6 files changed, 61 insertions, 59 deletions

diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 1ac01b1..16c0ba0 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -758,7 +758,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	 * about).
 	 */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc_node(countersize, numa_node_id());
+	counters = vmalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1005,8 +1005,7 @@ static int __do_replace(struct net *net, const char *name,
 	struct arpt_entry *iter;
 
 	ret = 0;
-	counters = vmalloc_node(num_counters * sizeof(struct xt_counters),
-				numa_node_id());
+	counters = vmalloc(num_counters * sizeof(struct xt_counters));
 	if (!counters) {
 		ret = -ENOMEM;
 		goto out;
@@ -1159,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user,
 	if (len != size + num_counters * sizeof(struct xt_counters))
 		return -EINVAL;
 
-	paddc = vmalloc_node(len - size, numa_node_id());
+	paddc = vmalloc(len - size);
 	if (!paddc)
 		return -ENOMEM;
 
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index a4e5fc5..d2c1311 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -42,7 +42,7 @@ typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long);
 
 static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
 static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
-static DEFINE_RWLOCK(queue_lock);
+static DEFINE_SPINLOCK(queue_lock);
 static int peer_pid __read_mostly;
 static unsigned int copy_range __read_mostly;
 static unsigned int queue_total;
@@ -72,10 +72,10 @@ __ipq_set_mode(unsigned char mode, unsigned int range)
 		break;
 
 	case IPQ_COPY_PACKET:
-		copy_mode = mode;
+		if (range > 0xFFFF)
+			range = 0xFFFF;
 		copy_range = range;
-		if (copy_range > 0xFFFF)
-			copy_range = 0xFFFF;
+		copy_mode = mode;
 		break;
 
 	default:
@@ -101,7 +101,7 @@ ipq_find_dequeue_entry(unsigned long id)
 {
 	struct nf_queue_entry *entry = NULL, *i;
 
-	write_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 
 	list_for_each_entry(i, &queue_list, list) {
 		if ((unsigned long)i == id) {
@@ -115,7 +115,7 @@ ipq_find_dequeue_entry(unsigned long id)
 		queue_total--;
 	}
 
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 	return entry;
 }
 
@@ -136,9 +136,9 @@ __ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 static void
 ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
 {
-	write_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 	__ipq_flush(cmpfn, data);
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 }
 
 static struct sk_buff *
@@ -152,9 +152,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
 	struct nlmsghdr *nlh;
 	struct timeval tv;
 
-	read_lock_bh(&queue_lock);
-
-	switch (copy_mode) {
+	switch (ACCESS_ONCE(copy_mode)) {
 	case IPQ_COPY_META:
 	case IPQ_COPY_NONE:
 		size = NLMSG_SPACE(sizeof(*pmsg));
@@ -162,26 +160,21 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
 
 	case IPQ_COPY_PACKET:
 		if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
-		    (*errp = skb_checksum_help(entry->skb))) {
-			read_unlock_bh(&queue_lock);
+		    (*errp = skb_checksum_help(entry->skb)))
 			return NULL;
-		}
-		if (copy_range == 0 || copy_range > entry->skb->len)
+
+		data_len = ACCESS_ONCE(copy_range);
+		if (data_len == 0 || data_len > entry->skb->len)
 			data_len = entry->skb->len;
-		else
-			data_len = copy_range;
 
 		size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
 		break;
 
 	default:
 		*errp = -EINVAL;
-		read_unlock_bh(&queue_lock);
 		return NULL;
 	}
 
-	read_unlock_bh(&queue_lock);
-
 	skb = alloc_skb(size, GFP_ATOMIC);
 	if (!skb)
 		goto nlmsg_failure;
@@ -242,7 +235,7 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 	if (nskb == NULL)
 		return status;
 
-	write_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 
 	if (!peer_pid)
 		goto err_out_free_nskb;
@@ -266,14 +259,14 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 
 	__ipq_enqueue_entry(entry);
 
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 	return status;
 
 err_out_free_nskb:
 	kfree_skb(nskb);
 
 err_out_unlock:
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 	return status;
 }
 
@@ -342,9 +335,9 @@ ipq_set_mode(unsigned char mode, unsigned int range)
 {
 	int status;
 
-	write_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 	status = __ipq_set_mode(mode, range);
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 	return status;
 }
 
@@ -440,11 +433,11 @@ __ipq_rcv_skb(struct sk_buff *skb)
 	if (security_netlink_recv(skb, CAP_NET_ADMIN))
 		RCV_SKB_FAIL(-EPERM);
 
-	write_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 
 	if (peer_pid) {
 		if (peer_pid != pid) {
-			write_unlock_bh(&queue_lock);
+			spin_unlock_bh(&queue_lock);
 			RCV_SKB_FAIL(-EBUSY);
 		}
 	} else {
@@ -452,7 +445,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
 		peer_pid = pid;
 	}
 
-	write_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 
 	status = ipq_receive_peer(NLMSG_DATA(nlh), type,
 				  nlmsglen - NLMSG_LENGTH(0));
@@ -497,10 +490,10 @@ ipq_rcv_nl_event(struct notifier_block *this,
 	struct netlink_notify *n = ptr;
 
 	if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) {
-		write_lock_bh(&queue_lock);
+		spin_lock_bh(&queue_lock);
 		if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid))
 			__ipq_reset();
-		write_unlock_bh(&queue_lock);
+		spin_unlock_bh(&queue_lock);
 	}
 	return NOTIFY_DONE;
 }
@@ -527,7 +520,7 @@ static ctl_table ipq_table[] = {
 #ifdef CONFIG_PROC_FS
 static int ip_queue_show(struct seq_file *m, void *v)
 {
-	read_lock_bh(&queue_lock);
+	spin_lock_bh(&queue_lock);
 
 	seq_printf(m,
 		      "Peer PID          : %d\n"
@@ -545,7 +538,7 @@ static int ip_queue_show(struct seq_file *m, void *v)
 		      queue_dropped,
 		      queue_user_dropped);
 
-	read_unlock_bh(&queue_lock);
+	spin_unlock_bh(&queue_lock);
 	return 0;
 }
 
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4b6c5ca..b38c118 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -928,7 +928,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 	   (other than comefrom, which userspace doesn't care
 	   about). */
 	countersize = sizeof(struct xt_counters) * private->number;
-	counters = vmalloc_node(countersize, numa_node_id());
+	counters = vmalloc(countersize);
 
 	if (counters == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1352,7 +1352,7 @@ do_add_counters(struct net *net, const void __user *user,
 	if (len != size + num_counters * sizeof(struct xt_counters))
 		return -EINVAL;
 
-	paddc = vmalloc_node(len - size, numa_node_id());
+	paddc = vmalloc(len - size);
 	if (!paddc)
 		return -ENOMEM;
 
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f91c94b..64d0875 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -53,12 +53,13 @@ struct clusterip_config {
 #endif
 	enum clusterip_hashmode hash_mode;	/* which hashing mode */
 	u_int32_t hash_initval;			/* hash initialization */
+	struct rcu_head rcu;
 };
 
 static LIST_HEAD(clusterip_configs);
 
 /* clusterip_lock protects the clusterip_configs list */
-static DEFINE_RWLOCK(clusterip_lock);
+static DEFINE_SPINLOCK(clusterip_lock);
 
 #ifdef CONFIG_PROC_FS
 static const struct file_operations clusterip_proc_fops;
@@ -71,11 +72,17 @@ clusterip_config_get(struct clusterip_config *c)
 	atomic_inc(&c->refcount);
 }
 
+
+static void clusterip_config_rcu_free(struct rcu_head *head)
+{
+	kfree(container_of(head, struct clusterip_config, rcu));
+}
+
 static inline void
 clusterip_config_put(struct clusterip_config *c)
 {
 	if (atomic_dec_and_test(&c->refcount))
-		kfree(c);
+		call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
 }
 
 /* decrease the count of entries using/referencing this config.  If last
@@ -84,10 +91,11 @@ clusterip_config_put(struct clusterip_config *c)
 static inline void
 clusterip_config_entry_put(struct clusterip_config *c)
 {
-	write_lock_bh(&clusterip_lock);
-	if (atomic_dec_and_test(&c->entries)) {
-		list_del(&c->list);
-		write_unlock_bh(&clusterip_lock);
+	local_bh_disable();
+	if (atomic_dec_and_lock(&c->entries, &clusterip_lock)) {
+		list_del_rcu(&c->list);
+		spin_unlock(&clusterip_lock);
+		local_bh_enable();
 
 		dev_mc_del(c->dev, c->clustermac);
 		dev_put(c->dev);
@@ -100,7 +108,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
 #endif
 		return;
 	}
-	write_unlock_bh(&clusterip_lock);
+	local_bh_enable();
 }
 
 static struct clusterip_config *
@@ -108,7 +116,7 @@ __clusterip_config_find(__be32 clusterip)
 {
 	struct clusterip_config *c;
 
-	list_for_each_entry(c, &clusterip_configs, list) {
+	list_for_each_entry_rcu(c, &clusterip_configs, list) {
 		if (c->clusterip == clusterip)
 			return c;
 	}
@@ -121,16 +129,15 @@ clusterip_config_find_get(__be32 clusterip, int entry)
 {
 	struct clusterip_config *c;
 
-	read_lock_bh(&clusterip_lock);
+	rcu_read_lock_bh();
 	c = __clusterip_config_find(clusterip);
-	if (!c) {
-		read_unlock_bh(&clusterip_lock);
-		return NULL;
+	if (c) {
+		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+			c = NULL;
+		else if (entry)
+			atomic_inc(&c->entries);
 	}
-	atomic_inc(&c->refcount);
-	if (entry)
-		atomic_inc(&c->entries);
-	read_unlock_bh(&clusterip_lock);
+	rcu_read_unlock_bh();
 
 	return c;
 }
@@ -181,9 +188,9 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
 	}
 #endif
 
-	write_lock_bh(&clusterip_lock);
-	list_add(&c->list, &clusterip_configs);
-	write_unlock_bh(&clusterip_lock);
+	spin_lock_bh(&clusterip_lock);
+	list_add_rcu(&c->list, &clusterip_configs);
+	spin_unlock_bh(&clusterip_lock);
 
 	return c;
 }
@@ -733,6 +740,9 @@ static void __exit clusterip_tg_exit(void)
 #endif
 	nf_unregister_hook(&cip_arp_ops);
 	xt_unregister_target(&clusterip_tg_reg);
+
+	/* Wait for completion of call_rcu_bh()'s (clusterip_config_rcu_free) */
+	rcu_barrier_bh();
 }
 
 module_init(clusterip_tg_init);
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 4f8bddb..c7719b2 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -742,7 +742,7 @@ static int __init nf_nat_init(void)
 	spin_unlock_bh(&nf_nat_lock);
 
 	/* Initialize fake conntrack so that NAT will skip it */
-	nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK;
+	nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);
 
 	l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);
 
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index beb2581..6723c68 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -98,7 +98,7 @@ nf_nat_fn(unsigned int hooknum,
 		return NF_ACCEPT;
 
 	/* Don't try to NAT if this packet is not conntracked */
-	if (ct == &nf_conntrack_untracked)
+	if (nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
 	nat = nfct_nat(ct);