[PATCH net-next 03/10] ipv6: add jumbo payload option to non-gso jumbograms

[Mariusz Klimek <maklimek97@gmail.com>]

This path reintroduces code recently removed by Alice in commit
741d069aa488 ("net/ipv6: Drop HBH for BIG TCP on TX side") and commit
35f66ce90037 ("net/ipv6: Remove HBH helpers") that adds a hop-by-hop header
containing a jumbo-payload option to packets larger than 65535 bytes. The
hop-by-hop header is only added to jumbograms that aren't BIG TCP packets
since BIG TCP packets no longer need to contain such hop-by-hop headers.

This fixes sending jumbograms to a loopback device with MTU > 65535.

Fixes: 741d069aa488 ("net/ipv6: Drop HBH for BIG TCP on TX side")
Signed-off-by: Mariusz Klimek <maklimek97@gmail.com>
---
 include/net/ipv6.h    | 11 +++++++++++
 net/ipv6/ip6_output.c | 22 ++++++++++++++++++++--
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 1dec81faff28..d9e1fdca6934 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -152,6 +152,17 @@ struct frag_hdr {
 	__be32	identification;
 };
 
+/*
+ * Jumbo payload option, as described in RFC 2675 2.
+ */
+struct hop_jumbo_hdr {
+	u8	nexthdr;
+	u8	hdrlen;
+	u8	tlv_type;	/* IPV6_TLV_JUMBO, 0xC2 */
+	u8	tlv_len;	/* 4 */
+	__be32	jumbo_payload_len;
+};
+
 #define	IP6_MF		0x0001
 #define	IP6_OFFSET	0xFFF8
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 67c34fb281c6..405a9a0e65a4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -293,6 +293,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	struct in6_addr *first_hop = &fl6->daddr;
 	struct dst_entry *dst = skb_dst(skb);
 	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
 	struct net *net = sock_net(sk);
 	unsigned int head_room;
 	struct net_device *dev;
@@ -305,7 +307,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	rcu_read_lock();
 
 	dev = dst_dev_rcu(dst);
-	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;
 
@@ -331,8 +333,24 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 						     &fl6->saddr);
 	}
 
-	if (unlikely(seg_len > IPV6_MAXPLEN))
+	if (unlikely(seg_len > IPV6_MAXPLEN)) {
+		/* Only "real" jumbograms require a jumbo-payload option.
+		 * BIG TCP packets just rely on skb->len.
+		 */
+		if (!skb_is_gso(skb)) {
+			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;
+	}
 
 	__skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
-- 
2.47.3