alua_bus_detach() might be running concurrently with alua_rtpg_work(),
so we might trip over h->sdev == NULL and call BUG_ON().
The correct way of handling it would be to not set h->sdev to NULL
in alua_bus_detach(), and call rcu_synchronize() before the final
delete to ensure that all concurrent threads have left the critical
section.
Then we can get rid of the BUG_ON(), and replace it with a simple
if condition.
Cc: Brian Bunker <brian@xxxxxxxxxxxxxxx>
Signed-off-by: Hannes Reinecke <hare@xxxxxxx>
---
drivers/scsi/device_handler/scsi_dh_alua.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index f32da0ca529e..308bda2e9c00 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -658,8 +658,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
rcu_read_lock();
list_for_each_entry_rcu(h,
&tmp_pg->dh_list, node) {
- /* h->sdev should always be valid */
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state = desc[0];
}
rcu_read_unlock();
@@ -705,7 +705,8 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
pg->expiry = 0;
rcu_read_lock();
list_for_each_entry_rcu(h, &pg->dh_list, node) {
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state =
(pg->state & SCSI_ACCESS_STATE_MASK);
if (pg->pref)
@@ -1147,7 +1148,6 @@ static void alua_bus_detach(struct scsi_device *sdev)
spin_lock(&h->pg_lock);
pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
rcu_assign_pointer(h->pg, NULL);
- h->sdev = NULL;
spin_unlock(&h->pg_lock);
if (pg) {
spin_lock_irq(&pg->lock);
@@ -1156,6 +1156,7 @@ static void alua_bus_detach(struct scsi_device *sdev)
kref_put(&pg->kref, release_port_group);
}
sdev->handler_data = NULL;
+ synchronize_rcu();
kfree(h);
}
--
2.16.4
