aboutsummaryrefslogtreecommitdiff
path: root/fs/gfs2/ops_address.c
blob: ce90032c010ec7176d8f31505a5c859833dc3650 (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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2007 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 version 2.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/fs.h>
#include <linux/writeback.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "ops_address.h"
#include "quota.h"
#include "trans.h"
#include "rgrp.h"
#include "ops_file.h"
#include "super.h"
#include "util.h"
#include "glops.h"


static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
				   unsigned int from, unsigned int to)
{
	struct buffer_head *head = page_buffers(page);
	unsigned int bsize = head->b_size;
	struct buffer_head *bh;
	unsigned int start, end;

	for (bh = head, start = 0; bh != head || !start;
	     bh = bh->b_this_page, start = end) {
		end = start + bsize;
		if (end <= from || start >= to)
			continue;
		if (gfs2_is_jdata(ip))
			set_buffer_uptodate(bh);
		gfs2_trans_add_bh(ip->i_gl, bh, 0);
	}
}

/**
 * gfs2_get_block - Fills in a buffer head with details about a block
 * @inode: The inode
 * @lblock: The block number to look up
 * @bh_result: The buffer head to return the result in
 * @create: Non-zero if we may add block to the file
 *
 * Returns: errno
 */

int gfs2_get_block(struct inode *inode, sector_t lblock,
	           struct buffer_head *bh_result, int create)
{
	return gfs2_block_map(inode, lblock, create, bh_result);
}

/**
 * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
 * @inode: The inode
 * @lblock: The block number to look up
 * @bh_result: The buffer head to return the result in
 * @create: Non-zero if we may add block to the file
 *
 * Returns: errno
 */

static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
				  struct buffer_head *bh_result, int create)
{
	int error;

	error = gfs2_block_map(inode, lblock, 0, bh_result);
	if (error)
		return error;
	if (bh_result->b_blocknr == 0)
		return -EIO;
	return 0;
}

static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
				 struct buffer_head *bh_result, int create)
{
	return gfs2_block_map(inode, lblock, 0, bh_result);
}

/**
 * gfs2_writepage - Write complete page
 * @page: Page to write
 *
 * Returns: errno
 *
 * Some of this is copied from block_write_full_page() although we still
 * call it to do most of the work.
 */

static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	loff_t i_size = i_size_read(inode);
	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	int error;
	int done_trans = 0;

	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) {
		unlock_page(page);
		return -EIO;
	}
	if (current->journal_info)
		goto out_ignore;

	/* Is the page fully outside i_size? (truncate in progress) */
        offset = i_size & (PAGE_CACHE_SIZE-1);
	if (page->index > end_index || (page->index == end_index && !offset)) {
		page->mapping->a_ops->invalidatepage(page, 0);
		unlock_page(page);
		return 0; /* don't care */
	}

	if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) &&
	    PageChecked(page)) {
		ClearPageChecked(page);
		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
		if (error)
			goto out_ignore;
		if (!page_has_buffers(page)) {
			create_empty_buffers(page, inode->i_sb->s_blocksize,
					     (1 << BH_Dirty)|(1 << BH_Uptodate));
		}
		gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1);
		done_trans = 1;
	}
	error = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
	if (done_trans)
		gfs2_trans_end(sdp);
	gfs2_meta_cache_flush(ip);
	return error;

out_ignore:
	redirty_page_for_writepage(wbc, page);
	unlock_page(page);
	return 0;
}

/**
 * gfs2_writepages - Write a bunch of dirty pages back to disk
 * @mapping: The mapping to write
 * @wbc: Write-back control
 *
 * For journaled files and/or ordered writes this just falls back to the
 * kernel's default writepages path for now. We will probably want to change
 * that eventually (i.e. when we look at allocate on flush).
 *
 * For the data=writeback case though we can already ignore buffer heads
 * and write whole extents at once. This is a big reduction in the
 * number of I/O requests we send and the bmap calls we make in this case.
 */
static int gfs2_writepages(struct address_space *mapping,
			   struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip))
		return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);

	return generic_writepages(mapping, wbc);
}

/**
 * stuffed_readpage - Fill in a Linux page with stuffed file data
 * @ip: the inode
 * @page: the page
 *
 * Returns: errno
 */

static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
{
	struct buffer_head *dibh;
	void *kaddr;
	int error;

	/*
	 * Due to the order of unstuffing files and ->nopage(), we can be
	 * asked for a zero page in the case of a stuffed file being extended,
	 * so we need to supply one here. It doesn't happen often.
	 */
	if (unlikely(page->index)) {
		zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0);
		return 0;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		return error;

	kaddr = kmap_atomic(page, KM_USER0);
	memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
	       ip->i_di.di_size);
	memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
	kunmap_atomic(kaddr, KM_USER0);
	flush_dcache_page(page);
	brelse(dibh);
	SetPageUptodate(page);

	return 0;
}


/**
 * gfs2_readpage - readpage with locking
 * @file: The file to read a page for. N.B. This may be NULL if we are
 * reading an internal file.
 * @page: The page to read
 *
 * Returns: errno
 */

static int gfs2_readpage(struct file *file, struct page *page)
{
	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
	struct gfs2_file *gf = NULL;
	struct gfs2_holder gh;
	int error;
	int do_unlock = 0;

	if (likely(file != &gfs2_internal_file_sentinel)) {
		if (file) {
			gf = file->private_data;
			if (test_bit(GFF_EXLOCK, &gf->f_flags))
				/* gfs2_sharewrite_fault has grabbed the ip->i_gl already */
				goto skip_lock;
		}
		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
		do_unlock = 1;
		error = gfs2_glock_nq_atime(&gh);
		if (unlikely(error))
			goto out_unlock;
	}

skip_lock:
	if (gfs2_is_stuffed(ip)) {
		error = stuffed_readpage(ip, page);
		unlock_page(page);
	} else
		error = mpage_readpage(page, gfs2_get_block);

	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		error = -EIO;

	if (do_unlock) {
		gfs2_glock_dq_m(1, &gh);
		gfs2_holder_uninit(&gh);
	}
out:
	return error;
out_unlock:
	unlock_page(page);
	if (error == GLR_TRYFAILED) {
		error = AOP_TRUNCATED_PAGE;
		yield();
	}
	if (do_unlock)
		gfs2_holder_uninit(&gh);
	goto out;
}

/**
 * gfs2_readpages - Read a bunch of pages at once
 *
 * Some notes:
 * 1. This is only for readahead, so we can simply ignore any things
 *    which are slightly inconvenient (such as locking conflicts between
 *    the page lock and the glock) and return having done no I/O. Its
 *    obviously not something we'd want to do on too regular a basis.
 *    Any I/O we ignore at this time will be done via readpage later.
 * 2. We don't handle stuffed files here we let readpage do the honours.
 * 3. mpage_readpages() does most of the heavy lifting in the common case.
 * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
 * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
 *    well as read-ahead.
 */
static int gfs2_readpages(struct file *file, struct address_space *mapping,
			  struct list_head *pages, unsigned nr_pages)
{
	struct inode *inode = mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_holder gh;
	int ret = 0;
	int do_unlock = 0;

	if (likely(file != &gfs2_internal_file_sentinel)) {
		if (file) {
			struct gfs2_file *gf = file->private_data;
			if (test_bit(GFF_EXLOCK, &gf->f_flags))
				goto skip_lock;
		}
		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
				 LM_FLAG_TRY_1CB|GL_ATIME, &gh);
		do_unlock = 1;
		ret = gfs2_glock_nq_atime(&gh);
		if (ret == GLR_TRYFAILED)
			goto out_noerror;
		if (unlikely(ret))
			goto out_unlock;
	}
skip_lock:
	if (!gfs2_is_stuffed(ip))
		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);

	if (do_unlock) {
		gfs2_glock_dq_m(1, &gh);
		gfs2_holder_uninit(&gh);
	}
out:
	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
		ret = -EIO;
	return ret;
out_noerror:
	ret = 0;
out_unlock:
	if (do_unlock)
		gfs2_holder_uninit(&gh);
	goto out;
}

/**
 * gfs2_prepare_write - Prepare to write a page to a file
 * @file: The file to write to
 * @page: The page which is to be prepared for writing
 * @from: From (byte range within page)
 * @to: To (byte range within page)
 *
 * Returns: errno
 */

static int gfs2_prepare_write(struct file *file, struct page *page,
			      unsigned from, unsigned to)
{
	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
	unsigned int data_blocks, ind_blocks, rblocks;
	int alloc_required;
	int error = 0;
	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
	loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
	struct gfs2_alloc *al;
	unsigned int write_len = to - from;


	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|LM_FLAG_TRY_1CB, &ip->i_gh);
	error = gfs2_glock_nq_atime(&ip->i_gh);
	if (unlikely(error)) {
		if (error == GLR_TRYFAILED) {
			unlock_page(page);
			error = AOP_TRUNCATED_PAGE;
			yield();
		}
		goto out_uninit;
	}

	gfs2_write_calc_reserv(ip, write_len, &data_blocks, &ind_blocks);

	error = gfs2_write_alloc_required(ip, pos, write_len, &alloc_required);
	if (error)
		goto out_unlock;


	ip->i_alloc.al_requested = 0;
	if (alloc_required) {
		al = gfs2_alloc_get(ip);

		error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
		if (error)
			goto out_alloc_put;

		error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
		if (error)
			goto out_qunlock;

		al->al_requested = data_blocks + ind_blocks;
		error = gfs2_inplace_reserve(ip);
		if (error)
			goto out_qunlock;
	}

	rblocks = RES_DINODE + ind_blocks;
	if (gfs2_is_jdata(ip))
		rblocks += data_blocks ? data_blocks : 1;
	if (ind_blocks || data_blocks)
		rblocks += RES_STATFS + RES_QUOTA;

	error = gfs2_trans_begin(sdp, rblocks, 0);
	if (error)
		goto out;

	if (gfs2_is_stuffed(ip)) {
		if (end > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
			error = gfs2_unstuff_dinode(ip, page);
			if (error == 0)
				goto prepare_write;
		} else if (!PageUptodate(page))
			error = stuffed_readpage(ip, page);
		goto out;
	}

prepare_write:
	error = block_prepare_write(page, from, to, gfs2_get_block);

out:
	if (error) {
		gfs2_trans_end(sdp);
		if (alloc_required) {
			gfs2_inplace_release(ip);
out_qunlock:
			gfs2_quota_unlock(ip);
out_alloc_put:
			gfs2_alloc_put(ip);
		}
out_unlock:
		gfs2_glock_dq_m(1, &ip->i_gh);
out_uninit:
		gfs2_holder_uninit(&ip->i_gh);
	}

	return error;
}

/**
 * adjust_fs_space - Adjusts the free space available due to gfs2_grow
 * @inode: the rindex inode
 */
static void adjust_fs_space(struct inode *inode)
{
	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
	u64 fs_total, new_free;

	/* Total up the file system space, according to the latest rindex. */
	fs_total = gfs2_ri_total(sdp);

	spin_lock(&sdp->sd_statfs_spin);
	if (fs_total > (m_sc->sc_total + l_sc->sc_total))
		new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
	else
		new_free = 0;
	spin_unlock(&sdp->sd_statfs_spin);
	fs_warn(sdp, "File system extended by %llu blocks.\n",
		(unsigned long long)new_free);
	gfs2_statfs_change(sdp, new_free, new_free, 0);
}

/**
 * gfs2_commit_write - Commit write to a file
 * @file: The file to write to
 * @page: The page containing the data
 * @from: From (byte range within page)
 * @to: To (byte range within page)
 *
 * Returns: errno
 */

static int gfs2_commit_write(struct file *file, struct page *page,
			     unsigned from, unsigned to)
{
	struct inode *inode = page->mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	int error = -EOPNOTSUPP;
	struct buffer_head *dibh;
	struct gfs2_alloc *al = &ip->i_alloc;
	struct gfs2_dinode *di;

	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
                goto fail_nounlock;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto fail_endtrans;

	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
	di = (struct gfs2_dinode *)dibh->b_data;

	if (gfs2_is_stuffed(ip)) {
		u64 file_size;
		void *kaddr;

		file_size = ((u64)page->index << PAGE_CACHE_SHIFT) + to;

		kaddr = kmap_atomic(page, KM_USER0);
		memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
		       kaddr + from, to - from);
		kunmap_atomic(kaddr, KM_USER0);

		SetPageUptodate(page);

		if (inode->i_size < file_size) {
			i_size_write(inode, file_size);
			mark_inode_dirty(inode);
		}
	} else {
		if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED ||
		    gfs2_is_jdata(ip))
			gfs2_page_add_databufs(ip, page, from, to);
		error = generic_commit_write(file, page, from, to);
		if (error)
			goto fail;
	}

	if (ip->i_di.di_size < inode->i_size) {
		ip->i_di.di_size = inode->i_size;
		di->di_size = cpu_to_be64(inode->i_size);
	}

	if (inode == sdp->sd_rindex)
		adjust_fs_space(inode);

	brelse(dibh);
	gfs2_trans_end(sdp);
	if (al->al_requested) {
		gfs2_inplace_release(ip);
		gfs2_quota_unlock(ip);
		gfs2_alloc_put(ip);
	}
	unlock_page(page);
	gfs2_glock_dq_m(1, &ip->i_gh);
	lock_page(page);
	gfs2_holder_uninit(&ip->i_gh);
	return 0;

fail:
	brelse(dibh);
fail_endtrans:
	gfs2_trans_end(sdp);
	if (al->al_requested) {
		gfs2_inplace_release(ip);
		gfs2_quota_unlock(ip);
		gfs2_alloc_put(ip);
	}
	unlock_page(page);
	gfs2_glock_dq_m(1, &ip->i_gh);
	lock_page(page);
	gfs2_holder_uninit(&ip->i_gh);
fail_nounlock:
	ClearPageUptodate(page);
	return error;
}

/**
 * gfs2_set_page_dirty - Page dirtying function
 * @page: The page to dirty
 *
 * Returns: 1 if it dirtyed the page, or 0 otherwise
 */
 
static int gfs2_set_page_dirty(struct page *page)
{
	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);

	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
		SetPageChecked(page);
	return __set_page_dirty_buffers(page);
}

/**
 * gfs2_bmap - Block map function
 * @mapping: Address space info
 * @lblock: The block to map
 *
 * Returns: The disk address for the block or 0 on hole or error
 */

static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
{
	struct gfs2_inode *ip = GFS2_I(mapping->host);
	struct gfs2_holder i_gh;
	sector_t dblock = 0;
	int error;

	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
	if (error)
		return 0;

	if (!gfs2_is_stuffed(ip))
		dblock = generic_block_bmap(mapping, lblock, gfs2_get_block);

	gfs2_glock_dq_uninit(&i_gh);

	return dblock;
}

static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	struct gfs2_bufdata *bd;

	gfs2_log_lock(sdp);
	bd = bh->b_private;
	if (bd) {
		bd->bd_bh = NULL;
		bh->b_private = NULL;
		if (!bd->bd_ail && list_empty(&bd->bd_le.le_list))
			kmem_cache_free(gfs2_bufdata_cachep, bd);
	}
	gfs2_log_unlock(sdp);

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	bh->b_bdev = NULL;
	clear_buffer_mapped(bh);
	clear_buffer_req(bh);
	clear_buffer_new(bh);
	clear_buffer_delay(bh);
	unlock_buffer(bh);
}

static void gfs2_invalidatepage(struct page *page, unsigned long offset)
{
	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
	struct buffer_head *head, *bh, *next;
	unsigned int curr_off = 0;

	BUG_ON(!PageLocked(page));
	if (offset == 0)
		ClearPageChecked(page);
	if (!page_has_buffers(page))
		return;

	bh = head = page_buffers(page);
	do {
		unsigned int next_off = curr_off + bh->b_size;
		next = bh->b_this_page;

		if (offset <= curr_off)
			discard_buffer(sdp, bh);

		curr_off = next_off;
		bh = next;
	} while (bh != head);

	if (!offset)
		try_to_release_page(page, 0);

	return;
}

/**
 * gfs2_ok_for_dio - check that dio is valid on this file
 * @ip: The inode
 * @rw: READ or WRITE
 * @offset: The offset at which we are reading or writing
 *
 * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
 *          1 (to accept the i/o request)
 */
static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
{
	/*
	 * Should we return an error here? I can't see that O_DIRECT for
	 * a journaled file makes any sense. For now we'll silently fall
	 * back to buffered I/O, likewise we do the same for stuffed
	 * files since they are (a) small and (b) unaligned.
	 */
	if (gfs2_is_jdata(ip))
		return 0;

	if (gfs2_is_stuffed(ip))
		return 0;

	if (offset > i_size_read(&ip->i_inode))
		return 0;
	return 1;
}



static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
			      const struct iovec *iov, loff_t offset,
			      unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int rv;

	/*
	 * Deferred lock, even if its a write, since we do no allocation
	 * on this path. All we need change is atime, and this lock mode
	 * ensures that other nodes have flushed their buffered read caches
	 * (i.e. their page cache entries for this inode). We do not,
	 * unfortunately have the option of only flushing a range like
	 * the VFS does.
	 */
	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
	rv = gfs2_glock_nq_atime(&gh);
	if (rv)
		return rv;
	rv = gfs2_ok_for_dio(ip, rw, offset);
	if (rv != 1)
		goto out; /* dio not valid, fall back to buffered i/o */

	rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
					   iov, offset, nr_segs,
					   gfs2_get_block_direct, NULL);
out:
	gfs2_glock_dq_m(1, &gh);
	gfs2_holder_uninit(&gh);
	return rv;
}

/**
 * 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;
static unsigned limit = 0;

	if (limit > 3)
		return;
	limit++;

	fs_warn(sdp, "stuck in gfs2_releasepage() %p\n", inode);
	fs_warn(sdp, "blkno = %llu, bh->b_count = %d\n",
		(unsigned long long)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, (unsigned long long)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",
			(unsigned long long)ip->i_no_formal_ino,
			(unsigned long long)ip->i_no_addr);

		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_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
 */

int gfs2_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 = jiffies + gfs2_tune_get(sdp, gt_stall_secs) * HZ;

	if (!page_has_buffers(page))
		goto out;

	head = bh = page_buffers(page);
	do {
		while (atomic_read(&bh->b_count)) {
			if (!atomic_read(&aspace->i_writecount))
				return 0;

			if (!(gfp_mask & __GFP_WAIT))
				return 0;

			if (time_after_eq(jiffies, t)) {
				stuck_releasepage(bh);
				/* should we withdraw here? */
				return 0;
			}

			yield();
		}

		gfs2_assert_warn(sdp, !buffer_pinned(bh));
		gfs2_assert_warn(sdp, !buffer_dirty(bh));

		gfs2_log_lock(sdp);
		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, !bd->bd_ail);
			bd->bd_bh = NULL;
			if (!list_empty(&bd->bd_le.le_list))
				bd = NULL;
			bh->b_private = NULL;
		}
		gfs2_log_unlock(sdp);
		if (bd)
			kmem_cache_free(gfs2_bufdata_cachep, bd);

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

out:
	return try_to_free_buffers(page);
}

const struct address_space_operations gfs2_file_aops = {
	.writepage = gfs2_writepage,
	.writepages = gfs2_writepages,
	.readpage = gfs2_readpage,
	.readpages = gfs2_readpages,
	.sync_page = block_sync_page,
	.prepare_write = gfs2_prepare_write,
	.commit_write = gfs2_commit_write,
	.set_page_dirty = gfs2_set_page_dirty,
	.bmap = gfs2_bmap,
	.invalidatepage = gfs2_invalidatepage,
	.releasepage = gfs2_releasepage,
	.direct_IO = gfs2_direct_IO,
};