loop.c 47.1 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
/*
 *  linux/drivers/block/loop.c
 *
 *  Written by Theodore Ts'o, 3/29/93
 *
 * Copyright 1993 by Theodore Ts'o.  Redistribution of this file is
 * permitted under the GNU General Public License.
 *
 * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993
 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996
 *
 * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994
 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996
 *
 * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997
 *
 * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998
 *
 * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998
 *
 * Loadable modules and other fixes by AK, 1998
 *
 * Make real block number available to downstream transfer functions, enables
 * CBC (and relatives) mode encryption requiring unique IVs per data block.
 * Reed H. Petty, rhp@draper.net
 *
 * Maximum number of loop devices now dynamic via max_loop module parameter.
 * Russell Kroll <rkroll@exploits.org> 19990701
 *
 * Maximum number of loop devices when compiled-in now selectable by passing
 * max_loop=<1-255> to the kernel on boot.
32
 * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999
L
Linus Torvalds 已提交
33 34 35 36 37 38 39 40 41 42
 *
 * Completely rewrite request handling to be make_request_fn style and
 * non blocking, pushing work to a helper thread. Lots of fixes from
 * Al Viro too.
 * Jens Axboe <axboe@suse.de>, Nov 2000
 *
 * Support up to 256 loop devices
 * Heinz Mauelshagen <mge@sistina.com>, Feb 2002
 *
 * Support for falling back on the write file operation when the address space
43
 * operations write_begin is not available on the backing filesystem.
L
Linus Torvalds 已提交
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
 * Anton Altaparmakov, 16 Feb 2005
 *
 * Still To Fix:
 * - Advisory locking is ignored here.
 * - Should use an own CAP_* category instead of CAP_SYS_ADMIN
 *
 */

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/init.h>
#include <linux/swap.h>
#include <linux/slab.h>
66
#include <linux/compat.h>
L
Linus Torvalds 已提交
67
#include <linux/suspend.h>
68
#include <linux/freezer.h>
69
#include <linux/mutex.h>
L
Linus Torvalds 已提交
70 71 72
#include <linux/writeback.h>
#include <linux/completion.h>
#include <linux/highmem.h>
73
#include <linux/kthread.h>
74
#include <linux/splice.h>
75
#include <linux/sysfs.h>
76
#include <linux/miscdevice.h>
77
#include <linux/falloc.h>
A
Al Viro 已提交
78
#include "loop.h"
L
Linus Torvalds 已提交
79 80 81

#include <asm/uaccess.h>

82 83
static DEFINE_IDR(loop_index_idr);
static DEFINE_MUTEX(loop_index_mutex);
L
Linus Torvalds 已提交
84

85 86 87
static int max_part;
static int part_shift;

L
Linus Torvalds 已提交
88 89 90 91 92 93 94 95
/*
 * Transfer functions
 */
static int transfer_none(struct loop_device *lo, int cmd,
			 struct page *raw_page, unsigned raw_off,
			 struct page *loop_page, unsigned loop_off,
			 int size, sector_t real_block)
{
96 97
	char *raw_buf = kmap_atomic(raw_page) + raw_off;
	char *loop_buf = kmap_atomic(loop_page) + loop_off;
L
Linus Torvalds 已提交
98 99 100 101 102 103

	if (cmd == READ)
		memcpy(loop_buf, raw_buf, size);
	else
		memcpy(raw_buf, loop_buf, size);

104 105
	kunmap_atomic(loop_buf);
	kunmap_atomic(raw_buf);
L
Linus Torvalds 已提交
106 107 108 109 110 111 112 113 114
	cond_resched();
	return 0;
}

static int transfer_xor(struct loop_device *lo, int cmd,
			struct page *raw_page, unsigned raw_off,
			struct page *loop_page, unsigned loop_off,
			int size, sector_t real_block)
{
115 116
	char *raw_buf = kmap_atomic(raw_page) + raw_off;
	char *loop_buf = kmap_atomic(loop_page) + loop_off;
L
Linus Torvalds 已提交
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
	char *in, *out, *key;
	int i, keysize;

	if (cmd == READ) {
		in = raw_buf;
		out = loop_buf;
	} else {
		in = loop_buf;
		out = raw_buf;
	}

	key = lo->lo_encrypt_key;
	keysize = lo->lo_encrypt_key_size;
	for (i = 0; i < size; i++)
		*out++ = *in++ ^ key[(i & 511) % keysize];

133 134
	kunmap_atomic(loop_buf);
	kunmap_atomic(raw_buf);
L
Linus Torvalds 已提交
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162
	cond_resched();
	return 0;
}

static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
	if (unlikely(info->lo_encrypt_key_size <= 0))
		return -EINVAL;
	return 0;
}

static struct loop_func_table none_funcs = {
	.number = LO_CRYPT_NONE,
	.transfer = transfer_none,
}; 	

static struct loop_func_table xor_funcs = {
	.number = LO_CRYPT_XOR,
	.transfer = transfer_xor,
	.init = xor_init
}; 	

/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
	&none_funcs,
	&xor_funcs
};

163
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
L
Linus Torvalds 已提交
164
{
165
	loff_t loopsize;
L
Linus Torvalds 已提交
166 167

	/* Compute loopsize in bytes */
168 169 170 171
	loopsize = i_size_read(file->f_mapping->host);
	if (offset > 0)
		loopsize -= offset;
	/* offset is beyond i_size, weird but possible */
172 173
	if (loopsize < 0)
		return 0;
L
Linus Torvalds 已提交
174

175 176
	if (sizelimit > 0 && sizelimit < loopsize)
		loopsize = sizelimit;
L
Linus Torvalds 已提交
177 178 179 180 181 182 183
	/*
	 * Unfortunately, if we want to do I/O on the device,
	 * the number of 512-byte sectors has to fit into a sector_t.
	 */
	return loopsize >> 9;
}

184 185 186 187 188
static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
}

L
Linus Torvalds 已提交
189
static int
190
figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
L
Linus Torvalds 已提交
191
{
192
	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
L
Linus Torvalds 已提交
193
	sector_t x = (sector_t)size;
194
	struct block_device *bdev = lo->lo_device;
L
Linus Torvalds 已提交
195 196 197

	if (unlikely((loff_t)x != size))
		return -EFBIG;
198 199 200 201
	if (lo->lo_offset != offset)
		lo->lo_offset = offset;
	if (lo->lo_sizelimit != sizelimit)
		lo->lo_sizelimit = sizelimit;
202
	set_capacity(lo->lo_disk, x);
203 204 205
	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
	/* let user-space know about the new size */
	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
206
	return 0;
L
Linus Torvalds 已提交
207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226
}

static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
	       struct page *rpage, unsigned roffs,
	       struct page *lpage, unsigned loffs,
	       int size, sector_t rblock)
{
	if (unlikely(!lo->transfer))
		return 0;

	return lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
}

/**
 * __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()
 * and do_lo_send_write().
 */
227
static int __do_lo_send_write(struct file *file,
A
Al Viro 已提交
228
		u8 *buf, const int len, loff_t pos)
L
Linus Torvalds 已提交
229 230 231 232
{
	ssize_t bw;
	mm_segment_t old_fs = get_fs();

A
Al Viro 已提交
233
	file_start_write(file);
L
Linus Torvalds 已提交
234 235 236
	set_fs(get_ds());
	bw = file->f_op->write(file, buf, len, &pos);
	set_fs(old_fs);
A
Al Viro 已提交
237
	file_end_write(file);
L
Linus Torvalds 已提交
238 239 240 241 242 243 244 245 246 247 248 249
	if (likely(bw == len))
		return 0;
	printk(KERN_ERR "loop: Write error at byte offset %llu, length %i.\n",
			(unsigned long long)pos, len);
	if (bw >= 0)
		bw = -EIO;
	return bw;
}

/**
 * do_lo_send_direct_write - helper for writing data to a loop device
 *
250 251
 * This is the fast, non-transforming version that does not need double
 * buffering.
L
Linus Torvalds 已提交
252 253
 */
static int do_lo_send_direct_write(struct loop_device *lo,
254
		struct bio_vec *bvec, loff_t pos, struct page *page)
L
Linus Torvalds 已提交
255 256
{
	ssize_t bw = __do_lo_send_write(lo->lo_backing_file,
A
Al Viro 已提交
257
			kmap(bvec->bv_page) + bvec->bv_offset,
L
Linus Torvalds 已提交
258 259 260 261 262 263 264 265 266
			bvec->bv_len, pos);
	kunmap(bvec->bv_page);
	cond_resched();
	return bw;
}

/**
 * do_lo_send_write - helper for writing data to a loop device
 *
267 268 269
 * 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.
L
Linus Torvalds 已提交
270 271
 */
static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
272
		loff_t pos, struct page *page)
L
Linus Torvalds 已提交
273 274 275 276 277
{
	int ret = lo_do_transfer(lo, WRITE, page, 0, bvec->bv_page,
			bvec->bv_offset, bvec->bv_len, pos >> 9);
	if (likely(!ret))
		return __do_lo_send_write(lo->lo_backing_file,
A
Al Viro 已提交
278
				page_address(page), bvec->bv_len,
L
Linus Torvalds 已提交
279 280 281 282 283 284 285 286
				pos);
	printk(KERN_ERR "loop: Transfer error at byte offset %llu, "
			"length %i.\n", (unsigned long long)pos, bvec->bv_len);
	if (ret > 0)
		ret = -EIO;
	return ret;
}

287
static int lo_send(struct loop_device *lo, struct bio *bio, loff_t pos)
L
Linus Torvalds 已提交
288
{
289
	int (*do_lo_send)(struct loop_device *, struct bio_vec *, loff_t,
L
Linus Torvalds 已提交
290
			struct page *page);
291 292
	struct bio_vec bvec;
	struct bvec_iter iter;
L
Linus Torvalds 已提交
293
	struct page *page = NULL;
294
	int ret = 0;
L
Linus Torvalds 已提交
295

296 297 298 299 300 301 302
	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 {
L
Linus Torvalds 已提交
303 304
		do_lo_send = do_lo_send_direct_write;
	}
305

306 307
	bio_for_each_segment(bvec, bio, iter) {
		ret = do_lo_send(lo, &bvec, pos, page);
L
Linus Torvalds 已提交
308 309
		if (ret < 0)
			break;
310
		pos += bvec.bv_len;
L
Linus Torvalds 已提交
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
	}
	if (page) {
		kunmap(page);
		__free_page(page);
	}
out:
	return ret;
fail:
	printk(KERN_ERR "loop: Failed to allocate temporary page for write.\n");
	ret = -ENOMEM;
	goto out;
}

struct lo_read_data {
	struct loop_device *lo;
	struct page *page;
	unsigned offset;
	int bsize;
};

static int
332 333
lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
		struct splice_desc *sd)
L
Linus Torvalds 已提交
334
{
335
	struct lo_read_data *p = sd->u.data;
L
Linus Torvalds 已提交
336
	struct loop_device *lo = p->lo;
337
	struct page *page = buf->page;
L
Linus Torvalds 已提交
338
	sector_t IV;
339
	int size;
L
Linus Torvalds 已提交
340

341 342 343 344 345
	IV = ((sector_t) page->index << (PAGE_CACHE_SHIFT - 9)) +
							(buf->offset >> 9);
	size = sd->len;
	if (size > p->bsize)
		size = p->bsize;
L
Linus Torvalds 已提交
346

347
	if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
L
Linus Torvalds 已提交
348 349
		printk(KERN_ERR "loop: transfer error block %ld\n",
		       page->index);
350
		size = -EINVAL;
L
Linus Torvalds 已提交
351 352 353 354
	}

	flush_dcache_page(p->page);

355 356 357
	if (size > 0)
		p->offset += size;

L
Linus Torvalds 已提交
358 359 360
	return size;
}

361 362 363 364 365 366
static int
lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
	return __splice_from_pipe(pipe, sd, lo_splice_actor);
}

367
static ssize_t
L
Linus Torvalds 已提交
368 369 370 371
do_lo_receive(struct loop_device *lo,
	      struct bio_vec *bvec, int bsize, loff_t pos)
{
	struct lo_read_data cookie;
372
	struct splice_desc sd;
L
Linus Torvalds 已提交
373
	struct file *file;
374
	ssize_t retval;
L
Linus Torvalds 已提交
375 376 377 378 379

	cookie.lo = lo;
	cookie.page = bvec->bv_page;
	cookie.offset = bvec->bv_offset;
	cookie.bsize = bsize;
380 381 382 383 384 385 386

	sd.len = 0;
	sd.total_len = bvec->bv_len;
	sd.flags = 0;
	sd.pos = pos;
	sd.u.data = &cookie;

L
Linus Torvalds 已提交
387
	file = lo->lo_backing_file;
388 389
	retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor);

390
	return retval;
L
Linus Torvalds 已提交
391 392 393 394 395
}

static int
lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
{
396 397
	struct bio_vec bvec;
	struct bvec_iter iter;
398
	ssize_t s;
L
Linus Torvalds 已提交
399

400 401
	bio_for_each_segment(bvec, bio, iter) {
		s = do_lo_receive(lo, &bvec, bsize, pos);
402 403 404
		if (s < 0)
			return s;

405
		if (s != bvec.bv_len) {
406
			zero_fill_bio(bio);
L
Linus Torvalds 已提交
407
			break;
408
		}
409
		pos += bvec.bv_len;
L
Linus Torvalds 已提交
410
	}
411
	return 0;
L
Linus Torvalds 已提交
412 413 414 415 416 417 418
}

static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
{
	loff_t pos;
	int ret;

419
	pos = ((loff_t) bio->bi_iter.bi_sector << 9) + lo->lo_offset;
420 421 422 423

	if (bio_rw(bio) == WRITE) {
		struct file *file = lo->lo_backing_file;

424
		if (bio->bi_rw & REQ_FLUSH) {
425
			ret = vfs_fsync(file, 0);
426
			if (unlikely(ret && ret != -EINVAL)) {
427 428 429 430 431
				ret = -EIO;
				goto out;
			}
		}

432 433
		/*
		 * We use punch hole to reclaim the free space used by the
434
		 * image a.k.a. discard. However we do not support discard if
435 436 437 438 439 440 441 442 443 444 445 446 447
		 * encryption is enabled, because it may give an attacker
		 * useful information.
		 */
		if (bio->bi_rw & REQ_DISCARD) {
			struct file *file = lo->lo_backing_file;
			int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;

			if ((!file->f_op->fallocate) ||
			    lo->lo_encrypt_key_size) {
				ret = -EOPNOTSUPP;
				goto out;
			}
			ret = file->f_op->fallocate(file, mode, pos,
448
						    bio->bi_iter.bi_size);
449 450 451 452 453 454
			if (unlikely(ret && ret != -EINVAL &&
				     ret != -EOPNOTSUPP))
				ret = -EIO;
			goto out;
		}

455
		ret = lo_send(lo, bio, pos);
456

457
		if ((bio->bi_rw & REQ_FUA) && !ret) {
458
			ret = vfs_fsync(file, 0);
459
			if (unlikely(ret && ret != -EINVAL))
460 461 462
				ret = -EIO;
		}
	} else
L
Linus Torvalds 已提交
463
		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
464 465

out:
L
Linus Torvalds 已提交
466 467 468 469 470 471 472 473
	return ret;
}

/*
 * Add bio to back of pending list
 */
static void loop_add_bio(struct loop_device *lo, struct bio *bio)
{
474
	lo->lo_bio_count++;
475
	bio_list_add(&lo->lo_bio_list, bio);
L
Linus Torvalds 已提交
476 477 478 479 480 481 482
}

/*
 * Grab first pending buffer
 */
static struct bio *loop_get_bio(struct loop_device *lo)
{
483
	lo->lo_bio_count--;
484
	return bio_list_pop(&lo->lo_bio_list);
L
Linus Torvalds 已提交
485 486
}

487
static void loop_make_request(struct request_queue *q, struct bio *old_bio)
L
Linus Torvalds 已提交
488 489 490 491
{
	struct loop_device *lo = q->queuedata;
	int rw = bio_rw(old_bio);

N
Nick Piggin 已提交
492 493 494 495
	if (rw == READA)
		rw = READ;

	BUG_ON(!lo || (rw != READ && rw != WRITE));
L
Linus Torvalds 已提交
496 497 498

	spin_lock_irq(&lo->lo_lock);
	if (lo->lo_state != Lo_bound)
N
Nick Piggin 已提交
499 500 501
		goto out;
	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
		goto out;
502 503 504 505
	if (lo->lo_bio_count >= q->nr_congestion_on)
		wait_event_lock_irq(lo->lo_req_wait,
				    lo->lo_bio_count < q->nr_congestion_off,
				    lo->lo_lock);
L
Linus Torvalds 已提交
506
	loop_add_bio(lo, old_bio);
507
	wake_up(&lo->lo_event);
N
Nick Piggin 已提交
508
	spin_unlock_irq(&lo->lo_lock);
509
	return;
N
Nick Piggin 已提交
510

L
Linus Torvalds 已提交
511
out:
N
Nick Piggin 已提交
512
	spin_unlock_irq(&lo->lo_lock);
513
	bio_io_error(old_bio);
L
Linus Torvalds 已提交
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528
}

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 {
N
Nick Piggin 已提交
529
		int ret = do_bio_filebacked(lo, bio);
530
		bio_endio(bio, ret);
L
Linus Torvalds 已提交
531 532 533 534 535 536 537 538
	}
}

/*
 * 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.
539 540 541 542 543 544
 *
 * 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.
L
Linus Torvalds 已提交
545 546 547 548 549 550 551 552
 */
static int loop_thread(void *data)
{
	struct loop_device *lo = data;
	struct bio *bio;

	set_user_nice(current, -20);

553
	while (!kthread_should_stop() || !bio_list_empty(&lo->lo_bio_list)) {
554

555
		wait_event_interruptible(lo->lo_event,
556 557
				!bio_list_empty(&lo->lo_bio_list) ||
				kthread_should_stop());
N
Nick Piggin 已提交
558

559
		if (bio_list_empty(&lo->lo_bio_list))
N
Nick Piggin 已提交
560 561
			continue;
		spin_lock_irq(&lo->lo_lock);
L
Linus Torvalds 已提交
562
		bio = loop_get_bio(lo);
563 564
		if (lo->lo_bio_count < lo->lo_queue->nr_congestion_off)
			wake_up(&lo->lo_req_wait);
N
Nick Piggin 已提交
565 566 567
		spin_unlock_irq(&lo->lo_lock);

		BUG_ON(!bio);
L
Linus Torvalds 已提交
568 569 570 571 572 573 574 575 576 577 578 579 580 581
		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;
582
	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
L
Linus Torvalds 已提交
583 584 585 586 587 588 589 590 591 592 593
	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;
}

594 595 596 597 598 599 600 601 602 603 604 605
/*
 * Helper to flush the IOs in loop, but keeping loop thread running
 */
static int loop_flush(struct loop_device *lo)
{
	/* loop not yet configured, no running thread, nothing to flush */
	if (!lo->lo_thread)
		return 0;

	return loop_switch(lo, NULL);
}

L
Linus Torvalds 已提交
606 607 608 609 610 611 612
/*
 * 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;
613 614 615 616 617
	struct address_space *mapping;

	/* if no new file, only flush of queued bios requested */
	if (!file)
		goto out;
L
Linus Torvalds 已提交
618

619
	mapping = file->f_mapping;
L
Linus Torvalds 已提交
620 621
	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
	lo->lo_backing_file = file;
622 623
	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
L
Linus Torvalds 已提交
624 625
	lo->old_gfp_mask = mapping_gfp_mask(mapping);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
626
out:
L
Linus Torvalds 已提交
627 628 629 630 631 632 633 634 635 636 637 638
	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.
 */
A
Al Viro 已提交
639 640
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
			  unsigned int arg)
L
Linus Torvalds 已提交
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677
{
	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;

	/* 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);
678
	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
679
		ioctl_by_bdev(bdev, BLKRRPART, 0);
L
Linus Torvalds 已提交
680 681 682 683 684 685 686 687 688 689 690 691 692 693 694
	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;
}

695 696 697 698 699
/* loop sysfs attributes */

static ssize_t loop_attr_show(struct device *dev, char *page,
			      ssize_t (*callback)(struct loop_device *, char *))
{
700 701
	struct gendisk *disk = dev_to_disk(dev);
	struct loop_device *lo = disk->private_data;
702

703
	return callback(lo, page);
704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720
}

#define LOOP_ATTR_RO(_name)						\
static ssize_t loop_attr_##_name##_show(struct loop_device *, char *);	\
static ssize_t loop_attr_do_show_##_name(struct device *d,		\
				struct device_attribute *attr, char *b)	\
{									\
	return loop_attr_show(d, b, loop_attr_##_name##_show);		\
}									\
static struct device_attribute loop_attr_##_name =			\
	__ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL);

static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
{
	ssize_t ret;
	char *p = NULL;

721
	spin_lock_irq(&lo->lo_lock);
722 723
	if (lo->lo_backing_file)
		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
724
	spin_unlock_irq(&lo->lo_lock);
725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754

	if (IS_ERR_OR_NULL(p))
		ret = PTR_ERR(p);
	else {
		ret = strlen(p);
		memmove(buf, p, ret);
		buf[ret++] = '\n';
		buf[ret] = 0;
	}

	return ret;
}

static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
}

static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
}

static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
{
	int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);

	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
}

755 756 757 758 759 760 761
static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
{
	int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);

	return sprintf(buf, "%s\n", partscan ? "1" : "0");
}

762 763 764 765
LOOP_ATTR_RO(backing_file);
LOOP_ATTR_RO(offset);
LOOP_ATTR_RO(sizelimit);
LOOP_ATTR_RO(autoclear);
766
LOOP_ATTR_RO(partscan);
767 768 769 770 771 772

static struct attribute *loop_attrs[] = {
	&loop_attr_backing_file.attr,
	&loop_attr_offset.attr,
	&loop_attr_sizelimit.attr,
	&loop_attr_autoclear.attr,
773
	&loop_attr_partscan.attr,
774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793
	NULL,
};

static struct attribute_group loop_attribute_group = {
	.name = "loop",
	.attrs= loop_attrs,
};

static int loop_sysfs_init(struct loop_device *lo)
{
	return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
				  &loop_attribute_group);
}

static void loop_sysfs_exit(struct loop_device *lo)
{
	sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
			   &loop_attribute_group);
}

794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816
static void loop_config_discard(struct loop_device *lo)
{
	struct file *file = lo->lo_backing_file;
	struct inode *inode = file->f_mapping->host;
	struct request_queue *q = lo->lo_queue;

	/*
	 * We use punch hole to reclaim the free space used by the
	 * image a.k.a. discard. However we do support discard if
	 * encryption is enabled, because it may give an attacker
	 * useful information.
	 */
	if ((!file->f_op->fallocate) ||
	    lo->lo_encrypt_key_size) {
		q->limits.discard_granularity = 0;
		q->limits.discard_alignment = 0;
		q->limits.max_discard_sectors = 0;
		q->limits.discard_zeroes_data = 0;
		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
		return;
	}

	q->limits.discard_granularity = inode->i_sb->s_blocksize;
817
	q->limits.discard_alignment = 0;
818 819 820 821 822
	q->limits.max_discard_sectors = UINT_MAX >> 9;
	q->limits.discard_zeroes_data = 1;
	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}

A
Al Viro 已提交
823
static int loop_set_fd(struct loop_device *lo, fmode_t mode,
L
Linus Torvalds 已提交
824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850
		       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;

A
Al Viro 已提交
851
		if (f->f_mapping->host->i_bdev == bdev)
L
Linus Torvalds 已提交
852 853 854 855 856 857 858 859 860 861 862 863 864 865
			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;

	error = -EINVAL;
866 867
	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
		goto out_putf;
L
Linus Torvalds 已提交
868

869 870 871
	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
	    !file->f_op->write)
		lo_flags |= LO_FLAGS_READ_ONLY;
872

873 874
	lo_blocksize = S_ISBLK(inode->i_mode) ?
		inode->i_bdev->bd_block_size : PAGE_SIZE;
L
Linus Torvalds 已提交
875

876
	error = -EFBIG;
L
Linus Torvalds 已提交
877
	size = get_loop_size(lo, file);
878
	if ((loff_t)(sector_t)size != size)
L
Linus Torvalds 已提交
879 880
		goto out_putf;

881
	error = 0;
L
Linus Torvalds 已提交
882 883 884 885 886 887 888

	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;
889
	lo->transfer = transfer_none;
L
Linus Torvalds 已提交
890 891
	lo->ioctl = NULL;
	lo->lo_sizelimit = 0;
892
	lo->lo_bio_count = 0;
L
Linus Torvalds 已提交
893 894 895
	lo->old_gfp_mask = mapping_gfp_mask(mapping);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));

896
	bio_list_init(&lo->lo_bio_list);
L
Linus Torvalds 已提交
897

898
	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
899
		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
900

901
	set_capacity(lo->lo_disk, size);
L
Linus Torvalds 已提交
902
	bd_set_size(bdev, size << 9);
903
	loop_sysfs_init(lo);
904 905
	/* let user-space know about the new size */
	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
L
Linus Torvalds 已提交
906 907 908

	set_blocksize(bdev, lo_blocksize);

909 910 911 912
	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);
913
		goto out_clr;
914 915 916
	}
	lo->lo_state = Lo_bound;
	wake_up_process(lo->lo_thread);
917 918 919
	if (part_shift)
		lo->lo_flags |= LO_FLAGS_PARTSCAN;
	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
920
		ioctl_by_bdev(bdev, BLKRRPART, 0);
921 922 923 924 925

	/* Grab the block_device to prevent its destruction after we
	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
	 */
	bdgrab(bdev);
L
Linus Torvalds 已提交
926 927
	return 0;

928
out_clr:
929
	loop_sysfs_exit(lo);
930 931 932 933
	lo->lo_thread = NULL;
	lo->lo_device = NULL;
	lo->lo_backing_file = NULL;
	lo->lo_flags = 0;
934
	set_capacity(lo->lo_disk, 0);
935
	invalidate_bdev(bdev);
936
	bd_set_size(bdev, 0);
937
	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
938 939
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
	lo->lo_state = Lo_unbound;
L
Linus Torvalds 已提交
940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984
 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;
}

985
static int loop_clr_fd(struct loop_device *lo)
L
Linus Torvalds 已提交
986 987
{
	struct file *filp = lo->lo_backing_file;
988
	gfp_t gfp = lo->old_gfp_mask;
989
	struct block_device *bdev = lo->lo_device;
L
Linus Torvalds 已提交
990 991 992 993

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

994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008
	/*
	 * If we've explicitly asked to tear down the loop device,
	 * and it has an elevated reference count, set it for auto-teardown when
	 * the last reference goes away. This stops $!~#$@ udev from
	 * preventing teardown because it decided that it needs to run blkid on
	 * the loopback device whenever they appear. xfstests is notorious for
	 * failing tests because blkid via udev races with a losetup
	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
	 * command to fail with EBUSY.
	 */
	if (lo->lo_refcnt > 1) {
		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
		mutex_unlock(&lo->lo_ctl_mutex);
		return 0;
	}
L
Linus Torvalds 已提交
1009 1010 1011 1012 1013 1014 1015 1016

	if (filp == NULL)
		return -EINVAL;

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

1017
	kthread_stop(lo->lo_thread);
L
Linus Torvalds 已提交
1018

1019
	spin_lock_irq(&lo->lo_lock);
L
Linus Torvalds 已提交
1020
	lo->lo_backing_file = NULL;
1021
	spin_unlock_irq(&lo->lo_lock);
L
Linus Torvalds 已提交
1022 1023 1024 1025 1026 1027 1028 1029 1030

	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;
1031
	lo->lo_thread = NULL;
L
Linus Torvalds 已提交
1032 1033 1034
	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);
1035 1036
	if (bdev) {
		bdput(bdev);
A
Al Viro 已提交
1037
		invalidate_bdev(bdev);
1038
	}
1039
	set_capacity(lo->lo_disk, 0);
1040
	loop_sysfs_exit(lo);
1041
	if (bdev) {
A
Al Viro 已提交
1042
		bd_set_size(bdev, 0);
1043 1044 1045
		/* let user-space know about this change */
		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
	}
L
Linus Torvalds 已提交
1046 1047 1048 1049
	mapping_set_gfp_mask(filp->f_mapping, gfp);
	lo->lo_state = Lo_unbound;
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
1050 1051
	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
		ioctl_by_bdev(bdev, BLKRRPART, 0);
1052 1053 1054
	lo->lo_flags = 0;
	if (!part_shift)
		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
1055 1056 1057 1058 1059 1060 1061 1062
	mutex_unlock(&lo->lo_ctl_mutex);
	/*
	 * Need not hold lo_ctl_mutex to fput backing file.
	 * Calling fput holding lo_ctl_mutex triggers a circular
	 * lock dependency possibility warning as fput can take
	 * bd_mutex which is usually taken before lo_ctl_mutex.
	 */
	fput(filp);
L
Linus Torvalds 已提交
1063 1064 1065 1066 1067 1068 1069 1070
	return 0;
}

static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
	int err;
	struct loop_func_table *xfer;
1071
	kuid_t uid = current_uid();
L
Linus Torvalds 已提交
1072

1073
	if (lo->lo_encrypt_key_size &&
1074
	    !uid_eq(lo->lo_key_owner, uid) &&
L
Linus Torvalds 已提交
1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
	    !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 ||
1102
	    lo->lo_sizelimit != info->lo_sizelimit)
1103
		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
L
Linus Torvalds 已提交
1104
			return -EFBIG;
1105

1106
	loop_config_discard(lo);
L
Linus Torvalds 已提交
1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117

	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;

1118 1119 1120 1121
	if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;

1122 1123 1124 1125 1126 1127 1128
	if ((info->lo_flags & LO_FLAGS_PARTSCAN) &&
	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
		lo->lo_flags |= LO_FLAGS_PARTSCAN;
		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
		ioctl_by_bdev(lo->lo_device, BLKRRPART, 0);
	}

L
Linus Torvalds 已提交
1129 1130 1131 1132 1133 1134
	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);
1135
		lo->lo_key_owner = uid;
L
Linus Torvalds 已提交
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149
	}	

	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;
A
Al Viro 已提交
1150
	error = vfs_getattr(&file->f_path, &stat);
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279
	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)
{
	memset(info, 0, sizeof(*info));
	info->lo_number = info64->lo_number;
	info->lo_device = info64->lo_device;
	info->lo_inode = info64->lo_inode;
	info->lo_rdevice = info64->lo_rdevice;
	info->lo_offset = info64->lo_offset;
	info->lo_encrypt_type = info64->lo_encrypt_type;
	info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
	info->lo_flags = info64->lo_flags;
	info->lo_init[0] = info64->lo_init[0];
	info->lo_init[1] = info64->lo_init[1];
	if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
	else
		memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
	memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

	/* error in case values were truncated */
	if (info->lo_device != info64->lo_device ||
	    info->lo_rdevice != info64->lo_rdevice ||
	    info->lo_inode != info64->lo_inode ||
	    info->lo_offset != info64->lo_offset)
		return -EOVERFLOW;

	return 0;
}

static int
loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg)
{
	struct loop_info info;
	struct loop_info64 info64;

	if (copy_from_user(&info, arg, sizeof (struct loop_info)))
		return -EFAULT;
	loop_info64_from_old(&info, &info64);
	return loop_set_status(lo, &info64);
}

static int
loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg)
{
	struct loop_info64 info64;

	if (copy_from_user(&info64, arg, sizeof (struct loop_info64)))
		return -EFAULT;
	return loop_set_status(lo, &info64);
}

static int
loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
	struct loop_info info;
	struct loop_info64 info64;
	int err = 0;

	if (!arg)
		err = -EINVAL;
	if (!err)
		err = loop_get_status(lo, &info64);
	if (!err)
		err = loop_info64_to_old(&info64, &info);
	if (!err && copy_to_user(arg, &info, sizeof(info)))
		err = -EFAULT;

	return err;
}

static int
loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
	struct loop_info64 info64;
	int err = 0;

	if (!arg)
		err = -EINVAL;
	if (!err)
		err = loop_get_status(lo, &info64);
	if (!err && copy_to_user(arg, &info64, sizeof(info64)))
		err = -EFAULT;

	return err;
}

1280 1281 1282
static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
{
	if (unlikely(lo->lo_state != Lo_bound))
1283
		return -ENXIO;
1284

1285
	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
1286 1287
}

A
Al Viro 已提交
1288
static int lo_ioctl(struct block_device *bdev, fmode_t mode,
L
Linus Torvalds 已提交
1289 1290
	unsigned int cmd, unsigned long arg)
{
A
Al Viro 已提交
1291
	struct loop_device *lo = bdev->bd_disk->private_data;
L
Linus Torvalds 已提交
1292 1293
	int err;

1294
	mutex_lock_nested(&lo->lo_ctl_mutex, 1);
L
Linus Torvalds 已提交
1295 1296
	switch (cmd) {
	case LOOP_SET_FD:
A
Al Viro 已提交
1297
		err = loop_set_fd(lo, mode, bdev, arg);
L
Linus Torvalds 已提交
1298 1299
		break;
	case LOOP_CHANGE_FD:
A
Al Viro 已提交
1300
		err = loop_change_fd(lo, bdev, arg);
L
Linus Torvalds 已提交
1301 1302
		break;
	case LOOP_CLR_FD:
1303
		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
1304
		err = loop_clr_fd(lo);
1305 1306
		if (!err)
			goto out_unlocked;
L
Linus Torvalds 已提交
1307 1308
		break;
	case LOOP_SET_STATUS:
1309 1310 1311 1312
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_status_old(lo,
					(struct loop_info __user *)arg);
L
Linus Torvalds 已提交
1313 1314 1315 1316 1317
		break;
	case LOOP_GET_STATUS:
		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
		break;
	case LOOP_SET_STATUS64:
1318 1319 1320 1321
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_status64(lo,
					(struct loop_info64 __user *) arg);
L
Linus Torvalds 已提交
1322 1323 1324 1325
		break;
	case LOOP_GET_STATUS64:
		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
		break;
1326 1327 1328 1329 1330
	case LOOP_SET_CAPACITY:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_capacity(lo, bdev);
		break;
L
Linus Torvalds 已提交
1331 1332 1333
	default:
		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
	}
1334
	mutex_unlock(&lo->lo_ctl_mutex);
1335 1336

out_unlocked:
L
Linus Torvalds 已提交
1337 1338 1339
	return err;
}

1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
#ifdef CONFIG_COMPAT
struct compat_loop_info {
	compat_int_t	lo_number;      /* ioctl r/o */
	compat_dev_t	lo_device;      /* ioctl r/o */
	compat_ulong_t	lo_inode;       /* ioctl r/o */
	compat_dev_t	lo_rdevice;     /* ioctl r/o */
	compat_int_t	lo_offset;
	compat_int_t	lo_encrypt_type;
	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
	compat_int_t	lo_flags;       /* ioctl r/o */
	char		lo_name[LO_NAME_SIZE];
	unsigned char	lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
	compat_ulong_t	lo_init[2];
	char		reserved[4];
};

/*
 * Transfer 32-bit compatibility structure in userspace to 64-bit loop info
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
A
Al Viro 已提交
1361
loop_info64_from_compat(const struct compat_loop_info __user *arg,
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
			struct loop_info64 *info64)
{
	struct compat_loop_info info;

	if (copy_from_user(&info, arg, sizeof(info)))
		return -EFAULT;

	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);
	return 0;
}

/*
 * Transfer 64-bit loop info to 32-bit compatibility structure in userspace
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
loop_info64_to_compat(const struct loop_info64 *info64,
		      struct compat_loop_info __user *arg)
{
	struct compat_loop_info info;

	memset(&info, 0, sizeof(info));
	info.lo_number = info64->lo_number;
	info.lo_device = info64->lo_device;
	info.lo_inode = info64->lo_inode;
	info.lo_rdevice = info64->lo_rdevice;
	info.lo_offset = info64->lo_offset;
	info.lo_encrypt_type = info64->lo_encrypt_type;
	info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
	info.lo_flags = info64->lo_flags;
	info.lo_init[0] = info64->lo_init[0];
	info.lo_init[1] = info64->lo_init[1];
	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
	else
		memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
	memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

	/* error in case values were truncated */
	if (info.lo_device != info64->lo_device ||
	    info.lo_rdevice != info64->lo_rdevice ||
	    info.lo_inode != info64->lo_inode ||
	    info.lo_offset != info64->lo_offset ||
	    info.lo_init[0] != info64->lo_init[0] ||
	    info.lo_init[1] != info64->lo_init[1])
		return -EOVERFLOW;

	if (copy_to_user(arg, &info, sizeof(info)))
		return -EFAULT;
	return 0;
}

static int
loop_set_status_compat(struct loop_device *lo,
		       const struct compat_loop_info __user *arg)
{
	struct loop_info64 info64;
	int ret;

	ret = loop_info64_from_compat(arg, &info64);
	if (ret < 0)
		return ret;
	return loop_set_status(lo, &info64);
}

static int
loop_get_status_compat(struct loop_device *lo,
		       struct compat_loop_info __user *arg)
{
	struct loop_info64 info64;
	int err = 0;

	if (!arg)
		err = -EINVAL;
	if (!err)
		err = loop_get_status(lo, &info64);
	if (!err)
		err = loop_info64_to_compat(&info64, arg);
	return err;
}

A
Al Viro 已提交
1459 1460
static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
			   unsigned int cmd, unsigned long arg)
1461
{
A
Al Viro 已提交
1462
	struct loop_device *lo = bdev->bd_disk->private_data;
1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
	int err;

	switch(cmd) {
	case LOOP_SET_STATUS:
		mutex_lock(&lo->lo_ctl_mutex);
		err = loop_set_status_compat(
			lo, (const struct compat_loop_info __user *) arg);
		mutex_unlock(&lo->lo_ctl_mutex);
		break;
	case LOOP_GET_STATUS:
		mutex_lock(&lo->lo_ctl_mutex);
		err = loop_get_status_compat(
			lo, (struct compat_loop_info __user *) arg);
		mutex_unlock(&lo->lo_ctl_mutex);
		break;
1478
	case LOOP_SET_CAPACITY:
1479 1480 1481 1482 1483 1484
	case LOOP_CLR_FD:
	case LOOP_GET_STATUS64:
	case LOOP_SET_STATUS64:
		arg = (unsigned long) compat_ptr(arg);
	case LOOP_SET_FD:
	case LOOP_CHANGE_FD:
A
Al Viro 已提交
1485
		err = lo_ioctl(bdev, mode, cmd, arg);
1486 1487 1488 1489 1490 1491 1492 1493 1494
		break;
	default:
		err = -ENOIOCTLCMD;
		break;
	}
	return err;
}
#endif

A
Al Viro 已提交
1495
static int lo_open(struct block_device *bdev, fmode_t mode)
L
Linus Torvalds 已提交
1496
{
1497 1498 1499 1500 1501 1502 1503 1504 1505
	struct loop_device *lo;
	int err = 0;

	mutex_lock(&loop_index_mutex);
	lo = bdev->bd_disk->private_data;
	if (!lo) {
		err = -ENXIO;
		goto out;
	}
L
Linus Torvalds 已提交
1506

1507
	mutex_lock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1508
	lo->lo_refcnt++;
1509
	mutex_unlock(&lo->lo_ctl_mutex);
1510 1511 1512
out:
	mutex_unlock(&loop_index_mutex);
	return err;
L
Linus Torvalds 已提交
1513 1514
}

1515
static void lo_release(struct gendisk *disk, fmode_t mode)
L
Linus Torvalds 已提交
1516
{
A
Al Viro 已提交
1517
	struct loop_device *lo = disk->private_data;
1518
	int err;
L
Linus Torvalds 已提交
1519

1520
	mutex_lock(&lo->lo_ctl_mutex);
1521

1522 1523 1524 1525 1526 1527 1528 1529
	if (--lo->lo_refcnt)
		goto out;

	if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
		/*
		 * In autoclear mode, stop the loop thread
		 * and remove configuration after last close.
		 */
1530
		err = loop_clr_fd(lo);
1531
		if (!err)
1532
			return;
1533 1534 1535 1536 1537 1538 1539
	} else {
		/*
		 * Otherwise keep thread (if running) and config,
		 * but flush possible ongoing bios in thread.
		 */
		loop_flush(lo);
	}
1540

1541
out:
1542
	mutex_unlock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1543 1544
}

1545
static const struct block_device_operations lo_fops = {
L
Linus Torvalds 已提交
1546
	.owner =	THIS_MODULE,
A
Al Viro 已提交
1547 1548 1549
	.open =		lo_open,
	.release =	lo_release,
	.ioctl =	lo_ioctl,
1550
#ifdef CONFIG_COMPAT
A
Al Viro 已提交
1551
	.compat_ioctl =	lo_compat_ioctl,
1552
#endif
L
Linus Torvalds 已提交
1553 1554 1555 1556 1557
};

/*
 * And now the modules code and kernel interface.
 */
1558
static int max_loop;
N
Namhyung Kim 已提交
1559
module_param(max_loop, int, S_IRUGO);
K
Ken Chen 已提交
1560
MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
N
Namhyung Kim 已提交
1561
module_param(max_part, int, S_IRUGO);
1562
MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
L
Linus Torvalds 已提交
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);

int loop_register_transfer(struct loop_func_table *funcs)
{
	unsigned int n = funcs->number;

	if (n >= MAX_LO_CRYPT || xfer_funcs[n])
		return -EINVAL;
	xfer_funcs[n] = funcs;
	return 0;
}

1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587
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;
}

L
Linus Torvalds 已提交
1588 1589 1590 1591 1592 1593 1594 1595 1596
int loop_unregister_transfer(int number)
{
	unsigned int n = number;
	struct loop_func_table *xfer;

	if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
		return -EINVAL;

	xfer_funcs[n] = NULL;
1597
	idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
L
Linus Torvalds 已提交
1598 1599 1600 1601 1602 1603
	return 0;
}

EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);

1604
static int loop_add(struct loop_device **l, int i)
1605 1606 1607
{
	struct loop_device *lo;
	struct gendisk *disk;
1608
	int err;
1609

1610
	err = -ENOMEM;
1611
	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
1612
	if (!lo)
1613
		goto out;
1614

1615 1616
	lo->lo_state = Lo_unbound;

T
Tejun Heo 已提交
1617
	/* allocate id, if @id >= 0, we're requesting that specific id */
1618
	if (i >= 0) {
T
Tejun Heo 已提交
1619 1620
		err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
		if (err == -ENOSPC)
1621 1622
			err = -EEXIST;
	} else {
T
Tejun Heo 已提交
1623
		err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL);
1624 1625 1626
	}
	if (err < 0)
		goto out_free_dev;
T
Tejun Heo 已提交
1627
	i = err;
1628

1629
	err = -ENOMEM;
1630 1631
	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
	if (!lo->lo_queue)
1632
		goto out_free_idr;
1633

1634 1635 1636 1637 1638 1639
	/*
	 * set queue make_request_fn
	 */
	blk_queue_make_request(lo->lo_queue, loop_make_request);
	lo->lo_queue->queuedata = lo;

1640
	disk = lo->lo_disk = alloc_disk(1 << part_shift);
1641 1642 1643
	if (!disk)
		goto out_free_queue;

1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
	/*
	 * Disable partition scanning by default. The in-kernel partition
	 * scanning can be requested individually per-device during its
	 * setup. Userspace can always add and remove partitions from all
	 * devices. The needed partition minors are allocated from the
	 * extended minor space, the main loop device numbers will continue
	 * to match the loop minors, regardless of the number of partitions
	 * used.
	 *
	 * If max_part is given, partition scanning is globally enabled for
	 * all loop devices. The minors for the main loop devices will be
	 * multiples of max_part.
	 *
	 * Note: Global-for-all-devices, set-only-at-init, read-only module
	 * parameteters like 'max_loop' and 'max_part' make things needlessly
	 * complicated, are too static, inflexible and may surprise
	 * userspace tools. Parameters like this in general should be avoided.
	 */
	if (!part_shift)
		disk->flags |= GENHD_FL_NO_PART_SCAN;
	disk->flags |= GENHD_FL_EXT_DEVT;
1665 1666 1667 1668
	mutex_init(&lo->lo_ctl_mutex);
	lo->lo_number		= i;
	lo->lo_thread		= NULL;
	init_waitqueue_head(&lo->lo_event);
1669
	init_waitqueue_head(&lo->lo_req_wait);
1670 1671
	spin_lock_init(&lo->lo_lock);
	disk->major		= LOOP_MAJOR;
1672
	disk->first_minor	= i << part_shift;
1673 1674 1675 1676
	disk->fops		= &lo_fops;
	disk->private_data	= lo;
	disk->queue		= lo->lo_queue;
	sprintf(disk->disk_name, "loop%d", i);
1677 1678 1679
	add_disk(disk);
	*l = lo;
	return lo->lo_number;
1680 1681 1682

out_free_queue:
	blk_cleanup_queue(lo->lo_queue);
1683 1684
out_free_idr:
	idr_remove(&loop_index_idr, i);
1685 1686 1687
out_free_dev:
	kfree(lo);
out:
1688
	return err;
1689 1690
}

1691
static void loop_remove(struct loop_device *lo)
L
Linus Torvalds 已提交
1692
{
1693
	del_gendisk(lo->lo_disk);
1694 1695 1696 1697
	blk_cleanup_queue(lo->lo_queue);
	put_disk(lo->lo_disk);
	kfree(lo);
}
L
Linus Torvalds 已提交
1698

1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710
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;
}

1711
static int loop_lookup(struct loop_device **l, int i)
K
Ken Chen 已提交
1712 1713
{
	struct loop_device *lo;
1714
	int ret = -ENODEV;
K
Ken Chen 已提交
1715

1716 1717 1718 1719 1720 1721 1722 1723 1724
	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;
K
Ken Chen 已提交
1725 1726
	}

1727
	/* lookup and return a specific i */
1728
	lo = idr_find(&loop_index_idr, i);
K
Ken Chen 已提交
1729
	if (lo) {
1730 1731
		*l = lo;
		ret = lo->lo_number;
K
Ken Chen 已提交
1732
	}
1733
out:
1734
	return ret;
K
Ken Chen 已提交
1735 1736
}

1737 1738
static struct kobject *loop_probe(dev_t dev, int *part, void *data)
{
A
Al Viro 已提交
1739
	struct loop_device *lo;
1740
	struct kobject *kobj;
1741
	int err;
1742

1743 1744 1745 1746 1747
	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)
1748
		kobj = NULL;
1749 1750 1751
	else
		kobj = get_disk(lo->lo_disk);
	mutex_unlock(&loop_index_mutex);
1752 1753

	*part = 0;
1754
	return kobj;
1755 1756
}

1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820
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");

1821 1822
static int __init loop_init(void)
{
K
Ken Chen 已提交
1823 1824
	int i, nr;
	unsigned long range;
1825
	struct loop_device *lo;
1826
	int err;
K
Ken Chen 已提交
1827

1828 1829 1830
	err = misc_register(&loop_misc);
	if (err < 0)
		return err;
1831 1832

	part_shift = 0;
N
Namhyung Kim 已提交
1833
	if (max_part > 0) {
1834 1835
		part_shift = fls(max_part);

N
Namhyung Kim 已提交
1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846
		/*
		 * Adjust max_part according to part_shift as it is exported
		 * to user space so that user can decide correct minor number
		 * if [s]he want to create more devices.
		 *
		 * Note that -1 is required because partition 0 is reserved
		 * for the whole disk.
		 */
		max_part = (1UL << part_shift) - 1;
	}

1847 1848 1849 1850
	if ((1UL << part_shift) > DISK_MAX_PARTS) {
		err = -EINVAL;
		goto misc_out;
	}
1851

1852 1853 1854 1855
	if (max_loop > 1UL << (MINORBITS - part_shift)) {
		err = -EINVAL;
		goto misc_out;
	}
L
Linus Torvalds 已提交
1856

1857 1858 1859 1860 1861 1862 1863 1864
	/*
	 * 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.
	 */
1865
	if (max_loop) {
K
Ken Chen 已提交
1866
		nr = max_loop;
1867
		range = max_loop << part_shift;
K
Ken Chen 已提交
1868
	} else {
1869
		nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
1870
		range = 1UL << MINORBITS;
K
Ken Chen 已提交
1871 1872
	}

1873 1874 1875 1876
	if (register_blkdev(LOOP_MAJOR, "loop")) {
		err = -EIO;
		goto misc_out;
	}
L
Linus Torvalds 已提交
1877

K
Ken Chen 已提交
1878 1879 1880
	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
				  THIS_MODULE, loop_probe, NULL, NULL);

1881
	/* pre-create number of devices given by config or max_loop */
1882 1883 1884 1885 1886
	mutex_lock(&loop_index_mutex);
	for (i = 0; i < nr; i++)
		loop_add(&lo, i);
	mutex_unlock(&loop_index_mutex);

1887
	printk(KERN_INFO "loop: module loaded\n");
L
Linus Torvalds 已提交
1888
	return 0;
1889 1890 1891 1892

misc_out:
	misc_deregister(&loop_misc);
	return err;
1893
}
K
Ken Chen 已提交
1894

1895 1896 1897
static int loop_exit_cb(int id, void *ptr, void *data)
{
	struct loop_device *lo = ptr;
K
Ken Chen 已提交
1898

1899 1900
	loop_remove(lo);
	return 0;
L
Linus Torvalds 已提交
1901 1902
}

1903
static void __exit loop_exit(void)
L
Linus Torvalds 已提交
1904
{
K
Ken Chen 已提交
1905
	unsigned long range;
L
Linus Torvalds 已提交
1906

1907
	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
K
Ken Chen 已提交
1908

1909 1910
	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
	idr_destroy(&loop_index_idr);
1911

K
Ken Chen 已提交
1912
	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
1913
	unregister_blkdev(LOOP_MAJOR, "loop");
1914 1915

	misc_deregister(&loop_misc);
L
Linus Torvalds 已提交
1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929
}

module_init(loop_init);
module_exit(loop_exit);

#ifndef MODULE
static int __init max_loop_setup(char *str)
{
	max_loop = simple_strtol(str, NULL, 0);
	return 1;
}

__setup("max_loop=", max_loop_setup);
#endif