[PATCH nf-next v6 1/6] net: netfilter: add ether_type to net_device_path_ctx

Add an ether_type field to struct net_device_path_ctx to allow IPv6
tunnel drivers to select the appropriate L3 protocol based on the
encapsulated traffic.
Update the airoha and mtk Ethernet drivers to use the new
dev_fill_forward_path() signature.
This is a preliminary patch to enable sw flowtable acceleration for
IPv4 over IPv6 tunnels.

Signed-off-by: Lorenzo Bianconi <[email protected]>
---
 drivers/net/ethernet/airoha/airoha_ppe.c        | 13 ++++++++-----
 drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 13 ++++++++-----
 include/linux/netdevice.h                       |  4 +++-
 net/core/dev.c                                  |  6 ++++--
 net/ipv6/ip6_tunnel.c                           |  5 ++++-
 net/netfilter/nf_flow_table_path.c              |  8 +++++---
 6 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index e7c78293002a..06d128c67c8c 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -276,7 +276,8 @@ static int airoha_ppe_flow_mangle_ipv4(const struct flow_action_entry *act,
 	return 0;
 }
 
-static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr,
+static int airoha_ppe_get_wdma_info(struct net_device *dev,
+				    const u8 *addr, __be16 ether_type,
 				    struct airoha_wdma_info *info)
 {
 	struct net_device_path_stack stack;
@@ -287,7 +288,7 @@ static int airoha_ppe_get_wdma_info(struct net_device *dev, const u8 *addr,
 		return -ENODEV;
 
 	rcu_read_lock();
-	err = dev_fill_forward_path(dev, addr, &stack);
+	err = dev_fill_forward_path(dev, addr, ether_type, &stack);
 	rcu_read_unlock();
 	if (err)
 		return err;
@@ -331,7 +332,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 					struct airoha_foe_entry *hwe,
 					struct net_device *netdev, int type,
 					struct airoha_flow_data *data,
-					int l4proto)
+					__be16 ether_type, int l4proto)
 {
 	u32 qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f), ports_pad, val;
 	int wlan_etype = -EINVAL, dsa_port = airoha_get_dsa_port(&netdev);
@@ -354,7 +355,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
 		struct airoha_wdma_info info = {};
 
 		if (!airoha_ppe_get_wdma_info(netdev, data->eth.h_dest,
-					      &info)) {
+					      ether_type, &info)) {
 			val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, info.idx) |
 			       FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT,
 					  FE_PSE_PORT_CDM4);
@@ -1081,6 +1082,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
 	struct flow_action_entry *act;
 	struct airoha_foe_entry hwe;
 	int err, i, offload_type;
+	__be16 ether_type = 0;
 	u16 addr_type = 0;
 	u8 l4proto = 0;
 
@@ -1107,6 +1109,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
+		ether_type = match.key->n_proto;
 		l4proto = match.key->ip_proto;
 	} else {
 		return -EOPNOTSUPP;
@@ -1177,7 +1180,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_eth *eth,
 		return -EINVAL;
 
 	err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type,
-					   &data, l4proto);
+					   &data, ether_type, l4proto);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index cc8c4ef8038f..2601c17b29c8 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -89,7 +89,8 @@ mtk_flow_offload_mangle_eth(const struct flow_action_entry *act, void *eth)
 }
 
 static int
-mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_info *info)
+mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr,
+		       __be16 ether_type, struct mtk_wdma_info *info)
 {
 	struct net_device_path_stack stack;
 	struct net_device_path *path;
@@ -102,7 +103,7 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i
 		return -1;
 
 	rcu_read_lock();
-	err = dev_fill_forward_path(dev, addr, &stack);
+	err = dev_fill_forward_path(dev, addr, ether_type, &stack);
 	rcu_read_unlock();
 	if (err)
 		return err;
@@ -190,12 +191,12 @@ mtk_flow_get_dsa_port(struct net_device **dev)
 static int
 mtk_flow_set_output_device(struct mtk_eth *eth, struct mtk_foe_entry *foe,
 			   struct net_device *dev, const u8 *dest_mac,
-			   int *wed_index)
+			   __be16 ether_type, int *wed_index)
 {
 	struct mtk_wdma_info info = {};
 	int pse_port, dsa_port, queue;
 
-	if (mtk_flow_get_wdma_info(dev, dest_mac, &info) == 0) {
+	if (mtk_flow_get_wdma_info(dev, dest_mac, ether_type, &info) == 0) {
 		mtk_foe_entry_set_wdma(eth, foe, info.wdma_idx, info.queue,
 				       info.bss, info.wcid, info.amsdu);
 		if (mtk_is_netsys_v2_or_greater(eth)) {
@@ -273,6 +274,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 	struct mtk_flow_data data = {};
 	struct mtk_foe_entry foe;
 	struct mtk_flow_entry *entry;
+	__be16 ether_type = 0;
 	int offload_type = 0;
 	int wed_index = -1;
 	u16 addr_type = 0;
@@ -319,6 +321,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		struct flow_match_basic match;
 
 		flow_rule_match_basic(rule, &match);
+		ether_type = match.key->n_proto;
 		l4proto = match.key->ip_proto;
 	} else {
 		return -EOPNOTSUPP;
@@ -481,7 +484,7 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
 
 	err = mtk_flow_set_output_device(eth, &foe, odev, data.eth.h_dest,
-					 &wed_index);
+					 ether_type, &wed_index);
 	if (err)
 		return err;
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8db25b79573e..3ed53f390606 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -938,6 +938,7 @@ struct net_device_path_stack {
 struct net_device_path_ctx {
 	const struct net_device *dev;
 	u8			daddr[ETH_ALEN];
+	__be16			ether_type;
 
 	int			num_vlans;
 	struct {
@@ -3425,7 +3426,8 @@ void dev_remove_offload(struct packet_offload *po);
 
 int dev_get_iflink(const struct net_device *dev);
 int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
-int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+int dev_fill_forward_path(const struct net_device *dev,
+			  const u8 *daddr, __be16 ether_type,
 			  struct net_device_path_stack *stack);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7c21bc0a1e34..e66447ccf0ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -750,12 +750,14 @@ static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack)
 	return &stack->path[k];
 }
 
-int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+int dev_fill_forward_path(const struct net_device *dev,
+			  const u8 *daddr, __be16 ether_type,
 			  struct net_device_path_stack *stack)
 {
 	const struct net_device *last_dev;
 	struct net_device_path_ctx ctx = {
-		.dev	= dev,
+		.dev		= dev,
+		.ether_type	= ether_type,
 	};
 	struct net_device_path *path;
 	int ret = 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index bf8e40af60b0..38da07101601 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1863,7 +1863,10 @@ static int ip6_tnl_fill_forward_path(struct net_device_path_ctx *ctx,
 		path->type = DEV_PATH_TUN;
 		path->tun.src_v6 = t->parms.laddr;
 		path->tun.dst_v6 = t->parms.raddr;
-		path->tun.l3_proto = IPPROTO_IPV6;
+		if (ctx->ether_type == cpu_to_be16(ETH_P_IP))
+			path->tun.l3_proto = IPPROTO_IPIP;
+		else
+			path->tun.l3_proto = IPPROTO_IPV6;
 		path->dev = ctx->dev;
 		ctx->dev = dst->dev;
 	}
diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c
index 98c03b487f52..c8011ec36532 100644
--- a/net/netfilter/nf_flow_table_path.c
+++ b/net/netfilter/nf_flow_table_path.c
@@ -45,7 +45,8 @@ static bool nft_is_valid_ether_device(const struct net_device *dev)
 static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 				     const struct dst_entry *dst_cache,
 				     const struct nf_conn *ct,
-				     enum ip_conntrack_dir dir, u8 *ha,
+				     enum ip_conntrack_dir dir,
+				     u8 *ha, __be16 ether_type,
 				     struct net_device_path_stack *stack)
 {
 	const void *daddr = &ct->tuplehash[!dir].tuple.src.u3;
@@ -72,7 +73,7 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 		return -1;
 
 out:
-	return dev_fill_forward_path(dev, ha, stack);
+	return dev_fill_forward_path(dev, ha, ether_type, stack);
 }
 
 struct nft_forward_info {
@@ -255,7 +256,8 @@ static int nft_dev_forward_path(const struct nft_pktinfo *pkt,
 	unsigned char ha[ETH_ALEN];
 	int i;
 
-	if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) < 0 ||
+	if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, pkt->ethertype,
+				      &stack) < 0 ||
 	    nft_dev_path_info(&stack, &info, ha, &ft->data) < 0)
 		return -ENOENT;
 

-- 
2.55.0