ipv6: icmp: allow flowlabel reflection in echo replies

Extend flowlabel_reflect bitmask to allow conditional
reflection of incoming flowlabels in echo replies.

Note this has precedence against auto flowlabels.

Add flowlabel_reflect enum to replace hard coded
values.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 17 insertions, 5 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e0d8a96e2c67..f0e6d1f53485 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1452,7 +1452,7 @@ flowlabel_reflect - INTEGER
 	environments. See RFC 7690 and:
 	https://tools.ietf.org/html/draft-wang-6man-flow-label-reflection-01
 
-	This is a mask of two bits.
+	This is a bitmask.
 	1: enabled for established flows
 
 	Note that this prevents automatic flowlabel changes, as done
@@ -1463,6 +1463,8 @@ flowlabel_reflect - INTEGER
 	If set, a RST packet sent in response to a SYN packet on a closed
 	port will reflect the incoming flow label.
 
+	4: enabled for ICMPv6 echo reply messages.
+
 	Default: 0
 
 fib_multipath_hash_policy - INTEGER
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b41f6a0fa903..8eca5fb30376 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -301,6 +301,13 @@ struct ipv6_txoptions {
 	/* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
+/* flowlabel_reflect sysctl values */
+enum flowlabel_reflect {
+	FLOWLABEL_REFLECT_ESTABLISHED		= 1,
+	FLOWLABEL_REFLECT_TCP_RESET		= 2,
+	FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES	= 4,
+};
+
 struct ip6_flowlabel {
 	struct ip6_flowlabel __rcu *next;
 	__be32			label;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7382a927d1eb..8369af32cef6 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -208,7 +208,7 @@ lookup_protocol:
 	np->mc_loop	= 1;
 	np->mc_all	= 1;
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
-	np->repflow	= net->ipv6.sysctl.flowlabel_reflect & 1;
+	np->repflow	= net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED;
 	sk->sk_ipv6only	= net->ipv6.sysctl.bindv6only;
 
 	/* Init the ipv4 part of the socket since we can have sockets
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 12906301ec7b..62c997201970 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -703,6 +703,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY;
 
 	memset(&fl6, 0, sizeof(fl6));
+	if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
+		fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb));
+
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
 	fl6.daddr = ipv6_hdr(skb)->saddr;
 	if (saddr)
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 6d86fac472e7..8b3fe81783ed 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -23,7 +23,7 @@
 
 static int zero;
 static int one = 1;
-static int three = 3;
+static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_min;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
 
@@ -116,7 +116,7 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 		.extra1		= &zero,
-		.extra2		= &three,
+		.extra2		= &flowlabel_reflect_max,
 	},
 	{
 		.procname	= "max_dst_opts_number",
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 408d9ec26971..4f3f99b39820 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -989,7 +989,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 		if (sk->sk_state == TCP_TIME_WAIT)
 			label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel);
 	} else {
-		if (net->ipv6.sysctl.flowlabel_reflect & 2)
+		if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET)
 			label = ip6_flowlabel(ipv6h);
 	}