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

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains Netfilter/IPVS updates for you net-next
tree:

1) Missing NFTA_RULE_POSITION_ID netlink attribute validation,
   from Phil Sutter.

2) Restrict matching on tunnel metadata to rx/tx path, from wenxu.

3) Avoid indirect calls for IPV6=y, from Florian Westphal.

4) Add two indirections to prepare merger of IPV4 and IPV6 nat
   modules, from Florian Westphal.

5) Broken indentation in ctnetlink, from Colin Ian King.

6) Patches to use struct_size() from netfilter and IPVS,
   from Gustavo A. R. Silva.

7) Display kernel splat only once in case of racing to confirm
   conntrack from bridge plus nfqueue setups, from Chieh-Min Wang.

8) Skip checksum validation for layer 4 protocols that don't need it,
   patch from Alin Nastac.

9) Sparse warning due to symbol that should be static in CLUSTERIP,
   from Wei Yongjun.

10) Add new toggle to disable SDP payload translation when media
    endpoint is reachable though the same interface as the signalling
    peer, from Alin Nastac.
====================

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

9 files changed, 97 insertions, 28 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 86afacb07e5f..3c36480559f9 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2744,8 +2744,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		int size;
 
 		get = (struct ip_vs_get_services *)arg;
-		size = sizeof(*get) +
-			sizeof(struct ip_vs_service_entry) * get->num_services;
+		size = struct_size(get, entrytable, get->num_services);
 		if (*len != size) {
 			pr_err("length: %u != %u\n", *len, size);
 			ret = -EINVAL;
@@ -2786,8 +2785,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 		int size;
 
 		get = (struct ip_vs_get_dests *)arg;
-		size = sizeof(*get) +
-			sizeof(struct ip_vs_dest_entry) * get->num_dests;
+		size = struct_size(get, entrytable, get->num_dests);
 		if (*len != size) {
 			pr_err("length: %u != %u\n", *len, size);
 			ret = -EINVAL;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 08ee03407ace..e139c256e269 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -936,10 +936,18 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 * REJECT will give spurious warnings here.
 	 */
 
-	/* No external references means no one else could have
-	 * confirmed us.
+	/* Another skb with the same unconfirmed conntrack may
+	 * win the race. This may happen for bridge(br_flood)
+	 * or broadcast/multicast packets do skb_clone with
+	 * unconfirmed conntrack.
 	 */
-	WARN_ON(nf_ct_is_confirmed(ct));
+	if (unlikely(nf_ct_is_confirmed(ct))) {
+		WARN_ON_ONCE(1);
+		nf_conntrack_double_unlock(hash, reply_hash);
+		local_bh_enable();
+		return NF_DROP;
+	}
+
 	pr_debug("Confirming conntrack %p\n", ct);
 	/* We have to check the DYING flag after unlink to prevent
 	 * a race against nf_ct_get_next_corpse() possibly called from
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 8071bb04a849..349b42a65c8a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2675,7 +2675,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 	ret = ctnetlink_dump_tuples_ip(skb, &m);
 	if (ret >= 0) {
 		l4proto = nf_ct_l4proto_find(tuple->dst.protonum);
-	ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto);
+		ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto);
 	}
 	rcu_read_unlock();
 
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index c8d2b6688a2a..f067c6b50857 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -21,6 +21,8 @@
 #include <linux/tcp.h>
 #include <linux/netfilter.h>
 
+#include <net/route.h>
+#include <net/ip6_route.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_expect.h>
@@ -54,6 +56,11 @@ module_param(sip_direct_media, int, 0600);
 MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling "
 				   "endpoints only (default 1)");
 
+static int sip_external_media __read_mostly = 0;
+module_param(sip_external_media, int, 0600);
+MODULE_PARM_DESC(sip_external_media, "Expect Media streams between external "
+				     "endpoints (default 0)");
+
 const struct nf_nat_sip_hooks *nf_nat_sip_hooks;
 EXPORT_SYMBOL_GPL(nf_nat_sip_hooks);
 
@@ -861,6 +868,41 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		if (!nf_inet_addr_cmp(daddr, &ct->tuplehash[dir].tuple.src.u3))
 			return NF_ACCEPT;
 		saddr = &ct->tuplehash[!dir].tuple.src.u3;
+	} else if (sip_external_media) {
+		struct net_device *dev = skb_dst(skb)->dev;
+		struct net *net = dev_net(dev);
+		struct rtable *rt;
+		struct flowi4 fl4 = {};
+#if IS_ENABLED(CONFIG_IPV6)
+		struct flowi6 fl6 = {};
+#endif
+		struct dst_entry *dst = NULL;
+
+		switch (nf_ct_l3num(ct)) {
+			case NFPROTO_IPV4:
+				fl4.daddr = daddr->ip;
+				rt = ip_route_output_key(net, &fl4);
+				if (!IS_ERR(rt))
+					dst = &rt->dst;
+				break;
+
+#if IS_ENABLED(CONFIG_IPV6)
+			case NFPROTO_IPV6:
+				fl6.daddr = daddr->in6;
+				dst = ip6_route_output(net, NULL, &fl6);
+				if (dst->error) {
+					dst_release(dst);
+					dst = NULL;
+				}
+				break;
+#endif
+		}
+
+		/* Don't predict any conntracks when media endpoint is reachable
+		 * through the same interface as the signalling peer.
+		 */
+		if (dst && dst->dev == dev)
+			return NF_ACCEPT;
 	}
 
 	/* We need to check whether the registration exists before attempting
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5ca5ec8f3cf0..de3f1e2acae0 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2238,6 +2238,7 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
 	[NFTA_RULE_USERDATA]	= { .type = NLA_BINARY,
 				    .len = NFT_USERDATA_MAXLEN },
 	[NFTA_RULE_ID]		= { .type = NLA_U32 },
+	[NFTA_RULE_POSITION_ID]	= { .type = NLA_U32 },
 };
 
 static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 3a15f219e4e7..ea28588c5eed 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -15,6 +15,7 @@
 struct nft_tunnel {
 	enum nft_tunnel_keys	key:8;
 	enum nft_registers	dreg:8;
+	enum nft_tunnel_mode	mode:8;
 };
 
 static void nft_tunnel_get_eval(const struct nft_expr *expr,
@@ -29,14 +30,32 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr,
 
 	switch (priv->key) {
 	case NFT_TUNNEL_PATH:
-		nft_reg_store8(dest, !!tun_info);
+		if (!tun_info) {
+			nft_reg_store8(dest, false);
+			return;
+		}
+		if (priv->mode == NFT_TUNNEL_MODE_NONE ||
+		    (priv->mode == NFT_TUNNEL_MODE_RX &&
+		     !(tun_info->mode & IP_TUNNEL_INFO_TX)) ||
+		    (priv->mode == NFT_TUNNEL_MODE_TX &&
+		     (tun_info->mode & IP_TUNNEL_INFO_TX)))
+			nft_reg_store8(dest, true);
+		else
+			nft_reg_store8(dest, false);
 		break;
 	case NFT_TUNNEL_ID:
 		if (!tun_info) {
 			regs->verdict.code = NFT_BREAK;
 			return;
 		}
-		*dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id));
+		if (priv->mode == NFT_TUNNEL_MODE_NONE ||
+		    (priv->mode == NFT_TUNNEL_MODE_RX &&
+		     !(tun_info->mode & IP_TUNNEL_INFO_TX)) ||
+		    (priv->mode == NFT_TUNNEL_MODE_TX &&
+		     (tun_info->mode & IP_TUNNEL_INFO_TX)))
+			*dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id));
+		else
+			regs->verdict.code = NFT_BREAK;
 		break;
 	default:
 		WARN_ON(1);
@@ -47,6 +66,7 @@ static void nft_tunnel_get_eval(const struct nft_expr *expr,
 static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = {
 	[NFTA_TUNNEL_KEY]	= { .type = NLA_U32 },
 	[NFTA_TUNNEL_DREG]	= { .type = NLA_U32 },
+	[NFTA_TUNNEL_MODE]	= { .type = NLA_U32 },
 };
 
 static int nft_tunnel_get_init(const struct nft_ctx *ctx,
@@ -74,6 +94,14 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx,
 
 	priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]);
 
+	if (tb[NFTA_TUNNEL_MODE]) {
+		priv->mode = ntohl(nla_get_be32(tb[NFTA_TUNNEL_MODE]));
+		if (priv->mode > NFT_TUNNEL_MODE_MAX)
+			return -EOPNOTSUPP;
+	} else {
+		priv->mode = NFT_TUNNEL_MODE_NONE;
+	}
+
 	return nft_validate_register_store(ctx, priv->dreg, NULL,
 					   NFT_DATA_VALUE, len);
 }
@@ -87,6 +115,8 @@ static int nft_tunnel_get_dump(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg))
 		goto nla_put_failure;
+	if (nla_put_be32(skb, NFTA_TUNNEL_MODE, htonl(priv->mode)))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index 55af9f247993..06dc55590441 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(nf_checksum_partial);
 int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 	     bool strict, unsigned short family)
 {
-	const struct nf_ipv6_ops *v6ops;
+	const struct nf_ipv6_ops *v6ops __maybe_unused;
 	int ret = 0;
 
 	switch (family) {
@@ -170,9 +170,7 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		ret = nf_ip_route(net, dst, fl, strict);
 		break;
 	case AF_INET6:
-		v6ops = rcu_dereference(nf_ipv6_ops);
-		if (v6ops)
-			ret = v6ops->route(net, dst, fl, strict);
+		ret = nf_ip6_route(net, dst, fl, strict);
 		break;
 	}
 
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index 89e281b3bfc2..29987ff03621 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -36,7 +36,6 @@ MODULE_ALIAS("ip6t_addrtype");
 static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 			    const struct in6_addr *addr, u16 mask)
 {
-	const struct nf_ipv6_ops *v6ops;
 	struct flowi6 flow;
 	struct rt6_info *rt;
 	u32 ret = 0;
@@ -47,18 +46,13 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 	if (dev)
 		flow.flowi6_oif = dev->ifindex;
 
-	v6ops = nf_get_ipv6_ops();
-	if (v6ops) {
-		if (dev && (mask & XT_ADDRTYPE_LOCAL)) {
-			if (v6ops->chk_addr(net, addr, dev, true))
-				ret = XT_ADDRTYPE_LOCAL;
-		}
-		route_err = v6ops->route(net, (struct dst_entry **)&rt,
-					 flowi6_to_flowi(&flow), false);
-	} else {
-		route_err = 1;
+	if (dev && (mask & XT_ADDRTYPE_LOCAL)) {
+		if (nf_ipv6_chk_addr(net, addr, dev, true))
+			ret = XT_ADDRTYPE_LOCAL;
 	}
 
+	route_err = nf_ip6_route(net, (struct dst_entry **)&rt,
+				 flowi6_to_flowi(&flow), false);
 	if (route_err)
 		return XT_ADDRTYPE_UNREACHABLE;
 
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index f44de4bc2100..1664d2ec8b2f 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -337,7 +337,6 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 	unsigned int nstamp_mask;
 	unsigned int i;
 	int ret = -EINVAL;
-	size_t sz;
 
 	net_get_random_once(&hash_rnd, sizeof(hash_rnd));
 
@@ -387,8 +386,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 		goto out;
 	}
 
-	sz = sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size;
-	t = kvzalloc(sz, GFP_KERNEL);
+	t = kvzalloc(struct_size(t, iphash, ip_list_hash_size), GFP_KERNEL);
 	if (t == NULL) {
 		ret = -ENOMEM;
 		goto out;