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.
Basically, more incremental updates for br_netfilter from Florian
Westphal, small nf_tables updates (including one fix for rb-tree
locking) and small two-liner to add extra validation for the REJECT6
target.

More specifically, they are:

1) Use the conntrack status flags from br_netfilter to know that DNAT is
   happening. Patch for Florian Westphal.

2) nf_bridge->physoutdev == NULL already indicates that the traffic is
   bridged, so let's get rid of the BRNF_BRIDGED flag. Also from Florian.

3) Another patch to prepare voidization of seq_printf/seq_puts/seq_putc,
   from Joe Perches.

4) Consolidation of nf_tables_newtable() error path.

5) Kill nf_bridge_pad used by br_netfilter from ip_fragment(),
   from Florian Westphal.

6) Access rb-tree root node inside the lock and remove unnecessary
   locking from the get path (we already hold nfnl_lock there), from
   Patrick McHardy.

7) You cannot use a NFT_SET_ELEM_INTERVAL_END when the set doesn't
   support interval, also from Patrick.

8) Enforce IP6T_F_PROTO from ip6t_REJECT to make sure the core is
   actually restricting matches to TCP.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netfilter_bridge.h

@@ -19,23 +19,10 @@ enum nf_br_hook_priorities {
 
 #define BRNF_PKT_TYPE			0x01
 #define BRNF_BRIDGED_DNAT		0x02
-#define BRNF_BRIDGED			0x04
 #define BRNF_NF_BRIDGE_PREROUTING	0x08
 #define BRNF_8021Q			0x10
 #define BRNF_PPPoE			0x20
 
-static inline unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
-{
-	switch (skb->protocol) {
-	case __cpu_to_be16(ETH_P_8021Q):
-		return VLAN_HLEN;
-	case __cpu_to_be16(ETH_P_PPP_SES):
-		return PPPOE_SES_HLEN;
-	default:
-		return 0;
-	}
-}
-
 static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 {
 	if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE))
@@ -45,21 +32,6 @@ static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 
 int br_handle_frame_finish(struct sk_buff *skb);
 
-/* This is called by the IP fragmenting code and it ensures there is
- * enough room for the encapsulating header (if there is one). */
-static inline unsigned int nf_bridge_pad(const struct sk_buff *skb)
-{
-	if (skb->nf_bridge)
-		return nf_bridge_encap_header_len(skb);
-	return 0;
-}
-
-struct bridge_skb_cb {
-	union {
-		__be32 ipv4;
-	} daddr;
-};
-
 static inline void br_drop_fake_rtable(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -69,7 +41,6 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb)
 }
 
 #else
-#define nf_bridge_pad(skb)			(0)
 #define br_drop_fake_rtable(skb)	        do { } while (0)
 #endif /* CONFIG_BRIDGE_NETFILTER */
 

net/bridge/br_netfilter.c

@@ -37,17 +37,16 @@
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
 #include <asm/uaccess.h>
 #include "br_private.h"
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 #endif
 
-#define skb_origaddr(skb)	 (((struct bridge_skb_cb *) \
-				 (skb->nf_bridge->data))->daddr.ipv4)
-#define store_orig_dstaddr(skb)	 (skb_origaddr(skb) = ip_hdr(skb)->daddr)
-#define dnat_took_place(skb)	 (skb_origaddr(skb) != ip_hdr(skb)->daddr)
-
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *brnf_sysctl_header;
 static int brnf_call_iptables __read_mostly = 1;
@@ -154,6 +153,18 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb)
 	return nf_bridge;
 }
 
+static unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case __cpu_to_be16(ETH_P_8021Q):
+		return VLAN_HLEN;
+	case __cpu_to_be16(ETH_P_PPP_SES):
+		return PPPOE_SES_HLEN;
+	default:
+		return 0;
+	}
+}
+
 static inline void nf_bridge_push_encap_header(struct sk_buff *skb)
 {
 	unsigned int len = nf_bridge_encap_header_len(skb);
@@ -322,6 +333,22 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 	return 0;
 }
 
+static bool dnat_took_place(const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || nf_ct_is_untracked(ct))
+		return false;
+
+	return test_bit(IPS_DST_NAT_BIT, &ct->status);
+#else
+	return false;
+#endif
+}
+
 /* This requires some explaining. If DNAT has taken place,
  * we will need to fix up the destination Ethernet address.
  *
@@ -625,7 +652,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops,
 		return NF_DROP;
 	if (!setup_pre_routing(skb))
 		return NF_DROP;
-	store_orig_dstaddr(skb);
+
 	skb->protocol = htons(ETH_P_IP);
 
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL,
@@ -721,8 +748,6 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb))
 		return NF_DROP;
 
-	/* The physdev module checks on this */
-	nf_bridge->mask |= BRNF_BRIDGED;
 	nf_bridge->physoutdev = skb->dev;
 	if (pf == NFPROTO_IPV4)
 		skb->protocol = htons(ETH_P_IP);
@@ -842,7 +867,12 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 	struct net_device *realoutdev = bridge_parent(skb->dev);
 	u_int8_t pf;
 
-	if (!nf_bridge || !(nf_bridge->mask & BRNF_BRIDGED))
+	/* if nf_bridge is set, but ->physoutdev is NULL, this packet came in
+	 * on a bridge, but was delivered locally and is now being routed:
+	 *
+	 * POST_ROUTING was already invoked from the ip stack.
+	 */
+	if (!nf_bridge || !nf_bridge->physoutdev)
 		return NF_ACCEPT;
 
 	if (!realoutdev)

net/ipv4/ip_output.c

@@ -636,10 +636,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */
 
-	/* for bridged IP traffic encapsulated inside f.e. a vlan header,
-	 * we need to make room for the encapsulating header
-	 */
-	ll_rs = LL_RESERVED_SPACE_EXTRA(rt->dst.dev, nf_bridge_pad(skb));
+	ll_rs = LL_RESERVED_SPACE(rt->dst.dev);
 
 	/*
 	 *	Fragment the datagram.

net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c

@@ -300,7 +300,9 @@ static int exp_seq_show(struct seq_file *s, void *v)
 		    __nf_ct_l3proto_find(exp->tuple.src.l3num),
 		    __nf_ct_l4proto_find(exp->tuple.src.l3num,
 					 exp->tuple.dst.protonum));
-	return seq_putc(s, '\n');
+	seq_putc(s, '\n');
+
+	return 0;
 }
 
 static const struct seq_operations exp_seq_ops = {

net/ipv6/netfilter/ip6t_REJECT.c

@@ -83,7 +83,8 @@ static int reject_tg6_check(const struct xt_tgchk_param *par)
 		return -EINVAL;
 	} else if (rejinfo->with == IP6T_TCP_RESET) {
 		/* Must specify that it's a TCP packet */
-		if (e->ipv6.proto != IPPROTO_TCP ||
+		if (!(e->ipv6.flags & IP6T_F_PROTO) ||
+		    e->ipv6.proto != IPPROTO_TCP ||
 		    (e->ipv6.invflags & XT_INV_PROTO)) {
 			pr_info("TCP_RESET illegal for non-tcp\n");
 			return -EINVAL;

net/netfilter/nf_conntrack_acct.c

@@ -47,9 +47,11 @@ seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
 		return 0;
 
 	counter = acct->counter;
-	return seq_printf(s, "packets=%llu bytes=%llu ",
-			  (unsigned long long)atomic64_read(&counter[dir].packets),
-			  (unsigned long long)atomic64_read(&counter[dir].bytes));
+	seq_printf(s, "packets=%llu bytes=%llu ",
+		   (unsigned long long)atomic64_read(&counter[dir].packets),
+		   (unsigned long long)atomic64_read(&counter[dir].bytes));
+
+	return 0;
 };
 EXPORT_SYMBOL_GPL(seq_print_acct);
 

net/netfilter/nf_conntrack_expect.c

@@ -561,7 +561,9 @@ static int exp_seq_show(struct seq_file *s, void *v)
 				   helper->expect_policy[expect->class].name);
 	}
 
-	return seq_putc(s, '\n');
+	seq_putc(s, '\n');
+
+	return 0;
 }
 
 static const struct seq_operations exp_seq_ops = {

net/netfilter/nf_tables_api.c

@@ -687,11 +687,10 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	if (!try_module_get(afi->owner))
 		return -EAFNOSUPPORT;
 
+	err = -ENOMEM;
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
-	if (table == NULL) {
-		module_put(afi->owner);
-		return -ENOMEM;
-	}
+	if (table == NULL)
+		goto err1;
 
 	nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN);
 	INIT_LIST_HEAD(&table->chains);
@@ -700,13 +699,16 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 
 	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
 	err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
-	if (err < 0) {
-		kfree(table);
-		module_put(afi->owner);
-		return err;
-	}
+	if (err < 0)
+		goto err2;
+
 	list_add_tail_rcu(&table->list, &afi->tables);
 	return 0;
+err2:
+	kfree(table);
+err1:
+	module_put(afi->owner);
+	return err;
 }
 
 static int nft_flush_table(struct nft_ctx *ctx)
@@ -3136,6 +3138,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		elem.flags = ntohl(nla_get_be32(nla[NFTA_SET_ELEM_FLAGS]));
 		if (elem.flags & ~NFT_SET_ELEM_INTERVAL_END)
 			return -EINVAL;
+		if (!(set->flags & NFT_SET_INTERVAL) &&
+		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
 	}
 
 	if (set->flags & NFT_SET_MAP) {

net/netfilter/nfnetlink_log.c

@@ -998,11 +998,13 @@ static int seq_show(struct seq_file *s, void *v)
 {
 	const struct nfulnl_instance *inst = v;
 
-	return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n",
-			  inst->group_num,
-			  inst->peer_portid, inst->qlen,
-			  inst->copy_mode, inst->copy_range,
-			  inst->flushtimeout, atomic_read(&inst->use));
+	seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n",
+		   inst->group_num,
+		   inst->peer_portid, inst->qlen,
+		   inst->copy_mode, inst->copy_range,
+		   inst->flushtimeout, atomic_read(&inst->use));
+
+	return 0;
 }
 
 static const struct seq_operations nful_seq_ops = {

net/netfilter/nft_rbtree.c

@@ -37,10 +37,11 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
 	const struct nft_rbtree_elem *rbe, *interval = NULL;
-	const struct rb_node *parent = priv->root.rb_node;
+	const struct rb_node *parent;
 	int d;
 
 	spin_lock_bh(&nft_rbtree_lock);
+	parent = priv->root.rb_node;
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -158,7 +159,6 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 	struct nft_rbtree_elem *rbe;
 	int d;
 
-	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -173,11 +173,9 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 				nft_data_copy(&elem->data, rbe->data);
 			elem->flags = rbe->flags;
-			spin_unlock_bh(&nft_rbtree_lock);
 			return 0;
 		}
 	}
-	spin_unlock_bh(&nft_rbtree_lock);
 	return -ENOENT;
 }
 

net/netfilter/xt_physdev.c

@@ -56,8 +56,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	/* This only makes sense in the FORWARD and POSTROUTING chains */
 	if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
-	    (!!(nf_bridge->mask & BRNF_BRIDGED) ^
-	    !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
+	    (!!nf_bridge->physoutdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&