Merge tag 'nf-next-2023-05-18' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next

Florian Westphal says:

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

nftables updates:

1. Allow key existence checks with maps.
   At the moment the kernel requires userspace to pass a destination
   register for the associated value, make this optional so userspace
   can query if the key exists, just like with normal sets.

2. nftables maintains a counter per set that holds the number of
   elements.  This counter gets decremented on element removal,
   but its only incremented if the set has a upper maximum value.
   Increment unconditionally, this will allow us to update the
   maximum value later on.

3. At DCCP option maching, from Jeremy Sowden.

4. use struct_size macro, from Christophe JAILLET.

Conntrack:

5. Squash holes in struct nf_conntrack_expect, also Christophe JAILLET.

6. Allow clash resolution for GRE Protocol to avoid a packet drop,
   from Faicker Mo.

Flowtable:

Simplify route logic and split large functions into smaller
chunks, from Pablo Neira Ayuso.

* tag 'nf-next-2023-05-18' of https://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next:
  netfilter: flowtable: split IPv6 datapath in helper functions
  netfilter: flowtable: split IPv4 datapath in helper functions
  netfilter: flowtable: simplify route logic
  netfilter: conntrack: allow insertion clash of gre protocol
  netfilter: nft_set_pipapo: Use struct_size()
  netfilter: Reorder fields in 'struct nf_conntrack_expect'
  netfilter: nft_exthdr: add boolean DCCP option matching
  netfilter: nf_tables: always increment set element count
  netfilter: nf_tables: relax set/map validation checks
====================

Link: https://lore.kernel.org/r/20230518100759.84858-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 106 insertions, 0 deletions

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a54a7f772cec..671474e59817 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -10,6 +10,7 @@
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/dccp.h>
 #include <linux/sctp.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
@@ -406,6 +407,82 @@ err:
 		regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
+				 struct nft_regs *regs,
+				 const struct nft_pktinfo *pkt)
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	unsigned int thoff, dataoff, optoff, optlen, i;
+	u32 *dest = &regs->data[priv->dreg];
+	const struct dccp_hdr *dh;
+	struct dccp_hdr _dh;
+
+	if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff)
+		goto err;
+
+	thoff = nft_thoff(pkt);
+
+	dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh);
+	if (!dh)
+		goto err;
+
+	dataoff = dh->dccph_doff * sizeof(u32);
+	optoff = __dccp_hdr_len(dh);
+	if (dataoff <= optoff)
+		goto err;
+
+	optlen = dataoff - optoff;
+
+	for (i = 0; i < optlen; ) {
+		/* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in
+		 * the length; the remaining options are at least 2B long.  In
+		 * all cases, the first byte contains the option type.  In
+		 * multi-byte options, the second byte contains the option
+		 * length, which must be at least two: 1 for the type plus 1 for
+		 * the length plus 0-253 for any following option data.  We
+		 * aren't interested in the option data, only the type and the
+		 * length, so we don't need to read more than two bytes at a
+		 * time.
+		 */
+		unsigned int buflen = optlen - i;
+		u8 buf[2], *bufp;
+		u8 type, len;
+
+		if (buflen > sizeof(buf))
+			buflen = sizeof(buf);
+
+		bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen,
+					  &buf);
+		if (!bufp)
+			goto err;
+
+		type = bufp[0];
+
+		if (type == priv->type) {
+			*dest = 1;
+			return;
+		}
+
+		if (type <= DCCPO_MAX_RESERVED) {
+			i++;
+			continue;
+		}
+
+		if (buflen < 2)
+			goto err;
+
+		len = bufp[1];
+
+		if (len < 2)
+			goto err;
+
+		i += len;
+	}
+
+err:
+	*dest = 0;
+}
+
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
 	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
 	[NFTA_EXTHDR_TYPE]		= { .type = NLA_U8 },
@@ -557,6 +634,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
+static int nft_exthdr_dccp_init(const struct nft_ctx *ctx,
+				const struct nft_expr *expr,
+				const struct nlattr * const tb[])
+{
+	struct nft_exthdr *priv = nft_expr_priv(expr);
+	int err = nft_exthdr_init(ctx, expr, tb);
+
+	if (err < 0)
+		return err;
+
+	if (!(priv->flags & NFT_EXTHDR_F_PRESENT))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv)
 {
 	if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type))
@@ -686,6 +779,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = {
 	.reduce		= nft_exthdr_reduce,
 };
 
+static const struct nft_expr_ops nft_exthdr_dccp_ops = {
+	.type		= &nft_exthdr_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+	.eval		= nft_exthdr_dccp_eval,
+	.init		= nft_exthdr_dccp_init,
+	.dump		= nft_exthdr_dump,
+	.reduce		= nft_exthdr_reduce,
+};
+
 static const struct nft_expr_ops *
 nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -720,6 +822,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_sctp_ops;
 		break;
+	case NFT_EXTHDR_OP_DCCP:
+		if (tb[NFTA_EXTHDR_DREG])
+			return &nft_exthdr_dccp_ops;
+		break;
 	}
 
 	return ERR_PTR(-EOPNOTSUPP);