block: merge struct block_device and struct hd_struct

Instead of having two structures that represent each block device with
different life time rules, merge them into a single one.  This also
greatly simplifies the reference counting rules, as we can use the inode
reference count as the main reference count for the new struct
block_device, with the device model reference front ending it for device
model interaction.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

4 files changed, 75 insertions, 141 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 79aa96240cec..031114d454a6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -820,9 +820,9 @@ static void blkcg_fill_root_iostats(void)
 
 	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 = disk_get_part(disk, 0);
-		struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue);
+		struct block_device *bdev = dev_to_bdev(dev);
+		struct blkcg_gq *blkg =
+			blk_queue_root_blkg(bdev->bd_disk->queue);
 		struct blkg_iostat tmp;
 		int cpu;
 
@@ -830,7 +830,7 @@ static void blkcg_fill_root_iostats(void)
 		for_each_possible_cpu(cpu) {
 			struct disk_stats *cpu_dkstats;
 
-			cpu_dkstats = per_cpu_ptr(part->bdev->bd_stats, cpu);
+			cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
 			tmp.ios[BLKG_IOSTAT_READ] +=
 				cpu_dkstats->ios[STAT_READ];
 			tmp.ios[BLKG_IOSTAT_WRITE] +=
diff --git a/block/blk.h b/block/blk.h
index 9657c6da7c77..98f0b1ae2641 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -356,7 +356,7 @@ char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
 #define ADDPART_FLAG_WHOLEDISK	2
-void delete_partition(struct hd_struct *part);
+void delete_partition(struct block_device *part);
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length);
 int bdev_del_partition(struct block_device *bdev, int partno);
diff --git a/block/genhd.c b/block/genhd.c
index 2d34dd2da4e9..0fabfc90b8e4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -106,13 +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->bdev->bd_stats, cpu);
+		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu);
 		int group;
 
 		for (group = 0; group < NR_STAT_GROUPS; group++) {
@@ -168,39 +169,6 @@ struct block_device *__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 block_device *bdev;
-	struct hd_struct *part;
-
-	rcu_read_lock();
-	bdev = __disk_get_part(disk, partno);
-	if (!bdev)
-		goto fail;
-	part = bdev->bd_part;
-	if (!kobject_get_unless_zero(&part_to_dev(part)->kobj))
-		goto fail;
-	rcu_read_unlock();
-	return part;
-fail:
-	rcu_read_unlock();
-	return NULL;
-}
-
-/**
  * disk_part_iter_init - initialize partition iterator
  * @piter: iterator to initialize
  * @disk: disk to iterate over
@@ -859,7 +827,7 @@ void del_gendisk(struct gendisk *disk)
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
 		invalidate_partition(part);
-		delete_partition(part->bd_part);
+		delete_partition(part);
 	}
 	disk_part_iter_exit(&piter);
 
@@ -952,13 +920,13 @@ void blk_request_module(dev_t devt)
  */
 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;
 }
@@ -1175,24 +1143,22 @@ 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", bdev_nr_sectors(p->bdev));
+	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->bdev);
+		inflight = blk_mq_in_flight(q, bdev);
 	else
-		inflight = part_in_flight(p->bdev);
+		inflight = part_in_flight(bdev);
 
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
@@ -1227,14 +1193,14 @@ 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->bdev, inflight);
+		blk_mq_in_flight_rw(q, bdev, inflight);
 	else
-		part_in_flight_rw(p->bdev, inflight);
+		part_in_flight_rw(bdev, inflight);
 
 	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
@@ -1282,20 +1248,17 @@ 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->bdev->bd_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->bdev->bd_make_it_fail = i;
+		dev_to_bdev(dev)->bd_make_it_fail = i;
 
 	return count;
 }
@@ -1505,7 +1468,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 
 	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
-		part_stat_read_all(hd->bd_part, &stat);
+		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
 			inflight = blk_mq_in_flight(gp->queue, hd);
 		else
@@ -1577,7 +1540,7 @@ 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;
@@ -1590,13 +1553,12 @@ 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;
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 4cb6df175f90..deca253583bd 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -182,44 +182,39 @@ static struct parsed_partitions *check_partition(struct gendisk *hd,
 static ssize_t part_partition_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%d\n", p->bdev->bd_partno);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_partno);
 }
 
 static ssize_t part_start_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
-	return sprintf(buf, "%llu\n", p->bdev->bd_start_sect);
+	return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect);
 }
 
 static ssize_t part_ro_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%d\n", p->bdev->bd_read_only);
+	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_read_only);
 }
 
 static ssize_t part_alignment_offset_show(struct device *dev,
 					  struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = dev_to_bdev(dev);
 
 	return sprintf(buf, "%u\n",
-		queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
-				p->bdev->bd_start_sect));
+		queue_limit_alignment_offset(&bdev->bd_disk->queue->limits,
+				bdev->bd_start_sect));
 }
 
 static ssize_t part_discard_alignment_show(struct device *dev,
 					   struct device_attribute *attr, char *buf)
 {
-	struct hd_struct *p = dev_to_part(dev);
+	struct block_device *bdev = dev_to_bdev(dev);
 
 	return sprintf(buf, "%u\n",
-		queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
-				p->bdev->bd_start_sect));
+		queue_limit_discard_alignment(&bdev->bd_disk->queue->limits,
+				bdev->bd_start_sect));
 }
 
 static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -264,20 +259,17 @@ static const struct attribute_group *part_attr_groups[] = {
 
 static void part_release(struct device *dev)
 {
-	struct hd_struct *p = dev_to_part(dev);
-
 	blk_free_devt(dev->devt);
-	bdput(p->bdev);
+	bdput(dev_to_bdev(dev));
 }
 
 static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	struct hd_struct *part = dev_to_part(dev);
+	struct block_device *part = dev_to_bdev(dev);
 
-	add_uevent_var(env, "PARTN=%u", part->bdev->bd_partno);
-	if (part->bdev->bd_meta_info && part->bdev->bd_meta_info->volname[0])
-		add_uevent_var(env, "PARTNAME=%s",
-			       part->bdev->bd_meta_info->volname);
+	add_uevent_var(env, "PARTN=%u", part->bd_partno);
+	if (part->bd_meta_info && part->bd_meta_info->volname[0])
+		add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname);
 	return 0;
 }
 
@@ -292,25 +284,25 @@ struct device_type part_type = {
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
  */
-void delete_partition(struct hd_struct *part)
+void delete_partition(struct block_device *part)
 {
-	struct gendisk *disk = part_to_disk(part);
+	struct gendisk *disk = part->bd_disk;
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
-	rcu_assign_pointer(ptbl->part[part->bdev->bd_partno], NULL);
+	rcu_assign_pointer(ptbl->part[part->bd_partno], NULL);
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 
-	kobject_put(part->bdev->bd_holder_dir);
-	device_del(part_to_dev(part));
+	kobject_put(part->bd_holder_dir);
+	device_del(&part->bd_device);
 
 	/*
 	 * Remove the block device from the inode hash, so that it cannot be
 	 * looked up any more even when openers still hold references.
 	 */
-	remove_inode_hash(part->bdev->bd_inode);
+	remove_inode_hash(part->bd_inode);
 
-	put_device(part_to_dev(part));
+	put_device(&part->bd_device);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -324,11 +316,10 @@ static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
  * Must be called either with bd_mutex held, before a disk can be opened or
  * after all disk users are gone.
  */
-static struct hd_struct *add_partition(struct gendisk *disk, int partno,
+static struct block_device *add_partition(struct gendisk *disk, int partno,
 				sector_t start, sector_t len, int flags,
 				struct partition_meta_info *info)
 {
-	struct hd_struct *p;
 	dev_t devt = MKDEV(0, 0);
 	struct device *ddev = disk_to_dev(disk);
 	struct device *pdev;
@@ -367,9 +358,6 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	if (!bdev)
 		return ERR_PTR(-ENOMEM);
 
-	p = bdev->bd_part;
-	pdev = part_to_dev(p);
-
 	bdev->bd_start_sect = start;
 	bdev_set_nr_sectors(bdev, len);
 	bdev->bd_read_only = get_disk_ro(disk);
@@ -381,6 +369,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 			goto out_bdput;
 	}
 
+	pdev = &bdev->bd_device;
 	dname = dev_name(ddev);
 	if (isdigit(dname[strlen(dname) - 1]))
 		dev_set_name(pdev, "%sp%d", dname, partno);
@@ -422,7 +411,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
-	return p;
+	return bdev;
 
 out_bdput:
 	bdput(bdev);
@@ -459,7 +448,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 int bdev_add_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length)
 {
-	struct hd_struct *part;
+	struct block_device *part;
 
 	mutex_lock(&bdev->bd_mutex);
 	if (partition_overlaps(bdev->bd_disk, start, length, -1)) {
@@ -475,76 +464,59 @@ int bdev_add_partition(struct block_device *bdev, int partno,
 
 int bdev_del_partition(struct block_device *bdev, int partno)
 {
-	struct block_device *bdevp;
-	struct hd_struct *part = NULL;
+	struct block_device *part;
 	int ret;
 
-	bdevp = bdget_disk(bdev->bd_disk, partno);
-	if (!bdevp)
+	part = bdget_disk(bdev->bd_disk, partno);
+	if (!part)
 		return -ENXIO;
 
-	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock(&part->bd_mutex);
 	mutex_lock_nested(&bdev->bd_mutex, 1);
 
-	ret = -ENXIO;
-	part = disk_get_part(bdev->bd_disk, partno);
-	if (!part)
-		goto out_unlock;
-
 	ret = -EBUSY;
-	if (bdevp->bd_openers)
+	if (part->bd_openers)
 		goto out_unlock;
 
-	sync_blockdev(bdevp);
-	invalidate_bdev(bdevp);
+	sync_blockdev(part);
+	invalidate_bdev(part);
 
 	delete_partition(part);
 	ret = 0;
 out_unlock:
 	mutex_unlock(&bdev->bd_mutex);
-	mutex_unlock(&bdevp->bd_mutex);
-	bdput(bdevp);
-	if (part)
-		disk_put_part(part);
+	mutex_unlock(&part->bd_mutex);
+	bdput(part);
 	return ret;
 }
 
 int bdev_resize_partition(struct block_device *bdev, int partno,
 		sector_t start, sector_t length)
 {
-	struct block_device *bdevp;
-	struct hd_struct *part;
+	struct block_device *part;
 	int ret = 0;
 
-	part = disk_get_part(bdev->bd_disk, partno);
+	part = bdget_disk(bdev->bd_disk, partno);
 	if (!part)
 		return -ENXIO;
 
-	ret = -ENOMEM;
-	bdevp = bdget_part(part);
-	if (!bdevp)
-		goto out_put_part;
-
-	mutex_lock(&bdevp->bd_mutex);
+	mutex_lock(&part->bd_mutex);
 	mutex_lock_nested(&bdev->bd_mutex, 1);
-
 	ret = -EINVAL;
-	if (start != part->bdev->bd_start_sect)
+	if (start != part->bd_start_sect)
 		goto out_unlock;
 
 	ret = -EBUSY;
 	if (partition_overlaps(bdev->bd_disk, start, length, partno))
 		goto out_unlock;
 
-	bdev_set_nr_sectors(bdevp, length);
+	bdev_set_nr_sectors(part, length);
 
 	ret = 0;
 out_unlock:
-	mutex_unlock(&bdevp->bd_mutex);
+	mutex_unlock(&part->bd_mutex);
 	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdevp);
-out_put_part:
-	disk_put_part(part);
+	bdput(part);
 	return ret;
 }
 
@@ -577,7 +549,7 @@ int blk_drop_partitions(struct block_device *bdev)
 
 	disk_part_iter_init(&piter, bdev->bd_disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter)))
-		delete_partition(part->bd_part);
+		delete_partition(part);
 	disk_part_iter_exit(&piter);
 
 	return 0;
@@ -592,7 +564,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 {
 	sector_t size = state->parts[p].size;
 	sector_t from = state->parts[p].from;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	if (!size)
 		return true;
@@ -632,7 +604,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
 
 	if (IS_BUILTIN(CONFIG_BLK_DEV_MD) &&
 	    (state->parts[p].flags & ADDPART_FLAG_RAID))
-		md_autodetect_dev(part_to_dev(part)->devt);
+		md_autodetect_dev(part->bd_dev);
 
 	return true;
 }