block: simplify bdev/disk lookup in blkdev_get

To simplify block device lookup and a few other upcoming areas, make sure
that we always have a struct block_device available for each disk and
each partition, and only find existing block devices in bdget.  The only
downside of this is that each device and partition uses a little more
memory.  The upside will be that a lot of code can be simplified.

With that all we need to look up the block device is to lookup the inode
and do a few sanity checks on the gendisk, instead of the separate lookup
for the gendisk.  For blk-cgroup which wants to access a gendisk without
opening it, a new blkdev_{get,put}_no_open low-level interface is added
to replace the previous get_gendisk use.

Note that the change to look up block device directly instead of the two
step lookup using struct gendisk causes a subtile change in behavior:
accessing a non-existing partition on an existing block device can now
cause a call to request_module.  That call is harmless, and in practice
no recent system will access these nodes as they aren't created by udev
and static /dev/ setups are unusual.

Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/blk-cgroup.c

@@ -556,22 +556,22 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
 }
 
 /**
- * blkg_conf_prep - parse and prepare for per-blkg config update
+ * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update
  * @inputp: input string pointer
  *
  * Parse the device node prefix part, MAJ:MIN, of per-blkg config update
- * from @input and get and return the matching gendisk.  *@inputp is
+ * from @input and get and return the matching bdev.  *@inputp is
  * updated to point past the device node prefix.  Returns an ERR_PTR()
  * value on error.
  *
  * Use this function iff blkg_conf_prep() can't be used for some reason.
  */
-struct gendisk *blkcg_conf_get_disk(char **inputp)
+struct block_device *blkcg_conf_open_bdev(char **inputp)
 {
 	char *input = *inputp;
 	unsigned int major, minor;
-	struct gendisk *disk;
-	int key_len, part;
+	struct block_device *bdev;
+	int key_len;
 
 	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
 		return ERR_PTR(-EINVAL);
@@ -581,16 +581,16 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
 		return ERR_PTR(-EINVAL);
 	input = skip_spaces(input);
 
-	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk)
+	bdev = blkdev_get_no_open(MKDEV(major, minor));
+	if (!bdev)
 		return ERR_PTR(-ENODEV);
-	if (part) {
-		put_disk_and_module(disk);
+	if (bdev_is_partition(bdev)) {
+		blkdev_put_no_open(bdev);
 		return ERR_PTR(-ENODEV);
 	}
 
 	*inputp = input;
-	return disk;
+	return bdev;
 }
 
 /**
@@ -607,18 +607,18 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
  */
 int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		   char *input, struct blkg_conf_ctx *ctx)
-	__acquires(rcu) __acquires(&disk->queue->queue_lock)
+	__acquires(rcu) __acquires(&bdev->bd_disk->queue->queue_lock)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	q = disk->queue;
+	q = bdev->bd_disk->queue;
 
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
@@ -689,7 +689,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 			goto success;
 	}
 success:
-	ctx->disk = disk;
+	ctx->bdev = bdev;
 	ctx->blkg = blkg;
 	ctx->body = input;
 	return 0;
@@ -700,7 +700,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	spin_unlock_irq(&q->queue_lock);
 	rcu_read_unlock();
 fail:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
@@ -723,11 +723,11 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
  * with blkg_conf_prep().
  */
 void blkg_conf_finish(struct blkg_conf_ctx *ctx)
-	__releases(&ctx->disk->queue->queue_lock) __releases(rcu)
+	__releases(&ctx->bdev->bd_disk->queue->queue_lock) __releases(rcu)
 {
-	spin_unlock_irq(&ctx->disk->queue->queue_lock);
+	spin_unlock_irq(&ctx->bdev->bd_disk->queue->queue_lock);
 	rcu_read_unlock();
-	put_disk_and_module(ctx->disk);
+	blkdev_put_no_open(ctx->bdev);
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 

block/blk-iocost.c

@@ -3120,23 +3120,23 @@ static const match_table_t qos_tokens = {
 static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 			     size_t nbytes, loff_t off)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct ioc *ioc;
 	u32 qos[NR_QOS_PARAMS];
 	bool enable, user;
 	char *p;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	ioc = q_to_ioc(disk->queue);
+	ioc = q_to_ioc(bdev->bd_disk->queue);
 	if (!ioc) {
-		ret = blk_iocost_init(disk->queue);
+		ret = blk_iocost_init(bdev->bd_disk->queue);
 		if (ret)
 			goto err;
-		ioc = q_to_ioc(disk->queue);
+		ioc = q_to_ioc(bdev->bd_disk->queue);
 	}
 
 	spin_lock_irq(&ioc->lock);
@@ -3231,12 +3231,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return nbytes;
 einval:
 	ret = -EINVAL;
 err:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return ret;
 }
 
@@ -3287,23 +3287,23 @@ static const match_table_t i_lcoef_tokens = {
 static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 				    size_t nbytes, loff_t off)
 {
-	struct gendisk *disk;
+	struct block_device *bdev;
 	struct ioc *ioc;
 	u64 u[NR_I_LCOEFS];
 	bool user;
 	char *p;
 	int ret;
 
-	disk = blkcg_conf_get_disk(&input);
-	if (IS_ERR(disk))
-		return PTR_ERR(disk);
+	bdev = blkcg_conf_open_bdev(&input);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
 
-	ioc = q_to_ioc(disk->queue);
+	ioc = q_to_ioc(bdev->bd_disk->queue);
 	if (!ioc) {
-		ret = blk_iocost_init(disk->queue);
+		ret = blk_iocost_init(bdev->bd_disk->queue);
 		if (ret)
 			goto err;
-		ioc = q_to_ioc(disk->queue);
+		ioc = q_to_ioc(bdev->bd_disk->queue);
 	}
 
 	spin_lock_irq(&ioc->lock);
@@ -3356,13 +3356,13 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	ioc_refresh_params(ioc, true);
 	spin_unlock_irq(&ioc->lock);
 
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return nbytes;
 
 einval:
 	ret = -EINVAL;
 err:
-	put_disk_and_module(disk);
+	blkdev_put_no_open(bdev);
 	return ret;
 }
 

block/blk.h

@@ -352,7 +352,6 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
 
 int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
 void blk_free_devt(dev_t devt);
-void blk_invalidate_devt(dev_t devt);
 char *disk_name(struct gendisk *hd, int partno, char *buf);
 #define ADDPART_FLAG_NONE	0
 #define ADDPART_FLAG_RAID	1
@@ -384,6 +383,7 @@ static inline void hd_free_part(struct hd_struct *part)
 {
 	free_percpu(part->dkstats);
 	kfree(part->info);
+	bdput(part->bdev);
 	percpu_ref_exit(&part->ref);
 }