Merge branch 'add-broadcast_neighbor-for-no-stacking-networking-arch'

Tonghao Zhang says:

====================
add broadcast_neighbor for no-stacking networking arch

For no-stacking networking arch, and enable the bond mode 4(lacp) in
datacenter, the switch require arp/nd packets as session synchronization.
More details please see patch.

Cc: Jay Vosburgh <jv@jvosburgh.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andrew Lunn <andrew+netdev@lunn.ch>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Cc: Zengbing Tu <tuzengbing@didiglobal.com>
====================

Link: https://patch.msgid.link/cover.1751031306.git.tonghao@bamaicloud.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Documentation/networking/bonding.rst

@@ -562,6 +562,12 @@ lacp_rate
 
 	The default is slow.
 
+broadcast_neighbor
+
+	Option specifying whether to broadcast ARP/ND packets to all
+	active slaves.  This option has no effect in modes other than
+	802.3ad mode.  The default is off (0).
+
 max_bonds
 
 	Specifies the number of bonding devices to create for this
@@ -767,8 +773,9 @@ num_unsol_na
 	greater than 1.
 
 	The valid range is 0 - 255; the default value is 1.  These options
-	affect only the active-backup mode.  These options were added for
-	bonding versions 3.3.0 and 3.4.0 respectively.
+	affect the active-backup or 802.3ad (broadcast_neighbor enabled) mode.
+	These options were added for bonding versions 3.3.0 and 3.4.0
+	respectively.
 
 	From Linux 3.0 and bonding version 3.7.1, these notifications
 	are generated by the ipv4 and ipv6 code and the numbers of

drivers/net/bonding/bond_3ad.c

@@ -982,6 +982,17 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker)
 	return 0;
 }
 
+static void ad_cond_set_peer_notif(struct port *port)
+{
+	struct bonding *bond = port->slave->bond;
+
+	if (bond->params.broadcast_neighbor && rtnl_trylock()) {
+		bond->send_peer_notif = bond->params.num_peer_notif *
+			max(1, bond->params.peer_notif_delay);
+		rtnl_unlock();
+	}
+}
+
 /**
  * ad_mux_machine - handle a port's mux state machine
  * @port: the port we're looking at
@@ -2062,6 +2073,8 @@ static void ad_enable_collecting_distributing(struct port *port,
 		__enable_port(port);
 		/* Slave array needs update */
 		*update_slave_arr = true;
+		/* Should notify peers if possible */
+		ad_cond_set_peer_notif(port);
 	}
 }
 

drivers/net/bonding/bond_main.c

@@ -212,6 +212,8 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
+DEFINE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled);
+
 static const struct flow_dissector_key flow_keys_bonding_keys[] = {
 	{
 		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
@@ -1235,17 +1237,32 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 /* must be called in RCU critical section or with RTNL held */
 static bool bond_should_notify_peers(struct bonding *bond)
 {
-	struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
+	struct bond_up_slave *usable;
+	struct slave *slave = NULL;
 
-	if (!slave || !bond->send_peer_notif ||
+	if (!bond->send_peer_notif ||
 	    bond->send_peer_notif %
 	    max(1, bond->params.peer_notif_delay) != 0 ||
-	    !netif_carrier_ok(bond->dev) ||
-	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
+	    !netif_carrier_ok(bond->dev))
 		return false;
 
+	/* The send_peer_notif is set by active-backup or 8023ad
+	 * mode, and cleared in bond_close() when changing mode.
+	 * It is safe to only check bond mode here.
+	 */
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+		usable = rcu_dereference_rtnl(bond->usable_slaves);
+		if (!usable || !READ_ONCE(usable->count))
+			return false;
+	} else {
+		slave = rcu_dereference_rtnl(bond->curr_active_slave);
+		if (!slave || test_bit(__LINK_STATE_LINKWATCH_PENDING,
+				       &slave->dev->state))
+			return false;
+	}
+
 	netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n",
-		   slave ? slave->dev->name : "NULL");
+		   slave ? slave->dev->name : "all");
 
 	return true;
 }
@@ -4456,6 +4473,9 @@ static int bond_open(struct net_device *bond_dev)
 
 		bond_for_each_slave(bond, slave, iter)
 			dev_mc_add(slave->dev, lacpdu_mcast_addr);
+
+		if (bond->params.broadcast_neighbor)
+			static_branch_inc(&bond_bcast_neigh_enabled);
 	}
 
 	if (bond_mode_can_use_xmit_hash(bond))
@@ -4475,6 +4495,10 @@ static int bond_close(struct net_device *bond_dev)
 		bond_alb_deinitialize(bond);
 	bond->recv_probe = NULL;
 
+	if (BOND_MODE(bond) == BOND_MODE_8023AD &&
+	    bond->params.broadcast_neighbor)
+		static_branch_dec(&bond_bcast_neigh_enabled);
+
 	if (bond_uses_primary(bond)) {
 		rcu_read_lock();
 		slave = rcu_dereference(bond->curr_active_slave);
@@ -5310,6 +5334,37 @@ static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond,
 	return slaves->arr[hash % count];
 }
 
+static bool bond_should_broadcast_neighbor(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct {
+		struct ipv6hdr ip6;
+		struct icmp6hdr icmp6;
+	} *combined, _combined;
+
+	if (!static_branch_unlikely(&bond_bcast_neigh_enabled))
+		return false;
+
+	if (!bond->params.broadcast_neighbor)
+		return false;
+
+	if (skb->protocol == htons(ETH_P_ARP))
+		return true;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		combined = skb_header_pointer(skb, skb_mac_header_len(skb),
+					      sizeof(_combined),
+					      &_combined);
+		if (combined && combined->ip6.nexthdr == NEXTHDR_ICMP &&
+		    (combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+		     combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT))
+			return true;
+	}
+
+	return false;
+}
+
 /* Use this Xmit function for 3AD as well as XOR modes. The current
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
@@ -5329,17 +5384,27 @@ static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb,
 	return bond_tx_drop(dev, skb);
 }
 
-/* in broadcast mode, we send everything to all usable interfaces. */
+/* in broadcast mode, we send everything to all or usable slave interfaces.
+ * under rcu_read_lock when this function is called.
+ */
 static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb,
-				       struct net_device *bond_dev)
+				       struct net_device *bond_dev,
+				       bool all_slaves)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave = NULL;
-	struct list_head *iter;
+	struct bond_up_slave *slaves;
 	bool xmit_suc = false;
 	bool skb_used = false;
+	int slaves_count, i;
 
-	bond_for_each_slave_rcu(bond, slave, iter) {
+	if (all_slaves)
+		slaves = rcu_dereference(bond->all_slaves);
+	else
+		slaves = rcu_dereference(bond->usable_slaves);
+
+	slaves_count = slaves ? READ_ONCE(slaves->count) : 0;
+	for (i = 0; i < slaves_count; i++) {
+		struct slave *slave = slaves->arr[i];
 		struct sk_buff *skb2;
 
 		if (!(bond_slave_is_up(slave) && slave->link == BOND_LINK_UP))
@@ -5577,10 +5642,13 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev
 	case BOND_MODE_ACTIVEBACKUP:
 		return bond_xmit_activebackup(skb, dev);
 	case BOND_MODE_8023AD:
+		if (bond_should_broadcast_neighbor(skb, dev))
+			return bond_xmit_broadcast(skb, dev, false);
+		fallthrough;
 	case BOND_MODE_XOR:
 		return bond_3ad_xor_xmit(skb, dev);
 	case BOND_MODE_BROADCAST:
-		return bond_xmit_broadcast(skb, dev);
+		return bond_xmit_broadcast(skb, dev, true);
 	case BOND_MODE_ALB:
 		return bond_alb_xmit(skb, dev);
 	case BOND_MODE_TLB:
@@ -6456,6 +6524,7 @@ static int __init bond_check_params(struct bond_params *params)
 	eth_zero_addr(params->ad_actor_system);
 	params->ad_user_port_key = ad_user_port_key;
 	params->coupled_control = 1;
+	params->broadcast_neighbor = 0;
 	if (packets_per_slave > 0) {
 		params->reciprocal_packets_per_slave =
 			reciprocal_value(packets_per_slave);

drivers/net/bonding/bond_netlink.c

@@ -124,6 +124,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_MISSED_MAX]		= { .type = NLA_U8 },
 	[IFLA_BOND_NS_IP6_TARGET]	= { .type = NLA_NESTED },
 	[IFLA_BOND_COUPLED_CONTROL]	= { .type = NLA_U8 },
+	[IFLA_BOND_BROADCAST_NEIGH]	= { .type = NLA_U8 },
 };
 
 static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
@@ -561,6 +562,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 			return err;
 	}
 
+	if (data[IFLA_BOND_BROADCAST_NEIGH]) {
+		int broadcast_neigh = nla_get_u8(data[IFLA_BOND_BROADCAST_NEIGH]);
+
+		bond_opt_initval(&newval, broadcast_neigh);
+		err = __bond_opt_set(bond, BOND_OPT_BROADCAST_NEIGH, &newval,
+				     data[IFLA_BOND_BROADCAST_NEIGH], extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -630,6 +641,7 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(struct nlattr)) +
 		nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS +
 		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_COUPLED_CONTROL */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_BROADCAST_NEIGH */
 		0;
 }
 
@@ -793,6 +805,10 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.coupled_control))
 		goto nla_put_failure;
 
+	if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH,
+		       bond->params.broadcast_neighbor))
+		goto nla_put_failure;
+
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info info;
 

drivers/net/bonding/bond_options.c

@@ -87,6 +87,8 @@ static int bond_option_missed_max_set(struct bonding *bond,
 				      const struct bond_opt_value *newval);
 static int bond_option_coupled_control_set(struct bonding *bond,
 					   const struct bond_opt_value *newval);
+static int bond_option_broadcast_neigh_set(struct bonding *bond,
+					   const struct bond_opt_value *newval);
 
 static const struct bond_opt_value bond_mode_tbl[] = {
 	{ "balance-rr",    BOND_MODE_ROUNDROBIN,   BOND_VALFLAG_DEFAULT},
@@ -240,6 +242,12 @@ static const struct bond_opt_value bond_coupled_control_tbl[] = {
 	{ NULL,  -1, 0},
 };
 
+static const struct bond_opt_value bond_broadcast_neigh_tbl[] = {
+	{ "off", 0, BOND_VALFLAG_DEFAULT},
+	{ "on",	 1, 0},
+	{ NULL,  -1, 0}
+};
+
 static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 	[BOND_OPT_MODE] = {
 		.id = BOND_OPT_MODE,
@@ -513,6 +521,14 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.flags = BOND_OPTFLAG_IFDOWN,
 		.values = bond_coupled_control_tbl,
 		.set = bond_option_coupled_control_set,
+	},
+	[BOND_OPT_BROADCAST_NEIGH] = {
+		.id = BOND_OPT_BROADCAST_NEIGH,
+		.name = "broadcast_neighbor",
+		.desc = "Broadcast neighbor packets to all active slaves",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.values = bond_broadcast_neigh_tbl,
+		.set = bond_option_broadcast_neigh_set,
 	}
 };
 
@@ -894,6 +910,13 @@ static int bond_option_mode_set(struct bonding *bond,
 	bond->params.arp_validate = BOND_ARP_VALIDATE_NONE;
 	bond->params.mode = newval->value;
 
+	/* When changing mode, the bond device is down, we may reduce
+	 * the bond_bcast_neigh_enabled in bond_close() if broadcast_neighbor
+	 * enabled in 8023ad mode. Therefore, only clear broadcast_neighbor
+	 * to 0.
+	 */
+	bond->params.broadcast_neighbor = 0;
+
 	if (bond->dev->reg_state == NETREG_REGISTERED) {
 		bool update = false;
 
@@ -1840,3 +1863,22 @@ static int bond_option_coupled_control_set(struct bonding *bond,
 	bond->params.coupled_control = newval->value;
 	return 0;
 }
+
+static int bond_option_broadcast_neigh_set(struct bonding *bond,
+					   const struct bond_opt_value *newval)
+{
+	if (bond->params.broadcast_neighbor == newval->value)
+		return 0;
+
+	bond->params.broadcast_neighbor = newval->value;
+	if (bond->dev->flags & IFF_UP) {
+		if (bond->params.broadcast_neighbor)
+			static_branch_inc(&bond_bcast_neigh_enabled);
+		else
+			static_branch_dec(&bond_bcast_neigh_enabled);
+	}
+
+	netdev_dbg(bond->dev, "Setting broadcast_neighbor to %s (%llu)\n",
+		   newval->string, newval->value);
+	return 0;
+}

include/net/bond_options.h

@@ -77,6 +77,7 @@ enum {
 	BOND_OPT_NS_TARGETS,
 	BOND_OPT_PRIO,
 	BOND_OPT_COUPLED_CONTROL,
+	BOND_OPT_BROADCAST_NEIGH,
 	BOND_OPT_LAST
 };
 

include/net/bonding.h

@@ -115,6 +115,8 @@ static inline int is_netpoll_tx_blocked(struct net_device *dev)
 #define is_netpoll_tx_blocked(dev) (0)
 #endif
 
+DECLARE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled);
+
 struct bond_params {
 	int mode;
 	int xmit_policy;
@@ -149,6 +151,7 @@ struct bond_params {
 	struct in6_addr ns_targets[BOND_MAX_NS_TARGETS];
 #endif
 	int coupled_control;
+	int broadcast_neighbor;
 
 	/* 2 bytes of padding : see ether_addr_equal_64bits() */
 	u8 ad_actor_system[ETH_ALEN + 2];

include/uapi/linux/if_link.h

@@ -1535,6 +1535,7 @@ enum {
 	IFLA_BOND_MISSED_MAX,
 	IFLA_BOND_NS_IP6_TARGET,
 	IFLA_BOND_COUPLED_CONTROL,
+	IFLA_BOND_BROADCAST_NEIGH,
 	__IFLA_BOND_MAX,
 };