tunnels: Don't apply GRO to multiple layers of encapsulation.

[ Upstream commit fac8e0f579695a3ecbc4d3cac369139d7f819971 ]

When drivers express support for TSO of encapsulated packets, they
only mean that they can do it for one layer of encapsulation.
Supporting additional levels would mean updating, at a minimum,
more IP length fields and they are unaware of this.

No encapsulation device expresses support for handling offloaded
encapsulated packets, so we won't generate these types of frames
in the transmit path. However, GRO doesn't have a check for
multiple levels of encapsulation and will attempt to build them.

UDP tunnel GRO actually does prevent this situation but it only
handles multiple UDP tunnels stacked on top of each other. This
generalizes that solution to prevent any kind of tunnel stacking
that would cause problems.

Fixes: bf5a755f ("net-gre-gro: Add GRE support to the GRO stack")
Signed-off-by: Jesse Gross <jesse@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

6 files changed, 38 insertions, 7 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index db3ad1860c2e..49ac10f99da0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1897,8 +1897,8 @@ struct napi_gro_cb {
 	/* This is non-zero if the packet may be of the same flow. */
 	u8	same_flow:1;
 
-	/* Used in udp_gro_receive */
-	u8	udp_mark:1;
+	/* Used in tunnel GRO receive */
+	u8	encap_mark:1;
 
 	/* GRO checksum is valid */
 	u8	csum_valid:1;
diff --git a/net/core/dev.c b/net/core/dev.c
index 93612b2e3bbf..2a24197f3a45 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4020,7 +4020,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->same_flow = 0;
 		NAPI_GRO_CB(skb)->flush = 0;
 		NAPI_GRO_CB(skb)->free = 0;
-		NAPI_GRO_CB(skb)->udp_mark = 0;
+		NAPI_GRO_CB(skb)->encap_mark = 0;
 
 		/* Setup for GRO checksum validation */
 		switch (skb->ip_summed) {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 40eb6fa6d4ce..1a621e1f1864 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1391,6 +1391,19 @@ out:
 	return pp;
 }
 
+static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
+					 struct sk_buff *skb)
+{
+	if (NAPI_GRO_CB(skb)->encap_mark) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	return inet_gro_receive(head, skb);
+}
+
 #define SECONDS_PER_DAY	86400
 
 /* inet_current_timestamp - Return IP network timestamp
@@ -1682,7 +1695,7 @@ static struct packet_offload ip_packet_offload __read_mostly = {
 static const struct net_offload ipip_offload = {
 	.callbacks = {
 		.gso_segment	= inet_gso_segment,
-		.gro_receive	= inet_gro_receive,
+		.gro_receive	= ipip_gro_receive,
 		.gro_complete	= ipip_gro_complete,
 	},
 };
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index abc50b41bc39..cc7b08232e92 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -128,6 +128,11 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 	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_fast(skb, off);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 6480cea7aa53..e6d05ae1f22e 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -266,14 +266,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
-	if (NAPI_GRO_CB(skb)->udp_mark ||
+	if (NAPI_GRO_CB(skb)->encap_mark ||
 	    (skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
 	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
-	/* mark that this skb passed once through the udp gro layer */
-	NAPI_GRO_CB(skb)->udp_mark = 1;
+	/* mark that this skb passed once through the tunnel gro layer */
+	NAPI_GRO_CB(skb)->encap_mark = 1;
 
 	rcu_read_lock();
 	uo_priv = rcu_dereference(udp_offload_base);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 01e12d0d8fcc..f291813c7c0c 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -258,6 +258,19 @@ out:
 	return pp;
 }
 
+static struct sk_buff **sit_gro_receive(struct sk_buff **head,
+					struct sk_buff *skb)
+{
+	if (NAPI_GRO_CB(skb)->encap_mark) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	return ipv6_gro_receive(head, skb);
+}
+
 static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;