PCI: shpchp: Use per-slot workqueues to avoid deadlock

When we have an SHPC-capable bridge with a second SHPC-capable bridge
below it, pushing the upstream bridge's attention button causes a
deadlock.

The deadlock happens because we use the shpchp_wq workqueue to run
shpchp_pushbutton_thread(), which uses shpchp_disable_slot() to remove
devices below the upstream bridge.  When we remove the downstream bridge,
we call shpc_remove(), the shpchp driver's .remove() method.  That calls
flush_workqueue(shpchp_wq), which deadlocks because the
shpchp_pushbutton_thread() work item is still running.

This patch avoids the deadlock by creating a workqueue for every slot
and removing the single shared workqueue.

Here's the call path that leads to the deadlock:

  shpchp_queue_pushbutton_work
    queue_work(shpchp_wq)		# shpchp_pushbutton_thread
    ...

  shpchp_pushbutton_thread
    shpchp_disable_slot
      remove_board
        shpchp_unconfigure_device
          pci_stop_and_remove_bus_device
            ...
              shpc_remove		# shpchp driver .remove method
                hpc_release_ctlr
                  cleanup_slots
                    flush_workqueue(shpchp_wq)

This change is based on code inspection, since we don't have hardware
with this topology.

Based-on-patch-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org

1 files changed, 14 insertions, 12 deletions

diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index 3774e0d5506e..3100c52c837c 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -39,7 +39,6 @@
 bool shpchp_debug;
 bool shpchp_poll_mode;
 int shpchp_poll_time;
-struct workqueue_struct *shpchp_wq;
 
 #define DRIVER_VERSION	"0.4"
 #define DRIVER_AUTHOR	"Dan Zink <dan.zink@compaq.com>, Greg Kroah-Hartman <greg@kroah.com>, Dely Sy <dely.l.sy@intel.com>"
@@ -128,6 +127,14 @@ static int init_slots(struct controller *ctrl)
 		slot->device = ctrl->slot_device_offset + i;
 		slot->hpc_ops = ctrl->hpc_ops;
 		slot->number = ctrl->first_slot + (ctrl->slot_num_inc * i);
+
+		snprintf(name, sizeof(name), "shpchp-%d", slot->number);
+		slot->wq = alloc_workqueue(name, 0, 0);
+		if (!slot->wq) {
+			retval = -ENOMEM;
+			goto error_info;
+		}
+
 		mutex_init(&slot->lock);
 		INIT_DELAYED_WORK(&slot->work, shpchp_queue_pushbutton_work);
 
@@ -147,7 +154,7 @@ static int init_slots(struct controller *ctrl)
 		if (retval) {
 			ctrl_err(ctrl, "pci_hp_register failed with error %d\n",
 				 retval);
-			goto error_info;
+			goto error_slotwq;
 		}
 
 		get_power_status(hotplug_slot, &info->power_status);
@@ -159,6 +166,8 @@ static int init_slots(struct controller *ctrl)
 	}
 
 	return 0;
+error_slotwq:
+	destroy_workqueue(slot->wq);
 error_info:
 	kfree(info);
 error_hpslot:
@@ -179,7 +188,7 @@ void cleanup_slots(struct controller *ctrl)
 		slot = list_entry(tmp, struct slot, slot_list);
 		list_del(&slot->slot_list);
 		cancel_delayed_work(&slot->work);
-		flush_workqueue(shpchp_wq);
+		destroy_workqueue(slot->wq);
 		pci_hp_deregister(slot->hotplug_slot);
 	}
 }
@@ -362,18 +371,12 @@ static struct pci_driver shpc_driver = {
 
 static int __init shpcd_init(void)
 {
-	int retval = 0;
-
-	shpchp_wq = alloc_workqueue("shpchp", 0, 0);
-	if (!shpchp_wq)
-		return -ENOMEM;
+	int retval;
 
 	retval = pci_register_driver(&shpc_driver);
 	dbg("%s: pci_register_driver = %d\n", __func__, retval);
 	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
-	if (retval) {
-		destroy_workqueue(shpchp_wq);
-	}
+
 	return retval;
 }
 
@@ -381,7 +384,6 @@ static void __exit shpcd_cleanup(void)
 {
 	dbg("unload_shpchpd()\n");
 	pci_unregister_driver(&shpc_driver);
-	destroy_workqueue(shpchp_wq);
 	info(DRIVER_DESC " version: " DRIVER_VERSION " unloaded\n");
 }