summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/meta_io.c
blob: 92c1a3f823d8a315a66ad439be6a4843f4ce0478 (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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License v.2.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/delay.h>
#include <linux/gfs2_ondisk.h>

#include "gfs2.h"
#include "lm_interface.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"

#define buffer_busy(bh) \
((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
#define buffer_in_io(bh) \
((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock)))

static int aspace_get_block(struct inode *inode, sector_t lblock,
			    struct buffer_head *bh_result, int create)
{
	gfs2_assert_warn(inode->i_sb->s_fs_info, 0);
	return -EOPNOTSUPP;
}

static int gfs2_aspace_writepage(struct page *page,
				 struct writeback_control *wbc)
{
	return block_write_full_page(page, aspace_get_block, wbc);
}

/**
 * stuck_releasepage - We're stuck in gfs2_releasepage().  Print stuff out.
 * @bh: the buffer we're stuck on
 *
 */

static void stuck_releasepage(struct buffer_head *bh)
{
	struct inode *inode = bh->b_page->mapping->host;
	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
	struct gfs2_bufdata *bd = bh->b_private;
	struct gfs2_glock *gl;

	fs_warn(sdp, "stuck in gfs2_releasepage() %p\n", inode);
	fs_warn(sdp, "blkno = %llu, bh->b_count = %d\n",
		(uint64_t)bh->b_blocknr, atomic_read(&bh->b_count));
	fs_warn(sdp, "pinned = %u\n", buffer_pinned(bh));
	fs_warn(sdp, "bh->b_private = %s\n", (bd) ? "!NULL" : "NULL");

	if (!bd)
		return;

	gl = bd->bd_gl;

	fs_warn(sdp, "gl = (%u, %llu)\n", 
		gl->gl_name.ln_type, gl->gl_name.ln_number);

	fs_warn(sdp, "bd_list_tr = %s, bd_le.le_list = %s\n",
		(list_empty(&bd->bd_list_tr)) ? "no" : "yes",
		(list_empty(&bd->bd_le.le_list)) ? "no" : "yes");

	if (gl->gl_ops == &gfs2_inode_glops) {
		struct gfs2_inode *ip = gl->gl_object;
		unsigned int x;

		if (!ip)
			return;

		fs_warn(sdp, "ip = %llu %llu\n",
			ip->i_num.no_formal_ino, ip->i_num.no_addr);
		fs_warn(sdp, "ip->i_count = %d, ip->i_vnode = %s\n",
			atomic_read(&ip->i_count),
			(ip->i_vnode) ? "!NULL" : "NULL");

		for (x = 0; x < GFS2_MAX_META_HEIGHT; x++)
			fs_warn(sdp, "ip->i_cache[%u] = %s\n",
				x, (ip->i_cache[x]) ? "!NULL" : "NULL");
	}
}

/**
 * gfs2_aspace_releasepage - free the metadata associated with a page
 * @page: the page that's being released
 * @gfp_mask: passed from Linux VFS, ignored by us
 *
 * Call try_to_free_buffers() if the buffers in this page can be
 * released.
 *
 * Returns: 0
 */

static int gfs2_aspace_releasepage(struct page *page, gfp_t gfp_mask)
{
	struct inode *aspace = page->mapping->host;
	struct gfs2_sbd *sdp = aspace->i_sb->s_fs_info;
	struct buffer_head *bh, *head;
	struct gfs2_bufdata *bd;
	unsigned long t;

	if (!page_has_buffers(page))
		goto out;

	head = bh = page_buffers(page);
	do {
		t = jiffies;

		while (atomic_read(&bh->b_count)) {
			if (atomic_read(&aspace->i_writecount)) {
				if (time_after_eq(jiffies, t +
				    gfs2_tune_get(sdp, gt_stall_secs) * HZ)) {
					stuck_releasepage(bh);
					t = jiffies;
				}

				yield();
				continue;
			}

			return 0;
		}

		gfs2_assert_warn(sdp, !buffer_pinned(bh));

		bd = bh->b_private;
		if (bd) {
			gfs2_assert_warn(sdp, bd->bd_bh == bh);
			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
			gfs2_assert_warn(sdp, list_empty(&bd->bd_le.le_list));
			gfs2_assert_warn(sdp, !bd->bd_ail);
			kmem_cache_free(gfs2_bufdata_cachep, bd);
			bh->b_private = NULL;
		}

		bh = bh->b_this_page;
	}
	while (bh != head);

 out:
	return try_to_free_buffers(page);
}

static struct address_space_operations aspace_aops = {
	.writepage = gfs2_aspace_writepage,
	.releasepage = gfs2_aspace_releasepage,
};

/**
 * gfs2_aspace_get - Create and initialize a struct inode structure
 * @sdp: the filesystem the aspace is in
 *
 * Right now a struct inode is just a struct inode.  Maybe Linux
 * will supply a more lightweight address space construct (that works)
 * in the future.
 *
 * Make sure pages/buffers in this aspace aren't in high memory.
 *
 * Returns: the aspace
 */

struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp)
{
	struct inode *aspace;

	aspace = new_inode(sdp->sd_vfs);
	if (aspace) {
		mapping_set_gfp_mask(aspace->i_mapping, GFP_KERNEL);
		aspace->i_mapping->a_ops = &aspace_aops;
		aspace->i_size = ~0ULL;
		aspace->u.generic_ip = NULL;
		insert_inode_hash(aspace);
	}
	return aspace;
}

void gfs2_aspace_put(struct inode *aspace)
{
	remove_inode_hash(aspace);
	iput(aspace);
}

/**
 * gfs2_ail1_start_one - Start I/O on a part of the AIL
 * @sdp: the filesystem
 * @tr: the part of the AIL
 *
 */

void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
	struct gfs2_bufdata *bd, *s;
	struct buffer_head *bh;
	int retry;

	BUG_ON(!spin_is_locked(&sdp->sd_log_lock));

	do {
		retry = 0;

		list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
						 bd_ail_st_list) {
			bh = bd->bd_bh;

			gfs2_assert(sdp, bd->bd_ail == ai);

			if (!buffer_busy(bh)) {
				if (!buffer_uptodate(bh)) {
					gfs2_log_unlock(sdp);
					gfs2_io_error_bh(sdp, bh);
					gfs2_log_lock(sdp);
				}
				list_move(&bd->bd_ail_st_list,
					  &ai->ai_ail2_list);
				continue;
			}

			if (!buffer_dirty(bh))
				continue;

			list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);

			gfs2_log_unlock(sdp);
			wait_on_buffer(bh);
			ll_rw_block(WRITE, 1, &bh);
			gfs2_log_lock(sdp);

			retry = 1;
			break;
		}
	} while (retry);
}

/**
 * gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
 * @sdp: the filesystem
 * @ai: the AIL entry
 *
 */

int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
{
	struct gfs2_bufdata *bd, *s;
	struct buffer_head *bh;

	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
					 bd_ail_st_list) {
		bh = bd->bd_bh;

		gfs2_assert(sdp, bd->bd_ail == ai);

		if (buffer_busy(bh)) {
			if (flags & DIO_ALL)
				continue;
			else
				break;
		}

		if (!buffer_uptodate(bh))
			gfs2_io_error_bh(sdp, bh);

		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
	}

	return list_empty(&ai->ai_ail1_list);
}

/**
 * gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
 * @sdp: the filesystem
 * @ai: the AIL entry
 *
 */

void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
	struct list_head *head = &ai->ai_ail2_list;
	struct gfs2_bufdata *bd;

	while (!list_empty(head)) {
		bd = list_entry(head->prev, struct gfs2_bufdata,
				bd_ail_st_list);
		gfs2_assert(sdp, bd->bd_ail == ai);
		bd->bd_ail = NULL;
		list_del(&bd->bd_ail_st_list);
		list_del(&bd->bd_ail_gl_list);
		atomic_dec(&bd->bd_gl->gl_ail_count);
		brelse(bd->bd_bh);
	}
}

/**
 * ail_empty_gl - remove all buffers for a given lock from the AIL
 * @gl: the glock
 *
 * None of the buffers should be dirty, locked, or pinned.
 */

void gfs2_ail_empty_gl(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	unsigned int blocks;
	struct list_head *head = &gl->gl_ail_list;
	struct gfs2_bufdata *bd;
	struct buffer_head *bh;
	uint64_t blkno;
	int error;

	blocks = atomic_read(&gl->gl_ail_count);
	if (!blocks)
		return;

	error = gfs2_trans_begin(sdp, 0, blocks);
	if (gfs2_assert_withdraw(sdp, !error))
		return;

	gfs2_log_lock(sdp);
	while (!list_empty(head)) {
		bd = list_entry(head->next, struct gfs2_bufdata,
				bd_ail_gl_list);
		bh = bd->bd_bh;
		blkno = bh->b_blocknr;
		gfs2_assert_withdraw(sdp, !buffer_busy(bh));

		bd->bd_ail = NULL;
		list_del(&bd->bd_ail_st_list);
		list_del(&bd->bd_ail_gl_list);
		atomic_dec(&gl->gl_ail_count);
		brelse(bh);
		gfs2_log_unlock(sdp);

		gfs2_trans_add_revoke(sdp, blkno);

		gfs2_log_lock(sdp);
	}
	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
	gfs2_log_unlock(sdp);

	gfs2_trans_end(sdp);
	gfs2_log_flush(sdp, NULL);
}

/**
 * gfs2_meta_inval - Invalidate all buffers associated with a glock
 * @gl: the glock
 *
 */

void gfs2_meta_inval(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct inode *aspace = gl->gl_aspace;
	struct address_space *mapping = gl->gl_aspace->i_mapping;

	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));

	atomic_inc(&aspace->i_writecount);
	truncate_inode_pages(mapping, 0);
	atomic_dec(&aspace->i_writecount);

	gfs2_assert_withdraw(sdp, !mapping->nrpages);
}

/**
 * gfs2_meta_sync - Sync all buffers associated with a glock
 * @gl: The glock
 * @flags: DIO_START | DIO_WAIT
 *
 */

void gfs2_meta_sync(struct gfs2_glock *gl, int flags)
{
	struct address_space *mapping = gl->gl_aspace->i_mapping;
	int error = 0;

	if (flags & DIO_START)
		filemap_fdatawrite(mapping);
	if (!error && (flags & DIO_WAIT))
		error = filemap_fdatawait(mapping);

	if (error)
		gfs2_io_error(gl->gl_sbd);
}

/**
 * getbuf - Get a buffer with a given address space
 * @sdp: the filesystem
 * @aspace: the address space
 * @blkno: the block number (filesystem scope)
 * @create: 1 if the buffer should be created
 *
 * Returns: the buffer
 */

static struct buffer_head *getbuf(struct gfs2_sbd *sdp, struct inode *aspace,
				  uint64_t blkno, int create)
{
	struct page *page;
	struct buffer_head *bh;
	unsigned int shift;
	unsigned long index;
	unsigned int bufnum;

	shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
	index = blkno >> shift;             /* convert block to page */
	bufnum = blkno - (index << shift);  /* block buf index within page */

	if (create) {
		for (;;) {
			page = grab_cache_page(aspace->i_mapping, index);
			if (page)
				break;
			yield();
		}
	} else {
		page = find_lock_page(aspace->i_mapping, index);
		if (!page)
			return NULL;
	}

	if (!page_has_buffers(page))
		create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);

	/* Locate header for our buffer within our page */
	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
		/* Do nothing */;
	get_bh(bh);

	if (!buffer_mapped(bh))
		map_bh(bh, sdp->sd_vfs, blkno);

	unlock_page(page);
	mark_page_accessed(page);
	page_cache_release(page);

	return bh;
}

static void meta_prep_new(struct buffer_head *bh)
{
	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);

	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
}

/**
 * gfs2_meta_new - Get a block
 * @gl: The glock associated with this block
 * @blkno: The block number
 *
 * Returns: The buffer
 */

struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, uint64_t blkno)
{
	struct buffer_head *bh;
	bh = getbuf(gl->gl_sbd, gl->gl_aspace, blkno, CREATE);
	meta_prep_new(bh);
	return bh;
}

/**
 * gfs2_meta_read - Read a block from disk
 * @gl: The glock covering the block
 * @blkno: The block number
 * @flags: flags to gfs2_dreread()
 * @bhp: the place where the buffer is returned (NULL on failure)
 *
 * Returns: errno
 */

int gfs2_meta_read(struct gfs2_glock *gl, uint64_t blkno, int flags,
		   struct buffer_head **bhp)
{
	int error;

	*bhp = getbuf(gl->gl_sbd, gl->gl_aspace, blkno, CREATE);
	error = gfs2_meta_reread(gl->gl_sbd, *bhp, flags);
	if (error)
		brelse(*bhp);

	return error;
}

/**
 * gfs2_meta_reread - Reread a block from disk
 * @sdp: the filesystem
 * @bh: The block to read
 * @flags: Flags that control the read
 *
 * Returns: errno
 */

int gfs2_meta_reread(struct gfs2_sbd *sdp, struct buffer_head *bh, int flags)
{
	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		return -EIO;

	if (flags & DIO_FORCE)
		clear_buffer_uptodate(bh);

	if ((flags & DIO_START) && !buffer_uptodate(bh))
		ll_rw_block(READ, 1, &bh);

	if (flags & DIO_WAIT) {
		wait_on_buffer(bh);

		if (!buffer_uptodate(bh)) {
			struct gfs2_trans *tr = current->journal_info;
			if (tr && tr->tr_touched)
				gfs2_io_error_bh(sdp, bh);
			return -EIO;
		}
		if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
			return -EIO;
	}

	return 0;
}

/**
 * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer
 * @gl: the glock the buffer belongs to
 * @bh: The buffer to be attached to
 * @meta: Flag to indicate whether its metadata or not
 */

void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
			 int meta)
{
	struct gfs2_bufdata *bd;

	if (meta)
		lock_page(bh->b_page);

	if (bh->b_private) {
		if (meta)
			unlock_page(bh->b_page);
		return;
	}

	bd = kmem_cache_alloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL),
	memset(bd, 0, sizeof(struct gfs2_bufdata));

	bd->bd_bh = bh;
	bd->bd_gl = gl;

	INIT_LIST_HEAD(&bd->bd_list_tr);
	if (meta) {
		lops_init_le(&bd->bd_le, &gfs2_buf_lops);
	} else {
		lops_init_le(&bd->bd_le, &gfs2_databuf_lops);
		get_bh(bh);
	}
	bh->b_private = bd;

	if (meta)
		unlock_page(bh->b_page);
}

/**
 * gfs2_pin - Pin a buffer in memory
 * @sdp: the filesystem the buffer belongs to
 * @bh: The buffer to be pinned
 *
 */

void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	struct gfs2_bufdata *bd = bh->b_private;

	gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));

	if (test_set_buffer_pinned(bh))
		gfs2_assert_withdraw(sdp, 0);

	wait_on_buffer(bh);

	/* If this buffer is in the AIL and it has already been written
	   to in-place disk block, remove it from the AIL. */

	gfs2_log_lock(sdp);
	if (bd->bd_ail && !buffer_in_io(bh))
		list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
	gfs2_log_unlock(sdp);

	clear_buffer_dirty(bh);
	wait_on_buffer(bh);

	if (!buffer_uptodate(bh))
		gfs2_io_error_bh(sdp, bh);

	get_bh(bh);
}

/**
 * gfs2_unpin - Unpin a buffer
 * @sdp: the filesystem the buffer belongs to
 * @bh: The buffer to unpin
 * @ai:
 *
 */

void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
	        struct gfs2_ail *ai)
{
	struct gfs2_bufdata *bd = bh->b_private;

	gfs2_assert_withdraw(sdp, buffer_uptodate(bh));

	if (!buffer_pinned(bh))
		gfs2_assert_withdraw(sdp, 0);

	mark_buffer_dirty(bh);
	clear_buffer_pinned(bh);

	gfs2_log_lock(sdp);
	if (bd->bd_ail) {
		list_del(&bd->bd_ail_st_list);
		brelse(bh);
	} else {
		struct gfs2_glock *gl = bd->bd_gl;
		list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
		atomic_inc(&gl->gl_ail_count);
	}
	bd->bd_ail = ai;
	list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
	gfs2_log_unlock(sdp);
}

/**
 * gfs2_meta_wipe - make inode's buffers so they aren't dirty/pinned anymore
 * @ip: the inode who owns the buffers
 * @bstart: the first buffer in the run
 * @blen: the number of buffers in the run
 *
 */

void gfs2_meta_wipe(struct gfs2_inode *ip, uint64_t bstart, uint32_t blen)
{
	struct gfs2_sbd *sdp = ip->i_sbd;
	struct inode *aspace = ip->i_gl->gl_aspace;
	struct buffer_head *bh;

	while (blen) {
		bh = getbuf(sdp, aspace, bstart, NO_CREATE);
		if (bh) {
			struct gfs2_bufdata *bd = bh->b_private;

			if (test_clear_buffer_pinned(bh)) {
				struct gfs2_trans *tr = current->journal_info;
				gfs2_log_lock(sdp);
				list_del_init(&bd->bd_le.le_list);
				gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
				sdp->sd_log_num_buf--;
				gfs2_log_unlock(sdp);
				tr->tr_num_buf_rm++;
				brelse(bh);
			}
			if (bd) {
				gfs2_log_lock(sdp);
				if (bd->bd_ail) {
					uint64_t blkno = bh->b_blocknr;
					bd->bd_ail = NULL;
					list_del(&bd->bd_ail_st_list);
					list_del(&bd->bd_ail_gl_list);
					atomic_dec(&bd->bd_gl->gl_ail_count);
					brelse(bh);
					gfs2_log_unlock(sdp);
					gfs2_trans_add_revoke(sdp, blkno);
				} else
					gfs2_log_unlock(sdp);
			}

			lock_buffer(bh);
			clear_buffer_dirty(bh);
			clear_buffer_uptodate(bh);
			unlock_buffer(bh);

			brelse(bh);
		}

		bstart++;
		blen--;
	}
}

/**
 * gfs2_meta_cache_flush - get rid of any references on buffers for this inode
 * @ip: The GFS2 inode
 *
 * This releases buffers that are in the most-recently-used array of
 * blocks used for indirect block addressing for this inode.
 */

void gfs2_meta_cache_flush(struct gfs2_inode *ip)
{
	struct buffer_head **bh_slot;
	unsigned int x;

	spin_lock(&ip->i_spin);

	for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) {
		bh_slot = &ip->i_cache[x];
		if (!*bh_slot)
			break;
		brelse(*bh_slot);
		*bh_slot = NULL;
	}

	spin_unlock(&ip->i_spin);
}

/**
 * gfs2_meta_indirect_buffer - Get a metadata buffer
 * @ip: The GFS2 inode
 * @height: The level of this buf in the metadata (indir addr) tree (if any)
 * @num: The block number (device relative) of the buffer
 * @new: Non-zero if we may create a new buffer
 * @bhp: the buffer is returned here
 *
 * Try to use the gfs2_inode's MRU metadata tree cache.
 *
 * Returns: errno
 */

int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, uint64_t num,
			      int new, struct buffer_head **bhp)
{
	struct buffer_head *bh, **bh_slot = ip->i_cache + height;
	int error;

	spin_lock(&ip->i_spin);
	bh = *bh_slot;
	if (bh) {
		if (bh->b_blocknr == num)
			get_bh(bh);
		else
			bh = NULL;
	}
	spin_unlock(&ip->i_spin);

	if (bh) {
		if (new)
			meta_prep_new(bh);
		else {
			error = gfs2_meta_reread(ip->i_sbd, bh,
						 DIO_START | DIO_WAIT);
			if (error) {
				brelse(bh);
				return error;
			}
		}
	} else {
		if (new)
			bh = gfs2_meta_new(ip->i_gl, num);
		else {
			error = gfs2_meta_read(ip->i_gl, num,
					       DIO_START | DIO_WAIT, &bh);
			if (error)
				return error;
		}

		spin_lock(&ip->i_spin);
		if (*bh_slot != bh) {
			brelse(*bh_slot);
			*bh_slot = bh;
			get_bh(bh);
		}
		spin_unlock(&ip->i_spin);
	}

	if (new) {
		if (gfs2_assert_warn(ip->i_sbd, height)) {
			brelse(bh);
			return -EIO;
		}
		gfs2_trans_add_bh(ip->i_gl, bh, 1);
		gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
		gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));

	} else if (gfs2_metatype_check(ip->i_sbd, bh,
			     (height) ? GFS2_METATYPE_IN : GFS2_METATYPE_DI)) {
		brelse(bh);
		return -EIO;
	}

	*bhp = bh;

	return 0;
}

/**
 * gfs2_meta_ra - start readahead on an extent of a file
 * @gl: the glock the blocks belong to
 * @dblock: the starting disk block
 * @extlen: the number of blocks in the extent
 *
 */

void gfs2_meta_ra(struct gfs2_glock *gl, uint64_t dblock, uint32_t extlen)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct inode *aspace = gl->gl_aspace;
	struct buffer_head *first_bh, *bh;
	uint32_t max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
			  sdp->sd_sb.sb_bsize_shift;
	int error;

	if (!extlen || !max_ra)
		return;
	if (extlen > max_ra)
		extlen = max_ra;

	first_bh = getbuf(sdp, aspace, dblock, CREATE);

	if (buffer_uptodate(first_bh))
		goto out;
	if (!buffer_locked(first_bh)) {
		error = gfs2_meta_reread(sdp, first_bh, DIO_START);
		if (error)
			goto out;
	}

	dblock++;
	extlen--;

	while (extlen) {
		bh = getbuf(sdp, aspace, dblock, CREATE);

		if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
			error = gfs2_meta_reread(sdp, bh, DIO_START);
			brelse(bh);
			if (error)
				goto out;
		} else
			brelse(bh);

		dblock++;
		extlen--;

		if (buffer_uptodate(first_bh))
			break;
	}

 out:
	brelse(first_bh);
}

/**
 * gfs2_meta_syncfs - sync all the buffers in a filesystem
 * @sdp: the filesystem
 *
 */

void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
{
	gfs2_log_flush(sdp, NULL);
	for (;;) {
		gfs2_ail1_start(sdp, DIO_ALL);
		if (gfs2_ail1_empty(sdp, DIO_ALL))
			break;
		msleep(10);
	}
}