Browse Source

Revert "Merge branch 'bonding_monitor_locking'"

This reverts commit 4d961a101e032b4bf223b279b4b35bc77576f5a8, reversing
changes made to a00f6fcc7d0c62a91768d9c4ccba4c7d64fbbce3.

Revert bond locking changes, they cause regressions and Veaceslav Falico
doesn't like how the commit messages were done at all.

Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller 11 years ago
parent
commit
1f2cd845d3
3 changed files with 89 additions and 40 deletions
  1. 4 5
      drivers/net/bonding/bond_3ad.c
  2. 16 4
      drivers/net/bonding/bond_alb.c
  3. 69 31
      drivers/net/bonding/bond_main.c

+ 4 - 5
drivers/net/bonding/bond_3ad.c

@@ -2068,10 +2068,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	struct slave *slave;
 	struct port *port;
 
-	if (!rtnl_trylock()) {
-		queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
-		return;
-	}
+	read_lock(&bond->lock);
+
 	//check if there are any slaves
 	if (!bond_has_slaves(bond))
 		goto re_arm;
@@ -2124,8 +2122,9 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	}
 
 re_arm:
-	rtnl_unlock();
 	queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
+
+	read_unlock(&bond->lock);
 }
 
 /**

+ 16 - 4
drivers/net/bonding/bond_alb.c

@@ -1495,13 +1495,11 @@ void bond_alb_monitor(struct work_struct *work)
 	struct list_head *iter;
 	struct slave *slave;
 
-	if (!rtnl_trylock())
-		goto re_arm;
+	read_lock(&bond->lock);
 
 	if (!bond_has_slaves(bond)) {
 		bond_info->tx_rebalance_counter = 0;
 		bond_info->lp_counter = 0;
-		rtnl_unlock();
 		goto re_arm;
 	}
 
@@ -1550,6 +1548,16 @@ void bond_alb_monitor(struct work_struct *work)
 		if (bond_info->primary_is_promisc &&
 		    (++bond_info->rlb_promisc_timeout_counter >= RLB_PROMISC_TIMEOUT)) {
 
+			/*
+			 * dev_set_promiscuity requires rtnl and
+			 * nothing else.  Avoid race with bond_close.
+			 */
+			read_unlock(&bond->lock);
+			if (!rtnl_trylock()) {
+				read_lock(&bond->lock);
+				goto re_arm;
+			}
+
 			bond_info->rlb_promisc_timeout_counter = 0;
 
 			/* If the primary was set to promiscuous mode
@@ -1558,6 +1566,9 @@ void bond_alb_monitor(struct work_struct *work)
 			 */
 			dev_set_promiscuity(bond->curr_active_slave->dev, -1);
 			bond_info->primary_is_promisc = 0;
+
+			rtnl_unlock();
+			read_lock(&bond->lock);
 		}
 
 		if (bond_info->rlb_rebalance) {
@@ -1580,9 +1591,10 @@ void bond_alb_monitor(struct work_struct *work)
 		}
 	}
 
-	rtnl_unlock();
 re_arm:
 	queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks);
+
+	read_unlock(&bond->lock);
 }
 
 /* assumption: called before the slave is attached to the bond

+ 69 - 31
drivers/net/bonding/bond_main.c

@@ -2118,29 +2118,49 @@ void bond_mii_monitor(struct work_struct *work)
 	struct bonding *bond = container_of(work, struct bonding,
 					    mii_work.work);
 	bool should_notify_peers = false;
+	unsigned long delay;
 
-	if (!rtnl_trylock())
-		goto re_arm;
+	read_lock(&bond->lock);
 
-	if (!bond_has_slaves(bond)) {
-		rtnl_unlock();
+	delay = msecs_to_jiffies(bond->params.miimon);
+
+	if (!bond_has_slaves(bond))
 		goto re_arm;
-	}
 
 	should_notify_peers = bond_should_notify_peers(bond);
 
-	if (bond_miimon_inspect(bond))
-		bond_miimon_commit(bond);
+	if (bond_miimon_inspect(bond)) {
+		read_unlock(&bond->lock);
 
-	if (should_notify_peers)
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+		/* Race avoidance with bond_close cancel of workqueue */
+		if (!rtnl_trylock()) {
+			read_lock(&bond->lock);
+			delay = 1;
+			should_notify_peers = false;
+			goto re_arm;
+		}
 
-	rtnl_unlock();
+		read_lock(&bond->lock);
+
+		bond_miimon_commit(bond);
+
+		read_unlock(&bond->lock);
+		rtnl_unlock();	/* might sleep, hold no other locks */
+		read_lock(&bond->lock);
+	}
 
 re_arm:
 	if (bond->params.miimon)
-		queue_delayed_work(bond->wq, &bond->mii_work,
-				msecs_to_jiffies(bond->params.miimon));
+		queue_delayed_work(bond->wq, &bond->mii_work, delay);
+
+	read_unlock(&bond->lock);
+
+	if (should_notify_peers) {
+		if (!rtnl_trylock())
+			return;
+		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+		rtnl_unlock();
+	}
 }
 
 static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
@@ -2396,13 +2416,10 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 	struct list_head *iter;
 	int do_failover = 0;
 
-	if (!rtnl_trylock())
-		goto re_arm;
+	read_lock(&bond->lock);
 
-	if (!bond_has_slaves(bond)) {
-		rtnl_unlock();
+	if (!bond_has_slaves(bond))
 		goto re_arm;
-	}
 
 	oldcurrent = bond->curr_active_slave;
 	/* see if any of the previous devices are up now (i.e. they have
@@ -2484,12 +2501,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 	}
-	rtnl_unlock();
 
 re_arm:
 	if (bond->params.arp_interval)
 		queue_delayed_work(bond->wq, &bond->arp_work,
 				   msecs_to_jiffies(bond->params.arp_interval));
+
+	read_unlock(&bond->lock);
 }
 
 /*
@@ -2726,31 +2744,51 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 	struct bonding *bond = container_of(work, struct bonding,
 					    arp_work.work);
 	bool should_notify_peers = false;
+	int delta_in_ticks;
 
-	if (!rtnl_trylock())
-		goto re_arm;
+	read_lock(&bond->lock);
 
-	if (!bond_has_slaves(bond)) {
-		rtnl_unlock();
+	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
+
+	if (!bond_has_slaves(bond))
 		goto re_arm;
-	}
 
 	should_notify_peers = bond_should_notify_peers(bond);
 
-	if (bond_ab_arp_inspect(bond))
-		bond_ab_arp_commit(bond);
+	if (bond_ab_arp_inspect(bond)) {
+		read_unlock(&bond->lock);
 
-	bond_ab_arp_probe(bond);
+		/* Race avoidance with bond_close flush of workqueue */
+		if (!rtnl_trylock()) {
+			read_lock(&bond->lock);
+			delta_in_ticks = 1;
+			should_notify_peers = false;
+			goto re_arm;
+		}
 
-	if (should_notify_peers)
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+		read_lock(&bond->lock);
 
-	rtnl_unlock();
+		bond_ab_arp_commit(bond);
+
+		read_unlock(&bond->lock);
+		rtnl_unlock();
+		read_lock(&bond->lock);
+	}
+
+	bond_ab_arp_probe(bond);
 
 re_arm:
 	if (bond->params.arp_interval)
-		queue_delayed_work(bond->wq, &bond->arp_work,
-				msecs_to_jiffies(bond->params.arp_interval));
+		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
+
+	read_unlock(&bond->lock);
+
+	if (should_notify_peers) {
+		if (!rtnl_trylock())
+			return;
+		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+		rtnl_unlock();
+	}
 }
 
 /*-------------------------- netdev event handling --------------------------*/