loop.c 38.7 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 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
 *
 * 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
 * operations prepare_write and/or commit_write are not available on the
 * backing filesystem.
 * 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/smp_lock.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/loop.h>
69
#include <linux/compat.h>
L
Linus Torvalds 已提交
70
#include <linux/suspend.h>
71
#include <linux/freezer.h>
L
Linus Torvalds 已提交
72 73 74 75 76
#include <linux/writeback.h>
#include <linux/buffer_head.h>		/* for invalidate_bdev() */
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/gfp.h>
77
#include <linux/kthread.h>
78
#include <linux/splice.h>
L
Linus Torvalds 已提交
79 80 81

#include <asm/uaccess.h>

82 83
static LIST_HEAD(loop_devices);
static DEFINE_MUTEX(loop_devices_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 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189
/*
 * 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)
{
	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;

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

	kunmap_atomic(raw_buf, KM_USER0);
	kunmap_atomic(loop_buf, KM_USER1);
	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)
{
	char *raw_buf = kmap_atomic(raw_page, KM_USER0) + raw_off;
	char *loop_buf = kmap_atomic(loop_page, KM_USER1) + loop_off;
	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];

	kunmap_atomic(raw_buf, KM_USER0);
	kunmap_atomic(loop_buf, KM_USER1);
	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
};

static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
	loff_t size, offset, loopsize;

	/* Compute loopsize in bytes */
	size = i_size_read(file->f_mapping->host);
	offset = lo->lo_offset;
	loopsize = size - offset;
	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
		loopsize = lo->lo_sizelimit;

	/*
	 * 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;
}

static int
figure_loop_size(struct loop_device *lo)
{
	loff_t size = get_loop_size(lo, lo->lo_backing_file);
	sector_t x = (sector_t)size;

	if (unlikely((loff_t)x != size))
		return -EFBIG;

190
	set_capacity(lo->lo_disk, x);
L
Linus Torvalds 已提交
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
	return 0;					
}

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_aops - helper for writing data to a loop device
 *
 * This is the fast version for backing filesystems which implement the address
210
 * space operations write_begin and write_end.
L
Linus Torvalds 已提交
211 212
 */
static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
213
		int bsize, loff_t pos, struct page *unused)
L
Linus Torvalds 已提交
214 215 216 217 218
{
	struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
	struct address_space *mapping = file->f_mapping;
	pgoff_t index;
	unsigned offset, bv_offs;
219
	int len, ret;
L
Linus Torvalds 已提交
220

221
	mutex_lock(&mapping->host->i_mutex);
L
Linus Torvalds 已提交
222 223 224 225 226 227
	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;
228
		unsigned size, copied;
L
Linus Torvalds 已提交
229
		int transfer_result;
230 231
		struct page *page;
		void *fsdata;
L
Linus Torvalds 已提交
232 233 234 235 236

		IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
		size = PAGE_CACHE_SIZE - offset;
		if (size > len)
			size = len;
237 238 239 240

		ret = pagecache_write_begin(file, mapping, pos, size, 0,
							&page, &fsdata);
		if (ret)
L
Linus Torvalds 已提交
241
			goto fail;
242

L
Linus Torvalds 已提交
243 244
		transfer_result = lo_do_transfer(lo, WRITE, page, offset,
				bvec->bv_page, bv_offs, size, IV);
245
		copied = size;
L
Linus Torvalds 已提交
246
		if (unlikely(transfer_result))
247 248 249 250
			copied = 0;

		ret = pagecache_write_end(file, mapping, pos, size, copied,
							page, fsdata);
251
		if (ret < 0 || ret != copied)
252 253 254 255 256 257 258
			goto fail;

		if (unlikely(transfer_result))
			goto fail;

		bv_offs += copied;
		len -= copied;
L
Linus Torvalds 已提交
259 260
		offset = 0;
		index++;
261
		pos += copied;
L
Linus Torvalds 已提交
262
	}
263
	ret = 0;
L
Linus Torvalds 已提交
264
out:
265
	mutex_unlock(&mapping->host->i_mutex);
L
Linus Torvalds 已提交
266 267 268 269 270 271 272 273 274 275 276 277
	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()
 * and do_lo_send_write().
 */
278
static int __do_lo_send_write(struct file *file,
A
Al Viro 已提交
279
		u8 *buf, const int len, loff_t pos)
L
Linus Torvalds 已提交
280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299
{
	ssize_t bw;
	mm_segment_t old_fs = get_fs();

	set_fs(get_ds());
	bw = file->f_op->write(file, buf, len, &pos);
	set_fs(old_fs);
	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
 *
 * This is the fast, non-transforming version for backing filesystems which do
300
 * not implement the address space operations write_begin and write_end.
L
Linus Torvalds 已提交
301 302 303 304 305 306 307
 * It uses the write file operation which should be present on all writeable
 * filesystems.
 */
static int do_lo_send_direct_write(struct loop_device *lo,
		struct bio_vec *bvec, int bsize, loff_t pos, struct page *page)
{
	ssize_t bw = __do_lo_send_write(lo->lo_backing_file,
A
Al Viro 已提交
308
			kmap(bvec->bv_page) + bvec->bv_offset,
L
Linus Torvalds 已提交
309 310 311 312 313 314 315 316 317 318
			bvec->bv_len, pos);
	kunmap(bvec->bv_page);
	cond_resched();
	return bw;
}

/**
 * do_lo_send_write - helper for writing data to a loop device
 *
 * This is the slow, transforming version for filesystems which do not
319
 * implement the address space operations write_begin and write_end.  It
L
Linus Torvalds 已提交
320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
 * 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.
 */
static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
		int bsize, loff_t pos, struct page *page)
{
	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
335
				page_address(page), bvec->bv_len,
L
Linus Torvalds 已提交
336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389
				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;
}

static int lo_send(struct loop_device *lo, struct bio *bio, int bsize,
		loff_t pos)
{
	int (*do_lo_send)(struct loop_device *, struct bio_vec *, int, loff_t,
			struct page *page);
	struct bio_vec *bvec;
	struct page *page = NULL;
	int i, ret = 0;

	do_lo_send = do_lo_send_aops;
	if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
		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, bsize, pos, page);
		if (ret < 0)
			break;
		pos += bvec->bv_len;
	}
	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
390 391
lo_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
		struct splice_desc *sd)
L
Linus Torvalds 已提交
392
{
393
	struct lo_read_data *p = sd->u.data;
L
Linus Torvalds 已提交
394
	struct loop_device *lo = p->lo;
395
	struct page *page = buf->page;
L
Linus Torvalds 已提交
396
	sector_t IV;
397 398
	size_t size;
	int ret;
L
Linus Torvalds 已提交
399

400
	ret = buf->ops->confirm(pipe, buf);
401 402
	if (unlikely(ret))
		return ret;
L
Linus Torvalds 已提交
403

404 405 406 407 408
	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
409

410
	if (lo_do_transfer(lo, READ, page, buf->offset, p->page, p->offset, size, IV)) {
L
Linus Torvalds 已提交
411 412
		printk(KERN_ERR "loop: transfer error block %ld\n",
		       page->index);
413
		size = -EINVAL;
L
Linus Torvalds 已提交
414 415 416 417
	}

	flush_dcache_page(p->page);

418 419 420
	if (size > 0)
		p->offset += size;

L
Linus Torvalds 已提交
421 422 423
	return size;
}

424 425 426 427 428 429
static int
lo_direct_splice_actor(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
	return __splice_from_pipe(pipe, sd, lo_splice_actor);
}

L
Linus Torvalds 已提交
430 431 432 433 434
static int
do_lo_receive(struct loop_device *lo,
	      struct bio_vec *bvec, int bsize, loff_t pos)
{
	struct lo_read_data cookie;
435
	struct splice_desc sd;
L
Linus Torvalds 已提交
436
	struct file *file;
437
	long retval;
L
Linus Torvalds 已提交
438 439 440 441 442

	cookie.lo = lo;
	cookie.page = bvec->bv_page;
	cookie.offset = bvec->bv_offset;
	cookie.bsize = bsize;
443 444 445 446 447 448 449

	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
450
	file = lo->lo_backing_file;
451 452 453 454 455 456
	retval = splice_direct_to_actor(file, &sd, lo_direct_splice_actor);

	if (retval < 0)
		return retval;

	return 0;
L
Linus Torvalds 已提交
457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
}

static int
lo_receive(struct loop_device *lo, struct bio *bio, int bsize, loff_t pos)
{
	struct bio_vec *bvec;
	int i, ret = 0;

	bio_for_each_segment(bvec, bio, i) {
		ret = do_lo_receive(lo, bvec, bsize, pos);
		if (ret < 0)
			break;
		pos += bvec->bv_len;
	}
	return ret;
}

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

	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
	if (bio_rw(bio) == WRITE)
		ret = lo_send(lo, bio, lo->lo_blocksize, pos);
	else
		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
	return ret;
}

/*
 * Add bio to back of pending list
 */
static void loop_add_bio(struct loop_device *lo, struct bio *bio)
{
	if (lo->lo_biotail) {
		lo->lo_biotail->bi_next = bio;
		lo->lo_biotail = bio;
	} else
		lo->lo_bio = lo->lo_biotail = bio;
}

/*
 * Grab first pending buffer
 */
static struct bio *loop_get_bio(struct loop_device *lo)
{
	struct bio *bio;

	if ((bio = lo->lo_bio)) {
		if (bio == lo->lo_biotail)
			lo->lo_biotail = NULL;
		lo->lo_bio = bio->bi_next;
		bio->bi_next = NULL;
	}

	return bio;
}

516
static int loop_make_request(struct request_queue *q, struct bio *old_bio)
L
Linus Torvalds 已提交
517 518 519 520
{
	struct loop_device *lo = q->queuedata;
	int rw = bio_rw(old_bio);

N
Nick Piggin 已提交
521 522 523 524
	if (rw == READA)
		rw = READ;

	BUG_ON(!lo || (rw != READ && rw != WRITE));
L
Linus Torvalds 已提交
525 526 527

	spin_lock_irq(&lo->lo_lock);
	if (lo->lo_state != Lo_bound)
N
Nick Piggin 已提交
528 529 530
		goto out;
	if (unlikely(rw == WRITE && (lo->lo_flags & LO_FLAGS_READ_ONLY)))
		goto out;
L
Linus Torvalds 已提交
531
	loop_add_bio(lo, old_bio);
532
	wake_up(&lo->lo_event);
N
Nick Piggin 已提交
533
	spin_unlock_irq(&lo->lo_lock);
L
Linus Torvalds 已提交
534
	return 0;
N
Nick Piggin 已提交
535

L
Linus Torvalds 已提交
536
out:
N
Nick Piggin 已提交
537
	spin_unlock_irq(&lo->lo_lock);
538
	bio_io_error(old_bio);
L
Linus Torvalds 已提交
539 540 541 542 543 544
	return 0;
}

/*
 * kick off io on the underlying address space
 */
545
static void loop_unplug(struct request_queue *q)
L
Linus Torvalds 已提交
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
{
	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 {
N
Nick Piggin 已提交
566
		int ret = do_bio_filebacked(lo, bio);
567
		bio_endio(bio, ret);
L
Linus Torvalds 已提交
568 569 570 571 572 573 574 575
	}
}

/*
 * 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.
576 577 578 579 580 581
 *
 * 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
582 583 584 585 586 587 588 589
 */
static int loop_thread(void *data)
{
	struct loop_device *lo = data;
	struct bio *bio;

	set_user_nice(current, -20);

590
	while (!kthread_should_stop() || lo->lo_bio) {
591

592 593
		wait_event_interruptible(lo->lo_event,
				lo->lo_bio || kthread_should_stop());
N
Nick Piggin 已提交
594

595
		if (!lo->lo_bio)
N
Nick Piggin 已提交
596 597
			continue;
		spin_lock_irq(&lo->lo_lock);
L
Linus Torvalds 已提交
598
		bio = loop_get_bio(lo);
N
Nick Piggin 已提交
599 600 601
		spin_unlock_irq(&lo->lo_lock);

		BUG_ON(!bio);
L
Linus Torvalds 已提交
602 603 604 605 606 607 608 609 610 611 612 613 614 615
		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;
616
	struct bio *bio = bio_alloc(GFP_KERNEL, 0);
L
Linus Torvalds 已提交
617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
	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;
639 640
	lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
		mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
L
Linus Torvalds 已提交
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683
	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;

684 685
	/* new backing store needs to support loop (eg splice_read) */
	if (!inode->i_fop->splice_read)
L
Linus Torvalds 已提交
686 687 688 689 690 691 692 693 694 695 696 697
		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);
698 699
	if (max_part > 0)
		ioctl_by_bdev(bdev, BLKRRPART, 0);
L
Linus Torvalds 已提交
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761
	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)) {
762
		const struct address_space_operations *aops = mapping->a_ops;
L
Linus Torvalds 已提交
763 764 765 766
		/*
		 * If we can't read - sorry. If we only can't write - well,
		 * it's going to be read-only.
		 */
767
		if (!file->f_op->splice_read)
L
Linus Torvalds 已提交
768
			goto out_putf;
769
		if (aops->prepare_write || aops->write_begin)
L
Linus Torvalds 已提交
770 771 772 773
			lo_flags |= LO_FLAGS_USE_AOPS;
		if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
			lo_flags |= LO_FLAGS_READ_ONLY;

774 775 776
		lo_blocksize = S_ISBLK(inode->i_mode) ?
			inode->i_bdev->bd_block_size : PAGE_SIZE;

L
Linus Torvalds 已提交
777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797
		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;
798
	lo->transfer = transfer_none;
L
Linus Torvalds 已提交
799 800 801 802 803 804 805 806 807 808 809 810 811 812 813
	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;

814
	set_capacity(lo->lo_disk, size);
L
Linus Torvalds 已提交
815 816 817 818
	bd_set_size(bdev, size << 9);

	set_blocksize(bdev, lo_blocksize);

819 820 821 822
	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);
823
		goto out_clr;
824 825 826
	}
	lo->lo_state = Lo_bound;
	wake_up_process(lo->lo_thread);
827 828
	if (max_part > 0)
		ioctl_by_bdev(bdev, BLKRRPART, 0);
L
Linus Torvalds 已提交
829 830
	return 0;

831 832 833 834 835
out_clr:
	lo->lo_thread = NULL;
	lo->lo_device = NULL;
	lo->lo_backing_file = NULL;
	lo->lo_flags = 0;
836
	set_capacity(lo->lo_disk, 0);
837
	invalidate_bdev(bdev);
838 839 840
	bd_set_size(bdev, 0);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask);
	lo->lo_state = Lo_unbound;
L
Linus Torvalds 已提交
841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888
 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;
889
	gfp_t gfp = lo->old_gfp_mask;
L
Linus Torvalds 已提交
890 891 892 893 894 895 896 897 898 899 900 901 902 903

	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);

904
	kthread_stop(lo->lo_thread);
L
Linus Torvalds 已提交
905 906 907 908 909 910 911 912 913 914 915 916

	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;
917
	lo->lo_thread = NULL;
L
Linus Torvalds 已提交
918 919 920
	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);
921
	invalidate_bdev(bdev);
922
	set_capacity(lo->lo_disk, 0);
L
Linus Torvalds 已提交
923 924 925 926 927 928
	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);
929 930
	if (max_part > 0)
		ioctl_by_bdev(bdev, BLKRRPART, 0);
L
Linus Torvalds 已提交
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984
	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;

985 986 987 988
	if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;

L
Linus Torvalds 已提交
989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
	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;
1010
	error = vfs_getattr(file->f_path.mnt, file->f_path.dentry, &stat);
L
Linus Torvalds 已提交
1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 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 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
	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;
}

static int lo_ioctl(struct inode * inode, struct file * file,
	unsigned int cmd, unsigned long arg)
{
	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
	int err;

1146
	mutex_lock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171
	switch (cmd) {
	case LOOP_SET_FD:
		err = loop_set_fd(lo, file, inode->i_bdev, arg);
		break;
	case LOOP_CHANGE_FD:
		err = loop_change_fd(lo, file, inode->i_bdev, arg);
		break;
	case LOOP_CLR_FD:
		err = loop_clr_fd(lo, inode->i_bdev);
		break;
	case LOOP_SET_STATUS:
		err = loop_set_status_old(lo, (struct loop_info __user *) arg);
		break;
	case LOOP_GET_STATUS:
		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
		break;
	case LOOP_SET_STATUS64:
		err = loop_set_status64(lo, (struct loop_info64 __user *) arg);
		break;
	case LOOP_GET_STATUS64:
		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
		break;
	default:
		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
	}
1172
	mutex_unlock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1173 1174 1175
	return err;
}

1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196
#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
1197
loop_info64_from_compat(const struct compat_loop_info __user *arg,
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 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
			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;
}

static long lo_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
1297
	struct inode *inode = file->f_path.dentry->d_inode;
1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329
	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
	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;
	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:
		err = lo_ioctl(inode, file, cmd, arg);
		break;
	default:
		err = -ENOIOCTLCMD;
		break;
	}
	return err;
}
#endif

L
Linus Torvalds 已提交
1330 1331 1332 1333
static int lo_open(struct inode *inode, struct file *file)
{
	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;

1334
	mutex_lock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1335
	lo->lo_refcnt++;
1336
	mutex_unlock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1337 1338 1339 1340 1341 1342 1343 1344

	return 0;
}

static int lo_release(struct inode *inode, struct file *file)
{
	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;

1345
	mutex_lock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1346
	--lo->lo_refcnt;
1347 1348 1349 1350

	if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) && !lo->lo_refcnt)
		loop_clr_fd(lo, inode->i_bdev);

1351
	mutex_unlock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1352 1353 1354 1355 1356 1357 1358 1359 1360

	return 0;
}

static struct block_device_operations lo_fops = {
	.owner =	THIS_MODULE,
	.open =		lo_open,
	.release =	lo_release,
	.ioctl =	lo_ioctl,
1361 1362 1363
#ifdef CONFIG_COMPAT
	.compat_ioctl =	lo_compat_ioctl,
#endif
L
Linus Torvalds 已提交
1364 1365 1366 1367 1368
};

/*
 * And now the modules code and kernel interface.
 */
1369
static int max_loop;
L
Linus Torvalds 已提交
1370
module_param(max_loop, int, 0);
K
Ken Chen 已提交
1371
MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
1372 1373
module_param(max_part, int, 0);
MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
L
Linus Torvalds 已提交
1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
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;
}

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;

1398
	list_for_each_entry(lo, &loop_devices, lo_list) {
1399
		mutex_lock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1400 1401 1402 1403

		if (lo->lo_encryption == xfer)
			loop_release_xfer(lo);

1404
		mutex_unlock(&lo->lo_ctl_mutex);
L
Linus Torvalds 已提交
1405 1406 1407 1408 1409 1410 1411 1412
	}

	return 0;
}

EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);

K
Ken Chen 已提交
1413
static struct loop_device *loop_alloc(int i)
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425
{
	struct loop_device *lo;
	struct gendisk *disk;

	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
	if (!lo)
		goto out;

	lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
	if (!lo->lo_queue)
		goto out_free_dev;

1426
	disk = lo->lo_disk = alloc_disk(1 << part_shift);
1427 1428 1429 1430 1431 1432 1433 1434 1435
	if (!disk)
		goto out_free_queue;

	mutex_init(&lo->lo_ctl_mutex);
	lo->lo_number		= i;
	lo->lo_thread		= NULL;
	init_waitqueue_head(&lo->lo_event);
	spin_lock_init(&lo->lo_lock);
	disk->major		= LOOP_MAJOR;
1436
	disk->first_minor	= i << part_shift;
1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447
	disk->fops		= &lo_fops;
	disk->private_data	= lo;
	disk->queue		= lo->lo_queue;
	sprintf(disk->disk_name, "loop%d", i);
	return lo;

out_free_queue:
	blk_cleanup_queue(lo->lo_queue);
out_free_dev:
	kfree(lo);
out:
1448
	return NULL;
1449 1450
}

K
Ken Chen 已提交
1451
static void loop_free(struct loop_device *lo)
L
Linus Torvalds 已提交
1452
{
1453 1454 1455 1456 1457
	blk_cleanup_queue(lo->lo_queue);
	put_disk(lo->lo_disk);
	list_del(&lo->lo_list);
	kfree(lo);
}
L
Linus Torvalds 已提交
1458

K
Ken Chen 已提交
1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481
static struct loop_device *loop_init_one(int i)
{
	struct loop_device *lo;

	list_for_each_entry(lo, &loop_devices, lo_list) {
		if (lo->lo_number == i)
			return lo;
	}

	lo = loop_alloc(i);
	if (lo) {
		add_disk(lo->lo_disk);
		list_add_tail(&lo->lo_list, &loop_devices);
	}
	return lo;
}

static void loop_del_one(struct loop_device *lo)
{
	del_gendisk(lo->lo_disk);
	loop_free(lo);
}

1482 1483
static struct kobject *loop_probe(dev_t dev, int *part, void *data)
{
A
Al Viro 已提交
1484
	struct loop_device *lo;
1485
	struct kobject *kobj;
1486

A
Al Viro 已提交
1487 1488
	mutex_lock(&loop_devices_mutex);
	lo = loop_init_one(dev & MINORMASK);
1489
	kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM);
1490 1491 1492
	mutex_unlock(&loop_devices_mutex);

	*part = 0;
1493
	return kobj;
1494 1495 1496 1497
}

static int __init loop_init(void)
{
K
Ken Chen 已提交
1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
	int i, nr;
	unsigned long range;
	struct loop_device *lo, *next;

	/*
	 * 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.
	 */
1516 1517 1518 1519 1520 1521

	part_shift = 0;
	if (max_part > 0)
		part_shift = fls(max_part);

	if (max_loop > 1UL << (MINORBITS - part_shift))
K
Ken Chen 已提交
1522
		return -EINVAL;
L
Linus Torvalds 已提交
1523

1524
	if (max_loop) {
K
Ken Chen 已提交
1525 1526 1527 1528
		nr = max_loop;
		range = max_loop;
	} else {
		nr = 8;
1529
		range = 1UL << (MINORBITS - part_shift);
K
Ken Chen 已提交
1530 1531 1532 1533
	}

	if (register_blkdev(LOOP_MAJOR, "loop"))
		return -EIO;
L
Linus Torvalds 已提交
1534

K
Ken Chen 已提交
1535 1536 1537 1538 1539
	for (i = 0; i < nr; i++) {
		lo = loop_alloc(i);
		if (!lo)
			goto Enomem;
		list_add_tail(&lo->lo_list, &loop_devices);
L
Linus Torvalds 已提交
1540
	}
K
Ken Chen 已提交
1541 1542 1543 1544 1545 1546 1547 1548 1549

	/* 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);

1550
	printk(KERN_INFO "loop: module loaded\n");
L
Linus Torvalds 已提交
1551
	return 0;
K
Ken Chen 已提交
1552 1553 1554 1555 1556 1557 1558 1559 1560

Enomem:
	printk(KERN_INFO "loop: out of memory\n");

	list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
		loop_free(lo);

	unregister_blkdev(LOOP_MAJOR, "loop");
	return -ENOMEM;
L
Linus Torvalds 已提交
1561 1562
}

1563
static void __exit loop_exit(void)
L
Linus Torvalds 已提交
1564
{
K
Ken Chen 已提交
1565
	unsigned long range;
1566
	struct loop_device *lo, *next;
L
Linus Torvalds 已提交
1567

1568
	range = max_loop ? max_loop :  1UL << (MINORBITS - part_shift);
K
Ken Chen 已提交
1569

1570 1571 1572
	list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
		loop_del_one(lo);

K
Ken Chen 已提交
1573
	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
1574
	unregister_blkdev(LOOP_MAJOR, "loop");
L
Linus Torvalds 已提交
1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588
}

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