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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for net-next:

1) Rewrite inner header IPv6 in ICMPv6 messages in ip6t_NPT,
   from Michael Zhou.

2) do_ip_vs_set_ctl() dereferences uninitialized value,
   from Peilin Ye.

3) Support for userdata in tables, from Jose M. Guisado.

4) Do not increment ct error and invalid stats at the same time,
   from Florian Westphal.

5) Remove ct ignore stats, also from Florian.

6) Add ct stats for clash resolution, from Florian Westphal.

7) Bump reference counter bump on ct clash resolution only,
   this is safe because bucket lock is held, again from Florian.

8) Use ip_is_fragment() in xt_HMARK, from YueHaibing.

9) Add wildcard support for nft_socket, from Balazs Scheidler.

10) Remove superfluous IPVS dependency on iptables, from
    Yaroslav Bolyukin.

11) Remove unused definition in ebt_stp, from Wang Hai.

12) Replace CONFIG_NFT_CHAIN_NAT_{IPV4,IPV6} by CONFIG_NFT_NAT
    in selftests/net, from Fabian Frederick.

13) Add userdata support for nft_object, from Jose M. Guisado.
====================

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

8 files changed, 95 insertions, 33 deletions

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 2c1593089ede..eb0e329f9b8d 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -29,7 +29,6 @@ if IP_VS
 config	IP_VS_IPV6
 	bool "IPv6 support for IPVS"
 	depends on IPV6 = y || IP_VS = IPV6
-	select IP6_NF_IPTABLES
 	select NF_DEFRAG_IPV6
 	help
 	  Add IPv6 support to IPVS.
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 678c5b14841c..8dbfd84322a8 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2508,6 +2508,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
 		/* Set timeout values for (tcp tcpfin udp) */
 		ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg);
 		goto out_unlock;
+	} else if (!len) {
+		/* No more commands with len == 0 below */
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	usvc_compat = (struct ip_vs_service_user *)arg;
@@ -2584,9 +2588,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
 		break;
 	case IP_VS_SO_SET_DELDEST:
 		ret = ip_vs_del_dest(svc, &udest);
-		break;
-	default:
-		ret = -EINVAL;
 	}
 
   out_unlock:
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5b97d233f89b..234b7cab37c3 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -859,7 +859,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 
 out:
 	nf_conntrack_double_unlock(hash, reply_hash);
-	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
 	return -EEXIST;
 }
@@ -909,6 +908,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
 		tstamp->start = ktime_get_real_ns();
 }
 
+/* caller must hold locks to prevent concurrent changes */
 static int __nf_ct_resolve_clash(struct sk_buff *skb,
 				 struct nf_conntrack_tuple_hash *h)
 {
@@ -922,23 +922,21 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb,
 	if (nf_ct_is_dying(ct))
 		return NF_DROP;
 
-	if (!atomic_inc_not_zero(&ct->ct_general.use))
-		return NF_DROP;
-
 	if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
 	    nf_ct_match(ct, loser_ct)) {
 		struct net *net = nf_ct_net(ct);
 
+		nf_conntrack_get(&ct->ct_general);
+
 		nf_ct_acct_merge(ct, ctinfo, loser_ct);
 		nf_ct_add_to_dying_list(loser_ct);
 		nf_conntrack_put(&loser_ct->ct_general);
 		nf_ct_set(skb, ct, ctinfo);
 
-		NF_CT_STAT_INC(net, insert_failed);
+		NF_CT_STAT_INC(net, clash_resolve);
 		return NF_ACCEPT;
 	}
 
-	nf_ct_put(ct);
 	return NF_DROP;
 }
 
@@ -998,6 +996,8 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
 
 	hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
 				 &nf_conntrack_hash[repl_idx]);
+
+	NF_CT_STAT_INC(net, clash_resolve);
 	return NF_ACCEPT;
 }
 
@@ -1027,10 +1027,10 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
  *
  * Failing that, the new, unconfirmed conntrack is still added to the table
  * provided that the collision only occurs in the ORIGINAL direction.
- * The new entry will be added after the existing one in the hash list,
+ * The new entry will be added only in the non-clashing REPLY direction,
  * so packets in the ORIGINAL direction will continue to match the existing
  * entry.  The new entry will also have a fixed timeout so it expires --
- * due to the collision, it will not see bidirectional traffic.
+ * due to the collision, it will only see reply traffic.
  *
  * Returns NF_DROP if the clash could not be resolved.
  */
@@ -1725,10 +1725,8 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl,
 	else
 		return NF_ACCEPT;
 
-	if (ret <= 0) {
+	if (ret <= 0)
 		NF_CT_STAT_INC_ATOMIC(state->net, error);
-		NF_CT_STAT_INC_ATOMIC(state->net, invalid);
-	}
 
 	return ret;
 }
@@ -1802,10 +1800,8 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
 	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
 		if ((tmpl && !nf_ct_is_template(tmpl)) ||
-		     ctinfo == IP_CT_UNTRACKED) {
-			NF_CT_STAT_INC_ATOMIC(state->net, ignore);
+		     ctinfo == IP_CT_UNTRACKED)
 			return NF_ACCEPT;
-		}
 		skb->_nfct = 0;
 	}
 
@@ -1813,7 +1809,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
 	dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum);
 	if (dataoff <= 0) {
 		pr_debug("not prepared to track yet or error occurred\n");
-		NF_CT_STAT_INC_ATOMIC(state->net, error);
 		NF_CT_STAT_INC_ATOMIC(state->net, invalid);
 		ret = NF_ACCEPT;
 		goto out;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 832eabecfbdd..89d99f6dfd0a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2509,7 +2509,6 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 
 	if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) ||
 	    nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) ||
-	    nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT_FAILED,
 				htonl(st->insert_failed)) ||
@@ -2517,7 +2516,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	    nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) ||
 	    nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) ||
 	    nla_put_be32(skb, CTA_STATS_SEARCH_RESTART,
-				htonl(st->search_restart)))
+				htonl(st->search_restart)) ||
+	    nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE,
+				htonl(st->clash_resolve)))
 		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index a604f43e3e6b..0ff39740797d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -435,11 +435,11 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "%08x  %08x %08x %08x %08x %08x %08x %08x "
 			"%08x %08x %08x %08x %08x  %08x %08x %08x %08x\n",
 		   nr_conntracks,
-		   0,
+		   st->clash_resolve, /* was: searched */
 		   st->found,
 		   0,
 		   st->invalid,
-		   st->ignore,
+		   0,
 		   0,
 		   0,
 		   st->insert,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b7dc1cbf40ea..84c0c1aaae99 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -650,6 +650,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 	[NFTA_TABLE_HANDLE]	= { .type = NLA_U64 },
+	[NFTA_TABLE_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN }
 };
 
 static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
@@ -676,6 +678,11 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 			 NFTA_TABLE_PAD))
 		goto nla_put_failure;
 
+	if (table->udata) {
+		if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata))
+			goto nla_put_failure;
+	}
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -977,8 +984,9 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	int family = nfmsg->nfgen_family;
 	const struct nlattr *attr;
 	struct nft_table *table;
-	u32 flags = 0;
 	struct nft_ctx ctx;
+	u32 flags = 0;
+	u16 udlen = 0;
 	int err;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
@@ -1014,6 +1022,16 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	if (table->name == NULL)
 		goto err_strdup;
 
+	if (nla[NFTA_TABLE_USERDATA]) {
+		udlen = nla_len(nla[NFTA_TABLE_USERDATA]);
+		table->udata = kzalloc(udlen, GFP_KERNEL);
+		if (table->udata == NULL)
+			goto err_table_udata;
+
+		nla_memcpy(table->udata, nla[NFTA_TABLE_USERDATA], udlen);
+		table->udlen = udlen;
+	}
+
 	err = rhltable_init(&table->chains_ht, &nft_chain_ht_params);
 	if (err)
 		goto err_chain_ht;
@@ -1036,6 +1054,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 err_trans:
 	rhltable_destroy(&table->chains_ht);
 err_chain_ht:
+	kfree(table->udata);
+err_table_udata:
 	kfree(table->name);
 err_strdup:
 	kfree(table);
@@ -5730,6 +5750,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
 	[NFTA_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 	[NFTA_OBJ_HANDLE]	= { .type = NLA_U64},
+	[NFTA_OBJ_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
@@ -5877,6 +5899,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	struct nft_object *obj;
 	struct nft_ctx ctx;
 	u32 objtype;
+	u16 udlen;
 	int err;
 
 	if (!nla[NFTA_OBJ_TYPE] ||
@@ -5921,7 +5944,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
-		goto err1;
+		goto err_init;
 	}
 	obj->key.table = table;
 	obj->handle = nf_tables_alloc_handle(table);
@@ -5929,32 +5952,44 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL);
 	if (!obj->key.name) {
 		err = -ENOMEM;
-		goto err2;
+		goto err_strdup;
+	}
+
+	if (nla[NFTA_OBJ_USERDATA]) {
+		udlen = nla_len(nla[NFTA_OBJ_USERDATA]);
+		obj->udata = kzalloc(udlen, GFP_KERNEL);
+		if (obj->udata == NULL)
+			goto err_userdata;
+
+		nla_memcpy(obj->udata, nla[NFTA_OBJ_USERDATA], udlen);
+		obj->udlen = udlen;
 	}
 
 	err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj);
 	if (err < 0)
-		goto err3;
+		goto err_trans;
 
 	err = rhltable_insert(&nft_objname_ht, &obj->rhlhead,
 			      nft_objname_ht_params);
 	if (err < 0)
-		goto err4;
+		goto err_obj_ht;
 
 	list_add_tail_rcu(&obj->list, &table->objects);
 	table->use++;
 	return 0;
-err4:
+err_obj_ht:
 	/* queued in transaction log */
 	INIT_LIST_HEAD(&obj->list);
 	return err;
-err3:
+err_trans:
 	kfree(obj->key.name);
-err2:
+err_userdata:
+	kfree(obj->udata);
+err_strdup:
 	if (obj->ops->destroy)
 		obj->ops->destroy(&ctx, obj);
 	kfree(obj);
-err1:
+err_init:
 	module_put(type->owner);
 	return err;
 }
@@ -5986,6 +6021,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 			 NFTA_OBJ_PAD))
 		goto nla_put_failure;
 
+	if (obj->udata &&
+	    nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 637ce3e8c575..a28aca5124ce 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -14,6 +14,25 @@ struct nft_socket {
 	};
 };
 
+static void nft_socket_wildcard(const struct nft_pktinfo *pkt,
+				struct nft_regs *regs, struct sock *sk,
+				u32 *dest)
+{
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0);
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr));
+		break;
+#endif
+	default:
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+}
+
 static void nft_socket_eval(const struct nft_expr *expr,
 			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
@@ -59,6 +78,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			return;
 		}
 		break;
+	case NFT_SOCKET_WILDCARD:
+		if (!sk_fullsock(sk)) {
+			regs->verdict.code = NFT_BREAK;
+			return;
+		}
+		nft_socket_wildcard(pkt, regs, sk, dest);
+		break;
 	default:
 		WARN_ON(1);
 		regs->verdict.code = NFT_BREAK;
@@ -97,6 +123,7 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY]));
 	switch(priv->key) {
 	case NFT_SOCKET_TRANSPARENT:
+	case NFT_SOCKET_WILDCARD:
 		len = sizeof(u8);
 		break;
 	case NFT_SOCKET_MARK:
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 713fb38541df..8928ec56c388 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -276,7 +276,7 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t,
 		return 0;
 
 	/* follow-up fragments don't contain ports, skip all fragments */
-	if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+	if (ip_is_fragment(ip))
 		return 0;
 
 	hmark_set_tuple_ports(skb, (ip->ihl * 4) + nhoff, t, info);