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 <eduma...@google.com>
---
 Documentation/networking/ip-sysctl.txt | 4 +++-
 include/net/ipv6.h                     | 7 +++++++
 net/ipv6/af_inet6.c                    | 2 +-
 net/ipv6/icmp.c                        | 3 +++
 net/ipv6/sysctl_net_ipv6.c             | 4 ++--
 net/ipv6/tcp_ipv6.c                    | 2 +-
 6 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt 
b/Documentation/networking/ip-sysctl.txt
index 
e0d8a96e2c671e3d09d234c8ed49799b08240259..f0e6d1f53485d6cbfcd73c9cd079b970d976b6d9
 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 
b41f6a0fa903e9916e293f86f8bfb0f264161e80..8eca5fb30376f3a0a40ff0dc438cbad9ff56142a
 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 
7382a927d1eb74a6bbf4d5f83de336ccab5a2ae2..8369af32cef619b5d8fd2fcfaeb12924941d4ae8
 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -208,7 +208,7 @@ static int inet6_create(struct net *net, struct socket 
*sock, int 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 
12906301ec7baedcccfba224b93d30cb6060c3b9..62c997201970a664cbcfd526d426af07ae019b0e
 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 
6d86fac472e7298cbd8df7aa0b190cf0087675e2..8b3fe81783ed945e2f9172fd9008f48fed474475
 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 
408d9ec2697154e840a26675765e8a9c1636ada4..4f3f99b3982099b3c64669f0445bc68d27390c89
 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);
        }
 
-- 
2.22.0.410.gd8fdbe21b5-goog

Reply via email to