net: bonding: fix possible peer notify event loss or dup issue

commit 10843e1 upstream.

If the send_peer_notif counter and the peer event notify are not synchronized.
It may cause problems such as the loss or dup of peer notify event.

Before this patch:
- If should_notify_peers is true and the lock for send_peer_notif-- fails, peer
  event may be sent again in next mii_monitor loop, because should_notify_peers
  is still true.
- If should_notify_peers is true and the lock for send_peer_notif-- succeeded,
  but the lock for peer event fails, the peer event will be lost.

This patch locks the RTNL for send_peer_notif, events, and commit simultaneously.

Fixes: 07a4dde ("bonding: add an option to specify a delay between peer notifications")
Cc: Jay Vosburgh <[email protected]>
Cc: Andrew Lunn <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Jakub Kicinski <[email protected]>
Cc: Paolo Abeni <[email protected]>
Cc: Hangbin Liu <[email protected]>
Cc: Nikolay Aleksandrov <[email protected]>
Cc: Vincent Bernat <[email protected]>
Cc: <[email protected]>
Signed-off-by: Tonghao Zhang <[email protected]>
Acked-by: Jay Vosburgh <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Paolo Abeni <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: hao022

drivers/net/bonding/bond_main.c

@@ -2951,7 +2951,7 @@ static void bond_mii_monitor(struct work_struct *work)
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    mii_work.work);
-	bool should_notify_peers = false;
+	bool should_notify_peers;
 	bool commit;
 	unsigned long delay;
 	struct slave *slave;
@@ -2963,44 +2963,40 @@ static void bond_mii_monitor(struct work_struct *work)
 		goto re_arm;
 
 	rcu_read_lock();
+
 	should_notify_peers = bond_should_notify_peers(bond);
 	commit = !!bond_miimon_inspect(bond);
-	if (bond->send_peer_notif) {
-		rcu_read_unlock();
-		if (rtnl_trylock()) {
-			bond->send_peer_notif--;
-			rtnl_unlock();
-		}
-	} else {
-		rcu_read_unlock();
-	}
 
-	if (commit) {
+	rcu_read_unlock();
+
+	if (commit || bond->send_peer_notif) {
 		/* Race avoidance with bond_close cancel of workqueue */
 		if (!rtnl_trylock()) {
 			delay = 1;
-			should_notify_peers = false;
 			goto re_arm;
 		}
 
-		bond_for_each_slave(bond, slave, iter) {
-			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		if (commit) {
+			bond_for_each_slave(bond, slave, iter) {
+				bond_commit_link_state(slave,
+						       BOND_SLAVE_NOTIFY_LATER);
+			}
+			bond_miimon_commit(bond);
+		}
+
+		if (bond->send_peer_notif) {
+			bond->send_peer_notif--;
+			if (should_notify_peers)
+				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+							 bond->dev);
 		}
-		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
 	}
 
 re_arm:
 	if (bond->params.miimon)
 		queue_delayed_work(bond->wq, &bond->mii_work, delay);
-
-	if (should_notify_peers) {
-		if (!rtnl_trylock())
-			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
-		rtnl_unlock();
-	}
 }
 
 static int bond_upper_dev_walk(struct net_device *upper,