1 files changed, 140 insertions, 24 deletions

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 1a98583a79f4..6d1a4bec2614 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/skbuff.h>
+#include <net/gro.h>
 #include <net/udp.h>
 #include <net/protocol.h>
 #include <net/inet_common.h>
@@ -49,6 +50,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	__skb_pull(skb, tnl_hlen);
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
+	skb_set_transport_header(skb, skb_inner_transport_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = new_protocol;
 
@@ -67,6 +69,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
 
 	features &= skb->dev->hw_enc_features;
+	if (need_csum)
+		features &= ~NETIF_F_SCTP_CRC;
 
 	/* The only checksum offload we care about from here on out is the
 	 * outer one so strip the existing checksum feature flags and
@@ -149,8 +153,8 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features,
 				       bool is_ipv6)
 {
+	const struct net_offload __rcu **offloads;
 	__be16 protocol = skb->protocol;
-	const struct net_offload **offloads;
 	const struct net_offload *ops;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb,
@@ -184,8 +188,67 @@ out_unlock:
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
+static void __udpv4_gso_segment_csum(struct sk_buff *seg,
+				     __be32 *oldip, __be32 *newip,
+				     __be16 *oldport, __be16 *newport)
+{
+	struct udphdr *uh;
+	struct iphdr *iph;
+
+	if (*oldip == *newip && *oldport == *newport)
+		return;
+
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if (uh->check) {
+		inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip,
+					 true);
+		inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport,
+					 false);
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	}
+	*oldport = *newport;
+
+	csum_replace4(&iph->check, *oldip, *newip);
+	*oldip = *newip;
+}
+
+static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
+{
+	struct sk_buff *seg;
+	struct udphdr *uh, *uh2;
+	struct iphdr *iph, *iph2;
+
+	seg = segs;
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) &&
+	    (udp_hdr(seg)->source == udp_hdr(seg->next)->source) &&
+	    (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) &&
+	    (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr))
+		return segs;
+
+	while ((seg = seg->next)) {
+		uh2 = udp_hdr(seg);
+		iph2 = ip_hdr(seg);
+
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->saddr, &iph->saddr,
+					 &uh2->source, &uh->source);
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->daddr, &iph->daddr,
+					 &uh2->dest, &uh->dest);
+	}
+
+	return segs;
+}
+
 static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
-					      netdev_features_t features)
+					      netdev_features_t features,
+					      bool is_ipv6)
 {
 	unsigned int mss = skb_shinfo(skb)->gso_size;
 
@@ -195,11 +258,11 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
 
 	udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
 
-	return skb;
+	return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
 }
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
-				  netdev_features_t features)
+				  netdev_features_t features, bool is_ipv6)
 {
 	struct sock *sk = gso_skb->sk;
 	unsigned int sum_truesize = 0;
@@ -211,7 +274,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	__be16 newlen;
 
 	if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
-		return __udp_gso_segment_list(gso_skb, features);
+		return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
@@ -325,7 +388,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-		return __udp_gso_segment(skb, features);
+		return __udp_gso_segment(skb, features, false);
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -362,11 +425,38 @@ out:
 	return segs;
 }
 
+static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
+{
+	if (unlikely(p->len + skb->len >= 65536))
+		return -E2BIG;
+
+	if (NAPI_GRO_CB(p)->last == p)
+		skb_shinfo(p)->frag_list = skb;
+	else
+		NAPI_GRO_CB(p)->last->next = skb;
+
+	skb_pull(skb, skb_gro_offset(skb));
+
+	NAPI_GRO_CB(p)->last = skb;
+	NAPI_GRO_CB(p)->count++;
+	p->data_len += skb->len;
+
+	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
+	p->truesize += skb->truesize;
+	p->len += skb->len;
+
+	NAPI_GRO_CB(skb)->same_flow = 1;
+
+	return 0;
+}
+
+
 #define UDP_GRO_CNT_MAX 64
 static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 					       struct sk_buff *skb)
 {
-	struct udphdr *uh = udp_hdr(skb);
+	struct udphdr *uh = udp_gro_udphdr(skb);
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
@@ -453,19 +543,26 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
-	if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
-		NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;
+	/* we can do L4 aggregation only if the packet can't land in a tunnel
+	 * otherwise we could corrupt the inner stream
+	 */
+	NAPI_GRO_CB(skb)->is_flist = 0;
+	if (!sk || !udp_sk(sk)->gro_receive) {
+		if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
+			NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1;
 
-	if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) {
-		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
-		return pp;
+		if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
+		    (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
+			return call_gro_receive(udp_gro_receive_segment, head, skb);
+
+		/* no GRO, be sure flush the current packet */
+		goto out;
 	}
 
-	if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
-	    (skb->ip_summed != CHECKSUM_PARTIAL &&
+	if (NAPI_GRO_CB(skb)->encap_mark ||
+	    (uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
-	     !NAPI_GRO_CB(skb)->csum_valid) ||
-	    !udp_sk(sk)->gro_receive)
+	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the tunnel gro layer */
@@ -499,12 +596,22 @@ out:
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+					__be16 dport)
+{
+	const struct iphdr *iph = skb_gro_network_header(skb);
+
+	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 inet_sdif(skb), &udp_table, NULL);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
+	struct sock *sk = NULL;
 	struct sk_buff *pp;
-	struct sock *sk;
 
 	if (unlikely(!uh))
 		goto flush;
@@ -521,10 +628,11 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 					     inet_gro_compute_pseudo);
 skip:
 	NAPI_GRO_CB(skb)->is_ipv6 = 0;
-	rcu_read_lock();
-	sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+	if (static_branch_unlikely(&udp_encap_needed_key))
+		sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
 	pp = udp_gro_receive(head, skb, uh, sk);
-	rcu_read_unlock();
 	return pp;
 
 flush:
@@ -542,6 +650,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb)
 
 	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
 	skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+
+	if (skb->encapsulation)
+		skb->inner_transport_header = skb->transport_header;
+
 	return 0;
 }
 
@@ -550,18 +662,22 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 {
 	__be16 newlen = htons(skb->len - nhoff);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
-	int err = -ENOSYS;
 	struct sock *sk;
+	int err;
 
 	uh->len = newlen;
 
-	rcu_read_lock();
 	sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb,
 				udp4_lib_lookup_skb, skb, uh->source, uh->dest);
 	if (sk && udp_sk(sk)->gro_complete) {
 		skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
 					: SKB_GSO_UDP_TUNNEL;
 
+		/* clear the encap mark, so that inner frag_list gro_complete
+		 * can take place
+		 */
+		NAPI_GRO_CB(skb)->encap_mark = 0;
+
 		/* Set encapsulation before calling into inner gro_complete()
 		 * functions to make them set up the inner offsets.
 		 */
@@ -571,7 +687,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 	} else {
 		err = udp_gro_complete_segment(skb);
 	}
-	rcu_read_unlock();
 
 	if (skb->remcsum_offload)
 		skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM;
@@ -585,7 +700,8 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (NAPI_GRO_CB(skb)->is_flist) {
+	/* do fraglist only if there is no outer UDP encap (or we already processed it) */
+	if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) {
 		uh->len = htons(skb->len - nhoff);
 
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);