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 nf-next:

1) Add IPS_HW_OFFLOAD status bit, from Bodong Wang.

2) Remove 128-bit limit on the set element data area, rise it
   to 64 bytes.

3) Report EOPNOTSUPP for unsupported NAT types and flags.

4) Set up nft_nat flags from the control plane path.

5) Add helper functions to set up the nf_nat_range2 structure.

6) Add netmap support for nft_nat.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netfilter/nf_tables.h

@@ -243,6 +243,10 @@ struct nft_set_elem {
 		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
 		struct nft_data	val;
 	} key_end;
+	union {
+		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
+		struct nft_data val;
+	} data;
 	void			*priv;
 };
 

include/uapi/linux/netfilter/nf_conntrack_common.h

@@ -114,15 +114,19 @@ enum ip_conntrack_status {
 	IPS_OFFLOAD_BIT = 14,
 	IPS_OFFLOAD = (1 << IPS_OFFLOAD_BIT),
 
+	/* Conntrack has been offloaded to hardware. */
+	IPS_HW_OFFLOAD_BIT = 15,
+	IPS_HW_OFFLOAD = (1 << IPS_HW_OFFLOAD_BIT),
+
 	/* Be careful here, modifying these bits can make things messy,
 	 * so don't let users modify them directly.
 	 */
 	IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK |
 				 IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING |
 				 IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED |
-				 IPS_OFFLOAD),
+				 IPS_OFFLOAD | IPS_HW_OFFLOAD),
 
-	__IPS_MAX_BIT = 15,
+	__IPS_MAX_BIT = 16,
 };
 
 /* Connection tracking event types */

include/uapi/linux/netfilter/nf_nat.h

@@ -11,6 +11,7 @@
 #define NF_NAT_RANGE_PERSISTENT			(1 << 3)
 #define NF_NAT_RANGE_PROTO_RANDOM_FULLY		(1 << 4)
 #define NF_NAT_RANGE_PROTO_OFFSET		(1 << 5)
+#define NF_NAT_RANGE_NETMAP			(1 << 6)
 
 #define NF_NAT_RANGE_PROTO_RANDOM_ALL		\
 	(NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY)
@@ -18,7 +19,8 @@
 #define NF_NAT_RANGE_MASK					\
 	(NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED |	\
 	 NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT |	\
-	 NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET)
+	 NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET | \
+	 NF_NAT_RANGE_NETMAP)
 
 struct nf_nat_ipv4_range {
 	unsigned int			flags;

net/netfilter/nf_conntrack_standalone.c

@@ -348,7 +348,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
 		goto release;
 
-	if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
+	if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status))
+		seq_puts(s, "[HW_OFFLOAD] ");
+	else if (test_bit(IPS_OFFLOAD_BIT, &ct->status))
 		seq_puts(s, "[OFFLOAD] ");
 	else if (test_bit(IPS_ASSURED_BIT, &ct->status))
 		seq_puts(s, "[ASSURED] ");

net/netfilter/nf_flow_table_offload.c

@@ -754,12 +754,15 @@ static void flow_offload_work_add(struct flow_offload_work *offload)
 	err = flow_offload_rule_add(offload, flow_rule);
 	if (err < 0)
 		set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags);
+	else
+		set_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
 
 	nf_flow_offload_destroy(flow_rule);
 }
 
 static void flow_offload_work_del(struct flow_offload_work *offload)
 {
+	clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status);
 	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL);
 	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY);
 	set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags);

net/netfilter/nf_tables_api.c

@@ -4669,6 +4669,25 @@ static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set,
 	return 0;
 }
 
+static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set,
+				  struct nft_data_desc *desc,
+				  struct nft_data *data,
+				  struct nlattr *attr)
+{
+	int err;
+
+	err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr);
+	if (err < 0)
+		return err;
+
+	if (desc->type != NFT_DATA_VERDICT && desc->len != set->dlen) {
+		nft_data_release(data, desc->type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr)
 {
@@ -4946,7 +4965,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_expr *expr = NULL;
 	struct nft_userdata *udata;
 	struct nft_data_desc desc;
-	struct nft_data data;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
 	u32 flags = 0;
@@ -5072,15 +5090,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	}
 
 	if (nla[NFTA_SET_ELEM_DATA] != NULL) {
-		err = nft_data_init(ctx, &data, sizeof(data), &desc,
-				    nla[NFTA_SET_ELEM_DATA]);
+		err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val,
+					     nla[NFTA_SET_ELEM_DATA]);
 		if (err < 0)
 			goto err_parse_key_end;
 
-		err = -EINVAL;
-		if (set->dtype != NFT_DATA_VERDICT && desc.len != set->dlen)
-			goto err_parse_data;
-
 		dreg = nft_type_to_reg(set->dtype);
 		list_for_each_entry(binding, &set->bindings, list) {
 			struct nft_ctx bind_ctx = {
@@ -5094,14 +5108,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 				continue;
 
 			err = nft_validate_register_store(&bind_ctx, dreg,
-							  &data,
+							  &elem.data.val,
 							  desc.type, desc.len);
 			if (err < 0)
 				goto err_parse_data;
 
 			if (desc.type == NFT_DATA_VERDICT &&
-			    (data.verdict.code == NFT_GOTO ||
-			     data.verdict.code == NFT_JUMP))
+			    (elem.data.val.verdict.code == NFT_GOTO ||
+			     elem.data.val.verdict.code == NFT_JUMP))
 				nft_validate_state_update(ctx->net,
 							  NFT_VALIDATE_NEED);
 		}
@@ -5123,7 +5137,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 
 	err = -ENOMEM;
 	elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data,
-				      elem.key_end.val.data, data.data,
+				      elem.key_end.val.data, elem.data.val.data,
 				      timeout, expiration, GFP_KERNEL);
 	if (elem.priv == NULL)
 		goto err_parse_data;
@@ -5201,7 +5215,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	nf_tables_set_elem_destroy(ctx, set, elem.priv);
 err_parse_data:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
-		nft_data_release(&data, desc.type);
+		nft_data_release(&elem.data.val, desc.type);
 err_parse_key_end:
 	nft_data_release(&elem.key_end.val, NFT_DATA_VALUE);
 err_parse_key:

net/netfilter/nft_nat.c

@@ -30,6 +30,76 @@ struct nft_nat {
 	u16			flags;
 };
 
+static void nft_nat_setup_addr(struct nf_nat_range2 *range,
+			       const struct nft_regs *regs,
+			       const struct nft_nat *priv)
+{
+	switch (priv->family) {
+	case AF_INET:
+		range->min_addr.ip = (__force __be32)
+				regs->data[priv->sreg_addr_min];
+		range->max_addr.ip = (__force __be32)
+				regs->data[priv->sreg_addr_max];
+		break;
+	case AF_INET6:
+		memcpy(range->min_addr.ip6, &regs->data[priv->sreg_addr_min],
+		       sizeof(range->min_addr.ip6));
+		memcpy(range->max_addr.ip6, &regs->data[priv->sreg_addr_max],
+		       sizeof(range->max_addr.ip6));
+		break;
+	}
+}
+
+static void nft_nat_setup_proto(struct nf_nat_range2 *range,
+				const struct nft_regs *regs,
+				const struct nft_nat *priv)
+{
+	range->min_proto.all = (__force __be16)
+		nft_reg_load16(&regs->data[priv->sreg_proto_min]);
+	range->max_proto.all = (__force __be16)
+		nft_reg_load16(&regs->data[priv->sreg_proto_max]);
+}
+
+static void nft_nat_setup_netmap(struct nf_nat_range2 *range,
+				 const struct nft_pktinfo *pkt,
+				 const struct nft_nat *priv)
+{
+	struct sk_buff *skb = pkt->skb;
+	union nf_inet_addr new_addr;
+	__be32 netmask;
+	int i, len = 0;
+
+	switch (priv->type) {
+	case NFT_NAT_SNAT:
+		if (nft_pf(pkt) == NFPROTO_IPV4) {
+			new_addr.ip = ip_hdr(skb)->saddr;
+			len = sizeof(struct in_addr);
+		} else {
+			new_addr.in6 = ipv6_hdr(skb)->saddr;
+			len = sizeof(struct in6_addr);
+		}
+		break;
+	case NFT_NAT_DNAT:
+		if (nft_pf(pkt) == NFPROTO_IPV4) {
+			new_addr.ip = ip_hdr(skb)->daddr;
+			len = sizeof(struct in_addr);
+		} else {
+			new_addr.in6 = ipv6_hdr(skb)->daddr;
+			len = sizeof(struct in6_addr);
+		}
+		break;
+	}
+
+	for (i = 0; i < len / sizeof(__be32); i++) {
+		netmask = ~(range->min_addr.ip6[i] ^ range->max_addr.ip6[i]);
+		new_addr.ip6[i] &= ~netmask;
+		new_addr.ip6[i] |= range->min_addr.ip6[i] & netmask;
+	}
+
+	range->min_addr = new_addr;
+	range->max_addr = new_addr;
+}
+
 static void nft_nat_eval(const struct nft_expr *expr,
 			 struct nft_regs *regs,
 			 const struct nft_pktinfo *pkt)
@@ -40,33 +110,17 @@ static void nft_nat_eval(const struct nft_expr *expr,
 	struct nf_nat_range2 range;
 
 	memset(&range, 0, sizeof(range));
-	if (priv->sreg_addr_min) {
-		if (priv->family == AF_INET) {
-			range.min_addr.ip = (__force __be32)
-					regs->data[priv->sreg_addr_min];
-			range.max_addr.ip = (__force __be32)
-					regs->data[priv->sreg_addr_max];
 
-		} else {
-			memcpy(range.min_addr.ip6,
-			       &regs->data[priv->sreg_addr_min],
-			       sizeof(range.min_addr.ip6));
-			memcpy(range.max_addr.ip6,
-			       &regs->data[priv->sreg_addr_max],
-			       sizeof(range.max_addr.ip6));
-		}
-		range.flags |= NF_NAT_RANGE_MAP_IPS;
+	if (priv->sreg_addr_min) {
+		nft_nat_setup_addr(&range, regs, priv);
+		if (priv->flags & NF_NAT_RANGE_NETMAP)
+			nft_nat_setup_netmap(&range, pkt, priv);
 	}
 
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_min]);
-		range.max_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_max]);
-		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
+	if (priv->sreg_proto_min)
+		nft_nat_setup_proto(&range, regs, priv);
 
-	range.flags |= priv->flags;
+	range.flags = priv->flags;
 
 	regs->verdict.code = nf_nat_setup_info(ct, &range, priv->type);
 }
@@ -129,7 +183,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		priv->type = NF_NAT_MANIP_DST;
 		break;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	if (tb[NFTA_NAT_FAMILY] == NULL)
@@ -169,6 +223,8 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		} else {
 			priv->sreg_addr_max = priv->sreg_addr_min;
 		}
+
+		priv->flags |= NF_NAT_RANGE_MAP_IPS;
 	}
 
 	plen = sizeof_field(struct nf_nat_range, min_addr.all);
@@ -191,12 +247,14 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		} else {
 			priv->sreg_proto_max = priv->sreg_proto_min;
 		}
+
+		priv->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
 	if (tb[NFTA_NAT_FLAGS]) {
-		priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
+		priv->flags |= ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS]));
 		if (priv->flags & ~NF_NAT_RANGE_MASK)
-			return -EINVAL;
+			return -EOPNOTSUPP;
 	}
 
 	return nf_ct_netns_get(ctx->net, family);