ipv6: Implement automatic flow label generation on transmit (cb1ce2ef) · Commits · 戴 / test

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>

Documentation/networking/ip-sysctl.txt

+9 −0

Original line number	Diff line number	Diff line
		@@ -1132,6 +1132,15 @@ flowlabel_consistency - BOOLEAN
		FALSE: disabled
		Default: TRUE

		auto_flowlabels - BOOLEAN
		Automatically generate flow labels based based on a flow hash
		of the packet. This allows intermediate devices, such as routers,
		to idenfify packet flows for mechanisms like Equal Cost Multipath
		Routing (see RFC 6438).
		TRUE: enabled
		FALSE: disabled
		Default: false

		anycast_src_echo_reply - BOOLEAN
		Controls the use of anycast addresses as source addresses for ICMPv6
		echo reply

include/linux/ipv6.h

+2 −1

Original line number	Diff line number	Diff line
		@@ -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;

include/net/ipv6.h

+20 −0

Original line number	Diff line number	Diff line
		@@ -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
		*/

include/net/netns/ipv6.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -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;

include/uapi/linux/in6.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -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)

Admin message