[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220203015140.3022854-9-eric.dumazet@gmail.com>
Date: Wed, 2 Feb 2022 17:51:33 -0800
From: Eric Dumazet <eric.dumazet@...il.com>
To: "David S . Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>
Cc: netdev <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
Coco Li <lixiaoyan@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH net-next 08/15] ipv6: Add hop-by-hop header to jumbograms in ip6_output
From: Coco Li <lixiaoyan@...gle.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@...gle.com>
Signed-off-by: Eric Dumazet <edumazet@...gle.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 1e0f8a31f3de175659dca9ecee9f97d8b01e2b68..d3fb87e1589997570cde9cb5d92b2222008a229d 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -144,6 +144,7 @@ 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 0c6c971ce0a58b50f8a9349b8507dffac9c7818c..f78ba145620560e5d7cb25aaf16fec61ddd9ed40 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -180,7 +180,9 @@ 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)) ||
@@ -251,6 +253,8 @@ 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;
@@ -258,7 +262,7 @@ 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;
@@ -281,6 +285,20 @@ 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);
--
2.35.0.rc2.247.g8bbb082509-goog
Powered by blists - more mailing lists