net/ipv6: Add support for path selection using hash of 5-tuple

Some operators prefer IPv6 path selection to use a standard 5-tuple
hash rather than just an L3 hash with the flow the label. To that end
add support to IPv6 for multipath hash policy similar to bf4e0a3db97eb
("net: ipv4: add support for ECMP hash policy choice"). The default
is still L3 which covers source and destination addresses along with
flow label and IPv6 protocol.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 91 insertions, 19 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a553d4e4a0fb..783675a730e5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1363,6 +1363,13 @@ flowlabel_reflect - BOOLEAN
 	FALSE: disabled
 	Default: FALSE
 
+fib_multipath_hash_policy - INTEGER
+	Controls which hash policy to use for multipath routes.
+	Default: 0 (Layer 3)
+	Possible values:
+	0 - Layer 3 (source and destination addresses plus flow label)
+	1 - Layer 4 (standard 5-tuple)
+
 anycast_src_echo_reply - BOOLEAN
 	Controls the use of anycast addresses as source addresses for ICMPv6
 	echo reply
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 9594f9317952..ce2abc0ff102 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -130,8 +130,8 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif,
 			    const struct sk_buff *skb, int flags);
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
-		       struct flow_keys *hkeys);
+u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
+		       const struct sk_buff *skb, struct flow_keys *hkeys);
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
 
diff --git a/include/net/netevent.h b/include/net/netevent.h
index baee605a94ab..d9918261701c 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -27,6 +27,7 @@ enum netevent_notif_type {
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
 	NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */
+	NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index e286fda09fcf..5b51110435fc 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -28,6 +28,7 @@ struct netns_sysctl_ipv6 {
 	int ip6_rt_gc_elasticity;
 	int ip6_rt_mtu_expires;
 	int ip6_rt_min_advmss;
+	int multipath_hash_policy;
 	int flowlabel_consistency;
 	int auto_flowlabels;
 	int icmpv6_time;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index a5d929223820..6f84668be6ea 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	fl6.mp_hash = rt6_multipath_hash(&fl6, skb, NULL);
+	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d2b8368663cb..f0ae58424c45 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -450,7 +450,8 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
+static struct rt6_info *rt6_multipath_select(const struct net *net,
+					     struct rt6_info *match,
 					     struct flowi6 *fl6, int oif,
 					     const struct sk_buff *skb,
 					     int strict)
@@ -461,7 +462,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
 	if (!fl6->mp_hash)
-		fl6->mp_hash = rt6_multipath_hash(fl6, skb, NULL);
+		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
 		return match;
@@ -932,7 +933,7 @@ restart:
 		rt = rt6_device_match(net, rt, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
 		if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
-			rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif,
+			rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
 						  skb, flags);
 	}
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -1674,7 +1675,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 redo_rt6_select:
 	rt = rt6_select(net, fn, oif, strict);
 	if (rt->rt6i_nsiblings)
-		rt = rt6_multipath_select(rt, fl6, oif, skb, strict);
+		rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
 	if (rt == net->ipv6.ip6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
@@ -1839,21 +1840,56 @@ out:
 }
 
 /* if skb is set it will be used and fl6 can be NULL */
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
-		       struct flow_keys *flkeys)
+u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
+		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	struct flow_keys hash_keys;
 	u32 mhash;
 
-	memset(&hash_keys, 0, sizeof(hash_keys));
-	hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	if (skb) {
-		ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
-	} else {
-		hash_keys.addrs.v6addrs.src = fl6->saddr;
-		hash_keys.addrs.v6addrs.dst = fl6->daddr;
-		hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
-		hash_keys.basic.ip_proto = fl6->flowi6_proto;
+	switch (net->ipv6.sysctl.multipath_hash_policy) {
+	case 0:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		if (skb) {
+			ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
+		} else {
+			hash_keys.addrs.v6addrs.src = fl6->saddr;
+			hash_keys.addrs.v6addrs.dst = fl6->daddr;
+			hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
+			hash_keys.basic.ip_proto = fl6->flowi6_proto;
+		}
+		break;
+	case 1:
+		if (skb) {
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			struct flow_keys keys;
+
+			/* short-circuit if we already have L4 hash present */
+			if (skb->l4_hash)
+				return skb_get_hash_raw(skb) >> 1;
+
+			memset(&hash_keys, 0, sizeof(hash_keys));
+
+                        if (!flkeys) {
+				skb_flow_dissect_flow_keys(skb, &keys, flag);
+				flkeys = &keys;
+			}
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src;
+			hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst;
+			hash_keys.ports.src = flkeys->ports.src;
+			hash_keys.ports.dst = flkeys->ports.dst;
+			hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
+		} else {
+			memset(&hash_keys, 0, sizeof(hash_keys));
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			hash_keys.addrs.v6addrs.src = fl6->saddr;
+			hash_keys.addrs.v6addrs.dst = fl6->daddr;
+			hash_keys.ports.src = fl6->fl6_sport;
+			hash_keys.ports.dst = fl6->fl6_dport;
+			hash_keys.basic.ip_proto = fl6->flowi6_proto;
+		}
+		break;
 	}
 	mhash = flow_hash_from_keys(&hash_keys);
 
@@ -1884,7 +1920,7 @@ void ip6_route_input(struct sk_buff *skb)
 		flkeys = &_flkeys;
 
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
-		fl6.mp_hash = rt6_multipath_hash(&fl6, skb, flkeys);
+		fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys);
 	skb_dst_drop(skb);
 	skb_dst_set(skb,
 		    ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags));
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 262f791f1b9b..966c42af92f4 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -16,14 +16,31 @@
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 #include <net/inet_frag.h>
+#include <net/netevent.h>
 #ifdef CONFIG_NETLABEL
 #include <net/calipso.h>
 #endif
 
+static int zero;
 static int one = 1;
 static int auto_flowlabels_min;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
 
+static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
+					  void __user *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	struct net *net;
+	int ret;
+
+	net = container_of(table->data, struct net,
+			   ipv6.sysctl.multipath_hash_policy);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net);
+
+	return ret;
+}
 
 static struct ctl_table ipv6_table_template[] = {
 	{
@@ -126,6 +143,15 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "fib_multipath_hash_policy",
+		.data		= &init_net.ipv6.sysctl.multipath_hash_policy,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler   = proc_rt6_multipath_hash_policy,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
@@ -190,6 +216,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net)
 	ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt;
 	ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len;
 	ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len;
+	ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy,
 
 	ipv6_route_table = ipv6_route_sysctl_init(net);
 	if (!ipv6_route_table)