1 files changed, 172 insertions, 393 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 9387f050c248..b84b8671e627 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -17,7 +17,6 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
-#include <linux/kobj_map.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
 #include <linux/log2.h>
@@ -26,17 +25,13 @@
 
 #include "blk.h"
 
-static DEFINE_MUTEX(block_class_lock);
 static struct kobject *block_depr;
 
+DECLARE_RWSEM(bdev_lookup_sem);
+
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
-
-/* For extended devt allocation.  ext_devt_lock prevents look up
- * results from going away underneath its user.
- */
-static DEFINE_SPINLOCK(ext_devt_lock);
-static DEFINE_IDR(ext_devt_idr);
+static DEFINE_IDA(ext_devt_ida);
 
 static void disk_check_events(struct disk_events *ev,
 			      unsigned int *clearing_ptr);
@@ -45,30 +40,49 @@ static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
 static void disk_release_events(struct gendisk *disk);
 
+void set_capacity(struct gendisk *disk, sector_t sectors)
+{
+	struct block_device *bdev = disk->part0;
+
+	spin_lock(&bdev->bd_size_lock);
+	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
+	spin_unlock(&bdev->bd_size_lock);
+}
+EXPORT_SYMBOL(set_capacity);
+
 /*
- * Set disk capacity and notify if the size is not currently
- * zero and will not be set to zero
+ * Set disk capacity and notify if the size is not currently zero and will not
+ * be set to zero.  Returns true if a uevent was sent, otherwise false.
  */
-bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
-					bool update_bdev)
+bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
 {
 	sector_t capacity = get_capacity(disk);
+	char *envp[] = { "RESIZE=1", NULL };
 
 	set_capacity(disk, size);
-	if (update_bdev)
-		revalidate_disk_size(disk, true);
 
-	if (capacity != size && capacity != 0 && size != 0) {
-		char *envp[] = { "RESIZE=1", NULL };
+	/*
+	 * Only print a message and send a uevent if the gendisk is user visible
+	 * and alive.  This avoids spamming the log and udev when setting the
+	 * initial capacity during probing.
+	 */
+	if (size == capacity ||
+	    (disk->flags & (GENHD_FL_UP | GENHD_FL_HIDDEN)) != GENHD_FL_UP)
+		return false;
 
-		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
-		return true;
-	}
+	pr_info("%s: detected capacity change from %lld to %lld\n",
+		disk->disk_name, size, capacity);
 
-	return false;
+	/*
+	 * Historically we did not send a uevent for changes to/from an empty
+	 * device.
+	 */
+	if (!capacity || !size)
+		return false;
+	kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+	return true;
 }
-
-EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
+EXPORT_SYMBOL_GPL(set_capacity_and_notify);
 
 /*
  * Format the device name of the indicated disk into the supplied buffer and
@@ -92,13 +106,14 @@ const char *bdevname(struct block_device *bdev, char *buf)
 }
 EXPORT_SYMBOL(bdevname);
 
-static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+static void part_stat_read_all(struct block_device *part,
+		struct disk_stats *stat)
 {
 	int cpu;
 
 	memset(stat, 0, sizeof(struct disk_stats));
 	for_each_possible_cpu(cpu) {
-		struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu);
 		int group;
 
 		for (group = 0; group < NR_STAT_GROUPS; group++) {
@@ -112,7 +127,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
 	}
 }
 
-static unsigned int part_in_flight(struct hd_struct *part)
+static unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;
@@ -127,7 +142,8 @@ static unsigned int part_in_flight(struct hd_struct *part)
 	return inflight;
 }
 
-static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
+static void part_in_flight_rw(struct block_device *part,
+		unsigned int inflight[2])
 {
 	int cpu;
 
@@ -143,7 +159,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
 		inflight[1] = 0;
 }
 
-struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
+struct block_device *__disk_get_part(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
 
@@ -153,33 +169,6 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
 }
 
 /**
- * disk_get_part - get partition
- * @disk: disk to look partition from
- * @partno: partition number
- *
- * Look for partition @partno from @disk.  If found, increment
- * reference count and return it.
- *
- * CONTEXT:
- * Don't care.
- *
- * RETURNS:
- * Pointer to the found partition on success, NULL if not found.
- */
-struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
-{
-	struct hd_struct *part;
-
-	rcu_read_lock();
-	part = __disk_get_part(disk, partno);
-	if (part)
-		get_device(part_to_dev(part));
-	rcu_read_unlock();
-
-	return part;
-}
-
-/**
  * disk_part_iter_init - initialize partition iterator
  * @piter: iterator to initialize
  * @disk: disk to iterate over
@@ -223,14 +212,13 @@ EXPORT_SYMBOL_GPL(disk_part_iter_init);
  * CONTEXT:
  * Don't care.
  */
-struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
+struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 {
 	struct disk_part_tbl *ptbl;
 	int inc, end;
 
 	/* put the last partition */
-	disk_put_part(piter->part);
-	piter->part = NULL;
+	disk_part_iter_exit(piter);
 
 	/* get part_tbl */
 	rcu_read_lock();
@@ -251,19 +239,20 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 
 	/* iterate to the next partition */
 	for (; piter->idx != end; piter->idx += inc) {
-		struct hd_struct *part;
+		struct block_device *part;
 
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!part_nr_sects_read(part) &&
+		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
 		      piter->idx == 0))
 			continue;
 
-		get_device(part_to_dev(part));
-		piter->part = part;
+		piter->part = bdgrab(part);
+		if (!piter->part)
+			continue;
 		piter->idx += inc;
 		break;
 	}
@@ -285,15 +274,16 @@ EXPORT_SYMBOL_GPL(disk_part_iter_next);
  */
 void disk_part_iter_exit(struct disk_part_iter *piter)
 {
-	disk_put_part(piter->part);
+	if (piter->part)
+		bdput(piter->part);
 	piter->part = NULL;
 }
 EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 
-static inline int sector_in_part(struct hd_struct *part, sector_t sector)
+static inline int sector_in_part(struct block_device *part, sector_t sector)
 {
-	return part->start_sect <= sector &&
-		sector < part->start_sect + part_nr_sects_read(part);
+	return part->bd_start_sect <= sector &&
+		sector < part->bd_start_sect + bdev_nr_sectors(part);
 }
 
 /**
@@ -305,44 +295,34 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector)
  * primarily used for stats accounting.
  *
  * CONTEXT:
- * RCU read locked.  The returned partition pointer is always valid
- * because its refcount is grabbed except for part0, which lifetime
- * is same with the disk.
+ * RCU read locked.
  *
  * RETURNS:
  * Found partition on success, part0 is returned if no partition matches
  * or the matched partition is being deleted.
  */
-struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
+struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 {
 	struct disk_part_tbl *ptbl;
-	struct hd_struct *part;
+	struct block_device *part;
 	int i;
 
 	rcu_read_lock();
 	ptbl = rcu_dereference(disk->part_tbl);
 
 	part = rcu_dereference(ptbl->last_lookup);
-	if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
+	if (part && sector_in_part(part, sector))
 		goto out_unlock;
 
 	for (i = 1; i < ptbl->len; i++) {
 		part = rcu_dereference(ptbl->part[i]);
-
 		if (part && sector_in_part(part, sector)) {
-			/*
-			 * only live partition can be cached for lookup,
-			 * so use-after-free on cached & deleting partition
-			 * can be avoided
-			 */
-			if (!hd_struct_try_get(part))
-				break;
 			rcu_assign_pointer(ptbl->last_lookup, part);
 			goto out_unlock;
 		}
 	}
 
-	part = &disk->part0;
+	part = disk->part0;
 out_unlock:
 	rcu_read_unlock();
 	return part;
@@ -393,7 +373,9 @@ static struct blk_major_name {
 	struct blk_major_name *next;
 	int major;
 	char name[16];
+	void (*probe)(dev_t devt);
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
+static DEFINE_MUTEX(major_names_lock);
 
 /* index in the above - for now: assume no multimajor ranges */
 static inline int major_to_index(unsigned major)
@@ -406,20 +388,21 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
 {
 	struct blk_major_name *dp;
 
-	mutex_lock(&block_class_lock);
+	mutex_lock(&major_names_lock);
 	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
 		if (dp->major == offset)
 			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
-	mutex_unlock(&block_class_lock);
+	mutex_unlock(&major_names_lock);
 }
 #endif /* CONFIG_PROC_FS */
 
 /**
- * register_blkdev - register a new block device
+ * __register_blkdev - register a new block device
  *
  * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If
  *         @major = 0, try to allocate any unused major number.
  * @name: the name of the new block device as a zero terminated string
+ * @probe: allback that is called on access to any minor number of @major
  *
  * The @name must be unique within the system.
  *
@@ -433,13 +416,16 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
  *
  * See Documentation/admin-guide/devices.txt for the list of allocated
  * major numbers.
+ *
+ * Use register_blkdev instead for any new code.
  */
-int register_blkdev(unsigned int major, const char *name)
+int __register_blkdev(unsigned int major, const char *name,
+		void (*probe)(dev_t devt))
 {
 	struct blk_major_name **n, *p;
 	int index, ret = 0;
 
-	mutex_lock(&block_class_lock);
+	mutex_lock(&major_names_lock);
 
 	/* temporary */
 	if (major == 0) {
@@ -473,6 +459,7 @@ int register_blkdev(unsigned int major, const char *name)
 	}
 
 	p->major = major;
+	p->probe = probe;
 	strlcpy(p->name, name, sizeof(p->name));
 	p->next = NULL;
 	index = major_to_index(major);
@@ -492,11 +479,10 @@ int register_blkdev(unsigned int major, const char *name)
 		kfree(p);
 	}
 out:
-	mutex_unlock(&block_class_lock);
+	mutex_unlock(&major_names_lock);
 	return ret;
 }
-
-EXPORT_SYMBOL(register_blkdev);
+EXPORT_SYMBOL(__register_blkdev);
 
 void unregister_blkdev(unsigned int major, const char *name)
 {
@@ -504,7 +490,7 @@ void unregister_blkdev(unsigned int major, const char *name)
 	struct blk_major_name *p = NULL;
 	int index = major_to_index(major);
 
-	mutex_lock(&block_class_lock);
+	mutex_lock(&major_names_lock);
 	for (n = &major_names[index]; *n; n = &(*n)->next)
 		if ((*n)->major == major)
 			break;
@@ -514,14 +500,12 @@ void unregister_blkdev(unsigned int major, const char *name)
 		p = *n;
 		*n = p->next;
 	}
-	mutex_unlock(&block_class_lock);
+	mutex_unlock(&major_names_lock);
 	kfree(p);
 }
 
 EXPORT_SYMBOL(unregister_blkdev);
 
-static struct kobj_map *bdev_map;
-
 /**
  * blk_mangle_minor - scatter minor numbers apart
  * @minor: minor number to mangle
@@ -555,8 +539,8 @@ static int blk_mangle_minor(int minor)
 }
 
 /**
- * blk_alloc_devt - allocate a dev_t for a partition
- * @part: partition to allocate dev_t for
+ * blk_alloc_devt - allocate a dev_t for a block device
+ * @bdev: block device to allocate dev_t for
  * @devt: out parameter for resulting dev_t
  *
  * Allocate a dev_t for block device.
@@ -568,25 +552,18 @@ static int blk_mangle_minor(int minor)
  * CONTEXT:
  * Might sleep.
  */
-int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
+int blk_alloc_devt(struct block_device *bdev, dev_t *devt)
 {
-	struct gendisk *disk = part_to_disk(part);
+	struct gendisk *disk = bdev->bd_disk;
 	int idx;
 
 	/* in consecutive minor range? */
-	if (part->partno < disk->minors) {
-		*devt = MKDEV(disk->major, disk->first_minor + part->partno);
+	if (bdev->bd_partno < disk->minors) {
+		*devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno);
 		return 0;
 	}
 
-	/* allocate ext devt */
-	idr_preload(GFP_KERNEL);
-
-	spin_lock_bh(&ext_devt_lock);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
-	spin_unlock_bh(&ext_devt_lock);
-
-	idr_preload_end();
+	idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL);
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -605,26 +582,8 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	if (devt == MKDEV(0, 0))
-		return;
-
-	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock_bh(&ext_devt_lock);
-		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		spin_unlock_bh(&ext_devt_lock);
-	}
-}
-
-/*
- * We invalidate devt by assigning NULL pointer for devt in idr.
- */
-void blk_invalidate_devt(dev_t devt)
-{
-	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock_bh(&ext_devt_lock);
-		idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt)));
-		spin_unlock_bh(&ext_devt_lock);
-	}
+	if (MAJOR(devt) == BLOCK_EXT_MAJOR)
+		ida_free(&ext_devt_ida, blk_mangle_minor(MINOR(devt)));
 }
 
 static char *bdevt_str(dev_t devt, char *buf)
@@ -639,43 +598,6 @@ static char *bdevt_str(dev_t devt, char *buf)
 	return buf;
 }
 
-/*
- * Register device numbers dev..(dev+range-1)
- * range must be nonzero
- * The hash chain is sorted on range, so that subranges can override.
- */
-void blk_register_region(dev_t devt, unsigned long range, struct module *module,
-			 struct kobject *(*probe)(dev_t, int *, void *),
-			 int (*lock)(dev_t, void *), void *data)
-{
-	kobj_map(bdev_map, devt, range, module, probe, lock, data);
-}
-
-EXPORT_SYMBOL(blk_register_region);
-
-void blk_unregister_region(dev_t devt, unsigned long range)
-{
-	kobj_unmap(bdev_map, devt, range);
-}
-
-EXPORT_SYMBOL(blk_unregister_region);
-
-static struct kobject *exact_match(dev_t devt, int *partno, void *data)
-{
-	struct gendisk *p = data;
-
-	return &disk_to_dev(p)->kobj;
-}
-
-static int exact_lock(dev_t devt, void *data)
-{
-	struct gendisk *p = data;
-
-	if (!get_disk_and_module(p))
-		return -1;
-	return 0;
-}
-
 static void disk_scan_partitions(struct gendisk *disk)
 {
 	struct block_device *bdev;
@@ -694,7 +616,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 {
 	struct device *ddev = disk_to_dev(disk);
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 	int err;
 
 	ddev->parent = parent;
@@ -726,7 +648,8 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	 */
 	pm_runtime_set_memalloc_noio(ddev, true);
 
-	disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+	disk->part0->bd_holder_dir =
+		kobject_create_and_add("holders", &ddev->kobj);
 	disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
 	if (disk->flags & GENHD_FL_HIDDEN) {
@@ -743,7 +666,7 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 	/* announce possible partitions */
 	disk_part_iter_init(&piter, disk, 0);
 	while ((part = disk_part_iter_next(&piter)))
-		kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+		kobject_uevent(bdev_kobj(part), KOBJ_ADD);
 	disk_part_iter_exit(&piter);
 
 	if (disk->queue->backing_dev_info->dev) {
@@ -792,7 +715,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 
 	disk->flags |= GENHD_FL_UP;
 
-	retval = blk_alloc_devt(&disk->part0, &devt);
+	retval = blk_alloc_devt(disk->part0, &devt);
 	if (retval) {
 		WARN_ON(1);
 		return;
@@ -819,8 +742,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk,
 		ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt));
 		WARN_ON(ret);
 		bdi_set_owner(bdi, dev);
-		blk_register_region(disk_devt(disk), disk->minors, NULL,
-				    exact_match, exact_lock, disk);
+		bdev_add(disk->part0, devt);
 	}
 	register_disk(parent, disk, groups);
 	if (register_queue)
@@ -850,23 +772,16 @@ void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk)
 }
 EXPORT_SYMBOL(device_add_disk_no_queue_reg);
 
-static void invalidate_partition(struct gendisk *disk, int partno)
+static void invalidate_partition(struct block_device *bdev)
 {
-	struct block_device *bdev;
-
-	bdev = bdget_disk(disk, partno);
-	if (!bdev)
-		return;
-
 	fsync_bdev(bdev);
 	__invalidate_device(bdev, true);
 
 	/*
-	 * Unhash the bdev inode for this device so that it gets evicted as soon
-	 * as last inode reference is dropped.
+	 * Unhash the bdev inode for this device so that it can't be looked
+	 * up any more even if openers still hold references to it.
 	 */
 	remove_inode_hash(bdev->bd_inode);
-	bdput(bdev);
 }
 
 /**
@@ -891,10 +806,13 @@ static void invalidate_partition(struct gendisk *disk, int partno)
 void del_gendisk(struct gendisk *disk)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	might_sleep();
 
+	if (WARN_ON_ONCE(!disk->queue))
+		return;
+
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
@@ -902,50 +820,39 @@ void del_gendisk(struct gendisk *disk)
 	 * Block lookups of the disk until all bdevs are unhashed and the
 	 * disk is marked as dead (GENHD_FL_UP cleared).
 	 */
-	down_write(&disk->lookup_sem);
+	down_write(&bdev_lookup_sem);
+
 	/* invalidate stuff */
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
-		invalidate_partition(disk, part->partno);
+		invalidate_partition(part);
 		delete_partition(part);
 	}
 	disk_part_iter_exit(&piter);
 
-	invalidate_partition(disk, 0);
+	invalidate_partition(disk->part0);
 	set_capacity(disk, 0);
 	disk->flags &= ~GENHD_FL_UP;
-	up_write(&disk->lookup_sem);
+	up_write(&bdev_lookup_sem);
 
-	if (!(disk->flags & GENHD_FL_HIDDEN))
+	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
-	if (disk->queue) {
+
 		/*
 		 * Unregister bdi before releasing device numbers (as they can
 		 * get reused and we'd get clashes in sysfs).
 		 */
-		if (!(disk->flags & GENHD_FL_HIDDEN))
-			bdi_unregister(disk->queue->backing_dev_info);
-		blk_unregister_queue(disk);
-	} else {
-		WARN_ON(1);
+		bdi_unregister(disk->queue->backing_dev_info);
 	}
 
-	if (!(disk->flags & GENHD_FL_HIDDEN))
-		blk_unregister_region(disk_devt(disk), disk->minors);
-	/*
-	 * Remove gendisk pointer from idr so that it cannot be looked up
-	 * while RCU period before freeing gendisk is running to prevent
-	 * use-after-free issues. Note that the device number stays
-	 * "in-use" until we really free the gendisk.
-	 */
-	blk_invalidate_devt(disk_devt(disk));
+	blk_unregister_queue(disk);
 
-	kobject_put(disk->part0.holder_dir);
+	kobject_put(disk->part0->bd_holder_dir);
 	kobject_put(disk->slave_dir);
 
-	part_stat_set_all(&disk->part0, 0);
-	disk->part0.stamp = 0;
+	part_stat_set_all(disk->part0, 0);
+	disk->part0->bd_stamp = 0;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -978,57 +885,24 @@ static ssize_t disk_badblocks_store(struct device *dev,
 	return badblocks_store(disk->bb, page, len, 0);
 }
 
-/**
- * get_gendisk - get partitioning information for a given device
- * @devt: device to get partitioning information for
- * @partno: returned partition index
- *
- * This function gets the structure containing partitioning
- * information for the given device @devt.
- *
- * Context: can sleep
- */
-struct gendisk *get_gendisk(dev_t devt, int *partno)
+void blk_request_module(dev_t devt)
 {
-	struct gendisk *disk = NULL;
-
-	might_sleep();
-
-	if (MAJOR(devt) != BLOCK_EXT_MAJOR) {
-		struct kobject *kobj;
-
-		kobj = kobj_lookup(bdev_map, devt, partno);
-		if (kobj)
-			disk = dev_to_disk(kobj_to_dev(kobj));
-	} else {
-		struct hd_struct *part;
+	unsigned int major = MAJOR(devt);
+	struct blk_major_name **n;
 
-		spin_lock_bh(&ext_devt_lock);
-		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		if (part && get_disk_and_module(part_to_disk(part))) {
-			*partno = part->partno;
-			disk = part_to_disk(part);
+	mutex_lock(&major_names_lock);
+	for (n = &major_names[major_to_index(major)]; *n; n = &(*n)->next) {
+		if ((*n)->major == major && (*n)->probe) {
+			(*n)->probe(devt);
+			mutex_unlock(&major_names_lock);
+			return;
 		}
-		spin_unlock_bh(&ext_devt_lock);
 	}
+	mutex_unlock(&major_names_lock);
 
-	if (!disk)
-		return NULL;
-
-	/*
-	 * Synchronize with del_gendisk() to not return disk that is being
-	 * destroyed.
-	 */
-	down_read(&disk->lookup_sem);
-	if (unlikely((disk->flags & GENHD_FL_HIDDEN) ||
-		     !(disk->flags & GENHD_FL_UP))) {
-		up_read(&disk->lookup_sem);
-		put_disk_and_module(disk);
-		disk = NULL;
-	} else {
-		up_read(&disk->lookup_sem);
-	}
-	return disk;
+	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
+		/* Make old-style 2.4 aliases work */
+		request_module("block-major-%d", MAJOR(devt));
 }
 
 /**
@@ -1046,17 +920,16 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
  */
 struct block_device *bdget_disk(struct gendisk *disk, int partno)
 {
-	struct hd_struct *part;
 	struct block_device *bdev = NULL;
 
-	part = disk_get_part(disk, partno);
-	if (part)
-		bdev = bdget_part(part);
-	disk_put_part(part);
+	rcu_read_lock();
+	bdev = __disk_get_part(disk, partno);
+	if (bdev && !bdgrab(bdev))
+		bdev = NULL;
+	rcu_read_unlock();
 
 	return bdev;
 }
-EXPORT_SYMBOL(bdget_disk);
 
 /*
  * print a full list of all partitions - intended for places where the root
@@ -1072,7 +945,7 @@ void __init printk_all_partitions(void)
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct gendisk *disk = dev_to_disk(dev);
 		struct disk_part_iter piter;
-		struct hd_struct *part;
+		struct block_device *part;
 		char name_buf[BDEVNAME_SIZE];
 		char devt_buf[BDEVT_SIZE];
 
@@ -1091,13 +964,14 @@ void __init printk_all_partitions(void)
 		 */
 		disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
 		while ((part = disk_part_iter_next(&piter))) {
-			bool is_part0 = part == &disk->part0;
+			bool is_part0 = part == disk->part0;
 
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
-			       bdevt_str(part_devt(part), devt_buf),
-			       (unsigned long long)part_nr_sects_read(part) >> 1
-			       , disk_name(disk, part->partno, name_buf),
-			       part->info ? part->info->uuid : "");
+			       bdevt_str(part->bd_dev, devt_buf),
+			       bdev_nr_sectors(part) >> 1,
+			       disk_name(disk, part->bd_partno, name_buf),
+			       part->bd_meta_info ?
+					part->bd_meta_info->uuid : "");
 			if (is_part0) {
 				if (dev->parent && dev->parent->driver)
 					printk(" driver: %s\n",
@@ -1173,7 +1047,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 {
 	struct gendisk *sgp = v;
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
@@ -1187,9 +1061,9 @@ static int show_partition(struct seq_file *seqf, void *v)
 	disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0);
 	while ((part = disk_part_iter_next(&piter)))
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
-			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
-			   (unsigned long long)part_nr_sects_read(part) >> 1,
-			   disk_name(sgp, part->partno, buf));
+			   MAJOR(part->bd_dev), MINOR(part->bd_dev),
+			   bdev_nr_sectors(part) >> 1,
+			   disk_name(sgp, part->bd_partno, buf));
 	disk_part_iter_exit(&piter);
 
 	return 0;
@@ -1203,15 +1077,6 @@ static const struct seq_operations partitions_op = {
 };
 #endif
 
-
-static struct kobject *base_probe(dev_t devt, int *partno, void *data)
-{
-	if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0)
-		/* Make old-style 2.4 aliases work */
-		request_module("block-major-%d", MAJOR(devt));
-	return NULL;
-}
-
 static int __init genhd_device_init(void)
 {
 	int error;
@@ -1220,7 +1085,6 @@ static int __init genhd_device_init(void)
 	error = class_register(&block_class);
 	if (unlikely(error))
 		return error;
-	bdev_map = kobj_map_init(base_probe, &block_class_lock);
 	blk_dev_init();
 
 	register_blkdev(BLOCK_EXT_MAJOR, "blkext");
@@ -1278,25 +1142,22 @@ static ssize_t disk_ro_show(struct device *dev,
 ssize_t part_size_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%llu\n",
-		(unsigned long long)part_nr_sects_read(p));
+	return sprintf(buf, "%llu\n", bdev_nr_sectors(dev_to_bdev(dev)));
 }
 
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = part_to_disk(p)->queue;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev->bd_disk->queue;
 	struct disk_stats stat;
 	unsigned int inflight;
 
-	part_stat_read_all(p, &stat);
+	part_stat_read_all(bdev, &stat);
 	if (queue_is_mq(q))
-		inflight = blk_mq_in_flight(q, p);
+		inflight = blk_mq_in_flight(q, bdev);
 	else
-		inflight = part_in_flight(p);
+		inflight = part_in_flight(bdev);
 
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
@@ -1331,14 +1192,14 @@ ssize_t part_stat_show(struct device *dev,
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	struct request_queue *q = part_to_disk(p)->queue;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev->bd_disk->queue;
 	unsigned int inflight[2];
 
 	if (queue_is_mq(q))
-		blk_mq_in_flight_rw(q, p, inflight);
+		blk_mq_in_flight_rw(q, bdev, inflight);
 	else
-		part_in_flight_rw(p, inflight);
+		part_in_flight_rw(bdev, inflight);
 
 	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
@@ -1386,20 +1247,17 @@ static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
 ssize_t part_fail_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%d\n", p->make_it_fail);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_make_it_fail);
 }
 
 ssize_t part_fail_store(struct device *dev,
 			struct device_attribute *attr,
 			const char *buf, size_t count)
 {
-	struct hd_struct *p = dev_to_part(dev);
 	int i;
 
 	if (count > 0 && sscanf(buf, "%d", &i) > 0)
-		p->make_it_fail = (i == 0) ? 0 : 1;
+		dev_to_bdev(dev)->bd_make_it_fail = i;
 
 	return count;
 }
@@ -1538,11 +1396,6 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
  *
  * This function releases all allocated resources of the gendisk.
  *
- * The struct gendisk refcount is incremented with get_gendisk() or
- * get_disk_and_module(), and its refcount is decremented with
- * put_disk_and_module() or put_disk(). Once the refcount reaches 0 this
- * function is called.
- *
  * Drivers which used __device_add_disk() have a gendisk with a request_queue
  * assigned. Since the request_queue sits on top of the gendisk for these
  * drivers we also call blk_put_queue() for them, and we expect the
@@ -1561,7 +1414,7 @@ static void disk_release(struct device *dev)
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
-	hd_free_part(&disk->part0);
+	bdput(disk->part0);
 	if (disk->queue)
 		blk_put_queue(disk->queue);
 	kfree(disk);
@@ -1599,7 +1452,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 {
 	struct gendisk *gp = v;
 	struct disk_part_iter piter;
-	struct hd_struct *hd;
+	struct block_device *hd;
 	char buf[BDEVNAME_SIZE];
 	unsigned int inflight;
 	struct disk_stats stat;
@@ -1627,8 +1480,8 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%lu %lu %lu %u "
 			   "%lu %u"
 			   "\n",
-			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
-			   disk_name(gp, hd->partno, buf),
+			   MAJOR(hd->bd_dev), MINOR(hd->bd_dev),
+			   disk_name(gp, hd->bd_partno, buf),
 			   stat.ios[STAT_READ],
 			   stat.merges[STAT_READ],
 			   stat.sectors[STAT_READ],
@@ -1686,7 +1539,7 @@ dev_t blk_lookup_devt(const char *name, int partno)
 	class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
 	while ((dev = class_dev_iter_next(&iter))) {
 		struct gendisk *disk = dev_to_disk(dev);
-		struct hd_struct *part;
+		struct block_device *part;
 
 		if (strcmp(dev_name(dev), name))
 			continue;
@@ -1699,13 +1552,12 @@ dev_t blk_lookup_devt(const char *name, int partno)
 				     MINOR(dev->devt) + partno);
 			break;
 		}
-		part = disk_get_part(disk, partno);
+		part = bdget_disk(disk, partno);
 		if (part) {
-			devt = part_devt(part);
-			disk_put_part(part);
+			devt = part->bd_dev;
+			bdput(part);
 			break;
 		}
-		disk_put_part(part);
 	}
 	class_dev_iter_exit(&iter);
 	return devt;
@@ -1727,32 +1579,16 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	if (!disk)
 		return NULL;
 
-	disk->part0.dkstats = alloc_percpu(struct disk_stats);
-	if (!disk->part0.dkstats)
+	disk->part0 = bdev_alloc(disk, 0);
+	if (!disk->part0)
 		goto out_free_disk;
 
-	init_rwsem(&disk->lookup_sem);
 	disk->node_id = node_id;
-	if (disk_expand_part_tbl(disk, 0)) {
-		free_percpu(disk->part0.dkstats);
-		goto out_free_disk;
-	}
+	if (disk_expand_part_tbl(disk, 0))
+		goto out_bdput;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
-	rcu_assign_pointer(ptbl->part[0], &disk->part0);
-
-	/*
-	 * set_capacity() and get_capacity() currently don't use
-	 * seqcounter to read/update the part0->nr_sects. Still init
-	 * the counter as we can read the sectors in IO submission
-	 * patch using seqence counters.
-	 *
-	 * TODO: Ideally set_capacity() and get_capacity() should be
-	 * converted to make use of bd_mutex and sequence counters.
-	 */
-	hd_sects_seq_init(&disk->part0);
-	if (hd_ref_init(&disk->part0))
-		goto out_free_part0;
+	rcu_assign_pointer(ptbl->part[0], disk->part0);
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
@@ -1761,8 +1597,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	device_initialize(disk_to_dev(disk));
 	return disk;
 
-out_free_part0:
-	hd_free_part(&disk->part0);
+out_bdput:
+	bdput(disk->part0);
 out_free_disk:
 	kfree(disk);
 	return NULL;
@@ -1770,35 +1606,6 @@ out_free_disk:
 EXPORT_SYMBOL(__alloc_disk_node);
 
 /**
- * get_disk_and_module - increments the gendisk and gendisk fops module refcount
- * @disk: the struct gendisk to increment the refcount for
- *
- * This increments the refcount for the struct gendisk, and the gendisk's
- * fops module owner.
- *
- * Context: Any context.
- */
-struct kobject *get_disk_and_module(struct gendisk *disk)
-{
-	struct module *owner;
-	struct kobject *kobj;
-
-	if (!disk->fops)
-		return NULL;
-	owner = disk->fops->owner;
-	if (owner && !try_module_get(owner))
-		return NULL;
-	kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj);
-	if (kobj == NULL) {
-		module_put(owner);
-		return NULL;
-	}
-	return kobj;
-
-}
-EXPORT_SYMBOL(get_disk_and_module);
-
-/**
  * put_disk - decrements the gendisk refcount
  * @disk: the struct gendisk to decrement the refcount for
  *
@@ -1811,31 +1618,10 @@ EXPORT_SYMBOL(get_disk_and_module);
 void put_disk(struct gendisk *disk)
 {
 	if (disk)
-		kobject_put(&disk_to_dev(disk)->kobj);
+		put_device(disk_to_dev(disk));
 }
 EXPORT_SYMBOL(put_disk);
 
-/**
- * put_disk_and_module - decrements the module and gendisk refcount
- * @disk: the struct gendisk to decrement the refcount for
- *
- * This is a counterpart of get_disk_and_module() and thus also of
- * get_gendisk().
- *
- * Context: Any context, but the last reference must not be dropped from
- *          atomic context.
- */
-void put_disk_and_module(struct gendisk *disk)
-{
-	if (disk) {
-		struct module *owner = disk->fops->owner;
-
-		put_disk(disk);
-		module_put(owner);
-	}
-}
-EXPORT_SYMBOL(put_disk_and_module);
-
 static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 {
 	char event[] = "DISK_RO=1";
@@ -1846,26 +1632,19 @@ static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
 }
 
-void set_device_ro(struct block_device *bdev, int flag)
-{
-	bdev->bd_part->policy = flag;
-}
-
-EXPORT_SYMBOL(set_device_ro);
-
 void set_disk_ro(struct gendisk *disk, int flag)
 {
 	struct disk_part_iter piter;
-	struct hd_struct *part;
+	struct block_device *part;
 
-	if (disk->part0.policy != flag) {
+	if (disk->part0->bd_read_only != flag) {
 		set_disk_ro_uevent(disk, flag);
-		disk->part0.policy = flag;
+		disk->part0->bd_read_only = flag;
 	}
 
 	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		part->policy = flag;
+		part->bd_read_only = flag;
 	disk_part_iter_exit(&piter);
 }
 
@@ -1875,7 +1654,7 @@ int bdev_read_only(struct block_device *bdev)
 {
 	if (!bdev)
 		return 0;
-	return bdev->bd_part->policy;
+	return bdev->bd_read_only;
 }
 
 EXPORT_SYMBOL(bdev_read_only);