From a0db2dad0935e798973bb79676e722b82f177206 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Fri, 23 Sep 2011 10:53:34 +0000 Subject: [PATCH] bonding: properly stop queuing work when requested During a test where a pair of bonding interfaces using ARP monitoring were both brought up and torn down (with an rmmod) repeatedly, a panic in the timer code was noticed. I tracked this down and determined that any of the bonding functions that ran as workqueue handlers and requeued more work might not properly exit when the module was removed. There was a flag protected by the bond lock called kill_timers that is set when the interface goes down or the module is removed, but many of the functions that monitor link status now unlock the bond lock to take rtnl first. There is a chance that another CPU running the rmmod could get the lock and set kill_timers after the first check has passed. This patch does not allow any function to queue work that will make itself run unless kill_timers is not set. I also noticed while doing this work that bond_resend_igmp_join_requests did not have a check for kill_timers, so I added the needed call there as well. Signed-off-by: Andy Gospodarek Reported-by: Liang Zheng Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 3 ++- drivers/net/bonding/bond_alb.c | 3 ++- drivers/net/bonding/bond_main.c | 13 ++++++++----- 3 files changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index a047eb973e3b..47b928ed08f8 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2168,7 +2168,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } re_arm: - queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); + if (!bond->kill_timers) + queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); out: read_unlock(&bond->lock); } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 7f8b20a34ee3..d4fbd2e62616 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1440,7 +1440,8 @@ void bond_alb_monitor(struct work_struct *work) } re_arm: - queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks); + if (!bond->kill_timers) + queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks); out: read_unlock(&bond->lock); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 43f2ea541088..6d79b78cfc75 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -777,6 +777,9 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) read_lock(&bond->lock); + if (bond->kill_timers) + goto out; + /* rejoin all groups on bond device */ __bond_resend_igmp_join_requests(bond->dev); @@ -790,9 +793,9 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) __bond_resend_igmp_join_requests(vlan_dev); } - if (--bond->igmp_retrans > 0) + if ((--bond->igmp_retrans > 0) && !bond->kill_timers) queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); - +out: read_unlock(&bond->lock); } @@ -2538,7 +2541,7 @@ void bond_mii_monitor(struct work_struct *work) } re_arm: - if (bond->params.miimon) + if (bond->params.miimon && !bond->kill_timers) queue_delayed_work(bond->wq, &bond->mii_work, msecs_to_jiffies(bond->params.miimon)); out: @@ -2886,7 +2889,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) } re_arm: - if (bond->params.arp_interval) + if (bond->params.arp_interval && !bond->kill_timers) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); out: read_unlock(&bond->lock); @@ -3154,7 +3157,7 @@ void bond_activebackup_arp_mon(struct work_struct *work) bond_ab_arp_probe(bond); re_arm: - if (bond->params.arp_interval) + if (bond->params.arp_interval && !bond->kill_timers) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); out: read_unlock(&bond->lock);