aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_trans_buf.c
blob: fb586360d1c909da5d1e1231e099b5d8e64f0a67 (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
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
/*
 * 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_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_buf_item.h"
#include "xfs_trans_priv.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_trace.h"


STATIC xfs_buf_t *xfs_trans_buf_item_match(xfs_trans_t *, xfs_buftarg_t *,
		xfs_daddr_t, int);
STATIC xfs_buf_t *xfs_trans_buf_item_match_all(xfs_trans_t *, xfs_buftarg_t *,
		xfs_daddr_t, int);

/*
 * Add the locked buffer to the transaction.
 *
 * The buffer must be locked, and it cannot be associated with any
 * transaction.
 *
 * If the buffer does not yet have a buf log item associated with it,
 * then allocate one for it.  Then add the buf item to the transaction.
 */
STATIC void
_xfs_trans_bjoin(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	int			reset_recur)
{
	struct xfs_buf_log_item	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL);

	/*
	 * The xfs_buf_log_item pointer is stored in b_fsprivate.  If
	 * it doesn't have one yet, then allocate one and initialize it.
	 * The checks to see if one is there are in xfs_buf_item_init().
	 */
	xfs_buf_item_init(bp, tp->t_mountp);
	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
	if (reset_recur)
		bip->bli_recur = 0;

	/*
	 * Take a reference for this transaction on the buf item.
	 */
	atomic_inc(&bip->bli_refcount);

	/*
	 * Get a log_item_desc to point at the new item.
	 */
	(void) xfs_trans_add_item(tp, (xfs_log_item_t *)bip);

	/*
	 * Initialize b_fsprivate2 so we can find it with incore_match()
	 * in xfs_trans_get_buf() and friends above.
	 */
	XFS_BUF_SET_FSPRIVATE2(bp, tp);

}

void
xfs_trans_bjoin(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp)
{
	_xfs_trans_bjoin(tp, bp, 0);
	trace_xfs_trans_bjoin(bp->b_fspriv);
}

/*
 * Get and lock the buffer for the caller if it is not already
 * locked within the given transaction.  If it is already locked
 * within the transaction, just increment its lock recursion count
 * and return a pointer to it.
 *
 * Use the fast path function xfs_trans_buf_item_match() or the buffer
 * cache routine incore_match() to find the buffer
 * if it is already owned by this transaction.
 *
 * If we don't already own the buffer, use get_buf() to get it.
 * If it doesn't yet have an associated xfs_buf_log_item structure,
 * then allocate one and add the item to this transaction.
 *
 * If the transaction pointer is NULL, make this just a normal
 * get_buf() call.
 */
xfs_buf_t *
xfs_trans_get_buf(xfs_trans_t	*tp,
		  xfs_buftarg_t	*target_dev,
		  xfs_daddr_t	blkno,
		  int		len,
		  uint		flags)
{
	xfs_buf_t		*bp;
	xfs_buf_log_item_t	*bip;

	if (flags == 0)
		flags = XBF_LOCK | XBF_MAPPED;

	/*
	 * Default to a normal get_buf() call if the tp is NULL.
	 */
	if (tp == NULL)
		return xfs_buf_get(target_dev, blkno, len,
				   flags | XBF_DONT_BLOCK);

	/*
	 * If we find the buffer in the cache with this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  In this case we just increment the lock
	 * recursion count and return the buffer to the caller.
	 */
	if (tp->t_items.lic_next == NULL) {
		bp = xfs_trans_buf_item_match(tp, target_dev, blkno, len);
	} else {
		bp  = xfs_trans_buf_item_match_all(tp, target_dev, blkno, len);
	}
	if (bp != NULL) {
		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
		if (XFS_FORCED_SHUTDOWN(tp->t_mountp))
			XFS_BUF_SUPER_STALE(bp);

		/*
		 * If the buffer is stale then it was binval'ed
		 * since last read.  This doesn't matter since the
		 * caller isn't allowed to use the data anyway.
		 */
		else if (XFS_BUF_ISSTALE(bp))
			ASSERT(!XFS_BUF_ISDELAYWRITE(bp));

		ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
		bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
		ASSERT(bip != NULL);
		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		bip->bli_recur++;
		trace_xfs_trans_get_buf_recur(bip);
		return (bp);
	}

	/*
	 * We always specify the XBF_DONT_BLOCK flag within a transaction
	 * so that get_buf does not try to push out a delayed write buffer
	 * which might cause another transaction to take place (if the
	 * buffer was delayed alloc).  Such recursive transactions can
	 * easily deadlock with our current transaction as well as cause
	 * us to run out of stack space.
	 */
	bp = xfs_buf_get(target_dev, blkno, len, flags | XBF_DONT_BLOCK);
	if (bp == NULL) {
		return NULL;
	}

	ASSERT(!XFS_BUF_GETERROR(bp));

	_xfs_trans_bjoin(tp, bp, 1);
	trace_xfs_trans_get_buf(bp->b_fspriv);
	return (bp);
}

/*
 * Get and lock the superblock buffer of this file system for the
 * given transaction.
 *
 * We don't need to use incore_match() here, because the superblock
 * buffer is a private buffer which we keep a pointer to in the
 * mount structure.
 */
xfs_buf_t *
xfs_trans_getsb(xfs_trans_t	*tp,
		struct xfs_mount *mp,
		int		flags)
{
	xfs_buf_t		*bp;
	xfs_buf_log_item_t	*bip;

	/*
	 * Default to just trying to lock the superblock buffer
	 * if tp is NULL.
	 */
	if (tp == NULL) {
		return (xfs_getsb(mp, flags));
	}

	/*
	 * If the superblock buffer already has this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  In this case we just increment the lock
	 * recursion count and return the buffer to the caller.
	 */
	bp = mp->m_sb_bp;
	if (XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp) {
		bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*);
		ASSERT(bip != NULL);
		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		bip->bli_recur++;
		trace_xfs_trans_getsb_recur(bip);
		return (bp);
	}

	bp = xfs_getsb(mp, flags);
	if (bp == NULL)
		return NULL;

	_xfs_trans_bjoin(tp, bp, 1);
	trace_xfs_trans_getsb(bp->b_fspriv);
	return (bp);
}

#ifdef DEBUG
xfs_buftarg_t *xfs_error_target;
int	xfs_do_error;
int	xfs_req_num;
int	xfs_error_mod = 33;
#endif

/*
 * Get and lock the buffer for the caller if it is not already
 * locked within the given transaction.  If it has not yet been
 * read in, read it from disk. If it is already locked
 * within the transaction and already read in, just increment its
 * lock recursion count and return a pointer to it.
 *
 * Use the fast path function xfs_trans_buf_item_match() or the buffer
 * cache routine incore_match() to find the buffer
 * if it is already owned by this transaction.
 *
 * If we don't already own the buffer, use read_buf() to get it.
 * If it doesn't yet have an associated xfs_buf_log_item structure,
 * then allocate one and add the item to this transaction.
 *
 * If the transaction pointer is NULL, make this just a normal
 * read_buf() call.
 */
int
xfs_trans_read_buf(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_buftarg_t	*target,
	xfs_daddr_t	blkno,
	int		len,
	uint		flags,
	xfs_buf_t	**bpp)
{
	xfs_buf_t		*bp;
	xfs_buf_log_item_t	*bip;
	int			error;

	if (flags == 0)
		flags = XBF_LOCK | XBF_MAPPED;

	/*
	 * Default to a normal get_buf() call if the tp is NULL.
	 */
	if (tp == NULL) {
		bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
		if (!bp)
			return (flags & XBF_TRYLOCK) ?
					EAGAIN : XFS_ERROR(ENOMEM);

		if (XFS_BUF_GETERROR(bp) != 0) {
			xfs_ioerror_alert("xfs_trans_read_buf", mp,
					  bp, blkno);
			error = XFS_BUF_GETERROR(bp);
			xfs_buf_relse(bp);
			return error;
		}
#ifdef DEBUG
		if (xfs_do_error) {
			if (xfs_error_target == target) {
				if (((xfs_req_num++) % xfs_error_mod) == 0) {
					xfs_buf_relse(bp);
					cmn_err(CE_DEBUG, "Returning error!\n");
					return XFS_ERROR(EIO);
				}
			}
		}
#endif
		if (XFS_FORCED_SHUTDOWN(mp))
			goto shutdown_abort;
		*bpp = bp;
		return 0;
	}

	/*
	 * If we find the buffer in the cache with this transaction
	 * pointer in its b_fsprivate2 field, then we know we already
	 * have it locked.  If it is already read in we just increment
	 * the lock recursion count and return the buffer to the caller.
	 * If the buffer is not yet read in, then we read it in, increment
	 * the lock recursion count, and return it to the caller.
	 */
	if (tp->t_items.lic_next == NULL) {
		bp = xfs_trans_buf_item_match(tp, target, blkno, len);
	} else {
		bp = xfs_trans_buf_item_match_all(tp, target, blkno, len);
	}
	if (bp != NULL) {
		ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
		ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
		ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
		ASSERT((XFS_BUF_ISERROR(bp)) == 0);
		if (!(XFS_BUF_ISDONE(bp))) {
			trace_xfs_trans_read_buf_io(bp, _RET_IP_);
			ASSERT(!XFS_BUF_ISASYNC(bp));
			XFS_BUF_READ(bp);
			xfsbdstrat(tp->t_mountp, bp);
			error = xfs_iowait(bp);
			if (error) {
				xfs_ioerror_alert("xfs_trans_read_buf", mp,
						  bp, blkno);
				xfs_buf_relse(bp);
				/*
				 * We can gracefully recover from most read
				 * errors. Ones we can't are those that happen
				 * after the transaction's already dirty.
				 */
				if (tp->t_flags & XFS_TRANS_DIRTY)
					xfs_force_shutdown(tp->t_mountp,
							SHUTDOWN_META_IO_ERROR);
				return error;
			}
		}
		/*
		 * We never locked this buf ourselves, so we shouldn't
		 * brelse it either. Just get out.
		 */
		if (XFS_FORCED_SHUTDOWN(mp)) {
			trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
			*bpp = NULL;
			return XFS_ERROR(EIO);
		}


		bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*);
		bip->bli_recur++;

		ASSERT(atomic_read(&bip->bli_refcount) > 0);
		trace_xfs_trans_read_buf_recur(bip);
		*bpp = bp;
		return 0;
	}

	/*
	 * We always specify the XBF_DONT_BLOCK flag within a transaction
	 * so that get_buf does not try to push out a delayed write buffer
	 * which might cause another transaction to take place (if the
	 * buffer was delayed alloc).  Such recursive transactions can
	 * easily deadlock with our current transaction as well as cause
	 * us to run out of stack space.
	 */
	bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK);
	if (bp == NULL) {
		*bpp = NULL;
		return 0;
	}
	if (XFS_BUF_GETERROR(bp) != 0) {
	    XFS_BUF_SUPER_STALE(bp);
		error = XFS_BUF_GETERROR(bp);

		xfs_ioerror_alert("xfs_trans_read_buf", mp,
				  bp, blkno);
		if (tp->t_flags & XFS_TRANS_DIRTY)
			xfs_force_shutdown(tp->t_mountp, SHUTDOWN_META_IO_ERROR);
		xfs_buf_relse(bp);
		return error;
	}
#ifdef DEBUG
	if (xfs_do_error && !(tp->t_flags & XFS_TRANS_DIRTY)) {
		if (xfs_error_target == target) {
			if (((xfs_req_num++) % xfs_error_mod) == 0) {
				xfs_force_shutdown(tp->t_mountp,
						   SHUTDOWN_META_IO_ERROR);
				xfs_buf_relse(bp);
				cmn_err(CE_DEBUG, "Returning trans error!\n");
				return XFS_ERROR(EIO);
			}
		}
	}
#endif
	if (XFS_FORCED_SHUTDOWN(mp))
		goto shutdown_abort;

	_xfs_trans_bjoin(tp, bp, 1);
	trace_xfs_trans_read_buf(bp->b_fspriv);

	*bpp = bp;
	return 0;

shutdown_abort:
	/*
	 * the theory here is that buffer is good but we're
	 * bailing out because the filesystem is being forcibly
	 * shut down.  So we should leave the b_flags alone since
	 * the buffer's not staled and just get out.
	 */
#if defined(DEBUG)
	if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
		cmn_err(CE_NOTE, "about to pop assert, bp == 0x%p", bp);
#endif
	ASSERT((XFS_BUF_BFLAGS(bp) & (XBF_STALE|XBF_DELWRI)) !=
				     (XBF_STALE|XBF_DELWRI));

	trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
	xfs_buf_relse(bp);
	*bpp = NULL;
	return XFS_ERROR(EIO);
}


/*
 * Release the buffer bp which was previously acquired with one of the
 * xfs_trans_... buffer allocation routines if the buffer has not
 * been modified within this transaction.  If the buffer is modified
 * within this transaction, do decrement the recursion count but do
 * not release the buffer even if the count goes to 0.  If the buffer is not
 * modified within the transaction, decrement the recursion count and
 * release the buffer if the recursion count goes to 0.
 *
 * If the buffer is to be released and it was not modified before
 * this transaction began, then free the buf_log_item associated with it.
 *
 * If the transaction pointer is NULL, make this just a normal
 * brelse() call.
 */
void
xfs_trans_brelse(xfs_trans_t	*tp,
		 xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;
	xfs_log_item_t		*lip;
	xfs_log_item_desc_t	*lidp;

	/*
	 * Default to a normal brelse() call if the tp is NULL.
	 */
	if (tp == NULL) {
		ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL);
		/*
		 * If there's a buf log item attached to the buffer,
		 * then let the AIL know that the buffer is being
		 * unlocked.
		 */
		if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) {
			lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
			if (lip->li_type == XFS_LI_BUF) {
				bip = XFS_BUF_FSPRIVATE(bp,xfs_buf_log_item_t*);
				xfs_trans_unlocked_item(bip->bli_item.li_ailp,
							lip);
			}
		}
		xfs_buf_relse(bp);
		return;
	}

	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	/*
	 * Find the item descriptor pointing to this buffer's
	 * log item.  It must be there.
	 */
	lidp = xfs_trans_find_item(tp, (xfs_log_item_t*)bip);
	ASSERT(lidp != NULL);

	trace_xfs_trans_brelse(bip);

	/*
	 * If the release is just for a recursive lock,
	 * then decrement the count and return.
	 */
	if (bip->bli_recur > 0) {
		bip->bli_recur--;
		return;
	}

	/*
	 * If the buffer is dirty within this transaction, we can't
	 * release it until we commit.
	 */
	if (lidp->lid_flags & XFS_LID_DIRTY)
		return;

	/*
	 * If the buffer has been invalidated, then we can't release
	 * it until the transaction commits to disk unless it is re-dirtied
	 * as part of this transaction.  This prevents us from pulling
	 * the item from the AIL before we should.
	 */
	if (bip->bli_flags & XFS_BLI_STALE)
		return;

	ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));

	/*
	 * Free up the log item descriptor tracking the released item.
	 */
	xfs_trans_free_item(tp, lidp);

	/*
	 * Clear the hold flag in the buf log item if it is set.
	 * We wouldn't want the next user of the buffer to
	 * get confused.
	 */
	if (bip->bli_flags & XFS_BLI_HOLD) {
		bip->bli_flags &= ~XFS_BLI_HOLD;
	}

	/*
	 * Drop our reference to the buf log item.
	 */
	atomic_dec(&bip->bli_refcount);

	/*
	 * If the buf item is not tracking data in the log, then
	 * we must free it before releasing the buffer back to the
	 * free pool.  Before releasing the buffer to the free pool,
	 * clear the transaction pointer in b_fsprivate2 to dissolve
	 * its relation to this transaction.
	 */
	if (!xfs_buf_item_dirty(bip)) {
/***
		ASSERT(bp->b_pincount == 0);
***/
		ASSERT(atomic_read(&bip->bli_refcount) == 0);
		ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
		ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
		xfs_buf_item_relse(bp);
		bip = NULL;
	}
	XFS_BUF_SET_FSPRIVATE2(bp, NULL);

	/*
	 * If we've still got a buf log item on the buffer, then
	 * tell the AIL that the buffer is being unlocked.
	 */
	if (bip != NULL) {
		xfs_trans_unlocked_item(bip->bli_item.li_ailp,
					(xfs_log_item_t*)bip);
	}

	xfs_buf_relse(bp);
	return;
}

/*
 * Mark the buffer as not needing to be unlocked when the buf item's
 * IOP_UNLOCK() routine is called.  The buffer must already be locked
 * and associated with the given transaction.
 */
/* ARGSUSED */
void
xfs_trans_bhold(xfs_trans_t	*tp,
		xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	bip->bli_flags |= XFS_BLI_HOLD;
	trace_xfs_trans_bhold(bip);
}

/*
 * Cancel the previous buffer hold request made on this buffer
 * for this transaction.
 */
void
xfs_trans_bhold_release(xfs_trans_t	*tp,
			xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
	ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_CANCEL));
	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	ASSERT(bip->bli_flags & XFS_BLI_HOLD);
	bip->bli_flags &= ~XFS_BLI_HOLD;

	trace_xfs_trans_bhold_release(bip);
}

/*
 * This is called to mark bytes first through last inclusive of the given
 * buffer as needing to be logged when the transaction is committed.
 * The buffer must already be associated with the given transaction.
 *
 * First and last are numbers relative to the beginning of this buffer,
 * so the first byte in the buffer is numbered 0 regardless of the
 * value of b_blkno.
 */
void
xfs_trans_log_buf(xfs_trans_t	*tp,
		  xfs_buf_t	*bp,
		  uint		first,
		  uint		last)
{
	xfs_buf_log_item_t	*bip;
	xfs_log_item_desc_t	*lidp;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
	ASSERT((first <= last) && (last < XFS_BUF_COUNT(bp)));
	ASSERT((XFS_BUF_IODONE_FUNC(bp) == NULL) ||
	       (XFS_BUF_IODONE_FUNC(bp) == xfs_buf_iodone_callbacks));

	/*
	 * Mark the buffer as needing to be written out eventually,
	 * and set its iodone function to remove the buffer's buf log
	 * item from the AIL and free it when the buffer is flushed
	 * to disk.  See xfs_buf_attach_iodone() for more details
	 * on li_cb and xfs_buf_iodone_callbacks().
	 * If we end up aborting this transaction, we trap this buffer
	 * inside the b_bdstrat callback so that this won't get written to
	 * disk.
	 */
	XFS_BUF_DELAYWRITE(bp);
	XFS_BUF_DONE(bp);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);
	XFS_BUF_SET_IODONE_FUNC(bp, xfs_buf_iodone_callbacks);
	bip->bli_item.li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*))xfs_buf_iodone;

	trace_xfs_trans_log_buf(bip);

	/*
	 * If we invalidated the buffer within this transaction, then
	 * cancel the invalidation now that we're dirtying the buffer
	 * again.  There are no races with the code in xfs_buf_item_unpin(),
	 * because we have a reference to the buffer this entire time.
	 */
	if (bip->bli_flags & XFS_BLI_STALE) {
		bip->bli_flags &= ~XFS_BLI_STALE;
		ASSERT(XFS_BUF_ISSTALE(bp));
		XFS_BUF_UNSTALE(bp);
		bip->bli_format.blf_flags &= ~XFS_BLI_CANCEL;
	}

	lidp = xfs_trans_find_item(tp, (xfs_log_item_t*)bip);
	ASSERT(lidp != NULL);

	tp->t_flags |= XFS_TRANS_DIRTY;
	lidp->lid_flags |= XFS_LID_DIRTY;
	lidp->lid_flags &= ~XFS_LID_BUF_STALE;
	bip->bli_flags |= XFS_BLI_LOGGED;
	xfs_buf_item_log(bip, first, last);
}


/*
 * This called to invalidate a buffer that is being used within
 * a transaction.  Typically this is because the blocks in the
 * buffer are being freed, so we need to prevent it from being
 * written out when we're done.  Allowing it to be written again
 * might overwrite data in the free blocks if they are reallocated
 * to a file.
 *
 * We prevent the buffer from being written out by clearing the
 * B_DELWRI flag.  We can't always
 * get rid of the buf log item at this point, though, because
 * the buffer may still be pinned by another transaction.  If that
 * is the case, then we'll wait until the buffer is committed to
 * disk for the last time (we can tell by the ref count) and
 * free it in xfs_buf_item_unpin().  Until it is cleaned up we
 * will keep the buffer locked so that the buffer and buf log item
 * are not reused.
 */
void
xfs_trans_binval(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_log_item_desc_t	*lidp;
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	lidp = xfs_trans_find_item(tp, (xfs_log_item_t*)bip);
	ASSERT(lidp != NULL);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	trace_xfs_trans_binval(bip);

	if (bip->bli_flags & XFS_BLI_STALE) {
		/*
		 * If the buffer is already invalidated, then
		 * just return.
		 */
		ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
		ASSERT(XFS_BUF_ISSTALE(bp));
		ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
		ASSERT(!(bip->bli_format.blf_flags & XFS_BLI_INODE_BUF));
		ASSERT(bip->bli_format.blf_flags & XFS_BLI_CANCEL);
		ASSERT(lidp->lid_flags & XFS_LID_DIRTY);
		ASSERT(tp->t_flags & XFS_TRANS_DIRTY);
		return;
	}

	/*
	 * Clear the dirty bit in the buffer and set the STALE flag
	 * in the buf log item.  The STALE flag will be used in
	 * xfs_buf_item_unpin() to determine if it should clean up
	 * when the last reference to the buf item is given up.
	 * We set the XFS_BLI_CANCEL flag in the buf log format structure
	 * and log the buf item.  This will be used at recovery time
	 * to determine that copies of the buffer in the log before
	 * this should not be replayed.
	 * We mark the item descriptor and the transaction dirty so
	 * that we'll hold the buffer until after the commit.
	 *
	 * Since we're invalidating the buffer, we also clear the state
	 * about which parts of the buffer have been logged.  We also
	 * clear the flag indicating that this is an inode buffer since
	 * the data in the buffer will no longer be valid.
	 *
	 * We set the stale bit in the buffer as well since we're getting
	 * rid of it.
	 */
	XFS_BUF_UNDELAYWRITE(bp);
	XFS_BUF_STALE(bp);
	bip->bli_flags |= XFS_BLI_STALE;
	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_DIRTY);
	bip->bli_format.blf_flags &= ~XFS_BLI_INODE_BUF;
	bip->bli_format.blf_flags |= XFS_BLI_CANCEL;
	memset((char *)(bip->bli_format.blf_data_map), 0,
	      (bip->bli_format.blf_map_size * sizeof(uint)));
	lidp->lid_flags |= XFS_LID_DIRTY|XFS_LID_BUF_STALE;
	tp->t_flags |= XFS_TRANS_DIRTY;
}

/*
 * This call is used to indicate that the buffer contains on-disk
 * inodes which must be handled specially during recovery.  They
 * require special handling because only the di_next_unlinked from
 * the inodes in the buffer should be recovered.  The rest of the
 * data in the buffer is logged via the inodes themselves.
 *
 * All we do is set the XFS_BLI_INODE_BUF flag in the buffer's log
 * format structure so that we'll know what to do at recovery time.
 */
/* ARGSUSED */
void
xfs_trans_inode_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_format.blf_flags |= XFS_BLI_INODE_BUF;
}

/*
 * This call is used to indicate that the buffer is going to
 * be staled and was an inode buffer. This means it gets
 * special processing during unpin - where any inodes 
 * associated with the buffer should be removed from ail.
 * There is also special processing during recovery,
 * any replay of the inodes in the buffer needs to be
 * prevented as the buffer may have been reused.
 */
void
xfs_trans_stale_inode_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_STALE_INODE;
	bip->bli_item.li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*))
		xfs_buf_iodone;
}



/*
 * Mark the buffer as being one which contains newly allocated
 * inodes.  We need to make sure that even if this buffer is
 * relogged as an 'inode buf' we still recover all of the inode
 * images in the face of a crash.  This works in coordination with
 * xfs_buf_item_committed() to ensure that the buffer remains in the
 * AIL at its original location even after it has been relogged.
 */
/* ARGSUSED */
void
xfs_trans_inode_alloc_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF;
}


/*
 * Similar to xfs_trans_inode_buf(), this marks the buffer as a cluster of
 * dquots. However, unlike in inode buffer recovery, dquot buffers get
 * recovered in their entirety. (Hence, no XFS_BLI_DQUOT_ALLOC_BUF flag).
 * The only thing that makes dquot buffers different from regular
 * buffers is that we must not replay dquot bufs when recovering
 * if a _corresponding_ quotaoff has happened. We also have to distinguish
 * between usr dquot bufs and grp dquot bufs, because usr and grp quotas
 * can be turned off independently.
 */
/* ARGSUSED */
void
xfs_trans_dquot_buf(
	xfs_trans_t	*tp,
	xfs_buf_t	*bp,
	uint		type)
{
	xfs_buf_log_item_t	*bip;

	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp);
	ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
	ASSERT(type == XFS_BLI_UDQUOT_BUF ||
	       type == XFS_BLI_PDQUOT_BUF ||
	       type == XFS_BLI_GDQUOT_BUF);

	bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *);
	ASSERT(atomic_read(&bip->bli_refcount) > 0);

	bip->bli_format.blf_flags |= type;
}

/*
 * Check to see if a buffer matching the given parameters is already
 * a part of the given transaction.  Only check the first, embedded
 * chunk, since we don't want to spend all day scanning large transactions.
 */
STATIC xfs_buf_t *
xfs_trans_buf_item_match(
	xfs_trans_t	*tp,
	xfs_buftarg_t	*target,
	xfs_daddr_t	blkno,
	int		len)
{
	xfs_log_item_chunk_t	*licp;
	xfs_log_item_desc_t	*lidp;
	xfs_buf_log_item_t	*blip;
	xfs_buf_t		*bp;
	int			i;

	bp = NULL;
	len = BBTOB(len);
	licp = &tp->t_items;
	if (!xfs_lic_are_all_free(licp)) {
		for (i = 0; i < licp->lic_unused; i++) {
			/*
			 * Skip unoccupied slots.
			 */
			if (xfs_lic_isfree(licp, i)) {
				continue;
			}

			lidp = xfs_lic_slot(licp, i);
			blip = (xfs_buf_log_item_t *)lidp->lid_item;
			if (blip->bli_item.li_type != XFS_LI_BUF) {
				continue;
			}

			bp = blip->bli_buf;
			if ((XFS_BUF_TARGET(bp) == target) &&
			    (XFS_BUF_ADDR(bp) == blkno) &&
			    (XFS_BUF_COUNT(bp) == len)) {
				/*
				 * We found it.  Break out and
				 * return the pointer to the buffer.
				 */
				break;
			} else {
				bp = NULL;
			}
		}
	}
	return bp;
}

/*
 * Check to see if a buffer matching the given parameters is already
 * a part of the given transaction.  Check all the chunks, we
 * want to be thorough.
 */
STATIC xfs_buf_t *
xfs_trans_buf_item_match_all(
	xfs_trans_t	*tp,
	xfs_buftarg_t	*target,
	xfs_daddr_t	blkno,
	int		len)
{
	xfs_log_item_chunk_t	*licp;
	xfs_log_item_desc_t	*lidp;
	xfs_buf_log_item_t	*blip;
	xfs_buf_t		*bp;
	int			i;

	bp = NULL;
	len = BBTOB(len);
	for (licp = &tp->t_items; licp != NULL; licp = licp->lic_next) {
		if (xfs_lic_are_all_free(licp)) {
			ASSERT(licp == &tp->t_items);
			ASSERT(licp->lic_next == NULL);
			return NULL;
		}
		for (i = 0; i < licp->lic_unused; i++) {
			/*
			 * Skip unoccupied slots.
			 */
			if (xfs_lic_isfree(licp, i)) {
				continue;
			}

			lidp = xfs_lic_slot(licp, i);
			blip = (xfs_buf_log_item_t *)lidp->lid_item;
			if (blip->bli_item.li_type != XFS_LI_BUF) {
				continue;
			}

			bp = blip->bli_buf;
			if ((XFS_BUF_TARGET(bp) == target) &&
			    (XFS_BUF_ADDR(bp) == blkno) &&
			    (XFS_BUF_COUNT(bp) == len)) {
				/*
				 * We found it.  Break out and
				 * return the pointer to the buffer.
				 */
				return bp;
			}
		}
	}
	return NULL;
}