net: Handle encapsulated offloads before fragmentation or handing to lower dev

This change allows the VXLAN to enable Tx checksum offloading even on
devices that do not support encapsulated checksum offloads. The
advantage to this is that it allows for the lower device to change due
to routing table changes without impacting features on the VXLAN itself.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/core/dev.c

@@ -2324,6 +2324,13 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			skb->vlan_tci = 0;
 		}
 
+		/* If encapsulation offload request, verify we are testing
+		 * hardware encapsulation features instead of standard
+		 * features for the netdev
+		 */
+		if (skb->encapsulation)
+			features &= dev->hw_enc_features;
+
 		if (netif_needs_gso(skb, features)) {
 			if (unlikely(dev_gso_segment(skb, features)))
 				goto out_kfree_skb;
@@ -2339,8 +2346,12 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			 * checksumming here.
 			 */
 			if (skb->ip_summed == CHECKSUM_PARTIAL) {
-				skb_set_transport_header(skb,
-					skb_checksum_start_offset(skb));
+				if (skb->encapsulation)
+					skb_set_inner_transport_header(skb,
+						skb_checksum_start_offset(skb));
+				else
+					skb_set_transport_header(skb,
+						skb_checksum_start_offset(skb));
 				if (!(features & NETIF_F_ALL_CSUM) &&
 				     skb_checksum_help(skb))
 					goto out_kfree_skb;

net/ipv4/ip_output.c

@@ -595,6 +595,10 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	}
 
 slow_path:
+	/* for offloaded checksums cleanup checksum before fragmentation */
+	if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb))
+		goto fail;
+
 	left = skb->len - hlen;		/* Space per frame */
 	ptr = hlen;		/* Where to start from */