Re: Strange block/scsi/workqueue issue

[James Bottomley <James.Bottomley@HansenPartnership.com>]

While you still have the problematic system, can you try this patch?  It
avoids changing anything in block (other than to add a missing state
guard for the elv_next_request).  If it works, we can defer the sync vs
async discussion and use it for a -stable fix.

Thanks,

James

---

diff --git a/block/blk.h b/block/blk.h
index c8db371..11d0d25 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -62,7 +62,8 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return rq;
 		}
 
-		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
+		if (test_bit(QUEUE_FLAG_DEAD, &q->queue_flags) ||
+		    !q->elevator->ops->elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index e44ff64..5aa4246 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -322,14 +322,9 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
 		kfree(evt);
 	}
 
-	if (sdev->request_queue) {
-		sdev->request_queue->queuedata = NULL;
-		/* user context needed to free queue */
-		scsi_free_queue(sdev->request_queue);
-		/* temporary expedient, try to catch use of queue lock
-		 * after free of sdev */
-		sdev->request_queue = NULL;
-	}
+	/* temporary expedient, try to catch use of queue lock after
+	 * free of sdev */
+	sdev->request_queue = NULL;
 
 	scsi_target_reap(scsi_target(sdev));
 
@@ -937,6 +932,11 @@ void __scsi_remove_device(struct scsi_device *sdev)
 	if (sdev->host->hostt->slave_destroy)
 		sdev->host->hostt->slave_destroy(sdev);
 	transport_destroy_device(dev);
+	/* Setting this to NULL causes the request function to reject
+	 * any I/O requests */
+	sdev->request_queue->queuedata = NULL;
+	/* Freeing the queue signals to block that we're done */
+	scsi_free_queue(sdev->request_queue);
 	put_device(dev);
 }