scsi_scan: fix queue depth initialisation problem

Currently we blindly use the value of cmd_per_lun as the initial setting for
queue_depth.  This fails miserably (hangs the system) if it is zero, which is
the default value for anything uninitialised in the template.  The net result
is that every host template has to set a value for cmd_per_lun.  Instead, use
a default value of 1 if the actual value is unset.  This should pave the way
for removing cmd_per_lun from all the templates and eventually from SCSI
itself.

Signed-off-by: James Bottomley <JBottomley@Odin.com>

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 6efab1c455e158a71a2792c07d9b6d3fadc7595c..53a2e3391454bd3eb8374b86f1d6065412a5d280 100644 (file)
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -280,7 +280,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
                                    sdev->host->cmd_per_lun, shost->bqt,
                                    shost->hostt->tag_alloc_policy);
        }
-       scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun);
+       scsi_change_queue_depth(sdev, sdev->host->cmd_per_lun ?
+                                       sdev->host->cmd_per_lun : 1);
 
        scsi_sysfs_device_initialize(sdev);