diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d9c961aa6a7f..a2a70cc70e7b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1632,7 +1632,10 @@ struct napi_gro_cb {
 	int data_offset;
 
 	/* This is non-zero if the packet cannot be merged with the new skb. */
-	int flush;
+	u16	flush;
+
+	/* Save the IP ID here and check when we get to the transport layer */
+	u16	flush_id;
 
 	/* Number of segments aggregated. */
 	u16	count;
@@ -1651,6 +1654,9 @@ struct napi_gro_cb {
 	/* Used in ipv6_gro_receive() */
 	int	proto;
 
+	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
+	__wsum	csum;
+
 	/* used in skb_gro_receive() slow path */
 	struct sk_buff *last;
 };
@@ -1900,6 +1906,14 @@ static inline void *skb_gro_network_header(struct sk_buff *skb)
 	       skb_network_offset(skb);
 }
 
+static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
+					const void *start, unsigned int len)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum,
+						  csum_partial(start, len, 0));
+}
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
 				  const void *daddr, const void *saddr,
@@ -2440,6 +2454,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
 gro_result_t napi_gro_frags(struct napi_struct *napi);
+struct packet_offload *gro_find_receive_by_type(__be16 type);
+struct packet_offload *gro_find_complete_by_type(__be16 type);
 
 static inline void napi_free_frags(struct napi_struct *napi)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index b3c574a88026..ce01847793c0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3846,6 +3846,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 	skb_gro_reset_offset(skb);
 	gro_list_prepare(napi, skb);
+	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
@@ -3922,6 +3923,31 @@ normal:
 	goto pull;
 }
 
+struct packet_offload *gro_find_receive_by_type(__be16 type)
+{
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->callbacks.gro_receive)
+			continue;
+		return ptype;
+	}
+	return NULL;
+}
+
+struct packet_offload *gro_find_complete_by_type(__be16 type)
+{
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->callbacks.gro_complete)
+			continue;
+		return ptype;
+	}
+	return NULL;
+}
 
 static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index b8bc1a3d5cf1..6268a4751e64 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1391,9 +1391,15 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 		NAPI_GRO_CB(p)->flush |=
 			(iph->ttl ^ iph2->ttl) |
 			(iph->tos ^ iph2->tos) |
-			(__force int)((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) |
-			((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
+			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
 
+		/* Save the IP ID check to be included later when we get to
+		 * the transport layer so only the inner most IP ID is checked.
+		 * This is because some GSO/TSO implementations do not
+		 * correctly increment the IP ID for the outer hdrs.
+		 */
+		NAPI_GRO_CB(p)->flush_id =
+			    ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 		NAPI_GRO_CB(p)->flush |= flush;
 	}
 
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 9138cfb10140..746a7b10d434 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -116,10 +116,170 @@ out:
 	return segs;
 }
 
+/* Compute the whole skb csum in s/w and store it, then verify GRO csum
+ * starting from gro_offset.
+ */
+static __sum16 gro_skb_checksum(struct sk_buff *skb)
+{
+	__sum16 sum;
+
+	skb->csum = skb_checksum(skb, 0, skb->len, 0);
+	NAPI_GRO_CB(skb)->csum = csum_sub(skb->csum,
+		csum_partial(skb->data, skb_gro_offset(skb), 0));
+	sum = csum_fold(NAPI_GRO_CB(skb)->csum);
+	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
+		if (unlikely(!sum))
+			netdev_rx_csum_fault(skb->dev);
+	} else
+		skb->ip_summed = CHECKSUM_COMPLETE;
+
+	return sum;
+}
+
+static struct sk_buff **gre_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	struct sk_buff **pp = NULL;
+	struct sk_buff *p;
+	const struct gre_base_hdr *greh;
+	unsigned int hlen, grehlen;
+	unsigned int off;
+	int flush = 1;
+	struct packet_offload *ptype;
+	__be16 type;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*greh);
+	greh = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out;
+	}
+
+	/* Only support version 0 and K (key), C (csum) flags. Note that
+	 * although the support for the S (seq#) flag can be added easily
+	 * for GRO, this is problematic for GSO hence can not be enabled
+	 * here because a GRO pkt may end up in the forwarding path, thus
+	 * requiring GSO support to break it up correctly.
+	 */
+	if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
+		goto out;
+
+	type = greh->protocol;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL)
+		goto out_unlock;
+
+	grehlen = GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	hlen = off + grehlen;
+	if (skb_gro_header_hard(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out_unlock;
+	}
+	if (greh->flags & GRE_CSUM) { /* Need to verify GRE csum first */
+		__sum16 csum = 0;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			csum = csum_fold(NAPI_GRO_CB(skb)->csum);
+		/* Don't trust csum error calculated/reported by h/w */
+		if (skb->ip_summed == CHECKSUM_NONE || csum != 0)
+			csum = gro_skb_checksum(skb);
+
+		/* GRE CSUM is the 1's complement of the 1's complement sum
+		 * of the GRE hdr plus payload so it should add up to 0xffff
+		 * (and 0 after csum_fold()) just like the IPv4 hdr csum.
+		 */
+		if (csum)
+			goto out_unlock;
+	}
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		const struct gre_base_hdr *greh2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		/* The following checks are needed to ensure only pkts
+		 * from the same tunnel are considered for aggregation.
+		 * The criteria for "the same tunnel" includes:
+		 * 1) same version (we only support version 0 here)
+		 * 2) same protocol (we only support ETH_P_IP for now)
+		 * 3) same set of flags
+		 * 4) same key if the key field is present.
+		 */
+		greh2 = (struct gre_base_hdr *)(p->data + off);
+
+		if (greh2->flags != greh->flags ||
+		    greh2->protocol != greh->protocol) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+		if (greh->flags & GRE_KEY) {
+			/* compare keys */
+			if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
+				NAPI_GRO_CB(p)->same_flow = 0;
+				continue;
+			}
+		}
+	}
+
+	skb_gro_pull(skb, grehlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, greh, grehlen);
+
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+
+int gre_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
+	struct packet_offload *ptype;
+	unsigned int grehlen = sizeof(*greh);
+	int err = -ENOENT;
+	__be16 type;
+
+	type = greh->protocol;
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
+
+	rcu_read_unlock();
+	return err;
+}
+
 static const struct net_offload gre_offload = {
 	.callbacks = {
 		.gso_send_check = gre_gso_send_check,
 		.gso_segment = gre_gso_segment,
+		.gro_receive = gre_gro_receive,
+		.gro_complete = gre_gro_complete,
 	},
 };
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2658a27f540d..771a3950d87a 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -197,7 +197,8 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	goto out_check_final;
 
 found:
-	flush = NAPI_GRO_CB(p)->flush;
+	/* Include the IP ID check below from the inner most IP hdr */
+	flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
@@ -230,7 +231,7 @@ out_check_final:
 		pp = head;
 
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	NAPI_GRO_CB(skb)->flush |= (flush != 0);
 
 	return pp;
 }
@@ -280,7 +281,7 @@ static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 6fb4162fa785..1e8683b135bb 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -190,7 +190,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	unsigned int nlen;
 	unsigned int hlen;
 	unsigned int off;
-	int flush = 1;
+	u16 flush = 1;
 	int proto;
 	__wsum csum;