Merge branch 'net-ipv6-Add-support-for-path-selection-using-hash-of-5…

…-tuple'

David Ahern says:

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

Hardware supports multipath selection using the standard L4 5-tuple
instead of just L3 and the flow label. In addition, some network
operators prefer IPv6 path selection to use the 5-tuple. To that end,
add support to IPv6 for multipath hash policy similar to
bf4e0a3 ("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. This gives users a choice in
hash algorithms if they believe L3 only and the IPv6 flow label are not
sufficient for their use case.

A separate sysctl is added for IPv6, allowing IPv4 and IPv6 to use
different algorithms if desired.

The first 3 patches modify the IPv4 variant so that at the end of the
patch set the ipv4 and ipv6 implementations are direct parallels.

Patch 4 refactors the existing rt6_multipath_hash in preparation for
adding the policy option.

Patch 5 renames the existing netevent to have IPv4 in the name so ipv4
changes can be distinguished from IPv6 if the netevent handler cares.

Patch 6 adds the skb as an argument through the FIB lookup functions
to the multipath selection. Needed for the forwarding case.

Patch 7 adds the L4 hash support.

Patch 8 adds the hook for the netevent to the spectrum driver to update
the ASIC.

Patch 9 removes no longer used code.

Patch 10 adds a testcase for IPv6 multipath with L4 hash.

v3
- comments from Ido:
  - removed fib_info arg in patch 1; left by mistake on rebase to net-next
  - removed __get_hash_from_flowi4 declaration
  - line wrap change to spectrum_router.c to maintain 80 chars

v2
- rebased to top of tree
- added refactor of fib_multipath_hash following recent change
- plumb skb through lookup functions to multipath selection
- fix sysctl setting; was missing the data set in ipv6_sysctl_net_init
- added test case

RFC to v1:
- rebase to top of net-next
- fix addr_type in hash_keys and removed flow label as noticed by Ido
- added a comment to cover letter about choice in algorithms based on
  use case per Or's comments
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

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

drivers/infiniband/core/cma.c

@@ -1334,7 +1334,7 @@ static bool validate_ipv6_net_dev(struct net_device *net_dev,
 			   IPV6_ADDR_LINKLOCAL;
 	struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr,
 					 &src_addr->sin6_addr, net_dev->ifindex,
-					 strict);
+					 NULL, strict);
 	bool ret;
 
 	if (!rt)

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -2430,7 +2430,8 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		mlxsw_core_schedule_work(&net_work->work);
 		mlxsw_sp_port_dev_put(mlxsw_sp_port);
 		break;
-	case NETEVENT_MULTIPATH_HASH_UPDATE:
+	case NETEVENT_IPV4_MPATH_HASH_UPDATE:
+	case NETEVENT_IPV6_MPATH_HASH_UPDATE:
 		net = ptr;
 
 		if (!net_eq(net, &init_net))
@@ -7030,13 +7031,25 @@ static void mlxsw_sp_mp4_hash_init(char *recr2_pl)
 
 static void mlxsw_sp_mp6_hash_init(char *recr2_pl)
 {
+	bool only_l3 = !init_net.ipv6.sysctl.multipath_hash_policy;
+
 	mlxsw_sp_mp_hash_header_set(recr2_pl,
 				    MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP);
 	mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_TCP_UDP);
 	mlxsw_reg_recr2_ipv6_sip_enable(recr2_pl);
 	mlxsw_reg_recr2_ipv6_dip_enable(recr2_pl);
-	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_FLOW_LABEL);
 	mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_NEXT_HEADER);
+	if (only_l3) {
+		mlxsw_sp_mp_hash_field_set(recr2_pl,
+					   MLXSW_REG_RECR2_IPV6_FLOW_LABEL);
+	} else {
+		mlxsw_sp_mp_hash_header_set(recr2_pl,
+					    MLXSW_REG_RECR2_TCP_UDP_EN_IPV6);
+		mlxsw_sp_mp_hash_field_set(recr2_pl,
+					   MLXSW_REG_RECR2_TCP_UDP_SPORT);
+		mlxsw_sp_mp_hash_field_set(recr2_pl,
+					   MLXSW_REG_RECR2_TCP_UDP_DPORT);
+	}
 }
 
 static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp)

drivers/net/ipvlan/ipvlan_core.c

@@ -817,7 +817,8 @@ struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb,
 		};
 
 		skb_dst_drop(skb);
-		dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, flags);
+		dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6,
+					     skb, flags);
 		skb_dst_set(skb, dst);
 		break;
 	}

drivers/net/vrf.c

@@ -941,6 +941,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
 					     const struct net_device *dev,
 					     struct flowi6 *fl6,
 					     int ifindex,
+					     const struct sk_buff *skb,
 					     int flags)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
@@ -959,7 +960,7 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
 	if (!table)
 		return NULL;
 
-	return ip6_pol_route(net, table, ifindex, fl6, flags);
+	return ip6_pol_route(net, table, ifindex, fl6, skb, flags);
 }
 
 static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
@@ -977,7 +978,7 @@ static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
 	struct net *net = dev_net(vrf_dev);
 	struct rt6_info *rt6;
 
-	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex,
+	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
 				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
 	if (unlikely(!rt6))
 		return;
@@ -1110,7 +1111,7 @@ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev,
 	if (!ipv6_addr_any(&fl6->saddr))
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, flags);
+	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags);
 	if (rt)
 		dst = &rt->dst;
 

include/net/fib_rules.h

@@ -47,6 +47,7 @@ struct fib_rule {
 
 struct fib_lookup_arg {
 	void			*lookup_ptr;
+	const void		*lookup_data;
 	void			*result;
 	struct fib_rule		*rule;
 	u32			table;

include/net/flow.h

@@ -222,20 +222,4 @@ static inline unsigned int flow_key_size(u16 family)
 
 __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys);
 
-static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6)
-{
-	struct flow_keys keys;
-
-	return __get_hash_from_flowi6(fl6, &keys);
-}
-
-__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys);
-
-static inline __u32 get_hash_from_flowi4(const struct flowi4 *fl4)
-{
-	struct flow_keys keys;
-
-	return __get_hash_from_flowi4(fl4, &keys);
-}
-
 #endif

include/net/ip6_fib.h

@@ -350,7 +350,8 @@ struct fib6_table {
 
 typedef struct rt6_info *(*pol_lookup_t)(struct net *,
 					 struct fib6_table *,
-					 struct flowi6 *, int);
+					 struct flowi6 *,
+					 const struct sk_buff *, int);
 
 struct fib6_entry_notifier_info {
 	struct fib_notifier_info info; /* must be first */
@@ -364,6 +365,7 @@ struct fib6_entry_notifier_info {
 struct fib6_table *fib6_get_table(struct net *net, u32 id);
 struct fib6_table *fib6_new_table(struct net *net, u32 id);
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
 struct fib6_node *fib6_lookup(struct fib6_node *root,

include/net/ip6_route.h

@@ -75,7 +75,8 @@ static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt)
 void ip6_route_input(struct sk_buff *skb);
 struct dst_entry *ip6_route_input_lookup(struct net *net,
 					 struct net_device *dev,
-					 struct flowi6 *fl6, int flags);
+					 struct flowi6 *fl6,
+					 const struct sk_buff *skb, int flags);
 
 struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 					 struct flowi6 *fl6, int flags);
@@ -88,9 +89,10 @@ static inline struct dst_entry *ip6_route_output(struct net *net,
 }
 
 struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
-				   int flags);
+				   const struct sk_buff *skb, int flags);
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
-			       int ifindex, struct flowi6 *fl6, int flags);
+			       int ifindex, struct flowi6 *fl6,
+			       const struct sk_buff *skb, int flags);
 
 void ip6_route_init_special_entries(void);
 int ip6_route_init(void);
@@ -126,9 +128,10 @@ 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, int flags);
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
-		       struct flow_keys *hkeys);
+			    const struct in6_addr *saddr, int oif,
+			    const struct sk_buff *skb, int flags);
+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);
 

include/net/ip_fib.h

@@ -395,7 +395,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local);
 int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys);
 #endif
 void fib_select_multipath(struct fib_result *res, int hash);

include/net/netevent.h

@@ -26,7 +26,8 @@ enum netevent_notif_type {
 	NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */
 	NETEVENT_REDIRECT,	   /* arg is struct netevent_redirect ptr */
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
-	NETEVENT_MULTIPATH_HASH_UPDATE, /* arg is struct net 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);

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;

net/core/flow_dissector.c

@@ -1341,22 +1341,6 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys)
 }
 EXPORT_SYMBOL(__get_hash_from_flowi6);
 
-__u32 __get_hash_from_flowi4(const struct flowi4 *fl4, struct flow_keys *keys)
-{
-	memset(keys, 0, sizeof(*keys));
-
-	keys->addrs.v4addrs.src = fl4->saddr;
-	keys->addrs.v4addrs.dst = fl4->daddr;
-	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-	keys->ports.src = fl4->fl4_sport;
-	keys->ports.dst = fl4->fl4_dport;
-	keys->keyid.keyid = fl4->fl4_gre_key;
-	keys->basic.ip_proto = fl4->flowi4_proto;
-
-	return flow_hash_from_keys(keys);
-}
-EXPORT_SYMBOL(__get_hash_from_flowi4);
-
 static const struct flow_dissector_key flow_keys_dissector_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,

net/ipv4/fib_semantics.c

@@ -1770,7 +1770,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, fl4, skb, NULL);
+		int h = fib_multipath_hash(net, fl4, skb, NULL);
 
 		fib_select_multipath(res, h);
 	}

net/ipv4/route.c

@@ -1748,44 +1748,45 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
 				 struct flow_keys *hash_keys)
 {
 	const struct iphdr *outer_iph = ip_hdr(skb);
+	const struct iphdr *key_iph = outer_iph;
 	const struct iphdr *inner_iph;
 	const struct icmphdr *icmph;
 	struct iphdr _inner_iph;
 	struct icmphdr _icmph;
 
-	hash_keys->addrs.v4addrs.src = outer_iph->saddr;
-	hash_keys->addrs.v4addrs.dst = outer_iph->daddr;
 	if (likely(outer_iph->protocol != IPPROTO_ICMP))
-		return;
+		goto out;
 
 	if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0))
-		return;
+		goto out;
 
 	icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph),
 				   &_icmph);
 	if (!icmph)
-		return;
+		goto out;
 
 	if (icmph->type != ICMP_DEST_UNREACH &&
 	    icmph->type != ICMP_REDIRECT &&
 	    icmph->type != ICMP_TIME_EXCEEDED &&
 	    icmph->type != ICMP_PARAMETERPROB)
-		return;
+		goto out;
 
 	inner_iph = skb_header_pointer(skb,
 				       outer_iph->ihl * 4 + sizeof(_icmph),
 				       sizeof(_inner_iph), &_inner_iph);
 	if (!inner_iph)
-		return;
-	hash_keys->addrs.v4addrs.src = inner_iph->saddr;
-	hash_keys->addrs.v4addrs.dst = inner_iph->daddr;
+		goto out;
+
+	key_iph = inner_iph;
+out:
+	hash_keys->addrs.v4addrs.src = key_iph->saddr;
+	hash_keys->addrs.v4addrs.dst = key_iph->daddr;
 }
 
 /* if skb is set it will be used and fl4 can be NULL */
-int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
+int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
-	struct net *net = fi->fib_net;
 	struct flow_keys hash_keys;
 	u32 mhash;
 
@@ -1809,24 +1810,20 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 			/* 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) {
-				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-				hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
-				hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.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 {
+			if (!flkeys) {
 				skb_flow_dissect_flow_keys(skb, &keys, flag);
-				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-				hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
-				hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
-				hash_keys.ports.src = keys.ports.src;
-				hash_keys.ports.dst = keys.ports.dst;
-				hash_keys.basic.ip_proto = keys.basic.ip_proto;
+				flkeys = &keys;
 			}
+
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+			hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
+			hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.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_IPV4_ADDRS;
@@ -1852,7 +1849,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, NULL, skb, hkeys);
+		int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
 	}

net/ipv4/sysctl_net_ipv4.c

@@ -400,7 +400,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net);
+		call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net);
 
 	return ret;
 }

net/ipv6/anycast.c

@@ -78,7 +78,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
-		rt = rt6_lookup(net, addr, NULL, 0, 0);
+		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
 			dev = rt->dst.dev;
 			ip6_rt_put(rt);