ioctl.c 15.7 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9
/*
 *  linux/fs/ioctl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
10
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
11 12 13 14
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/module.h>
15
#include <linux/uaccess.h>
16 17
#include <linux/writeback.h>
#include <linux/buffer_head.h>
18
#include <linux/falloc.h>
Linus Torvalds's avatar
Linus Torvalds committed
19 20 21

#include <asm/ioctls.h>

Mark Fasheh's avatar
Mark Fasheh committed
22 23 24
/* So that the fiemap access checks can't overflow on 32 bit machines. */
#define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))

25 26
/**
 * vfs_ioctl - call filesystem specific ioctl methods
27 28 29
 * @filp:	open file to invoke ioctl method on
 * @cmd:	ioctl command to execute
 * @arg:	command-specific argument for ioctl
30 31 32 33 34 35
 *
 * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
 * returns -ENOTTY.
 *
 * Returns 0 on success, -errno on error.
 */
Adrian Bunk's avatar
Adrian Bunk committed
36 37
static long vfs_ioctl(struct file *filp, unsigned int cmd,
		      unsigned long arg)
Linus Torvalds's avatar
Linus Torvalds committed
38 39 40
{
	int error = -ENOTTY;

41
	if (!filp->f_op || !filp->f_op->unlocked_ioctl)
Linus Torvalds's avatar
Linus Torvalds committed
42 43
		goto out;

44 45 46
	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	if (error == -ENOIOCTLCMD)
		error = -EINVAL;
Linus Torvalds's avatar
Linus Torvalds committed
47 48 49 50
 out:
	return error;
}

51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
static int ioctl_fibmap(struct file *filp, int __user *p)
{
	struct address_space *mapping = filp->f_mapping;
	int res, block;

	/* do we support this mess? */
	if (!mapping->a_ops->bmap)
		return -EINVAL;
	if (!capable(CAP_SYS_RAWIO))
		return -EPERM;
	res = get_user(block, p);
	if (res)
		return res;
	res = mapping->a_ops->bmap(mapping, block);
	return put_user(res, p);
}

Mark Fasheh's avatar
Mark Fasheh committed
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 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
/**
 * fiemap_fill_next_extent - Fiemap helper function
 * @fieinfo:	Fiemap context passed into ->fiemap
 * @logical:	Extent logical start offset, in bytes
 * @phys:	Extent physical start offset, in bytes
 * @len:	Extent length, in bytes
 * @flags:	FIEMAP_EXTENT flags that describe this extent
 *
 * Called from file system ->fiemap callback. Will populate extent
 * info as passed in via arguments and copy to user memory. On
 * success, extent count on fieinfo is incremented.
 *
 * Returns 0 on success, -errno on error, 1 if this was the last
 * extent that will fit in user array.
 */
#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
			    u64 phys, u64 len, u32 flags)
{
	struct fiemap_extent extent;
	struct fiemap_extent *dest = fieinfo->fi_extents_start;

	/* only count the extents */
	if (fieinfo->fi_extents_max == 0) {
		fieinfo->fi_extents_mapped++;
		return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	}

	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
		return 1;

	if (flags & SET_UNKNOWN_FLAGS)
		flags |= FIEMAP_EXTENT_UNKNOWN;
	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
		flags |= FIEMAP_EXTENT_ENCODED;
	if (flags & SET_NOT_ALIGNED_FLAGS)
		flags |= FIEMAP_EXTENT_NOT_ALIGNED;

	memset(&extent, 0, sizeof(extent));
	extent.fe_logical = logical;
	extent.fe_physical = phys;
	extent.fe_length = len;
	extent.fe_flags = flags;

	dest += fieinfo->fi_extents_mapped;
	if (copy_to_user(dest, &extent, sizeof(extent)))
		return -EFAULT;

	fieinfo->fi_extents_mapped++;
	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
		return 1;
	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
}
EXPORT_SYMBOL(fiemap_fill_next_extent);

/**
 * fiemap_check_flags - check validity of requested flags for fiemap
 * @fieinfo:	Fiemap context passed into ->fiemap
 * @fs_flags:	Set of fiemap flags that the file system understands
 *
 * Called from file system ->fiemap callback. This will compute the
 * intersection of valid fiemap flags and those that the fs supports. That
 * value is then compared against the user supplied flags. In case of bad user
 * flags, the invalid values will be written into the fieinfo structure, and
 * -EBADR is returned, which tells ioctl_fiemap() to return those values to
 * userspace. For this reason, a return code of -EBADR should be preserved.
 *
 * Returns 0 on success, -EBADR on bad flags.
 */
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
{
	u32 incompat_flags;

	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
	if (incompat_flags) {
		fieinfo->fi_flags = incompat_flags;
		return -EBADR;
	}
	return 0;
}
EXPORT_SYMBOL(fiemap_check_flags);

static int fiemap_check_ranges(struct super_block *sb,
			       u64 start, u64 len, u64 *new_len)
{
155 156
	u64 maxbytes = (u64) sb->s_maxbytes;

Mark Fasheh's avatar
Mark Fasheh committed
157 158 159 160 161
	*new_len = len;

	if (len == 0)
		return -EINVAL;

162
	if (start > maxbytes)
Mark Fasheh's avatar
Mark Fasheh committed
163 164 165 166 167
		return -EFBIG;

	/*
	 * Shrink request scope to what the fs can actually handle.
	 */
168 169
	if (len > maxbytes || (maxbytes - len) < start)
		*new_len = maxbytes - start;
Mark Fasheh's avatar
Mark Fasheh committed
170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218

	return 0;
}

static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
	struct fiemap fiemap;
	struct fiemap_extent_info fieinfo = { 0, };
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct super_block *sb = inode->i_sb;
	u64 len;
	int error;

	if (!inode->i_op->fiemap)
		return -EOPNOTSUPP;

	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
			   sizeof(struct fiemap)))
		return -EFAULT;

	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
		return -EINVAL;

	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
				    &len);
	if (error)
		return error;

	fieinfo.fi_flags = fiemap.fm_flags;
	fieinfo.fi_extents_max = fiemap.fm_extent_count;
	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));

	if (fiemap.fm_extent_count != 0 &&
	    !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
		       fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
		return -EFAULT;

	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
		filemap_write_and_wait(inode->i_mapping);

	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
	fiemap.fm_flags = fieinfo.fi_flags;
	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
		error = -EFAULT;

	return error;
}

219 220
#ifdef CONFIG_BLOCK

221 222 223 224 225 226 227 228 229
static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
	return (offset >> inode->i_blkbits);
}

static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
{
	return (blk << inode->i_blkbits);
}
230

231 232
/**
 * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
233 234 235 236 237
 * @inode: the inode to map
 * @fieinfo: the fiemap info struct that will be passed back to userspace
 * @start: where to start mapping in the inode
 * @len: how much space to map
 * @get_block: the fs's get_block function
238 239 240 241 242 243 244
 *
 * This does FIEMAP for block based inodes.  Basically it will just loop
 * through get_block until we hit the number of extents we want to map, or we
 * go past the end of the file and hit a hole.
 *
 * If it is possible to have data blocks beyond a hole past @inode->i_size, then
 * please do not use this function, it will stop at the first unmapped block
245 246 247 248
 * beyond i_size.
 *
 * If you use this function directly, you need to do your own locking. Use
 * generic_block_fiemap if you want the locking done for you.
249
 */
250 251

int __generic_block_fiemap(struct inode *inode,
252 253
			   struct fiemap_extent_info *fieinfo, loff_t start,
			   loff_t len, get_block_t *get_block)
254
{
255 256 257
	struct buffer_head map_bh;
	sector_t start_blk, last_blk;
	loff_t isize = i_size_read(inode);
258 259
	u64 logical = 0, phys = 0, size = 0;
	u32 flags = FIEMAP_EXTENT_MERGED;
260 261
	bool past_eof = false, whole_file = false;
	int ret = 0;
262

263 264
	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
	if (ret)
265 266
		return ret;

267 268 269 270 271 272 273 274 275
	/*
	 * Either the i_mutex or other appropriate locking needs to be held
	 * since we expect isize to not change at all through the duration of
	 * this call.
	 */
	if (len >= isize) {
		whole_file = true;
		len = isize;
	}
276

277 278
	start_blk = logical_to_blk(inode, start);
	last_blk = logical_to_blk(inode, start + len - 1);
279 280 281 282 283 284

	do {
		/*
		 * we set b_size to the total size we want so it will map as
		 * many contiguous blocks as possible at once
		 */
285 286
		memset(&map_bh, 0, sizeof(struct buffer_head));
		map_bh.b_size = len;
287

288
		ret = get_block(inode, start_blk, &map_bh, 0);
289 290 291 292
		if (ret)
			break;

		/* HOLE */
293
		if (!buffer_mapped(&map_bh)) {
294 295 296
			start_blk++;

			/*
297
			 * We want to handle the case where there is an
298 299 300 301 302 303
			 * allocated block at the front of the file, and then
			 * nothing but holes up to the end of the file properly,
			 * to make sure that extent at the front gets properly
			 * marked with FIEMAP_EXTENT_LAST
			 */
			if (!past_eof &&
304
			    blk_to_logical(inode, start_blk) >= isize)
305 306
				past_eof = 1;

307
			/*
308
			 * First hole after going past the EOF, this is our
309 310
			 * last extent
			 */
311
			if (past_eof && size) {
312 313 314 315
				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
316 317 318 319
			} else if (size) {
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size, flags);
				size = 0;
320 321 322
			}

			/* if we have holes up to/past EOF then we're done */
323
			if (start_blk > last_blk || past_eof || ret)
324 325
				break;
		} else {
326
			/*
327
			 * We have gone over the length of what we wanted to
328 329 330 331 332 333 334 335 336 337 338 339 340
			 * map, and it wasn't the entire file, so add the extent
			 * we got last time and exit.
			 *
			 * This is for the case where say we want to map all the
			 * way up to the second to the last block in a file, but
			 * the last block is a hole, making the second to last
			 * block FIEMAP_EXTENT_LAST.  In this case we want to
			 * see if there is a hole after the second to last block
			 * so we can mark it properly.  If we found data after
			 * we exceeded the length we were requesting, then we
			 * are good to go, just add the extent to the fieinfo
			 * and break
			 */
341
			if (start_blk > last_blk && !whole_file) {
342 343 344 345 346 347 348 349 350 351 352
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				break;
			}

			/*
			 * if size != 0 then we know we already have an extent
			 * to add, so add it.
			 */
			if (size) {
353 354 355 356 357 358 359 360
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				if (ret)
					break;
			}

			logical = blk_to_logical(inode, start_blk);
361 362
			phys = blk_to_logical(inode, map_bh.b_blocknr);
			size = map_bh.b_size;
363 364 365 366 367
			flags = FIEMAP_EXTENT_MERGED;

			start_blk += logical_to_blk(inode, size);

			/*
368 369 370
			 * If we are past the EOF, then we need to make sure as
			 * soon as we find a hole that the last extent we found
			 * is marked with FIEMAP_EXTENT_LAST
371
			 */
372 373
			if (!past_eof && logical + size >= isize)
				past_eof = true;
374 375 376 377
		}
		cond_resched();
	} while (1);

378
	/* If ret is 1 then we just hit the end of the extent array */
379 380 381 382 383
	if (ret == 1)
		ret = 0;

	return ret;
}
384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
EXPORT_SYMBOL(__generic_block_fiemap);

/**
 * generic_block_fiemap - FIEMAP for block based inodes
 * @inode: The inode to map
 * @fieinfo: The mapping information
 * @start: The initial block to map
 * @len: The length of the extect to attempt to map
 * @get_block: The block mapping function for the fs
 *
 * Calls __generic_block_fiemap to map the inode, after taking
 * the inode's mutex lock.
 */

int generic_block_fiemap(struct inode *inode,
			 struct fiemap_extent_info *fieinfo, u64 start,
			 u64 len, get_block_t *get_block)
{
	int ret;
	mutex_lock(&inode->i_mutex);
	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
	mutex_unlock(&inode->i_mutex);
	return ret;
}
408 409
EXPORT_SYMBOL(generic_block_fiemap);

410 411
#endif  /*  CONFIG_BLOCK  */

412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
/*
 * This provides compatibility with legacy XFS pre-allocation ioctls
 * which predate the fallocate syscall.
 *
 * Only the l_start, l_len and l_whence fields of the 'struct space_resv'
 * are used here, rest are ignored.
 */
int ioctl_preallocate(struct file *filp, void __user *argp)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct space_resv sr;

	if (copy_from_user(&sr, argp, sizeof(sr)))
		return -EFAULT;

	switch (sr.l_whence) {
	case SEEK_SET:
		break;
	case SEEK_CUR:
		sr.l_start += filp->f_pos;
		break;
	case SEEK_END:
		sr.l_start += i_size_read(inode);
		break;
	default:
		return -EINVAL;
	}

	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
}

Linus Torvalds's avatar
Linus Torvalds committed
443 444 445
static int file_ioctl(struct file *filp, unsigned int cmd,
		unsigned long arg)
{
446
	struct inode *inode = filp->f_path.dentry->d_inode;
Linus Torvalds's avatar
Linus Torvalds committed
447 448 449
	int __user *p = (int __user *)arg;

	switch (cmd) {
450
	case FIBMAP:
451
		return ioctl_fibmap(filp, p);
452 453
	case FIONREAD:
		return put_user(i_size_read(inode) - filp->f_pos, p);
454 455 456
	case FS_IOC_RESVSP:
	case FS_IOC_RESVSP64:
		return ioctl_preallocate(filp, p);
Linus Torvalds's avatar
Linus Torvalds committed
457 458
	}

459
	return vfs_ioctl(filp, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
460 461
}

462 463 464 465 466 467 468 469 470 471 472 473 474 475
static int ioctl_fionbio(struct file *filp, int __user *argp)
{
	unsigned int flag;
	int on, error;

	error = get_user(on, argp);
	if (error)
		return error;
	flag = O_NONBLOCK;
#ifdef __sparc__
	/* SunOS compatibility item. */
	if (O_NONBLOCK != O_NDELAY)
		flag |= O_NDELAY;
#endif
476
	spin_lock(&filp->f_lock);
477 478 479 480
	if (on)
		filp->f_flags |= flag;
	else
		filp->f_flags &= ~flag;
481
	spin_unlock(&filp->f_lock);
482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497
	return error;
}

static int ioctl_fioasync(unsigned int fd, struct file *filp,
			  int __user *argp)
{
	unsigned int flag;
	int on, error;

	error = get_user(on, argp);
	if (error)
		return error;
	flag = on ? FASYNC : 0;

	/* Did FASYNC state change ? */
	if ((flag ^ filp->f_flags) & FASYNC) {
498
		if (filp->f_op && filp->f_op->fasync)
499
			/* fasync() adjusts filp->f_flags */
500
			error = filp->f_op->fasync(fd, filp, on);
501
		else
502 503
			error = -ENOTTY;
	}
504
	return error < 0 ? error : 0;
505 506
}

507 508 509 510 511 512 513 514 515 516 517 518
static int ioctl_fsfreeze(struct file *filp)
{
	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	/* If filesystem doesn't support freeze feature, return. */
	if (sb->s_op->freeze_fs == NULL)
		return -EOPNOTSUPP;

	/* Freeze */
519
	return freeze_super(sb);
520 521 522 523 524 525 526 527 528 529
}

static int ioctl_fsthaw(struct file *filp)
{
	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	/* Thaw */
530
	return thaw_super(sb);
531 532
}

Linus Torvalds's avatar
Linus Torvalds committed
533 534 535 536
/*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
 *
537
 * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
Linus Torvalds's avatar
Linus Torvalds committed
538 539
 * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
 */
540 541
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
	     unsigned long arg)
Linus Torvalds's avatar
Linus Torvalds committed
542
{
543 544
	int error = 0;
	int __user *argp = (int __user *)arg;
Linus Torvalds's avatar
Linus Torvalds committed
545 546

	switch (cmd) {
547 548 549
	case FIOCLEX:
		set_close_on_exec(fd, 1);
		break;
Linus Torvalds's avatar
Linus Torvalds committed
550

551 552 553
	case FIONCLEX:
		set_close_on_exec(fd, 0);
		break;
Linus Torvalds's avatar
Linus Torvalds committed
554

555
	case FIONBIO:
556
		error = ioctl_fionbio(filp, argp);
557 558 559
		break;

	case FIOASYNC:
560
		error = ioctl_fioasync(fd, filp, argp);
561 562 563 564 565 566 567 568 569 570 571 572 573
		break;

	case FIOQSIZE:
		if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) ||
		    S_ISREG(filp->f_path.dentry->d_inode->i_mode) ||
		    S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
			loff_t res =
				inode_get_bytes(filp->f_path.dentry->d_inode);
			error = copy_to_user((loff_t __user *)arg, &res,
					     sizeof(res)) ? -EFAULT : 0;
		} else
			error = -ENOTTY;
		break;
574 575 576 577 578 579 580 581 582

	case FIFREEZE:
		error = ioctl_fsfreeze(filp);
		break;

	case FITHAW:
		error = ioctl_fsthaw(filp);
		break;

583 584 585 586 587 588 589 590 591 592
	case FS_IOC_FIEMAP:
		return ioctl_fiemap(filp, arg);

	case FIGETBSZ:
	{
		struct inode *inode = filp->f_path.dentry->d_inode;
		int __user *p = (int __user *)arg;
		return put_user(inode->i_sb->s_blocksize, p);
	}

593 594 595 596
	default:
		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
			error = file_ioctl(filp, cmd, arg);
		else
597
			error = vfs_ioctl(filp, cmd, arg);
598
		break;
Linus Torvalds's avatar
Linus Torvalds committed
599 600 601 602
	}
	return error;
}

603
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
Linus Torvalds's avatar
Linus Torvalds committed
604
{
605
	struct file *filp;
Linus Torvalds's avatar
Linus Torvalds committed
606 607 608 609 610 611 612 613 614 615 616
	int error = -EBADF;
	int fput_needed;

	filp = fget_light(fd, &fput_needed);
	if (!filp)
		goto out;

	error = security_file_ioctl(filp, cmd, arg);
	if (error)
		goto out_fput;

617
	error = do_vfs_ioctl(filp, fd, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
618 619 620 621 622
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}