[PATCH v4 net-next 08/12] ipv6: Add hop-by-hop header to jumbograms in ip6_output

[Eric Dumazet <eric.dumazet@gmail.com>]

From: Coco Li <lixiaoyan@google.com>

Instead of simply forcing a 0 payload_len in IPv6 header,
implement RFC 2675 and insert a custom extension header.

Note that only TCP stack is currently potentially generating
jumbograms, and that this extension header is purely local,
it wont be sent on a physical link.

This is needed so that packet capture (tcpdump and friends)
can properly dissect these large packets.

Signed-off-by: Coco Li <lixiaoyan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/linux/ipv6.h  |  1 +
 net/ipv6/ip6_output.c | 22 ++++++++++++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ec5ca392eaa31e83a022b1124fae6b607ba168cd..38c8203d52cbf39e523c43fe630a7b184b9991aa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -145,6 +145,7 @@ struct inet6_skb_parm {
 #define IP6SKB_L3SLAVE         64
 #define IP6SKB_JUMBOGRAM      128
 #define IP6SKB_SEG6	      256
+#define IP6SKB_FAKEJUMBO      512
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index afa5bd4ad167c4a40878f33773d43be85e89c32f..4081b12a01ff22ecf94a6490aef0665808407a6e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -182,7 +182,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #endif
 
 	mtu = ip6_skb_dst_mtu(skb);
-	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+	if (skb_is_gso(skb) &&
+	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
 		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
 
 	if ((skb->len > mtu && !skb_is_gso(skb)) ||
@@ -252,6 +254,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
 	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
 	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
@@ -259,7 +263,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	int hlimit = -1;
 	u32 mtu;
 
-	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev);
+	head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
 	if (opt)
 		head_room += opt->opt_nflen + opt->opt_flen;
 
@@ -282,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 					     &fl6->saddr);
 	}
 
+	if (unlikely(seg_len > IPV6_MAXPLEN)) {
+		hop_jumbo = skb_push(skb, hoplen);
+
+		hop_jumbo->nexthdr = proto;
+		hop_jumbo->hdrlen = 0;
+		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+		hop_jumbo->tlv_len = 4;
+		hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
+
+		proto = IPPROTO_HOPOPTS;
+		seg_len = 0;
+		IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
-- 
2.36.0.512.ge40c2bad7a-goog