loop.c

来自「linux 内核源代码」· C语言 代码 · 共 1,565 行 · 第 1/3 页

	spin_lock_irq(&lo->lo_lock);
	if (lo->lo_state != Lo_bound)
		goto out;
	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
		goto out;
	loop_add_bio(lo, old_bio);
	wake_up(&lo->lo_event);
	spin_unlock_irq(&lo->lo_lock);
	return 0;

out:
	spin_unlock_irq(&lo->lo_lock);
	bio_io_error(old_bio);
	return 0;
}

/*
 * kick off io on the underlying address space
 */
static void loop_unplug(struct request_queue *q)
{
	struct loop_device *lo = q->queuedata;

	clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
	blk_run_address_space(lo->lo_backing_file->f_mapping);
}

struct switch_request {
	struct file *file;
	struct completion wait;
};

static void do_loop_switch(struct loop_device *, struct switch_request *);

static inline void loop_handle_bio(struct loop_device *lo, struct bio *bio)
{
	if (unlikely(!bio->bi_bdev)) {
		do_loop_switch(lo, bio->bi_private);
		bio_put(bio);
	} else {
		int ret = do_bio_filebacked(lo, bio);
		bio_endio(bio, ret);
	}
}

/*
 * worker thread that handles reads/writes to file backed loop devices,
 * to avoid blocking in our make_request_fn. it also does loop decrypting
 * on reads for block backed loop, as that is too heavy to do from
 * b_end_io context where irqs may be disabled.
 *
 * Loop explanation:  loop_clr_fd() sets lo_state to Lo_rundown before
 * calling kthread_stop().  Therefore once kthread_should_stop() is
 * true, make_request will not place any more requests.  Therefore
 * once kthread_should_stop() is true and lo_bio is NULL, we are
 * done with the loop.
 */
static int loop_thread(void *data)
{
	struct loop_device *lo = data;
	struct bio *bio;

	set_user_nice(current, -20);

	while (!kthread_should_stop() || lo->lo_bio) {

		wait_event_interruptible(lo->lo_event,
				lo->lo_bio || kthread_should_stop());

		if (!lo->lo_bio)
			continue;
		spin_lock_irq(&lo->lo_lock);
		bio = loop_get_bio(lo);
		spin_unlock_irq(&lo->lo_lock);

		BUG_ON(!bio);
		loop_handle_bio(lo, bio);
	}

	return 0;
}

/*
 * loop_switch performs the hard work of switching a backing store.
 * First it needs to flush existing IO, it does this by sending a magic
 * BIO down the pipe. The completion of this BIO does the actual switch.
 */
static int loop_switch(struct loop_device *lo, struct file *file)
{
	struct switch_request w;
	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
	if (!bio)
		return -ENOMEM;
	init_completion(&w.wait);
	w.file = file;
	bio->bi_private = &w;
	bio->bi_bdev = NULL;
	loop_make_request(lo->lo_queue, bio);
	wait_for_completion(&w.wait);
	return 0;
}

/*
 * Do the actual switch; called from the BIO completion routine
 */
static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
{
	struct file *file = p->file;
	struct file *old_file = lo->lo_backing_file;
	struct address_space *mapping = file->f_mapping;

	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
	lo->lo_backing_file = file;
	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
	lo->old_gfp_mask = mapping_gfp_mask(mapping);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
	complete(&p->wait);
}


/*
 * loop_change_fd switched the backing store of a loopback device to
 * a new file. This is useful for operating system installers to free up
 * the original file and in High Availability environments to switch to
 * an alternative location for the content in case of server meltdown.
 * This can only work if the loop device is used read-only, and if the
 * new backing store is the same size and type as the old backing store.
 */
static int loop_change_fd(struct loop_device *lo, struct file *lo_file,
		       struct block_device *bdev, unsigned int arg)
{
	struct file	*file, *old_file;
	struct inode	*inode;
	int		error;

	error = -ENXIO;
	if (lo->lo_state != Lo_bound)
		goto out;

	/* the loop device has to be read-only */
	error = -EINVAL;
	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
		goto out;

	error = -EBADF;
	file = fget(arg);
	if (!file)
		goto out;

	inode = file->f_mapping->host;
	old_file = lo->lo_backing_file;

	error = -EINVAL;

	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
		goto out_putf;

	/* new backing store needs to support loop (eg splice_read) */
	if (!inode->i_fop->splice_read)
		goto out_putf;

	/* size of the new backing store needs to be the same */
	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
		goto out_putf;

	/* and ... switch */
	error = loop_switch(lo, file);
	if (error)
		goto out_putf;

	fput(old_file);
	return 0;

 out_putf:
	fput(file);
 out:
	return error;
}

static inline int is_loop_device(struct file *file)
{
	struct inode *i = file->f_mapping->host;

	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
}

static int loop_set_fd(struct loop_device *lo, struct file *lo_file,
		       struct block_device *bdev, unsigned int arg)
{
	struct file	*file, *f;
	struct inode	*inode;
	struct address_space *mapping;
	unsigned lo_blocksize;
	int		lo_flags = 0;
	int		error;
	loff_t		size;

	/* This is safe, since we have a reference from open(). */
	__module_get(THIS_MODULE);

	error = -EBADF;
	file = fget(arg);
	if (!file)
		goto out;

	error = -EBUSY;
	if (lo->lo_state != Lo_unbound)
		goto out_putf;

	/* Avoid recursion */
	f = file;
	while (is_loop_device(f)) {
		struct loop_device *l;

		if (f->f_mapping->host->i_rdev == lo_file->f_mapping->host->i_rdev)
			goto out_putf;

		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
		if (l->lo_state == Lo_unbound) {
			error = -EINVAL;
			goto out_putf;
		}
		f = l->lo_backing_file;
	}

	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 we can't read - sorry. If we only can't write - well,
		 * it's going to be read-only.
		 */
		if (!file->f_op->splice_read)
			goto out_putf;
		if (aops->prepare_write || 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;

		lo_blocksize = S_ISBLK(inode->i_mode) ?
			inode->i_bdev->bd_block_size : PAGE_SIZE;

		error = 0;
	} else {
		goto out_putf;
	}

	size = get_loop_size(lo, file);

	if ((loff_t)(sector_t)size != size) {
		error = -EFBIG;
		goto out_putf;
	}

	if (!(lo_file->f_mode & FMODE_WRITE))
		lo_flags |= LO_FLAGS_READ_ONLY;

	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);

	lo->lo_blocksize = lo_blocksize;
	lo->lo_device = bdev;
	lo->lo_flags = lo_flags;
	lo->lo_backing_file = file;
	lo->transfer = transfer_none;
	lo->ioctl = NULL;
	lo->lo_sizelimit = 0;
	lo->old_gfp_mask = mapping_gfp_mask(mapping);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));

	lo->lo_bio = lo->lo_biotail = NULL;

	/*
	 * set queue make_request_fn, and add limits based on lower level
	 * device
	 */
	blk_queue_make_request(lo->lo_queue, loop_make_request);
	lo->lo_queue->queuedata = lo;
	lo->lo_queue->unplug_fn = loop_unplug;

	set_capacity(lo->lo_disk, size);
	bd_set_size(bdev, size << 9);

	set_blocksize(bdev, lo_blocksize);

	lo->lo_thread = kthread_create(loop_thread, lo, "loop%d",
						lo->lo_number);
	if (IS_ERR(lo->lo_thread)) {
		error = PTR_ERR(lo->lo_thread);
		goto out_clr;
	}
	lo->lo_state = Lo_bound;
	wake_up_process(lo->lo_thread);
	return 0;

out_clr:
	lo->lo_thread = NULL;
	lo->lo_device = NULL;
	lo->lo_backing_file = NULL;
	lo->lo_flags = 0;
	set_capacity(lo->lo_disk, 0);
	invalidate_bdev(bdev);
	bd_set_size(bdev, 0);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
	lo->lo_state = Lo_unbound;
 out_putf:
	fput(file);
 out:
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
	return error;
}

static int
loop_release_xfer(struct loop_device *lo)
{
	int err = 0;
	struct loop_func_table *xfer = lo->lo_encryption;

	if (xfer) {
		if (xfer->release)
			err = xfer->release(lo);
		lo->transfer = NULL;
		lo->lo_encryption = NULL;
		module_put(xfer->owner);
	}
	return err;
}

static int
loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
	       const struct loop_info64 *i)
{
	int err = 0;

	if (xfer) {
		struct module *owner = xfer->owner;

		if (!try_module_get(owner))
			return -EINVAL;
		if (xfer->init)
			err = xfer->init(lo, i);
		if (err)
			module_put(owner);
		else
			lo->lo_encryption = xfer;
	}
	return err;
}

static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
{
	struct file *filp = lo->lo_backing_file;
	gfp_t gfp = lo->old_gfp_mask;

	if (lo->lo_state != Lo_bound)
		return -ENXIO;

	if (lo->lo_refcnt > 1)	/* we needed one fd for the ioctl */
		return -EBUSY;

	if (filp == NULL)
		return -EINVAL;

	spin_lock_irq(&lo->lo_lock);
	lo->lo_state = Lo_rundown;
	spin_unlock_irq(&lo->lo_lock);

	kthread_stop(lo->lo_thread);

	lo->lo_backing_file = NULL;

	loop_release_xfer(lo);
	lo->transfer = NULL;
	lo->ioctl = NULL;
	lo->lo_device = NULL;
	lo->lo_encryption = NULL;
	lo->lo_offset = 0;
	lo->lo_sizelimit = 0;
	lo->lo_encrypt_key_size = 0;
	lo->lo_flags = 0;
	lo->lo_thread = NULL;
	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
	invalidate_bdev(bdev);
	set_capacity(lo->lo_disk, 0);
	bd_set_size(bdev, 0);
	mapping_set_gfp_mask(filp->f_mapping, gfp);
	lo->lo_state = Lo_unbound;
	fput(filp);
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
	return 0;
}

static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
	int err;
	struct loop_func_table *xfer;

	if (lo->lo_encrypt_key_size && lo->lo_key_owner != current->uid &&
	    !capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (lo->lo_state != Lo_bound)
		return -ENXIO;
	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
		return -EINVAL;

	err = loop_release_xfer(lo);
	if (err)
		return err;

	if (info->lo_encrypt_type) {
		unsigned int type = info->lo_encrypt_type;

		if (type >= MAX_LO_CRYPT)
			return -EINVAL;
		xfer = xfer_funcs[type];
		if (xfer == NULL)
			return -EINVAL;
	} else
		xfer = NULL;

	err = loop_init_xfer(lo, xfer, info);
	if (err)
		return err;

	if (lo->lo_offset != info->lo_offset ||
	    lo->lo_sizelimit != info->lo_sizelimit) {
		lo->lo_offset = info->lo_offset;
		lo->lo_sizelimit = info->lo_sizelimit;
		if (figure_loop_size(lo))
			return -EFBIG;
	}

	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
	lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;

	if (!xfer)
		xfer = &none_funcs;
	lo->transfer = xfer->transfer;
	lo->ioctl = xfer->ioctl;

	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
	lo->lo_init[0] = info->lo_init[0];
	lo->lo_init[1] = info->lo_init[1];
	if (info->lo_encrypt_key_size) {
		memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
		       info->lo_encrypt_key_size);
		lo->lo_key_owner = current->uid;
	}	

	return 0;
}

static int
loop_get_status(struct loop_device *lo, struct loop_info64 *info)
{
	struct file *file = lo->lo_backing_file;
	struct kstat stat;
	int error;

	if (lo->lo_state != Lo_bound)
		return -ENXIO;
	error = vfs_getattr(file->f_path.mnt, file->f_path.dentry, &stat);
	if (error)
		return error;
	memset(info, 0, sizeof(*info));
	info->lo_number = lo->lo_number;
	info->lo_device = huge_encode_dev(stat.dev);
	info->lo_inode = stat.ino;
	info->lo_rdevice = huge_encode_dev(lo->lo_device ? stat.rdev : stat.dev);
	info->lo_offset = lo->lo_offset;
	info->lo_sizelimit = lo->lo_sizelimit;
	info->lo_flags = lo->lo_flags;
	memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
	memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
	info->lo_encrypt_type =
		lo->lo_encryption ? lo->lo_encryption->number : 0;
	if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
		info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
		memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
		       lo->lo_encrypt_key_size);
	}
	return 0;
}

static void
loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
{
	memset(info64, 0, sizeof(*info64));
	info64->lo_number = info->lo_number;
	info64->lo_device = info->lo_device;
	info64->lo_inode = info->lo_inode;
	info64->lo_rdevice = info->lo_rdevice;
	info64->lo_offset = info->lo_offset;
	info64->lo_sizelimit = 0;
	info64->lo_encrypt_type = info->lo_encrypt_type;
	info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
	info64->lo_flags = info->lo_flags;
	info64->lo_init[0] = info->lo_init[0];
	info64->lo_init[1] = info->lo_init[1];
	if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
	else
		memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
	memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
}

static int
loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
{