summaryrefslogtreecommitdiff
path: root/fs/afs/write.c
blob: aa03d43984b37cb4916538dd6b7fa54aa2e47e4e (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
/* handling of writes to regular files and writing back to the server
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * 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; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include "internal.h"

static int afs_write_back_from_locked_page(struct afs_writeback *wb,
					   struct page *page);

/*
 * mark a page as having been made dirty and thus needing writeback
 */
int afs_set_page_dirty(struct page *page)
{
	_enter("");
	return __set_page_dirty_nobuffers(page);
}

/*
 * unlink a writeback record because its usage has reached zero
 * - must be called with the wb->vnode->writeback_lock held
 */
static void afs_unlink_writeback(struct afs_writeback *wb)
{
	struct afs_writeback *front;
	struct afs_vnode *vnode = wb->vnode;

	list_del_init(&wb->link);
	if (!list_empty(&vnode->writebacks)) {
		/* if an fsync rises to the front of the queue then wake it
		 * up */
		front = list_entry(vnode->writebacks.next,
				   struct afs_writeback, link);
		if (front->state == AFS_WBACK_SYNCING) {
			_debug("wake up sync");
			front->state = AFS_WBACK_COMPLETE;
			wake_up(&front->waitq);
		}
	}
}

/*
 * free a writeback record
 */
static void afs_free_writeback(struct afs_writeback *wb)
{
	_enter("");
	key_put(wb->key);
	kfree(wb);
}

/*
 * dispose of a reference to a writeback record
 */
void afs_put_writeback(struct afs_writeback *wb)
{
	struct afs_vnode *vnode = wb->vnode;

	_enter("{%d}", wb->usage);

	spin_lock(&vnode->writeback_lock);
	if (--wb->usage == 0)
		afs_unlink_writeback(wb);
	else
		wb = NULL;
	spin_unlock(&vnode->writeback_lock);
	if (wb)
		afs_free_writeback(wb);
}

/*
 * partly or wholly fill a page that's under preparation for writing
 */
static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
			 unsigned start, unsigned len, struct page *page)
{
	int ret;

	_enter(",,%u,%u", start, len);

	ASSERTCMP(start + len, <=, PAGE_SIZE);

	ret = afs_vnode_fetch_data(vnode, key, start, len, page);
	if (ret < 0) {
		if (ret == -ENOENT) {
			_debug("got NOENT from server"
			       " - marking file deleted and stale");
			set_bit(AFS_VNODE_DELETED, &vnode->flags);
			ret = -ESTALE;
		}
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * prepare a page for being written to
 */
static int afs_prepare_page(struct afs_vnode *vnode, struct page *page,
			    struct key *key, unsigned offset, unsigned to)
{
	unsigned eof, tail, start, stop, len;
	loff_t i_size, pos;
	void *p;
	int ret;

	_enter("");

	if (offset == 0 && to == PAGE_SIZE)
		return 0;

	p = kmap_atomic(page, KM_USER0);

	i_size = i_size_read(&vnode->vfs_inode);
	pos = (loff_t) page->index << PAGE_SHIFT;
	if (pos >= i_size) {
		/* partial write, page beyond EOF */
		_debug("beyond");
		if (offset > 0)
			memset(p, 0, offset);
		if (to < PAGE_SIZE)
			memset(p + to, 0, PAGE_SIZE - to);
		kunmap_atomic(p, KM_USER0);
		return 0;
	}

	if (i_size - pos >= PAGE_SIZE) {
		/* partial write, page entirely before EOF */
		_debug("before");
		tail = eof = PAGE_SIZE;
	} else {
		/* partial write, page overlaps EOF */
		eof = i_size - pos;
		_debug("overlap %u", eof);
		tail = max(eof, to);
		if (tail < PAGE_SIZE)
			memset(p + tail, 0, PAGE_SIZE - tail);
		if (offset > eof)
			memset(p + eof, 0, PAGE_SIZE - eof);
	}

	kunmap_atomic(p, KM_USER0);

	ret = 0;
	if (offset > 0 || eof > to) {
		/* need to fill one or two bits that aren't going to be written
		 * (cover both fillers in one read if there are two) */
		start = (offset > 0) ? 0 : to;
		stop = (eof > to) ? eof : offset;
		len = stop - start;
		_debug("wr=%u-%u av=0-%u rd=%u@%u",
		       offset, to, eof, start, len);
		ret = afs_fill_page(vnode, key, start, len, page);
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * prepare to perform part of a write to a page
 * - the caller holds the page locked, preventing it from being written out or
 *   modified by anyone else
 */
int afs_prepare_write(struct file *file, struct page *page,
		      unsigned offset, unsigned to)
{
	struct afs_writeback *candidate, *wb;
	struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
	struct key *key = file->private_data;
	pgoff_t index;
	int ret;

	_enter("{%x:%u},{%lx},%u,%u",
	       vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);

	candidate = kzalloc(sizeof(*candidate), GFP_KERNEL);
	if (!candidate)
		return -ENOMEM;
	candidate->vnode = vnode;
	candidate->first = candidate->last = page->index;
	candidate->offset_first = offset;
	candidate->to_last = to;
	candidate->usage = 1;
	candidate->state = AFS_WBACK_PENDING;
	init_waitqueue_head(&candidate->waitq);

	if (!PageUptodate(page)) {
		_debug("not up to date");
		ret = afs_prepare_page(vnode, page, key, offset, to);
		if (ret < 0) {
			kfree(candidate);
			_leave(" = %d [prep]", ret);
			return ret;
		}
		SetPageUptodate(page);
	}

try_again:
	index = page->index;
	spin_lock(&vnode->writeback_lock);

	/* see if this page is already pending a writeback under a suitable key
	 * - if so we can just join onto that one */
	wb = (struct afs_writeback *) page_private(page);
	if (wb) {
		if (wb->key == key && wb->state == AFS_WBACK_PENDING)
			goto subsume_in_current_wb;
		goto flush_conflicting_wb;
	}

	if (index > 0) {
		/* see if we can find an already pending writeback that we can
		 * append this page to */
		list_for_each_entry(wb, &vnode->writebacks, link) {
			if (wb->last == index - 1 && wb->key == key &&
			    wb->state == AFS_WBACK_PENDING)
				goto append_to_previous_wb;
		}
	}

	list_add_tail(&candidate->link, &vnode->writebacks);
	candidate->key = key_get(key);
	spin_unlock(&vnode->writeback_lock);
	SetPagePrivate(page);
	set_page_private(page, (unsigned long) candidate);
	_leave(" = 0 [new]");
	return 0;

subsume_in_current_wb:
	_debug("subsume");
	ASSERTRANGE(wb->first, <=, index, <=, wb->last);
	if (index == wb->first && offset < wb->offset_first)
		wb->offset_first = offset;
	if (index == wb->last && to > wb->to_last)
		wb->to_last = to;
	spin_unlock(&vnode->writeback_lock);
	kfree(candidate);
	_leave(" = 0 [sub]");
	return 0;

append_to_previous_wb:
	_debug("append into %lx-%lx", wb->first, wb->last);
	wb->usage++;
	wb->last++;
	wb->to_last = to;
	spin_unlock(&vnode->writeback_lock);
	SetPagePrivate(page);
	set_page_private(page, (unsigned long) wb);
	kfree(candidate);
	_leave(" = 0 [app]");
	return 0;

	/* the page is currently bound to another context, so if it's dirty we
	 * need to flush it before we can use the new context */
flush_conflicting_wb:
	_debug("flush conflict");
	if (wb->state == AFS_WBACK_PENDING)
		wb->state = AFS_WBACK_CONFLICTING;
	spin_unlock(&vnode->writeback_lock);
	if (PageDirty(page)) {
		ret = afs_write_back_from_locked_page(wb, page);
		if (ret < 0) {
			afs_put_writeback(candidate);
			_leave(" = %d", ret);
			return ret;
		}
	}

	/* the page holds a ref on the writeback record */
	afs_put_writeback(wb);
	set_page_private(page, 0);
	ClearPagePrivate(page);
	goto try_again;
}

/*
 * finalise part of a write to a page
 */
int afs_commit_write(struct file *file, struct page *page,
		     unsigned offset, unsigned to)
{
	struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
	loff_t i_size, maybe_i_size;

	_enter("{%x:%u},{%lx},%u,%u",
	       vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);

	maybe_i_size = (loff_t) page->index << PAGE_SHIFT;
	maybe_i_size += to;

	i_size = i_size_read(&vnode->vfs_inode);
	if (maybe_i_size > i_size) {
		spin_lock(&vnode->writeback_lock);
		i_size = i_size_read(&vnode->vfs_inode);
		if (maybe_i_size > i_size)
			i_size_write(&vnode->vfs_inode, maybe_i_size);
		spin_unlock(&vnode->writeback_lock);
	}

	set_page_dirty(page);

	if (PageDirty(page))
		_debug("dirtied");

	return 0;
}

/*
 * kill all the pages in the given range
 */
static void afs_kill_pages(struct afs_vnode *vnode, bool error,
			   pgoff_t first, pgoff_t last)
{
	struct pagevec pv;
	unsigned count, loop;

	_enter("{%x:%u},%lx-%lx",
	       vnode->fid.vid, vnode->fid.vnode, first, last);

	pagevec_init(&pv, 0);

	do {
		_debug("kill %lx-%lx", first, last);

		count = last - first + 1;
		if (count > PAGEVEC_SIZE)
			count = PAGEVEC_SIZE;
		pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping,
					      first, count, pv.pages);
		ASSERTCMP(pv.nr, ==, count);

		for (loop = 0; loop < count; loop++) {
			ClearPageUptodate(pv.pages[loop]);
			if (error)
				SetPageError(pv.pages[loop]);
			end_page_writeback(pv.pages[loop]);
		}

		__pagevec_release(&pv);
	} while (first < last);

	_leave("");
}

/*
 * synchronously write back the locked page and any subsequent non-locked dirty
 * pages also covered by the same writeback record
 */
static int afs_write_back_from_locked_page(struct afs_writeback *wb,
					   struct page *primary_page)
{
	struct page *pages[8], *page;
	unsigned long count;
	unsigned n, offset, to;
	pgoff_t start, first, last;
	int loop, ret;

	_enter(",%lx", primary_page->index);

	count = 1;
	if (!clear_page_dirty_for_io(primary_page))
		BUG();
	if (test_set_page_writeback(primary_page))
		BUG();

	/* find all consecutive lockable dirty pages, stopping when we find a
	 * page that is not immediately lockable, is not dirty or is missing,
	 * or we reach the end of the range */
	start = primary_page->index;
	if (start >= wb->last)
		goto no_more;
	start++;
	do {
		_debug("more %lx [%lx]", start, count);
		n = wb->last - start + 1;
		if (n > ARRAY_SIZE(pages))
			n = ARRAY_SIZE(pages);
		n = find_get_pages_contig(wb->vnode->vfs_inode.i_mapping,
					  start, n, pages);
		_debug("fgpc %u", n);
		if (n == 0)
			goto no_more;
		if (pages[0]->index != start) {
			for (n--; n >= 0; n--)
				put_page(pages[n]);
			goto no_more;
		}

		for (loop = 0; loop < n; loop++) {
			page = pages[loop];
			if (page->index > wb->last)
				break;
			if (TestSetPageLocked(page))
				break;
			if (!PageDirty(page) ||
			    page_private(page) != (unsigned long) wb) {
				unlock_page(page);
				break;
			}
			if (!clear_page_dirty_for_io(page))
				BUG();
			if (test_set_page_writeback(page))
				BUG();
			unlock_page(page);
			put_page(page);
		}
		count += loop;
		if (loop < n) {
			for (; loop < n; loop++)
				put_page(pages[loop]);
			goto no_more;
		}

		start += loop;
	} while (start <= wb->last && count < 65536);

no_more:
	/* we now have a contiguous set of dirty pages, each with writeback set
	 * and the dirty mark cleared; the first page is locked and must remain
	 * so, all the rest are unlocked */
	first = primary_page->index;
	last = first + count - 1;

	offset = (first == wb->first) ? wb->offset_first : 0;
	to = (last == wb->last) ? wb->to_last : PAGE_SIZE;

	_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);

	ret = afs_vnode_store_data(wb, first, last, offset, to);
	if (ret < 0) {
		switch (ret) {
		case -EDQUOT:
		case -ENOSPC:
			set_bit(AS_ENOSPC,
				&wb->vnode->vfs_inode.i_mapping->flags);
			break;
		case -EROFS:
		case -EIO:
		case -EREMOTEIO:
		case -EFBIG:
		case -ENOENT:
		case -ENOMEDIUM:
		case -ENXIO:
			afs_kill_pages(wb->vnode, true, first, last);
			set_bit(AS_EIO, &wb->vnode->vfs_inode.i_mapping->flags);
			break;
		case -EACCES:
		case -EPERM:
		case -ENOKEY:
		case -EKEYEXPIRED:
		case -EKEYREJECTED:
		case -EKEYREVOKED:
			afs_kill_pages(wb->vnode, false, first, last);
			break;
		default:
			break;
		}
	} else {
		ret = count;
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * write a page back to the server
 * - the caller locked the page for us
 */
int afs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct backing_dev_info *bdi = page->mapping->backing_dev_info;
	struct afs_writeback *wb;
	int ret;

	_enter("{%lx},", page->index);

	wb = (struct afs_writeback *) page_private(page);
	ASSERT(wb != NULL);

	ret = afs_write_back_from_locked_page(wb, page);
	unlock_page(page);
	if (ret < 0) {
		_leave(" = %d", ret);
		return 0;
	}

	wbc->nr_to_write -= ret;
	if (wbc->nonblocking && bdi_write_congested(bdi))
		wbc->encountered_congestion = 1;

	_leave(" = 0");
	return 0;
}

/*
 * write a region of pages back to the server
 */
int afs_writepages_region(struct address_space *mapping,
			  struct writeback_control *wbc,
			  pgoff_t index, pgoff_t end, pgoff_t *_next)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	struct afs_writeback *wb;
	struct page *page;
	int ret, n;

	_enter(",,%lx,%lx,", index, end);

	do {
		n = find_get_pages_tag(mapping, &index, PAGECACHE_TAG_DIRTY,
				       1, &page);
		if (!n)
			break;

		_debug("wback %lx", page->index);

		if (page->index > end) {
			*_next = index;
			page_cache_release(page);
			_leave(" = 0 [%lx]", *_next);
			return 0;
		}

		/* at this point we hold neither mapping->tree_lock nor lock on
		 * the page itself: the page may be truncated or invalidated
		 * (changing page->mapping to NULL), or even swizzled back from
		 * swapper_space to tmpfs file mapping
		 */
		lock_page(page);

		if (page->mapping != mapping) {
			unlock_page(page);
			page_cache_release(page);
			continue;
		}

		if (wbc->sync_mode != WB_SYNC_NONE)
			wait_on_page_writeback(page);

		if (PageWriteback(page) || !PageDirty(page)) {
			unlock_page(page);
			continue;
		}

		wb = (struct afs_writeback *) page_private(page);
		ASSERT(wb != NULL);

		spin_lock(&wb->vnode->writeback_lock);
		wb->state = AFS_WBACK_WRITING;
		spin_unlock(&wb->vnode->writeback_lock);

		ret = afs_write_back_from_locked_page(wb, page);
		unlock_page(page);
		page_cache_release(page);
		if (ret < 0) {
			_leave(" = %d", ret);
			return ret;
		}

		wbc->nr_to_write -= ret;

		if (wbc->nonblocking && bdi_write_congested(bdi)) {
			wbc->encountered_congestion = 1;
			break;
		}

		cond_resched();
	} while (index < end && wbc->nr_to_write > 0);

	*_next = index;
	_leave(" = 0 [%lx]", *_next);
	return 0;
}

/*
 * write some of the pending data back to the server
 */
int afs_writepages(struct address_space *mapping,
		   struct writeback_control *wbc)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	pgoff_t start, end, next;
	int ret;

	_enter("");

	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		_leave(" = 0 [congest]");
		return 0;
	}

	if (wbc->range_cyclic) {
		start = mapping->writeback_index;
		end = -1;
		ret = afs_writepages_region(mapping, wbc, start, end, &next);
		if (start > 0 && wbc->nr_to_write > 0 && ret == 0 &&
		    !(wbc->nonblocking && wbc->encountered_congestion))
			ret = afs_writepages_region(mapping, wbc, 0, start,
						    &next);
		mapping->writeback_index = next;
	} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
		end = (pgoff_t)(LLONG_MAX >> PAGE_CACHE_SHIFT);
		ret = afs_writepages_region(mapping, wbc, 0, end, &next);
		if (wbc->nr_to_write > 0)
			mapping->writeback_index = next;
	} else {
		start = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		ret = afs_writepages_region(mapping, wbc, start, end, &next);
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * write an inode back
 */
int afs_write_inode(struct inode *inode, int sync)
{
	struct afs_vnode *vnode = AFS_FS_I(inode);
	int ret;

	_enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode);

	ret = 0;
	if (sync) {
		ret = filemap_fdatawait(inode->i_mapping);
		if (ret < 0)
			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
	}

	_leave(" = %d", ret);
	return ret;
}

/*
 * completion of write to server
 */
void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
{
	struct afs_writeback *wb = call->wb;
	struct pagevec pv;
	unsigned count, loop;
	pgoff_t first = call->first, last = call->last;
	bool free_wb;

	_enter("{%x:%u},{%lx-%lx}",
	       vnode->fid.vid, vnode->fid.vnode, first, last);

	ASSERT(wb != NULL);

	pagevec_init(&pv, 0);

	do {
		_debug("attach %lx-%lx", first, last);

		count = last - first + 1;
		if (count > PAGEVEC_SIZE)
			count = PAGEVEC_SIZE;
		pv.nr = find_get_pages_contig(call->mapping, first, count,
					      pv.pages);
		ASSERTCMP(pv.nr, ==, count);

		spin_lock(&vnode->writeback_lock);
		for (loop = 0; loop < count; loop++) {
			struct page *page = pv.pages[loop];
			end_page_writeback(page);
			if (page_private(page) == (unsigned long) wb) {
				set_page_private(page, 0);
				ClearPagePrivate(page);
				wb->usage--;
			}
		}
		free_wb = false;
		if (wb->usage == 0) {
			afs_unlink_writeback(wb);
			free_wb = true;
		}
		spin_unlock(&vnode->writeback_lock);
		first += count;
		if (free_wb) {
			afs_free_writeback(wb);
			wb = NULL;
		}

		__pagevec_release(&pv);
	} while (first < last);

	_leave("");
}

/*
 * write to an AFS file
 */
ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
		       unsigned long nr_segs, loff_t pos)
{
	struct dentry *dentry = iocb->ki_filp->f_path.dentry;
	struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
	ssize_t result;
	size_t count = iov_length(iov, nr_segs);
	int ret;

	_enter("{%x.%u},{%zu},%lu,",
	       vnode->fid.vid, vnode->fid.vnode, count, nr_segs);

	if (IS_SWAPFILE(&vnode->vfs_inode)) {
		printk(KERN_INFO
		       "AFS: Attempt to write to active swap file!\n");
		return -EBUSY;
	}

	if (!count)
		return 0;

	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
	if (IS_ERR_VALUE(result)) {
		_leave(" = %zd", result);
		return result;
	}

	/* return error values for O_SYNC and IS_SYNC() */
	if (IS_SYNC(&vnode->vfs_inode) || iocb->ki_filp->f_flags & O_SYNC) {
		ret = afs_fsync(iocb->ki_filp, dentry, 1);
		if (ret < 0)
			result = ret;
	}

	_leave(" = %zd", result);
	return result;
}

/*
 * flush the vnode to the fileserver
 */
int afs_writeback_all(struct afs_vnode *vnode)
{
	struct address_space *mapping = vnode->vfs_inode.i_mapping;
	struct writeback_control wbc = {
		.bdi		= mapping->backing_dev_info,
		.sync_mode	= WB_SYNC_ALL,
		.nr_to_write	= LONG_MAX,
		.for_writepages = 1,
		.range_cyclic	= 1,
	};
	int ret;

	_enter("");

	ret = mapping->a_ops->writepages(mapping, &wbc);
	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	_leave(" = %d", ret);
	return ret;
}

/*
 * flush any dirty pages for this process, and check for write errors.
 * - the return status from this call provides a reliable indication of
 *   whether any write errors occurred for this process.
 */
int afs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	struct afs_writeback *wb, *xwb;
	struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
	int ret;

	_enter("{%x:%u},{n=%s},%d",
	       vnode->fid.vid, vnode->fid.vnode, dentry->d_name.name,
	       datasync);

	/* use a writeback record as a marker in the queue - when this reaches
	 * the front of the queue, all the outstanding writes are either
	 * completed or rejected */
	wb = kzalloc(sizeof(*wb), GFP_KERNEL);
	if (!wb)
		return -ENOMEM;
	wb->vnode = vnode;
	wb->first = 0;
	wb->last = -1;
	wb->offset_first = 0;
	wb->to_last = PAGE_SIZE;
	wb->usage = 1;
	wb->state = AFS_WBACK_SYNCING;
	init_waitqueue_head(&wb->waitq);

	spin_lock(&vnode->writeback_lock);
	list_for_each_entry(xwb, &vnode->writebacks, link) {
		if (xwb->state == AFS_WBACK_PENDING)
			xwb->state = AFS_WBACK_CONFLICTING;
	}
	list_add_tail(&wb->link, &vnode->writebacks);
	spin_unlock(&vnode->writeback_lock);

	/* push all the outstanding writebacks to the server */
	ret = afs_writeback_all(vnode);
	if (ret < 0) {
		afs_put_writeback(wb);
		_leave(" = %d [wb]", ret);
		return ret;
	}

	/* wait for the preceding writes to actually complete */
	ret = wait_event_interruptible(wb->waitq,
				       wb->state == AFS_WBACK_COMPLETE ||
				       vnode->writebacks.next == &wb->link);
	afs_put_writeback(wb);
	_leave(" = %d", ret);
	return ret;
}