block: introduce holder ops

Add a new blk_holder_ops structure, which is passed to blkdev_get_by_* and
installed in the block_device for exclusive claims.  It will be used to
allow the block layer to call back into the user of the block device for
thing like notification of a removed device or a device resize.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Link: https://lore.kernel.org/r/20230601094459.1350643-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/bdev.c

@@ -102,7 +102,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
 	 * under live filesystem.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
+		int err = bd_prepare_to_claim(bdev, truncate_bdev_range, NULL);
 		if (err)
 			goto invalidate;
 	}
@@ -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;
@@ -464,13 +465,15 @@ long nr_blockdev_pages(void)
  * bd_may_claim - test whether a block device can be claimed
  * @bdev: block device of interest
  * @holder: holder trying to claim @bdev
+ * @hops: holder ops
  *
  * Test whether @bdev can be claimed by @holder.
  *
  * RETURNS:
  * %true if @bdev can be claimed, %false otherwise.
  */
-static bool bd_may_claim(struct block_device *bdev, void *holder)
+static bool bd_may_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	struct block_device *whole = bdev_whole(bdev);
 
@@ -480,8 +483,11 @@ static bool bd_may_claim(struct block_device *bdev, void *holder)
 		/*
 		 * The same holder can always re-claim.
 		 */
-		if (bdev->bd_holder == holder)
+		if (bdev->bd_holder == holder) {
+			if (WARN_ON_ONCE(bdev->bd_holder_ops != hops))
+				return false;
 			return true;
+		}
 		return false;
 	}
 
@@ -499,6 +505,7 @@ static bool bd_may_claim(struct block_device *bdev, void *holder)
  * 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
@@ -507,7 +514,8 @@ static bool bd_may_claim(struct block_device *bdev, void *holder)
  * 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);
 
@@ -516,7 +524,7 @@ int bd_prepare_to_claim(struct block_device *bdev, void *holder)
 retry:
 	mutex_lock(&bdev_lock);
 	/* if someone else claimed, fail */
-	if (!bd_may_claim(bdev, holder)) {
+	if (!bd_may_claim(bdev, holder, hops)) {
 		mutex_unlock(&bdev_lock);
 		return -EBUSY;
 	}
@@ -557,20 +565,24 @@ static void bd_clear_claiming(struct block_device *whole, void *holder)
  * 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);
 
 	mutex_lock(&bdev_lock);
-	BUG_ON(!bd_may_claim(bdev, holder));
+	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
 	 */
 	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);
 	mutex_unlock(&bdev_lock);
 }
@@ -605,7 +617,10 @@ static void bd_end_claim(struct block_device *bdev)
 	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;
 	}
@@ -735,6 +750,7 @@ void blkdev_put_no_open(struct block_device *bdev)
  * @dev: device number of block device to open
  * @mode: FMODE_* mask
  * @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
@@ -751,7 +767,8 @@ 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, fmode_t mode, void *holder,
+		const struct blk_holder_ops *hops)
 {
 	bool unblock_events = true;
 	struct block_device *bdev;
@@ -771,7 +788,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	disk = bdev->bd_disk;
 
 	if (mode & FMODE_EXCL) {
-		ret = bd_prepare_to_claim(bdev, holder);
+		ret = bd_prepare_to_claim(bdev, holder, hops);
 		if (ret)
 			goto put_blkdev;
 	}
@@ -791,7 +808,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	if (ret)
 		goto put_module;
 	if (mode & FMODE_EXCL) {
-		bd_finish_claiming(bdev, holder);
+		bd_finish_claiming(bdev, holder, hops);
 
 		/*
 		 * Block event polling for write claims if requested.  Any write
@@ -842,7 +859,7 @@ EXPORT_SYMBOL(blkdev_get_by_dev);
  * 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)
+		void *holder, const struct blk_holder_ops *hops)
 {
 	struct block_device *bdev;
 	dev_t dev;
@@ -852,7 +869,7 @@ 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);
+	bdev = blkdev_get_by_dev(dev, mode, holder, hops);
 	if (!IS_ERR(bdev) && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
 		blkdev_put(bdev, mode);
 		return ERR_PTR(-EACCES);

block/fops.c

@@ -490,7 +490,7 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if ((filp->f_flags & O_ACCMODE) == 3)
 		filp->f_mode |= FMODE_WRITE_IOCTL;
 
-	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
+	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp, NULL);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 

block/genhd.c

@@ -370,13 +370,15 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode)
 	 * scanners.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions);
+		ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions,
+					  NULL);
 		if (ret)
 			return ret;
 	}
 
 	set_bit(GD_NEED_PART_SCAN, &disk->state);
-	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL);
+	bdev = blkdev_get_by_dev(disk_devt(disk), mode & ~FMODE_EXCL, NULL,
+				 NULL);
 	if (IS_ERR(bdev))
 		ret =  PTR_ERR(bdev);
 	else

block/ioctl.c

@@ -454,7 +454,8 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 	if (mode & FMODE_EXCL)
 		return set_blocksize(bdev, n);
 
-	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev)))
+	if (IS_ERR(blkdev_get_by_dev(bdev->bd_dev, mode | FMODE_EXCL, &bdev,
+			NULL)))
 		return -EBUSY;
 	ret = set_blocksize(bdev, n);
 	blkdev_put(bdev, mode | FMODE_EXCL);

drivers/block/drbd/drbd_nl.c

@@ -1641,7 +1641,8 @@ static struct block_device *open_backing_dev(struct drbd_device *device,
 	int err = 0;
 
 	bdev = blkdev_get_by_path(bdev_path,
-				  FMODE_READ | FMODE_WRITE | FMODE_EXCL, claim_ptr);
+				  FMODE_READ | FMODE_WRITE | FMODE_EXCL,
+				  claim_ptr, NULL);
 	if (IS_ERR(bdev)) {
 		drbd_err(device, "open(\"%s\") failed with %ld\n",
 				bdev_path, PTR_ERR(bdev));

drivers/block/loop.c

@@ -1015,7 +1015,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
 	 * here to avoid changing device under exclusive owner.
 	 */
 	if (!(mode & FMODE_EXCL)) {
-		error = bd_prepare_to_claim(bdev, loop_configure);
+		error = bd_prepare_to_claim(bdev, loop_configure, NULL);
 		if (error)
 			goto out_putf;
 	}

drivers/block/pktcdvd.c

@@ -2125,7 +2125,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
 	 * so open should not fail.
 	 */
-	bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd);
+	bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd,
+				 NULL);
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
 		goto out;
@@ -2530,7 +2531,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 		}
 	}
 
-	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
+	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL, NULL);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 	sdev = scsi_device_from_queue(bdev->bd_disk->queue);

drivers/block/rnbd/rnbd-srv.c

@@ -719,7 +719,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess,
 		goto reject;
 	}
 
-	bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE);
+	bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE, NULL);
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
 		pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n",

drivers/block/xen-blkback/xenbus.c

@@ -492,7 +492,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 	vbd->pdevice  = MKDEV(major, minor);
 
 	bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ?
-				 FMODE_READ : FMODE_WRITE, NULL);
+				 FMODE_READ : FMODE_WRITE, NULL, NULL);
 
 	if (IS_ERR(bdev)) {
 		pr_warn("xen_vbd_create: device %08x could not be opened\n",

drivers/block/zram/zram_drv.c

@@ -508,7 +508,7 @@ static ssize_t backing_dev_store(struct device *dev,
 	}
 
 	bdev = blkdev_get_by_dev(inode->i_rdev,
-			FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram);
+			FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram, NULL);
 	if (IS_ERR(bdev)) {
 		err = PTR_ERR(bdev);
 		bdev = NULL;

drivers/md/bcache/super.c

@@ -2560,7 +2560,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	err = "failed to open device";
 	bdev = blkdev_get_by_path(strim(path),
 				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
-				  sb);
+				  sb, NULL);
 	if (IS_ERR(bdev)) {
 		if (bdev == ERR_PTR(-EBUSY)) {
 			dev_t dev;

drivers/md/dm.c

@@ -746,7 +746,7 @@ static struct table_device *open_table_device(struct mapped_device *md,
 		return ERR_PTR(-ENOMEM);
 	refcount_set(&td->count, 1);
 
-	bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr);
+	bdev = blkdev_get_by_dev(dev, mode | FMODE_EXCL, _dm_claim_ptr, NULL);
 	if (IS_ERR(bdev)) {
 		r = PTR_ERR(bdev);
 		goto out_free_td;

drivers/md/md.c

@@ -3642,7 +3642,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 
 	rdev->bdev = blkdev_get_by_dev(newdev,
 			FMODE_READ | FMODE_WRITE | FMODE_EXCL,
-			super_format == -2 ? &claim_rdev : rdev);
+			super_format == -2 ? &claim_rdev : rdev, NULL);
 	if (IS_ERR(rdev->bdev)) {
 		pr_warn("md: could not open device unknown-block(%u,%u).\n",
 			MAJOR(newdev), MINOR(newdev));

drivers/mtd/devices/block2mtd.c

@@ -235,7 +235,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		return NULL;
 
 	/* Get a handle on the device */
-	bdev = blkdev_get_by_path(devname, mode, dev);
+	bdev = blkdev_get_by_path(devname, mode, dev, NULL);
 
 #ifndef MODULE
 	/*
@@ -257,7 +257,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size,
 		devt = name_to_dev_t(devname);
 		if (!devt)
 			continue;
-		bdev = blkdev_get_by_dev(devt, mode, dev);
+		bdev = blkdev_get_by_dev(devt, mode, dev, NULL);
 	}
 #endif
 

drivers/nvme/target/io-cmd-bdev.c

@@ -85,7 +85,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
 		return -ENOTBLK;
 
 	ns->bdev = blkdev_get_by_path(ns->device_path,
-			FMODE_READ | FMODE_WRITE, NULL);
+			FMODE_READ | FMODE_WRITE, NULL, NULL);
 	if (IS_ERR(ns->bdev)) {
 		ret = PTR_ERR(ns->bdev);
 		if (ret != -ENOTBLK) {

drivers/s390/block/dasd_genhd.c

@@ -130,7 +130,7 @@ int dasd_scan_partitions(struct dasd_block *block)
 	struct block_device *bdev;
 	int rc;
 
-	bdev = blkdev_get_by_dev(disk_devt(block->gdp), FMODE_READ, NULL);
+	bdev = blkdev_get_by_dev(disk_devt(block->gdp), FMODE_READ, NULL, NULL);
 	if (IS_ERR(bdev)) {
 		DBF_DEV_EVENT(DBF_ERR, block->base,
 			      "scan partitions error, blkdev_get returned %ld",

drivers/target/target_core_iblock.c

@@ -114,7 +114,7 @@ static int iblock_configure_device(struct se_device *dev)
 	else
 		dev->dev_flags |= DF_READ_ONLY;
 
-	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
+	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev, NULL);
 	if (IS_ERR(bd)) {
 		ret = PTR_ERR(bd);
 		goto out_free_bioset;

drivers/target/target_core_pscsi.c

@@ -367,7 +367,8 @@ static int pscsi_create_type_disk(struct se_device *dev, struct scsi_device *sd)
 	 * for TYPE_DISK and TYPE_ZBC using supplied udev_path
 	 */
 	bd = blkdev_get_by_path(dev->udev_path,
-				FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv);
+				FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv,
+				NULL);
 	if (IS_ERR(bd)) {
 		pr_err("pSCSI: blkdev_get_by_path() failed\n");
 		scsi_device_put(sd);

fs/btrfs/dev-replace.c

@@ -258,7 +258,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	}
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
-				  fs_info->bdev_holder);
+				  fs_info->bdev_holder, NULL);
 	if (IS_ERR(bdev)) {
 		btrfs_err(fs_info, "target device %s is invalid!", device_path);
 		return PTR_ERR(bdev);

fs/btrfs/volumes.c

@@ -496,7 +496,7 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
 {
 	int ret;
 
-	*bdev = blkdev_get_by_path(device_path, flags, holder);
+	*bdev = blkdev_get_by_path(device_path, flags, holder, NULL);
 
 	if (IS_ERR(*bdev)) {
 		ret = PTR_ERR(*bdev);
@@ -1377,7 +1377,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 	 * values temporarily, as the device paths of the fsid are the only
 	 * required information for assembling the volume.
 	 */
-	bdev = blkdev_get_by_path(path, flags, holder);
+	bdev = blkdev_get_by_path(path, flags, holder, NULL);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
@@ -2629,7 +2629,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		return -EROFS;
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
-				  fs_info->bdev_holder);
+				  fs_info->bdev_holder, NULL);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 

fs/erofs/super.c

@@ -254,7 +254,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 		dif->fscache = fscache;
 	} else if (!sbi->devs->flatdev) {
 		bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL,
-					  sb->s_type);
+					  sb->s_type, NULL);
 		if (IS_ERR(bdev))
 			return PTR_ERR(bdev);
 		dif->bdev = bdev;