1 files changed, 235 insertions, 78 deletions

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 55e6bfb3a289..5028c72d494a 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -1,130 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	IPV4 GSO/GRO offload support
  *	Linux INET implementation
  *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
  *	GRE GSO support
  */
 
 #include <linux/skbuff.h>
+#include <linux/init.h>
 #include <net/protocol.h>
 #include <net/gre.h>
-
-static int gre_gso_send_check(struct sk_buff *skb)
-{
-	if (!skb->encapsulation)
-		return -EINVAL;
-	return 0;
-}
+#include <net/gro.h>
+#include <net/gso.h>
 
 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);
-	netdev_features_t enc_features;
-	int ghl = GRE_HEADER_SECTION;
-	struct gre_base_hdr *greh;
-	int mac_len = skb->mac_len;
+	u16 mac_offset = skb->mac_header;
 	__be16 protocol = skb->protocol;
-	int tnl_hlen;
-	bool csum;
-
-	if (unlikely(skb_shinfo(skb)->gso_type &
-				~(SKB_GSO_TCPV4 |
-				  SKB_GSO_TCPV6 |
-				  SKB_GSO_UDP |
-				  SKB_GSO_DODGY |
-				  SKB_GSO_TCP_ECN |
-				  SKB_GSO_GRE)))
-		goto out;
+	u16 mac_len = skb->mac_len;
+	int gre_offset, outer_hlen;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
+	if (!skb->encapsulation)
 		goto out;
 
-	greh = (struct gre_base_hdr *)skb_transport_header(skb);
+	if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr)))
+		goto out;
 
-	if (greh->flags & GRE_KEY)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_SEQ)
-		ghl += GRE_HEADER_SECTION;
-	if (greh->flags & GRE_CSUM) {
-		ghl += GRE_HEADER_SECTION;
-		csum = true;
-	} else
-		csum = false;
+	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
+		goto out;
 
 	/* setup inner skb. */
-	skb->protocol = greh->protocol;
 	skb->encapsulation = 0;
-
-	if (unlikely(!pskb_may_pull(skb, ghl)))
-		goto out;
-
-	__skb_pull(skb, ghl);
+	SKB_GSO_CB(skb)->encap_level = 0;
+	__skb_pull(skb, tnl_hlen);
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
+	skb->protocol = skb->inner_protocol;
+
+	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	skb->encap_hdr_csum = need_csum;
+
+	features &= skb->dev->hw_enc_features;
+	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. */
-	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
-	segs = skb_mac_gso_segment(skb, enc_features);
-	if (!segs || IS_ERR(segs))
+	segs = skb_mac_gso_segment(skb, features);
+	if (IS_ERR_OR_NULL(segs)) {
+		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+				     mac_len);
 		goto out;
+	}
+
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
 
+	outer_hlen = skb_tnl_header_len(skb);
+	gre_offset = outer_hlen - tnl_hlen;
 	skb = segs;
-	tnl_hlen = skb_tnl_header_len(skb);
 	do {
-		__skb_push(skb, ghl);
-		if (csum) {
-			__be32 *pcsum;
-
-			if (skb_has_shared_frag(skb)) {
-				int err;
-
-				err = __skb_linearize(skb);
-				if (err) {
-					kfree_skb_list(segs);
-					segs = ERR_PTR(err);
-					goto out;
-				}
-			}
+		struct gre_base_hdr *greh;
+		__sum16 *pcsum;
 
-			greh = (struct gre_base_hdr *)(skb->data);
-			pcsum = (__be32 *)(greh + 1);
-			*pcsum = 0;
-			*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+		/* Set up inner headers if we are offloading inner checksum */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			skb_reset_inner_headers(skb);
+			skb->encapsulation = 1;
 		}
-		__skb_push(skb, tnl_hlen - ghl);
 
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
+		skb->mac_len = mac_len;
+		skb->protocol = protocol;
 
+		__skb_push(skb, outer_hlen);
 		skb_reset_mac_header(skb);
 		skb_set_network_header(skb, mac_len);
-		skb->mac_len = mac_len;
-		skb->protocol = protocol;
+		skb_set_transport_header(skb, gre_offset);
+
+		if (!need_csum)
+			continue;
+
+		greh = (struct gre_base_hdr *)skb_transport_header(skb);
+		pcsum = (__sum16 *)(greh + 1);
+
+		if (gso_partial && skb_is_gso(skb)) {
+			unsigned int partial_adj;
+
+			/* Adjust checksum to account for the fact that
+			 * the partial checksum is based on actual size
+			 * whereas headers should be based on MSS size.
+			 */
+			partial_adj = skb->len + skb_headroom(skb) -
+				      SKB_GSO_CB(skb)->data_offset -
+				      skb_shinfo(skb)->gso_size;
+			*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
+		} else {
+			*pcsum = 0;
+		}
+
+		*(pcsum + 1) = 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;
 }
 
+static struct sk_buff *gre_gro_receive(struct list_head *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;
+
+	if (NAPI_GRO_CB(skb)->encap_mark)
+		goto out;
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*greh);
+	greh = skb_gro_header(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;
+
+	/* We can only support GRE_CSUM if we can track the location of
+	 * the GRE header.  In the case of FOU/GUE we cannot because the
+	 * outer UDP header displaces the GRE header leaving us in a state
+	 * of limbo.
+	 */
+	if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou)
+		goto out;
+
+	type = greh->protocol;
+
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype)
+		goto out;
+
+	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_may_pull(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out;
+	}
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) {
+		if (skb_gro_checksum_simple_validate(skb))
+			goto out;
+
+		skb_gro_checksum_try_convert(skb, IPPROTO_GRE,
+					     null_compute_pseudo);
+	}
+
+	list_for_each_entry(p, head, list) {
+		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 = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+	flush = 0;
+
+out:
+	skb_gro_flush_final(skb, pp, flush);
+
+	return pp;
+}
+
+static 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;
+
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
+	type = greh->protocol;
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
+
+	skb_set_inner_mac_header(skb, nhoff + grehlen);
+
+	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,
 	},
 };
 
-int __init gre_offload_init(void)
+static int __init gre_offload_init(void)
 {
-	return inet_add_offload(&gre_offload, IPPROTO_GRE);
-}
+	int err;
 
-void __exit gre_offload_exit(void)
-{
-	inet_del_offload(&gre_offload, IPPROTO_GRE);
+	err = inet_add_offload(&gre_offload, IPPROTO_GRE);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (err)
+		return err;
+
+	err = inet6_add_offload(&gre_offload, IPPROTO_GRE);
+	if (err)
+		inet_del_offload(&gre_offload, IPPROTO_GRE);
+#endif
+
+	return err;
 }
+device_initcall(gre_offload_init);