summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNikolay Aleksandrov <nikolay@redhat.com>2013-06-12 00:07:02 +0200
committerDavid S. Miller <davem@davemloft.net>2013-06-13 02:33:37 -0700
commit4f5474e7fd68988cb11373fc698bf10b35b49e31 (patch)
tree99c4f8a2c6313182ed3016dad8b7288e9ae9b672
parentb8fad459f9cc8417b74f71c6c229eef7412163d1 (diff)
downloadop-kernel-dev-4f5474e7fd68988cb11373fc698bf10b35b49e31.zip
op-kernel-dev-4f5474e7fd68988cb11373fc698bf10b35b49e31.tar.gz
bonding: fix igmp_retrans type and two related races
First the type of igmp_retrans (which is the actual counter of igmp_resend parameter) is changed to u8 to be able to store values up to 255 (as per documentation). There are two races that were hidden there and which are easy to trigger after the previous fix, the first is between bond_resend_igmp_join_requests and bond_change_active_slave where igmp_retrans is set and can be altered by the periodic. The second race condition is between multiple running instances of the periodic (upon execution it can be scheduled again for immediate execution which can cause the counter to go < 0 which in the unsigned case leads to unnecessary igmp retransmissions). Since in bond_change_active_slave bond->lock is held for reading and curr_slave_lock for writing, we use curr_slave_lock for mutual exclusion. We can't drop them as there're cases where RTNL is not held when bond_change_active_slave is called. RCU is unlocked in bond_resend_igmp_join_requests before getting curr_slave_lock since we don't need it there and it's pointless to delay. The decrement is moved inside the "if" block because if we decrement unconditionally there's still a possibility for a race condition although it is much more difficult to hit (many changes have to happen in a very short period in order to trigger) which in the case of 3 parallel running instances of this function and igmp_retrans == 1 (with check bond->igmp_retrans-- > 1) is: f1 passes, doesn't re-schedule, but decrements - igmp_retrans = 0 f2 then passes, doesn't re-schedule, but decrements - igmp_retrans = 255 f3 does the unnecessary retransmissions. Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Signed-off-by: Jay Vosburgh <fubar@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--drivers/net/bonding/bond_main.c15
-rw-r--r--drivers/net/bonding/bonding.h2
2 files changed, 12 insertions, 5 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 473633a..02d9ae7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -764,8 +764,8 @@ static void bond_resend_igmp_join_requests(struct bonding *bond)
struct net_device *bond_dev, *vlan_dev, *upper_dev;
struct vlan_entry *vlan;
- rcu_read_lock();
read_lock(&bond->lock);
+ rcu_read_lock();
bond_dev = bond->dev;
@@ -787,12 +787,19 @@ static void bond_resend_igmp_join_requests(struct bonding *bond)
if (vlan_dev)
__bond_resend_igmp_join_requests(vlan_dev);
}
+ rcu_read_unlock();
- if (--bond->igmp_retrans > 0)
+ /* We use curr_slave_lock to protect against concurrent access to
+ * igmp_retrans from multiple running instances of this function and
+ * bond_change_active_slave
+ */
+ write_lock_bh(&bond->curr_slave_lock);
+ if (bond->igmp_retrans > 1) {
+ bond->igmp_retrans--;
queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
-
+ }
+ write_unlock_bh(&bond->curr_slave_lock);
read_unlock(&bond->lock);
- rcu_read_unlock();
}
static void bond_resend_igmp_join_requests_delayed(struct work_struct *work)
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 2baec24..f989e15 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -225,7 +225,7 @@ struct bonding {
rwlock_t curr_slave_lock;
u8 send_peer_notif;
s8 setup_by_slave;
- s8 igmp_retrans;
+ u8 igmp_retrans;
#ifdef CONFIG_PROC_FS
struct proc_dir_entry *proc_entry;
char proc_file_name[IFNAMSIZ];
OpenPOWER on IntegriCloud