Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter/IPVS fixes for net

The following patchset contains Netfilter/IPVS fixes for your net tree,
they are:

1) Fix packet drops due to incorrect ECN handling in IPVS, from Vadim
   Fedorenko.

2) Fix splat with mark restoration in xt_socket with non-full-sock,
   patch from Subash Abhinov Kasiviswanathan.

3) ipset bogusly bails out when adding IPv4 range containing more than
   2^31 addresses, from Jozsef Kadlecsik.

4) Incorrect pernet unregistration order in ipset, from Florian Westphal.

5) Races between dump and swap in ipset results in BUG_ON splats, from
   Ross Lagerwall.

6) Fix chain renames in nf_tables, from JingPiao Chen.

7) Fix race in pernet codepath with ebtables table registration, from
   Artem Savkov.

8) Memory leak in error path in set name allocation in nf_tables, patch
   from Arvind Yadav.

9) Don't dump chain counters if they are not available, this fixes a
   crash when listing the ruleset.

10) Fix out of bound memory read in strlcpy() in x_tables compat code,
    from Eric Dumazet.

11) Make sure we only process TCP packets in SYNPROXY hooks, patch from
    Lin Zhang.

12) Cannot load rules incrementally anymore after xt_bpf with pinned
    objects, added in revision 1. From Shmulik Ladkani.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf.h

@@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
 {
 }
 
+static inline int bpf_obj_get_user(const char __user *pathname)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline struct net_device  *__dev_map_lookup_elem(struct bpf_map *map,
 						       u32 key)
 {

include/linux/netfilter_bridge/ebtables.h

@@ -108,9 +108,10 @@ struct ebt_table {
 
 #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \
 		     ~(__alignof__(struct _xt_align)-1))
-extern struct ebt_table *ebt_register_table(struct net *net,
-					    const struct ebt_table *table,
-					    const struct nf_hook_ops *);
+extern int ebt_register_table(struct net *net,
+			      const struct ebt_table *table,
+			      const struct nf_hook_ops *ops,
+			      struct ebt_table **res);
 extern void ebt_unregister_table(struct net *net, struct ebt_table *table,
 				 const struct nf_hook_ops *);
 extern unsigned int ebt_do_table(struct sk_buff *skb,

include/uapi/linux/netfilter/xt_bpf.h

@@ -23,6 +23,7 @@ enum xt_bpf_modes {
 	XT_BPF_MODE_FD_PINNED,
 	XT_BPF_MODE_FD_ELF,
 };
+#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED
 
 struct xt_bpf_info_v1 {
 	__u16 mode;

kernel/bpf/inode.c

@@ -363,6 +363,7 @@ int bpf_obj_get_user(const char __user *pathname)
 	putname(pname);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(bpf_obj_get_user);
 
 static void bpf_evict_inode(struct inode *inode)
 {

net/bridge/netfilter/ebtable_broute.c

@@ -65,8 +65,8 @@ static int ebt_broute(struct sk_buff *skb)
 
 static int __net_init broute_net_init(struct net *net)
 {
-	net->xt.broute_table = ebt_register_table(net, &broute_table, NULL);
-	return PTR_ERR_OR_ZERO(net->xt.broute_table);
+	return ebt_register_table(net, &broute_table, NULL,
+				  &net->xt.broute_table);
 }
 
 static void __net_exit broute_net_exit(struct net *net)

net/bridge/netfilter/ebtable_filter.c

@@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_filter[] = {
 
 static int __net_init frame_filter_net_init(struct net *net)
 {
-	net->xt.frame_filter = ebt_register_table(net, &frame_filter, ebt_ops_filter);
-	return PTR_ERR_OR_ZERO(net->xt.frame_filter);
+	return ebt_register_table(net, &frame_filter, ebt_ops_filter,
+				  &net->xt.frame_filter);
 }
 
 static void __net_exit frame_filter_net_exit(struct net *net)

net/bridge/netfilter/ebtable_nat.c

@@ -93,8 +93,8 @@ static const struct nf_hook_ops ebt_ops_nat[] = {
 
 static int __net_init frame_nat_net_init(struct net *net)
 {
-	net->xt.frame_nat = ebt_register_table(net, &frame_nat, ebt_ops_nat);
-	return PTR_ERR_OR_ZERO(net->xt.frame_nat);
+	return ebt_register_table(net, &frame_nat, ebt_ops_nat,
+				  &net->xt.frame_nat);
 }
 
 static void __net_exit frame_nat_net_exit(struct net *net)

net/bridge/netfilter/ebtables.c

@@ -1169,9 +1169,8 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table)
 	kfree(table);
 }
 
-struct ebt_table *
-ebt_register_table(struct net *net, const struct ebt_table *input_table,
-		   const struct nf_hook_ops *ops)
+int ebt_register_table(struct net *net, const struct ebt_table *input_table,
+		       const struct nf_hook_ops *ops, struct ebt_table **res)
 {
 	struct ebt_table_info *newinfo;
 	struct ebt_table *t, *table;
@@ -1183,7 +1182,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	    repl->entries == NULL || repl->entries_size == 0 ||
 	    repl->counters != NULL || input_table->private != NULL) {
 		BUGPRINT("Bad table data for ebt_register_table!!!\n");
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
 	/* Don't add one table to multiple lists. */
@@ -1252,16 +1251,18 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	list_add(&table->list, &net->xt.tables[NFPROTO_BRIDGE]);
 	mutex_unlock(&ebt_mutex);
 
+	WRITE_ONCE(*res, table);
+
 	if (!ops)
-		return table;
+		return 0;
 
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret) {
 		__ebt_unregister_table(net, table);
-		return ERR_PTR(ret);
+		*res = NULL;
 	}
 
-	return table;
+	return ret;
 free_unlock:
 	mutex_unlock(&ebt_mutex);
 free_chainstack:
@@ -1276,7 +1277,7 @@ ebt_register_table(struct net *net, const struct ebt_table *input_table,
 free_table:
 	kfree(table);
 out:
-	return ERR_PTR(ret);
+	return ret;
 }
 
 void ebt_unregister_table(struct net *net, struct ebt_table *table,

net/ipv4/netfilter/ipt_SYNPROXY.c

@@ -330,7 +330,8 @@ static unsigned int ipv4_synproxy_hook(void *priv,
 	if (synproxy == NULL)
 		return NF_ACCEPT;
 
-	if (nf_is_loopback_packet(skb))
+	if (nf_is_loopback_packet(skb) ||
+	    ip_hdr(skb)->protocol != IPPROTO_TCP)
 		return NF_ACCEPT;
 
 	thoff = ip_hdrlen(skb);

net/ipv6/netfilter/ip6t_SYNPROXY.c

@@ -353,7 +353,7 @@ static unsigned int ipv6_synproxy_hook(void *priv,
 	nexthdr = ipv6_hdr(skb)->nexthdr;
 	thoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
 				 &frag_off);
-	if (thoff < 0)
+	if (thoff < 0 || nexthdr != IPPROTO_TCP)
 		return NF_ACCEPT;
 
 	th = skb_header_pointer(skb, thoff, sizeof(_th), &_th);

net/netfilter/ipset/ip_set_core.c

@@ -1191,14 +1191,17 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	      from->family == to->family))
 		return -IPSET_ERR_TYPE_MISMATCH;
 
-	if (from->ref_netlink || to->ref_netlink)
+	write_lock_bh(&ip_set_ref_lock);
+
+	if (from->ref_netlink || to->ref_netlink) {
+		write_unlock_bh(&ip_set_ref_lock);
 		return -EBUSY;
+	}
 
 	strncpy(from_name, from->name, IPSET_MAXNAMELEN);
 	strncpy(from->name, to->name, IPSET_MAXNAMELEN);
 	strncpy(to->name, from_name, IPSET_MAXNAMELEN);
 
-	write_lock_bh(&ip_set_ref_lock);
 	swap(from->ref, to->ref);
 	ip_set(inst, from_id) = to;
 	ip_set(inst, to_id) = from;
@@ -2072,35 +2075,39 @@ static struct pernet_operations ip_set_net_ops = {
 static int __init
 ip_set_init(void)
 {
-	int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+	int ret = register_pernet_subsys(&ip_set_net_ops);
+
+	if (ret) {
+		pr_err("ip_set: cannot register pernet_subsys.\n");
+		return ret;
+	}
 
+	ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
 	if (ret != 0) {
 		pr_err("ip_set: cannot register with nfnetlink.\n");
+		unregister_pernet_subsys(&ip_set_net_ops);
 		return ret;
 	}
+
 	ret = nf_register_sockopt(&so_set);
 	if (ret != 0) {
 		pr_err("SO_SET registry failed: %d\n", ret);
 		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+		unregister_pernet_subsys(&ip_set_net_ops);
 		return ret;
 	}
-	ret = register_pernet_subsys(&ip_set_net_ops);
-	if (ret) {
-		pr_err("ip_set: cannot register pernet_subsys.\n");
-		nf_unregister_sockopt(&so_set);
-		nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-		return ret;
-	}
+
 	pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
 	return 0;
 }
 
 static void __exit
 ip_set_fini(void)
 {
-	unregister_pernet_subsys(&ip_set_net_ops);
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+
+	unregister_pernet_subsys(&ip_set_net_ops);
 	pr_debug("these are the famous last words\n");
 }
 

net/netfilter/ipset/ip_set_hash_ip.c

@@ -123,13 +123,12 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
 		return ret;
 
 	ip &= ip_set_hostmask(h->netmask);
+	e.ip = htonl(ip);
+	if (e.ip == 0)
+		return -IPSET_ERR_HASH_ELEM;
 
-	if (adt == IPSET_TEST) {
-		e.ip = htonl(ip);
-		if (e.ip == 0)
-			return -IPSET_ERR_HASH_ELEM;
+	if (adt == IPSET_TEST)
 		return adtfn(set, &e, &ext, &ext, flags);
-	}
 
 	ip_to = ip;
 	if (tb[IPSET_ATTR_IP_TO]) {
@@ -148,17 +147,20 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
 
-	if (retried)
+	if (retried) {
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip += hosts) {
 		e.ip = htonl(ip);
-		if (e.ip == 0)
-			return -IPSET_ERR_HASH_ELEM;
+	}
+	for (; ip <= ip_to;) {
 		ret = adtfn(set, &e, &ext, &ext, flags);
-
 		if (ret && !ip_set_eexist(ret, flags))
 			return ret;
 
+		ip += hosts;
+		e.ip = htonl(ip);
+		if (e.ip == 0)
+			return 0;
+
 		ret = 0;
 	}
 	return ret;

net/netfilter/ipset/ip_set_hash_ipmark.c

@@ -149,7 +149,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		e.ip = htonl(ip);
 		ret = adtfn(set, &e, &ext, &ext, flags);
 

net/netfilter/ipset/ip_set_hash_ipport.c

@@ -178,7 +178,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
 		for (; p <= port_to; p++) {

net/netfilter/ipset/ip_set_hash_ipportip.c

@@ -185,7 +185,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
 		for (; p <= port_to; p++) {

net/netfilter/ipset/ip_set_hash_ipportnet.c

@@ -271,7 +271,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; !before(ip_to, ip); ip++) {
+	for (; ip <= ip_to; ip++) {
 		e.ip = htonl(ip);
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
@@ -281,7 +281,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 			      ip == ntohl(h->next.ip) &&
 			      p == ntohs(h->next.port)
 				? ntohl(h->next.ip2) : ip2_from;
-			while (!after(ip2, ip2_to)) {
+			while (ip2 <= ip2_to) {
 				e.ip2 = htonl(ip2);
 				ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
 								&cidr);

net/netfilter/ipset/ip_set_hash_net.c

@@ -193,7 +193,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
 	}
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);

net/netfilter/ipset/ip_set_hash_netiface.c

@@ -255,7 +255,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);

net/netfilter/ipset/ip_set_hash_netnet.c

@@ -250,13 +250,13 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (retried)
 		ip = ntohl(h->next.ip[0]);
 
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip[0] = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		ip2 = (retried &&
 		       ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1])
 						   : ip2_from;
-		while (!after(ip2, ip2_to)) {
+		while (ip2 <= ip2_to) {
 			e.ip[1] = htonl(ip2);
 			last2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
 			ret = adtfn(set, &e, &ext, &ext, flags);

net/netfilter/ipset/ip_set_hash_netport.c

@@ -241,7 +241,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (retried)
 		ip = ntohl(h->next.ip);
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip = htonl(ip);
 		last = ip_set_range_to_cidr(ip, ip_to, &cidr);
 		e.cidr = cidr - 1;

net/netfilter/ipset/ip_set_hash_netportnet.c

@@ -291,7 +291,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (retried)
 		ip = ntohl(h->next.ip[0]);
 
-	while (!after(ip, ip_to)) {
+	while (ip <= ip_to) {
 		e.ip[0] = htonl(ip);
 		ip_last = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port)
@@ -301,7 +301,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 			ip2 = (retried && ip == ntohl(h->next.ip[0]) &&
 			       p == ntohs(h->next.port)) ? ntohl(h->next.ip[1])
 							 : ip2_from;
-			while (!after(ip2, ip2_to)) {
+			while (ip2 <= ip2_to) {
 				e.ip[1] = htonl(ip2);
 				ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
 								&e.cidr[1]);

net/netfilter/ipvs/ip_vs_xmit.c

@@ -921,6 +921,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 {
 	struct sk_buff *new_skb = NULL;
 	struct iphdr *old_iph = NULL;
+	__u8 old_dsfield;
 #ifdef CONFIG_IP_VS_IPV6
 	struct ipv6hdr *old_ipv6h = NULL;
 #endif
@@ -945,7 +946,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 			*payload_len =
 				ntohs(old_ipv6h->payload_len) +
 				sizeof(*old_ipv6h);
-		*dsfield = ipv6_get_dsfield(old_ipv6h);
+		old_dsfield = ipv6_get_dsfield(old_ipv6h);
 		*ttl = old_ipv6h->hop_limit;
 		if (df)
 			*df = 0;
@@ -960,12 +961,15 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 
 		/* fix old IP header checksum */
 		ip_send_check(old_iph);
-		*dsfield = ipv4_get_dsfield(old_iph);
+		old_dsfield = ipv4_get_dsfield(old_iph);
 		*ttl = old_iph->ttl;
 		if (payload_len)
 			*payload_len = ntohs(old_iph->tot_len);
 	}
 
+	/* Implement full-functionality option for ECN encapsulation */
+	*dsfield = INET_ECN_encapsulate(old_dsfield, old_dsfield);
+
 	return skb;
 error:
 	kfree_skb(skb);