ip_gre: add csum offload support for gre header

This patch is to add csum offload support for gre header:

On the TX path in gre_build_header(), when CHECKSUM_PARTIAL's set
for inner proto, it will calculate the csum for outer proto, and
inner csum will be offloaded later. Otherwise, CHECKSUM_PARTIAL
and csum_start/offset will be set for outer proto, and the outer
csum will be offloaded later.

On the GSO path in gre_gso_segment(), when CHECKSUM_PARTIAL is
not set for inner proto and the hardware supports csum offload,
CHECKSUM_PARTIAL and csum_start/offset will be set for outer
proto, and outer csum will be offloaded later. Otherwise, it
will do csum for outer proto by calling gso_make_checksum().

Note that SCTP has to do the csum by itself for non GSO path in
sctp_packet_pack(), as gre_build_header() can't handle the csum
with CHECKSUM_PARTIAL set for SCTP CRC csum offload.

v1->v2:
  - remove the SCTP part, as GRE dev doesn't support SCTP CRC CSUM
    and it will always do checksum for SCTP in sctp_packet_pack()
    when it's not a GSO packet.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/gre.h

@@ -106,17 +106,6 @@ static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags)
 	return flags;
 }
 
-static inline __sum16 gre_checksum(struct sk_buff *skb)
-{
-	__wsum csum;
-
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		csum = lco_csum(skb);
-	else
-		csum = skb_checksum(skb, 0, skb->len, 0);
-	return csum_fold(csum);
-}
-
 static inline void gre_build_header(struct sk_buff *skb, int hdr_len,
 				    __be16 flags, __be16 proto,
 				    __be32 key, __be32 seq)
@@ -146,7 +135,13 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len,
 		    !(skb_shinfo(skb)->gso_type &
 		      (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) {
 			*ptr = 0;
-			*(__sum16 *)ptr = gre_checksum(skb);
+			if (skb->ip_summed == CHECKSUM_PARTIAL) {
+				*(__sum16 *)ptr = csum_fold(lco_csum(skb));
+			} else {
+				skb->ip_summed = CHECKSUM_PARTIAL;
+				skb->csum_start = skb_transport_header(skb) - skb->head;
+				skb->csum_offset = sizeof(*greh);
+			}
 		}
 	}
 }

net/ipv4/gre_offload.c

@@ -15,10 +15,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, offload_csum, gso_partial, need_ipsec;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
-	bool need_csum, gso_partial;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
 
@@ -47,6 +47,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	if (need_csum)
 		features &= ~NETIF_F_SCTP_CRC;
 
+	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
+	/* Try to offload checksum if possible */
+	offload_csum = !!(need_csum && !need_ipsec &&
+			  (skb->dev->features & NETIF_F_HW_CSUM));
+
 	/* segment inner packet. */
 	segs = skb_mac_gso_segment(skb, features);
 	if (IS_ERR_OR_NULL(segs)) {
@@ -100,7 +105,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		}
 
 		*(pcsum + 1) = 0;
-		*pcsum = gso_make_checksum(skb, 0);
+		if (skb->encapsulation || !offload_csum) {
+			*pcsum = gso_make_checksum(skb, 0);
+		} else {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_transport_header(skb) - skb->head;
+			skb->csum_offset = sizeof(*greh);
+		}
 	} while ((skb = skb->next));
 out:
 	return segs;