ioctl.c 15.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8
/*
 *  linux/fs/ioctl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/mm.h>
9
#include <linux/capability.h>
L
Linus Torvalds 已提交
10 11 12 13
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/module.h>
14
#include <linux/uaccess.h>
15 16
#include <linux/writeback.h>
#include <linux/buffer_head.h>
17
#include <linux/falloc.h>
L
Linus Torvalds 已提交
18 19 20

#include <asm/ioctls.h>

M
Mark Fasheh 已提交
21 22 23
/* So that the fiemap access checks can't overflow on 32 bit machines. */
#define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))

24 25
/**
 * vfs_ioctl - call filesystem specific ioctl methods
26 27 28
 * @filp:	open file to invoke ioctl method on
 * @cmd:	ioctl command to execute
 * @arg:	command-specific argument for ioctl
29 30 31 32 33 34
 *
 * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
 * returns -ENOTTY.
 *
 * Returns 0 on success, -errno on error.
 */
A
Adrian Bunk 已提交
35 36
static long vfs_ioctl(struct file *filp, unsigned int cmd,
		      unsigned long arg)
L
Linus Torvalds 已提交
37 38 39
{
	int error = -ENOTTY;

40
	if (!filp->f_op || !filp->f_op->unlocked_ioctl)
L
Linus Torvalds 已提交
41 42
		goto out;

43 44 45
	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	if (error == -ENOIOCTLCMD)
		error = -EINVAL;
L
Linus Torvalds 已提交
46 47 48 49
 out:
	return error;
}

50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
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);
}

M
Mark Fasheh 已提交
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
/**
 * 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;
89
	struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
M
Mark Fasheh 已提交
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

	/* 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)
{
154 155
	u64 maxbytes = (u64) sb->s_maxbytes;

M
Mark Fasheh 已提交
156 157 158 159 160
	*new_len = len;

	if (len == 0)
		return -EINVAL;

161
	if (start > maxbytes)
M
Mark Fasheh 已提交
162 163 164 165 166
		return -EFBIG;

	/*
	 * Shrink request scope to what the fs can actually handle.
	 */
167 168
	if (len > maxbytes || (maxbytes - len) < start)
		*new_len = maxbytes - start;
M
Mark Fasheh 已提交
169 170 171 172 173 174 175

	return 0;
}

static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
	struct fiemap fiemap;
176
	struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
M
Mark Fasheh 已提交
177 178 179 180 181 182 183 184 185
	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;

186
	if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
M
Mark Fasheh 已提交
187 188 189 190 191 192 193 194 195 196 197 198
		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;
199
	fieinfo.fi_extents_start = ufiemap->fm_extents;
M
Mark Fasheh 已提交
200 201 202 203 204 205 206 207 208 209 210 211

	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;
212
	if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
M
Mark Fasheh 已提交
213 214 215 216 217
		error = -EFAULT;

	return error;
}

218 219
#ifdef CONFIG_BLOCK

J
Josef Bacik 已提交
220 221 222 223 224 225 226 227 228
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);
}
229

230 231
/**
 * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
J
Josef Bacik 已提交
232 233 234 235 236
 * @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
237 238 239 240 241 242 243
 *
 * 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
244 245 246 247
 * 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.
248
 */
249 250

int __generic_block_fiemap(struct inode *inode,
J
Josef Bacik 已提交
251 252
			   struct fiemap_extent_info *fieinfo, loff_t start,
			   loff_t len, get_block_t *get_block)
253
{
J
Josef Bacik 已提交
254 255 256
	struct buffer_head map_bh;
	sector_t start_blk, last_blk;
	loff_t isize = i_size_read(inode);
257 258
	u64 logical = 0, phys = 0, size = 0;
	u32 flags = FIEMAP_EXTENT_MERGED;
J
Josef Bacik 已提交
259 260
	bool past_eof = false, whole_file = false;
	int ret = 0;
261

J
Josef Bacik 已提交
262 263
	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
	if (ret)
264 265
		return ret;

J
Josef Bacik 已提交
266 267 268 269 270 271 272 273 274
	/*
	 * 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;
	}
275

276 277 278 279 280 281 282
	/*
	 * Some filesystems can't deal with being asked to map less than
	 * blocksize, so make sure our len is at least block length.
	 */
	if (logical_to_blk(inode, len) == 0)
		len = blk_to_logical(inode, 1);

J
Josef Bacik 已提交
283 284
	start_blk = logical_to_blk(inode, start);
	last_blk = logical_to_blk(inode, start + len - 1);
285 286 287 288 289 290

	do {
		/*
		 * we set b_size to the total size we want so it will map as
		 * many contiguous blocks as possible at once
		 */
J
Josef Bacik 已提交
291 292
		memset(&map_bh, 0, sizeof(struct buffer_head));
		map_bh.b_size = len;
293

J
Josef Bacik 已提交
294
		ret = get_block(inode, start_blk, &map_bh, 0);
295 296 297 298
		if (ret)
			break;

		/* HOLE */
J
Josef Bacik 已提交
299
		if (!buffer_mapped(&map_bh)) {
300 301 302
			start_blk++;

			/*
J
Josef Bacik 已提交
303
			 * We want to handle the case where there is an
304 305 306 307 308 309
			 * 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 &&
J
Josef Bacik 已提交
310
			    blk_to_logical(inode, start_blk) >= isize)
311 312
				past_eof = 1;

313
			/*
J
Josef Bacik 已提交
314
			 * First hole after going past the EOF, this is our
315 316
			 * last extent
			 */
317
			if (past_eof && size) {
318 319 320 321
				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
J
Josef Bacik 已提交
322 323 324 325
			} else if (size) {
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size, flags);
				size = 0;
326 327 328
			}

			/* if we have holes up to/past EOF then we're done */
J
Josef Bacik 已提交
329
			if (start_blk > last_blk || past_eof || ret)
330 331
				break;
		} else {
332
			/*
J
Josef Bacik 已提交
333
			 * We have gone over the length of what we wanted to
334 335 336 337 338 339 340 341 342 343 344 345 346
			 * 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
			 */
J
Josef Bacik 已提交
347
			if (start_blk > last_blk && !whole_file) {
348 349 350 351 352 353 354 355 356 357 358
				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) {
359 360 361 362 363 364 365 366
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				if (ret)
					break;
			}

			logical = blk_to_logical(inode, start_blk);
J
Josef Bacik 已提交
367 368
			phys = blk_to_logical(inode, map_bh.b_blocknr);
			size = map_bh.b_size;
369 370 371 372 373
			flags = FIEMAP_EXTENT_MERGED;

			start_blk += logical_to_blk(inode, size);

			/*
374 375 376
			 * 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
377
			 */
J
Josef Bacik 已提交
378 379
			if (!past_eof && logical + size >= isize)
				past_eof = true;
380 381 382 383
		}
		cond_resched();
	} while (1);

J
Josef Bacik 已提交
384
	/* If ret is 1 then we just hit the end of the extent array */
385 386 387 388 389
	if (ret == 1)
		ret = 0;

	return ret;
}
390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
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;
}
414 415
EXPORT_SYMBOL(generic_block_fiemap);

416 417
#endif  /*  CONFIG_BLOCK  */

418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448
/*
 * 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);
}

L
Linus Torvalds 已提交
449 450 451
static int file_ioctl(struct file *filp, unsigned int cmd,
		unsigned long arg)
{
452
	struct inode *inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
453 454 455
	int __user *p = (int __user *)arg;

	switch (cmd) {
456
	case FIBMAP:
457
		return ioctl_fibmap(filp, p);
458 459
	case FIONREAD:
		return put_user(i_size_read(inode) - filp->f_pos, p);
460 461 462
	case FS_IOC_RESVSP:
	case FS_IOC_RESVSP64:
		return ioctl_preallocate(filp, p);
L
Linus Torvalds 已提交
463 464
	}

465
	return vfs_ioctl(filp, cmd, arg);
L
Linus Torvalds 已提交
466 467
}

468 469 470 471 472 473 474 475 476 477 478 479 480 481
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
J
Jonathan Corbet 已提交
482
	spin_lock(&filp->f_lock);
483 484 485 486
	if (on)
		filp->f_flags |= flag;
	else
		filp->f_flags &= ~flag;
J
Jonathan Corbet 已提交
487
	spin_unlock(&filp->f_lock);
488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503
	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) {
504
		if (filp->f_op && filp->f_op->fasync)
505
			/* fasync() adjusts filp->f_flags */
506
			error = filp->f_op->fasync(fd, filp, on);
507
		else
508 509
			error = -ENOTTY;
	}
510
	return error < 0 ? error : 0;
511 512
}

513 514 515 516 517 518 519 520 521 522 523 524
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 */
525
	return freeze_super(sb);
526 527 528 529 530 531 532 533 534 535
}

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 */
536
	return thaw_super(sb);
537 538
}

L
Linus Torvalds 已提交
539 540 541 542
/*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
 *
543
 * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
L
Linus Torvalds 已提交
544 545
 * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
 */
546 547
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
	     unsigned long arg)
L
Linus Torvalds 已提交
548
{
549 550
	int error = 0;
	int __user *argp = (int __user *)arg;
L
Linus Torvalds 已提交
551 552

	switch (cmd) {
553 554 555
	case FIOCLEX:
		set_close_on_exec(fd, 1);
		break;
L
Linus Torvalds 已提交
556

557 558 559
	case FIONCLEX:
		set_close_on_exec(fd, 0);
		break;
L
Linus Torvalds 已提交
560

561
	case FIONBIO:
562
		error = ioctl_fionbio(filp, argp);
563 564 565
		break;

	case FIOASYNC:
566
		error = ioctl_fioasync(fd, filp, argp);
567 568 569 570 571 572 573 574 575 576 577 578 579
		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;
580 581 582 583 584 585 586 587 588

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

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

589 590 591 592 593 594 595 596 597 598
	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);
	}

599 600 601 602
	default:
		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
			error = file_ioctl(filp, cmd, arg);
		else
603
			error = vfs_ioctl(filp, cmd, arg);
604
		break;
L
Linus Torvalds 已提交
605 606 607 608
	}
	return error;
}

609
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
L
Linus Torvalds 已提交
610
{
611
	struct file *filp;
L
Linus Torvalds 已提交
612 613 614 615 616 617 618 619 620 621 622
	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;

623
	error = do_vfs_ioctl(filp, fd, cmd, arg);
L
Linus Torvalds 已提交
624 625 626 627 628
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}