Commit d74cf7c3 authored by Christof Schmitt's avatar Christof Schmitt Committed by James Bottomley

[SCSI] zfcp: Fix hang when offlining device with offline chpid

Running chchp --vary 0 and chccwdev -d on a FCP device with scsi
devices attached can lead to this thread hanging:

================================================================
STACK TRACE FOR TASK: 0x2fbfcc00 (kslowcrw)

 STACK:
 0 schedule+1136 [0x45f99c]
 1 schedule_timeout+534 [0x46054e]
 2 wait_for_common+374 [0x45f442]
 3 blk_execute_rq+160 [0x217a2c]
 4 scsi_execute+278 [0x26daf2]
 5 scsi_execute_req+150 [0x26dc86]
 6 sd_sync_cache+138 [0x28460a]
 7 sd_shutdown+130 [0x28486a]
 8 sd_remove+104 [0x284c84]
 9 __device_release_driver+152 [0x257430]
10 device_release_driver+56 [0x2575c8]
11 bus_remove_device+214 [0x25672a]
12 device_del+352 [0x25456c]
13 __scsi_remove_device+108 [0x272630]
14 scsi_remove_device+66 [0x2726ba]
15 zfcp_ccw_remove+824 [0x335558]
16 ccw_device_remove+62 [0x2b3f2a]
17 __device_release_driver+152 [0x257430]
18 device_release_driver+56 [0x2575c8]
19 bus_remove_device+214 [0x25672a]
20 device_del+352 [0x25456c]
21 ccw_device_unregister+92 [0x2b48c4]
22 io_subchannel_remove+108 [0x2b4950]
23 css_remove+62 [0x2af7ee]
24 __device_release_driver+152 [0x257430]
25 device_release_driver+56 [0x2575c8]
26 bus_remove_device+214 [0x25672a]
27 device_del+352 [0x25456c]
28 device_unregister+38 [0x25464a]
29 css_sch_device_unregister+68 [0x2af97c]
30 ccw_device_call_sch_unregister+78 [0x2b581e]
31 worker_thread+604 [0x69eb0]
32 kthread+154 [0x6ff42]
33 kernel_thread_starter+6 [0x1c952]
================================================================

The problem is that the chchp --vary 0 leads to zfcp first calling
fc_remote_port_delete which blocks all scsi devices on the remote
port. Calling scsi_remove_device later lets the sd driver issue a
SYNCHRONIZE_CACHE command. This command stays on the "stopped" request
requeue because the SCSI device is blocked. Fix this by first removing
the scsi and fc hosts which removes all scsi devices and do not use
scsi_remove_device.
Reviewed-by: default avatarFelix Beck <felix.beck@de.ibm.com>
Signed-off-by: default avatarChristof Schmitt <christof.schmitt@de.ibm.com>
Signed-off-by: default avatarJames Bottomley <James.Bottomley@suse.de>
parent f45a5421
......@@ -604,7 +604,6 @@ void zfcp_adapter_dequeue(struct zfcp_adapter *adapter)
cancel_work_sync(&adapter->stat_work);
zfcp_fc_wka_ports_force_offline(adapter->gs);
zfcp_adapter_scsi_unregister(adapter);
sysfs_remove_group(&adapter->ccw_device->dev.kobj,
&zfcp_sysfs_adapter_attrs);
dev_set_drvdata(&adapter->ccw_device->dev, NULL);
......
......@@ -107,6 +107,10 @@ static void zfcp_ccw_remove(struct ccw_device *ccw_device)
cancel_work_sync(&adapter->scan_work);
mutex_lock(&zfcp_data.config_mutex);
/* this also removes the scsi devices, so call it first */
zfcp_adapter_scsi_unregister(adapter);
write_lock_irq(&zfcp_data.config_lock);
list_for_each_entry_safe(port, p, &adapter->port_list_head, list) {
list_for_each_entry_safe(unit, u, &port->unit_list_head, list) {
......@@ -121,11 +125,8 @@ static void zfcp_ccw_remove(struct ccw_device *ccw_device)
write_unlock_irq(&zfcp_data.config_lock);
list_for_each_entry_safe(port, p, &port_remove_lh, list) {
list_for_each_entry_safe(unit, u, &unit_remove_lh, list) {
if (unit->device)
scsi_remove_device(unit->device);
list_for_each_entry_safe(unit, u, &unit_remove_lh, list)
zfcp_unit_dequeue(unit);
}
zfcp_port_dequeue(port);
}
wait_event(adapter->remove_wq, atomic_read(&adapter->refcount) == 0);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment