summaryrefslogtreecommitdiff
path: root/fs/exofs/inode.c
blob: a3691d8bfb98a935e7cc11dd37a6a7fb425d403e (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
/*
 * Copyright (C) 2005, 2006
 * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
 * Copyright (C) 2005, 2006
 * International Business Machines
 * Copyright (C) 2008, 2009
 * Boaz Harrosh <bharrosh@panasas.com>
 *
 * Copyrights for code taken from ext2:
 *     Copyright (C) 1992, 1993, 1994, 1995
 *     Remy Card (card@masi.ibp.fr)
 *     Laboratoire MASI - Institut Blaise Pascal
 *     Universite Pierre et Marie Curie (Paris VI)
 *     from
 *     linux/fs/minix/inode.c
 *     Copyright (C) 1991, 1992  Linus Torvalds
 *
 * This file is part of exofs.
 *
 * exofs 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.  Since it is based on ext2, and the only
 * valid version of GPL for the Linux kernel is version 2, the only valid
 * version of GPL for exofs is version 2.
 *
 * exofs is distributed in the hope that it will 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 exofs; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <scsi/scsi_device.h>

#include "exofs.h"

#ifdef CONFIG_EXOFS_DEBUG
#  define EXOFS_DEBUG_OBJ_ISIZE 1
#endif

struct page_collect {
	struct exofs_sb_info *sbi;
	struct request_queue *req_q;
	struct inode *inode;
	unsigned expected_pages;

	struct bio *bio;
	unsigned nr_pages;
	unsigned long length;
	loff_t pg_first; /* keep 64bit also in 32-arches */
};

static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
		struct inode *inode)
{
	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
	struct request_queue *req_q = sbi->s_dev->scsi_device->request_queue;

	pcol->sbi = sbi;
	pcol->req_q = req_q;
	pcol->inode = inode;
	pcol->expected_pages = expected_pages;

	pcol->bio = NULL;
	pcol->nr_pages = 0;
	pcol->length = 0;
	pcol->pg_first = -1;

	EXOFS_DBGMSG("_pcol_init ino=0x%lx expected_pages=%u\n", inode->i_ino,
		     expected_pages);
}

static void _pcol_reset(struct page_collect *pcol)
{
	pcol->expected_pages -= min(pcol->nr_pages, pcol->expected_pages);

	pcol->bio = NULL;
	pcol->nr_pages = 0;
	pcol->length = 0;
	pcol->pg_first = -1;
	EXOFS_DBGMSG("_pcol_reset ino=0x%lx expected_pages=%u\n",
		     pcol->inode->i_ino, pcol->expected_pages);

	/* this is probably the end of the loop but in writes
	 * it might not end here. don't be left with nothing
	 */
	if (!pcol->expected_pages)
		pcol->expected_pages = 128;
}

static int pcol_try_alloc(struct page_collect *pcol)
{
	int pages = min_t(unsigned, pcol->expected_pages, BIO_MAX_PAGES);

	for (; pages; pages >>= 1) {
		pcol->bio = bio_alloc(GFP_KERNEL, pages);
		if (likely(pcol->bio))
			return 0;
	}

	EXOFS_ERR("Failed to kcalloc expected_pages=%u\n",
		  pcol->expected_pages);
	return -ENOMEM;
}

static void pcol_free(struct page_collect *pcol)
{
	bio_put(pcol->bio);
	pcol->bio = NULL;
}

static int pcol_add_page(struct page_collect *pcol, struct page *page,
			 unsigned len)
{
	int added_len = bio_add_pc_page(pcol->req_q, pcol->bio, page, len, 0);
	if (unlikely(len != added_len))
		return -ENOMEM;

	++pcol->nr_pages;
	pcol->length += len;
	return 0;
}

static int update_read_page(struct page *page, int ret)
{
	if (ret == 0) {
		/* Everything is OK */
		SetPageUptodate(page);
		if (PageError(page))
			ClearPageError(page);
	} else if (ret == -EFAULT) {
		/* In this case we were trying to read something that wasn't on
		 * disk yet - return a page full of zeroes.  This should be OK,
		 * because the object should be empty (if there was a write
		 * before this read, the read would be waiting with the page
		 * locked */
		clear_highpage(page);

		SetPageUptodate(page);
		if (PageError(page))
			ClearPageError(page);
		ret = 0; /* recovered error */
		EXOFS_DBGMSG("recovered read error\n");
	} else /* Error */
		SetPageError(page);

	return ret;
}

static void update_write_page(struct page *page, int ret)
{
	if (ret) {
		mapping_set_error(page->mapping, ret);
		SetPageError(page);
	}
	end_page_writeback(page);
}

/* Called at the end of reads, to optionally unlock pages and update their
 * status.
 */
static int __readpages_done(struct osd_request *or, struct page_collect *pcol,
			    bool do_unlock)
{
	struct bio_vec *bvec;
	int i;
	u64 resid;
	u64 good_bytes;
	u64 length = 0;
	int ret = exofs_check_ok_resid(or, &resid, NULL);

	osd_end_request(or);

	if (likely(!ret))
		good_bytes = pcol->length;
	else if (!resid)
		good_bytes = 0;
	else
		good_bytes = pcol->length - resid;

	EXOFS_DBGMSG("readpages_done(0x%lx) good_bytes=0x%llx"
		     " length=0x%lx nr_pages=%u\n",
		     pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
		     pcol->nr_pages);

	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
		struct page *page = bvec->bv_page;
		struct inode *inode = page->mapping->host;
		int page_stat;

		if (inode != pcol->inode)
			continue; /* osd might add more pages at end */

		if (likely(length < good_bytes))
			page_stat = 0;
		else
			page_stat = ret;

		EXOFS_DBGMSG("    readpages_done(0x%lx, 0x%lx) %s\n",
			  inode->i_ino, page->index,
			  page_stat ? "bad_bytes" : "good_bytes");

		ret = update_read_page(page, page_stat);
		if (do_unlock)
			unlock_page(page);
		length += bvec->bv_len;
	}

	pcol_free(pcol);
	EXOFS_DBGMSG("readpages_done END\n");
	return ret;
}

/* callback of async reads */
static void readpages_done(struct osd_request *or, void *p)
{
	struct page_collect *pcol = p;

	__readpages_done(or, pcol, true);
	atomic_dec(&pcol->sbi->s_curr_pending);
	kfree(p);
}

static void _unlock_pcol_pages(struct page_collect *pcol, int ret, int rw)
{
	struct bio_vec *bvec;
	int i;

	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
		struct page *page = bvec->bv_page;

		if (rw == READ)
			update_read_page(page, ret);
		else
			update_write_page(page, ret);

		unlock_page(page);
	}
	pcol_free(pcol);
}

static int read_exec(struct page_collect *pcol, bool is_sync)
{
	struct exofs_i_info *oi = exofs_i(pcol->inode);
	struct osd_obj_id obj = {pcol->sbi->s_pid,
					pcol->inode->i_ino + EXOFS_OBJ_OFF};
	struct osd_request *or = NULL;
	struct page_collect *pcol_copy = NULL;
	loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
	int ret;

	if (!pcol->bio)
		return 0;

	/* see comment in _readpage() about sync reads */
	WARN_ON(is_sync && (pcol->nr_pages != 1));

	or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		ret = -ENOMEM;
		goto err;
	}

	osd_req_read(or, &obj, pcol->bio, i_start);

	if (is_sync) {
		exofs_sync_op(or, pcol->sbi->s_timeout, oi->i_cred);
		return __readpages_done(or, pcol, false);
	}

	pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
	if (!pcol_copy) {
		ret = -ENOMEM;
		goto err;
	}

	*pcol_copy = *pcol;
	ret = exofs_async_op(or, readpages_done, pcol_copy, oi->i_cred);
	if (unlikely(ret))
		goto err;

	atomic_inc(&pcol->sbi->s_curr_pending);

	EXOFS_DBGMSG("read_exec obj=0x%llx start=0x%llx length=0x%lx\n",
		  obj.id, _LLU(i_start), pcol->length);

	/* pages ownership was passed to pcol_copy */
	_pcol_reset(pcol);
	return 0;

err:
	if (!is_sync)
		_unlock_pcol_pages(pcol, ret, READ);
	kfree(pcol_copy);
	if (or)
		osd_end_request(or);
	return ret;
}

/* readpage_strip is called either directly from readpage() or by the VFS from
 * within read_cache_pages(), to add one more page to be read. It will try to
 * collect as many contiguous pages as posible. If a discontinuity is
 * encountered, or it runs out of resources, it will submit the previous segment
 * and will start a new collection. Eventually caller must submit the last
 * segment if present.
 */
static int readpage_strip(void *data, struct page *page)
{
	struct page_collect *pcol = data;
	struct inode *inode = pcol->inode;
	struct exofs_i_info *oi = exofs_i(inode);
	loff_t i_size = i_size_read(inode);
	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	size_t len;
	int ret;

	/* FIXME: Just for debugging, will be removed */
	if (PageUptodate(page))
		EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino,
			  page->index);

	if (page->index < end_index)
		len = PAGE_CACHE_SIZE;
	else if (page->index == end_index)
		len = i_size & ~PAGE_CACHE_MASK;
	else
		len = 0;

	if (!len || !obj_created(oi)) {
		/* this will be out of bounds, or doesn't exist yet.
		 * Current page is cleared and the request is split
		 */
		clear_highpage(page);

		SetPageUptodate(page);
		if (PageError(page))
			ClearPageError(page);

		unlock_page(page);
		EXOFS_DBGMSG("readpage_strip(0x%lx, 0x%lx) empty page,"
			     " splitting\n", inode->i_ino, page->index);

		return read_exec(pcol, false);
	}

try_again:

	if (unlikely(pcol->pg_first == -1)) {
		pcol->pg_first = page->index;
	} else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
		   page->index)) {
		/* Discontinuity detected, split the request */
		ret = read_exec(pcol, false);
		if (unlikely(ret))
			goto fail;
		goto try_again;
	}

	if (!pcol->bio) {
		ret = pcol_try_alloc(pcol);
		if (unlikely(ret))
			goto fail;
	}

	if (len != PAGE_CACHE_SIZE)
		zero_user(page, len, PAGE_CACHE_SIZE - len);

	EXOFS_DBGMSG("    readpage_strip(0x%lx, 0x%lx) len=0x%zx\n",
		     inode->i_ino, page->index, len);

	ret = pcol_add_page(pcol, page, len);
	if (ret) {
		EXOFS_DBGMSG("Failed pcol_add_page pages[i]=%p "
			  "this_len=0x%zx nr_pages=%u length=0x%lx\n",
			  page, len, pcol->nr_pages, pcol->length);

		/* split the request, and start again with current page */
		ret = read_exec(pcol, false);
		if (unlikely(ret))
			goto fail;

		goto try_again;
	}

	return 0;

fail:
	/* SetPageError(page); ??? */
	unlock_page(page);
	return ret;
}

static int exofs_readpages(struct file *file, struct address_space *mapping,
			   struct list_head *pages, unsigned nr_pages)
{
	struct page_collect pcol;
	int ret;

	_pcol_init(&pcol, nr_pages, mapping->host);

	ret = read_cache_pages(mapping, pages, readpage_strip, &pcol);
	if (ret) {
		EXOFS_ERR("read_cache_pages => %d\n", ret);
		return ret;
	}

	return read_exec(&pcol, false);
}

static int _readpage(struct page *page, bool is_sync)
{
	struct page_collect pcol;
	int ret;

	_pcol_init(&pcol, 1, page->mapping->host);

	/* readpage_strip might call read_exec(,async) inside at several places
	 * but this is safe for is_async=0 since read_exec will not do anything
	 * when we have a single page.
	 */
	ret = readpage_strip(&pcol, page);
	if (ret) {
		EXOFS_ERR("_readpage => %d\n", ret);
		return ret;
	}

	return read_exec(&pcol, is_sync);
}

/*
 * We don't need the file
 */
static int exofs_readpage(struct file *file, struct page *page)
{
	return _readpage(page, false);
}

/* Callback for osd_write. All writes are asynchronouse */
static void writepages_done(struct osd_request *or, void *p)
{
	struct page_collect *pcol = p;
	struct bio_vec *bvec;
	int i;
	u64 resid;
	u64  good_bytes;
	u64  length = 0;

	int ret = exofs_check_ok_resid(or, NULL, &resid);

	osd_end_request(or);
	atomic_dec(&pcol->sbi->s_curr_pending);

	if (likely(!ret))
		good_bytes = pcol->length;
	else if (!resid)
		good_bytes = 0;
	else
		good_bytes = pcol->length - resid;

	EXOFS_DBGMSG("writepages_done(0x%lx) good_bytes=0x%llx"
		     " length=0x%lx nr_pages=%u\n",
		     pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
		     pcol->nr_pages);

	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
		struct page *page = bvec->bv_page;
		struct inode *inode = page->mapping->host;
		int page_stat;

		if (inode != pcol->inode)
			continue; /* osd might add more pages to a bio */

		if (likely(length < good_bytes))
			page_stat = 0;
		else
			page_stat = ret;

		update_write_page(page, page_stat);
		unlock_page(page);
		EXOFS_DBGMSG("    writepages_done(0x%lx, 0x%lx) status=%d\n",
			     inode->i_ino, page->index, page_stat);

		length += bvec->bv_len;
	}

	pcol_free(pcol);
	kfree(pcol);
	EXOFS_DBGMSG("writepages_done END\n");
}

static int write_exec(struct page_collect *pcol)
{
	struct exofs_i_info *oi = exofs_i(pcol->inode);
	struct osd_obj_id obj = {pcol->sbi->s_pid,
					pcol->inode->i_ino + EXOFS_OBJ_OFF};
	struct osd_request *or = NULL;
	struct page_collect *pcol_copy = NULL;
	loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
	int ret;

	if (!pcol->bio)
		return 0;

	or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		EXOFS_ERR("write_exec: Faild to osd_start_request()\n");
		ret = -ENOMEM;
		goto err;
	}

	pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
	if (!pcol_copy) {
		EXOFS_ERR("write_exec: Faild to kmalloc(pcol)\n");
		ret = -ENOMEM;
		goto err;
	}

	*pcol_copy = *pcol;

	osd_req_write(or, &obj, pcol_copy->bio, i_start);
	ret = exofs_async_op(or, writepages_done, pcol_copy, oi->i_cred);
	if (unlikely(ret)) {
		EXOFS_ERR("write_exec: exofs_async_op() Faild\n");
		goto err;
	}

	atomic_inc(&pcol->sbi->s_curr_pending);
	EXOFS_DBGMSG("write_exec(0x%lx, 0x%llx) start=0x%llx length=0x%lx\n",
		  pcol->inode->i_ino, pcol->pg_first, _LLU(i_start),
		  pcol->length);
	/* pages ownership was passed to pcol_copy */
	_pcol_reset(pcol);
	return 0;

err:
	_unlock_pcol_pages(pcol, ret, WRITE);
	kfree(pcol_copy);
	if (or)
		osd_end_request(or);
	return ret;
}

/* writepage_strip is called either directly from writepage() or by the VFS from
 * within write_cache_pages(), to add one more page to be written to storage.
 * It will try to collect as many contiguous pages as possible. If a
 * discontinuity is encountered or it runs out of resources it will submit the
 * previous segment and will start a new collection.
 * Eventually caller must submit the last segment if present.
 */
static int writepage_strip(struct page *page,
			   struct writeback_control *wbc_unused, void *data)
{
	struct page_collect *pcol = data;
	struct inode *inode = pcol->inode;
	struct exofs_i_info *oi = exofs_i(inode);
	loff_t i_size = i_size_read(inode);
	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	size_t len;
	int ret;

	BUG_ON(!PageLocked(page));

	ret = wait_obj_created(oi);
	if (unlikely(ret))
		goto fail;

	if (page->index < end_index)
		/* in this case, the page is within the limits of the file */
		len = PAGE_CACHE_SIZE;
	else {
		len = i_size & ~PAGE_CACHE_MASK;

		if (page->index > end_index || !len) {
			/* in this case, the page is outside the limits
			 * (truncate in progress)
			 */
			ret = write_exec(pcol);
			if (unlikely(ret))
				goto fail;
			if (PageError(page))
				ClearPageError(page);
			unlock_page(page);
			return 0;
		}
	}

try_again:

	if (unlikely(pcol->pg_first == -1)) {
		pcol->pg_first = page->index;
	} else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
		   page->index)) {
		/* Discontinuity detected, split the request */
		ret = write_exec(pcol);
		if (unlikely(ret))
			goto fail;
		goto try_again;
	}

	if (!pcol->bio) {
		ret = pcol_try_alloc(pcol);
		if (unlikely(ret))
			goto fail;
	}

	EXOFS_DBGMSG("    writepage_strip(0x%lx, 0x%lx) len=0x%zx\n",
		     inode->i_ino, page->index, len);

	ret = pcol_add_page(pcol, page, len);
	if (unlikely(ret)) {
		EXOFS_DBGMSG("Failed pcol_add_page "
			     "nr_pages=%u total_length=0x%lx\n",
			     pcol->nr_pages, pcol->length);

		/* split the request, next loop will start again */
		ret = write_exec(pcol);
		if (unlikely(ret)) {
			EXOFS_DBGMSG("write_exec faild => %d", ret);
			goto fail;
		}

		goto try_again;
	}

	BUG_ON(PageWriteback(page));
	set_page_writeback(page);

	return 0;

fail:
	set_bit(AS_EIO, &page->mapping->flags);
	unlock_page(page);
	return ret;
}

static int exofs_writepages(struct address_space *mapping,
		       struct writeback_control *wbc)
{
	struct page_collect pcol;
	long start, end, expected_pages;
	int ret;

	start = wbc->range_start >> PAGE_CACHE_SHIFT;
	end = (wbc->range_end == LLONG_MAX) ?
			start + mapping->nrpages :
			wbc->range_end >> PAGE_CACHE_SHIFT;

	if (start || end)
		expected_pages = min(end - start + 1, 32L);
	else
		expected_pages = mapping->nrpages;

	EXOFS_DBGMSG("inode(0x%lx) wbc->start=0x%llx wbc->end=0x%llx"
		     " m->nrpages=%lu start=0x%lx end=0x%lx\n",
		     mapping->host->i_ino, wbc->range_start, wbc->range_end,
		     mapping->nrpages, start, end);

	_pcol_init(&pcol, expected_pages, mapping->host);

	ret = write_cache_pages(mapping, wbc, writepage_strip, &pcol);
	if (ret) {
		EXOFS_ERR("write_cache_pages => %d\n", ret);
		return ret;
	}

	return write_exec(&pcol);
}

static int exofs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct page_collect pcol;
	int ret;

	_pcol_init(&pcol, 1, page->mapping->host);

	ret = writepage_strip(page, NULL, &pcol);
	if (ret) {
		EXOFS_ERR("exofs_writepage => %d\n", ret);
		return ret;
	}

	return write_exec(&pcol);
}

int exofs_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	int ret = 0;
	struct page *page;

	page = *pagep;
	if (page == NULL) {
		ret = simple_write_begin(file, mapping, pos, len, flags, pagep,
					 fsdata);
		if (ret) {
			EXOFS_DBGMSG("simple_write_begin faild\n");
			return ret;
		}

		page = *pagep;
	}

	 /* read modify write */
	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
		ret = _readpage(page, true);
		if (ret) {
			/*SetPageError was done by _readpage. Is it ok?*/
			unlock_page(page);
			EXOFS_DBGMSG("__readpage_filler faild\n");
		}
	}

	return ret;
}

static int exofs_write_begin_export(struct file *file,
		struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	*pagep = NULL;

	return exofs_write_begin(file, mapping, pos, len, flags, pagep,
					fsdata);
}

const struct address_space_operations exofs_aops = {
	.readpage	= exofs_readpage,
	.readpages	= exofs_readpages,
	.writepage	= exofs_writepage,
	.writepages	= exofs_writepages,
	.write_begin	= exofs_write_begin_export,
	.write_end	= simple_write_end,
};

/******************************************************************************
 * INODE OPERATIONS
 *****************************************************************************/

/*
 * Test whether an inode is a fast symlink.
 */
static inline int exofs_inode_is_fast_symlink(struct inode *inode)
{
	struct exofs_i_info *oi = exofs_i(inode);

	return S_ISLNK(inode->i_mode) && (oi->i_data[0] != 0);
}

/*
 * get_block_t - Fill in a buffer_head
 * An OSD takes care of block allocation so we just fake an allocation by
 * putting in the inode's sector_t in the buffer_head.
 * TODO: What about the case of create==0 and @iblock does not exist in the
 * object?
 */
static int exofs_get_block(struct inode *inode, sector_t iblock,
		    struct buffer_head *bh_result, int create)
{
	map_bh(bh_result, inode->i_sb, iblock);
	return 0;
}

const struct osd_attr g_attr_logical_length = ATTR_DEF(
	OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);

/*
 * Truncate a file to the specified size - all we have to do is set the size
 * attribute.  We make sure the object exists first.
 */
void exofs_truncate(struct inode *inode)
{
	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
	struct exofs_i_info *oi = exofs_i(inode);
	struct osd_obj_id obj = {sbi->s_pid, inode->i_ino + EXOFS_OBJ_OFF};
	struct osd_request *or;
	struct osd_attr attr;
	loff_t isize = i_size_read(inode);
	__be64 newsize;
	int ret;

	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
	     || S_ISLNK(inode->i_mode)))
		return;
	if (exofs_inode_is_fast_symlink(inode))
		return;
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return;
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;

	nobh_truncate_page(inode->i_mapping, isize, exofs_get_block);

	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
	if (unlikely(!or)) {
		EXOFS_ERR("ERROR: exofs_truncate: osd_start_request failed\n");
		goto fail;
	}

	osd_req_set_attributes(or, &obj);

	newsize = cpu_to_be64((u64)isize);
	attr = g_attr_logical_length;
	attr.val_ptr = &newsize;
	osd_req_add_set_attr_list(or, &attr, 1);

	/* if we are about to truncate an object, and it hasn't been
	 * created yet, wait
	 */
	if (unlikely(wait_obj_created(oi)))
		goto fail;

	ret = exofs_sync_op(or, sbi->s_timeout, oi->i_cred);
	osd_end_request(or);
	if (ret)
		goto fail;

out:
	mark_inode_dirty(inode);
	return;
fail:
	make_bad_inode(inode);
	goto out;
}

/*
 * Set inode attributes - just call generic functions.
 */
int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct inode *inode = dentry->d_inode;
	int error;

	error = inode_change_ok(inode, iattr);
	if (error)
		return error;

	error = inode_setattr(inode, iattr);
	return error;
}