net-gro: Prepare GRO stack for the upcoming tunneling support

This patch modifies the GRO stack to avoid the use of "network_header"
and associated macros like ip_hdr() and ipv6_hdr() in order to allow
an arbitary number of IP hdrs (v4 or v6) to be used in the
encapsulation chain. This lays the foundation for various IP
tunneling support (IP-in-IP, GRE, VXLAN, SIT,...) to be added later.

With this patch, the GRO stack traversing now is mostly based on
skb_gro_offset rather than special hdr offsets saved in skb (e.g.,
skb->network_header). As a result all but the top layer (i.e., the
the transport layer) must have hdrs of the same length in order for
a pkt to be considered for aggregation. Therefore when adding a new
encap layer (e.g., for tunneling), one must check and skip flows
(e.g., by setting NAPI_GRO_CB(p)->same_flow to 0) that have a
different hdr length.

Note that unlike the network header, the transport header can and
will continue to be set by the GRO code since there will be at
most one "transport layer" in the encap chain.

Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 44 insertions, 10 deletions

diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 4b851692b1f..7540a0ed75a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -154,6 +154,35 @@ out:
 	return segs;
 }
 
+/* Return the total length of all the extension hdrs, following the same
+ * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs.
+ */
+static int ipv6_exthdrs_len(struct ipv6hdr *iph,
+			    const struct net_offload **opps)
+{
+	struct ipv6_opt_hdr *opth = NULL;
+	int len = 0, proto, optlen;
+
+	proto = iph->nexthdr;
+	for (;;) {
+		if (proto != NEXTHDR_HOP) {
+			*opps = rcu_dereference(inet6_offloads[proto]);
+			if (unlikely(!(*opps)))
+				break;
+			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
+				break;
+		}
+		if (opth == NULL)
+			opth = (void *)(iph+1);
+		else
+			opth = (void *)opth + optlen;
+		optlen = ipv6_optlen(opth);
+		len += optlen;
+		proto = opth->nexthdr;
+	}
+	return len;
+}
+
 static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -177,6 +206,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 			goto out;
 	}
 
+	skb_set_network_header(skb, off);
 	skb_gro_pull(skb, sizeof(*iph));
 	skb_set_transport_header(skb, skb_gro_offset(skb));
 
@@ -211,12 +241,16 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
-		iph2 = ipv6_hdr(p);
+		iph2 = (struct ipv6hdr *)(p->data + off);
 		first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
 
-		/* All fields must match except length and Traffic Class. */
-		if (nlen != skb_network_header_len(p) ||
-		    (first_word & htonl(0xF00FFFFF)) ||
+		/* All fields must match except length and Traffic Class.
+		 * XXX skbs on the gro_list have all been parsed and pulled
+		 * already so we don't need to compare nlen
+		 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
+		 * memcmp() alone below is suffcient, right?
+		 */
+		 if ((first_word & htonl(0xF00FFFFF)) ||
 		    memcmp(&iph->nexthdr, &iph2->nexthdr,
 			   nlen - offsetof(struct ipv6hdr, nexthdr))) {
 			NAPI_GRO_CB(p)->same_flow = 0;
@@ -245,21 +279,21 @@ out:
 	return pp;
 }
 
-static int ipv6_gro_complete(struct sk_buff *skb)
+static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
-	struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	iph->payload_len = htons(skb->len - skb_network_offset(skb) -
-				 sizeof(*iph));
+	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_offloads[NAPI_GRO_CB(skb)->proto]);
+
+	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
 		goto out_unlock;
 
-	err = ops->callbacks.gro_complete(skb);
+	err = ops->callbacks.gro_complete(skb, nhoff);
 
 out_unlock:
 	rcu_read_unlock();