netfilter: nft_payload: support for inner header matching / mangling

Allow to match and mangle on inner headers / payload data after the
transport header. There is a new field in the pktinfo structure that
stores the inner header offset which is calculated only when requested.
Only TCP and UDP supported at this stage.

Signed-off-by: Pablo Neira Ayuso <[e-mail]>

include/net/netfilter/nf_tables.h

···
 
 enum {
 	NFT_PKTINFO_L4PROTO	= (1 << 0),
+	NFT_PKTINFO_INNER	= (1 << 1),
 };
 
 struct nft_pktinfo {
···
 	u8				tprot;
 	u16				fragoff;
 	unsigned int			thoff;
+	unsigned int			inneroff;
 };
 
 static inline struct sock *nft_sk(const struct nft_pktinfo *pkt)

include/uapi/linux/netfilter/nf_tables.h

···
  * @NFT_PAYLOAD_LL_HEADER: link layer header
  * @NFT_PAYLOAD_NETWORK_HEADER: network header
  * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header
+ * @NFT_PAYLOAD_INNER_HEADER: inner header / payload
  */
 enum nft_payload_bases {
 	NFT_PAYLOAD_LL_HEADER,
 	NFT_PAYLOAD_NETWORK_HEADER,
 	NFT_PAYLOAD_TRANSPORT_HEADER,
+	NFT_PAYLOAD_INNER_HEADER,
 };
 
 /**

net/netfilter/nft_payload.c

···
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/ip.h>
 #include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
···
 	return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0;
 }
 
+static int __nft_payload_inner_offset(struct nft_pktinfo *pkt)
+{
+	unsigned int thoff = nft_thoff(pkt);
+
+	if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
+		return -1;
+
+	switch (pkt->tprot) {
+	case IPPROTO_UDP:
+		pkt->inneroff = thoff + sizeof(struct udphdr);
+		break;
+	case IPPROTO_TCP: {
+		struct tcphdr *th, _tcph;
+
+		th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph);
+		if (!th)
+			return -1;
+
+		pkt->inneroff = thoff + __tcp_hdrlen(th);
+		}
+		break;
+	default:
+		return -1;
+	}
+
+	pkt->flags |= NFT_PKTINFO_INNER;
+
+	return 0;
+}
+
+static int nft_payload_inner_offset(const struct nft_pktinfo *pkt)
+{
+	if (!(pkt->flags & NFT_PKTINFO_INNER) &&
+	    __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0)
+		return -1;
+
+	return pkt->inneroff;
+}
+
 void nft_payload_eval(const struct nft_expr *expr,
 		      struct nft_regs *regs,
 		      const struct nft_pktinfo *pkt)
···
 		if (!(pkt->flags & NFT_PKTINFO_L4PROTO))
 			goto err;
 		offset = nft_thoff(pkt);
+		break;
+	case NFT_PAYLOAD_INNER_HEADER:
+		offset = nft_payload_inner_offset(pkt);
+		if (offset < 0)
+			goto err;
 		break;
 	default:
 		BUG();
···
 			goto err;
 		offset = nft_thoff(pkt);
 		break;
+	case NFT_PAYLOAD_INNER_HEADER:
+		offset = nft_payload_inner_offset(pkt);
+		if (offset < 0)
+			goto err;
+		break;
 	default:
 		BUG();
 	}
···
 	offset += priv->offset;
 
 	if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) &&
-	    (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER ||
+	    ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER &&
+	      priv->base != NFT_PAYLOAD_INNER_HEADER) ||
 	     skb->ip_summed != CHECKSUM_PARTIAL)) {
 		fsum = skb_checksum(skb, offset, priv->len, 0);
 		tsum = csum_partial(src, priv->len, 0);
···
 	case NFT_PAYLOAD_LL_HEADER:
 	case NFT_PAYLOAD_NETWORK_HEADER:
 	case NFT_PAYLOAD_TRANSPORT_HEADER:
+	case NFT_PAYLOAD_INNER_HEADER:
 		break;
 	default:
 		return ERR_PTR(-EOPNOTSUPP);
···
 	len    = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN]));
 
 	if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) &&
-	    base != NFT_PAYLOAD_LL_HEADER)
+	    base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER)
 		return &nft_payload_fast_ops;
 	else
 		return &nft_payload_ops;