diff mbox series

[v11,nf-next,2/2] netfilter: nf_flow_table_offload: Add nf_flow_encap_push() for xmit direct

Message ID 20250408142425.95437-3-ericwouds@gmail.com (mailing list archive)
State New
Headers show
Series Add nf_flow_encap_push() for xmit direct | expand

Commit Message

Eric Woudstra April 8, 2025, 2:24 p.m. UTC
Loosely based on wenxu's patches:

"nf_flow_table_offload: offload the vlan/PPPoE encap in the flowtable".

Fixed double vlan and pppoe packets, almost entirely rewriting the patch.

When there is no extra vlan-device or pppoe-device added to the fastpath,
it may still be possible that the other tuple has encaps.

This is the case when there is only a bridge in the forward-fastpath,
without a vlan-device. When the bridge is tagging at ingress and keeping
at egress, the other tuple will have an encap.

It will be also be the case in the future bridge-fastpath.

In these cases it is necessary to push these encaps.

This patch adds nf_flow_encap_push() and alters nf_flow_queue_xmit()
to call it, only when (tuple.out.ifidx == tuple.out.hw_ifidx).

Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
---
 net/netfilter/nf_flow_table_ip.c | 97 +++++++++++++++++++++++++++++++-
 1 file changed, 95 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 8cd4cf7ae211..64a12b9668e7 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -306,6 +306,92 @@  static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
 	return false;
 }
 
+static int nf_flow_vlan_inner_push(struct sk_buff *skb, __be16 proto, u16 id)
+{
+	struct vlan_hdr *vhdr;
+
+	if (skb_cow_head(skb, VLAN_HLEN))
+		return -1;
+
+	__skb_push(skb, VLAN_HLEN);
+	skb_reset_network_header(skb);
+
+	vhdr = (struct vlan_hdr *)(skb->data);
+	vhdr->h_vlan_TCI = htons(id);
+	vhdr->h_vlan_encapsulated_proto = skb->protocol;
+	skb->protocol = proto;
+
+	return 0;
+}
+
+static int nf_flow_ppoe_push(struct sk_buff *skb, u16 id)
+{
+	struct ppp_hdr {
+		struct pppoe_hdr hdr;
+		__be16 proto;
+	} *ph;
+	int data_len = skb->len + 2;
+	__be16 proto;
+
+	if (skb_cow_head(skb, PPPOE_SES_HLEN))
+		return -1;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		proto = htons(PPP_IP);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		proto = htons(PPP_IPV6);
+	else
+		return -1;
+
+	__skb_push(skb, PPPOE_SES_HLEN);
+	skb_reset_network_header(skb);
+
+	ph = (struct ppp_hdr *)(skb->data);
+	ph->hdr.ver  = 1;
+	ph->hdr.type = 1;
+	ph->hdr.code = 0;
+	ph->hdr.sid  = htons(id);
+	ph->hdr.length = htons(data_len);
+	ph->proto = proto;
+	skb->protocol = htons(ETH_P_PPP_SES);
+
+	return 0;
+}
+
+static int nf_flow_encap_push(struct sk_buff *skb,
+			      struct flow_offload_tuple_rhash *tuplehash,
+			      unsigned short *type)
+{
+	int i = 0, ret = 0;
+
+	if (!tuplehash->tuple.encap_num)
+		return 0;
+
+	if (tuplehash->tuple.encap[i].proto == htons(ETH_P_8021Q) ||
+	    tuplehash->tuple.encap[i].proto == htons(ETH_P_8021AD)) {
+		__vlan_hwaccel_put_tag(skb, tuplehash->tuple.encap[i].proto,
+				       tuplehash->tuple.encap[i].id);
+		i++;
+		if (i >= tuplehash->tuple.encap_num)
+			return 0;
+	}
+
+	switch (tuplehash->tuple.encap[i].proto) {
+	case htons(ETH_P_8021Q):
+		*type = ETH_P_8021Q;
+		ret = nf_flow_vlan_inner_push(skb,
+					      tuplehash->tuple.encap[i].proto,
+					      tuplehash->tuple.encap[i].id);
+		break;
+	case htons(ETH_P_PPP_SES):
+		*type = ETH_P_PPP_SES;
+		ret = nf_flow_ppoe_push(skb,
+					tuplehash->tuple.encap[i].id);
+		break;
+	}
+	return ret;
+}
+
 static void nf_flow_encap_pop(struct sk_buff *skb,
 			      struct flow_offload_tuple_rhash *tuplehash)
 {
@@ -335,6 +421,7 @@  static void nf_flow_encap_pop(struct sk_buff *skb,
 
 static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
 				       const struct flow_offload_tuple_rhash *tuplehash,
+				       struct flow_offload_tuple_rhash *other_tuplehash,
 				       unsigned short type)
 {
 	struct net_device *outdev;
@@ -343,6 +430,10 @@  static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
 	if (!outdev)
 		return NF_DROP;
 
+	if (tuplehash->tuple.out.ifidx == tuplehash->tuple.out.hw_ifidx &&
+	    (nf_flow_encap_push(skb, other_tuplehash, &type) < 0))
+		return NF_DROP;
+
 	skb->dev = outdev;
 	dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest,
 			tuplehash->tuple.out.h_source, skb->len);
@@ -462,7 +553,8 @@  nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 		ret = NF_STOLEN;
 		break;
 	case FLOW_OFFLOAD_XMIT_DIRECT:
-		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP);
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash,
+					 &flow->tuplehash[!dir], ETH_P_IP);
 		if (ret == NF_DROP)
 			flow_offload_teardown(flow);
 		break;
@@ -757,7 +849,8 @@  nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 		ret = NF_STOLEN;
 		break;
 	case FLOW_OFFLOAD_XMIT_DIRECT:
-		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6);
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash,
+					 &flow->tuplehash[!dir], ETH_P_IPV6);
 		if (ret == NF_DROP)
 			flow_offload_teardown(flow);
 		break;