Merge branch 'bonding_monitor_locking'

Ding Tianhong says:

====================
bonding: patchset for rcu use in bonding

The slave list will add and del by bond_master_upper_dev_link() and
bond_upper_dev_unlink(), which will call call_netdevice_notifiers(),
even it is safe to call it in write bond lock now, but we can't sure
that whether it is safe later, because other drivers may deal
NETDEV_CHANGEUPPER in sleep way, so I didn't admit move the
bond_upper_dev_unlink() in write bond lock.

now the bond_for_each_slave only protect by rtnl_lock(), maybe use
bond_for_each_slave_rcu is a good way to protect slave list for bond,
but as a system slow path, it is no need to transform
bond_for_each_slave() to bond_for_each_slave_rcu() in slow path, so in
the patchset, I will remove the unused read bond lock for monitor
function, maybe it is a better way, I will wait to accept any relay
for it.

Thanks for the Veaceslav Falico opinion.

v2: add and modify commit for patchset and patch, it will be the first
step for the whole patchset.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 40 insertions, 89 deletions

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 187b1b7..d6fe00b 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2068,8 +2068,10 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	struct slave *slave;
 	struct port *port;
 
-	read_lock(&bond->lock);
-
+	if (!rtnl_trylock()) {
+		queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
+		return;
+	}
 	//check if there are any slaves
 	if (!bond_has_slaves(bond))
 		goto re_arm;
@@ -2122,9 +2124,8 @@ 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);
 }
 
 /**
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 0287240..5d79f5e 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1495,11 +1495,13 @@ void bond_alb_monitor(struct work_struct *work)
 	struct list_head *iter;
 	struct slave *slave;
 
-	read_lock(&bond->lock);
+	if (!rtnl_trylock())
+		goto re_arm;
 
 	if (!bond_has_slaves(bond)) {
 		bond_info->tx_rebalance_counter = 0;
 		bond_info->lp_counter = 0;
+		rtnl_unlock();
 		goto re_arm;
 	}
 
@@ -1548,16 +1550,6 @@ 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
@@ -1566,9 +1558,6 @@ 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) {
@@ -1591,10 +1580,9 @@ 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
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a141f40..535570e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2118,49 +2118,29 @@ 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;
 
-	read_lock(&bond->lock);
-
-	delay = msecs_to_jiffies(bond->params.miimon);
+	if (!rtnl_trylock())
+		goto re_arm;
 
-	if (!bond_has_slaves(bond))
+	if (!bond_has_slaves(bond)) {
+		rtnl_unlock();
 		goto re_arm;
+	}
 
 	should_notify_peers = bond_should_notify_peers(bond);
 
-	if (bond_miimon_inspect(bond)) {
-		read_unlock(&bond->lock);
-
-		/* Race avoidance with bond_close cancel of workqueue */
-		if (!rtnl_trylock()) {
-			read_lock(&bond->lock);
-			delay = 1;
-			should_notify_peers = false;
-			goto re_arm;
-		}
-
-		read_lock(&bond->lock);
-
+	if (bond_miimon_inspect(bond))
 		bond_miimon_commit(bond);
 
-		read_unlock(&bond->lock);
-		rtnl_unlock();	/* might sleep, hold no other locks */
-		read_lock(&bond->lock);
-	}
+	if (should_notify_peers)
+		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
+
+	rtnl_unlock();
 
 re_arm:
 	if (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();
-	}
+		queue_delayed_work(bond->wq, &bond->mii_work,
+				msecs_to_jiffies(bond->params.miimon));
 }
 
 static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
@@ -2416,10 +2396,13 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 	struct list_head *iter;
 	int do_failover = 0;
 
-	read_lock(&bond->lock);
+	if (!rtnl_trylock())
+		goto re_arm;
 
-	if (!bond_has_slaves(bond))
+	if (!bond_has_slaves(bond)) {
+		rtnl_unlock();
 		goto re_arm;
+	}
 
 	oldcurrent = bond->curr_active_slave;
 	/* see if any of the previous devices are up now (i.e. they have
@@ -2501,13 +2484,12 @@ 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);
 }
 
 /*
@@ -2744,51 +2726,31 @@ 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;
 
-	read_lock(&bond->lock);
-
-	delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval);
+	if (!rtnl_trylock())
+		goto re_arm;
 
-	if (!bond_has_slaves(bond))
+	if (!bond_has_slaves(bond)) {
+		rtnl_unlock();
 		goto re_arm;
+	}
 
 	should_notify_peers = bond_should_notify_peers(bond);
 
-	if (bond_ab_arp_inspect(bond)) {
-		read_unlock(&bond->lock);
-
-		/* 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;
-		}
-
-		read_lock(&bond->lock);
-
+	if (bond_ab_arp_inspect(bond))
 		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, delta_in_ticks);
+	if (should_notify_peers)
+		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
 
-	read_unlock(&bond->lock);
+	rtnl_unlock();
 
-	if (should_notify_peers) {
-		if (!rtnl_trylock())
-			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
-		rtnl_unlock();
-	}
+re_arm:
+	if (bond->params.arp_interval)
+		queue_delayed_work(bond->wq, &bond->arp_work,
+				msecs_to_jiffies(bond->params.arp_interval));
 }
 
 /*-------------------------- netdev event handling --------------------------*/