This allows to replace a tcp option with nop padding to selectively disable
a particular tcp option.
Optstrip mode is chosen when userspace passes the exthdr expression with
neither a source nor a destination register attribute.
This is identical to xtables TCPOPTSTRIP extension.
Signed-off-by: Florian Westphal <fw@xxxxxxxxx>
---
proposed userspace syntax is:
nft add rule f in delete tcp option sack-perm
net/netfilter/nft_exthdr.c | 88 +++++++++++++++++++++++++++++++++++++-
1 file changed, 87 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index dbe1f2e7dd9e..37e427ca2b34 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -308,6 +308,55 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
regs->verdict.code = NFT_BREAK;
}
+static void nft_exthdr_tcp_strip_eval(const struct nft_expr *expr,
+ struct nft_regs *regs,
+ const struct nft_pktinfo *pkt)
+{
+ u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE];
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+ unsigned int i, tcphdr_len, optl;
+ struct tcphdr *tcph;
+ u8 *opt;
+
+ tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
+ if (!tcph)
+ goto err;
+
+ if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + tcphdr_len))
+ goto err;
+
+ opt = (u8 *)nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
+ if (!opt)
+ goto err;
+ for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
+ unsigned int j;
+
+ optl = optlen(opt, i);
+ if (priv->type != opt[i])
+ continue;
+
+ if (i + optl > tcphdr_len)
+ goto err;
+
+ for (j = 0; j < optl; ++j) {
+ u16 n = TCPOPT_NOP;
+ u16 o = opt[i+j];
+
+ if ((i + j) % 2 == 0) {
+ o <<= 8;
+ n <<= 8;
+ }
+ inet_proto_csum_replace2(&tcph->check, pkt->skb, htons(o),
+ htons(n), false);
+ }
+ memset(opt + i, TCPOPT_NOP, optl);
+ return;
+ }
+ return;
+err:
+ regs->verdict.code = NFT_BREAK;
+}
+
static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
@@ -457,6 +506,28 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx,
priv->len);
}
+static int nft_exthdr_tcp_strip_init(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nlattr * const tb[])
+{
+ struct nft_exthdr *priv = nft_expr_priv(expr);
+
+ if (tb[NFTA_EXTHDR_SREG] ||
+ tb[NFTA_EXTHDR_DREG] ||
+ tb[NFTA_EXTHDR_FLAGS] ||
+ tb[NFTA_EXTHDR_OFFSET] ||
+ tb[NFTA_EXTHDR_LEN])
+ return -EINVAL;
+
+ if (!tb[NFTA_EXTHDR_TYPE])
+ return -EINVAL;
+
+ priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
+ priv->op = NFT_EXTHDR_OP_TCPOPT;
+
+ return 0;
+}
+
static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
@@ -517,6 +588,13 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr)
return nft_exthdr_dump_common(skb, priv);
}
+static int nft_exthdr_dump_strip(struct sk_buff *skb, const struct nft_expr *expr)
+{
+ const struct nft_exthdr *priv = nft_expr_priv(expr);
+
+ return nft_exthdr_dump_common(skb, priv);
+}
+
static const struct nft_expr_ops nft_exthdr_ipv6_ops = {
.type = &nft_exthdr_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
@@ -549,6 +627,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = {
.dump = nft_exthdr_dump_set,
};
+static const struct nft_expr_ops nft_exthdr_tcp_strip_ops = {
+ .type = &nft_exthdr_type,
+ .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
+ .eval = nft_exthdr_tcp_strip_eval,
+ .init = nft_exthdr_tcp_strip_init,
+ .dump = nft_exthdr_dump_strip,
+};
+
static const struct nft_expr_ops nft_exthdr_sctp_ops = {
.type = &nft_exthdr_type,
.size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
@@ -576,7 +662,7 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
return &nft_exthdr_tcp_set_ops;
if (tb[NFTA_EXTHDR_DREG])
return &nft_exthdr_tcp_ops;
- break;
+ return &nft_exthdr_tcp_strip_ops;
case NFT_EXTHDR_OP_IPV6:
if (tb[NFTA_EXTHDR_DREG])
return &nft_exthdr_ipv6_ops;
--
2.33.1
