[SCSI] ipr: move setting of the allow_restart flag for vsets and disks
A problem was found where the call to scsi_add_device() fails intermittently
for an adapter. This is caused when __scsi_add_device() returns -ENODEV as
a result of not calling scsi_probe_and_add_lun() since the call to
scsi_host_scan_allowed() fails. scsi_host_scan_allowed() fails because the
adapter state is set to SHOST_RECOVERY instead of SHOST_RUNNING. The state of
the adapter is being set to SHOST_RECOVERY by scsi_eh_scmd_add() during
error handling.
This problem is avoided by moving the setting of the allow_restart flag to
later in the device initialization sequence. This prevents further error
handling if we get a NOT_READY response from a TUR command by causing
scsi_check_sense() to return SUCCESS. Therefore, scsi_eh_scmd_add() will
not run and the adapter state will remain as SHOST_RUNNING.
Signed-off-by: Wayne Boyer <wayneb@linux.vnet.ibm.com>
Acked-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 62bbe31..37158ea 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4353,8 +4353,6 @@
IPR_VSET_RW_TIMEOUT);
blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS);
}
- if (ipr_is_vset_device(res) || ipr_is_scsi_disk(res))
- sdev->allow_restart = 1;
if (ipr_is_gata(res) && res->sata_port)
ap = res->sata_port->ap;
spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
@@ -6771,7 +6769,8 @@
list_move_tail(&res->queue, &ioa_cfg->used_res_q);
ipr_init_res_entry(res, &cfgtew);
res->add_to_ml = 1;
- }
+ } else if (res->sdev && (ipr_is_vset_device(res) || ipr_is_scsi_disk(res)))
+ res->sdev->allow_restart = 1;
if (found)
ipr_update_res_entry(res, &cfgtew);