Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

32 files changed, 1152 insertions, 632 deletions

diff --git a/block/Makefile b/block/Makefile
index b31b05390749..46ada9dc8bbf 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-y		:= bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
-			disk-events.o blk-ia-ranges.o
+			disk-events.o blk-ia-ranges.o early-lookup.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
diff --git a/block/bdev.c b/block/bdev.c
index 21c63bfef323..979e28a46b98 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -93,7 +93,7 @@ EXPORT_SYMBOL(invalidate_bdev);
  * Drop all buffers & page cache for given bdev range. This function bails
  * with error if bdev has other exclusive owner (such as filesystem).
  */
-int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode,
 			loff_t lstart, loff_t lend)
 {
 	/*
@@ -101,14 +101,14 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 	 * while we discard the buffer cache to avoid discarding buffers
 	 * under live filesystem.
 	 */
-	if (!(mode & FMODE_EXCL)) {
-		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
+	if (!(mode & BLK_OPEN_EXCL)) {
+		int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL);
 		if (err)
 			goto invalidate;
 	}
 
 	truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
-	if (!(mode & FMODE_EXCL))
+	if (!(mode & BLK_OPEN_EXCL))
 		bd_abort_claiming(bdev, truncate_bdev_range);
 	return 0;
 
@@ -308,7 +308,7 @@ EXPORT_SYMBOL(thaw_bdev);
  * pseudo-fs
  */
 
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
+static  __cacheline_aligned_in_smp DEFINE_MUTEX(bdev_lock);
 static struct kmem_cache * bdev_cachep __read_mostly;
 
 static struct inode *bdev_alloc_inode(struct super_block *sb)
@@ -415,6 +415,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	bdev = I_BDEV(inode);
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
+	mutex_init(&bdev->bd_holder_lock);
 	bdev->bd_partno = partno;
 	bdev->bd_inode = inode;
 	bdev->bd_queue = disk->queue;
@@ -463,39 +464,48 @@ long nr_blockdev_pages(void)
 /**
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
- * @whole: whole block device containing @bdev, may equal @bdev
  * @holder: holder trying to claim @bdev
+ * @hops: holder ops
  *
  * Test whether @bdev can be claimed by @holder.
  *
- * CONTEXT:
- * spin_lock(&bdev_lock).
- *
  * RETURNS:
  * %true if @bdev can be claimed, %false otherwise.
  */
-static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
-			 void *holder)
+static bool bd_may_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
-	if (bdev->bd_holder == holder)
-		return true;	 /* already a holder */
-	else if (bdev->bd_holder != NULL)
-		return false; 	 /* held by someone else */
-	else if (whole == bdev)
-		return true;  	 /* is a whole device which isn't held */
-
-	else if (whole->bd_holder == bd_may_claim)
-		return true; 	 /* is a partition of a device that is being partitioned */
-	else if (whole->bd_holder != NULL)
-		return false;	 /* is a partition of a held device */
-	else
-		return true;	 /* is a partition of an un-held device */
+	struct block_device *whole = bdev_whole(bdev);
+
+	lockdep_assert_held(&bdev_lock);
+
+	if (bdev->bd_holder) {
+		/*
+		 * The same holder can always re-claim.
+		 */
+		if (bdev->bd_holder == holder) {
+			if (WARN_ON_ONCE(bdev->bd_holder_ops != hops))
+				return false;
+			return true;
+		}
+		return false;
+	}
+
+	/*
+	 * If the whole devices holder is set to bd_may_claim, a partition on
+	 * the device is claimed, but not the whole device.
+	 */
+	if (whole != bdev &&
+	    whole->bd_holder && whole->bd_holder != bd_may_claim)
+		return false;
+	return true;
 }
 
 /**
  * bd_prepare_to_claim - claim a block device
  * @bdev: block device of interest
  * @holder: holder trying to claim @bdev
+ * @hops: holder ops.
  *
  * Claim @bdev.  This function fails if @bdev is already claimed by another
  * holder and waits if another claiming is in progress. return, the caller
@@ -504,17 +514,18 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
  * RETURNS:
  * 0 if @bdev can be claimed, -EBUSY otherwise.
  */
-int bd_prepare_to_claim(struct block_device *bdev, void *holder)
+int bd_prepare_to_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	struct block_device *whole = bdev_whole(bdev);
 
 	if (WARN_ON_ONCE(!holder))
 		return -EINVAL;
 retry:
-	spin_lock(&bdev_lock);
+	mutex_lock(&bdev_lock);
 	/* if someone else claimed, fail */
-	if (!bd_may_claim(bdev, whole, holder)) {
-		spin_unlock(&bdev_lock);
+	if (!bd_may_claim(bdev, holder, hops)) {
+		mutex_unlock(&bdev_lock);
 		return -EBUSY;
 	}
 
@@ -524,7 +535,7 @@ retry:
 		DEFINE_WAIT(wait);
 
 		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&bdev_lock);
+		mutex_unlock(&bdev_lock);
 		schedule();
 		finish_wait(wq, &wait);
 		goto retry;
@@ -532,7 +543,7 @@ retry:
 
 	/* yay, all mine */
 	whole->bd_claiming = holder;
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */
@@ -550,16 +561,18 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
  * bd_finish_claiming - finish claiming of a block device
  * @bdev: block device of interest
  * @holder: holder that has claimed @bdev
+ * @hops: block device holder operations
  *
  * Finish exclusive open of a block device. Mark the device as exlusively
  * open by the holder and wake up all waiters for exclusive open to finish.
  */
-static void bd_finish_claiming(struct block_device *bdev, void *holder)
+static void bd_finish_claiming(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	struct block_device *whole = bdev_whole(bdev);
 
-	spin_lock(&bdev_lock);
-	BUG_ON(!bd_may_claim(bdev, whole, holder));
+	mutex_lock(&bdev_lock);
+	BUG_ON(!bd_may_claim(bdev, holder, hops));
 	/*
 	 * Note that for a whole device bd_holders will be incremented twice,
 	 * and bd_holder will be set to bd_may_claim before being set to holder
@@ -567,9 +580,12 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder)
 	whole->bd_holders++;
 	whole->bd_holder = bd_may_claim;
 	bdev->bd_holders++;
+	mutex_lock(&bdev->bd_holder_lock);
 	bdev->bd_holder = holder;
+	bdev->bd_holder_ops = hops;
+	mutex_unlock(&bdev->bd_holder_lock);
 	bd_clear_claiming(whole, holder);
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 }
 
 /**
@@ -583,12 +599,47 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder)
  */
 void bd_abort_claiming(struct block_device *bdev, void *holder)
 {
-	spin_lock(&bdev_lock);
+	mutex_lock(&bdev_lock);
 	bd_clear_claiming(bdev_whole(bdev), holder);
-	spin_unlock(&bdev_lock);
+	mutex_unlock(&bdev_lock);
 }
 EXPORT_SYMBOL(bd_abort_claiming);
 
+static void bd_end_claim(struct block_device *bdev, void *holder)
+{
+	struct block_device *whole = bdev_whole(bdev);
+	bool unblock = false;
+
+	/*
+	 * Release a claim on the device.  The holder fields are protected with
+	 * bdev_lock.  open_mutex is used to synchronize disk_holder unlinking.
+	 */
+	mutex_lock(&bdev_lock);
+	WARN_ON_ONCE(bdev->bd_holder != holder);
+	WARN_ON_ONCE(--bdev->bd_holders < 0);
+	WARN_ON_ONCE(--whole->bd_holders < 0);
+	if (!bdev->bd_holders) {
+		mutex_lock(&bdev->bd_holder_lock);
+		bdev->bd_holder = NULL;
+		bdev->bd_holder_ops = NULL;
+		mutex_unlock(&bdev->bd_holder_lock);
+		if (bdev->bd_write_holder)
+			unblock = true;
+	}
+	if (!whole->bd_holders)
+		whole->bd_holder = NULL;
+	mutex_unlock(&bdev_lock);
+
+	/*
+	 * If this was the last claim, remove holder link and unblock evpoll if
+	 * it was a write holder.
+	 */
+	if (unblock) {
+		disk_unblock_events(bdev->bd_disk);
+		bdev->bd_write_holder = false;
+	}
+}
+
 static void blkdev_flush_mapping(struct block_device *bdev)
 {
 	WARN_ON_ONCE(bdev->bd_holders);
@@ -597,13 +648,13 @@ static void blkdev_flush_mapping(struct block_device *bdev)
 	bdev_write_inode(bdev);
 }
 
-static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
+static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	int ret;
 
 	if (disk->fops->open) {
-		ret = disk->fops->open(bdev, mode);
+		ret = disk->fops->open(disk, mode);
 		if (ret) {
 			/* avoid ghost partitions on a removed medium */
 			if (ret == -ENOMEDIUM &&
@@ -621,22 +672,19 @@ static int blkdev_get_whole(struct block_device *bdev, fmode_t mode)
 	return 0;
 }
 
-static void blkdev_put_whole(struct block_device *bdev, fmode_t mode)
+static void blkdev_put_whole(struct block_device *bdev)
 {
 	if (atomic_dec_and_test(&bdev->bd_openers))
 		blkdev_flush_mapping(bdev);
 	if (bdev->bd_disk->fops->release)
-		bdev->bd_disk->fops->release(bdev->bd_disk, mode);
+		bdev->bd_disk->fops->release(bdev->bd_disk);
 }
 
-static int blkdev_get_part(struct block_device *part, fmode_t mode)
+static int blkdev_get_part(struct block_device *part, blk_mode_t mode)
 {
 	struct gendisk *disk = part->bd_disk;
 	int ret;
 
-	if (atomic_read(&part->bd_openers))
-		goto done;
-
 	ret = blkdev_get_whole(bdev_whole(part), mode);
 	if (ret)
 		return ret;
@@ -645,26 +693,27 @@ static int blkdev_get_part(struct block_device *part, fmode_t mode)
 	if (!bdev_nr_sectors(part))
 		goto out_blkdev_put;
 
-	disk->open_partitions++;
-	set_init_blocksize(part);
-done:
+	if (!atomic_read(&part->bd_openers)) {
+		disk->open_partitions++;
+		set_init_blocksize(part);
+	}
 	atomic_inc(&part->bd_openers);
 	return 0;
 
 out_blkdev_put:
-	blkdev_put_whole(bdev_whole(part), mode);
+	blkdev_put_whole(bdev_whole(part));
 	return ret;
 }
 
-static void blkdev_put_part(struct block_device *part, fmode_t mode)
+static void blkdev_put_part(struct block_device *part)
 {
 	struct block_device *whole = bdev_whole(part);
 
-	if (!atomic_dec_and_test(&part->bd_openers))
-		return;
-	blkdev_flush_mapping(part);
-	whole->bd_disk->open_partitions--;
-	blkdev_put_whole(whole, mode);
+	if (atomic_dec_and_test(&part->bd_openers)) {
+		blkdev_flush_mapping(part);
+		whole->bd_disk->open_partitions--;
+	}
+	blkdev_put_whole(whole);
 }
 
 struct block_device *blkdev_get_no_open(dev_t dev)
@@ -695,17 +744,17 @@ void blkdev_put_no_open(struct block_device *bdev)
 {
 	put_device(&bdev->bd_device);
 }
-
+	
 /**
  * blkdev_get_by_dev - open a block device by device number
  * @dev: device number of block device to open
- * @mode: FMODE_* mask
+ * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
+ * @hops: holder operations
  *
- * Open the block device described by device number @dev. If @mode includes
- * %FMODE_EXCL, the block device is opened with exclusive access.  Specifying
- * %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may nest for
- * the same @holder.
+ * Open the block device described by device number @dev. If @holder is not
+ * %NULL, the block device is opened with exclusive access.  Exclusive opens may
+ * nest for the same @holder.
  *
  * Use this interface ONLY if you really do not have anything better - i.e. when
  * you are behind a truly sucky interface and all you are given is a device
@@ -717,7 +766,8 @@ void blkdev_put_no_open(struct block_device *bdev)
  * RETURNS:
  * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
+struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	bool unblock_events = true;
 	struct block_device *bdev;
@@ -726,8 +776,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 
 	ret = devcgroup_check_permission(DEVCG_DEV_BLOCK,
 			MAJOR(dev), MINOR(dev),
-			((mode & FMODE_READ) ? DEVCG_ACC_READ : 0) |
-			((mode & FMODE_WRITE) ? DEVCG_ACC_WRITE : 0));
+			((mode & BLK_OPEN_READ) ? DEVCG_ACC_READ : 0) |
+			((mode & BLK_OPEN_WRITE) ? DEVCG_ACC_WRITE : 0));
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -736,10 +786,16 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		return ERR_PTR(-ENXIO);
 	disk = bdev->bd_disk;
 
-	if (mode & FMODE_EXCL) {
-		ret = bd_prepare_to_claim(bdev, holder);
+	if (holder) {
+		mode |= BLK_OPEN_EXCL;
+		ret = bd_prepare_to_claim(bdev, holder, hops);
 		if (ret)
 			goto put_blkdev;
+	} else {
+		if (WARN_ON_ONCE(mode & BLK_OPEN_EXCL)) {
+			ret = -EIO;
+			goto put_blkdev;
+		}
 	}
 
 	disk_block_events(disk);
@@ -756,8 +812,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
 		goto put_module;
-	if (mode & FMODE_EXCL) {
-		bd_finish_claiming(bdev, holder);
+	if (holder) {
+		bd_finish_claiming(bdev, holder, hops);
 
 		/*
 		 * Block event polling for write claims if requested.  Any write
@@ -766,7 +822,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 		 * writeable reference is too fragile given the way @mode is
 		 * used in blkdev_get/put().
 		 */
-		if ((mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder &&
 		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			unblock_events = false;
@@ -780,7 +836,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 put_module:
 	module_put(disk->fops->owner);
 abort_claiming:
-	if (mode & FMODE_EXCL)
+	if (holder)
 		bd_abort_claiming(bdev, holder);
 	mutex_unlock(&disk->open_mutex);
 	disk_unblock_events(disk);
@@ -793,13 +849,13 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
 /**
  * blkdev_get_by_path - open a block device by name
  * @path: path to the block device to open
- * @mode: FMODE_* mask
+ * @mode: open mode (BLK_OPEN_*)
  * @holder: exclusive holder identifier
+ * @hops: holder operations
  *
- * Open the block device described by the device file at @path.  If @mode
- * includes %FMODE_EXCL, the block device is opened with exclusive access.
- * Specifying %FMODE_EXCL with a %NULL @holder is invalid.  Exclusive opens may
- * nest for the same @holder.
+ * Open the block device described by the device file at @path.  If @holder is
+ * not %NULL, the block device is opened with exclusive access.  Exclusive opens
+ * may nest for the same @holder.
  *
  * CONTEXT:
  * Might sleep.
@@ -807,8 +863,8 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
  * RETURNS:
  * Reference to the block_device on success, ERR_PTR(-errno) on failure.
  */
-struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-					void *holder)
+struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
+		void *holder, const struct blk_holder_ops *hops)
 {
 	struct block_device *bdev;
 	dev_t dev;
@@ -818,9 +874,9 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 	if (error)
 		return ERR_PTR(error);
 
-	bdev = blkdev_get_by_dev(dev, mode, holder);
-	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
-		blkdev_put(bdev, mode);
+	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
+	if (!IS_ERR(bdev) && (mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
+		blkdev_put(bdev, holder);
 		return ERR_PTR(-EACCES);
 	}
 
@@ -828,7 +884,7 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(blkdev_get_by_path);
 
-void blkdev_put(struct block_device *bdev, fmode_t mode)
+void blkdev_put(struct block_device *bdev, void *holder)
 {
 	struct gendisk *disk = bdev->bd_disk;
 
@@ -843,36 +899,8 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		sync_blockdev(bdev);
 
 	mutex_lock(&disk->open_mutex);
-	if (mode & FMODE_EXCL) {
-		struct block_device *whole = bdev_whole(bdev);
-		bool bdev_free;
-
-		/*
-		 * Release a claim on the device.  The holder fields
-		 * are protected with bdev_lock.  open_mutex is to
-		 * synchronize disk_holder unlinking.
-		 */
-		spin_lock(&bdev_lock);
-
-		WARN_ON_ONCE(--bdev->bd_holders < 0);
-		WARN_ON_ONCE(--whole->bd_holders < 0);
-
-		if ((bdev_free = !bdev->bd_holders))
-			bdev->bd_holder = NULL;
-		if (!whole->bd_holders)
-			whole->bd_holder = NULL;
-
-		spin_unlock(&bdev_lock);
-
-		/*
-		 * If this was the last claim, remove holder link and
-		 * unblock evpoll if it was a write holder.
-		 */
-		if (bdev_free && bdev->bd_write_holder) {
-			disk_unblock_events(disk);
-			bdev->bd_write_holder = false;
-		}
-	}
+	if (holder)
+		bd_end_claim(bdev, holder);
 
 	/*
 	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -882,9 +910,9 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 	disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE);
 
 	if (bdev_is_partition(bdev))
-		blkdev_put_part(bdev, mode);
+		blkdev_put_part(bdev);
 	else
-		blkdev_put_whole(bdev, mode);
+		blkdev_put_whole(bdev);
 	mutex_unlock(&disk->open_mutex);
 
 	module_put(disk->fops->owner);
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3164e3177965..09bbbcf9e049 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5403,6 +5403,10 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 	if (bfqq->bfqd->last_completed_rq_bfqq == bfqq)
 		bfqq->bfqd->last_completed_rq_bfqq = NULL;
 
+	WARN_ON_ONCE(!list_empty(&bfqq->fifo));
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&bfqq->sort_list));
+	WARN_ON_ONCE(bfqq->dispatched);
+
 	kmem_cache_free(bfq_pool, bfqq);
 	bfqg_and_blkg_put(bfqg);
 }
@@ -7135,6 +7139,7 @@ static void bfq_exit_queue(struct elevator_queue *e)
 {
 	struct bfq_data *bfqd = e->elevator_data;
 	struct bfq_queue *bfqq, *n;
+	unsigned int actuator;
 
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
@@ -7143,6 +7148,10 @@ static void bfq_exit_queue(struct elevator_queue *e)
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	spin_unlock_irq(&bfqd->lock);
 
+	for (actuator = 0; actuator < bfqd->num_actuators; actuator++)
+		WARN_ON_ONCE(bfqd->rq_in_driver[actuator]);
+	WARN_ON_ONCE(bfqd->tot_rq_in_driver);
+
 	hrtimer_cancel(&bfqd->idle_slice_timer);
 
 	/* release oom-queue reference to root group */
diff --git a/block/bio.c b/block/bio.c
index 043944fd46eb..8672179213b9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1138,6 +1138,14 @@ int bio_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_add_page);
 
+void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
+			  size_t off)
+{
+	WARN_ON_ONCE(len > UINT_MAX);
+	WARN_ON_ONCE(off > UINT_MAX);
+	__bio_add_page(bio, &folio->page, len, off);
+}
+
 /**
  * bio_add_folio - Attempt to add part of a folio to a bio.
  * @bio: BIO to add to.
@@ -1169,7 +1177,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty)
 	bio_for_each_segment_all(bvec, bio, iter_all) {
 		if (mark_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		bio_release_page(bio, bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1191,7 +1199,6 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
 	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
 	bio->bi_iter.bi_bvec_done = iter->iov_offset;
 	bio->bi_iter.bi_size = size;
-	bio_set_flag(bio, BIO_NO_PAGE_REF);
 	bio_set_flag(bio, BIO_CLONED);
 }
 
@@ -1206,7 +1213,7 @@ static int bio_iov_add_page(struct bio *bio, struct page *page,
 	}
 
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1220,7 +1227,7 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
 			queue_max_zone_append_sectors(q), &same_page) != len)
 		return -EINVAL;
 	if (same_page)
-		put_page(page);
+		bio_release_page(bio, page);
 	return 0;
 }
 
@@ -1231,10 +1238,10 @@ static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page,
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
- * For multi-segment *iter, this function only adds pages from the
- * next non-empty segment of the iov iterator.
+ * Extracts pages from *iter and appends them to @bio's bvec array.  The pages
+ * will have to be cleaned up in the way indicated by the BIO_PAGE_PINNED flag.
+ * For a multi-segment *iter, this function only adds pages from the next
+ * non-empty segment of the iov iterator.
  */
 static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
@@ -1266,9 +1273,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	 * result to ensure the bio's total size is correct. The remainder of
 	 * the iov data will be picked up in the next bio iteration.
 	 */
-	size = iov_iter_get_pages(iter, pages,
-				  UINT_MAX - bio->bi_iter.bi_size,
-				  nr_pages, &offset, extraction_flags);
+	size = iov_iter_extract_pages(iter, &pages,
+				      UINT_MAX - bio->bi_iter.bi_size,
+				      nr_pages, extraction_flags, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 
@@ -1301,7 +1308,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	iov_iter_revert(iter, left);
 out:
 	while (i < nr_pages)
-		put_page(pages[i++]);
+		bio_release_page(bio, pages[i++]);
 
 	return ret;
 }
@@ -1336,6 +1343,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 		return 0;
 	}
 
+	if (iov_iter_extract_will_pin(iter))
+		bio_set_flag(bio, BIO_PAGE_PINNED);
 	do {
 		ret = __bio_iov_iter_get_pages(bio, iter);
 	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));
@@ -1489,8 +1498,8 @@ void bio_set_pages_dirty(struct bio *bio)
  * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
- * here on.  It will run one put_page() against each page and will run one
- * bio_put() against the BIO.
+ * here on.  It will unpin each page and will run one bio_put() against the
+ * BIO.
  */
 
 static void bio_dirty_fn(struct work_struct *work);
diff --git a/block/blk-cgroup-fc-appid.c b/block/blk-cgroup-fc-appid.c
index 842e5e1c0f3c..3ec21333f393 100644
--- a/block/blk-cgroup-fc-appid.c
+++ b/block/blk-cgroup-fc-appid.c
@@ -34,7 +34,7 @@ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len)
 	 * the vmid from the fabric.
 	 * Adding the overhead of a lock is not necessary.
 	 */
-	strlcpy(blkcg->fc_app_id, app_id, app_id_len);
+	strscpy(blkcg->fc_app_id, app_id, app_id_len);
 	css_put(css);
 out_cgrp_put:
 	cgroup_put(cgrp);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index dce1548a7a0c..aaf9903ad7b2 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -624,8 +624,13 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 			struct blkg_iostat_set *bis =
 				per_cpu_ptr(blkg->iostat_cpu, cpu);
 			memset(bis, 0, sizeof(*bis));
+
+			/* Re-initialize the cleared blkg_iostat_set */
+			u64_stats_init(&bis->sync);
+			bis->blkg = blkg;
 		}
 		memset(&blkg->iostat, 0, sizeof(blkg->iostat));
+		u64_stats_init(&blkg->iostat.sync);
 
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
@@ -762,6 +767,13 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 		return -ENODEV;
 	}
 
+	mutex_lock(&bdev->bd_queue->rq_qos_mutex);
+	if (!disk_live(bdev->bd_disk)) {
+		blkdev_put_no_open(bdev);
+		mutex_unlock(&bdev->bd_queue->rq_qos_mutex);
+		return -ENODEV;
+	}
+
 	ctx->body = input;
 	ctx->bdev = bdev;
 	return 0;
@@ -906,6 +918,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
  */
 void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 	__releases(&ctx->bdev->bd_queue->queue_lock)
+	__releases(&ctx->bdev->bd_queue->rq_qos_mutex)
 {
 	if (ctx->blkg) {
 		spin_unlock_irq(&bdev_get_queue(ctx->bdev)->queue_lock);
@@ -913,6 +926,7 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 	}
 
 	if (ctx->bdev) {
+		mutex_unlock(&ctx->bdev