aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_inode_item.c
blob: 378081109844b09b2bbfd07dcb4214027fefe2c2 (plain)
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
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
/*
 * Copyright (c) 2000-2002,2005 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_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_trans_priv.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_error.h"
#include "xfs_trace.h"


kmem_zone_t	*xfs_ili_zone;		/* inode log item zone */

static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
{
	return container_of(lip, struct xfs_inode_log_item, ili_item);
}


/*
 * This returns the number of iovecs needed to log the given inode item.
 *
 * We need one iovec for the inode log format structure, one for the
 * inode core, and possibly one for the inode data/extents/b-tree root
 * and one for the inode attribute data/extents/b-tree root.
 */
STATIC void
xfs_inode_item_size(
	struct xfs_log_item	*lip,
	int			*nvecs,
	int			*nbytes)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;

	*nvecs += 2;
	*nbytes += sizeof(struct xfs_inode_log_format) +
		   xfs_icdinode_size(ip->i_d.di_version);

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		if ((iip->ili_fields & XFS_ILOG_DEXT) &&
		    ip->i_d.di_nextents > 0 &&
		    ip->i_df.if_bytes > 0) {
			/* worst case, doesn't subtract delalloc extents */
			*nbytes += XFS_IFORK_DSIZE(ip);
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
		    ip->i_df.if_broot_bytes > 0) {
			*nbytes += ip->i_df.if_broot_bytes;
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
		    ip->i_df.if_bytes > 0) {
			*nbytes += roundup(ip->i_df.if_bytes, 4);
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_DEV:
	case XFS_DINODE_FMT_UUID:
		break;

	default:
		ASSERT(0);
		break;
	}

	if (!XFS_IFORK_Q(ip))
		return;


	/*
	 * Log any necessary attribute data.
	 */
	switch (ip->i_d.di_aformat) {
	case XFS_DINODE_FMT_EXTENTS:
		if ((iip->ili_fields & XFS_ILOG_AEXT) &&
		    ip->i_d.di_anextents > 0 &&
		    ip->i_afp->if_bytes > 0) {
			/* worst case, doesn't subtract unused space */
			*nbytes += XFS_IFORK_ASIZE(ip);
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
		    ip->i_afp->if_broot_bytes > 0) {
			*nbytes += ip->i_afp->if_broot_bytes;
			*nvecs += 1;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
		    ip->i_afp->if_bytes > 0) {
			*nbytes += roundup(ip->i_afp->if_bytes, 4);
			*nvecs += 1;
		}
		break;

	default:
		ASSERT(0);
		break;
	}
}

/*
 * xfs_inode_item_format_extents - convert in-core extents to on-disk form
 *
 * For either the data or attr fork in extent format, we need to endian convert
 * the in-core extent as we place them into the on-disk inode. In this case, we
 * need to do this conversion before we write the extents into the log. Because
 * we don't have the disk inode to write into here, we allocate a buffer and
 * format the extents into it via xfs_iextents_copy(). We free the buffer in
 * the unlock routine after the copy for the log has been made.
 *
 * In the case of the data fork, the in-core and on-disk fork sizes can be
 * different due to delayed allocation extents. We only log on-disk extents
 * here, so always use the physical fork size to determine the size of the
 * buffer we need to allocate.
 */
STATIC void
xfs_inode_item_format_extents(
	struct xfs_inode	*ip,
	struct xfs_log_iovec	*vecp,
	int			whichfork,
	int			type)
{
	xfs_bmbt_rec_t		*ext_buffer;

	ext_buffer = kmem_alloc(XFS_IFORK_SIZE(ip, whichfork), KM_SLEEP);
	if (whichfork == XFS_DATA_FORK)
		ip->i_itemp->ili_extents_buf = ext_buffer;
	else
		ip->i_itemp->ili_aextents_buf = ext_buffer;

	vecp->i_addr = ext_buffer;
	vecp->i_len = xfs_iextents_copy(ip, ext_buffer, whichfork);
	vecp->i_type = type;
}

/*
 * This is called to fill in the vector of log iovecs for the
 * given inode log item.  It fills the first item with an inode
 * log format structure, the second with the on-disk inode structure,
 * and a possible third and/or fourth with the inode data/extents/b-tree
 * root and inode attributes data/extents/b-tree root.
 */
STATIC void
xfs_inode_item_format(
	struct xfs_log_item	*lip,
	struct xfs_log_iovec	*vecp)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	uint			nvecs;
	size_t			data_bytes;
	xfs_mount_t		*mp;

	vecp->i_addr = &iip->ili_format;
	vecp->i_len  = sizeof(xfs_inode_log_format_t);
	vecp->i_type = XLOG_REG_TYPE_IFORMAT;
	vecp++;
	nvecs	     = 1;

	vecp->i_addr = &ip->i_d;
	vecp->i_len  = xfs_icdinode_size(ip->i_d.di_version);
	vecp->i_type = XLOG_REG_TYPE_ICORE;
	vecp++;
	nvecs++;

	/*
	 * If this is really an old format inode, then we need to
	 * log it as such.  This means that we have to copy the link
	 * count from the new field to the old.  We don't have to worry
	 * about the new fields, because nothing trusts them as long as
	 * the old inode version number is there.  If the superblock already
	 * has a new version number, then we don't bother converting back.
	 */
	mp = ip->i_mount;
	ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb));
	if (ip->i_d.di_version == 1) {
		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
			/*
			 * Convert it back.
			 */
			ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
			ip->i_d.di_onlink = ip->i_d.di_nlink;
		} else {
			/*
			 * The superblock version has already been bumped,
			 * so just make the conversion to the new inode
			 * format permanent.
			 */
			ip->i_d.di_version = 2;
			ip->i_d.di_onlink = 0;
			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
		}
	}

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);

		if ((iip->ili_fields & XFS_ILOG_DEXT) &&
		    ip->i_d.di_nextents > 0 &&
		    ip->i_df.if_bytes > 0) {
			ASSERT(ip->i_df.if_u1.if_extents != NULL);
			ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0);
			ASSERT(iip->ili_extents_buf == NULL);

#ifdef XFS_NATIVE_HOST
                       if (ip->i_d.di_nextents == ip->i_df.if_bytes /
                                               (uint)sizeof(xfs_bmbt_rec_t)) {
				/*
				 * There are no delayed allocation
				 * extents, so just point to the
				 * real extents array.
				 */
				vecp->i_addr = ip->i_df.if_u1.if_extents;
				vecp->i_len = ip->i_df.if_bytes;
				vecp->i_type = XLOG_REG_TYPE_IEXT;
			} else
#endif
			{
				xfs_inode_item_format_extents(ip, vecp,
					XFS_DATA_FORK, XLOG_REG_TYPE_IEXT);
			}
			ASSERT(vecp->i_len <= ip->i_df.if_bytes);
			iip->ili_format.ilf_dsize = vecp->i_len;
			vecp++;
			nvecs++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_DEXT;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);

		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
		    ip->i_df.if_broot_bytes > 0) {
			ASSERT(ip->i_df.if_broot != NULL);
			vecp->i_addr = ip->i_df.if_broot;
			vecp->i_len = ip->i_df.if_broot_bytes;
			vecp->i_type = XLOG_REG_TYPE_IBROOT;
			vecp++;
			nvecs++;
			iip->ili_format.ilf_dsize = ip->i_df.if_broot_bytes;
		} else {
			ASSERT(!(iip->ili_fields &
				 XFS_ILOG_DBROOT));
			iip->ili_fields &= ~XFS_ILOG_DBROOT;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		iip->ili_fields &=
			~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEV | XFS_ILOG_UUID);
		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
		    ip->i_df.if_bytes > 0) {
			ASSERT(ip->i_df.if_u1.if_data != NULL);
			ASSERT(ip->i_d.di_size > 0);

			vecp->i_addr = ip->i_df.if_u1.if_data;
			/*
			 * Round i_bytes up to a word boundary.
			 * The underlying memory is guaranteed to
			 * to be there by xfs_idata_realloc().
			 */
			data_bytes = roundup(ip->i_df.if_bytes, 4);
			ASSERT((ip->i_df.if_real_bytes == 0) ||
			       (ip->i_df.if_real_bytes == data_bytes));
			vecp->i_len = (int)data_bytes;
			vecp->i_type = XLOG_REG_TYPE_ILOCAL;
			vecp++;
			nvecs++;
			iip->ili_format.ilf_dsize = (unsigned)data_bytes;
		} else {
			iip->ili_fields &= ~XFS_ILOG_DDATA;
		}
		break;

	case XFS_DINODE_FMT_DEV:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEXT | XFS_ILOG_UUID);
		if (iip->ili_fields & XFS_ILOG_DEV) {
			iip->ili_format.ilf_u.ilfu_rdev =
				ip->i_df.if_u2.if_rdev;
		}
		break;

	case XFS_DINODE_FMT_UUID:
		iip->ili_fields &=
			~(XFS_ILOG_DDATA | XFS_ILOG_DBROOT |
			  XFS_ILOG_DEXT | XFS_ILOG_DEV);
		if (iip->ili_fields & XFS_ILOG_UUID) {
			iip->ili_format.ilf_u.ilfu_uuid =
				ip->i_df.if_u2.if_uuid;
		}
		break;

	default:
		ASSERT(0);
		break;
	}

	/*
	 * If there are no attributes associated with the file, then we're done.
	 */
	if (!XFS_IFORK_Q(ip)) {
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT | XFS_ILOG_AEXT);
		goto out;
	}

	switch (ip->i_d.di_aformat) {
	case XFS_DINODE_FMT_EXTENTS:
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_ABROOT);

		if ((iip->ili_fields & XFS_ILOG_AEXT) &&
		    ip->i_d.di_anextents > 0 &&
		    ip->i_afp->if_bytes > 0) {
			ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) ==
				ip->i_d.di_anextents);
			ASSERT(ip->i_afp->if_u1.if_extents != NULL);
#ifdef XFS_NATIVE_HOST
			/*
			 * There are not delayed allocation extents
			 * for attributes, so just point at the array.
			 */
			vecp->i_addr = ip->i_afp->if_u1.if_extents;
			vecp->i_len = ip->i_afp->if_bytes;
			vecp->i_type = XLOG_REG_TYPE_IATTR_EXT;
#else
			ASSERT(iip->ili_aextents_buf == NULL);
			xfs_inode_item_format_extents(ip, vecp,
					XFS_ATTR_FORK, XLOG_REG_TYPE_IATTR_EXT);
#endif
			iip->ili_format.ilf_asize = vecp->i_len;
			vecp++;
			nvecs++;
		} else {
			iip->ili_fields &= ~XFS_ILOG_AEXT;
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		iip->ili_fields &=
			~(XFS_ILOG_ADATA | XFS_ILOG_AEXT);

		if ((iip->ili_fields & XFS_ILOG_ABROOT) &&
		    ip->i_afp->if_broot_bytes > 0) {
			ASSERT(ip->i_afp->if_broot != NULL);

			vecp->i_addr = ip->i_afp->if_broot;
			vecp->i_len = ip->i_afp->if_broot_bytes;
			vecp->i_type = XLOG_REG_TYPE_IATTR_BROOT;
			vecp++;
			nvecs++;
			iip->ili_format.ilf_asize = ip->i_afp->if_broot_bytes;
		} else {
			iip->ili_fields &= ~XFS_ILOG_ABROOT;
		}
		break;

	case XFS_DINODE_FMT_LOCAL:
		iip->ili_fields &=
			~(XFS_ILOG_AEXT | XFS_ILOG_ABROOT);

		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
		    ip->i_afp->if_bytes > 0) {
			ASSERT(ip->i_afp->if_u1.if_data != NULL);

			vecp->i_addr = ip->i_afp->if_u1.if_data;
			/*
			 * Round i_bytes up to a word boundary.
			 * The underlying memory is guaranteed to
			 * to be there by xfs_idata_realloc().
			 */
			data_bytes = roundup(ip->i_afp->if_bytes, 4);
			ASSERT((ip->i_afp->if_real_bytes == 0) ||
			       (ip->i_afp->if_real_bytes == data_bytes));
			vecp->i_len = (int)data_bytes;
			vecp->i_type = XLOG_REG_TYPE_IATTR_LOCAL;
			vecp++;
			nvecs++;
			iip->ili_format.ilf_asize = (unsigned)data_bytes;
		} else {
			iip->ili_fields &= ~XFS_ILOG_ADATA;
		}
		break;

	default:
		ASSERT(0);
		break;
	}

out:
	/*
	 * Now update the log format that goes out to disk from the in-core
	 * values.  We always write the inode core to make the arithmetic
	 * games in recovery easier, which isn't a big deal as just about any
	 * transaction would dirty it anyway.
	 */
	iip->ili_format.ilf_fields = XFS_ILOG_CORE |
		(iip->ili_fields & ~XFS_ILOG_TIMESTAMP);
	iip->ili_format.ilf_size = nvecs;
}


/*
 * This is called to pin the inode associated with the inode log
 * item in memory so it cannot be written out.
 */
STATIC void
xfs_inode_item_pin(
	struct xfs_log_item	*lip)
{
	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

	trace_xfs_inode_pin(ip, _RET_IP_);
	atomic_inc(&ip->i_pincount);
}


/*
 * This is called to unpin the inode associated with the inode log
 * item which was previously pinned with a call to xfs_inode_item_pin().
 *
 * Also wake up anyone in xfs_iunpin_wait() if the count goes to 0.
 */
STATIC void
xfs_inode_item_unpin(
	struct xfs_log_item	*lip,
	int			remove)
{
	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;

	trace_xfs_inode_unpin(ip, _RET_IP_);
	ASSERT(atomic_read(&ip->i_pincount) > 0);
	if (atomic_dec_and_test(&ip->i_pincount))
		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
}

STATIC uint
xfs_inode_item_push(
	struct xfs_log_item	*lip,
	struct list_head	*buffer_list)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	struct xfs_buf		*bp = NULL;
	uint			rval = XFS_ITEM_SUCCESS;
	int			error;

	if (xfs_ipincount(ip) > 0)
		return XFS_ITEM_PINNED;

	if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
		return XFS_ITEM_LOCKED;

	/*
	 * Re-check the pincount now that we stabilized the value by
	 * taking the ilock.
	 */
	if (xfs_ipincount(ip) > 0) {
		rval = XFS_ITEM_PINNED;
		goto out_unlock;
	}

	/*
	 * Stale inode items should force out the iclog.
	 */
	if (ip->i_flags & XFS_ISTALE) {
		rval = XFS_ITEM_PINNED;
		goto out_unlock;
	}

	/*
	 * Someone else is already flushing the inode.  Nothing we can do
	 * here but wait for the flush to finish and remove the item from
	 * the AIL.
	 */
	if (!xfs_iflock_nowait(ip)) {
		rval = XFS_ITEM_FLUSHING;
		goto out_unlock;
	}

	ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
	ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));

	spin_unlock(&lip->li_ailp->xa_lock);

	error = xfs_iflush(ip, &bp);
	if (!error) {
		if (!xfs_buf_delwri_queue(bp, buffer_list))
			rval = XFS_ITEM_FLUSHING;
		xfs_buf_relse(bp);
	}

	spin_lock(&lip->li_ailp->xa_lock);
out_unlock:
	xfs_iunlock(ip, XFS_ILOCK_SHARED);
	return rval;
}

/*
 * Unlock the inode associated with the inode log item.
 * Clear the fields of the inode and inode log item that
 * are specific to the current transaction.  If the
 * hold flags is set, do not unlock the inode.
 */
STATIC void
xfs_inode_item_unlock(
	struct xfs_log_item	*lip)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;
	unsigned short		lock_flags;

	ASSERT(ip->i_itemp != NULL);
	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

	/*
	 * If the inode needed a separate buffer with which to log
	 * its extents, then free it now.
	 */
	if (iip->ili_extents_buf != NULL) {
		ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS);
		ASSERT(ip->i_d.di_nextents > 0);
		ASSERT(iip->ili_fields & XFS_ILOG_DEXT);
		ASSERT(ip->i_df.if_bytes > 0);
		kmem_free(iip->ili_extents_buf);
		iip->ili_extents_buf = NULL;
	}
	if (iip->ili_aextents_buf != NULL) {
		ASSERT(ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS);
		ASSERT(ip->i_d.di_anextents > 0);
		ASSERT(iip->ili_fields & XFS_ILOG_AEXT);
		ASSERT(ip->i_afp->if_bytes > 0);
		kmem_free(iip->ili_aextents_buf);
		iip->ili_aextents_buf = NULL;
	}

	lock_flags = iip->ili_lock_flags;
	iip->ili_lock_flags = 0;
	if (lock_flags)
		xfs_iunlock(ip, lock_flags);
}

/*
 * This is called to find out where the oldest active copy of the inode log
 * item in the on disk log resides now that the last log write of it completed
 * at the given lsn.  Since we always re-log all dirty data in an inode, the
 * latest copy in the on disk log is the only one that matters.  Therefore,
 * simply return the given lsn.
 *
 * If the inode has been marked stale because the cluster is being freed, we
 * don't want to (re-)insert this inode into the AIL. There is a race condition
 * where the cluster buffer may be unpinned before the inode is inserted into
 * the AIL during transaction committed processing. If the buffer is unpinned
 * before the inode item has been committed and inserted, then it is possible
 * for the buffer to be written and IO completes before the inode is inserted
 * into the AIL. In that case, we'd be inserting a clean, stale inode into the
 * AIL which will never get removed. It will, however, get reclaimed which
 * triggers an assert in xfs_inode_free() complaining about freein an inode
 * still in the AIL.
 *
 * To avoid this, just unpin the inode directly and return a LSN of -1 so the
 * transaction committed code knows that it does not need to do any further
 * processing on the item.
 */
STATIC xfs_lsn_t
xfs_inode_item_committed(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
	struct xfs_inode	*ip = iip->ili_inode;

	if (xfs_iflags_test(ip, XFS_ISTALE)) {
		xfs_inode_item_unpin(lip, 0);
		return -1;
	}
	return lsn;
}

/*
 * XXX rcc - this one really has to do something.  Probably needs
 * to stamp in a new field in the incore inode.
 */
STATIC void
xfs_inode_item_committing(
	struct xfs_log_item	*lip,
	xfs_lsn_t		lsn)
{
	INODE_ITEM(lip)->ili_last_lsn = lsn;
}

/*
 * This is the ops vector shared by all buf log items.
 */
static const struct xfs_item_ops xfs_inode_item_ops = {
	.iop_size	= xfs_inode_item_size,
	.iop_format	= xfs_inode_item_format,
	.iop_pin	= xfs_inode_item_pin,
	.iop_unpin	= xfs_inode_item_unpin,
	.iop_unlock	= xfs_inode_item_unlock,
	.iop_committed	= xfs_inode_item_committed,
	.iop_push	= xfs_inode_item_push,
	.iop_committing = xfs_inode_item_committing
};


/*
 * Initialize the inode log item for a newly allocated (in-core) inode.
 */
void
xfs_inode_item_init(
	struct xfs_inode	*ip,
	struct xfs_mount	*mp)
{
	struct xfs_inode_log_item *iip;

	ASSERT(ip->i_itemp == NULL);
	iip = ip->i_itemp = kmem_zone_zalloc(xfs_ili_zone, KM_SLEEP);

	iip->ili_inode = ip;
	xfs_log_item_init(mp, &iip->ili_item, XFS_LI_INODE,
						&xfs_inode_item_ops);
	iip->ili_format.ilf_type = XFS_LI_INODE;
	iip->ili_format.ilf_ino = ip->i_ino;
	iip->ili_format.ilf_blkno = ip->i_imap.im_blkno;
	iip->ili_format.ilf_len = ip->i_imap.im_len;
	iip->ili_format.ilf_boffset = ip->i_imap.im_boffset;
}

/*
 * Free the inode log item and any memory hanging off of it.
 */
void
xfs_inode_item_destroy(
	xfs_inode_t	*ip)
{
	kmem_zone_free(xfs_ili_zone, ip->i_itemp);
}


/*
 * This is the inode flushing I/O completion routine.  It is called
 * from interrupt level when the buffer containing the inode is
 * flushed to disk.  It is responsible for removing the inode item
 * from the AIL if it has not been re-logged, and unlocking the inode's
 * flush lock.
 *
 * To reduce AIL lock traffic as much as possible, we scan the buffer log item
 * list for other inodes that will run this function. We remove them from the
 * buffer list so we can process all the inode IO completions in one AIL lock
 * traversal.
 */
void
xfs_iflush_done(
	struct xfs_buf		*bp,
	struct xfs_log_item	*lip)
{
	struct xfs_inode_log_item *iip;
	struct xfs_log_item	*blip;
	struct xfs_log_item	*next;
	struct xfs_log_item	*prev;
	struct xfs_ail		*ailp = lip->li_ailp;
	int			need_ail = 0;

	/*
	 * Scan the buffer IO completions for other inodes being completed and
	 * attach them to the current inode log item.
	 */
	blip = bp->b_fspriv;
	prev = NULL;
	while (blip != NULL) {
		if (lip->li_cb != xfs_iflush_done) {
			prev = blip;
			blip = blip->li_bio_list;
			continue;
		}

		/* remove from list */
		next = blip->li_bio_list;
		if (!prev) {
			bp->b_fspriv = next;
		} else {
			prev->li_bio_list = next;
		}

		/* add to current list */
		blip->li_bio_list = lip->li_bio_list;
		lip->li_bio_list = blip;

		/*
		 * while we have the item, do the unlocked check for needing
		 * the AIL lock.
		 */
		iip = INODE_ITEM(blip);
		if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn)
			need_ail++;

		blip = next;
	}

	/* make sure we capture the state of the initial inode. */
	iip = INODE_ITEM(lip);
	if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn)
		need_ail++;

	/*
	 * We only want to pull the item from the AIL if it is
	 * actually there and its location in the log has not
	 * changed since we started the flush.  Thus, we only bother
	 * if the ili_logged flag is set and the inode's lsn has not
	 * changed.  First we check the lsn outside
	 * the lock since it's cheaper, and then we recheck while
	 * holding the lock before removing the inode from the AIL.
	 */
	if (need_ail) {
		struct xfs_log_item *log_items[need_ail];
		int i = 0;
		spin_lock(&ailp->xa_lock);
		for (blip = lip; blip; blip = blip->li_bio_list) {
			iip = INODE_ITEM(blip);
			if (iip->ili_logged &&
			    blip->li_lsn == iip->ili_flush_lsn) {
				log_items[i++] = blip;
			}
			ASSERT(i <= need_ail);
		}
		/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
		xfs_trans_ail_delete_bulk(ailp, log_items, i,
					  SHUTDOWN_CORRUPT_INCORE);
	}


	/*
	 * clean up and unlock the flush lock now we are done. We can clear the
	 * ili_last_fields bits now that we know that the data corresponding to
	 * them is safely on disk.
	 */
	for (blip = lip; blip; blip = next) {
		next = blip->li_bio_list;
		blip->li_bio_list = NULL;

		iip = INODE_ITEM(blip);
		iip->ili_logged = 0;
		iip->ili_last_fields = 0;
		xfs_ifunlock(iip->ili_inode);
	}
}

/*
 * This is the inode flushing abort routine.  It is called from xfs_iflush when
 * the filesystem is shutting down to clean up the inode state.  It is
 * responsible for removing the inode item from the AIL if it has not been
 * re-logged, and unlocking the inode's flush lock.
 */
void
xfs_iflush_abort(
	xfs_inode_t		*ip,
	bool			stale)
{
	xfs_inode_log_item_t	*iip = ip->i_itemp;

	if (iip) {
		struct xfs_ail	*ailp = iip->ili_item.li_ailp;
		if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
			spin_lock(&ailp->xa_lock);
			if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
				/* xfs_trans_ail_delete() drops the AIL lock. */
				xfs_trans_ail_delete(ailp, &iip->ili_item,
						stale ?
						     SHUTDOWN_LOG_IO_ERROR :
						     SHUTDOWN_CORRUPT_INCORE);
			} else
				spin_unlock(&ailp->xa_lock);
		}
		iip->ili_logged = 0;
		/*
		 * Clear the ili_last_fields bits now that we know that the
		 * data corresponding to them is safely on disk.
		 */
		iip->ili_last_fields = 0;
		/*
		 * Clear the inode logging fields so no more flushes are
		 * attempted.
		 */
		iip->ili_fields = 0;
	}
	/*
	 * Release the inode's flush lock since we're done with it.
	 */
	xfs_ifunlock(ip);
}

void
xfs_istale_done(
	struct xfs_buf		*bp,
	struct xfs_log_item	*lip)
{
	xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true);
}

/*
 * convert an xfs_inode_log_format struct from either 32 or 64 bit versions
 * (which can have different field alignments) to the native version
 */
int
xfs_inode_item_format_convert(
	xfs_log_iovec_t		*buf,
	xfs_inode_log_format_t	*in_f)
{
	if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
		xfs_inode_log_format_32_t *in_f32 = buf->i_addr;

		in_f->ilf_type = in_f32->ilf_type;
		in_f->ilf_size = in_f32->ilf_size;
		in_f->ilf_fields = in_f32->ilf_fields;
		in_f->ilf_asize = in_f32->ilf_asize;
		in_f->ilf_dsize = in_f32->ilf_dsize;
		in_f->ilf_ino = in_f32->ilf_ino;
		/* copy biggest field of ilf_u */
		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
		       in_f32->ilf_u.ilfu_uuid.__u_bits,
		       sizeof(uuid_t));
		in_f->ilf_blkno = in_f32->ilf_blkno;
		in_f->ilf_len = in_f32->ilf_len;
		in_f->ilf_boffset = in_f32->ilf_boffset;
		return 0;
	} else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
		xfs_inode_log_format_64_t *in_f64 = buf->i_addr;

		in_f->ilf_type = in_f64->ilf_type;
		in_f->ilf_size = in_f64->ilf_size;
		in_f->ilf_fields = in_f64->ilf_fields;
		in_f->ilf_asize = in_f64->ilf_asize;
		in_f->ilf_dsize = in_f64->ilf_dsize;
		in_f->ilf_ino = in_f64->ilf_ino;
		/* copy biggest field of ilf_u */
		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
		       in_f64->ilf_u.ilfu_uuid.__u_bits,
		       sizeof(uuid_t));
		in_f->ilf_blkno = in_f64->ilf_blkno;
		in_f->ilf_len = in_f64->ilf_len;
		in_f->ilf_boffset = in_f64->ilf_boffset;
		return 0;
	}
	return EFSCORRUPTED;
}