ipv6: Implement automatic flow label generation on transmit

Automatically generate flow labels for IPv6 packets on transmit.
The flow label is computed based on skb_get_hash. The flow label will
only automatically be set when it is zero otherwise (i.e. flow label
manager hasn't set one). This supports the transmit side functionality
of RFC 6438.

Added an IPv6 sysctl auto_flowlabels to enable/disable this behavior
system wide, and added IPV6_AUTOFLOWLABEL socket option to enable this
functionality per socket.

By default, auto flowlabels are disabled to avoid possible conflicts
with flow label manager, however if this feature proves useful we
may want to enable it by default.

It should also be noted that FreeBSD has already implemented automatic
flow labels (including the sysctl and socket option). In FreeBSD,
automatic flow labels default to enabled.

Performance impact:

Running super_netperf with 200 flows for TCP_RR and UDP_RR for
IPv6. Note that in UDP case, __skb_get_hash will be called for
every packet with explains slight regression. In the TCP case
the hash is saved in the socket so there is no regression.

Automatic flow labels disabled:

  TCP_RR:
    86.53% CPU utilization
    127/195/322 90/95/99% latencies
    1.40498e+06 tps

  UDP_RR:
    90.70% CPU utilization
    118/168/243 90/95/99% latencies
    1.50309e+06 tps

Automatic flow labels enabled:

  TCP_RR:
    85.90% CPU utilization
    128/199/337 90/95/99% latencies
    1.40051e+06

  UDP_RR
    92.61% CPU utilization
    115/164/236 90/95/99% latencies
    1.4687e+06

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 24 insertions, 1 deletions

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5dc68c3ebcbd..ff560537dd61 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -199,7 +199,8 @@ struct ipv6_pinfo {
                                                  * 010: prefer public address
                                                  * 100: prefer care-of address
                                                  */
-                                dontfrag:1;
+                                dontfrag:1,
+                                autoflowlabel:1;
         __u8                    min_hopcount;
         __u8                    tclass;
         __be32                  rcv_flowinfo;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 2aa86e1135a1..4308f2ada8b3 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -699,6 +699,26 @@ static inline void ip6_set_txhash(struct sock *sk)
         sk->sk_txhash = flow_hash_from_keys(&keys);
 }
 
+static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
+                                        __be32 flowlabel, bool autolabel)
+{
+        if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
+                __be32 hash;
+
+                hash = skb_get_hash(skb);
+
+                /* Since this is being sent on the wire obfuscate hash a bit
+                 * to minimize possbility that any useful information to an
+                 * attacker is leaked. Only lower 20 bits are relevant.
+                 */
+                hash ^= hash >> 12;
+
+                flowlabel = hash & IPV6_FLOWLABEL_MASK;
+        }
+
+        return flowlabel;
+}
+
 /*
  *      Header manipulation
  */
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 19d3446e59d2..eade27adecf3 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -28,6 +28,7 @@ struct netns_sysctl_ipv6 {
         int ip6_rt_mtu_expires;
         int ip6_rt_min_advmss;
         int flowlabel_consistency;
+        int auto_flowlabels;
         int icmpv6_time;
         int anycast_src_echo_reply;
         int fwmark_reflect;
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index 0d8e0f0342dc..22b7a69619d8 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -233,6 +233,7 @@ struct in6_flowlabel_req {
 #if 0   /* not yet */
 #define IPV6_USE_MIN_MTU        63
 #endif
+#define IPV6_AUTOFLOWLABEL      64
 
 /*
  * Netfilter (1)