1 files changed, 231 insertions, 205 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 9b2f5d3c19ab..3d806820280e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -75,12 +75,13 @@
 #include <linux/kthread.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
+#include <linux/miscdevice.h>
 #include <linux/falloc.h>
 
 #include <asm/uaccess.h>
 
-static LIST_HEAD(loop_devices);
-static DEFINE_MUTEX(loop_devices_mutex);
+static DEFINE_IDR(loop_index_idr);
+static DEFINE_MUTEX(loop_index_mutex);
 
 static int max_part;
 static int part_shift;
@@ -204,74 +205,6 @@ lo_do_transfer(struct loop_device *lo, int cmd,
 }
 
 /**
- * do_lo_send_aops - helper for writing data to a loop device
- *
- * This is the fast version for backing filesystems which implement the address
- * space operations write_begin and write_end.
- */
-static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
-		loff_t pos, struct page *unused)
-{
-	struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
-	struct address_space *mapping = file->f_mapping;
-	pgoff_t index;
-	unsigned offset, bv_offs;
-	int len, ret;
-
-	mutex_lock(&mapping->host->i_mutex);
-	index = pos >> PAGE_CACHE_SHIFT;
-	offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
-	bv_offs = bvec->bv_offset;
-	len = bvec->bv_len;
-	while (len > 0) {
-		sector_t IV;
-		unsigned size, copied;
-		int transfer_result;
-		struct page *page;
-		void *fsdata;
-
-		IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
-		size = PAGE_CACHE_SIZE - offset;
-		if (size > len)
-			size = len;
-
-		ret = pagecache_write_begin(file, mapping, pos, size, 0,
-							&page, &fsdata);
-		if (ret)
-			goto fail;
-
-		file_update_time(file);
-
-		transfer_result = lo_do_transfer(lo, WRITE, page, offset,
-				bvec->bv_page, bv_offs, size, IV);
-		copied = size;
-		if (unlikely(transfer_result))
-			copied = 0;
-
-		ret = pagecache_write_end(file, mapping, pos, size, copied,
-							page, fsdata);
-		if (ret < 0 || ret != copied)
-			goto fail;
-
-		if (unlikely(transfer_result))
-			goto fail;
-
-		bv_offs += copied;
-		len -= copied;
-		offset = 0;
-		index++;
-		pos += copied;
-	}
-	ret = 0;
-out:
-	mutex_unlock(&mapping->host->i_mutex);
-	return ret;
-fail:
-	ret = -1;
-	goto out;
-}
-
-/**
  * __do_lo_send_write - helper for writing data to a loop device
  *
  * This helper just factors out common code between do_lo_send_direct_write()
@@ -298,10 +231,8 @@ static int __do_lo_send_write(struct file *file,
 /**
  * do_lo_send_direct_write - helper for writing data to a loop device
  *
- * This is the fast, non-transforming version for backing filesystems which do
- * not implement the address space operations write_begin and write_end.
- * It uses the write file operation which should be present on all writeable
- * filesystems.
+ * This is the fast, non-transforming version that does not need double
+ * buffering.
  */
 static int do_lo_send_direct_write(struct loop_device *lo,
 		struct bio_vec *bvec, loff_t pos, struct page *page)
@@ -317,15 +248,9 @@ static int do_lo_send_direct_write(struct loop_device *lo,
 /**
  * do_lo_send_write - helper for writing data to a loop device
  *
- * This is the slow, transforming version for filesystems which do not
- * implement the address space operations write_begin and write_end.  It
- * uses the write file operation which should be present on all writeable
- * filesystems.
- *
- * Using fops->write is slower than using aops->{prepare,commit}_write in the
- * transforming case because we need to double buffer the data as we cannot do
- * the transformations in place as we do not have direct access to the
- * destination pages of the backing file.
+ * This is the slow, transforming version that needs to double buffer the
+ * data as it cannot do the transformations in place without having direct
+ * access to the destination pages of the backing file.
  */
 static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
 		loff_t pos, struct page *page)
@@ -351,17 +276,16 @@ static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
 	struct page *page = NULL;
 	int i, ret = 0;
 
-	do_lo_send = do_lo_send_aops;
-	if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
+	if (lo->transfer != transfer_none) {
+		page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
+		if (unlikely(!page))
+			goto fail;
+		kmap(page);
+		do_lo_send = do_lo_send_write;
+	} else {
 		do_lo_send = do_lo_send_direct_write;
-		if (lo->transfer != transfer_none) {
-			page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
-			if (unlikely(!page))
-				goto fail;
-			kmap(page);
-			do_lo_send = do_lo_send_write;
-		}
 	}
+
 	bio_for_each_segment(bvec, bio, i) {
 		ret = do_lo_send(lo, bvec, pos, page);
 		if (ret < 0)
@@ -538,7 +462,7 @@ static struct bio *loop_get_bio(struct loop_device *lo)
 	return bio_list_pop(&lo->lo_bio_list);
 }
 
-static int loop_make_request(struct request_queue *q, struct bio *old_bio)
+static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 {
 	struct loop_device *lo = q->queuedata;
 	int rw = bio_rw(old_bio);
@@ -556,12 +480,11 @@ static int loop_make_request(struct request_queue *q, struct bio *old_bio)
 	loop_add_bio(lo, old_bio);
 	wake_up(&lo->lo_event);
 	spin_unlock_irq(&lo->lo_lock);
-	return 0;
+	return;
 
 out:
 	spin_unlock_irq(&lo->lo_lock);
 	bio_io_error(old_bio);
-	return 0;
 }
 
 struct switch_request {
@@ -746,17 +669,10 @@ static inline int is_loop_device(struct file *file)
 static ssize_t loop_attr_show(struct device *dev, char *page,
 			      ssize_t (*callback)(struct loop_device *, char *))
 {
-	struct loop_device *l, *lo = NULL;
-
-	mutex_lock(&loop_devices_mutex);
-	list_for_each_entry(l, &loop_devices, lo_list)
-		if (disk_to_dev(l->lo_disk) == dev) {
-			lo = l;
-			break;
-		}
-	mutex_unlock(&loop_devices_mutex);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct loop_device *lo = disk->private_data;
 
-	return lo ? callback(lo, page) : -EIO;
+	return callback(lo, page);
 }
 
 #define LOOP_ATTR_RO(_name)						\
@@ -774,10 +690,10 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 	ssize_t ret;
 	char *p = NULL;
 
-	mutex_lock(&lo->lo_ctl_mutex);
+	spin_lock_irq(&lo->lo_lock);
 	if (lo->lo_backing_file)
 		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
-	mutex_unlock(&lo->lo_ctl_mutex);
+	spin_unlock_irq(&lo->lo_lock);
 
 	if (IS_ERR_OR_NULL(p))
 		ret = PTR_ERR(p);
@@ -918,35 +834,23 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	mapping = file->f_mapping;
 	inode = mapping->host;
 
-	if (!(file->f_mode & FMODE_WRITE))
-		lo_flags |= LO_FLAGS_READ_ONLY;
-
 	error = -EINVAL;
-	if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
-		const struct address_space_operations *aops = mapping->a_ops;
-
-		if (aops->write_begin)
-			lo_flags |= LO_FLAGS_USE_AOPS;
-		if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
-			lo_flags |= LO_FLAGS_READ_ONLY;
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+		goto out_putf;
 
-		lo_blocksize = S_ISBLK(inode->i_mode) ?
-			inode->i_bdev->bd_block_size : PAGE_SIZE;
+	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+	    !file->f_op->write)
+		lo_flags |= LO_FLAGS_READ_ONLY;
 
-		error = 0;
-	} else {
-		goto out_putf;
-	}
+	lo_blocksize = S_ISBLK(inode->i_mode) ?
+		inode->i_bdev->bd_block_size : PAGE_SIZE;
 
+	error = -EFBIG;
 	size = get_loop_size(lo, file);
-
-	if ((loff_t)(sector_t)size != size) {
-		error = -EFBIG;
+	if ((loff_t)(sector_t)size != size)
 		goto out_putf;
-	}
 
-	if (!(mode & FMODE_WRITE))
-		lo_flags |= LO_FLAGS_READ_ONLY;
+	error = 0;
 
 	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
 
@@ -1072,7 +976,9 @@ static int loop_clr_fd(struct loop_device *lo)
 
 	kthread_stop(lo->lo_thread);
 
+	spin_lock_irq(&lo->lo_lock);
 	lo->lo_backing_file = NULL;
+	spin_unlock_irq(&lo->lo_lock);
 
 	loop_release_xfer(lo);
 	lo->transfer = NULL;
@@ -1560,13 +1466,22 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 
 static int lo_open(struct block_device *bdev, fmode_t mode)
 {
-	struct loop_device *lo = bdev->bd_disk->private_data;
+	struct loop_device *lo;
+	int err = 0;
+
+	mutex_lock(&loop_index_mutex);
+	lo = bdev->bd_disk->private_data;
+	if (!lo) {
+		err = -ENXIO;
+		goto out;
+	}
 
 	mutex_lock(&lo->lo_ctl_mutex);
 	lo->lo_refcnt++;
 	mutex_unlock(&lo->lo_ctl_mutex);
-
-	return 0;
+out:
+	mutex_unlock(&loop_index_mutex);
+	return err;
 }
 
 static int lo_release(struct gendisk *disk, fmode_t mode)
@@ -1632,40 +1547,71 @@ int loop_register_transfer(struct loop_func_table *funcs)
 	return 0;
 }
 
+static int unregister_transfer_cb(int id, void *ptr, void *data)
+{
+	struct loop_device *lo = ptr;
+	struct loop_func_table *xfer = data;
+
+	mutex_lock(&lo->lo_ctl_mutex);
+	if (lo->lo_encryption == xfer)
+		loop_release_xfer(lo);
+	mutex_unlock(&lo->lo_ctl_mutex);
+	return 0;
+}
+
 int loop_unregister_transfer(int number)
 {
 	unsigned int n = number;
-	struct loop_device *lo;
 	struct loop_func_table *xfer;
 
 	if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
 		return -EINVAL;
 
 	xfer_funcs[n] = NULL;
-
-	list_for_each_entry(lo, &loop_devices, lo_list) {
-		mutex_lock(&lo->lo_ctl_mutex);
-
-		if (lo->lo_encryption == xfer)
-			loop_release_xfer(lo);
-
-		mutex_unlock(&lo->lo_ctl_mutex);
-	}
-
+	idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
 	return 0;
 }
 
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
-static struct loop_device *loop_alloc(int i)
+static int loop_add(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
 	struct gendisk *disk;
+	int err;
 
 	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
-	if (!lo)
+	if (!lo) {
+		err = -ENOMEM;
 		goto out;
+	}
+
+	err = idr_pre_get(&loop_index_idr, GFP_KERNEL);
+	if (err < 0)
+		goto out_free_dev;
+
+	if (i >= 0) {
+		int m;
+
+		/* create specific i in the index */
+		err = idr_get_new_above(&loop_index_idr, lo, i, &m);
+		if (err >= 0 && i != m) {
+			idr_remove(&loop_index_idr, m);
+			err = -EEXIST;
+		}
+	} else if (i == -1) {
+		int m;
+
+		/* get next free nr */
+		err = idr_get_new(&loop_index_idr, lo, &m);
+		if (err >= 0)
+			i = m;
+	} else {
+		err = -EINVAL;
+	}
+	if (err < 0)
+		goto out_free_dev;
 
 	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
 	if (!lo->lo_queue)
@@ -1707,81 +1653,158 @@ static struct loop_device *loop_alloc(int i)
 	disk->private_data	= lo;
 	disk->queue		= lo->lo_queue;
 	sprintf(disk->disk_name, "loop%d", i);
-	return lo;
+	add_disk(disk);
+	*l = lo;
+	return lo->lo_number;
 
 out_free_queue:
 	blk_cleanup_queue(lo->lo_queue);
 out_free_dev:
 	kfree(lo);
 out:
-	return NULL;
+	return err;
 }
 
-static void loop_free(struct loop_device *lo)
+static void loop_remove(struct loop_device *lo)
 {
+	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
 	put_disk(lo->lo_disk);
-	list_del(&lo->lo_list);
 	kfree(lo);
 }
 
-static struct loop_device *loop_init_one(int i)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+	struct loop_device *lo = ptr;
+	struct loop_device **l = data;
+
+	if (lo->lo_state == Lo_unbound) {
+		*l = lo;
+		return 1;
+	}
+	return 0;
+}
+
+static int loop_lookup(struct loop_device **l, int i)
 {
 	struct loop_device *lo;
+	int ret = -ENODEV;
 
-	list_for_each_entry(lo, &loop_devices, lo_list) {
-		if (lo->lo_number == i)
-			return lo;
+	if (i < 0) {
+		int err;
+
+		err = idr_for_each(&loop_index_idr, &find_free_cb, &lo);
+		if (err == 1) {
+			*l = lo;
+			ret = lo->lo_number;
+		}
+		goto out;
 	}
 
-	lo = loop_alloc(i);
+	/* lookup and return a specific i */
+	lo = idr_find(&loop_index_idr, i);
 	if (lo) {
-		add_disk(lo->lo_disk);
-		list_add_tail(&lo->lo_list, &loop_devices);
+		*l = lo;
+		ret = lo->lo_number;
 	}
-	return lo;
-}
-
-static void loop_del_one(struct loop_device *lo)
-{
-	del_gendisk(lo->lo_disk);
-	loop_free(lo);
+out:
+	return ret;
 }
 
 static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 {
 	struct loop_device *lo;
 	struct kobject *kobj;
+	int err;
 
-	mutex_lock(&loop_devices_mutex);
-	lo = loop_init_one(MINOR(dev) >> part_shift);
-	kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM);
-	mutex_unlock(&loop_devices_mutex);
+	mutex_lock(&loop_index_mutex);
+	err = loop_lookup(&lo, MINOR(dev) >> part_shift);
+	if (err < 0)
+		err = loop_add(&lo, MINOR(dev) >> part_shift);
+	if (err < 0)
+		kobj = ERR_PTR(err);
+	else
+		kobj = get_disk(lo->lo_disk);
+	mutex_unlock(&loop_index_mutex);
 
 	*part = 0;
 	return kobj;
 }
 
+static long loop_control_ioctl(struct file *file, unsigned int cmd,
+			       unsigned long parm)
+{
+	struct loop_device *lo;
+	int ret = -ENOSYS;
+
+	mutex_lock(&loop_index_mutex);
+	switch (cmd) {
+	case LOOP_CTL_ADD:
+		ret = loop_lookup(&lo, parm);
+		if (ret >= 0) {
+			ret = -EEXIST;
+			break;
+		}
+		ret = loop_add(&lo, parm);
+		break;
+	case LOOP_CTL_REMOVE:
+		ret = loop_lookup(&lo, parm);
+		if (ret < 0)
+			break;
+		mutex_lock(&lo->lo_ctl_mutex);
+		if (lo->lo_state != Lo_unbound) {
+			ret = -EBUSY;
+			mutex_unlock(&lo->lo_ctl_mutex);
+			break;
+		}
+		if (lo->lo_refcnt > 0) {
+			ret = -EBUSY;
+			mutex_unlock(&lo->lo_ctl_mutex);
+			break;
+		}
+		lo->lo_disk->private_data = NULL;
+		mutex_unlock(&lo->lo_ctl_mutex);
+		idr_remove(&loop_index_idr, lo->lo_number);
+		loop_remove(lo);
+		break;
+	case LOOP_CTL_GET_FREE:
+		ret = loop_lookup(&lo, -1);
+		if (ret >= 0)
+			break;
+		ret = loop_add(&lo, -1);
+	}
+	mutex_unlock(&loop_index_mutex);
+
+	return ret;
+}
+
+static const struct file_operations loop_ctl_fops = {
+	.open		= nonseekable_open,
+	.unlocked_ioctl	= loop_control_ioctl,
+	.compat_ioctl	= loop_control_ioctl,
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice loop_misc = {
+	.minor		= LOOP_CTRL_MINOR,
+	.name		= "loop-control",
+	.fops		= &loop_ctl_fops,
+};
+
+MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR);
+MODULE_ALIAS("devname:loop-control");
+
 static int __init loop_init(void)
 {
 	int i, nr;
 	unsigned long range;
-	struct loop_device *lo, *next;
+	struct loop_device *lo;
+	int err;
 
-	/*
-	 * loop module now has a feature to instantiate underlying device
-	 * structure on-demand, provided that there is an access dev node.
-	 * However, this will not work well with user space tool that doesn't
-	 * know about such "feature".  In order to not break any existing
-	 * tool, we do the following:
-	 *
-	 * (1) if max_loop is specified, create that many upfront, and this
-	 *     also becomes a hard limit.
-	 * (2) if max_loop is not specified, create 8 loop device on module
-	 *     load, user can further extend loop device by create dev node
-	 *     themselves and have kernel automatically instantiate actual
-	 *     device on-demand.
-	 */
+	err = misc_register(&loop_misc);
+	if (err < 0)
+		return err;
 
 	part_shift = 0;
 	if (max_part > 0) {
@@ -1804,57 +1827,60 @@ static int __init loop_init(void)
 	if (max_loop > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
 
+	/*
+	 * If max_loop is specified, create that many devices upfront.
+	 * This also becomes a hard limit. If max_loop is not specified,
+	 * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
+	 * init time. Loop devices can be requested on-demand with the
+	 * /dev/loop-control interface, or be instantiated by accessing
+	 * a 'dead' device node.
+	 */
 	if (max_loop) {
 		nr = max_loop;
 		range = max_loop << part_shift;
 	} else {
-		nr = 8;
+		nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
 		range = 1UL << MINORBITS;
 	}
 
 	if (register_blkdev(LOOP_MAJOR, "loop"))
 		return -EIO;
 
-	for (i = 0; i < nr; i++) {
-		lo = loop_alloc(i);
-		if (!lo)
-			goto Enomem;
-		list_add_tail(&lo->lo_list, &loop_devices);
-	}
-
-	/* point of no return */
-
-	list_for_each_entry(lo, &loop_devices, lo_list)
-		add_disk(lo->lo_disk);
-
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
+	/* pre-create number of devices given by config or max_loop */
+	mutex_lock(&loop_index_mutex);
+	for (i = 0; i < nr; i++)
+		loop_add(&lo, i);
+	mutex_unlock(&loop_index_mutex);
+
 	printk(KERN_INFO "loop: module loaded\n");
 	return 0;
+}
 
-Enomem:
-	printk(KERN_INFO "loop: out of memory\n");
-
-	list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
-		loop_free(lo);
+static int loop_exit_cb(int id, void *ptr, void *data)
+{
+	struct loop_device *lo = ptr;
 
-	unregister_blkdev(LOOP_MAJOR, "loop");
-	return -ENOMEM;
+	loop_remove(lo);
+	return 0;
 }
 
 static void __exit loop_exit(void)
 {
 	unsigned long range;
-	struct loop_device *lo, *next;
 
 	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
-	list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
-		loop_del_one(lo);
+	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
+	idr_remove_all(&loop_index_idr);
+	idr_destroy(&loop_index_idr);
 
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
 	unregister_blkdev(LOOP_MAJOR, "loop");
+
+	misc_deregister(&loop_misc);
 }
 
 module_init(loop_init);