net/bonding: Implement ndo_sk_get_lower_dev

Add ndo_sk_get_lower_dev() implementation for bond interfaces.

Support only for the cases where the socket's and SKBs' hash
yields identical value for the whole connection lifetime.

Here we restrict it to L3+4 sockets only, with
xmit_hash_policy==LAYER34 and bond modes xor/802.3ad.
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Boris Pismenny <borisp@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/bonding/bond_main.c

@@ -301,6 +301,19 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
 	return dev_queue_xmit(skb);
 }
 
+bool bond_sk_check(struct bonding *bond)
+{
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
+			return true;
+		fallthrough;
+	default:
+		return false;
+	}
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
@@ -4555,6 +4568,85 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
 	return NULL;
 }
 
+static void bond_sk_to_flow(struct sock *sk, struct flow_keys *flow)
+{
+	switch (sk->sk_family) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		if (sk->sk_ipv6only ||
+		    ipv6_addr_type(&sk->sk_v6_daddr) != IPV6_ADDR_MAPPED) {
+			flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			flow->addrs.v6addrs.src = inet6_sk(sk)->saddr;
+			flow->addrs.v6addrs.dst = sk->sk_v6_daddr;
+			break;
+		}
+		fallthrough;
+#endif
+	default: /* AF_INET */
+		flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+		flow->addrs.v4addrs.src = inet_sk(sk)->inet_rcv_saddr;
+		flow->addrs.v4addrs.dst = inet_sk(sk)->inet_daddr;
+		break;
+	}
+
+	flow->ports.src = inet_sk(sk)->inet_sport;
+	flow->ports.dst = inet_sk(sk)->inet_dport;
+}
+
+/**
+ * bond_sk_hash_l34 - generate a hash value based on the socket's L3 and L4 fields
+ * @sk: socket to use for headers
+ *
+ * This function will extract the necessary field from the socket and use
+ * them to generate a hash based on the LAYER34 xmit_policy.
+ * Assumes that sk is a TCP or UDP socket.
+ */
+static u32 bond_sk_hash_l34(struct sock *sk)
+{
+	struct flow_keys flow;
+	u32 hash;
+
+	bond_sk_to_flow(sk, &flow);
+
+	/* L4 */
+	memcpy(&hash, &flow.ports.ports, sizeof(hash));
+	/* L3 */
+	return bond_ip_hash(hash, &flow);
+}
+
+static struct net_device *__bond_sk_get_lower_dev(struct bonding *bond,
+						  struct sock *sk)
+{
+	struct bond_up_slave *slaves;
+	struct slave *slave;
+	unsigned int count;
+	u32 hash;
+
+	slaves = rcu_dereference(bond->usable_slaves);
+	count = slaves ? READ_ONCE(slaves->count) : 0;
+	if (unlikely(!count))
+		return NULL;
+
+	hash = bond_sk_hash_l34(sk);
+	slave = slaves->arr[hash % count];
+
+	return slave->dev;
+}
+
+static struct net_device *bond_sk_get_lower_dev(struct net_device *dev,
+						struct sock *sk)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct net_device *lower = NULL;
+
+	rcu_read_lock();
+	if (bond_sk_check(bond))
+		lower = __bond_sk_get_lower_dev(bond, sk);
+	rcu_read_unlock();
+
+	return lower;
+}
+
 static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
@@ -4691,6 +4783,7 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_fix_features	= bond_fix_features,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_xmit_slave	= bond_xmit_get_slave,
+	.ndo_sk_get_lower_dev	= bond_sk_get_lower_dev,
 };
 
 static const struct device_type bond_type = {

include/net/bonding.h

@@ -265,6 +265,8 @@ struct bond_vlan_tag {
 	unsigned short	vlan_id;
 };
 
+bool bond_sk_check(struct bonding *bond);
+
 /**
  * Returns NULL if the net_device does not belong to any of the bond's slaves
  *