[PATCH net-next v5 2/3] net/xfrm: Add inner_ipproto into sec_path

[Huy Nguyen <huyn@nvidia.com>]

The inner_ipproto saves the inner IP protocol of the plain
text packet. This allows vendor's IPsec feature making offload
decision at skb's features_check and configuring hardware at
ndo_start_xmit.

For example, ConnectX6-DX IPsec device needs the plaintext's
IP protocol to support partial checksum offload on
VXLAN/GENEVE packet over IPsec transport mode tunnel.

Signed-off-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Huy Nguyen <huyn@nvidia.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |  1 +
 net/xfrm/xfrm_output.c | 41 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c8890da00b8a..30e94d98005b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1022,6 +1022,7 @@ struct xfrm_offload {
 #define CRYPTO_INVALID_PROTOCOL			128
 
 	__u8			proto;
+	__u8			inner_ipproto;
 };
 
 struct sec_path {
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index e14fca1fb003..1eac2c8565ed 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -640,6 +640,42 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb
 	return 0;
 }
 
+/* For partial checksum offload, the outer header checksum is calculated
+ * by software and the inner header checksum is calculated by hardware.
+ * This requires hardware to know the inner packet type to calculate
+ * the inner header checksum. Save inner ip protocol here to avoid
+ * traversing the packet in the vendor's xmit code.
+ * If the encap type is IPIP, just save skb->inner_ipproto. Otherwise,
+ * get the ip protocol from the IP header.
+ */
+static void xfrm_get_inner_ipproto(struct sk_buff *skb)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+	const struct ethhdr *eth;
+
+	if (!xo)
+		return;
+
+	if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) {
+		xo->inner_ipproto = skb->inner_ipproto;
+		return;
+	}
+
+	if (skb->inner_protocol_type != ENCAP_TYPE_ETHER)
+		return;
+
+	eth = (struct ethhdr *)skb_inner_mac_header(skb);
+
+	switch (ntohs(eth->h_proto)) {
+	case ETH_P_IPV6:
+		xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr;
+		break;
+	case ETH_P_IP:
+		xo->inner_ipproto = inner_ip_hdr(skb)->protocol;
+		break;
+	}
+}
+
 int xfrm_output(struct sock *sk, struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
@@ -669,12 +705,15 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 			kfree_skb(skb);
 			return -ENOMEM;
 		}
-		skb->encapsulation = 1;
 
 		sp->olen++;
 		sp->xvec[sp->len++] = x;
 		xfrm_state_hold(x);
 
+		if (skb->encapsulation)
+			xfrm_get_inner_ipproto(skb);
+		skb->encapsulation = 1;
+
 		if (skb_is_gso(skb)) {
 			if (skb->inner_protocol)
 				return xfrm_output_gso(net, sk, skb);
-- 
2.24.1