aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_iget.c
blob: bf4dc5eb4cfc77c673c6843ec1ad1c12fb808182 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
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
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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_quota.h"
#include "xfs_utils.h"
#include "xfs_trans_priv.h"
#include "xfs_inode_item.h"

/*
 * Check the validity of the inode we just found it the cache
 */
static int
xfs_iget_cache_hit(
	struct xfs_perag	*pag,
	struct xfs_inode	*ip,
	int			flags,
	int			lock_flags) __releases(pag->pag_ici_lock)
{
	struct xfs_mount	*mp = ip->i_mount;
	int			error = EAGAIN;

	/*
	 * If INEW is set this inode is being set up
	 * If IRECLAIM is set this inode is being torn down
	 * Pause and try again.
	 */
	if (xfs_iflags_test(ip, (XFS_INEW|XFS_IRECLAIM))) {
		XFS_STATS_INC(xs_ig_frecycle);
		goto out_error;
	}

	/* If IRECLAIMABLE is set, we've torn down the vfs inode part */
	if (xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {

		/*
		 * If lookup is racing with unlink, then we should return an
		 * error immediately so we don't remove it from the reclaim
		 * list and potentially leak the inode.
		 */
		if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
			error = ENOENT;
			goto out_error;
		}

		xfs_itrace_exit_tag(ip, "xfs_iget.alloc");

		/*
		 * We need to re-initialise the VFS inode as it has been
		 * 'freed' by the VFS. Do this here so we can deal with
		 * errors cleanly, then tag it so it can be set up correctly
		 * later.
		 */
		if (!inode_init_always(mp->m_super, VFS_I(ip))) {
			error = ENOMEM;
			goto out_error;
		}

		/*
		 * We must set the XFS_INEW flag before clearing the
		 * XFS_IRECLAIMABLE flag so that if a racing lookup does
		 * not find the XFS_IRECLAIMABLE above but has the igrab()
		 * below succeed we can safely check XFS_INEW to detect
		 * that this inode is still being initialised.
		 */
		xfs_iflags_set(ip, XFS_INEW);
		xfs_iflags_clear(ip, XFS_IRECLAIMABLE);

		/* clear the radix tree reclaim flag as well. */
		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
	} else if (!igrab(VFS_I(ip))) {
		/* If the VFS inode is being torn down, pause and try again. */
		XFS_STATS_INC(xs_ig_frecycle);
		goto out_error;
	} else if (xfs_iflags_test(ip, XFS_INEW)) {
		/*
		 * We are racing with another cache hit that is
		 * currently recycling this inode out of the XFS_IRECLAIMABLE
		 * state. Wait for the initialisation to complete before
		 * continuing.
		 */
		wait_on_inode(VFS_I(ip));
	}

	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
		error = ENOENT;
		iput(VFS_I(ip));
		goto out_error;
	}

	/* We've got a live one. */
	read_unlock(&pag->pag_ici_lock);

	if (lock_flags != 0)
		xfs_ilock(ip, lock_flags);

	xfs_iflags_clear(ip, XFS_ISTALE);
	xfs_itrace_exit_tag(ip, "xfs_iget.found");
	XFS_STATS_INC(xs_ig_found);
	return 0;

out_error:
	read_unlock(&pag->pag_ici_lock);
	return error;
}


static int
xfs_iget_cache_miss(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	xfs_trans_t		*tp,
	xfs_ino_t		ino,
	struct xfs_inode	**ipp,
	xfs_daddr_t		bno,
	int			flags,
	int			lock_flags) __releases(pag->pag_ici_lock)
{
	struct xfs_inode	*ip;
	int			error;
	unsigned long		first_index, mask;
	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);

	/*
	 * Read the disk inode attributes into a new inode structure and get
	 * a new vnode for it. This should also initialize i_ino and i_mount.
	 */
	error = xfs_iread(mp, tp, ino, &ip, bno,
			  (flags & XFS_IGET_BULKSTAT) ? XFS_IMAP_BULKSTAT : 0);
	if (error)
		return error;

	xfs_itrace_exit_tag(ip, "xfs_iget.alloc");

	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
		error = ENOENT;
		goto out_destroy;
	}

	if (lock_flags)
		xfs_ilock(ip, lock_flags);

	/*
	 * Preload the radix tree so we can insert safely under the
	 * write spinlock. Note that we cannot sleep inside the preload
	 * region.
	 */
	if (radix_tree_preload(GFP_KERNEL)) {
		error = EAGAIN;
		goto out_unlock;
	}

	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
	first_index = agino & mask;
	write_lock(&pag->pag_ici_lock);

	/* insert the new inode */
	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
	if (unlikely(error)) {
		WARN_ON(error != -EEXIST);
		XFS_STATS_INC(xs_ig_dup);
		error = EAGAIN;
		goto out_preload_end;
	}

	/* These values _must_ be set before releasing the radix tree lock! */
	ip->i_udquot = ip->i_gdquot = NULL;
	xfs_iflags_set(ip, XFS_INEW);

	write_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
	*ipp = ip;
	return 0;

out_preload_end:
	write_unlock(&pag->pag_ici_lock);
	radix_tree_preload_end();
out_unlock:
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
out_destroy:
	xfs_destroy_inode(ip);
	return error;
}

/*
 * Look up an inode by number in the given file system.
 * The inode is looked up in the cache held in each AG.
 * If the inode is found in the cache, initialise the vfs inode
 * if necessary.
 *
 * If it is not in core, read it in from the file system's device,
 * add it to the cache and initialise the vfs inode.
 *
 * The inode is locked according to the value of the lock_flags parameter.
 * This flag parameter indicates how and if the inode's IO lock and inode lock
 * should be taken.
 *
 * mp -- the mount point structure for the current file system.  It points
 *       to the inode hash table.
 * tp -- a pointer to the current transaction if there is one.  This is
 *       simply passed through to the xfs_iread() call.
 * ino -- the number of the inode desired.  This is the unique identifier
 *        within the file system for the inode being requested.
 * lock_flags -- flags indicating how to lock the inode.  See the comment
 *		 for xfs_ilock() for a list of valid values.
 * bno -- the block number starting the buffer containing the inode,
 *	  if known (as by bulkstat), else 0.
 */
int
xfs_iget(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	uint		flags,
	uint		lock_flags,
	xfs_inode_t	**ipp,
	xfs_daddr_t	bno)
{
	xfs_inode_t	*ip;
	int		error;
	xfs_perag_t	*pag;
	xfs_agino_t	agino;

	/* the radix tree exists only in inode capable AGs */
	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
		return EINVAL;

	/* get the perag structure and ensure that it's inode capable */
	pag = xfs_get_perag(mp, ino);
	if (!pag->pagi_inodeok)
		return EINVAL;
	ASSERT(pag->pag_ici_init);
	agino = XFS_INO_TO_AGINO(mp, ino);

again:
	error = 0;
	read_lock(&pag->pag_ici_lock);
	ip = radix_tree_lookup(&pag->pag_ici_root, agino);

	if (ip) {
		error = xfs_iget_cache_hit(pag, ip, flags, lock_flags);
		if (error)
			goto out_error_or_again;
	} else {
		read_unlock(&pag->pag_ici_lock);
		XFS_STATS_INC(xs_ig_missed);

		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, bno,
							flags, lock_flags);
		if (error)
			goto out_error_or_again;
	}
	xfs_put_perag(mp, pag);

	xfs_iflags_set(ip, XFS_IMODIFIED);
	*ipp = ip;

	ASSERT(ip->i_df.if_ext_max ==
	       XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t));
	/*
	 * If we have a real type for an on-disk inode, we can set ops(&unlock)
	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
	 */
	if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
		xfs_setup_inode(ip);
	return 0;

out_error_or_again:
	if (error == EAGAIN) {
		delay(1);
		goto again;
	}
	xfs_put_perag(mp, pag);
	return error;
}


/*
 * Look for the inode corresponding to the given ino in the hash table.
 * If it is there and its i_transp pointer matches tp, return it.
 * Otherwise, return NULL.
 */
xfs_inode_t *
xfs_inode_incore(xfs_mount_t	*mp,
		 xfs_ino_t	ino,
		 xfs_trans_t	*tp)
{
	xfs_inode_t	*ip;
	xfs_perag_t	*pag;

	pag = xfs_get_perag(mp, ino);
	read_lock(&pag->pag_ici_lock);
	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ino));
	read_unlock(&pag->pag_ici_lock);
	xfs_put_perag(mp, pag);

	/* the returned inode must match the transaction */
	if (ip && (ip->i_transp != tp))
		return NULL;
	return ip;
}

/*
 * Decrement reference count of an inode structure and unlock it.
 *
 * ip -- the inode being released
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be released.  See the comment on xfs_iunlock() for a list
 *	 of valid values.
 */
void
xfs_iput(xfs_inode_t	*ip,
	 uint		lock_flags)
{
	xfs_itrace_entry(ip);
	xfs_iunlock(ip, lock_flags);
	IRELE(ip);
}

/*
 * Special iput for brand-new inodes that are still locked
 */
void
xfs_iput_new(
	xfs_inode_t	*ip,
	uint		lock_flags)
{
	struct inode	*inode = VFS_I(ip);

	xfs_itrace_entry(ip);

	if ((ip->i_d.di_mode == 0)) {
		ASSERT(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
		make_bad_inode(inode);
	}
	if (inode->i_state & I_NEW)
		unlock_new_inode(inode);
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
	IRELE(ip);
}


/*
 * This routine embodies the part of the reclaim code that pulls
 * the inode from the inode hash table and the mount structure's
 * inode list.
 * This should only be called from xfs_reclaim().
 */
void
xfs_ireclaim(xfs_inode_t *ip)
{
	/*
	 * Remove from old hash list and mount list.
	 */
	XFS_STATS_INC(xs_ig_reclaims);

	xfs_iextract(ip);

	/*
	 * Here we do a spurious inode lock in order to coordinate with inode
	 * cache radix tree lookups.  This is because the lookup can reference
	 * the inodes in the cache without taking references.  We make that OK
	 * here by ensuring that we wait until the inode is unlocked after the
	 * lookup before we go ahead and free it.  We get both the ilock and
	 * the iolock because the code may need to drop the ilock one but will
	 * still hold the iolock.
	 */
	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);

	/*
	 * Release dquots (and their references) if any. An inode may escape
	 * xfs_inactive and get here via vn_alloc->vn_reclaim path.
	 */
	XFS_QM_DQDETACH(ip->i_mount, ip);

	/*
	 * Free all memory associated with the inode.
	 */
	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_idestroy(ip);
}

/*
 * This routine removes an about-to-be-destroyed inode from
 * all of the lists in which it is located with the exception
 * of the behavior chain.
 */
void
xfs_iextract(
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_perag_t	*pag = xfs_get_perag(mp, ip->i_ino);

	write_lock(&pag->pag_ici_lock);
	radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino));
	write_unlock(&pag->pag_ici_lock);
	xfs_put_perag(mp, pag);

	mp->m_ireclaims++;
}

/*
 * This is a wrapper routine around the xfs_ilock() routine
 * used to centralize some grungy code.  It is used in places
 * that wish to lock the inode solely for reading the extents.
 * The reason these places can't just call xfs_ilock(SHARED)
 * is that the inode lock also guards to bringing in of the
 * extents from disk for a file in b-tree format.  If the inode
 * is in b-tree format, then we need to lock the inode exclusively
 * until the extents are read in.  Locking it exclusively all
 * the time would limit our parallelism unnecessarily, though.
 * What we do instead is check to see if the extents have been
 * read in yet, and only lock the inode exclusively if they
 * have not.
 *
 * The function returns a value which should be given to the
 * corresponding xfs_iunlock_map_shared().  This value is
 * the mode in which the lock was actually taken.
 */
uint
xfs_ilock_map_shared(
	xfs_inode_t	*ip)
{
	uint	lock_mode;

	if ((ip->i_d.di_format == XFS_DINODE_FMT_BTREE) &&
	    ((ip->i_df.if_flags & XFS_IFEXTENTS) == 0)) {
		lock_mode = XFS_ILOCK_EXCL;
	} else {
		lock_mode = XFS_ILOCK_SHARED;
	}

	xfs_ilock(ip, lock_mode);

	return lock_mode;
}

/*
 * This is simply the unlock routine to go with xfs_ilock_map_shared().
 * All it does is call xfs_iunlock() with the given lock_mode.
 */
void
xfs_iunlock_map_shared(
	xfs_inode_t	*ip,
	unsigned int	lock_mode)
{
	xfs_iunlock(ip, lock_mode);
}

/*
 * The xfs inode contains 2 locks: a multi-reader lock called the
 * i_iolock and a multi-reader lock called the i_lock.  This routine
 * allows either or both of the locks to be obtained.
 *
 * The 2 locks should always be ordered so that the IO lock is
 * obtained first in order to prevent deadlock.
 *
 * ip -- the inode being locked
 * lock_flags -- this parameter indicates the inode's locks
 *       to be locked.  It can be:
 *		XFS_IOLOCK_SHARED,
 *		XFS_IOLOCK_EXCL,
 *		XFS_ILOCK_SHARED,
 *		XFS_ILOCK_EXCL,
 *		XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED,
 *		XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL,
 *		XFS_IOLOCK_EXCL | XFS_ILOCK_SHARED,
 *		XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL
 */
void
xfs_ilock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);

	if (lock_flags & XFS_IOLOCK_EXCL)
		mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
	else if (lock_flags & XFS_IOLOCK_SHARED)
		mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));

	if (lock_flags & XFS_ILOCK_EXCL)
		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
	else if (lock_flags & XFS_ILOCK_SHARED)
		mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));

	xfs_ilock_trace(ip, 1, lock_flags, (inst_t *)__return_address);
}

/*
 * This is just like xfs_ilock(), except that the caller
 * is guaranteed not to sleep.  It returns 1 if it gets
 * the requested locks and 0 otherwise.  If the IO lock is
 * obtained but the inode lock cannot be, then the IO lock
 * is dropped before returning.
 *
 * ip -- the inode being locked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be locked.  See the comment for xfs_ilock() for a list
 *	 of valid values.
 */
int
xfs_ilock_nowait(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);

	if (lock_flags & XFS_IOLOCK_EXCL) {
		if (!mrtryupdate(&ip->i_iolock))
			goto out;
	} else if (lock_flags & XFS_IOLOCK_SHARED) {
		if (!mrtryaccess(&ip->i_iolock))
			goto out;
	}
	if (lock_flags & XFS_ILOCK_EXCL) {
		if (!mrtryupdate(&ip->i_lock))
			goto out_undo_iolock;
	} else if (lock_flags & XFS_ILOCK_SHARED) {
		if (!mrtryaccess(&ip->i_lock))
			goto out_undo_iolock;
	}
	xfs_ilock_trace(ip, 2, lock_flags, (inst_t *)__return_address);
	return 1;

 out_undo_iolock:
	if (lock_flags & XFS_IOLOCK_EXCL)
		mrunlock_excl(&ip->i_iolock);
	else if (lock_flags & XFS_IOLOCK_SHARED)
		mrunlock_shared(&ip->i_iolock);
 out:
	return 0;
}

/*
 * xfs_iunlock() is used to drop the inode locks acquired with
 * xfs_ilock() and xfs_ilock_nowait().  The caller must pass
 * in the flags given to xfs_ilock() or xfs_ilock_nowait() so
 * that we know which locks to drop.
 *
 * ip -- the inode being unlocked
 * lock_flags -- this parameter indicates the inode's locks to be
 *       to be unlocked.  See the comment for xfs_ilock() for a list
 *	 of valid values for this parameter.
 *
 */
void
xfs_iunlock(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	/*
	 * You can't set both SHARED and EXCL for the same lock,
	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
	 */
	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_IUNLOCK_NONOTIFY |
			XFS_LOCK_DEP_MASK)) == 0);
	ASSERT(lock_flags != 0);

	if (lock_flags & XFS_IOLOCK_EXCL)
		mrunlock_excl(&ip->i_iolock);
	else if (lock_flags & XFS_IOLOCK_SHARED)
		mrunlock_shared(&ip->i_iolock);

	if (lock_flags & XFS_ILOCK_EXCL)
		mrunlock_excl(&ip->i_lock);
	else if (lock_flags & XFS_ILOCK_SHARED)
		mrunlock_shared(&ip->i_lock);

	if ((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) &&
	    !(lock_flags & XFS_IUNLOCK_NONOTIFY) && ip->i_itemp) {
		/*
		 * Let the AIL know that this item has been unlocked in case
		 * it is in the AIL and anyone is waiting on it.  Don't do
		 * this if the caller has asked us not to.
		 */
		xfs_trans_unlocked_item(ip->i_itemp->ili_item.li_ailp,
					(xfs_log_item_t*)(ip->i_itemp));
	}
	xfs_ilock_trace(ip, 3, lock_flags, (inst_t *)__return_address);
}

/*
 * give up write locks.  the i/o lock cannot be held nested
 * if it is being demoted.
 */
void
xfs_ilock_demote(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL));
	ASSERT((lock_flags & ~(XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);

	if (lock_flags & XFS_ILOCK_EXCL)
		mrdemote(&ip->i_lock);
	if (lock_flags & XFS_IOLOCK_EXCL)
		mrdemote(&ip->i_iolock);
}

#ifdef DEBUG
/*
 * Debug-only routine, without additional rw_semaphore APIs, we can
 * now only answer requests regarding whether we hold the lock for write
 * (reader state is outside our visibility, we only track writer state).
 *
 * Note: this means !xfs_isilocked would give false positives, so don't do that.
 */
int
xfs_isilocked(
	xfs_inode_t		*ip,
	uint			lock_flags)
{
	if ((lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) ==
			XFS_ILOCK_EXCL) {
		if (!ip->i_lock.mr_writer)
			return 0;
	}

	if ((lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) ==
			XFS_IOLOCK_EXCL) {
		if (!ip->i_iolock.mr_writer)
			return 0;
	}

	return 1;
}
#endif