
 	table[4].data = &net->ct.sysctl_log_invalid;
 

net/netfilter/nf_nat_core.c

@@ -824,7 +824,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
 static int __net_init nf_nat_net_init(struct net *net)
 {
 	/* Leave them the same for the moment. */
-	net->ct.nat_htable_size = net->ct.htable_size;
+	net->ct.nat_htable_size = nf_conntrack_htable_size;
 	net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0);
 	if (!net->ct.nat_bysource)
 		return -ENOMEM;

net/netfilter/nfnetlink_cttimeout.c

@@ -306,10 +306,10 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout)
 	int i;
 
 	local_bh_disable();
-	for (i = 0; i < net->ct.htable_size; i++) {
+	for (i = 0; i < nf_conntrack_htable_size; i++) {
 		nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);
-		if (i < net->ct.htable_size) {
-			hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode)
+		if (i < nf_conntrack_htable_size) {
+			hlist_nulls_for_each_entry(h, nn, &nf_conntrack_hash[i], hnnode)
 				untimeout(h, timeout);
 		}
 		spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]);