ioctl.c 15.9 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
 *
 * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
32
 * invokes filesystem specific ->ioctl method.  If neither method exists,
33 34 35 36
 * returns -ENOTTY.
 *
 * Returns 0 on success, -errno on error.
 */
Adrian Bunk's avatar
Adrian Bunk committed
37 38
static long vfs_ioctl(struct file *filp, unsigned int cmd,
		      unsigned long arg)
Linus Torvalds's avatar
Linus Torvalds committed
39 40 41 42 43 44 45 46 47 48 49
{
	int error = -ENOTTY;

	if (!filp->f_op)
		goto out;

	if (filp->f_op->unlocked_ioctl) {
		error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
		if (error == -ENOIOCTLCMD)
			error = -EINVAL;
		goto out;
50
	} else if (filp->f_op->ioctl) {
Linus Torvalds's avatar
Linus Torvalds committed
51
		lock_kernel();
52 53
		error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
					  filp, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
54 55 56 57 58 59 60
		unlock_kernel();
	}

 out:
	return error;
}

61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
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
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164
/**
 * 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)
{
165 166
	u64 maxbytes = (u64) sb->s_maxbytes;

Mark Fasheh's avatar
Mark Fasheh committed
167 168 169 170 171
	*new_len = len;

	if (len == 0)
		return -EINVAL;

172
	if (start > maxbytes)
Mark Fasheh's avatar
Mark Fasheh committed
173 174 175 176 177
		return -EFBIG;

	/*
	 * Shrink request scope to what the fs can actually handle.
	 */
178 179
	if (len > maxbytes || (maxbytes - len) < start)
		*new_len = maxbytes - start;
Mark Fasheh's avatar
Mark Fasheh committed
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228

	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;
}

229 230
#ifdef CONFIG_BLOCK

231 232 233
#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);

234 235
/**
 * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
236 237 238 239 240 241 242 243 244 245
 * @inode - the inode to map
 * @arg - the pointer to userspace where we copy everything to
 * @get_block - the fs's get_block function
 *
 * 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
246 247 248 249
 * 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.
250
 */
251 252 253 254

int __generic_block_fiemap(struct inode *inode,
			   struct fiemap_extent_info *fieinfo, u64 start,
			   u64 len, get_block_t *get_block)
255 256 257 258 259 260
{
	struct buffer_head tmp;
	unsigned int start_blk;
	long long length = 0, map_len = 0;
	u64 logical = 0, phys = 0, size = 0;
	u32 flags = FIEMAP_EXTENT_MERGED;
261
	int ret = 0, past_eof = 0, whole_file = 0;
262 263 264 265 266 267 268

	if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
		return ret;

	start_blk = logical_to_blk(inode, start);

	length = (long long)min_t(u64, len, i_size_read(inode));
269 270 271
	if (length < len)
		whole_file = 1;

272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
	map_len = length;

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

		ret = get_block(inode, start_blk, &tmp, 0);
		if (ret)
			break;

		/* HOLE */
		if (!buffer_mapped(&tmp)) {
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302
			length -= blk_to_logical(inode, 1);
			start_blk++;

			/*
			 * we want to handle the case where there is an
			 * 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 &&
			    blk_to_logical(inode, start_blk) >=
			    blk_to_logical(inode, 0)+i_size_read(inode))
				past_eof = 1;

303 304 305 306
			/*
			 * first hole after going past the EOF, this is our
			 * last extent
			 */
307
			if (past_eof && size) {
308 309 310 311 312 313 314 315
				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				break;
			}

			/* if we have holes up to/past EOF then we're done */
316
			if (length <= 0 || past_eof)
317 318
				break;
		} else {
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
			/*
			 * we have gone over the length of what we wanted to
			 * 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
			 */
			if (length <= 0 && !whole_file) {
				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) {
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				if (ret)
					break;
			}

			logical = blk_to_logical(inode, start_blk);
			phys = blk_to_logical(inode, tmp.b_blocknr);
			size = tmp.b_size;
			flags = FIEMAP_EXTENT_MERGED;

			length -= tmp.b_size;
			start_blk += logical_to_blk(inode, size);

			/*
362 363 364
			 * 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
365
			 */
366 367 368 369
			if (!past_eof &&
			    logical+size >=
			    blk_to_logical(inode, 0)+i_size_read(inode))
				past_eof = 1;
370 371 372 373 374 375 376 377 378 379
		}
		cond_resched();
	} while (1);

	/* if ret is 1 then we just hit the end of the extent array */
	if (ret == 1)
		ret = 0;

	return ret;
}
380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403
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;
}
404 405
EXPORT_SYMBOL(generic_block_fiemap);

406 407
#endif  /*  CONFIG_BLOCK  */

408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438
/*
 * 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
439 440 441
static int file_ioctl(struct file *filp, unsigned int cmd,
		unsigned long arg)
{
442
	struct inode *inode = filp->f_path.dentry->d_inode;
Linus Torvalds's avatar
Linus Torvalds committed
443 444 445
	int __user *p = (int __user *)arg;

	switch (cmd) {
446
	case FIBMAP:
447
		return ioctl_fibmap(filp, p);
448 449
	case FIONREAD:
		return put_user(i_size_read(inode) - filp->f_pos, p);
450 451 452
	case FS_IOC_RESVSP:
	case FS_IOC_RESVSP64:
		return ioctl_preallocate(filp, p);
Linus Torvalds's avatar
Linus Torvalds committed
453 454
	}

455
	return vfs_ioctl(filp, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
456 457
}

458 459 460 461 462 463 464 465 466 467 468 469 470 471
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
472
	spin_lock(&filp->f_lock);
473 474 475 476
	if (on)
		filp->f_flags |= flag;
	else
		filp->f_flags &= ~flag;
477
	spin_unlock(&filp->f_lock);
478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493
	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) {
494
		if (filp->f_op && filp->f_op->fasync)
495
			/* fasync() adjusts filp->f_flags */
496
			error = filp->f_op->fasync(fd, filp, on);
497
		else
498 499
			error = -ENOTTY;
	}
500
	return error < 0 ? error : 0;
501 502
}

503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539
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;

	/* If a blockdevice-backed filesystem isn't specified, return. */
	if (sb->s_bdev == NULL)
		return -EINVAL;

	/* Freeze */
	sb = freeze_bdev(sb->s_bdev);
	if (IS_ERR(sb))
		return PTR_ERR(sb);
	return 0;
}

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;

	/* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
	if (sb->s_bdev == NULL)
		return -EINVAL;

	/* Thaw */
	return thaw_bdev(sb->s_bdev, sb);
}

Linus Torvalds's avatar
Linus Torvalds committed
540 541 542 543
/*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
 *
544
 * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
Linus Torvalds's avatar
Linus Torvalds committed
545 546
 * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
 */
547 548
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
	     unsigned long arg)
Linus Torvalds's avatar
Linus Torvalds committed
549
{
550 551
	int error = 0;
	int __user *argp = (int __user *)arg;
Linus Torvalds's avatar
Linus Torvalds committed
552 553

	switch (cmd) {
554 555 556
	case FIOCLEX:
		set_close_on_exec(fd, 1);
		break;
Linus Torvalds's avatar
Linus Torvalds committed
557

558 559 560
	case FIONCLEX:
		set_close_on_exec(fd, 0);
		break;
Linus Torvalds's avatar
Linus Torvalds committed
561

562
	case FIONBIO:
563
		error = ioctl_fionbio(filp, argp);
564 565 566
		break;

	case FIOASYNC:
567
		error = ioctl_fioasync(fd, filp, argp);
568 569 570 571 572 573 574 575 576 577 578 579 580
		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;
581 582 583 584 585 586 587 588 589

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

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

590 591 592 593 594 595 596 597 598 599
	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);
	}

600 601 602 603
	default:
		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
			error = file_ioctl(filp, cmd, arg);
		else
604
			error = vfs_ioctl(filp, cmd, arg);
605
		break;
Linus Torvalds's avatar
Linus Torvalds committed
606 607 608 609
	}
	return error;
}

610
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
Linus Torvalds's avatar
Linus Torvalds committed
611
{
612
	struct file *filp;
Linus Torvalds's avatar
Linus Torvalds committed
613 614 615 616 617 618 619 620 621 622 623
	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;

624
	error = do_vfs_ioctl(filp, fd, cmd, arg);
Linus Torvalds's avatar
Linus Torvalds committed
625 626 627 628 629
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}