From: Tonghao Zhang <tonghao@bamaicloud.com>
Date: Fri, 27 Jun 2025 13:49:30 +0000 (+0800)
Subject: net: bonding: send peer notify when failure recovery
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=2f9afffc399d450c68a4dbebd7865b8e631a3cff;p=thirdparty%2Flinux.git

net: bonding: send peer notify when failure recovery

In LACP mode with broadcast_neighbor enabled, after LACP protocol
recovery, the port can transmit packets. However, if the bond port
doesn't send gratuitous ARP/ND packets to the switch, the switch
won't return packets through the current interface. This causes
traffic imbalance. To resolve this issue, when LACP protocol recovers,
send ARP/ND packets if broadcast_neighbor is enabled.

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>
Signed-off-by: Tonghao Zhang <tonghao@bamaicloud.com>
Signed-off-by: Zengbing Tu <tuzengbing@didiglobal.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/3993652dc093fffa9504ce1c2448fb9dea31d2d2.1751031306.git.tonghao@bamaicloud.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---

diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index 14f7593d888d1..f8f5766703d4b 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -773,8 +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
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index a8d8aaa169fc0..2fca8e84ab100 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/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);
 	}
 }
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 12046ef515692..17c7542be6a55 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1237,17 +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;
 }