Merge branch 'bonding-next'

Nikolay Aleksandrov says:

====================
bonding: get rid of curr_slave_lock

This is the second patch-set dealing with bond locking and the purpose here
is to convert curr_slave_lock into a spinlock called "mode_lock" which can
be used in the various modes for their specific needs. The first three
patches cleanup the use of curr_slave_lock and prepare it for the
conversion which is done in patch 4 and then the modes that were using
their own locks are converted to use the new "mode_lock" giving us the
opportunity to remove their locks.
This patch-set has been tested in each mode by running enslave/release of
slaves in parallel with traffic transmission and miimon=1 i.e. running
all the time. In fact this lead to the discovery of a subtle bug related to
RCU which will be fixed in -net.
Also did an allmodconfig test just in case :-)

v2: fix bond_3ad_state_machine_handler's use of mode_lock and
    curr_slave_lock
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bonding/bond_3ad.c

@@ -233,24 +233,6 @@ static inline int __check_agg_selection_timer(struct port *port)
 	return BOND_AD_INFO(bond).agg_select_timer ? 1 : 0;
 }
 
-/**
- * __get_state_machine_lock - lock the port's state machines
- * @port: the port we're looking at
- */
-static inline void __get_state_machine_lock(struct port *port)
-{
-	spin_lock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock));
-}
-
-/**
- * __release_state_machine_lock - unlock the port's state machines
- * @port: the port we're looking at
- */
-static inline void __release_state_machine_lock(struct port *port)
-{
-	spin_unlock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock));
-}
-
 /**
  * __get_link_speed - get a port's speed
  * @port: the port we're looking at
@@ -341,16 +323,6 @@ static u8 __get_duplex(struct port *port)
 	return retval;
 }
 
-/**
- * __initialize_port_locks - initialize a port's STATE machine spinlock
- * @port: the slave of the port we're looking at
- */
-static inline void __initialize_port_locks(struct slave *slave)
-{
-	/* make sure it isn't called twice */
-	spin_lock_init(&(SLAVE_AD_INFO(slave)->state_machine_lock));
-}
-
 /* Conversions */
 
 /**
@@ -1843,7 +1815,6 @@ void bond_3ad_bind_slave(struct slave *slave)
 
 		ad_initialize_port(port, bond->params.lacp_fast);
 
-		__initialize_port_locks(slave);
 		port->slave = slave;
 		port->actor_port_number = SLAVE_AD_INFO(slave)->id;
 		/* key is determined according to the link speed, duplex and user key(which
@@ -1899,6 +1870,8 @@ void bond_3ad_unbind_slave(struct slave *slave)
 	struct slave *slave_iter;
 	struct list_head *iter;
 
+	/* Sync against bond_3ad_state_machine_handler() */
+	spin_lock_bh(&bond->mode_lock);
 	aggregator = &(SLAVE_AD_INFO(slave)->aggregator);
 	port = &(SLAVE_AD_INFO(slave)->port);
 
@@ -1906,7 +1879,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
 	if (!port->slave) {
 		netdev_warn(bond->dev, "Trying to unbind an uninitialized port on %s\n",
 			    slave->dev->name);
-		return;
+		goto out;
 	}
 
 	netdev_dbg(bond->dev, "Unbinding Link Aggregation Group %d\n",
@@ -2032,6 +2005,9 @@ void bond_3ad_unbind_slave(struct slave *slave)
 		}
 	}
 	port->slave = NULL;
+
+out:
+	spin_unlock_bh(&bond->mode_lock);
 }
 
 /**
@@ -2057,7 +2033,11 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	struct port *port;
 	bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER;
 
-	read_lock(&bond->curr_slave_lock);
+	/* Lock to protect data accessed by all (e.g., port->sm_vars) and
+	 * against running with bond_3ad_unbind_slave. ad_rx_machine may run
+	 * concurrently due to incoming LACPDU as well.
+	 */
+	spin_lock_bh(&bond->mode_lock);
 	rcu_read_lock();
 
 	/* check if there are any slaves */
@@ -2093,12 +2073,6 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 			goto re_arm;
 		}
 
-		/* Lock around state machines to protect data accessed
-		 * by all (e.g., port->sm_vars).  ad_rx_machine may run
-		 * concurrently due to incoming LACPDU.
-		 */
-		__get_state_machine_lock(port);
-
 		ad_rx_machine(NULL, port);
 		ad_periodic_machine(port);
 		ad_port_selection_logic(port);
@@ -2108,8 +2082,6 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		/* turn off the BEGIN bit, since we already handled it */
 		if (port->sm_vars & AD_PORT_BEGIN)
 			port->sm_vars &= ~AD_PORT_BEGIN;
-
-		__release_state_machine_lock(port);
 	}
 
 re_arm:
@@ -2120,7 +2092,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		}
 	}
 	rcu_read_unlock();
-	read_unlock(&bond->curr_slave_lock);
+	spin_unlock_bh(&bond->mode_lock);
 
 	if (should_notify_rtnl && rtnl_trylock()) {
 		bond_slave_state_notify(bond);
@@ -2161,9 +2133,9 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave,
 			netdev_dbg(slave->bond->dev, "Received LACPDU on port %d\n",
 				   port->actor_port_number);
 			/* Protect against concurrent state machines */
-			__get_state_machine_lock(port);
+			spin_lock(&slave->bond->mode_lock);
 			ad_rx_machine(lacpdu, port);
-			__release_state_machine_lock(port);
+			spin_unlock(&slave->bond->mode_lock);
 			break;
 
 		case AD_TYPE_MARKER:
@@ -2213,7 +2185,7 @@ void bond_3ad_adapter_speed_changed(struct slave *slave)
 		return;
 	}
 
-	__get_state_machine_lock(port);
+	spin_lock_bh(&slave->bond->mode_lock);
 
 	port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS;
 	port->actor_oper_port_key = port->actor_admin_port_key |=
@@ -2224,7 +2196,7 @@ void bond_3ad_adapter_speed_changed(struct slave *slave)
 	 */
 	port->sm_vars |= AD_PORT_BEGIN;
 
-	__release_state_machine_lock(port);
+	spin_unlock_bh(&slave->bond->mode_lock);
 }
 
 /**
@@ -2246,7 +2218,7 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave)
 		return;
 	}
 
-	__get_state_machine_lock(port);
+	spin_lock_bh(&slave->bond->mode_lock);
 
 	port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS;
 	port->actor_oper_port_key = port->actor_admin_port_key |=
@@ -2257,7 +2229,7 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave)
 	 */
 	port->sm_vars |= AD_PORT_BEGIN;
 
-	__release_state_machine_lock(port);
+	spin_unlock_bh(&slave->bond->mode_lock);
 }
 
 /**
@@ -2280,7 +2252,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 		return;
 	}
 
-	__get_state_machine_lock(port);
+	spin_lock_bh(&slave->bond->mode_lock);
 	/* on link down we are zeroing duplex and speed since
 	 * some of the adaptors(ce1000.lan) report full duplex/speed
 	 * instead of N/A(duplex) / 0(speed).
@@ -2311,7 +2283,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 	 */
 	port->sm_vars |= AD_PORT_BEGIN;
 
-	__release_state_machine_lock(port);
+	spin_unlock_bh(&slave->bond->mode_lock);
 }
 
 /**
@@ -2476,20 +2448,16 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave)
 {
-	int ret = RX_HANDLER_ANOTHER;
 	struct lacpdu *lacpdu, _lacpdu;
 
 	if (skb->protocol != PKT_TYPE_LACPDU)
-		return ret;
+		return RX_HANDLER_ANOTHER;
 
 	lacpdu = skb_header_pointer(skb, 0, sizeof(_lacpdu), &_lacpdu);
 	if (!lacpdu)
-		return ret;
+		return RX_HANDLER_ANOTHER;
 
-	read_lock(&bond->curr_slave_lock);
-	ret = bond_3ad_rx_indication(lacpdu, slave, skb->len);
-	read_unlock(&bond->curr_slave_lock);
-	return ret;
+	return bond_3ad_rx_indication(lacpdu, slave, skb->len);
 }
 
 /**
@@ -2499,7 +2467,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
  * When modify lacp_rate parameter via sysfs,
  * update actor_oper_port_state of each port.
  *
- * Hold slave->state_machine_lock,
+ * Hold bond->mode_lock,
  * so we can modify port->actor_oper_port_state,
  * no matter bond is up or down.
  */
@@ -2511,13 +2479,13 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 	int lacp_fast;
 
 	lacp_fast = bond->params.lacp_fast;
+	spin_lock_bh(&bond->mode_lock);
 	bond_for_each_slave(bond, slave, iter) {
 		port = &(SLAVE_AD_INFO(slave)->port);
-		__get_state_machine_lock(port);
 		if (lacp_fast)
 			port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT;
 		else
 			port->actor_oper_port_state &= ~AD_STATE_LACP_TIMEOUT;
-		__release_state_machine_lock(port);
 	}
+	spin_unlock_bh(&bond->mode_lock);
 }

drivers/net/bonding/bond_3ad.h

@@ -259,7 +259,6 @@ struct ad_bond_info {
 struct ad_slave_info {
 	struct aggregator aggregator;	/* 802.3ad aggregator structure */
 	struct port port;		/* 802.3ad port structure */
-	spinlock_t state_machine_lock;	/* mutex state machines vs. incoming LACPDU */
 	u16 id;
 };
 

drivers/net/bonding/bond_alb.h

@@ -147,7 +147,6 @@ struct tlb_up_slave {
 
 struct alb_bond_info {
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
-	spinlock_t		tx_hashtbl_lock;
 	u32			unbalanced_load;
 	int			tx_rebalance_counter;
 	int			lp_counter;
@@ -156,7 +155,6 @@ struct alb_bond_info {
 	/* -------- rlb parameters -------- */
 	int rlb_enabled;
 	struct rlb_client_info	*rx_hashtbl;	/* Receive hash table */
-	spinlock_t		rx_hashtbl_lock;
 	u32			rx_hashtbl_used_head;
 	u8			rx_ntt;	/* flag - need to transmit
 					 * to all rx clients

drivers/net/bonding/bond_debugfs.c

@@ -29,7 +29,7 @@ static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
 	seq_printf(m, "SourceIP        DestinationIP   "
 			"Destination MAC   DEV\n");
 
-	spin_lock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+	spin_lock_bh(&bond->mode_lock);
 
 	hash_index = bond_info->rx_hashtbl_used_head;
 	for (; hash_index != RLB_NULL_INDEX;
@@ -42,7 +42,7 @@ static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
 			client_info->slave->dev->name);
 	}
 
-	spin_unlock_bh(&(BOND_ALB_INFO(bond).rx_hashtbl_lock));
+	spin_unlock_bh(&bond->mode_lock);
 
 	return 0;
 }

drivers/net/bonding/bond_main.c

@@ -637,13 +637,11 @@ static void bond_set_dev_addr(struct net_device *bond_dev,
  *
  * Perform special MAC address swapping for fail_over_mac settings
  *
- * Called with RTNL, curr_slave_lock for write_bh.
+ * Called with RTNL
  */
 static void bond_do_fail_over_mac(struct bonding *bond,
 				  struct slave *new_active,
 				  struct slave *old_active)
-	__releases(&bond->curr_slave_lock)
-	__acquires(&bond->curr_slave_lock)
 {
 	u8 tmp_mac[ETH_ALEN];
 	struct sockaddr saddr;
@@ -651,11 +649,8 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 
 	switch (bond->params.fail_over_mac) {
 	case BOND_FOM_ACTIVE:
-		if (new_active) {
-			write_unlock_bh(&bond->curr_slave_lock);
+		if (new_active)
 			bond_set_dev_addr(bond->dev, new_active->dev);
-			write_lock_bh(&bond->curr_slave_lock);
-		}
 		break;
 	case BOND_FOM_FOLLOW:
 		/*
@@ -666,8 +661,6 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 		if (!new_active)
 			return;
 
-		write_unlock_bh(&bond->curr_slave_lock);
-
 		if (old_active) {
 			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
 			ether_addr_copy(saddr.sa_data,
@@ -696,7 +689,6 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			netdev_err(bond->dev, "Error %d setting MAC of slave %s\n",
 				   -rv, new_active->dev->name);
 out:
-		write_lock_bh(&bond->curr_slave_lock);
 		break;
 	default:
 		netdev_err(bond->dev, "bond_do_fail_over_mac impossible: bad policy %d\n",
@@ -709,7 +701,7 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 static bool bond_should_change_active(struct bonding *bond)
 {
 	struct slave *prim = rtnl_dereference(bond->primary_slave);
-	struct slave *curr = bond_deref_active_protected(bond);
+	struct slave *curr = rtnl_dereference(bond->curr_active_slave);
 
 	if (!prim || !curr || curr->link != BOND_LINK_UP)
 		return true;
@@ -785,15 +777,15 @@ static bool bond_should_notify_peers(struct bonding *bond)
  * because it is apparently the best available slave we have, even though its
  * updelay hasn't timed out yet.
  *
- * If new_active is not NULL, caller must hold curr_slave_lock for write_bh.
+ * Caller must hold RTNL.
  */
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 {
 	struct slave *old_active;
 
-	old_active = rcu_dereference_protected(bond->curr_active_slave,
-					       !new_active ||
-					       lockdep_is_held(&bond->curr_slave_lock));
+	ASSERT_RTNL();
+
+	old_active = rtnl_dereference(bond->curr_active_slave);
 
 	if (old_active == new_active)
 		return;
@@ -861,14 +853,10 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 					bond_should_notify_peers(bond);
 			}
 
-			write_unlock_bh(&bond->curr_slave_lock);
-
 			call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev);
 			if (should_notify_peers)
 				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
 							 bond->dev);
-
-			write_lock_bh(&bond->curr_slave_lock);
 		}
 	}
 
@@ -893,7 +881,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
  * - The primary_slave has got its link back.
  * - A slave has got its link back and there's no old curr_active_slave.
  *
- * Caller must hold curr_slave_lock for write_bh.
+ * Caller must hold RTNL.
  */
 void bond_select_active_slave(struct bonding *bond)
 {
@@ -901,7 +889,7 @@ void bond_select_active_slave(struct bonding *bond)
 	int rv;
 
 	best_slave = bond_find_best_slave(bond);
-	if (best_slave != bond_deref_active_protected(bond)) {
+	if (best_slave != rtnl_dereference(bond->curr_active_slave)) {
 		bond_change_active_slave(bond, best_slave);
 		rv = bond_set_carrier(bond);
 		if (!rv)
@@ -1571,9 +1559,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 	if (bond_uses_primary(bond)) {
 		block_netpoll_tx();
-		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
-		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 	}
 
@@ -1601,10 +1587,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
 	if (rcu_access_pointer(bond->curr_active_slave) == new_slave) {
 		block_netpoll_tx();
-		write_lock_bh(&bond->curr_slave_lock);
 		bond_change_active_slave(bond, NULL);
 		bond_select_active_slave(bond);
-		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 	}
 	/* either primary_slave or curr_active_slave might've changed */
@@ -1645,7 +1629,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 /*
  * Try to release the slave device <slave> from the bond device <master>
  * It is legal to access curr_active_slave without a lock because all the function
- * is write-locked. If "all" is true it means that the function is being called
+ * is RTNL-locked. If "all" is true it means that the function is being called
  * while destroying a bond interface and all slaves are being released.
  *
  * The rules for slave state should be:
@@ -1691,14 +1675,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	 */
 	netdev_rx_handler_unregister(slave_dev);
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
-		/* Sync against bond_3ad_rx_indication and
-		 * bond_3ad_state_machine_handler
-		 */
-		write_lock_bh(&bond->curr_slave_lock);
+	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		bond_3ad_unbind_slave(slave);
-		write_unlock_bh(&bond->curr_slave_lock);
-	}
 
 	netdev_info(bond_dev, "Releasing %s interface %s\n",
 		    bond_is_active_slave(slave) ? "active" : "backup",
@@ -1720,11 +1698,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (rtnl_dereference(bond->primary_slave) == slave)
 		RCU_INIT_POINTER(bond->primary_slave, NULL);
 
-	if (oldcurrent == slave) {
-		write_lock_bh(&bond->curr_slave_lock);
+	if (oldcurrent == slave)
 		bond_change_active_slave(bond, NULL);
-		write_unlock_bh(&bond->curr_slave_lock);
-	}
 
 	if (bond_is_lb(bond)) {
 		/* Must be called only after the slave has been
@@ -1743,11 +1718,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 		 * is no concern that another slave add/remove event
 		 * will interfere.
 		 */
-		write_lock_bh(&bond->curr_slave_lock);
-
 		bond_select_active_slave(bond);
-
-		write_unlock_bh(&bond->curr_slave_lock);
 	}
 
 	if (!bond_has_slaves(bond)) {
@@ -2058,9 +2029,7 @@ static void bond_miimon_commit(struct bonding *bond)
 do_failover:
 		ASSERT_RTNL();
 		block_netpoll_tx();
-		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
-		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 	}
 
@@ -2506,15 +2475,8 @@ static void bond_loadbalance_arp_mon(struct work_struct *work)
 		if (slave_state_changed) {
 			bond_slave_state_change(bond);
 		} else if (do_failover) {
-			/* the bond_select_active_slave must hold RTNL
-			 * and curr_slave_lock for write.
-			 */
 			block_netpoll_tx();
-			write_lock_bh(&bond->curr_slave_lock);
-
 			bond_select_active_slave(bond);
-
-			write_unlock_bh(&bond->curr_slave_lock);
 			unblock_netpoll_tx();
 		}
 		rtnl_unlock();
@@ -2532,7 +2494,7 @@ static void bond_loadbalance_arp_mon(struct work_struct *work)
  * place for the slave.  Returns 0 if no changes are found, >0 if changes
  * to link states must be committed.
  *
- * Called with rcu_read_lock hold.
+ * Called with rcu_read_lock held.
  */
 static int bond_ab_arp_inspect(struct bonding *bond)
 {
@@ -2670,9 +2632,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 do_failover:
 		ASSERT_RTNL();
 		block_netpoll_tx();
-		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
-		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 	}
 
@@ -2682,7 +2642,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 /*
  * Send ARP probes for active-backup mode ARP monitor.
  *
- * Called with rcu_read_lock hold.
+ * Called with rcu_read_lock held.
  */
 static bool bond_ab_arp_probe(struct bonding *bond)
 {
@@ -2939,9 +2899,7 @@ static int bond_slave_netdev_event(unsigned long event,
 			    primary ? slave_dev->name : "none");
 
 		block_netpoll_tx();
-		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
-		write_unlock_bh(&bond->curr_slave_lock);
 		unblock_netpoll_tx();
 		break;
 	case NETDEV_FEAT_CHANGE:
@@ -3106,7 +3064,6 @@ static int bond_open(struct net_device *bond_dev)
 
 	/* reset slave->backup and slave->inactive */
 	if (bond_has_slaves(bond)) {
-		read_lock(&bond->curr_slave_lock);
 		bond_for_each_slave(bond, slave, iter) {
 			if (bond_uses_primary(bond) &&
 			    slave != rcu_access_pointer(bond->curr_active_slave)) {
@@ -3117,7 +3074,6 @@ static int bond_open(struct net_device *bond_dev)
 							    BOND_SLAVE_NOTIFY_NOW);
 			}
 		}
-		read_unlock(&bond->curr_slave_lock);
 	}
 
 	bond_work_init_all(bond);
@@ -3239,14 +3195,10 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd
 		if (!mii)
 			return -EINVAL;
 
-
 		if (mii->reg_num == 1) {
 			mii->val_out = 0;
-			read_lock(&bond->curr_slave_lock);
 			if (netif_carrier_ok(bond->dev))
 				mii->val_out = BMSR_LSTATUS;
-
-			read_unlock(&bond->curr_slave_lock);
 		}
 
 		return 0;
@@ -3892,8 +3844,7 @@ void bond_setup(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 
-	/* initialize rwlocks */
-	rwlock_init(&bond->curr_slave_lock);
+	spin_lock_init(&bond->mode_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
@@ -4340,19 +4291,9 @@ static int bond_init(struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct bond_net *bn = net_generic(dev_net(bond_dev), bond_net_id);
-	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
 
 	netdev_dbg(bond_dev, "Begin bond_init\n");
 
-	/*
-	 * Initialize locks that may be required during
-	 * en/deslave operations.  All of the bond_open work
-	 * (of which this is part) should really be moved to
-	 * a phase prior to dev_open
-	 */
-	spin_lock_init(&(bond_info->tx_hashtbl_lock));
-	spin_lock_init(&(bond_info->rx_hashtbl_lock));
-
 	bond->wq = create_singlethread_workqueue(bond_dev->name);
 	if (!bond->wq)
 		return -ENOMEM;

drivers/net/bonding/bond_options.c

@@ -734,15 +734,13 @@ static int bond_option_active_slave_set(struct bonding *bond,
 	}
 
 	block_netpoll_tx();
-	write_lock_bh(&bond->curr_slave_lock);
-
 	/* check to see if we are clearing active */
 	if (!slave_dev) {
 		netdev_info(bond->dev, "Clearing current active slave\n");
 		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
 		bond_select_active_slave(bond);
 	} else {
-		struct slave *old_active = bond_deref_active_protected(bond);
+		struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
 		struct slave *new_active = bond_slave_get_rtnl(slave_dev);
 
 		BUG_ON(!new_active);
@@ -765,8 +763,6 @@ static int bond_option_active_slave_set(struct bonding *bond,
 			}
 		}
 	}
-
-	write_unlock_bh(&bond->curr_slave_lock);
 	unblock_netpoll_tx();
 
 	return ret;
@@ -1066,7 +1062,6 @@ static int bond_option_primary_set(struct bonding *bond,
 	struct slave *slave;
 
 	block_netpoll_tx();
-	write_lock_bh(&bond->curr_slave_lock);
 
 	p = strchr(primary, '\n');
 	if (p)
@@ -1103,7 +1098,6 @@ static int bond_option_primary_set(struct bonding *bond,
 		    primary, bond->dev->name);
 
 out:
-	write_unlock_bh(&bond->curr_slave_lock);
 	unblock_netpoll_tx();
 
 	return 0;
@@ -1117,9 +1111,7 @@ static int bond_option_primary_reselect_set(struct bonding *bond,
 	bond->params.primary_reselect = newval->value;
 
 	block_netpoll_tx();
-	write_lock_bh(&bond->curr_slave_lock);
 	bond_select_active_slave(bond);
-	write_unlock_bh(&bond->curr_slave_lock);
 	unblock_netpoll_tx();
 
 	return 0;

drivers/net/bonding/bonding.h

@@ -184,9 +184,7 @@ struct slave {
 
 /*
  * Here are the locking policies for the two bonding locks:
- *
- * 1) Get rcu_read_lock when reading or RTNL when writing slave list.
- * 2) Get bond->curr_slave_lock when reading/writing bond->curr_active_slave.
+ * Get rcu_read_lock when reading or RTNL when writing slave list.
  */
 struct bonding {
 	struct   net_device *dev; /* first - useful for panic debug */
@@ -197,7 +195,13 @@ struct bonding {
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
 			      struct slave *);
-	rwlock_t curr_slave_lock;
+	/* mode_lock is used for mode-specific locking needs, currently used by:
+	 * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and
+	 *                bond_3ad_state_machine_handler() concurrently.
+	 * TLB mode (5) - to sync the use and modifications of its hash table
+	 * ALB mode (6) - to sync the use and modifications of its hash table
+	 */
+	spinlock_t mode_lock;
 	u8	 send_peer_notif;
 	u8       igmp_retrans;
 #ifdef CONFIG_PROC_FS
@@ -227,10 +231,6 @@ struct bonding {
 #define bond_slave_get_rtnl(dev) \
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
-#define bond_deref_active_protected(bond)				   \
-	rcu_dereference_protected(bond->curr_active_slave,		   \
-				  lockdep_is_held(&bond->curr_slave_lock))
-
 struct bond_vlan_tag {
 	__be16		vlan_proto;
 	unsigned short	vlan_id;