diff options
| author | Roland Dreier <rdreier@cisco.com> | 2009-09-23 11:10:15 -0700 |
|---|---|---|
| committer | Roland Dreier <rolandd@cisco.com> | 2009-09-23 11:10:15 -0700 |
| commit | 0e442afd92fcdde2cc63b6f25556b8934e42b7d2 (patch) | |
| tree | 49b2f52ee849e7888473eb228f1abe3c27ed9434 | |
| parent | 86d710146fb9975f04c505ec78caa43d227c1018 (diff) | |
| download | op-kernel-dev-0e442afd92fcdde2cc63b6f25556b8934e42b7d2.zip op-kernel-dev-0e442afd92fcdde2cc63b6f25556b8934e42b7d2.tar.gz | |
IB/mad: Fix lock-lock-timer deadlock in RMPP code
Holding agent->lock across cancel_delayed_work() (which does
del_timer_sync()) in ib_cancel_rmpp_recvs() leads to lockdep reports of
possible lock-timer deadlocks if a consumer ever does something that
connects agent->lock to a lock taken in IRQ context (cf
http://marc.info/?l=linux-rdma&m=125243699026045).
Fix this by changing the list items to a new state "CANCELING" while
holding the lock, and then canceling the delayed work without holding
the lock. If the delayed work runs after the lock is dropped, it will
see the state is CANCELING and return immediately, so the list will
stay stable while we traverse it with the lock not held.
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
| -rw-r--r-- | drivers/infiniband/core/mad_rmpp.c | 17 |
1 files changed, 13 insertions, 4 deletions
diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c index 57a3c6f..4e0f2829 100644 --- a/drivers/infiniband/core/mad_rmpp.c +++ b/drivers/infiniband/core/mad_rmpp.c @@ -37,7 +37,8 @@ enum rmpp_state { RMPP_STATE_ACTIVE, RMPP_STATE_TIMEOUT, - RMPP_STATE_COMPLETE + RMPP_STATE_COMPLETE, + RMPP_STATE_CANCELING }; struct mad_rmpp_recv { @@ -87,18 +88,22 @@ void ib_cancel_rmpp_recvs(struct ib_mad_agent_private *agent) spin_lock_irqsave(&agent->lock, flags); list_for_each_entry(rmpp_recv, &agent->rmpp_list, list) { + if (rmpp_recv->state != RMPP_STATE_COMPLETE) + ib_free_recv_mad(rmpp_recv->rmpp_wc); + rmpp_recv->state = RMPP_STATE_CANCELING; + } + spin_unlock_irqrestore(&agent->lock, flags); + + list_for_each_entry(rmpp_recv, &agent->rmpp_list, list) { cancel_delayed_work(&rmpp_recv->timeout_work); cancel_delayed_work(&rmpp_recv->cleanup_work); } - spin_unlock_irqrestore(&agent->lock, flags); flush_workqueue(agent->qp_info->port_priv->wq); list_for_each_entry_safe(rmpp_recv, temp_rmpp_recv, &agent->rmpp_list, list) { list_del(&rmpp_recv->list); - if (rmpp_recv->state != RMPP_STATE_COMPLETE) - ib_free_recv_mad(rmpp_recv->rmpp_wc); destroy_rmpp_recv(rmpp_recv); } } @@ -260,6 +265,10 @@ static void recv_cleanup_handler(struct work_struct *work) unsigned long flags; spin_lock_irqsave(&rmpp_recv->agent->lock, flags); + if (rmpp_recv->state == RMPP_STATE_CANCELING) { + spin_unlock_irqrestore(&rmpp_recv->agent->lock, flags); + return; + } list_del(&rmpp_recv->list); spin_unlock_irqrestore(&rmpp_recv->agent->lock, flags); destroy_rmpp_recv(rmpp_recv); |
