diff options
author | Pablo Neira Ayuso <pablo@netfilter.org> | 2022-10-25 14:48:15 +0300 |
---|---|---|
committer | Pablo Neira Ayuso <pablo@netfilter.org> | 2022-10-25 14:48:42 +0300 |
commit | 3a07327d10a09379315c844c63f27941f5081e0a (patch) | |
tree | f19a194677a2a43ea1d8800adb1ee38bdace0ad2 /net/netfilter/nft_payload.c | |
parent | 3927ce8850cacc1790cd4c5d02ca42e24df9fa6b (diff) | |
download | linux-3a07327d10a09379315c844c63f27941f5081e0a.tar.xz |
netfilter: nft_inner: support for inner tunnel header matching
This new expression allows you to match on the inner headers that are
encapsulated by any of the existing tunneling protocols.
This expression parses the inner packet to set the link, network and
transport offsets, so the existing expressions (with a few updates) can
be reused to match on the inner headers.
The inner expression supports for different tunnel combinations such as:
- ethernet frame over IPv4/IPv6 packet, eg. VxLAN.
- IPv4/IPv6 packet over IPv4/IPv6 packet, eg. IPIP.
- IPv4/IPv6 packet over IPv4/IPv6 + transport header, eg. GRE.
- transport header (ESP or SCTP) over transport header (usually UDP)
The following fields are used to describe the tunnel protocol:
- flags, which describe how to parse the inner headers:
NFT_PAYLOAD_CTX_INNER_TUN, the tunnel provides its own header.
NFT_PAYLOAD_CTX_INNER_ETHER, the ethernet frame is available as inner header.
NFT_PAYLOAD_CTX_INNER_NH, the network header is available as inner header.
NFT_PAYLOAD_CTX_INNER_TH, the transport header is available as inner header.
For example, VxLAN sets on all of these flags. While GRE only sets on
NFT_PAYLOAD_CTX_INNER_NH and NFT_PAYLOAD_CTX_INNER_TH. Then, ESP over
UDP only sets on NFT_PAYLOAD_CTX_INNER_TH.
The tunnel description is composed of the following attributes:
- header size: in case the tunnel comes with its own header, eg. VxLAN.
- type: this provides a hint to userspace on how to delinearize the rule.
This is useful for VxLAN and Geneve since they run over UDP, since
transport does not provide a hint. This is also useful in case hardware
offload is ever supported. The type is not currently interpreted by the
kernel.
- expression: currently only payload supported. Follow up patch adds
also inner meta support which is required by autogenerated
dependencies. The exthdr expression should be supported too
at some point. There is a new inner_ops operation that needs to be
set on to allow to use an existing expression from the inner expression.
This patch adds a new NFT_PAYLOAD_TUN_HEADER base which allows to match
on the tunnel header fields, eg. vxlan vni.
The payload expression is embedded into nft_inner private area and this
private data area is passed to the payload inner eval function via
direct call.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Diffstat (limited to 'net/netfilter/nft_payload.c')
-rw-r--r-- | net/netfilter/nft_payload.c | 89 |
1 files changed, 88 insertions, 1 deletions
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 84b490d6cc75..9d2ac764a14c 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -144,7 +144,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) return 0; } -static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +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) @@ -587,6 +587,92 @@ const struct nft_expr_ops nft_payload_fast_ops = { .offload = nft_payload_offload, }; +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_payload *priv = nft_expr_priv(expr); + const struct sk_buff *skb = pkt->skb; + u32 *dest = ®s->data[priv->dreg]; + int offset; + + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + + switch (priv->base) { + case NFT_PAYLOAD_TUN_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TUN)) + goto err; + + offset = tun_ctx->inner_tunoff; + break; + case NFT_PAYLOAD_LL_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_LL)) + goto err; + + offset = tun_ctx->inner_lloff; + break; + case NFT_PAYLOAD_NETWORK_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_NH)) + goto err; + + offset = tun_ctx->inner_nhoff; + break; + case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + offset = tun_ctx->inner_thoff; + break; + default: + WARN_ON_ONCE(1); + goto err; + } + offset += priv->offset; + + if (skb_copy_bits(skb, offset, dest, priv->len) < 0) + goto err; + + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static int nft_payload_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_payload *priv = nft_expr_priv(expr); + u32 base; + + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); + switch (base) { + case NFT_PAYLOAD_TUN_HEADER: + case NFT_PAYLOAD_LL_HEADER: + case NFT_PAYLOAD_NETWORK_HEADER: + case NFT_PAYLOAD_TRANSPORT_HEADER: + break; + default: + return -EOPNOTSUPP; + } + + priv->base = base; + priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); + priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); +} + +static const struct nft_expr_ops nft_payload_inner_ops = { + .type = &nft_payload_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_payload)), + .init = nft_payload_inner_init, + .dump = nft_payload_dump, + /* direct call to nft_payload_inner_eval(). */ +}; + static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum) { *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum)); @@ -930,6 +1016,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, struct nft_expr_type nft_payload_type __read_mostly = { .name = "payload", .select_ops = nft_payload_select_ops, + .inner_ops = &nft_payload_inner_ops, .policy = nft_payload_policy, .maxattr = NFTA_PAYLOAD_MAX, .owner = THIS_MODULE, |