bonding: Fix deadlock in bonding driver resulting from internal locking when using netpoll

The monitoring paths in the bonding driver take write locks that are shared by
the tx path.  If netconsole is in use, these paths can call printk which puts us
in the netpoll tx path, which, if netconsole is attached to the bonding driver,
result in deadlock (the xmit_lock guards are useless in netpoll_send_skb, as the
monitor paths in the bonding driver don't claim the xmit_lock, nor should they).
The solution is to use a per cpu flag internal to the driver to indicate when a
cpu is holding the lock in a path that might recusrse into the tx path for the
driver via netconsole.  By checking this flag on transmit, we can defer the
sending of the netconsole frames until a later time using the retransmit feature
of netpoll_send_skb that is triggered on the return code NETDEV_TX_BUSY.  I've
tested this and am able to transmit via netconsole while causing failover
conditions on the bond slave links.

Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 0 deletions

diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 01b4c3f5d9e7..8fd0174c5380 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1066,6 +1066,7 @@ static ssize_t bonding_store_primary(struct device *d,
 
 	if (!rtnl_trylock())
 		return restart_syscall();
+	block_netpoll_tx();
 	read_lock(&bond->lock);
 	write_lock_bh(&bond->curr_slave_lock);
 
@@ -1101,6 +1102,7 @@ static ssize_t bonding_store_primary(struct device *d,
 out:
 	write_unlock_bh(&bond->curr_slave_lock);
 	read_unlock(&bond->lock);
+	unblock_netpoll_tx();
 	rtnl_unlock();
 
 	return count;
@@ -1146,11 +1148,13 @@ static ssize_t bonding_store_primary_reselect(struct device *d,
 		bond->dev->name, pri_reselect_tbl[new_value].modename,
 		new_value);
 
+	block_netpoll_tx();
 	read_lock(&bond->lock);
 	write_lock_bh(&bond->curr_slave_lock);
 	bond_select_active_slave(bond);
 	write_unlock_bh(&bond->curr_slave_lock);
 	read_unlock(&bond->lock);
+	unblock_netpoll_tx();
 out:
 	rtnl_unlock();
 	return ret;
@@ -1232,6 +1236,8 @@ static ssize_t bonding_store_active_slave(struct device *d,
 
 	if (!rtnl_trylock())
 		return restart_syscall();
+
+	block_netpoll_tx();
 	read_lock(&bond->lock);
 	write_lock_bh(&bond->curr_slave_lock);
 
@@ -1288,6 +1294,8 @@ static ssize_t bonding_store_active_slave(struct device *d,
  out:
 	write_unlock_bh(&bond->curr_slave_lock);
 	read_unlock(&bond->lock);
+	unblock_netpoll_tx();
+
 	rtnl_unlock();
 
 	return count;