ip: load balance tcp connections to single dst addr and port

Load balance new TCP connections across nexthops also when they
connect to the same service at a single remote address and port.

This affects only port-based multipath hashing:
fib_multipath_hash_policy 1 or 3.

Local connections must choose both a source address and port when
connecting to a remote service, in ip_route_connect. This
"chicken-and-egg problem" (commit 2d7192d ("ipv4: Sanitize and
simplify ip_route_{connect,newports}()")) is resolved by first
selecting a source address, by looking up a route using the zero
wildcard source port and address.

As a result multiple connections to the same destination address and
port have no entropy in fib_multipath_hash.

This is not a problem when forwarding, as skb-based hashing has a
4-tuple. Nor when establishing UDP connections, as autobind there
selects a port before reaching ip_route_connect.

Load balance also TCP, by using a random port in fib_multipath_hash.
Port assignment in inet_hash_connect is not atomic with
ip_route_connect. Thus ports are unpredictable, effectively random.

Implementation details:

Do not actually pass a random fl4_sport, as that affects not only
hashing, but routing more broadly, and can match a source port based
policy route, which existing wildcard port 0 will not. Instead,
define a new wildcard flowi flag that is used only for hashing.

Selecting a random source is equivalent to just selecting a random
hash entirely. But for code clarity, follow the normal 4-tuple hash
process and only update this field.

fib_multipath_hash can be reached with zero sport from other code
paths, so explicitly pass this flowi flag, rather than trying to infer
this case in the function itself.

Signed-off-by: Willem de Bruijn <[email protected]>
Reviewed-by: David Ahern <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
Reviewed-by: Ido Schimmel <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>

Author: wdebruij

include/net/flow.h

@@ -39,6 +39,7 @@ struct flowi_common {
 #define FLOWI_FLAG_ANYSRC		0x01
 #define FLOWI_FLAG_KNOWN_NH		0x02
 #define FLOWI_FLAG_L3MDEV_OIF		0x04
+#define FLOWI_FLAG_ANY_SPORT		0x08
 	__u32	flowic_secid;
 	kuid_t  flowic_uid;
 	__u32		flowic_multipath_hash;

include/net/route.h

@@ -326,6 +326,9 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst,
 	if (inet_test_bit(TRANSPARENT, sk))
 		flow_flags |= FLOWI_FLAG_ANYSRC;
 
+	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !sport)
+		flow_flags |= FLOWI_FLAG_ANY_SPORT;
+
 	flowi4_init_output(fl4, oif, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk), protocol, flow_flags, dst,
 			   src, dport, sport, sk->sk_uid);

net/ipv4/route.c

@@ -2037,8 +2037,12 @@ static u32 fib_multipath_custom_hash_fl4(const struct net *net,
 		hash_keys.addrs.v4addrs.dst = fl4->daddr;
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO)
 		hash_keys.basic.ip_proto = fl4->flowi4_proto;
-	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
-		hash_keys.ports.src = fl4->fl4_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+		if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT)
+			hash_keys.ports.src = (__force __be16)get_random_u16();
+		else
+			hash_keys.ports.src = fl4->fl4_sport;
+	}
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl4->fl4_dport;
 
@@ -2093,7 +2097,10 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 			hash_keys.addrs.v4addrs.src = fl4->saddr;
 			hash_keys.addrs.v4addrs.dst = fl4->daddr;
-			hash_keys.ports.src = fl4->fl4_sport;
+			if (fl4->flowi4_flags & FLOWI_FLAG_ANY_SPORT)
+				hash_keys.ports.src = (__force __be16)get_random_u16();
+			else
+				hash_keys.ports.src = fl4->fl4_sport;
 			hash_keys.ports.dst = fl4->fl4_dport;
 			hash_keys.basic.ip_proto = fl4->flowi4_proto;
 		}

net/ipv6/route.c

@@ -2492,8 +2492,12 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net,
 		hash_keys.basic.ip_proto = fl6->flowi6_proto;
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL)
 		hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
-	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT)
-		hash_keys.ports.src = fl6->fl6_sport;
+	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) {
+		if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+			hash_keys.ports.src = (__force __be16)get_random_u16();
+		else
+			hash_keys.ports.src = fl6->fl6_sport;
+	}
 	if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT)
 		hash_keys.ports.dst = fl6->fl6_dport;
 
@@ -2547,7 +2551,10 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			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;
+			if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT)
+				hash_keys.ports.src = (__force __be16)get_random_u16();
+			else
+				hash_keys.ports.src = fl6->fl6_sport;
 			hash_keys.ports.dst = fl6->fl6_dport;
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}

net/ipv6/tcp_ipv6.c

@@ -267,6 +267,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
+	if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport)
+		fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT;
 	fl6.flowi6_uid = sk->sk_uid;
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));