9 files changed, 105 insertions, 20 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index ad751fe..6d77cce 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -499,7 +499,7 @@ config NFT_LIMIT
 config NFT_NAT
 	depends on NF_TABLES
 	depends on NF_CONNTRACK
-	depends on NF_NAT
+	select NF_NAT
 	tristate "Netfilter nf_tables nat module"
 	help
 	  This option adds the "nat" expression that you can use to perform
@@ -747,7 +747,9 @@ config NETFILTER_XT_TARGET_LED
 
 config NETFILTER_XT_TARGET_LOG
 	tristate "LOG target support"
-	depends on NF_LOG_IPV4 && NF_LOG_IPV6
+	select NF_LOG_COMMON
+	select NF_LOG_IPV4
+	select NF_LOG_IPV6 if IPV6
 	default m if NETFILTER_ADVANCED=n
 	help
 	  This option adds a `LOG' target, which allows you to create rules in
@@ -764,6 +766,14 @@ config NETFILTER_XT_TARGET_MARK
 	(e.g. when running oldconfig). It selects
 	CONFIG_NETFILTER_XT_MARK (combined mark/MARK module).
 
+config NETFILTER_XT_NAT
+	tristate '"SNAT and DNAT" targets support'
+	depends on NF_NAT
+	---help---
+	This option enables the SNAT and DNAT targets.
+
+	To compile it as a module, choose M here. If unsure, say N.
+
 config NETFILTER_XT_TARGET_NETMAP
 	tristate '"NETMAP" target support'
 	depends on NF_NAT
@@ -837,6 +847,7 @@ config NETFILTER_XT_TARGET_TPROXY
 	tristate '"TPROXY" target transparent proxying support'
 	depends on NETFILTER_XTABLES
 	depends on NETFILTER_ADVANCED
+	depends on (IPV6 || IPV6=n)
 	depends on IP_NF_MANGLE
 	select NF_DEFRAG_IPV4
 	select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 8308624..fad5fdb 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -95,7 +95,7 @@ obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
 obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
 obj-$(CONFIG_NETFILTER_XT_SET) += xt_set.o
-obj-$(CONFIG_NF_NAT) += xt_nat.o
+obj-$(CONFIG_NETFILTER_XT_NAT) += xt_nat.o
 
 # targets
 obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a93c97f..024a2e2 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
 struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
 EXPORT_SYMBOL(nf_hooks);
 
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 EXPORT_SYMBOL(nf_hooks_needed);
 #endif
@@ -72,7 +72,7 @@ int nf_register_hook(struct nf_hook_ops *reg)
 	}
 	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 	static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	return 0;
@@ -84,7 +84,7 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	mutex_lock(&nf_hook_mutex);
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
-#if defined(CONFIG_JUMP_LABEL)
+#ifdef HAVE_JUMP_LABEL
 	static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
 #endif
 	synchronize_net();
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e683675..5c34e8d 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1906,7 +1906,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
 	{
 		.hook		= ip_vs_local_reply6,
 		.owner		= THIS_MODULE,
-		.pf		= NFPROTO_IPV4,
+		.pf		= NFPROTO_IPV6,
 		.hooknum	= NF_INET_LOCAL_OUT,
 		.priority	= NF_IP6_PRI_NAT_DST + 1,
 	},
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 6f70bdd..56896a41 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -38,6 +38,7 @@
 #include <net/route.h>                  /* for ip_route_output */
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
+#include <net/ip_tunnels.h>
 #include <net/addrconf.h>
 #include <linux/icmpv6.h>
 #include <linux/netfilter.h>
@@ -862,11 +863,15 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		old_iph = ip_hdr(skb);
 	}
 
-	skb->transport_header = skb->network_header;
-
 	/* fix old IP header checksum */
 	ip_send_check(old_iph);
 
+	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_IPIP);
+	if (IS_ERR(skb))
+		goto tx_error;
+
+	skb->transport_header = skb->network_header;
+
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -900,7 +905,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	return NF_STOLEN;
 
   tx_error:
-	kfree_skb(skb);
+	if (!IS_ERR(skb))
+		kfree_skb(skb);
 	rcu_read_unlock();
 	LeaveFunction(10);
 	return NF_STOLEN;
@@ -953,6 +959,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		old_iph = ipv6_hdr(skb);
 	}
 
+	/* GSO: we need to provide proper SKB_GSO_ value for IPv6 */
+	skb = iptunnel_handle_offloads(skb, false, 0); /* SKB_GSO_SIT/IPV6 */
+	if (IS_ERR(skb))
+		goto tx_error;
+
 	skb->transport_header = skb->network_header;
 
 	skb_push(skb, sizeof(struct ipv6hdr));
@@ -988,7 +999,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	return NF_STOLEN;
 
 tx_error:
-	kfree_skb(skb);
+	if (!IS_ERR(skb))
+		kfree_skb(skb);
 	rcu_read_unlock();
 	LeaveFunction(10);
 	return NF_STOLEN;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index c138b8f..f37f071 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -222,6 +222,51 @@ replay:
 	}
 }
 
+struct nfnl_err {
+	struct list_head	head;
+	struct nlmsghdr		*nlh;
+	int			err;
+};
+
+static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err)
+{
+	struct nfnl_err *nfnl_err;
+
+	nfnl_err = kmalloc(sizeof(struct nfnl_err), GFP_KERNEL);
+	if (nfnl_err == NULL)
+		return -ENOMEM;
+
+	nfnl_err->nlh = nlh;
+	nfnl_err->err = err;
+	list_add_tail(&nfnl_err->head, list);
+
+	return 0;
+}
+
+static void nfnl_err_del(struct nfnl_err *nfnl_err)
+{
+	list_del(&nfnl_err->head);
+	kfree(nfnl_err);
+}
+
+static void nfnl_err_reset(struct list_head *err_list)
+{
+	struct nfnl_err *nfnl_err, *next;
+
+	list_for_each_entry_safe(nfnl_err, next, err_list, head)
+		nfnl_err_del(nfnl_err);
+}
+
+static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb)
+{
+	struct nfnl_err *nfnl_err, *next;
+
+	list_for_each_entry_safe(nfnl_err, next, err_list, head) {
+		netlink_ack(skb, nfnl_err->nlh, nfnl_err->err);
+		nfnl_err_del(nfnl_err);
+	}
+}
+
 static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 				u_int16_t subsys_id)
 {
@@ -230,6 +275,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 	const struct nfnetlink_subsystem *ss;
 	const struct nfnl_callback *nc;
 	bool success = true, done = false;
+	static LIST_HEAD(err_list);
 	int err;
 
 	if (subsys_id >= NFNL_SUBSYS_COUNT)
@@ -287,6 +333,7 @@ replay:
 		type = nlh->nlmsg_type;
 		if (type == NFNL_MSG_BATCH_BEGIN) {
 			/* Malformed: Batch begin twice */
+			nfnl_err_reset(&err_list);
 			success = false;
 			goto done;
 		} else if (type == NFNL_MSG_BATCH_END) {
@@ -333,6 +380,7 @@ replay:
 			 * original skb.
 			 */
 			if (err == -EAGAIN) {
+				nfnl_err_reset(&err_list);
 				ss->abort(skb);
 				nfnl_unlock(subsys_id);
 				kfree_skb(nskb);
@@ -341,11 +389,24 @@ replay:
 		}
 ack:
 		if (nlh->nlmsg_flags & NLM_F_ACK || err) {
+			/* Errors are delivered once the full batch has been
+			 * processed, this avoids that the same error is
+			 * reported several times when replaying the batch.
+			 */
+			if (nfnl_err_add(&err_list, nlh, err) < 0) {
+				/* We failed to enqueue an error, reset the
+				 * list of errors and send OOM to userspace
+				 * pointing to the batch header.
+				 */
+				nfnl_err_reset(&err_list);
+				netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM);
+				success = false;
+				goto done;
+			}
 			/* We don't stop processing the batch on errors, thus,
 			 * userspace gets all the errors that the batch
 			 * triggers.
 			 */
-			netlink_ack(skb, nlh, err);
 			if (err)
 				success = false;
 		}
@@ -361,6 +422,7 @@ done:
 	else
 		ss->abort(skb);
 
+	nfnl_err_deliver(&err_list, oskb);
 	nfnl_unlock(subsys_id);
 	kfree_skb(nskb);
 }
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 28fb8f3..8892b7b 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -180,15 +180,17 @@ static int nft_hash_init(const struct nft_set *set,
 static void nft_hash_destroy(const struct nft_set *set)
 {
 	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl;
+	const struct bucket_table *tbl = priv->tbl;
 	struct nft_hash_elem *he, *next;
 	unsigned int i;
 
-	tbl = rht_dereference(priv->tbl, priv);
-	for (i = 0; i < tbl->size; i++)
-		rht_for_each_entry_safe(he, next, tbl->buckets[i], priv, node)
+	for (i = 0; i < tbl->size; i++) {
+		for (he = rht_entry(tbl->buckets[i], struct nft_hash_elem, node);
+		     he != NULL; he = next) {
+			next = rht_entry(he->node.next, struct nft_hash_elem, node);
 			nft_hash_elem_destroy(set, he);
-
+		}
+	}
 	rhashtable_destroy(priv);
 }
 
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index e1836ff..46214f2 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -234,13 +234,11 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *node;
 
-	spin_lock_bh(&nft_rbtree_lock);
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_rbtree_elem_destroy(set, rbe);
 	}
-	spin_unlock_bh(&nft_rbtree_lock);
 }
 
 static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index f4e8330..7198d66 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -31,7 +31,7 @@ static int cgroup_mt_check(const struct xt_mtchk_param *par)
 	if (info->invert & ~1)
 		return -EINVAL;
 
-	return info->id ? 0 : -EINVAL;
+	return 0;
 }
 
 static bool