bonding: rebuild the lock use for bond_loadbalance_arp_mon()

The bond_loadbalance_arp_mon() use the bond lock to protect the
bond slave list, it is no effect, so I could use RTNL or RCU to
replace it, considering the performance impact, the RCU is more
better here, so the bond lock replace with the RCU.

The bond_select_active_slave() need RTNL and curr_slave_lock
together, but there is no RTNL lock here, so add a rtnl_rtylock.

Suggested-by: Jay Vosburgh <fubar@us.ibm.com>
Suggested-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b34634a96710d28b9dc77c7abee08b9e2f4d88b6..1781ea620d76b256af0f2342f3354ed1cbcf827d 100644 (file)
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2411,12 +2411,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
        struct list_head *iter;
        int do_failover = 0;
 
-       read_lock(&bond->lock);
-
        if (!bond_has_slaves(bond))
                goto re_arm;
 
-       oldcurrent = bond->curr_active_slave;
+       rcu_read_lock();
+
+       oldcurrent = ACCESS_ONCE(bond->curr_active_slave);
        /* see if any of the previous devices are up now (i.e. they have
         * xmt and rcv traffic). the curr_active_slave does not come into
         * the picture unless it is null. also, slave->jiffies is not needed
@@ -2425,7 +2425,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
         * TODO: what about up/down delay in arp mode? it wasn't here before
         *       so it can wait
         */
-       bond_for_each_slave(bond, slave, iter) {
+       bond_for_each_slave_rcu(bond, slave, iter) {
                unsigned long trans_start = dev_trans_start(slave->dev);
 
                if (slave->link != BOND_LINK_UP) {
@@ -2487,7 +2487,14 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
                        bond_arp_send_all(bond, slave);
        }
 
+       rcu_read_unlock();
+
        if (do_failover) {
+               /* the bond_select_active_slave must hold RTNL
+                * and curr_slave_lock for write.
+                */
+               if (!rtnl_trylock())
+                       goto re_arm;
                block_netpoll_tx();
                write_lock_bh(&bond->curr_slave_lock);
 
@@ -2495,14 +2502,13 @@ 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);
 }
 
 /*