vxlan: fix GRO with VXLAN-GPE

index 42be8a26c171..6d82adf1f8b3 100644
@@ -623,6 +623,32 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	return 1;
 }
 
+static bool vxlan_parse_gpe_proto(struct vxlanhdr *hdr, __be16 *protocol)
+{
+	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)hdr;
+
+	/* Need to have Next Protocol set for interfaces in GPE mode. */
+	if (!gpe->np_applied)
+		return false;
+	/* "The initial version is 0. If a receiver does not support the
+	 * version indicated it MUST drop the packet.
+	 */
+	if (gpe->version != 0)
+		return false;
+	/* "When the O bit is set to 1, the packet is an OAM packet and OAM
+	 * processing MUST occur." However, we don't implement OAM
+	 * processing, thus drop the packet.
+	 */
+	if (gpe->oam_flag)
+		return false;
+
+	*protocol = tun_p_to_eth_p(gpe->next_protocol);
+	if (!*protocol)
+		return false;
+
+	return true;
+}
+
 static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 					  unsigned int off,
 					  struct vxlanhdr *vh, size_t hdrlen,

@@ -1525,35 +1551,6 @@ static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed,
 	unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS;
 }
 
-static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed,
-				__be16 *protocol,
-				struct sk_buff *skb, u32 vxflags)
-{
-	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)unparsed;
-
-	/* Need to have Next Protocol set for interfaces in GPE mode. */
-	if (!gpe->np_applied)
-		return false;
-	/* "The initial version is 0. If a receiver does not support the
-	 * version indicated it MUST drop the packet.
-	 */
-	if (gpe->version != 0)
-		return false;
-	/* "When the O bit is set to 1, the packet is an OAM packet and OAM
-	 * processing MUST occur." However, we don't implement OAM
-	 * processing, thus drop the packet.
-	 */
-	if (gpe->oam_flag)
-		return false;
-
-	*protocol = tun_p_to_eth_p(gpe->next_protocol);
-	if (!*protocol)
-		return false;
-
-	unparsed->vx_flags &= ~VXLAN_GPE_USED_BITS;
-	return true;
-}
-
 static bool vxlan_set_mac(struct vxlan_dev *vxlan,
 			  struct vxlan_sock *vs,
 			  struct sk_buff *skb, __be32 vni)

@@ -1655,8 +1652,9 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 	 * used by VXLAN extensions if explicitly requested.
 	 */
 	if (vs->flags & VXLAN_F_GPE) {
-		if (!vxlan_parse_gpe_hdr(&unparsed, &protocol, skb, vs->flags))
+		if (!vxlan_parse_gpe_proto(&unparsed, &protocol))
 			goto drop;
+		unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS;
 		raw_proto = true;
 	}
 

index 6d82adf1f8b3..c9a9373733c0 100644
@@ -675,26 +675,24 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 	return vh;
 }
 
-static struct sk_buff *vxlan_gro_receive(struct sock *sk,
-					 struct list_head *head,
-					 struct sk_buff *skb)
+static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk,
+						  struct list_head *head,
+						  struct sk_buff *skb,
+						  struct gro_remcsum *grc)
 {
-	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct vxlanhdr *vh, *vh2;
 	unsigned int hlen, off_vx;
-	int flush = 1;
 	struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk);
 	__be32 flags;
-	struct gro_remcsum grc;
 
-	skb_gro_remcsum_init(&grc);
+	skb_gro_remcsum_init(grc);
 
 	off_vx = skb_gro_offset(skb);
 	hlen = off_vx + sizeof(*vh);
 	vh = skb_gro_header(skb, hlen, off_vx);
 	if (unlikely(!vh))
-		goto out;
+		return NULL;
 
 	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
 

@@ -702,12 +700,12 @@ static struct sk_buff *vxlan_gro_receive(struct sock *sk,
 
 	if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
 		vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
-				       vh->vx_vni, &grc,
+				       vh->vx_vni, grc,
 				       !!(vs->flags &
 					  VXLAN_F_REMCSUM_NOPARTIAL));
 
 		if (!vh)
-			goto out;
+			return NULL;
 	}
 
 	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */

@@ -724,12 +722,48 @@ static struct sk_buff *vxlan_gro_receive(struct sock *sk,
 		}
 	}
 
-	pp = call_gro_receive(eth_gro_receive, head, skb);
-	flush = 0;
+	return vh;
+}
+
+static struct sk_buff *vxlan_gro_receive(struct sock *sk,
+					 struct list_head *head,
+					 struct sk_buff *skb)
+{
+	struct sk_buff *pp = NULL;
+	struct gro_remcsum grc;
+	int flush = 1;
 
-out:
+	if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) {
+		pp = call_gro_receive(eth_gro_receive, head, skb);
+		flush = 0;
+	}
 	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
+	return pp;
+}
 
+static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk,
+					     struct list_head *head,
+					     struct sk_buff *skb)
+{
+	const struct packet_offload *ptype;
+	struct sk_buff *pp = NULL;
+	struct gro_remcsum grc;
+	struct vxlanhdr *vh;
+	__be16 protocol;
+	int flush = 1;
+
+	vh = vxlan_gro_prepare_receive(sk, head, skb, &grc);
+	if (vh) {
+		if (!vxlan_parse_gpe_proto(vh, &protocol))
+			goto out;
+		ptype = gro_find_receive_by_type(protocol);
+		if (!ptype)
+			goto out;
+		pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+		flush = 0;
+	}
+out:
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 	return pp;
 }
 

@@ -741,6 +775,21 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
+static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
+{
+	struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff);
+	const struct packet_offload *ptype;
+	int err = -ENOSYS;
+	__be16 protocol;
+
+	if (!vxlan_parse_gpe_proto(vh, &protocol))
+		return err;
+	ptype = gro_find_complete_by_type(protocol);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
+	return err;
+}
+
 static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac,
 					 __u16 state, __be32 src_vni,
 					 __u16 ndm_flags)

@@ -3376,8 +3425,13 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 	tunnel_cfg.encap_rcv = vxlan_rcv;
 	tunnel_cfg.encap_err_lookup = vxlan_err_lookup;
 	tunnel_cfg.encap_destroy = NULL;
-	tunnel_cfg.gro_receive = vxlan_gro_receive;
-	tunnel_cfg.gro_complete = vxlan_gro_complete;
+	if (vs->flags & VXLAN_F_GPE) {
+		tunnel_cfg.gro_receive = vxlan_gpe_gro_receive;
+		tunnel_cfg.gro_complete = vxlan_gpe_gro_complete;
+	} else {
+		tunnel_cfg.gro_receive = vxlan_gro_receive;
+		tunnel_cfg.gro_complete = vxlan_gro_complete;
+	}
 
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);