ioctl.c 13.8 KB
Newer Older
L
Linus Torvalds 已提交
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>
L
Linus Torvalds 已提交
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>
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
 *
 * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
31
 * invokes filesystem specific ->ioctl method.  If neither method exists,
32 33 34 35
 * returns -ENOTTY.
 *
 * Returns 0 on success, -errno on error.
 */
A
Adrian Bunk 已提交
36 37
static long vfs_ioctl(struct file *filp, unsigned int cmd,
		      unsigned long arg)
L
Linus Torvalds 已提交
38 39 40 41 42 43 44 45 46 47 48
{
	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;
49
	} else if (filp->f_op->ioctl) {
L
Linus Torvalds 已提交
50
		lock_kernel();
51 52
		error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
					  filp, cmd, arg);
L
Linus Torvalds 已提交
53 54 55 56 57 58 59
		unlock_kernel();
	}

 out:
	return error;
}

60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78
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;
	lock_kernel();
	res = mapping->a_ops->bmap(mapping, block);
	unlock_kernel();
	return put_user(res, p);
}

M
Mark Fasheh 已提交
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
/**
 * 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)
{
	*new_len = len;

	if (len == 0)
		return -EINVAL;

	if (start > sb->s_maxbytes)
		return -EFBIG;

	/*
	 * Shrink request scope to what the fs can actually handle.
	 */
	if ((len > sb->s_maxbytes) ||
	    (sb->s_maxbytes - len) < start)
		*new_len = sb->s_maxbytes - start;

	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)
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
{
	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;
	int ret = 0;

	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));
	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)) {
			/*
			 * first hole after going past the EOF, this is our
			 * last extent
			 */
			if (length <= 0) {
				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				break;
			}

			length -= blk_to_logical(inode, 1);

			/* if we have holes up to/past EOF then we're done */
			if (length <= 0)
				break;

			start_blk++;
		} else {
			if (length <= 0 && size) {
				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);

			/*
			 * if we are past the EOF we need to loop again to see
			 * if there is a hole so we can mark this extent as the
			 * last one, and if not keep mapping things until we
			 * find a hole, or we run out of slots in the extent
			 * array
			 */
			if (length <= 0)
				continue;

			ret = fiemap_fill_next_extent(fieinfo, logical, phys,
						      size, flags);
			if (ret)
				break;
		}
		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;
}
345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
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;
}
369 370
EXPORT_SYMBOL(generic_block_fiemap);

371 372
#endif  /*  CONFIG_BLOCK  */

L
Linus Torvalds 已提交
373 374 375
static int file_ioctl(struct file *filp, unsigned int cmd,
		unsigned long arg)
{
376
	struct inode *inode = filp->f_path.dentry->d_inode;
L
Linus Torvalds 已提交
377 378 379
	int __user *p = (int __user *)arg;

	switch (cmd) {
380
	case FIBMAP:
381
		return ioctl_fibmap(filp, p);
M
Mark Fasheh 已提交
382 383
	case FS_IOC_FIEMAP:
		return ioctl_fiemap(filp, arg);
384 385 386 387
	case FIGETBSZ:
		return put_user(inode->i_sb->s_blocksize, p);
	case FIONREAD:
		return put_user(i_size_read(inode) - filp->f_pos, p);
L
Linus Torvalds 已提交
388 389
	}

390
	return vfs_ioctl(filp, cmd, arg);
L
Linus Torvalds 已提交
391 392
}

393 394 395 396 397 398 399 400 401 402 403 404 405 406
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
407
	spin_lock(&filp->f_lock);
408 409 410 411
	if (on)
		filp->f_flags |= flag;
	else
		filp->f_flags &= ~flag;
J
Jonathan Corbet 已提交
412
	spin_unlock(&filp->f_lock);
413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
	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) {
429
		if (filp->f_op && filp->f_op->fasync)
430
			/* fasync() adjusts filp->f_flags */
431
			error = filp->f_op->fasync(fd, filp, on);
432
		else
433 434
			error = -ENOTTY;
	}
435
	return error < 0 ? error : 0;
436 437
}

438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474
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);
}

L
Linus Torvalds 已提交
475 476 477 478
/*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
 *
479
 * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
L
Linus Torvalds 已提交
480 481
 * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
 */
482 483
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
	     unsigned long arg)
L
Linus Torvalds 已提交
484
{
485 486
	int error = 0;
	int __user *argp = (int __user *)arg;
L
Linus Torvalds 已提交
487 488

	switch (cmd) {
489 490 491
	case FIOCLEX:
		set_close_on_exec(fd, 1);
		break;
L
Linus Torvalds 已提交
492

493 494 495
	case FIONCLEX:
		set_close_on_exec(fd, 0);
		break;
L
Linus Torvalds 已提交
496

497
	case FIONBIO:
498
		error = ioctl_fionbio(filp, argp);
499 500 501
		break;

	case FIOASYNC:
502
		error = ioctl_fioasync(fd, filp, argp);
503 504 505 506 507 508 509 510 511 512 513 514 515
		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;
516 517 518 519 520 521 522 523 524

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

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

525 526 527 528
	default:
		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
			error = file_ioctl(filp, cmd, arg);
		else
529
			error = vfs_ioctl(filp, cmd, arg);
530
		break;
L
Linus Torvalds 已提交
531 532 533 534
	}
	return error;
}

535
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
L
Linus Torvalds 已提交
536
{
537
	struct file *filp;
L
Linus Torvalds 已提交
538 539 540 541 542 543 544 545 546 547 548
	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;

549
	error = do_vfs_ioctl(filp, fd, cmd, arg);
L
Linus Torvalds 已提交
550 551 552 553 554
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}