litmus-rt-pandaboard.git - LITMUS^RT and MC^2 V0 support for the pandaboard.

about summary refs log tree commit diff stats

diff options

Diffstat (limited to 'fs/jbd/commit.c')

0 files changed, 0 insertions, 0 deletions

Linus Torvalds <torvalds@ppc970.osdl.org> 2005-04-16 18:20:36 -0400 Linux-2.6.12-rc2' href='/cgit/cgit.cgi/litmus-rt-imx6.git/commit/fs/namei.c?id=1da177e4c3f41524e886b7f1b8a0c1fc7321cac2'>1da177e4c3f4

20
21
22

25
26

28
29
30

37
38

128
129

130
131

137
138

146
147

159
160

185
186
187

189
190
191

193
194

201
202

205
206

207
208

218
219

221
222

223
224

226
227

229
230

232
233
234

241
242
243

245
246

247
248

277
278

281
282

319
320

322
323

325
326

328
329
330

331
332

333
334

372
373
374

377
378

379
380
381

396
397
398

404
405

407
408

469
470

498
499
500

503
504
505

508
509
510

512
513

514
515

527
528

551
552

553
554

557
558

567
568

569
570
571

598
599

600
601
602

604
605

607
608
609

614
615
616

617
618

619
620

621
622

623
624

636
637
638

641
642

649
650

655
656

659
660
661

663
664

666
667
668

669
670

679
680

692
693

694
695
696

702
703

741
742

811
812
813

815
816
817

822
823

825
826

827
828
829

834
835
836

841
842

845
846

854
855

864
865
866

867
868

869
870

871
872

873
874

879
880
881

894
895

902
903

907
908
909

911
912
913

915
916
917

919
920

941
942
943

960
961

964
965

974
975
976

980
981

983
984

987
988

989
990

1002
1003

1020
1021

1058
1059

1061
1062
1063

1082
1083

1084
1085

1100
1101
1102

1103
1104

1114
1115
1116

1122
1123

1124
1125

1127
1128
1129

1130
1131

1132
1133

1155
1156

1158
1159
1160

1161
1162

1165
1166

1168
1169
1170

1239
1240

1241
1242

1244
1245

1246
1247
1248

1254
1255

1269
1270
1271

1305
1306
1307

1325
1326

1328
1329

1332
1333

1344
1345

1346
1347

1353
1354

1356
1357
1358

1374
1375

1386
1387

1394
1395

1400
1401
1402

1416
1417
1418

1419
1420

1423
1424

1427
1428

1439
1440
1441

1443
1444
1445

1456
1457

1458
1459
1460

1462
1463

1465
1466

1468
1469

1488
1489

1491
1492
1493

1524
1525

1528
1529
1530

1542
1543

1544
1545

1546
1547

1560
1561

1586
1587

1588
1589

1666
1667
1668

1688
1689

1706
1707

1741
1742

1745
1746

1748
1749

1752
1753

1761
1762

1768
1769
1770

1780
1781

1786
1787

1797
1798
1799

1810
1811

1815
1816

1829
1830
1831

1832
1833

1834
1835

1836
1837

1840
1841

1849
1850
1851

1861
1862

1872
1873
1874

1889
1890

1891
1892

1898
1899
1900

1905
1906

1910
1911

1917
1918

1926
1927

1930
1931

1933
1934

1952
1953

1954
1955

1956
1957
1958

1963
1964
1965

1968
1969
1970

1972
1973

1975
1976

1982
1983

1985
1986

1989
1990
1991

1996
1997

2002
2003

2008
2009

2018
2019

2039
2040

2057
2058
2059

2072
2073

2082
2083

2090
2091

2092
2093
2094

2095
2096

2101
2102

2103
2104

2106
2107
2108

2134
2135

2136
2137

2143
2144
2145

2148
2149

2154
2155
2156

2158
2159

2167
2168

2171
2172

2173
2174
2175

2182
2183

2186
2187

2196
2197

2271
2272

2282
2283
2284

2292
2293

2299
2300

2301
2302

2312
2313
2314

2319
2320
2321

2332
2333
2334

2338
2339
2340

2345
2346
2347

2348
2349

2359
2360
2361

2367
2368

2378
2379
2380

2400
2401
2402

2404
2405

2407
2408

2409
2410

2411
2412

2413
2414
2415

2442
2443
2444

2461
2462
2463

2465
2466
2467

2482
2483
2484

2493
2494
2495

2514
2515
2516

2519
2520

2533
2534

2550
2551
2552

2553
2554
2555

2558
2559

2584
2585

2588
2589
2590

2604
2605
2606

2608
2609

2611
2612

2627
2628

2629
2630
2631

2635
2636

2649
2650

2654
2655
2656

2657
2658

2659
2660
2661

2663
2664

2666
2667
2668

2670
2671
2672

2675
2676

2686
2687

2690
2691
2692

2693
2694

2696
2697

2719
2720

2730
2731

2744
2745
2746

2765
2766

2767
2768

2774
2775

2784
2785
2786

2800
2801

2804
2805

2806
2807
2808

2810
2811
2812

2813
2814

2815
2816

2818
2819

2828
2829
2830

2843
2844

2845
2846

2852
2853

2860
2861
2862

2870
2871
2872

2879
2880

2887
2888

2897
2898

2901
2902

2918
2919
2920

2921
2922

2933
2934

2947
2948

2952
2953

2955
2956

2957
2958
2959

2960
2961

2964
2965

2969
2970

2971
2972

2973
2974

2987
2988

2990
2991

2993
2994

3000
3001
3002

3016
3017

3023
3024
3025

3026
3027

3042
3043

3054
3055

3056
3057
3058

3059
3060

3077
3078

3084
3085
3086

3088
3089

3090
3091

3092
3093

3094
3095

3105
3106

3109
3110
3111

3126
3127

3129
3130

3142
3143
3144

3166
3167

3170
3171
3172

3173
3174

3175
3176

3186
3187

3189
3190
3191

3201
3202
3203

3225
3226
3227

3231
3232
3233

3237
3238

3241
3242

3249
3250

3256
3257
3258

3267
3268

3284
3285

3296
3297

3300
3301

3322
3323
3324

3326
3327

3329
3330

3331
3332
3333

3334
3335

3336
3337

3348
3349

3350
3351
3352

3357
3358

3363
3364

3368
3369

3379
3380
3381

3395
3396

3409
3410
3411

3422
3423
3424

3429
3430
3431

3432
3433
3434

3435
3436

3438
3439
3440

3441
3442

3443
3444
3445

3449
3450
3451

3452
3453

3456
3457

3458
3459

3463
3464

3466
3467

3518
3519
3520

3521
3522

3529
3530

3533
3534

3535
3536

3557
3558
3559

3588
3589
3590

3591
3592

3593
3594

3610
3611

3612
3613

3636
3637

3638
3639

3647
3648
3649

3669
3670

3679
3680

3682
3683

3685
3686
3687

3689
3690
3691

3696
3697

3698
3699

3700
3701

3732
3733

3739
3740

3742
3743
3744

3747
3748

3749
3750
3751

3752
3753

3765
3766

3807
3808

3809
3810

3815
3816

3818
3819

3820
3821
3822

3823
3824

3826
3827
3828

3830
3831

3832
3833

3835
3836

3837
3838

3843
3844

3847
3848

3850
3851

3858
3859
3860

3865
3866

3869
3870

3900
3901
3902

3914
3915

3927
3928
3929

3982
3983

3989
3990
3991

4011
4012

4015
4016
4017

4018
4019

4020
4021
4022

4027
4028

4033
4034
4035

4041
4042

4046
4047
4048

4049
4050

4051
4052
4053

4054
4055

4060
4061
4062

4064
4065

4074
4075

4083
4084

/*
 *  linux/fs/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * Some corrections by tytso.
 */

/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
 * lookup logic.
 */
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
 */

#include <linux/init.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/ima.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <linux/posix_acl.h>
#include <asm/uaccess.h>

#include "internal.h"
#include "mount.h"

/* [Feb-1997 T. Schoebel-Theuer]
 * Fundamental changes in the pathname lookup mechanisms (namei)
 * were necessary because of omirr.  The reason is that omirr needs
 * to know the _real_ pathname, not the user-supplied one, in case
 * of symlinks (and also when transname replacements occur).
 *
 * The new code replaces the old recursive symlink resolution with
 * an iterative one (in case of non-nested symlink chains).  It does
 * this with calls to <fs>_follow_link().
 * As a side effect, dir_namei(), _namei() and follow_link() are now 
 * replaced with a single function lookup_dentry() that can handle all 
 * the special cases of the former code.
 *
 * With the new dcache, the pathname is stored at each inode, at least as
 * long as the refcount of the inode is positive.  As a side effect, the
 * size of the dcache depends on the inode cache and thus is dynamic.
 *
 * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
 * resolution to correspond with current state of the code.
 *
 * Note that the symlink resolution is not *completely* iterative.
 * There is still a significant amount of tail- and mid- recursion in
 * the algorithm.  Also, note that <fs>_readlink() is not used in
 * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
 * may return different results than <fs>_follow_link().  Many virtual
 * filesystems (including /proc) exhibit this behavior.
 */

/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
 * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
 * and the name already exists in form of a symlink, try to create the new
 * name indicated by the symlink. The old code always complained that the
 * name already exists, due to not following the symlink even if its target
 * is nonexistent.  The new semantics affects also mknod() and link() when
 * the name is a symlink pointing to a non-existent name.
 *
 * I don't know which semantics is the right one, since I have no access
 * to standards. But I found by trial that HP-UX 9.0 has the full "new"
 * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
 * "old" one. Personally, I think the new semantics is much more logical.
 * Note that "ln old new" where "new" is a symlink pointing to a non-existing
 * file does succeed in both HP-UX and SunOs, but not in Solaris
 * and in the old Linux semantics.
 */

/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
 * semantics.  See the comments in "open_namei" and "do_link" below.
 *
 * [10-Sep-98 Alan Modra] Another symlink change.
 */

/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
 *	inside the path - always follow.
 *	in the last component in creation/removal/renaming - never follow.
 *	if LOOKUP_FOLLOW passed - follow.
 *	if the pathname has trailing slashes - follow.
 *	otherwise - don't follow.
 * (applied in that order).
 *
 * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
 * restored for 2.4. This is the last surviving part of old 4.2BSD bug.
 * During the 2.4 we need to fix the userland stuff depending on it -
 * hopefully we will be able to get rid of that wart in 2.5. So far only
 * XEmacs seems to be relying on it...
 */
/*
 * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
 * implemented.  Let's see if raised priority of ->s_vfs_rename_mutex gives
 * any extra contention...
 */

/* In order to reduce some races, while at the same time doing additional
 * checking and hopefully speeding things up, we copy filenames to the
 * kernel data space before using them..
 *
 * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
 * PATH_MAX includes the nul terminator --RR.
 */
void final_putname(struct filename *name)
{
	if (name->separate) {
		__putname(name->name);
		kfree(name);
	} else {
		__putname(name);
	}
}

#define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))

static struct filename *
getname_flags(const char __user *filename, int flags, int *empty)
{
	struct filename *result, *err;
	int len;
	long max;
	char *kname;

	result = audit_reusename(filename);
	if (result)
		return result;

	result = __getname();
	if (unlikely(!result))
		return ERR_PTR(-ENOMEM);

	/*
	 * First, try to embed the struct filename inside the names_cache
	 * allocation
	 */
	kname = (char *)result + sizeof(*result);
	result->name = kname;
	result->separate = false;
	max = EMBEDDED_NAME_MAX;

recopy:
	len = strncpy_from_user(kname, filename, max);
	if (unlikely(len < 0)) {
		err = ERR_PTR(len);
		goto error;
	}

	/*
	 * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
	 * separate struct filename so we can dedicate the entire
	 * names_cache allocation for the pathname, and re-do the copy from
	 * userland.
	 */
	if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) {
		kname = (char *)result;

		result = kzalloc(sizeof(*result), GFP_KERNEL);
		if (!result) {
			err = ERR_PTR(-ENOMEM);
			result = (struct filename *)kname;
			goto error;
		}
		result->name = kname;
		result->separate = true;
		max = PATH_MAX;
		goto recopy;
	}

	/* The empty path is special. */
	if (unlikely(!len)) {
		if (empty)
			*empty = 1;
		err = ERR_PTR(-ENOENT);
		if (!(flags & LOOKUP_EMPTY))
			goto error;
	}

	err = ERR_PTR(-ENAMETOOLONG);
	if (unlikely(len >= PATH_MAX))
		goto error;

	result->uptr = filename;
	audit_getname(result);
	return result;

error:
	final_putname(result);
	return err;
}

struct filename *
getname(const char __user * filename)
{
	return getname_flags(filename, 0, NULL);
}
EXPORT_SYMBOL(getname);

#ifdef CONFIG_AUDITSYSCALL
void putname(struct filename *name)
{
	if (unlikely(!audit_dummy_context()))
		return audit_putname(name);
	final_putname(name);
}
#endif

static int check_acl(struct inode *inode, int mask)
{
#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl *acl;

	if (mask & MAY_NOT_BLOCK) {
		acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
	        if (!acl)
	                return -EAGAIN;
		/* no ->get_acl() calls in RCU mode... */
		if (acl == ACL_NOT_CACHED)
			return -ECHILD;
	        return posix_acl_permission(inode, acl, mask & ~MAY_NOT_BLOCK);
	}

	acl = get_cached_acl(inode, ACL_TYPE_ACCESS);

	/*
	 * A filesystem can force a ACL callback by just never filling the
	 * ACL cache. But normally you'd fill the cache either at inode
	 * instantiation time, or on the first ->get_acl call.
	 *
	 * If the filesystem doesn't have a get_acl() function at all, we'll
	 * just create the negative cache entry.
	 */
	if (acl == ACL_NOT_CACHED) {
	        if (inode->i_op->get_acl) {
			acl = inode->i_op->get_acl(inode, ACL_TYPE_ACCESS);
			if (IS_ERR(acl))
				return PTR_ERR(acl);
		} else {
		        set_cached_acl(inode, ACL_TYPE_ACCESS, NULL);
		        return -EAGAIN;
		}
	}

	if (acl) {
	        int error = posix_acl_permission(inode, acl, mask);
	        posix_acl_release(acl);
	        return error;
	}
#endif

	return -EAGAIN;
}

/*
 * This does the basic permission checking
 */
static int acl_permission_check(struct inode *inode, int mask)
{
	unsigned int mode = inode->i_mode;

	if (likely(uid_eq(current_fsuid(), inode->i_uid)))
		mode >>= 6;
	else {
		if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
			int error = check_acl(inode, mask);
			if (error != -EAGAIN)
				return error;
		}

		if (in_group_p(inode->i_gid))
			mode >>= 3;
	}

	/*
	 * If the DACs are ok we don't need any capability check.
	 */
	if ((mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
		return 0;
	return -EACCES;
}

/**
 * generic_permission -  check for access rights on a Posix-like filesystem
 * @inode:	inode to check access rights for
 * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
 *
 * Used to check for read/write/execute permissions on a file.
 * We use "fsuid" for this, letting us set arbitrary permissions
 * for filesystem access without changing the "normal" uids which
 * are used for other things.
 *
 * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
 * request cannot be satisfied (eg. requires blocking or too much complexity).
 * It would then be called again in ref-walk mode.
 */
int generic_permission(struct inode *inode, int mask)
{
	int ret;

	/*
	 * Do the basic permission checks.
	 */
	ret = acl_permission_check(inode, mask);
	if (ret != -EACCES)
		return ret;

	if (S_ISDIR(inode->i_mode)) {
		/* DACs are overridable for directories */
		if (inode_capable(inode, CAP_DAC_OVERRIDE))
			return 0;
		if (!(mask & MAY_WRITE))
			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
				return 0;
		return -EACCES;
	}
	/*
	 * Read/write DACs are always overridable.
	 * Executable DACs are overridable when there is
	 * at least one exec bit set.
	 */
	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
		if (inode_capable(inode, CAP_DAC_OVERRIDE))
			return 0;

	/*
	 * Searching includes executable on directories, else just read.
	 */
	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
	if (mask == MAY_READ)
		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
			return 0;

	return -EACCES;
}

/*
 * We _really_ want to just do "generic_permission()" without
 * even looking at the inode->i_op values. So we keep a cache
 * flag in inode->i_opflags, that says "this has not special
 * permission function, use the fast case".
 */
static inline int do_inode_permission(struct inode *inode, int mask)
{
	if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
		if (likely(inode->i_op->permission))
			return inode->i_op->permission(inode, mask);

		/* This gets set once for the inode lifetime */
		spin_lock(&inode->i_lock);
		inode->i_opflags |= IOP_FASTPERM;
		spin_unlock(&inode->i_lock);
	}
	return generic_permission(inode, mask);
}

/**
 * __inode_permission - Check for access rights to a given inode
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Check for read/write/execute permissions on an inode.
 *
 * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
 *
 * This does not check for a read-only file system.  You probably want
 * inode_permission().
 */
int __inode_permission(struct inode *inode, int mask)
{
	int retval;

	if (unlikely(mask & MAY_WRITE)) {
		/*
		 * Nobody gets write access to an immutable file.
		 */
		if (IS_IMMUTABLE(inode))
			return -EACCES;
	}

	retval = do_inode_permission(inode, mask);
	if (retval)
		return retval;

	retval = devcgroup_inode_permission(inode, mask);
	if (retval)
		return retval;

	return security_inode_permission(inode, mask);
}

/**
 * sb_permission - Check superblock-level permissions
 * @sb: Superblock of inode to check permission on
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Separate out file-system wide checks from inode-specific permission checks.
 */
static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
{
	if (unlikely(mask & MAY_WRITE)) {
		umode_t mode = inode->i_mode;

		/* Nobody gets write access to a read-only fs. */
		if ((sb->s_flags & MS_RDONLY) &&
		    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
			return -EROFS;
	}
	return 0;
}

/**
 * inode_permission - Check for access rights to a given inode
 * @inode: Inode to check permission on
 * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
 *
 * Check for read/write/execute permissions on an inode.  We use fs[ug]id for
 * this, letting us set arbitrary permissions for filesystem access without
 * changing the "normal" UIDs which are used for other things.
 *
 * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
 */
int inode_permission(struct inode *inode, int mask)
{
	int retval;

	retval = sb_permission(inode->i_sb, inode, mask);
	if (retval)
		return retval;
	return __inode_permission(inode, mask);
}

/**
 * path_get - get a reference to a path
 * @path: path to get the reference to
 *
 * Given a path increment the reference count to the dentry and the vfsmount.
 */
void path_get(const struct path *path)
{
	mntget(path->mnt);
	dget(path->dentry);
}
EXPORT_SYMBOL(path_get);

/**
 * path_put - put a reference to a path
 * @path: path to put the reference to
 *
 * Given a path decrement the reference count to the dentry and the vfsmount.
 */
void path_put(const struct path *path)
{
	dput(path->dentry);
	mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);

/*
 * Path walking has 2 modes, rcu-walk and ref-walk (see
 * Documentation/filesystems/path-lookup.txt).  In situations when we can't
 * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
 * normal reference counts on dentries and vfsmounts to transition to rcu-walk
 * mode.  Refcounts are grabbed at the last known good point before rcu-walk
 * got stuck, so ref-walk may continue from there. If this is not successful
 * (eg. a seqcount has changed), then failure is returned and it's up to caller
 * to restart the path walk from the beginning in ref-walk mode.
 */

static inline void lock_rcu_walk(void)
{
	br_read_lock(&vfsmount_lock);
	rcu_read_lock();
}

static inline void unlock_rcu_walk(void)
{
	rcu_read_unlock();
	br_read_unlock(&vfsmount_lock);
}

/**
 * unlazy_walk - try to switch to ref-walk mode.
 * @nd: nameidata pathwalk data
 * @dentry: child of nd->path.dentry or NULL
 * Returns: 0 on success, -ECHILD on failure
 *
 * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
 * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
 * @nd or NULL.  Must be called from rcu-walk context.
 */
static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
{
	struct fs_struct *fs = current->fs;
	struct dentry *parent = nd->path.dentry;
	int want_root = 0;

	BUG_ON(!(nd->flags & LOOKUP_RCU));
	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
		want_root = 1;
		spin_lock(&fs->lock);
		if (nd->root.mnt != fs->root.mnt ||
				nd->root.dentry != fs->root.dentry)
			goto err_root;
	}
	spin_lock(&parent->d_lock);
	if (!dentry) {
		if (!__d_rcu_to_refcount(parent, nd->seq))
			goto err_parent;
		BUG_ON(nd->inode != parent->d_inode);
	} else {
		if (dentry->d_parent != parent)
			goto err_parent;
		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
		if (!__d_rcu_to_refcount(dentry, nd->seq))
			goto err_child;
		/*
		 * If the sequence check on the child dentry passed, then
		 * the child has not been removed from its parent. This
		 * means the parent dentry must be valid and able to take
		 * a reference at this point.
		 */
		BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
		BUG_ON(!parent->d_count);
		parent->d_count++;
		spin_unlock(&dentry->d_lock);
	}
	spin_unlock(&parent->d_lock);
	if (want_root) {
		path_get(&nd->root);
		spin_unlock(&fs->lock);
	}
	mntget(nd->path.mnt);

	unlock_rcu_walk();
	nd->flags &= ~LOOKUP_RCU;
	return 0;

err_child:
	spin_unlock(&dentry->d_lock);
err_parent:
	spin_unlock(&parent->d_lock);
err_root:
	if (want_root)
		spin_unlock(&fs->lock);
	return -ECHILD;
}

static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
	return dentry->d_op->d_revalidate(dentry, flags);
}

/**
 * complete_walk - successful completion of path walk
 * @nd:  pointer nameidata
 *
 * If we had been in RCU mode, drop out of it and legitimize nd->path.
 * Revalidate the final result, unless we'd already done that during
 * the path walk or the filesystem doesn't ask for it.  Return 0 on
 * success, -error on failure.  In case of failure caller does not
 * need to drop nd->path.
 */
static int complete_walk(struct nameidata *nd)
{
	struct dentry *dentry = nd->path.dentry;
	int status;

	if (nd->flags & LOOKUP_RCU) {
		nd->flags &= ~LOOKUP_RCU;
		if (!(nd->flags & LOOKUP_ROOT))
			nd->root.mnt = NULL;
		spin_lock(&dentry->d_lock);
		if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
			spin_unlock(&dentry->d_lock);
			unlock_rcu_walk();
			return -ECHILD;
		}
		BUG_ON(nd->inode != dentry->d_inode);
		spin_unlock(&dentry->d_lock);
		mntget(nd->path.mnt);
		unlock_rcu_walk();
	}

	if (likely(!(nd->flags & LOOKUP_JUMPED)))
		return 0;

	if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
		return 0;

	status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
	if (status > 0)
		return 0;

	if (!status)
		status = -ESTALE;

	path_put(&nd->path);
	return status;
}

static __always_inline void set_root(struct nameidata *nd)
{
	if (!nd->root.mnt)
		get_fs_root(current->fs, &nd->root);
}

static int link_path_walk(const char *, struct nameidata *);

static __always_inline void set_root_rcu(struct nameidata *nd)
{
	if (!nd->root.mnt) {
		struct fs_struct *fs = current->fs;
		unsigned seq;

		do {
			seq = read_seqcount_begin(&fs->seq);
			nd->root = fs->root;
			nd->seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
		} while (read_seqcount_retry(&fs->seq, seq));
	}
}

static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
	int ret;

	if (IS_ERR(link))
		goto fail;

	if (*link == '/') {
		set_root(nd);
		path_put(&nd->path);
		nd->path = nd->root;
		path_get(&nd->root);
		nd->flags |= LOOKUP_JUMPED;
	}
	nd->inode = nd->path.dentry->d_inode;

	ret = link_path_walk(link, nd);
	return ret;
fail:
	path_put(&nd->path);
	return PTR_ERR(link);
}

static void path_put_conditional(struct path *path, struct nameidata *nd)
{
	dput(path->dentry);
	if (path->mnt != nd->path.mnt)
		mntput(path->mnt);
}

static inline void path_to_nameidata(const struct path *path,
					struct nameidata *nd)
{
	if (!(nd->flags & LOOKUP_RCU)) {
		dput(nd->path.dentry);
		if (nd->path.mnt != path->mnt)
			mntput(nd->path.mnt);
	}
	nd->path.mnt = path->mnt;
	nd->path.dentry = path->dentry;
}

/*
 * Helper to directly jump to a known parsed path from ->follow_link,
 * caller must have taken a reference to path beforehand.
 */
void nd_jump_link(struct nameidata *nd, struct path *path)
{
	path_put(&nd->path);

	nd->path = *path;
	nd->inode = nd->path.dentry->d_inode;
	nd->flags |= LOOKUP_JUMPED;
}

static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
{
	struct inode *inode = link->dentry->d_inode;
	if (inode->i_op->put_link)
		inode->i_op->put_link(link->dentry, nd, cookie);
	path_put(link);
}

int sysctl_protected_symlinks __read_mostly = 0;
int sysctl_protected_hardlinks __read_mostly = 0;

/**
 * may_follow_link - Check symlink following for unsafe situations
 * @link: The path of the symlink
 * @nd: nameidata pathwalk data
 *
 * In the case of the sysctl_protected_symlinks sysctl being enabled,
 * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
 * in a sticky world-writable directory. This is to protect privileged
 * processes from failing races against path names that may change out
 * from under them by way of other users creating malicious symlinks.
 * It will permit symlinks to be followed only when outside a sticky
 * world-writable directory, or when the uid of the symlink and follower
 * match, or when the directory owner matches the symlink's owner.
 *
 * Returns 0 if following the symlink is allowed, -ve on error.
 */
static inline int may_follow_link(struct path *link, struct nameidata *nd)
{
	const struct inode *inode;
	const struct inode *parent;

	if (!sysctl_protected_symlinks)
		return 0;

	/* Allowed if owner and follower match. */
	inode = link->dentry->d_inode;
	if (uid_eq(current_cred()->fsuid, inode->i_uid))
		return 0;

	/* Allowed if parent directory not sticky and world-writable. */
	parent = nd->path.dentry->d_inode;
	if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
		return 0;

	/* Allowed if parent directory and link owner match. */
	if (uid_eq(parent->i_uid, inode->i_uid))
		return 0;

	audit_log_link_denied("follow_link", link);
	path_put_conditional(link, nd);
	path_put(&nd->path);
	return -EACCES;
}

/**
 * safe_hardlink_source - Check for safe hardlink conditions
 * @inode: the source inode to hardlink from
 *
 * Return false if at least one of the following conditions:
 *    - inode is not a regular file
 *    - inode is setuid
 *    - inode is setgid and group-exec
 *    - access failure for read and write
 *
 * Otherwise returns true.
 */
static bool safe_hardlink_source(struct inode *inode)
{
	umode_t mode = inode->i_mode;

	/* Special files should not get pinned to the filesystem. */
	if (!S_ISREG(mode))
		return false;

	/* Setuid files should not get pinned to the filesystem. */
	if (mode & S_ISUID)
		return false;

	/* Executable setgid files should not get pinned to the filesystem. */
	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
		return false;

	/* Hardlinking to unreadable or unwritable sources is dangerous. */
	if (inode_permission(inode, MAY_READ | MAY_WRITE))
		return false;

	return true;
}

/**
 * may_linkat - Check permissions for creating a hardlink
 * @link: the source to hardlink from
 *
 * Block hardlink when all of:
 *  - sysctl_protected_hardlinks enabled
 *  - fsuid does not match inode
 *  - hardlink source is unsafe (see safe_hardlink_source() above)
 *  - not CAP_FOWNER
 *
 * Returns 0 if successful, -ve on error.
 */
static int may_linkat(struct path *link)
{
	const struct cred *cred;
	struct inode *inode;

	if (!sysctl_protected_hardlinks)
		return 0;

	cred = current_cred();
	inode = link->dentry->d_inode;

	/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
	 * otherwise, it must be a safe source.
	 */
	if (uid_eq(cred->fsuid, inode->i_uid) || safe_hardlink_source(inode) ||
	    capable(CAP_FOWNER))
		return 0;

	audit_log_link_denied("linkat", link);
	return -EPERM;
}

static __always_inline int
follow_link(struct path *link, struct nameidata *nd, void **p)
{
	struct dentry *dentry = link->dentry;
	int error;
	char *s;

	BUG_ON(nd->flags & LOOKUP_RCU);

	if (link->mnt == nd->path.mnt)
		mntget(link->mnt);

	error = -ELOOP;
	if (unlikely(current->total_link_count >= 40))
		goto out_put_nd_path;

	cond_resched();
	current->total_link_count++;

	touch_atime(link);
	nd_set_link(nd, NULL);

	error = security_inode_follow_link(link->dentry, nd);
	if (error)
		goto out_put_nd_path;

	nd->last_type = LAST_BIND;
	*p = dentry->d_inode->i_op->follow_link(dentry, nd);
	error = PTR_ERR(*p);
	if (IS_ERR(*p))
		goto out_put_nd_path;

	error = 0;
	s = nd_get_link(nd);
	if (s) {
		error = __vfs_follow_link(nd, s);
		if (unlikely(error))
			put_link(nd, link, *p);
	}

	return error;

out_put_nd_path:
	*p = NULL;
	path_put(&nd->path);
	path_put(link);
	return error;
}

static int follow_up_rcu(struct path *path)
{
	struct mount *mnt = real_mount(path->mnt);
	struct mount *parent;
	struct dentry *mountpoint;

	parent = mnt->mnt_parent;
	if (&parent->mnt == path->mnt)
		return 0;
	mountpoint = mnt->mnt_mountpoint;
	path->dentry = mountpoint;
	path->mnt = &parent->mnt;
	return 1;
}

/*
 * follow_up - Find the mountpoint of path's vfsmount
 *
 * Given a path, find the mountpoint of its source file system.
 * Replace @path with the path of the mountpoint in the parent mount.
 * Up is towards /.
 *
 * Return 1 if we went up a level and 0 if we were already at the
 * root.
 */
int follow_up(struct path *path)
{
	struct mount *mnt = real_mount(path->mnt);
	struct mount *parent;
	struct dentry *mountpoint;

	br_read_lock(&vfsmount_lock);
	parent = mnt->mnt_parent;
	if (parent == mnt) {
		br_read_unlock(&vfsmount_lock);
		return 0;
	}
	mntget(&parent->mnt);
	mountpoint = dget(mnt->mnt_mountpoint);
	br_read_unlock(&vfsmount_lock);
	dput(path->dentry);
	path->dentry = mountpoint;
	mntput(path->mnt);
	path->mnt = &parent->mnt;
	return 1;
}

/*
 * Perform an automount
 * - return -EISDIR to tell follow_managed() to stop and return the path we
 *   were called with.
 */
static int follow_automount(struct path *path, unsigned flags,
			    bool *need_mntput)
{
	struct vfsmount *mnt;
	int err;

	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
		return -EREMOTE;

	/* We don't want to mount if someone's just doing a stat -
	 * unless they're stat'ing a directory and appended a '/' to
	 * the name.
	 *
	 * We do, however, want to mount if someone wants to open or
	 * create a file of any type under the mountpoint, wants to
	 * traverse through the mountpoint or wants to open the
	 * mounted directory.  Also, autofs may mark negative dentries
	 * as being automount points.  These will need the attentions
	 * of the daemon to instantiate them before they can be used.
	 */
	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
	    path->dentry->d_inode)
		return -EISDIR;

	current->total_link_count++;
	if (current->total_link_count >= 40)
		return -ELOOP;

	mnt = path->dentry->d_op->d_automount(path);
	if (IS_ERR(mnt)) {
		/*
		 * The filesystem is allowed to return -EISDIR here to indicate
		 * it doesn't want to automount.  For instance, autofs would do
		 * this so that its userspace daemon can mount on this dentry.
		 *
		 * However, we can only permit this if it's a terminal point in
		 * the path being looked up; if it wasn't then the remainder of
		 * the path is inaccessible and we should say so.
		 */
		if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_PARENT))
			return -EREMOTE;
		return PTR_ERR(mnt);
	}

	if (!mnt) /* mount collision */
		return 0;

	if (!*need_mntput) {
		/* lock_mount() may release path->mnt on error */
		mntget(path->mnt);
		*need_mntput = true;
	}
	err = finish_automount(mnt, path);

	switch (err) {
	case -EBUSY:
		/* Someone else made a mount here whilst we were busy */
		return 0;
	case 0:
		path_put(path);
		path->mnt = mnt;
		path->dentry = dget(mnt->mnt_root);
		return 0;
	default:
		return err;
	}

}

/*
 * Handle a dentry that is managed in some way.
 * - Flagged for transit management (autofs)
 * - Flagged as mountpoint
 * - Flagged as automount point
 *
 * This may only be called in refwalk mode.
 *
 * Serialization is taken care of in namespace.c
 */
static int follow_managed(struct path *path, unsigned flags)
{
	struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
	unsigned managed;
	bool need_mntput = false;
	int ret = 0;

	/* Given that we're not holding a lock here, we retain the value in a
	 * local variable for each dentry as we look at it so that we don't see
	 * the components of that value change under us */
	while (managed = ACCESS_ONCE(path->dentry->d_flags),
	       managed &= DCACHE_MANAGED_DENTRY,
	       unlikely(managed != 0)) {
		/* Allow the filesystem to manage the transit without i_mutex
		 * being held. */
		if (managed & DCACHE_MANAGE_TRANSIT) {
			BUG_ON(!path->dentry->d_op);
			BUG_ON(!path->dentry->d_op->d_manage);
			ret = path->dentry->d_op->d_manage(path->dentry, false);
			if (ret < 0)
				break;
		}

		/* Transit to a mounted filesystem. */
		if (managed & DCACHE_MOUNTED) {
			struct vfsmount *mounted = lookup_mnt(path);
			if (mounted) {
				dput(path->dentry);
				if (need_mntput)
					mntput(path->mnt);
				path->mnt = mounted;
				path->dentry = dget(mounted->mnt_root);
				need_mntput = true;
				continue;
			}

			/* Something is mounted on this dentry in another
			 * namespace and/or whatever was mounted there in this
			 * namespace got unmounted before we managed to get the
			 * vfsmount_lock */
		}

		/* Handle an automount point */
		if (managed & DCACHE_NEED_AUTOMOUNT) {
			ret = follow_automount(path, flags, &need_mntput);
			if (ret < 0)
				break;
			continue;
		}

		/* We didn't change the current path point */
		break;
	}

	if (need_mntput && path->mnt == mnt)
		mntput(path->mnt);
	if (ret == -EISDIR)
		ret = 0;
	return ret < 0 ? ret : need_mntput;
}

int follow_down_one(struct path *path)
{
	struct vfsmount *mounted;

	mounted = lookup_mnt(path);
	if (mounted) {
		dput(path->dentry);
		mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
		return 1;
	}
	return 0;
}

static inline bool managed_dentry_might_block(struct dentry *dentry)
{
	return (dentry->d_flags & DCACHE_MANAGE_TRANSIT &&
		dentry->d_op->d_manage(dentry, true) < 0);
}

/*
 * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
 * we meet a managed dentry that would need blocking.
 */
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
			       struct inode **inode)
{
	for (;;) {
		struct mount *mounted;
		/*
		 * Don't forget we might have a non-mountpoint managed dentry
		 * that wants to block transit.
		 */
		if (unlikely(managed_dentry_might_block(path->dentry)))
			return false;

		if (!d_mountpoint(path->dentry))
			break;

		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
		if (!mounted)
			break;
		path->mnt = &mounted->mnt;
		path->dentry = mounted->mnt.mnt_root;
		nd->flags |= LOOKUP_JUMPED;
		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
		/*
		 * Update the inode too. We don't need to re-check the
		 * dentry sequence number here after this d_inode read,
		 * because a mount-point is always pinned.
		 */
		*inode = path->dentry->d_inode;
	}
	return true;
}

static void follow_mount_rcu(struct nameidata *nd)
{
	while (d_mountpoint(nd->path.dentry)) {
		struct mount *mounted;
		mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
		if (!mounted)
			break;
		nd->path.mnt = &mounted->mnt;
		nd->path.dentry = mounted->mnt.mnt_root;
		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
	}
}

static int follow_dotdot_rcu(struct nameidata *nd)
{
	set_root_rcu(nd);

	while (1) {
		if (nd->path.dentry == nd->root.dentry &&
		    nd->path.mnt == nd->root.mnt) {
			break;
		}
		if (nd->path.dentry != nd->path.mnt->mnt_root) {
			struct dentry *old = nd->path.dentry;
			struct dentry *parent = old->d_parent;
			unsigned seq;

			seq = read_seqcount_begin(&parent->d_seq);
			if (read_seqcount_retry(&old->d_seq, nd->seq))
				goto failed;
			nd->path.dentry = parent;
			nd->seq = seq;
			break;
		}
		if (!follow_up_rcu(&nd->path))
			break;
		nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
	}
	follow_mount_rcu(nd);
	nd->inode = nd->path.dentry->d_inode;
	return 0;

failed:
	nd->flags &= ~LOOKUP_RCU;
	if (!(nd->flags & LOOKUP_ROOT))
		nd->root.mnt = NULL;
	unlock_rcu_walk();
	return -ECHILD;
}

/*
 * Follow down to the covering mount currently visible to userspace.  At each
 * point, the filesystem owning that dentry may be queried as to whether the
 * caller is permitted to proceed or not.
 */
int follow_down(struct path *path)
{
	unsigned managed;
	int ret;

	while (managed = ACCESS_ONCE(path->dentry->d_flags),
	       unlikely(managed & DCACHE_MANAGED_DENTRY)) {
		/* Allow the filesystem to manage the transit without i_mutex
		 * being held.
		 *
		 * We indicate to the filesystem if someone is trying to mount
		 * something here.  This gives autofs the chance to deny anyone
		 * other than its daemon the right to mount on its
		 * superstructure.
		 *
		 * The filesystem may sleep at this point.
		 */
		if (managed & DCACHE_MANAGE_TRANSIT) {
			BUG_ON(!path->dentry->d_op);
			BUG_ON(!path->dentry->d_op->d_manage);
			ret = path->dentry->d_op->d_manage(
				path->dentry, false);
			if (ret < 0)
				return ret == -EISDIR ? 0 : ret;
		}

		/* Transit to a mounted filesystem. */
		if (managed & DCACHE_MOUNTED) {
			struct vfsmount *mounted = lookup_mnt(path);
			if (!mounted)
				break;
			dput(path->dentry);
			mntput(path->mnt);
			path->mnt = mounted;
			path->dentry = dget(mounted->mnt_root);
			continue;
		}

		/* Don't handle automount points here */
		break;
	}
	return 0;
}

/*
 * Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
 */
static void follow_mount(struct path *path)
{
	while (d_mountpoint(path->dentry)) {
		struct vfsmount *mounted = lookup_mnt(path);
		if (!mounted)
			break;
		dput(path->dentry);
		mntput(path->mnt);
		path->mnt = mounted;
		path->dentry = dget(mounted->mnt_root);
	}
}

static void follow_dotdot(struct nameidata *nd)
{
	set_root(nd);

	while(1) {
		struct dentry *old = nd->path.dentry;

		if (nd->path.dentry == nd->root.dentry &&
		    nd->path.mnt == nd->root.mnt) {
			break;
		}
		if (nd->path.dentry != nd->path.mnt->mnt_root) {
			/* rare case of legitimate dget_parent()... */
			nd->path.dentry = dget_parent(nd->path.dentry);
			dput(old);
			break;
		}
		if (!follow_up(&nd->path))
			break;
	}
	follow_mount(&nd->path);
	nd->inode = nd->path.dentry->d_inode;
}

/*
 * This looks up the name in dcache, possibly revalidates the old dentry and
 * allocates a new one if not found or not valid.  In the need_lookup argument
 * returns whether i_op->lookup is necessary.
 *
 * dir->d_inode->i_mutex must be held
 */
static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
				    unsigned int flags, bool *need_lookup)
{
	struct dentry *dentry;
	int error;

	*need_lookup = false;
	dentry = d_lookup(dir, name);
	if (dentry) {
		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
			error = d_revalidate(dentry, flags);
			if (unlikely(error <= 0)) {
				if (error < 0) {
					dput(dentry);
					return ERR_PTR(error);
				} else if (!d_invalidate(dentry)) {
					dput(dentry);
					dentry = NULL;
				}
			}
		}
	}

	if (!dentry) {
		dentry = d_alloc(dir, name);
		if (unlikely(!dentry))
			return ERR_PTR(-ENOMEM);

		*need_lookup = true;
	}
	return dentry;
}

/*
 * Call i_op->lookup on the dentry.  The dentry must be negative but may be
 * hashed if it was pouplated with DCACHE_NEED_LOOKUP.
 *
 * dir->d_inode->i_mutex must be held
 */
static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
				  unsigned int flags)
{
	struct dentry *old;

	/* Don't create child dentry for a dead directory. */
	if (unlikely(IS_DEADDIR(dir))) {
		dput(dentry);
		return ERR_PTR(-ENOENT);
	}

	old = dir->i_op->lookup(dir, dentry, flags);
	if (unlikely(old)) {
		dput(dentry);
		dentry = old;
	}
	return dentry;
}

static struct dentry *__lookup_hash(struct qstr *name,
		struct dentry *base, unsigned int flags)
{
	bool need_lookup;
	struct dentry *dentry;

	dentry = lookup_dcache(name, base, flags, &need_lookup);
	if (!need_lookup)
		return dentry;

	return lookup_real(base->d_inode, dentry, flags);
}

/*
 *  It's more convoluted than I'd like it to be, but... it's still fairly
 *  small and for now I'd prefer to have fast path as straight as possible.
 *  It _is_ time-critical.
 */
static int lookup_fast(struct nameidata *nd,
		       struct path *path, struct inode **inode)
{
	struct vfsmount *mnt = nd->path.mnt;
	struct dentry *dentry, *parent = nd->path.dentry;
	int need_reval = 1;
	int status = 1;
	int err;

	/*
	 * Rename seqlock is not required here because in the off chance
	 * of a false negative due to a concurrent rename, we're going to
	 * do the non-racy lookup, below.
	 */
	if (nd->flags & LOOKUP_RCU) {
		unsigned seq;
		dentry = __d_lookup_rcu(parent, &nd->last, &seq, nd->inode);
		if (!dentry)
			goto unlazy;

		/*
		 * This sequence count validates that the inode matches
		 * the dentry name information from lookup.
		 */
		*inode = dentry->d_inode;
		if (read_seqcount_retry(&dentry->d_seq, seq))
			return -ECHILD;

		/*
		 * This sequence count validates that the parent had no
		 * changes while we did the lookup of the dentry above.
		 *
		 * The memory barrier in read_seqcount_begin of child is
		 *  enough, we can use __read_seqcount_retry here.
		 */
		if (__read_seqcount_retry(&parent->d_seq, nd->seq))
			return -ECHILD;
		nd->seq = seq;

		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
			status = d_revalidate(dentry, nd->flags);
			if (unlikely(status <= 0)) {
				if (status != -ECHILD)
					need_reval = 0;
				goto unlazy;
			}
		}
		path->mnt = mnt;
		path->dentry = dentry;
		if (unlikely(!__follow_mount_rcu(nd, path, inode)))
			goto unlazy;
		if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
			goto unlazy;
		return 0;
unlazy:
		if (unlazy_walk(nd, dentry))
			return -ECHILD;
	} else {
		dentry = __d_lookup(parent, &nd->last);
	}

	if (unlikely(!dentry))
		goto need_lookup;

	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
		status = d_revalidate(dentry, nd->flags);
	if (unlikely(status <= 0)) {
		if (status < 0) {
			dput(dentry);
			return status;
		}
		if (!d_invalidate(dentry)) {
			dput(dentry);
			goto need_lookup;
		}
	}

	path->mnt = mnt;
	path->dentry = dentry;
	err = follow_managed(path, nd->flags);
	if (unlikely(err < 0)) {
		path_put_conditional(path, nd);
		return err;
	}
	if (err)
		nd->flags |= LOOKUP_JUMPED;
	*inode = path->dentry->d_inode;
	return 0;

need_lookup:
	return 1;
}

/* Fast lookup failed, do it the slow way */
static int lookup_slow(struct nameidata *nd, struct path *path)
{
	struct dentry *dentry, *parent;
	int err;

	parent = nd->path.dentry;
	BUG_ON(nd->inode != parent->d_inode);

	mutex_lock(&parent->d_inode->i_mutex);
	dentry = __lookup_hash(&nd->last, parent, nd->flags);
	mutex_unlock(&parent->d_inode->i_mutex);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	path->mnt = nd->path.mnt;
	path->dentry = dentry;
	err = follow_managed(path, nd->flags);
	if (unlikely(err < 0)) {
		path_put_conditional(path, nd);
		return err;
	}
	if (err)
		nd->flags |= LOOKUP_JUMPED;
	return 0;
}

static inline int may_lookup(struct nameidata *nd)
{
	if (nd->flags & LOOKUP_RCU) {
		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
		if (err != -ECHILD)
			return err;
		if (unlazy_walk(nd, NULL))
			return -ECHILD;
	}
	return inode_permission(nd->inode, MAY_EXEC);
}

static inline int handle_dots(struct nameidata *nd, int type)
{
	if (type == LAST_DOTDOT) {
		if (nd->flags & LOOKUP_RCU) {
			if (follow_dotdot_rcu(nd))
				return -ECHILD;
		} else
			follow_dotdot(nd);
	}
	return 0;
}

static void terminate_walk(struct nameidata *nd)
{
	if (!(nd->flags & LOOKUP_RCU)) {
		path_put(&nd->path);
	} else {
		nd->flags &= ~LOOKUP_RCU;
		if (!(nd->flags & LOOKUP_ROOT))
			nd->root.mnt = NULL;
		unlock_rcu_walk();
	}
}

/*
 * Do we need to follow links? We _really_ want to be able
 * to do this check without having to look at inode->i_op,
 * so we keep a cache of "no, this doesn't need follow_link"
 * for the common case.
 */
static inline int should_follow_link(struct inode *inode, int follow)
{
	if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
		if (likely(inode->i_op->follow_link))
			return follow;

		/* This gets set once for the inode lifetime */
		spin_lock(&inode->i_lock);
		inode->i_opflags |= IOP_NOFOLLOW;
		spin_unlock(&inode->i_lock);
	}
	return 0;
}

static inline int walk_component(struct nameidata *nd, struct path *path,
		int follow)
{
	struct inode *inode;
	int err;
	/*
	 * "." and ".." are special - ".." especially so because it has
	 * to be able to know about the current root directory and
	 * parent relationships.
	 */
	if (unlikely(nd->last_type != LAST_NORM))
		return handle_dots(nd, nd->last_type);
	err = lookup_fast(nd, path, &inode);
	if (unlikely(err)) {
		if (err < 0)
			goto out_err;

		err = lookup_slow(nd, path);
		if (err < 0)
			goto out_err;

		inode = path->dentry->d_inode;
	}
	err = -ENOENT;
	if (!inode)
		goto out_path_put;

	if (should_follow_link(inode, follow)) {
		if (nd->flags & LOOKUP_RCU) {
			if (unlikely(unlazy_walk(nd, path->dentry))) {
				err = -ECHILD;
				goto out_err;
			}
		}
		BUG_ON(inode != path->dentry->d_inode);
		return 1;
	}
	path_to_nameidata(path, nd);
	nd->inode = inode;
	return 0;

out_path_put:
	path_to_nameidata(path, nd);
out_err:
	terminate_walk(nd);
	return err;
}

/*
 * This limits recursive symlink follows to 8, while
 * limiting consecutive symlinks to 40.
 *
 * Without that kind of total limit, nasty chains of consecutive
 * symlinks can cause almost arbitrarily long lookups.
 */
static inline int nested_symlink(struct path *path, struct nameidata *nd)
{
	int res;

	if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
		path_put_conditional(path, nd);
		path_put(&nd->path);
		return -ELOOP;
	}
	BUG_ON(nd->depth >= MAX_NESTED_LINKS);

	nd->depth++;
	current->link_count++;

	do {
		struct path link = *path;
		void *cookie;

		res = follow_link(&link, nd, &cookie);
		if (res)
			break;
		res = walk_component(nd, path, LOOKUP_FOLLOW);
		put_link(nd, &link, cookie);
	} while (res > 0);

	current->link_count--;
	nd->depth--;
	return res;
}

/*
 * We really don't want to look at inode->i_op->lookup
 * when we don't have to. So we keep a cache bit in
 * the inode ->i_opflags field that says "yes, we can
 * do lookup on this inode".
 */
static inline int can_lookup(struct inode *inode)
{
	if (likely(inode->i_opflags & IOP_LOOKUP))
		return 1;
	if (likely(!inode->i_op->lookup))
		return 0;

	/* We do this once for the lifetime of the inode */
	spin_lock(&inode->i_lock);
	inode->i_opflags |= IOP_LOOKUP;
	spin_unlock(&inode->i_lock);
	return 1;
}

/*
 * We can do the critical dentry name comparison and hashing
 * operations one word at a time, but we are limited to:
 *
 * - Architectures with fast unaligned word accesses. We could
 *   do a "get_unaligned()" if this helps and is sufficiently
 *   fast.
 *
 * - Little-endian machines (so that we can generate the mask
 *   of low bytes efficiently). Again, we *could* do a byte
 *   swapping load on big-endian architectures if that is not
 *   expensive enough to make the optimization worthless.
 *
 * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
 *   do not trap on the (extremely unlikely) case of a page
 *   crossing operation.
 *
 * - Furthermore, we need an efficient 64-bit compile for the
 *   64-bit case in order to generate the "number of bytes in
 *   the final mask". Again, that could be replaced with a
 *   efficient population count instruction or similar.
 */
#ifdef CONFIG_DCACHE_WORD_ACCESS

#include <asm/word-at-a-time.h>

#ifdef CONFIG_64BIT

static inline unsigned int fold_hash(unsigned long hash)
{
	hash += hash >> (8*sizeof(int));
	return hash;
}

#else	/* 32-bit case */

#define fold_hash(x) (x)

#endif

unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
	unsigned long a, mask;
	unsigned long hash = 0;

	for (;;) {
		a = load_unaligned_zeropad(name);
		if (len < sizeof(unsigned long))
			break;
		hash += a;
		hash *= 9;
		name += sizeof(unsigned long);
		len -= sizeof(unsigned long);
		if (!len)
			goto done;
	}
	mask = ~(~0ul << len*8);
	hash += mask & a;
done:
	return fold_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);

/*
 * Calculate the length and hash of the path component, and
 * return the length of the component;
 */
static inline unsigned long hash_name(const char *name, unsigned int *hashp)
{
	unsigned long a, b, adata, bdata, mask, hash, len;
	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;

	hash = a = 0;
	len = -sizeof(unsigned long);
	do {
		hash = (hash + a) * 9;
		len += sizeof(unsigned long);
		a = load_unaligned_zeropad(name+len);
		b = a ^ REPEAT_BYTE('/');
	} while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));

	adata = prep_zero_mask(a, adata, &constants);
	bdata = prep_zero_mask(b, bdata, &constants);

	mask = create_zero_mask(adata | bdata);

	hash += a & zero_bytemask(mask);
	*hashp = fold_hash(hash);

	return len + find_zero(mask);
}

#else

unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
	unsigned long hash = init_name_hash();
	while (len--)
		hash = partial_name_hash(*name++, hash);
	return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);

/*
 * We know there's a real path component here of at least
 * one character.
 */
static inline unsigned long hash_name(const char *name, unsigned int *hashp)
{
	unsigned long hash = init_name_hash();
	unsigned long len = 0, c;

	c = (unsigned char)*name;
	do {
		len++;
		hash = partial_name_hash(c, hash);
		c = (unsigned char)name[len];
	} while (c && c != '/');
	*hashp = end_name_hash(hash);
	return len;
}

#endif

/*
 * Name resolution.
 * This is the basic name resolution function, turning a pathname into
 * the final dentry. We expect 'base' to be positive and a directory.
 *
 * Returns 0 and nd will have valid dentry and mnt on success.
 * Returns error and drops reference to input namei data on failure.
 */
static int link_path_walk(const char *name, struct nameidata *nd)
{
	struct path next;
	int err;
	
	while (*name=='/')
		name++;
	if (!*name)
		return 0;

	/* At this point we know we have a real path component. */
	for(;;) {
		struct qstr this;
		long len;
		int type;

		err = may_lookup(nd);
 		if (err)
			break;

		len = hash_name(name, &this.hash);
		this.name = name;
		this.len = len;

		type = LAST_NORM;
		if (name[0] == '.') switch (len) {
			case 2:
				if (name[1] == '.') {
					type = LAST_DOTDOT;
					nd->flags |= LOOKUP_JUMPED;
				}
				break;
			case 1:
				type = LAST_DOT;
		}
		if (likely(type == LAST_NORM)) {
			struct dentry *parent = nd->path.dentry;
			nd->flags &= ~LOOKUP_JUMPED;
			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
				err = parent->d_op->d_hash(parent, nd->inode,
							   &this);
				if (err < 0)
					break;
			}
		}

		nd->last = this;
		nd->last_type = type;

		if (!name[len])
			return 0;
		/*
		 * If it wasn't NUL, we know it was '/'. Skip that
		 * slash, and continue until no more slashes.
		 */
		do {
			len++;
		} while (unlikely(name[len] == '/'));
		if (!name[len])
			return 0;

		name += len;

		err = walk_component(nd, &next, LOOKUP_FOLLOW);
		if (err < 0)
			return err;

		if (err) {
			err = nested_symlink(&next, nd);
			if (err)
				return err;
		}
		if (!can_lookup(nd->inode)) {
			err = -ENOTDIR; 
			break;
		}
	}
	terminate_walk(nd);
	return err;
}

static int path_init(int dfd, const char *name, unsigned int flags,
		     struct nameidata *nd, struct file **fp)
{
	int retval = 0;

	nd->last_type = LAST_ROOT; /* if there are only slashes... */
	nd->flags = flags | LOOKUP_JUMPED;
	nd->depth = 0;
	if (flags & LOOKUP_ROOT) {
		struct inode *inode = nd->root.dentry->d_inode;
		if (*name) {
			if (!can_lookup(inode))
				return -ENOTDIR;
			retval = inode_permission(inode, MAY_EXEC);
			if (retval)
				return retval;
		}
		nd->path = nd->root;
		nd->inode = inode;
		if (flags & LOOKUP_RCU) {
			lock_rcu_walk();
			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
		} else {
			path_get(&nd->path);
		}
		return 0;
	}

	nd->root.mnt = NULL;

	if (*name=='/') {
		if (flags & LOOKUP_RCU) {
			lock_rcu_walk();
			set_root_rcu(nd);
		} else {
			set_root(nd);
			path_get(&nd->root);
		}
		nd->path = nd->root;
	} else if (dfd == AT_FDCWD) {
		if (flags & LOOKUP_RCU) {
			struct fs_struct *fs = current->fs;
			unsigned seq;

			lock_rcu_walk();

			do {
				seq = read_seqcount_begin(&fs->seq);
				nd->path = fs->pwd;
				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			} while (read_seqcount_retry(&fs->seq, seq));
		} else {
			get_fs_pwd(current->fs, &nd->path);
		}
	} else {
		/* Caller must check execute permissions on the starting path component */
		struct fd f = fdget_raw(dfd);
		struct dentry *dentry;

		if (!f.file)
			return -EBADF;

		dentry = f.file->f_path.dentry;

		if (*name) {
			if (!can_lookup(dentry->d_inode)) {
				fdput(f);
				return -ENOTDIR;
			}
		}

		nd->path = f.file->f_path;
		if (flags & LOOKUP_RCU) {
			if (f.need_put)
				*fp = f.file;
			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
			lock_rcu_walk();
		} else {
			path_get(&nd->path);
			fdput(f);
		}
	}

	nd->inode = nd->path.dentry->d_inode;
	return 0;
}

static inline int lookup_last(struct nameidata *nd, struct path *path)
{
	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;

	nd->flags &= ~LOOKUP_PARENT;
	return walk_component(nd, path, nd->flags & LOOKUP_FOLLOW);
}

/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(int dfd, const char *name,
				unsigned int flags, struct nameidata *nd)
{
	struct file *base = NULL;
	struct path path;
	int err;

	/*
	 * Path walking is largely split up into 2 different synchronisation
	 * schemes, rcu-walk and ref-walk (explained in
	 * Documentation/filesystems/path-lookup.txt). These share much of the
	 * path walk code, but some things particularly setup, cleanup, and
	 * following mounts are sufficiently divergent that functions are
	 * duplicated. Typically there is a function foo(), and its RCU
	 * analogue, foo_rcu().
	 *
	 * -ECHILD is the error number of choice (just to avoid clashes) that
	 * is returned if some aspect of an rcu-walk fails. Such an error must
	 * be handled by restarting a traditional ref-walk (which will always


context:
space:
mode: