Merge branch 'tunnel-fixes'

Jesse Gross says:

====================
Tunneling fixes

This series fixes a problem that was reported where encapsulated packets
do not have their encapsulation offload markers stripped off when being
decapsulated. This causes a significant performance drop if the packets
are later retransmitted.

Fixing this revealed two other bugs which are also addressed as prerequisites:
 * GRO can aggregate packets for multiple layers of encapsulation which the
   stack cannot properly handle.
 * IPIP packets which are combined by GRO are not marked properly with their
   GSO type.

Note that this is based off the net-next tree as the current target for
bug fixes.

v2: No code changes, just additional information in commit messages and
    a new cover letter.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 80 insertions, 14 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index be693b34662f..f9eebd518545 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2096,8 +2096,8 @@ 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/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index c35dda9ec991..56050f913339 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -305,6 +305,22 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 
 struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
 
+static inline int iptunnel_pull_offloads(struct sk_buff *skb)
+{
+	if (skb_is_gso(skb)) {
+		int err;
+
+		err = skb_unclone(skb, GFP_ATOMIC);
+		if (unlikely(err))
+			return err;
+		skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >>
+					       NETIF_F_GSO_SHIFT);
+	}
+
+	skb->encapsulation = 0;
+	return 0;
+}
+
 static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 {
 	if (pkt_len > 0) {
diff --git a/net/core/dev.c b/net/core/dev.c
index edb7179bc051..43c74cad25bc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4438,7 +4438,7 @@ 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;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0cc923f83e10..0fefba64ee79 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1380,6 +1380,19 @@ 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
@@ -1448,6 +1461,13 @@ out_unlock:
 	return err;
 }
 
+static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_IPIP;
+	return inet_gro_complete(skb, nhoff);
+}
+
 int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 			 unsigned short type, unsigned char protocol,
 			 struct net *net)
@@ -1675,8 +1695,8 @@ 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_complete	= inet_gro_complete,
+		.gro_receive	= ipip_gro_receive,
+		.gro_complete	= ipip_gro_complete,
 	},
 };
 
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 780484243e14..a0586b4a197d 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -48,7 +48,7 @@ static inline struct fou *fou_from_sock(struct sock *sk)
 	return sk->sk_user_data;
 }
 
-static void fou_recv_pull(struct sk_buff *skb, size_t len)
+static int fou_recv_pull(struct sk_buff *skb, size_t len)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
@@ -59,6 +59,7 @@ static void fou_recv_pull(struct sk_buff *skb, size_t len)
 	__skb_pull(skb, len);
 	skb_postpull_rcsum(skb, udp_hdr(skb), len);
 	skb_reset_transport_header(skb);
+	return iptunnel_pull_offloads(skb);
 }
 
 static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
@@ -68,9 +69,14 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (!fou)
 		return 1;
 
-	fou_recv_pull(skb, sizeof(struct udphdr));
+	if (fou_recv_pull(skb, sizeof(struct udphdr)))
+		goto drop;
 
 	return -fou->protocol;
+
+drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
@@ -170,6 +176,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
+	if (iptunnel_pull_offloads(skb))
+		goto drop;
+
 	return -guehdr->proto_ctype;
 
 drop:
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 540866dbd27d..dd031617160a 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -126,6 +126,11 @@ 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/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index d27276f6f8dd..02dd990af542 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -114,7 +114,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto,
 	skb->vlan_tci = 0;
 	skb_set_queue_mapping(skb, 0);
 	skb_scrub_packet(skb, xnet);
-	return 0;
+
+	return iptunnel_pull_offloads(skb);
 }
 EXPORT_SYMBOL_GPL(iptunnel_pull_header);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 8a3405a80260..8007f73b8981 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -311,14 +311,14 @@ 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 eeca943f12dc..82e9f3076028 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;
@@ -302,7 +315,7 @@ static struct packet_offload ipv6_packet_offload __read_mostly = {
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive    = ipv6_gro_receive,
+		.gro_receive    = sit_gro_receive,
 		.gro_complete   = sit_gro_complete,
 	},
 };
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index f45b8ffc2840..83384308d032 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -681,14 +681,16 @@ static int ipip6_rcv(struct sk_buff *skb)
 		skb->mac_header = skb->network_header;
 		skb_reset_network_header(skb);
 		IPCB(skb)->flags = 0;
-		skb->protocol = htons(ETH_P_IPV6);
+		skb->dev = tunnel->dev;
 
 		if (packet_is_spoofed(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
 			goto out;
 		}
 
-		__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
+		if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6),
+		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
+			goto out;
 
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {