netdev - [PATCH v3 net-next 08/14] ipv6: Add hop-by-hop header to jumbograms in ip6

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220310002846.460907-9-eric.dumazet@gmail.com>
Date:   Wed,  9 Mar 2022 16:28:40 -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>,
        Alexander Duyck <alexanderduyck@...com>,
        Coco Li <lixiaoyan@...gle.com>,
        Eric Dumazet <edumazet@...gle.com>,
        Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH v3 net-next 08/14] 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 16870f86c74d3d1f5dfb7edac1e7db85f1ef6755..93b273db1c9926aba4199f486ce90778311916f5 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 e69fac576970a9b85fb68aa02822c0e2df67e1a2..941ceff83b616cec11c6bb7ccaf81bc041f8d9cc 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);
-- 
2.35.1.616.g0bdcbb4464-goog