aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--mm/mmap.c9
1 files changed, 7 insertions, 2 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index 68b9ad2ef1d6..906ed402f7ca 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1536,9 +1536,14 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
1536 * vma->vm_start/vm_end cannot change under us because the caller 1536 * vma->vm_start/vm_end cannot change under us because the caller
1537 * is required to hold the mmap_sem in read mode. We need the 1537 * is required to hold the mmap_sem in read mode. We need the
1538 * anon_vma lock to serialize against concurrent expand_stacks. 1538 * anon_vma lock to serialize against concurrent expand_stacks.
1539 * Also guard against wrapping around to address 0.
1539 */ 1540 */
1540 address += 4 + PAGE_SIZE - 1; 1541 if (address < PAGE_ALIGN(address+4))
1541 address &= PAGE_MASK; 1542 address = PAGE_ALIGN(address+4);
1543 else {
1544 anon_vma_unlock(vma);
1545 return -ENOMEM;
1546 }
1542 error = 0; 1547 error = 0;
1543 1548
1544 /* Somebody else might have raced and expanded it already */ 1549 /* Somebody else might have raced and expanded it already */
'>222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 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 1146 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 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191
/*
 *  linux/fs/open.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/fcntl.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
#include <linux/falloc.h>

int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	int retval = -ENODEV;

	if (dentry) {
		retval = -ENOSYS;
		if (dentry->d_sb->s_op->statfs) {
			memset(buf, 0, sizeof(*buf));
			retval = security_sb_statfs(dentry);
			if (retval)
				return retval;
			retval = dentry->d_sb->s_op->statfs(dentry, buf);
			if (retval == 0 && buf->f_frsize == 0)
				buf->f_frsize = buf->f_bsize;
		}
	}
	return retval;
}

EXPORT_SYMBOL(vfs_statfs);

static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
{
	struct kstatfs st;
	int retval;

	retval = vfs_statfs(dentry, &st);
	if (retval)
		return retval;

	if (sizeof(*buf) == sizeof(st))
		memcpy(buf, &st, sizeof(st));
	else {
		if (sizeof buf->f_blocks == 4) {
			if ((st.f_blocks | st.f_bfree | st.f_bavail |
			     st.f_bsize | st.f_frsize) &
			    0xffffffff00000000ULL)
				return -EOVERFLOW;
			/*
			 * f_files and f_ffree may be -1; it's okay to stuff
			 * that into 32 bits
			 */
			if (st.f_files != -1 &&
			    (st.f_files & 0xffffffff00000000ULL))
				return -EOVERFLOW;
			if (st.f_ffree != -1 &&
			    (st.f_ffree & 0xffffffff00000000ULL))
				return -EOVERFLOW;
		}

		buf->f_type = st.f_type;
		buf->f_bsize = st.f_bsize;
		buf->f_blocks = st.f_blocks;
		buf->f_bfree = st.f_bfree;
		buf->f_bavail = st.f_bavail;
		buf->f_files = st.f_files;
		buf->f_ffree = st.f_ffree;
		buf->f_fsid = st.f_fsid;
		buf->f_namelen = st.f_namelen;
		buf->f_frsize = st.f_frsize;
		memset(buf->f_spare, 0, sizeof(buf->f_spare));
	}
	return 0;
}

static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf)
{
	struct kstatfs st;
	int retval;

	retval = vfs_statfs(dentry, &st);
	if (retval)
		return retval;

	if (sizeof(*buf) == sizeof(st))
		memcpy(buf, &st, sizeof(st));
	else {
		buf->f_type = st.f_type;
		buf->f_bsize = st.f_bsize;
		buf->f_blocks = st.f_blocks;
		buf->f_bfree = st.f_bfree;
		buf->f_bavail = st.f_bavail;
		buf->f_files = st.f_files;
		buf->f_ffree = st.f_ffree;
		buf->f_fsid = st.f_fsid;
		buf->f_namelen = st.f_namelen;
		buf->f_frsize = st.f_frsize;
		memset(buf->f_spare, 0, sizeof(buf->f_spare));
	}
	return 0;
}

SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
{
	struct path path;
	int error;

	error = user_path(pathname, &path);
	if (!error) {
		struct statfs tmp;
		error = vfs_statfs_native(path.dentry, &tmp);
		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
			error = -EFAULT;
		path_put(&path);
	}
	return error;
}

SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
{
	struct path path;
	long error;

	if (sz != sizeof(*buf))
		return -EINVAL;
	error = user_path(pathname, &path);
	if (!error) {
		struct statfs64 tmp;
		error = vfs_statfs64(path.dentry, &tmp);
		if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
			error = -EFAULT;
		path_put(&path);
	}
	return error;
}

SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
{
	struct file * file;
	struct statfs tmp;
	int error;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;
	error = vfs_statfs_native(file->f_path.dentry, &tmp);
	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
		error = -EFAULT;
	fput(file);
out:
	return error;
}

SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
{
	struct file * file;
	struct statfs64 tmp;
	int error;

	if (sz != sizeof(*buf))
		return -EINVAL;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;
	error = vfs_statfs64(file->f_path.dentry, &tmp);
	if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
		error = -EFAULT;
	fput(file);
out:
	return error;
}

int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
	struct file *filp)
{
	int err;
	struct iattr newattrs;

	/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
	if (length < 0)
		return -EINVAL;

	newattrs.ia_size = length;
	newattrs.ia_valid = ATTR_SIZE | time_attrs;
	if (filp) {
		newattrs.ia_file = filp;
		newattrs.ia_valid |= ATTR_FILE;
	}

	/* Remove suid/sgid on truncate too */
	newattrs.ia_valid |= should_remove_suid(dentry);

	mutex_lock(&dentry->d_inode->i_mutex);
	err = notify_change(dentry, &newattrs);
	mutex_unlock(&dentry->d_inode->i_mutex);
	return err;
}

static long do_sys_truncate(const char __user *pathname, loff_t length)
{
	struct path path;
	struct inode *inode;
	int error;

	error = -EINVAL;
	if (length < 0)	/* sorry, but loff_t says... */
		goto out;

	error = user_path(pathname, &path);
	if (error)
		goto out;
	inode = path.dentry->d_inode;

	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
	error = -EISDIR;
	if (S_ISDIR(inode->i_mode))
		goto dput_and_out;

	error = -EINVAL;
	if (!S_ISREG(inode->i_mode))
		goto dput_and_out;

	error = mnt_want_write(path.mnt);
	if (error)
		goto dput_and_out;

	error = inode_permission(inode, MAY_WRITE);
	if (error)
		goto mnt_drop_write_and_out;

	error = -EPERM;
	if (IS_APPEND(inode))
		goto mnt_drop_write_and_out;

	error = get_write_access(inode);
	if (error)
		goto mnt_drop_write_and_out;

	/*
	 * Make sure that there are no leases.  get_write_access() protects
	 * against the truncate racing with a lease-granting setlease().
	 */
	error = break_lease(inode, FMODE_WRITE);
	if (error)
		goto put_write_and_out;

	error = locks_verify_truncate(inode, NULL, length);
	if (!error)
		error = security_path_truncate(&path, length, 0);
	if (!error) {
		DQUOT_INIT(inode);
		error = do_truncate(path.dentry, length, 0, NULL);
	}

put_write_and_out:
	put_write_access(inode);
mnt_drop_write_and_out:
	mnt_drop_write(path.mnt);
dput_and_out:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE2(truncate, const char __user *, path, unsigned long, length)
{
	/* on 32-bit boxen it will cut the range 2^31--2^32-1 off */
	return do_sys_truncate(path, (long)length);
}

static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
	struct inode * inode;
	struct dentry *dentry;
	struct file * file;
	int error;

	error = -EINVAL;
	if (length < 0)
		goto out;
	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	/* explicitly opened as large or we are on 64-bit box */
	if (file->f_flags & O_LARGEFILE)
		small = 0;

	dentry = file->f_path.dentry;
	inode = dentry->d_inode;
	error = -EINVAL;
	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
		goto out_putf;

	error = -EINVAL;
	/* Cannot ftruncate over 2^31 bytes without large file support */
	if (small && length > MAX_NON_LFS)
		goto out_putf;

	error = -EPERM;
	if (IS_APPEND(inode))
		goto out_putf;

	error = locks_verify_truncate(inode, file, length);
	if (!error)
		error = security_path_truncate(&file->f_path, length,
					       ATTR_MTIME|ATTR_CTIME);
	if (!error)
		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
out_putf:
	fput(file);
out:
	return error;
}

SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
{
	long ret = do_sys_ftruncate(fd, length, 1);
	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(2, ret, fd, length);
	return ret;
}

/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length)
{
	return do_sys_truncate(path, length);
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_truncate64(long path, loff_t length)
{
	return SYSC_truncate64((const char __user *) path, length);
}
SYSCALL_ALIAS(sys_truncate64, SyS_truncate64);
#endif

SYSCALL_DEFINE(ftruncate64)(unsigned int fd, loff_t length)
{
	long ret = do_sys_ftruncate(fd, length, 0);
	/* avoid REGPARM breakage on x86: */
	asmlinkage_protect(2, ret, fd, length);
	return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_ftruncate64(long fd, loff_t length)
{
	return SYSC_ftruncate64((unsigned int) fd, length);
}
SYSCALL_ALIAS(sys_ftruncate64, SyS_ftruncate64);
#endif
#endif /* BITS_PER_LONG == 32 */

SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
{
	struct file *file;
	struct inode *inode;
	long ret = -EINVAL;

	if (offset < 0 || len <= 0)
		goto out;

	/* Return error if mode is not supported */
	ret = -EOPNOTSUPP;
	if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
		goto out;

	ret = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;
	if (!(file->f_mode & FMODE_WRITE))
		goto out_fput;
	/*
	 * Revalidate the write permissions, in case security policy has
	 * changed since the files were opened.
	 */
	ret = security_file_permission(file, MAY_WRITE);
	if (ret)
		goto out_fput;

	inode = file->f_path.dentry->d_inode;

	ret = -ESPIPE;
	if (S_ISFIFO(inode->i_mode))
		goto out_fput;

	ret = -ENODEV;
	/*
	 * Let individual file system decide if it supports preallocation
	 * for directories or not.
	 */
	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
		goto out_fput;

	ret = -EFBIG;
	/* Check for wrap through zero too */
	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
		goto out_fput;

	if (inode->i_op->fallocate)
		ret = inode->i_op->fallocate(inode, mode, offset, len);
	else
		ret = -EOPNOTSUPP;

out_fput:
	fput(file);
out:
	return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len)
{
	return SYSC_fallocate((int)fd, (int)mode, offset, len);
}
SYSCALL_ALIAS(sys_fallocate, SyS_fallocate);
#endif

/*
 * access() needs to use the real uid/gid, not the effective uid/gid.
 * We do this by temporarily clearing all FS-related capabilities and
 * switching the fsuid/fsgid around to the real ones.
 */
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
	const struct cred *old_cred;
	struct cred *override_cred;
	struct path path;
	struct inode *inode;
	int res;

	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
		return -EINVAL;

	override_cred = prepare_creds();
	if (!override_cred)
		return -ENOMEM;

	override_cred->fsuid = override_cred->uid;
	override_cred->fsgid = override_cred->gid;

	if (!issecure(SECURE_NO_SETUID_FIXUP)) {
		/* Clear the capabilities if we switch to a non-root user */
		if (override_cred->uid)
			cap_clear(override_cred->cap_effective);
		else
			override_cred->cap_effective =
				override_cred->cap_permitted;
	}

	old_cred = override_creds(override_cred);

	res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
	if (res)
		goto out;

	inode = path.dentry->d_inode;

	if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
		/*
		 * MAY_EXEC on regular files is denied if the fs is mounted
		 * with the "noexec" flag.
		 */
		res = -EACCES;
		if (path.mnt->mnt_flags & MNT_NOEXEC)
			goto out_path_release;
	}

	res = inode_permission(inode, mode | MAY_ACCESS);
	/* SuS v2 requires we report a read only fs too */
	if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
		goto out_path_release;
	/*
	 * This is a rare case where using __mnt_is_readonly()
	 * is OK without a mnt_want/drop_write() pair.  Since
	 * no actual write to the fs is performed here, we do
	 * not need to telegraph to that to anyone.
	 *
	 * By doing this, we accept that this access is
	 * inherently racy and know that the fs may change
	 * state before we even see this result.
	 */
	if (__mnt_is_readonly(path.mnt))
		res = -EROFS;

out_path_release:
	path_put(&path);
out:
	revert_creds(old_cred);
	put_cred(override_cred);
	return res;
}

SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
{
	return sys_faccessat(AT_FDCWD, filename, mode);
}

SYSCALL_DEFINE1(chdir, const char __user *, filename)
{
	struct path path;
	int error;

	error = user_path_dir(filename, &path);
	if (error)
		goto out;

	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
	if (error)
		goto dput_and_out;

	set_fs_pwd(current->fs, &path);

dput_and_out:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
	struct file *file;
	struct inode *inode;
	int error;

	error = -EBADF;
	file = fget(fd);
	if (!file)
		goto out;

	inode = file->f_path.dentry->d_inode;

	error = -ENOTDIR;
	if (!S_ISDIR(inode->i_mode))
		goto out_putf;

	error = inode_permission(inode, MAY_EXEC | MAY_ACCESS);
	if (!error)
		set_fs_pwd(current->fs, &file->f_path);
out_putf:
	fput(file);
out:
	return error;
}

SYSCALL_DEFINE1(chroot, const char __user *, filename)
{
	struct path path;
	int error;

	error = user_path_dir(filename, &path);
	if (error)
		goto out;

	error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
	if (error)
		goto dput_and_out;

	error = -EPERM;
	if (!capable(CAP_SYS_CHROOT))
		goto dput_and_out;

	set_fs_root(current->fs, &path);
	error = 0;
dput_and_out:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
{
	struct inode * inode;
	struct dentry * dentry;
	struct file * file;
	int err = -EBADF;
	struct iattr newattrs;

	file = fget(fd);
	if (!file)
		goto out;

	dentry = file->f_path.dentry;
	inode = dentry->d_inode;

	audit_inode(NULL, dentry);

	err = mnt_want_write(file->f_path.mnt);
	if (err)
		goto out_putf;
	mutex_lock(&inode->i_mutex);
	if (mode == (mode_t) -1)
		mode = inode->i_mode;
	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
	err = notify_change(dentry, &newattrs);
	mutex_unlock(&inode->i_mutex);
	mnt_drop_write(file->f_path.mnt);
out_putf:
	fput(file);
out:
	return err;
}

SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
{
	struct path path;
	struct inode *inode;
	int error;
	struct iattr newattrs;

	error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
	if (error)
		goto out;
	inode = path.dentry->d_inode;

	error = mnt_want_write(path.mnt);
	if (error)
		goto dput_and_out;
	mutex_lock(&inode->i_mutex);
	if (mode == (mode_t) -1)
		mode = inode->i_mode;
	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
	error = notify_change(path.dentry, &newattrs);
	mutex_unlock(&inode->i_mutex);
	mnt_drop_write(path.mnt);
dput_and_out:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE2(chmod, const char __user *, filename, mode_t, mode)
{
	return sys_fchmodat(AT_FDCWD, filename, mode);
}

static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
{
	struct inode *inode = dentry->d_inode;
	int error;
	struct iattr newattrs;

	newattrs.ia_valid =  ATTR_CTIME;
	if (user != (uid_t) -1) {
		newattrs.ia_valid |= ATTR_UID;
		newattrs.ia_uid = user;
	}
	if (group != (gid_t) -1) {
		newattrs.ia_valid |= ATTR_GID;
		newattrs.ia_gid = group;
	}
	if (!S_ISDIR(inode->i_mode))
		newattrs.ia_valid |=
			ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
	mutex_lock(&inode->i_mutex);
	error = notify_change(dentry, &newattrs);
	mutex_unlock(&inode->i_mutex);

	return error;
}

SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
{
	struct path path;
	int error;

	error = user_path(filename, &path);
	if (error)
		goto out;
	error = mnt_want_write(path.mnt);
	if (error)
		goto out_release;
	error = chown_common(path.dentry, user, group);
	mnt_drop_write(path.mnt);
out_release:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
		gid_t, group, int, flag)
{
	struct path path;
	int error = -EINVAL;
	int follow;

	if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
		goto out;

	follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
	error = user_path_at(dfd, filename, follow, &path);
	if (error)
		goto out;
	error = mnt_want_write(path.mnt);
	if (error)
		goto out_release;
	error = chown_common(path.dentry, user, group);
	mnt_drop_write(path.mnt);
out_release:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
{
	struct path path;
	int error;

	error = user_lpath(filename, &path);
	if (error)
		goto out;
	error = mnt_want_write(path.mnt);
	if (error)
		goto out_release;
	error = chown_common(path.dentry, user, group);
	mnt_drop_write(path.mnt);
out_release:
	path_put(&path);
out:
	return error;
}

SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
{
	struct file * file;
	int error = -EBADF;
	struct dentry * dentry;

	file = fget(fd);
	if (!file)
		goto out;

	error = mnt_want_write(file->f_path.mnt);
	if (error)
		goto out_fput;
	dentry = file->f_path.dentry;
	audit_inode(NULL, dentry);
	error = chown_common(dentry, user, group);
	mnt_drop_write(file->f_path.mnt);
out_fput:
	fput(file);
out:
	return error;
}

/*
 * You have to be very careful that these write
 * counts get cleaned up in error cases and
 * upon __fput().  This should probably never
 * be called outside of __dentry_open().
 */
static inline int __get_file_write_access(struct inode *inode,
					  struct vfsmount *mnt)
{
	int error;
	error = get_write_access(inode);
	if (error)
		return error;
	/*
	 * Do not take mount writer counts on
	 * special files since no writes to
	 * the mount itself will occur.
	 */
	if (!special_file(inode->i_mode)) {
		/*
		 * Balanced in __fput()
		 */
		error = mnt_want_write(mnt);
		if (error)
			put_write_access(inode);
	}
	return error;
}

static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
					int flags, struct file *f,
					int (*open)(struct inode *, struct file *),
					const struct cred *cred)
{
	struct inode *inode;
	int error;

	f->f_flags = flags;
	f->f_mode = (__force fmode_t)((flags+1) & O_ACCMODE) | FMODE_LSEEK |
				FMODE_PREAD | FMODE_PWRITE;
	inode = dentry->d_inode;
	if (f->f_mode & FMODE_WRITE) {
		error = __get_file_write_access(inode, mnt);
		if (error)
			goto cleanup_file;
		if (!special_file(inode->i_mode))
			file_take_write(f);
	}

	f->f_mapping = inode->i_mapping;
	f->f_path.dentry = dentry;
	f->f_path.mnt = mnt;
	f->f_pos = 0;
	f->f_op = fops_get(inode->i_fop);
	file_move(f, &inode->i_sb->s_files);

	error = security_dentry_open(f, cred);
	if (error)
		goto cleanup_all;

	if (!open && f->f_op)
		open = f->f_op->open;
	if (open) {
		error = open(inode, f);
		if (error)
			goto cleanup_all;
	}

	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);

	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);

	/* NB: we're sure to have correct a_ops only after f_op->open */
	if (f->f_flags & O_DIRECT) {
		if (!f->f_mapping->a_ops ||
		    ((!f->f_mapping->a_ops->direct_IO) &&
		    (!f->f_mapping->a_ops->get_xip_mem))) {
			fput(f);
			f = ERR_PTR(-EINVAL);
		}
	}

	return f;

cleanup_all:
	fops_put(f->f_op);
	if (f->f_mode & FMODE_WRITE) {
		put_write_access(inode);
		if (!special_file(inode->i_mode)) {
			/*
			 * We don't consider this a real
			 * mnt_want/drop_write() pair
			 * because it all happenend right
			 * here, so just reset the state.
			 */
			file_reset_write(f);
			mnt_drop_write(mnt);
		}
	}
	file_kill(f);
	f->f_path.dentry = NULL;
	f->f_path.mnt = NULL;
cleanup_file:
	put_filp(f);
	dput(dentry);
	mntput(mnt);
	return ERR_PTR(error);
}

/**
 * lookup_instantiate_filp - instantiates the open intent filp
 * @nd: pointer to nameidata
 * @dentry: pointer to dentry
 * @open: open callback
 *
 * Helper for filesystems that want to use lookup open intents and pass back
 * a fully instantiated struct file to the caller.
 * This function is meant to be called from within a filesystem's
 * lookup method.
 * Beware of calling it for non-regular files! Those ->open methods might block
 * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
 * leading to a deadlock, as nobody can open that fifo anymore, because
 * another process to open fifo will block on locked parent when doing lookup).
 * Note that in case of error, nd->intent.open.file is destroyed, but the
 * path information remains valid.
 * If the open callback is set to NULL, then the standard f_op->open()
 * filesystem callback is substituted.
 */
struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
		int (*open)(struct inode *, struct file *))
{
	const struct cred *cred = current_cred();

	if (IS_ERR(nd->intent.open.file))
		goto out;
	if (IS_ERR(dentry))
		goto out_err;
	nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
					     nd->intent.open.flags - 1,
					     nd->intent.open.file,
					     open, cred);
out:
	return nd->intent.open.file;
out_err:
	release_open_intent(nd);
	nd->intent.open.file = (struct file *)dentry;
	goto out;
}
EXPORT_SYMBOL_GPL(lookup_instantiate_filp);

/**
 * nameidata_to_filp - convert a nameidata to an open filp.
 * @nd: pointer to nameidata
 * @flags: open flags
 *
 * Note that this function destroys the original nameidata
 */
struct file *nameidata_to_filp(struct nameidata *nd, int flags)
{
	const struct cred *cred = current_cred();
	struct file *filp;

	/* Pick up the filp from the open intent */
	filp = nd->intent.open.file;
	/* Has the filesystem initialised the file for us? */
	if (filp->f_path.dentry == NULL)
		filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp,
				     NULL, cred);
	else
		path_put(&nd->path);
	return filp;
}

/*
 * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
 * error.
 */
struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
			 const struct cred *cred)
{
	int error;
	struct file *f;

	/*
	 * We must always pass in a valid mount pointer.   Historically
	 * callers got away with not passing it, but we must enforce this at
	 * the earliest possible point now to avoid strange problems deep in the
	 * filesystem stack.
	 */
	if (!mnt) {
		printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
		dump_stack();
		return ERR_PTR(-EINVAL);
	}

	error = -ENFILE;
	f = get_empty_filp();
	if (f == NULL) {
		dput(dentry);
		mntput(mnt);
		return ERR_PTR(error);
	}

	return __dentry_open(dentry, mnt, flags, f, NULL, cred);
}
EXPORT_SYMBOL(dentry_open);

static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
	struct fdtable *fdt = files_fdtable(files);
	__FD_CLR(fd, fdt->open_fds);
	if (fd < files->next_fd)
		files->next_fd = fd;
}

void put_unused_fd(unsigned int fd)
{
	struct files_struct *files = current->files;
	spin_lock(&files->file_lock);
	__put_unused_fd(files, fd);
	spin_unlock(&files->file_lock);
}

EXPORT_SYMBOL(put_unused_fd);

/*
 * Install a file pointer in the fd array.
 *
 * The VFS is full of places where we drop the files lock between
 * setting the open_fds bitmap and installing the file in the file
 * array.  At any such point, we are vulnerable to a dup2() race
 * installing a file in the array before us.  We need to detect this and
 * fput() the struct file we are about to overwrite in this case.
 *
 * It should never happen - if we allow dup2() do it, _really_ bad things
 * will follow.
 */

void fd_install(unsigned int fd, struct file *file)
{
	struct files_struct *files = current->files;
	struct fdtable *fdt;
	spin_lock(&files->file_lock);
	fdt = files_fdtable(files);
	BUG_ON(fdt->fd[fd] != NULL);
	rcu_assign_pointer(fdt->fd[fd], file);
	spin_unlock(&files->file_lock);
}

EXPORT_SYMBOL(fd_install);

long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
{
	char *tmp = getname(filename);
	int fd = PTR_ERR(tmp);

	if (!IS_ERR(tmp)) {
		fd = get_unused_fd_flags(flags);
		if (fd >= 0) {
			struct file *f = do_filp_open(dfd, tmp, flags, mode);