i40e/i40evf: Enable support for SKB_GSO_UDP_TUNNEL_CSUM

BugLink: http://bugs.launchpad.net/bugs/1547674

The XL722 has support for providing the outer UDP tunnel checksum on
transmits.  Make use of this feature to support segmenting UDP tunnels with
outer checksums enabled.
Signed-off-by: Alexander Duyck <aduyck@mirantis.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
(cherry picked from net-next commit 5453205c)
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2273,6 +2273,7 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	} ip;
 	union {
 		struct tcphdr *tcp;
+		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
 	u32 paylen, l4_offset;
@@ -2299,7 +2300,18 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		ip.v6->payload_len = 0;
 	}
 
-	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			/* determine offset of outer transport header */
+			l4_offset = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = (__force u16)l4.udp->check;
+			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+		}
+
 		/* reset pointers to inner headers */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
@@ -2461,6 +2473,11 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
 			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 
+		/* indicate if we need to offload outer UDP header */
+		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+
 		/* record tunnel offload values */
 		*cd_tunneling |= tunnel;
 

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -1533,6 +1533,7 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	} ip;
 	union {
 		struct tcphdr *tcp;
+		struct udphdr *udp;
 		unsigned char *hdr;
 	} l4;
 	u32 paylen, l4_offset;
@@ -1559,7 +1560,18 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		ip.v6->payload_len = 0;
 	}
 
-	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE)) {
+	if (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_GRE |
+					 SKB_GSO_UDP_TUNNEL_CSUM)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			/* determine offset of outer transport header */
+			l4_offset = l4.hdr - skb->data;
+
+			/* remove payload length from outer checksum */
+			paylen = (__force u16)l4.udp->check;
+			paylen += ntohs(1) * (u16)~(skb->len - l4_offset);
+			l4.udp->check = ~csum_fold((__force __wsum)paylen);
+		}
+
 		/* reset pointers to inner headers */
 		ip.hdr = skb_inner_network_header(skb);
 		l4.hdr = skb_inner_transport_header(skb);
@@ -1679,6 +1691,11 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 		tunnel |= ((ip.hdr - l4.hdr) / 2) <<
 			  I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 
+		/* indicate if we need to offload outer UDP header */
+		if ((*tx_flags & I40E_TX_FLAGS_TSO) &&
+		    (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM))
+			tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK;
+
 		/* record tunnel offload values */
 		*cd_tunneling |= tunnel;