block: fix surprise removal for drivers calling blk_set_queue_dying

Various block drivers call blk_set_queue_dying to mark a disk as dead due
to surprise removal events, but since commit 8e141f9 that doesn't
work given that the GD_DEAD flag needs to be set to stop I/O.

Replace the driver calls to blk_set_queue_dying with a new (and properly
documented) blk_mark_disk_dead API, and fold blk_set_queue_dying into the
only remaining caller.

Fixes: 8e141f9 ("block: drain file system I/O on del_gendisk")
Reported-by: Markus Blöchl <markus.bloechl@ipetronik.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Link: https://lore.kernel.org/r/20220217075231.1140-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Christoph Hellwig

block/blk-core.c

@@ -284,13 +284,6 @@ void blk_queue_start_drain(struct request_queue *q)
 	wake_up_all(&q->mq_freeze_wq);
 }
 
-void blk_set_queue_dying(struct request_queue *q)
-{
-	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	blk_queue_start_drain(q);
-}
-EXPORT_SYMBOL_GPL(blk_set_queue_dying);
-
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -308,7 +301,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	WARN_ON_ONCE(blk_queue_registered(q));
 
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	blk_set_queue_dying(q);
+	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
+	blk_queue_start_drain(q);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);

block/genhd.c

@@ -548,6 +548,20 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 }
 EXPORT_SYMBOL(device_add_disk);
 
+/**
+ * blk_mark_disk_dead - mark a disk as dead
+ * @disk: disk to mark as dead
+ *
+ * Mark as disk as dead (e.g. surprise removed) and don't accept any new I/O
+ * to this disk.
+ */
+void blk_mark_disk_dead(struct gendisk *disk)
+{
+	set_bit(GD_DEAD, &disk->state);
+	blk_queue_start_drain(disk->queue);
+}
+EXPORT_SYMBOL_GPL(blk_mark_disk_dead);
+
 /**
  * del_gendisk - remove the gendisk
  * @disk: the struct gendisk to remove

drivers/block/mtip32xx/mtip32xx.c

@@ -4112,7 +4112,7 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 			"Completion workers still active!\n");
 	}
 
-	blk_set_queue_dying(dd->queue);
+	blk_mark_disk_dead(dd->disk);
 	set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag);
 
 	/* Clean up the block layer. */

drivers/block/rbd.c

@@ -7185,7 +7185,7 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
 		 * IO to complete/fail.
 		 */
 		blk_mq_freeze_queue(rbd_dev->disk->queue);
-		blk_set_queue_dying(rbd_dev->disk->queue);
+		blk_mark_disk_dead(rbd_dev->disk);
 	}
 
 	del_gendisk(rbd_dev->disk);

drivers/block/xen-blkfront.c

@@ -2126,7 +2126,7 @@ static void blkfront_closing(struct blkfront_info *info)
 
 	/* No more blkif_request(). */
 	blk_mq_stop_hw_queues(info->rq);
-	blk_set_queue_dying(info->rq);
+	blk_mark_disk_dead(info->gd);
 	set_capacity(info->gd, 0);
 
 	for_each_rinfo(info, rinfo, i) {

drivers/md/dm.c

@@ -2077,7 +2077,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	set_bit(DMF_FREEING, &md->flags);
 	spin_unlock(&_minor_lock);
 
-	blk_set_queue_dying(md->queue);
+	blk_mark_disk_dead(md->disk);
 
 	/*
 	 * Take suspend_lock so that presuspend and postsuspend methods

drivers/nvme/host/core.c

@@ -4574,7 +4574,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
 
-	blk_set_queue_dying(ns->queue);
+	blk_mark_disk_dead(ns->disk);
 	nvme_start_ns_queue(ns);
 
 	set_capacity_and_notify(ns->disk, 0);

drivers/nvme/host/multipath.c

@@ -848,7 +848,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	blk_set_queue_dying(head->disk->queue);
+	blk_mark_disk_dead(head->disk);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);

include/linux/blkdev.h

@@ -748,7 +748,8 @@ extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 
 bool __must_check blk_get_queue(struct request_queue *);
 extern void blk_put_queue(struct request_queue *);
-extern void blk_set_queue_dying(struct request_queue *);
+
+void blk_mark_disk_dead(struct gendisk *disk);
 
 #ifdef CONFIG_BLOCK
 /*