Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

23 files changed, 709 insertions, 767 deletions

diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 7ca76ed2e71a..84d0fcebd6af 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -100,6 +100,10 @@ enum {
 	MAX_TAINT = 1000,	/* cap on aoetgt taint */
 };
 
+struct aoe_req {
+	unsigned long nr_bios;
+};
+
 struct buf {
 	ulong nframesout;
 	struct bio *bio;
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index ed26b7287256..e2c6aae2d636 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -387,6 +387,7 @@ aoeblk_gdalloc(void *vp)
 
 	set = &d->tag_set;
 	set->ops = &aoeblk_mq_ops;
+	set->cmd_size = sizeof(struct aoe_req);
 	set->nr_hw_queues = 1;
 	set->queue_depth = 128;
 	set->numa_node = NUMA_NO_NODE;
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index bb2fba651bd2..3cf9bc5d8d95 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -822,17 +822,6 @@ out:
 	spin_unlock_irqrestore(&d->lock, flags);
 }
 
-static unsigned long
-rqbiocnt(struct request *r)
-{
-	struct bio *bio;
-	unsigned long n = 0;
-
-	__rq_for_each_bio(bio, r)
-		n++;
-	return n;
-}
-
 static void
 bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 {
@@ -847,6 +836,7 @@ nextbuf(struct aoedev *d)
 {
 	struct request *rq;
 	struct request_queue *q;
+	struct aoe_req *req;
 	struct buf *buf;
 	struct bio *bio;
 
@@ -865,7 +855,11 @@ nextbuf(struct aoedev *d)
 		blk_mq_start_request(rq);
 		d->ip.rq = rq;
 		d->ip.nxbio = rq->bio;
-		rq->special = (void *) rqbiocnt(rq);
+
+		req = blk_mq_rq_to_pdu(rq);
+		req->nr_bios = 0;
+		__rq_for_each_bio(bio, rq)
+			req->nr_bios++;
 	}
 	buf = mempool_alloc(d->bufpool, GFP_ATOMIC);
 	if (buf == NULL) {
@@ -1069,16 +1063,13 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 static void
 aoe_end_buf(struct aoedev *d, struct buf *buf)
 {
-	struct request *rq;
-	unsigned long n;
+	struct request *rq = buf->rq;
+	struct aoe_req *req = blk_mq_rq_to_pdu(rq);
 
 	if (buf == d->ip.buf)
 		d->ip.buf = NULL;
-	rq = buf->rq;
 	mempool_free(buf, d->bufpool);
-	n = (unsigned long) rq->special;
-	rq->special = (void *) --n;
-	if (n == 0)
+	if (--req->nr_bios == 0)
 		aoe_end_request(d, rq, 0);
 }
 
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 9063f8efbd3b..5b49f1b33ebe 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -160,21 +160,22 @@ static void
 aoe_failip(struct aoedev *d)
 {
 	struct request *rq;
+	struct aoe_req *req;
 	struct bio *bio;
-	unsigned long n;
 
 	aoe_failbuf(d, d->ip.buf);
-
 	rq = d->ip.rq;
 	if (rq == NULL)
 		return;
+
+	req = blk_mq_rq_to_pdu(rq);
 	while ((bio = d->ip.nxbio)) {
 		bio->bi_status = BLK_STS_IOERR;
 		d->ip.nxbio = bio->bi_next;
-		n = (unsigned long) rq->special;
-		rq->special = (void *) --n;
+		req->nr_bios--;
 	}
-	if ((unsigned long) rq->special == 0)
+
+	if (!req->nr_bios)
 		aoe_end_request(d, rq, 0);
 }
 
diff --git a/drivers/block/aoe/aoemain.c b/drivers/block/aoe/aoemain.c
index 251482066977..1e4e2971171c 100644
--- a/drivers/block/aoe/aoemain.c
+++ b/drivers/block/aoe/aoemain.c
@@ -24,7 +24,7 @@ static void discover_timer(struct timer_list *t)
 	aoecmd_cfg(0xffff, 0xff);
 }
 
-static void
+static void __exit
 aoe_exit(void)
 {
 	del_timer_sync(&timer);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index f88b4c26d422..b0dbbdfeb33e 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1471,6 +1471,15 @@ static void setup_req_params( int drive )
 			ReqTrack, ReqSector, (unsigned long)ReqData ));
 }
 
+static void ataflop_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	spin_lock_irq(&ataflop_lock);
+	atari_disable_irq(IRQ_MFP_FDC);
+	finish_fdc();
+	atari_enable_irq(IRQ_MFP_FDC);
+	spin_unlock_irq(&ataflop_lock);
+}
+
 static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
 				     const struct blk_mq_queue_data *bd)
 {
@@ -1947,6 +1956,7 @@ static const struct block_device_operations floppy_fops = {
 
 static const struct blk_mq_ops ataflop_mq_ops = {
 	.queue_rq = ataflop_queue_rq,
+	.commit_rqs = ataflop_commit_rqs,
 };
 
 static struct kobject *floppy_find(dev_t dev, int *part, void *data)
@@ -1982,6 +1992,7 @@ static int __init atari_floppy_init (void)
 							   &ataflop_mq_ops, 2,
 							   BLK_MQ_F_SHOULD_MERGE);
 		if (IS_ERR(unit[i].disk->queue)) {
+			put_disk(unit[i].disk);
 			ret = PTR_ERR(unit[i].disk->queue);
 			unit[i].disk->queue = NULL;
 			goto err;
@@ -2033,18 +2044,13 @@ static int __init atari_floppy_init (void)
 	return 0;
 
 err:
-	do {
+	while (--i >= 0) {
 		struct gendisk *disk = unit[i].disk;
 
-		if (disk) {
-			if (disk->queue) {
-				blk_cleanup_queue(disk->queue);
-				disk->queue = NULL;
-			}
-			blk_mq_free_tag_set(&unit[i].tag_set);
-			put_disk(unit[i].disk);
-		}
-	} while (i--);
+		blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&unit[i].tag_set);
+		put_disk(unit[i].disk);
+	}
 
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 	return ret;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index fa8204214ac0..f973a2a845c8 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2792,7 +2792,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	drbd_init_set_defaults(device);
 
-	q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, &resource->req_lock);
+	q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE);
 	if (!q)
 		goto out_no_q;
 	device->rq_queue = q;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index fb23578e9a41..6f2856c6d0f2 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2231,7 +2231,6 @@ static void request_done(int uptodate)
 {
 	struct request *req = current_req;
 	struct request_queue *q;
-	unsigned long flags;
 	int block;
 	char msg[sizeof("request done ") + sizeof(int) * 3];
 
@@ -2254,10 +2253,7 @@ static void request_done(int uptodate)
 		if (block > _floppy->sect)
 			DRS->maxtrack = 1;
 
-		/* unlock chained buffers */
-		spin_lock_irqsave(q->queue_lock, flags);
 		floppy_end_request(req, 0);
-		spin_unlock_irqrestore(q->queue_lock, flags);
 	} else {
 		if (rq_data_dir(req) == WRITE) {
 			/* record write error information */
@@ -2269,9 +2265,7 @@ static void request_done(int uptodate)
 			DRWE->last_error_sector = blk_rq_pos(req);
 			DRWE->last_error_generation = DRS->generation;
 		}
-		spin_lock_irqsave(q->queue_lock, flags);
 		floppy_end_request(req, BLK_STS_IOERR);
-		spin_unlock_irqrestore(q->queue_lock, flags);
 	}
 }
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cb0cc8685076..0939f36548c9 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -77,13 +77,14 @@
 #include <linux/falloc.h>
 #include <linux/uio.h>
 #include <linux/ioprio.h>
+#include <linux/blk-cgroup.h>
 
 #include "loop.h"
 
 #include <linux/uaccess.h>
 
 static DEFINE_IDR(loop_index_idr);
-static DEFINE_MUTEX(loop_index_mutex);
+static DEFINE_MUTEX(loop_ctl_mutex);
 
 static int max_part;
 static int part_shift;
@@ -630,18 +631,7 @@ static void loop_reread_partitions(struct loop_device *lo,
 {
 	int rc;
 
-	/*
-	 * bd_mutex has been held already in release path, so don't
-	 * acquire it if this function is called in such case.
-	 *
-	 * If the reread partition isn't from release path, lo_refcnt
-	 * must be at least one and it can only become zero when the
-	 * current holder is released.
-	 */
-	if (!atomic_read(&lo->lo_refcnt))
-		rc = __blkdev_reread_part(bdev);
-	else
-		rc = blkdev_reread_part(bdev);
+	rc = blkdev_reread_part(bdev);
 	if (rc)
 		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
 			__func__, lo->lo_number, lo->lo_file_name, rc);
@@ -688,26 +678,30 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
 static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
-	struct file	*file, *old_file;
+	struct file	*file = NULL, *old_file;
 	int		error;
+	bool		partscan;
 
+	error = mutex_lock_killable(&loop_ctl_mutex);
+	if (error)
+		return error;
 	error = -ENXIO;
 	if (lo->lo_state != Lo_bound)
-		goto out;
+		goto out_err;
 
 	/* the loop device has to be read-only */
 	error = -EINVAL;
 	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
-		goto out;
+		goto out_err;
 
 	error = -EBADF;
 	file = fget(arg);
 	if (!file)
-		goto out;
+		goto out_err;
 
 	error = loop_validate_file(file, bdev);
 	if (error)
-		goto out_putf;
+		goto out_err;
 
 	old_file = lo->lo_backing_file;
 
@@ -715,7 +709,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 
 	/* size of the new backing store needs to be the same */
 	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
-		goto out_putf;
+		goto out_err;
 
 	/* and ... switch */
 	blk_mq_freeze_queue(lo->lo_queue);
@@ -726,15 +720,22 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 	loop_update_dio(lo);
 	blk_mq_unfreeze_queue(lo->lo_queue);
-
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
+	mutex_unlock(&loop_ctl_mutex);
+	/*
+	 * We must drop file reference outside of loop_ctl_mutex as dropping
+	 * the file ref can take bd_mutex which creates circular locking
+	 * dependency.
+	 */
 	fput(old_file);
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
+	if (partscan)
 		loop_reread_partitions(lo, bdev);
 	return 0;
 
- out_putf:
-	fput(file);
- out:
+out_err:
+	mutex_unlock(&loop_ctl_mutex);
+	if (file)
+		fput(file);
 	return error;
 }
 
@@ -909,6 +910,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	int		lo_flags = 0;
 	int		error;
 	loff_t		size;
+	bool		partscan;
 
 	/* This is safe, since we have a reference from open(). */
 	__module_get(THIS_MODULE);
@@ -918,13 +920,17 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (!file)
 		goto out;
 
+	error = mutex_lock_killable(&loop_ctl_mutex);
+	if (error)
+		goto out_putf;
+
 	error = -EBUSY;
 	if (lo->lo_state != Lo_unbound)
-		goto out_putf;
+		goto out_unlock;
 
 	error = loop_validate_file(file, bdev);
 	if (error)
-		goto out_putf;
+		goto out_unlock;
 
 	mapping = file->f_mapping;
 	inode = mapping->host;
@@ -936,10 +942,10 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	error = -EFBIG;
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
-		goto out_putf;
+		goto out_unlock;
 	error = loop_prepare_queue(lo);
 	if (error)
-		goto out_putf;
+		goto out_unlock;
 
 	error = 0;
 
@@ -971,18 +977,22 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_state = Lo_bound;
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
-		loop_reread_partitions(lo, bdev);
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 
 	/* Grab the block_device to prevent its destruction after we
-	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
+	 * put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev).
 	 */
 	bdgrab(bdev);
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan)
+		loop_reread_partitions(lo, bdev);
 	return 0;
 
- out_putf:
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+out_putf:
 	fput(file);
- out:
+out:
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return error;
@@ -1025,39 +1035,31 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
 	return err;
 }
 
-static int loop_clr_fd(struct loop_device *lo)
+static int __loop_clr_fd(struct loop_device *lo, bool release)
 {
-	struct file *filp = lo->lo_backing_file;
+	struct file *filp = NULL;
 	gfp_t gfp = lo->old_gfp_mask;
 	struct block_device *bdev = lo->lo_device;
+	int err = 0;
+	bool partscan = false;
+	int lo_number;
 
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
-
-	/*
-	 * If we've explicitly asked to tear down the loop device,
-	 * and it has an elevated reference count, set it for auto-teardown when
-	 * the last reference goes away. This stops $!~#$@ udev from
-	 * preventing teardown because it decided that it needs to run blkid on
-	 * the loopback device whenever they appear. xfstests is notorious for
-	 * failing tests because blkid via udev races with a losetup
-	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
-	 * command to fail with EBUSY.
-	 */
-	if (atomic_read(&lo->lo_refcnt) > 1) {
-		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
-		mutex_unlock(&lo->lo_ctl_mutex);
-		return 0;
+	mutex_lock(&loop_ctl_mutex);
+	if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
+		err = -ENXIO;
+		goto out_unlock;
 	}
 
-	if (filp == NULL)
-		return -EINVAL;
+	filp = lo->lo_backing_file;
+	if (filp == NULL) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	/* freeze request queue during the transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
 	spin_lock_irq(&lo->lo_lock);
-	lo->lo_state = Lo_rundown;
 	lo->lo_backing_file = NULL;
 	spin_unlock_irq(&lo->lo_lock);
 
@@ -1093,21 +1095,73 @@ static int loop_clr_fd(struct loop_device *lo)
 	module_put(THIS_MODULE);
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
-		loop_reread_partitions(lo, bdev);
+	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
+	lo_number = lo->lo_number;
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
 	loop_unprepare_queue(lo);
-	mutex_unlock(&lo->lo_ctl_mutex);
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan) {
+		/*
+		 * bd_mutex has been held already in release path, so don't
+		 * acquire it if this function is called in such case.
+		 *
+		 * If the reread partition isn't from release path, lo_refcnt
+		 * must be at least one and it can only become zero when the
+		 * current holder is released.
+		 */
+		if (release)
+			err = __blkdev_reread_part(bdev);
+		else
+			err = blkdev_reread_part(bdev);
+		pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
+			__func__, lo_number, err);
+		/* Device is gone, no point in returning error */
+		err = 0;
+	}
 	/*
-	 * Need not hold lo_ctl_mutex to fput backing file.
-	 * Calling fput holding lo_ctl_mutex triggers a circular
+	 * Need not hold loop_ctl_mutex to fput backing file.
+	 * Calling fput holding loop_ctl_mutex triggers a circular
 	 * lock dependency possibility warning as fput can take
-	 * bd_mutex which is usually taken before lo_ctl_mutex.
+	 * bd_mutex which is usually taken before loop_ctl_mutex.
 	 */
-	fput(filp);
-	return 0;
+	if (filp)
+		fput(filp);
+	return err;
+}
+
+static int loop_clr_fd(struct loop_device *lo)
+{
+	int err;
+
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
+	if (lo->lo_state != Lo_bound) {
+		mutex_unlock(&loop_ctl_mutex);
+		return -ENXIO;
+	}
+	/*
+	 * If we've explicitly asked to tear down the loop device,
+	 * and it has an elevated reference count, set it for auto-teardown when
+	 * the last reference goes away. This stops $!~#$@ udev from
+	 * preventing teardown because it decided that it needs to run blkid on
+	 * the loopback device whenever they appear. xfstests is notorious for
+	 * failing tests because blkid via udev races with a losetup
+	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
+	 * command to fail with EBUSY.
+	 */
+	if (atomic_read(&lo->lo_refcnt) > 1) {
+		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
+		mutex_unlock(&loop_ctl_mutex);
+		return 0;
+	}
+	lo->lo_state = Lo_rundown;
+	mutex_unlock(&loop_ctl_mutex);
+
+	return __loop_clr_fd(lo, false);
 }
 
 static int
@@ -1116,47 +1170,58 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	struct loop_func_table *xfer;
 	kuid_t uid = current_uid();
+	struct block_device *bdev;
+	bool partscan = false;
 
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
 	if (lo->lo_encrypt_key_size &&
 	    !uid_eq(lo->lo_key_owner, uid) &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	if (lo->lo_state != Lo_bound)
-		return -ENXIO;
-	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
-		return -EINVAL;
+	    !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+	if (lo->lo_state != Lo_bound) {
+		err = -ENXIO;
+		goto out_unlock;
+	}
+	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 
 	/* I/O need to be drained during transfer transition */
 	blk_mq_freeze_queue(lo->lo_queue);
 
 	err = loop_release_xfer(lo);
 	if (err)
-		goto exit;
+		goto out_unfreeze;
 
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
 
 		if (type >= MAX_LO_CRYPT) {
 			err = -EINVAL;
-			goto exit;
+			goto out_unfreeze;
 		}
 		xfer = xfer_funcs[type];
 		if (xfer == NULL) {
 			err = -EINVAL;
-			goto exit;
+			goto out_unfreeze;
 		}
 	} else
 		xfer = NULL;
 
 	err = loop_init_xfer(lo, xfer, info);
 	if (err)
-		goto exit;
+		goto out_unfreeze;
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
 		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
 			err = -EFBIG;
-			goto exit;
+			goto out_unfreeze;
 		}
 	}
 
@@ -1188,15 +1253,20 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
- exit:
+out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue);
 
 	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
 	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
-		loop_reread_partitions(lo, lo->lo_device);
+		bdev = lo->lo_device;
+		partscan = true;
 	}
+out_unlock:
+	mutex_unlock(&loop_ctl_mutex);
+	if (partscan)
+		loop_reread_partitions(lo, bdev);
 
 	return err;
 }
@@ -1204,12 +1274,15 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 static int
 loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 {
-	struct file *file;
+	struct path path;
 	struct kstat stat;
 	int ret;
 
+	ret = mutex_lock_killable(&loop_ctl_mutex);
+	if (ret)
+		return ret;
 	if (lo->lo_state != Lo_bound) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+		mutex_unlock(&loop_ctl_mutex);
 		return -ENXIO;
 	}
 
@@ -1228,17 +1301,17 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
 		       lo->lo_encrypt_key_size);
 	}
 
-	/* Drop lo_ctl_mutex while we call into the filesystem. */
-	file = get_file(lo->lo_backing_file);
-	mutex_unlock(&lo->lo_ctl_mutex);
-	ret = vfs_getattr(&file->f_path, &stat, STATX_INO,
-			  AT_STATX_SYNC_AS_STAT);
+	/* Drop loop_ctl_mutex while we call into the filesystem. */
+	path = lo->lo_backing_file->f_path;
+	path_get(&path);
+	mutex_unlock(&loop_ctl_mutex);
+	ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT);
 	if (!ret) {
 		info->lo_device = huge_encode_dev(stat.dev);
 		info->lo_inode = stat.ino;
 		info->lo_rdevice = huge_encode_dev(stat.rdev);
 	}
-	fput(file);
+	path_put(&path);
 	return ret;
 }
 
@@ -1322,10 +1395,8 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_old(&info64, &info);
@@ -1340,10 +1411,8 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err && copy_to_user(arg, &info64, sizeof(info64)))
 		err = -EFAULT;
@@ -1393,70 +1462,73 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	return 0;
 }
 
+static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
+			   unsigned long arg)
+{
+	int err;
+
+	err = mutex_lock_killable(&loop_ctl_mutex);
+	if (err)
+		return err;
+	switch (cmd) {
+	case LOOP_SET_CAPACITY:
+		err = loop_set_capacity(lo);
+		break;
+	case LOOP_SET_DIRECT_IO:
+		err = loop_set_dio(lo, arg);
+		break;
+	case LOOP_SET_BLOCK_SIZE:
+		err = loop_set_block_size(lo, arg);
+		break;
+	default:
+		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+	}
+	mutex_unlock(&loop_ctl_mutex);
+	return err;
+}
+
 static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
 	struct loop_device *lo = bdev->bd_disk->private_data;
 	int err;
 
-	err = mutex_lock_killable_nested(&lo->lo_ctl_mutex, 1);
-	if (err)
-		goto out_unlocked;
-
 	switch (cmd) {
 	case LOOP_SET_FD:
-		err = loop_set_fd(lo, mode, bdev, arg);
-		break;
+		return loop_set_fd(lo, mode, bdev, arg);
 	case LOOP_CHANGE_FD:
-		err = loop_change_fd(lo, bdev, arg);
-		break;
+		return loop_change_fd(lo, bdev, arg);
 	case LOOP_CLR_FD:
-		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
-		err = loop_clr_fd(lo);
-		if (!err)
-			goto out_unlocked;
-		break;
+		return loop_clr_fd(lo);
 	case LOOP_SET_STATUS:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
 			err = loop_set_status_old(lo,
 					(struct loop_info __user *)arg);
+		}
 		break;
 	case LOOP_GET_STATUS:
-		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
-		/* loop_get_status() unlocks lo_ctl_mutex */
-		goto out_unlocked;
+		return loop_get_status_old(lo, (struct loop_info __user *) arg);
 	case LOOP_SET_STATUS64:
 		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) {
 			err = loop_set_status64(lo,
 					(struct loop_info64 __user *) arg);
+		}
 		break;
 	case LOOP_GET_STATUS64:
-		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
-		/* loop_get_status() unlocks lo_ctl_mutex */
-		goto out_unlocked;
+		return loop_get_status64(lo, (struct loop_info64 __user *) arg);
 	case LOOP_SET_CAPACITY:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_capacity(lo);
-		break;
 	case LOOP_SET_DIRECT_IO:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_dio(lo, arg);
-		break;
 	case LOOP_SET_BLOCK_SIZE:
-		err = -EPERM;
-		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_block_size(lo, arg);
-		break;
+		if (!(mode & FMODE_WRITE) && !capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		/* Fall through */
 	default:
-		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+		err = lo_simple_ioctl(lo, cmd, arg);
+		break;
 	}
-	mutex_unlock(&lo->lo_ctl_mutex);
 
-out_unlocked:
 	return err;
 }
 
@@ -1570,10 +1642,8 @@ loop_get_status_compat(struct loop_device *lo,
 	struct loop_info64 info64;
 	int err;
 
-	if (!arg) {
-		mutex_unlock(&lo->lo_ctl_mutex);
+	if (!arg)
 		return -EINVAL;
-	}
 	err = loop_get_status(lo, &info64);
 	if (!err)
 		err = loop_info64_to_compat(&info64, arg);