[PATCH v16 nf-next 3/3] netfilter: nft_chain_filter: Add bridge double vlan and pppoe

[Eric Woudstra <ericwouds@gmail.com>]

In nft_do_chain_bridge() pktinfo is only fully populated for plain packets
and packets encapsulated in single 802.1q or 802.1ad.

When implementing the software bridge-fastpath and testing all possible
encapulations, there can be more encapsulations:

The packet could (also) be encapsulated in PPPoE, or the packet could be
encapsulated in an inner 802.1q, combined with an outer 802.1ad or 802.1q
encapsulation.

nft_flow_offload_eval() also examines the L4 header, with the L4 protocol
known from the conntrack-tuplehash. To access the header it uses
nft_thoff(), but for these packets it returns zero.

Introduce nft_set_bridge_pktinfo() to help populate pktinfo with the
offsets, without setting pkt->tprot and the corresponding pkt->flags.

This will not change rule processing, but does make these offsets
available for code that is not checking pkt->flags to use the offsets,
like nft_flow_offload_eval().

Existing behaviour for a rule like "tcp dport 22 accept" is not changed
when, for instance, a PPPoE packet is being matched.

Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
 net/netfilter/nft_chain_filter.c | 58 ++++++++++++++++++++++++++++++--
 1 file changed, 56 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index b16185e9a6dd..1f3ae5687917 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -227,16 +227,64 @@ static inline void nft_chain_filter_inet_fini(void) {}
 #endif /* CONFIG_NF_TABLES_IPV6 */
 
 #if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE)
+static int nft_set_bridge_pktinfo(struct nft_pktinfo *pkt, struct sk_buff *skb,
+				  const struct nf_hook_state *state,
+				  __be16 *proto)
+{
+	nft_set_pktinfo(pkt, skb, state);
+
+	switch (*proto) {
+	case htons(ETH_P_PPP_SES): {
+		struct ppp_hdr {
+			struct pppoe_hdr hdr;
+			__be16 proto;
+		} *ph;
+
+		if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+			return -1;
+		ph = (struct ppp_hdr *)(skb->data);
+		switch (ph->proto) {
+		case htons(PPP_IP):
+			*proto = htons(ETH_P_IP);
+			skb_set_network_header(skb, PPPOE_SES_HLEN);
+			return PPPOE_SES_HLEN;
+		case htons(PPP_IPV6):
+			*proto = htons(ETH_P_IPV6);
+			skb_set_network_header(skb, PPPOE_SES_HLEN);
+			return PPPOE_SES_HLEN;
+		}
+		break;
+	}
+	case htons(ETH_P_8021Q): {
+		struct vlan_hdr *vhdr;
+
+		if (!pskb_may_pull(skb, VLAN_HLEN))
+			return -1;
+		vhdr = (struct vlan_hdr *)(skb->data);
+		*proto = vhdr->h_vlan_encapsulated_proto;
+		skb_set_network_header(skb, VLAN_HLEN);
+		return VLAN_HLEN;
+	}
+	}
+	return 0;
+}
+
 static unsigned int
 nft_do_chain_bridge(void *priv,
 		    struct sk_buff *skb,
 		    const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
+	__be16 proto;
+	int offset;
 
-	nft_set_pktinfo(&pkt, skb, state);
+	proto = eth_hdr(skb)->h_proto;
 
-	switch (eth_hdr(skb)->h_proto) {
+	offset = nft_set_bridge_pktinfo(&pkt, skb, state, &proto);
+	if (offset < 0)
+		return NF_ACCEPT;
+
+	switch (proto) {
 	case htons(ETH_P_IP):
 		nft_set_pktinfo_ipv4_validate(&pkt);
 		break;
@@ -248,6 +296,12 @@ nft_do_chain_bridge(void *priv,
 		break;
 	}
 
+	if (offset) {
+		skb_reset_network_header(skb);
+		pkt.flags = 0;
+		pkt.tprot = 0;
+	}
+
 	return nft_do_chain(&pkt, priv);
 }
 
-- 
2.50.0