summaryrefslogtreecommitdiff
path: root/fs/afs/file.c
blob: 85f5adf21aa08a50f372a9db3b5215d3822c3940 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* AFS filesystem file handling
 *
 * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/gfp.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/mm.h>
#include "internal.h"

static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
static int afs_readpage(struct file *file, struct page *page);
static void afs_invalidatepage(struct page *page, unsigned int offset,
			       unsigned int length);
static int afs_releasepage(struct page *page, gfp_t gfp_flags);

static int afs_readpages(struct file *filp, struct address_space *mapping,
			 struct list_head *pages, unsigned nr_pages);

const struct file_operations afs_file_operations = {
	.open		= afs_open,
	.release	= afs_release,
	.llseek		= generic_file_llseek,
	.read_iter	= generic_file_read_iter,
	.write_iter	= afs_file_write,
	.mmap		= afs_file_mmap,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fsync		= afs_fsync,
	.lock		= afs_lock,
	.flock		= afs_flock,
};

const struct inode_operations afs_file_inode_operations = {
	.getattr	= afs_getattr,
	.setattr	= afs_setattr,
	.permission	= afs_permission,
	.listxattr	= afs_listxattr,
};

const struct address_space_operations afs_fs_aops = {
	.readpage	= afs_readpage,
	.readpages	= afs_readpages,
	.set_page_dirty	= afs_set_page_dirty,
	.launder_page	= afs_launder_page,
	.releasepage	= afs_releasepage,
	.invalidatepage	= afs_invalidatepage,
	.write_begin	= afs_write_begin,
	.write_end	= afs_write_end,
	.writepage	= afs_writepage,
	.writepages	= afs_writepages,
};

static const struct vm_operations_struct afs_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= afs_page_mkwrite,
};

/*
 * Discard a pin on a writeback key.
 */
void afs_put_wb_key(struct afs_wb_key *wbk)
{
	if (wbk && refcount_dec_and_test(&wbk->usage)) {
		key_put(wbk->key);
		kfree(wbk);
	}
}

/*
 * Cache key for writeback.
 */
int afs_cache_wb_key(struct afs_vnode *vnode, struct afs_file *af)
{
	struct afs_wb_key *wbk, *p;

	wbk = kzalloc(sizeof(struct afs_wb_key), GFP_KERNEL);
	if (!wbk)
		return -ENOMEM;
	refcount_set(&wbk->usage, 2);
	wbk->key = af->key;

	spin_lock(&vnode->wb_lock);
	list_for_each_entry(p, &vnode->wb_keys, vnode_link) {
		if (p->key == wbk->key)
			goto found;
	}

	key_get(wbk->key);
	list_add_tail(&wbk->vnode_link, &vnode->wb_keys);
	spin_unlock(&vnode->wb_lock);
	af->wb = wbk;
	return 0;

found:
	refcount_inc(&p->usage);
	spin_unlock(&vnode->wb_lock);
	af->wb = p;
	kfree(wbk);
	return 0;
}

/*
 * open an AFS file or directory and attach a key to it
 */
int afs_open(struct inode *inode, struct file *file)
{
	struct afs_vnode *vnode = AFS_FS_I(inode);
	struct afs_file *af;
	struct key *key;
	int ret;

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

	key = afs_request_key(vnode->volume->cell);
	if (IS_ERR(key)) {
		ret = PTR_ERR(key);
		goto error;
	}

	af = kzalloc(sizeof(*af), GFP_KERNEL);
	if (!af) {
		ret = -ENOMEM;
		goto error_key;
	}
	af->key = key;

	ret = afs_validate(vnode, key);
	if (ret < 0)
		goto error_af;

	if (file->f_mode & FMODE_WRITE) {
		ret = afs_cache_wb_key(vnode, af);
		if (ret < 0)
			goto error_af;
	}

	if (file->f_flags & O_TRUNC)
		set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags);
	
	file->private_data = af;
	_leave(" = 0");
	return 0;

error_af:
	kfree(af);
error_key:
	key_put(key);
error:
	_leave(" = %d", ret);
	return ret;
}

/*
 * release an AFS file or directory and discard its key
 */
int afs_release(struct inode *inode, struct file *file)
{
	struct afs_vnode *vnode = AFS_FS_I(inode);
	struct afs_file *af = file->private_data;
	int ret = 0;

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

	if ((file->f_mode & FMODE_WRITE))
		ret = vfs_fsync(file, 0);

	file->private_data = NULL;
	if (af->wb)
		afs_put_wb_key(af->wb);
	key_put(af->key);
	kfree(af);
	afs_prune_wb_keys(vnode);
	_leave(" = %d", ret);
	return ret;
}

/*
 * Dispose of a ref to a read record.
 */
void afs_put_read(struct afs_read *req)
{
	int i;

	if (refcount_dec_and_test(&req->usage)) {
		if (req->pages) {
			for (i = 0; i < req->nr_pages; i++)
				if (req->pages[i])
					put_page(req->pages[i]);
			if (req->pages != req->array)
				kfree(req->pages);
		}
		kfree(req);
	}
}

#ifdef CONFIG_AFS_FSCACHE
/*
 * deal with notification that a page was read from the cache
 */
static void afs_file_readpage_read_complete(struct page *page,
					    void *data,
					    int error)
{
	_enter("%p,%p,%d", page, data, error);

	/* if the read completes with an error, we just unlock the page and let
	 * the VM reissue the readpage */
	if (!error)
		SetPageUptodate(page);
	unlock_page(page);
}
#endif

static void afs_fetch_data_success(struct afs_operation *op)
{
	struct afs_vnode *vnode = op->file[0].vnode;

	_enter("op=%08x", op->debug_id);
	afs_vnode_commit_status(op, &op->file[0]);
	afs_stat_v(vnode, n_fetches);
	atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes);
}

static void afs_fetch_data_put(struct afs_operation *op)
{
	afs_put_read(op->fetch.req);
}

static const struct afs_operation_ops afs_fetch_data_operation = {
	.issue_afs_rpc	= afs_fs_fetch_data,
	.issue_yfs_rpc	= yfs_fs_fetch_data,
	.success	= afs_fetch_data_success,
	.aborted	= afs_check_for_remote_deletion,
	.put		= afs_fetch_data_put,
};

/*
 * Fetch file data from the volume.
 */
int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *req)
{
	struct afs_operation *op;

	_enter("%s{%llx:%llu.%u},%x,,,",
	       vnode->volume->name,
	       vnode->fid.vid,
	       vnode->fid.vnode,
	       vnode->fid.unique,
	       key_serial(key));

	op = afs_alloc_operation(key, vnode->volume);
	if (IS_ERR(op))
		return PTR_ERR(op);

	afs_op_set_vnode(op, 0, vnode);

	op->fetch.req	= afs_get_read(req);
	op->ops		= &afs_fetch_data_operation;
	return afs_do_sync_operation(op);
}

/*
 * read page from file, directory or symlink, given a key to use
 */
int afs_page_filler(void *data, struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct afs_vnode *vnode = AFS_FS_I(inode);
	struct afs_read *req;
	struct key *key = data;
	int ret;

	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);

	BUG_ON(!PageLocked(page));

	ret = -ESTALE;
	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		goto error;

	/* is it cached? */
#ifdef CONFIG_AFS_FSCACHE
	ret = fscache_read_or_alloc_page(vnode->cache,
					 page,
					 afs_file_readpage_read_complete,
					 NULL,
					 GFP_KERNEL);
#else
	ret = -ENOBUFS;
#endif
	switch (ret) {
		/* read BIO submitted (page in cache) */
	case 0:
		break;

		/* page not yet cached */
	case -ENODATA:
		_debug("cache said ENODATA");
		goto go_on;

		/* page will not be cached */
	case -ENOBUFS:
		_debug("cache said ENOBUFS");

		fallthrough;
	default:
	go_on:
		req = kzalloc(struct_size(req, array, 1), GFP_KERNEL);
		if (!req)
			goto enomem;

		/* We request a full page.  If the page is a partial one at the
		 * end of the file, the server will return a short read and the
		 * unmarshalling code will clear the unfilled space.
		 */
		refcount_set(&req->usage, 1);
		req->pos = (loff_t)page->index << PAGE_SHIFT;
		req->len = PAGE_SIZE;
		req->nr_pages = 1;
		req->pages = req->array;
		req->pages[0] = page;
		get_page(page);

		/* read the contents of the file from the server into the
		 * page */
		ret = afs_fetch_data(vnode, key, req);
		afs_put_read(req);

		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;
			}

#ifdef CONFIG_AFS_FSCACHE
			fscache_uncache_page(vnode->cache, page);
#endif
			BUG_ON(PageFsCache(page));

			if (ret == -EINTR ||
			    ret == -ENOMEM ||
			    ret == -ERESTARTSYS ||
			    ret == -EAGAIN)
				goto error;
			goto io_error;
		}

		SetPageUptodate(page);

		/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
		if (PageFsCache(page) &&
		    fscache_write_page(vnode->cache, page, vnode->status.size,
				       GFP_KERNEL) != 0) {
			fscache_uncache_page(vnode->cache, page);
			BUG_ON(PageFsCache(page));
		}
#endif
		unlock_page(page);
	}

	_leave(" = 0");
	return 0;

io_error:
	SetPageError(page);
	goto error;
enomem:
	ret = -ENOMEM;
error:
	unlock_page(page);
	_leave(" = %d", ret);
	return ret;
}

/*
 * read page from file, directory or symlink, given a file to nominate the key
 * to be used
 */
static int afs_readpage(struct file *file, struct page *page)
{
	struct key *key;
	int ret;

	if (file) {
		key = afs_file_key(file);
		ASSERT(key != NULL);
		ret = afs_page_filler(key, page);
	} else {
		struct inode *inode = page->mapping->host;
		key = afs_request_key(AFS_FS_S(inode->i_sb)->cell);
		if (IS_ERR(key)) {
			ret = PTR_ERR(key);
		} else {
			ret = afs_page_filler(key, page);
			key_put(key);
		}
	}
	return ret;
}

/*
 * Make pages available as they're filled.
 */
static void afs_readpages_page_done(struct afs_read *req)
{
#ifdef CONFIG_AFS_FSCACHE
	struct afs_vnode *vnode = req->vnode;
#endif
	struct page *page = req->pages[req->index];

	req->pages[req->index] = NULL;
	SetPageUptodate(page);

	/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
	if (PageFsCache(page) &&
	    fscache_write_page(vnode->cache, page, vnode->status.size,
			       GFP_KERNEL) != 0) {
		fscache_uncache_page(vnode->cache, page);
		BUG_ON(PageFsCache(page));
	}
#endif
	unlock_page(page);
	put_page(page);
}

/*
 * Read a contiguous set of pages.
 */
static int afs_readpages_one(struct file *file, struct address_space *mapping,
			     struct list_head *pages)
{
	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
	struct afs_read *req;
	struct list_head *p;
	struct page *first, *page;
	struct key *key = afs_file_key(file);
	pgoff_t index;
	int ret, n, i;

	/* Count the number of contiguous pages at the front of the list.  Note
	 * that the list goes prev-wards rather than next-wards.
	 */
	first = lru_to_page(pages);
	index = first->index + 1;
	n = 1;
	for (p = first->lru.prev; p != pages; p = p->prev) {
		page = list_entry(p, struct page, lru);
		if (page->index != index)
			break;
		index++;
		n++;
	}

	req = kzalloc(struct_size(req, array, n), GFP_NOFS);
	if (!req)
		return -ENOMEM;

	refcount_set(&req->usage, 1);
	req->vnode = vnode;
	req->page_done = afs_readpages_page_done;
	req->pos = first->index;
	req->pos <<= PAGE_SHIFT;
	req->pages = req->array;

	/* Transfer the pages to the request.  We add them in until one fails
	 * to add to the LRU and then we stop (as that'll make a hole in the
	 * contiguous run.
	 *
	 * Note that it's possible for the file size to change whilst we're
	 * doing this, but we rely on the server returning less than we asked
	 * for if the file shrank.  We also rely on this to deal with a partial
	 * page at the end of the file.
	 */
	do {
		page = lru_to_page(pages);
		list_del(&page->lru);
		index = page->index;
		if (add_to_page_cache_lru(page, mapping, index,
					  readahead_gfp_mask(mapping))) {
#ifdef CONFIG_AFS_FSCACHE
			fscache_uncache_page(vnode->cache, page);
#endif
			put_page(page);
			break;
		}

		req->pages[req->nr_pages++] = page;
		req->len += PAGE_SIZE;
	} while (req->nr_pages < n);

	if (req->nr_pages == 0) {
		kfree(req);
		return 0;
	}

	ret = afs_fetch_data(vnode, key, req);
	if (ret < 0)
		goto error;

	task_io_account_read(PAGE_SIZE * req->nr_pages);
	afs_put_read(req);
	return 0;

error:
	if (ret == -ENOENT) {
		_debug("got NOENT from server"
		       " - marking file deleted and stale");
		set_bit(AFS_VNODE_DELETED, &vnode->flags);
		ret = -ESTALE;
	}

	for (i = 0; i < req->nr_pages; i++) {
		page = req->pages[i];
		if (page) {
#ifdef CONFIG_AFS_FSCACHE
			fscache_uncache_page(vnode->cache, page);
#endif
			SetPageError(page);
			unlock_page(page);
		}
	}

	afs_put_read(req);
	return ret;
}

/*
 * read a set of pages
 */
static int afs_readpages(struct file *file, struct address_space *mapping,
			 struct list_head *pages, unsigned nr_pages)
{
	struct key *key = afs_file_key(file);
	struct afs_vnode *vnode;
	int ret = 0;

	_enter("{%d},{%lu},,%d",
	       key_serial(key), mapping->host->i_ino, nr_pages);

	ASSERT(key != NULL);

	vnode = AFS_FS_I(mapping->host);
	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		_leave(" = -ESTALE");
		return -ESTALE;
	}

	/* attempt to read as many of the pages as possible */
#ifdef CONFIG_AFS_FSCACHE
	ret = fscache_read_or_alloc_pages(vnode->cache,
					  mapping,
					  pages,
					  &nr_pages,
					  afs_file_readpage_read_complete,
					  NULL,
					  mapping_gfp_mask(mapping));
#else
	ret = -ENOBUFS;
#endif

	switch (ret) {
		/* all pages are being read from the cache */
	case 0:
		BUG_ON(!list_empty(pages));
		BUG_ON(nr_pages != 0);
		_leave(" = 0 [reading all]");
		return 0;

		/* there were pages that couldn't be read from the cache */
	case -ENODATA:
	case -ENOBUFS:
		break;

		/* other error */
	default:
		_leave(" = %d", ret);
		return ret;
	}

	while (!list_empty(pages)) {
		ret = afs_readpages_one(file, mapping, pages);
		if (ret < 0)
			break;
	}

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

/*
 * Adjust the dirty region of the page on truncation or full invalidation,
 * getting rid of the markers altogether if the region is entirely invalidated.
 */
static void afs_invalidate_dirty(struct page *page, unsigned int offset,
				 unsigned int length)
{
	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
	unsigned long priv;
	unsigned int f, t, end = offset + length;

	priv = page_private(page);

	/* we clean up only if the entire page is being invalidated */
	if (offset == 0 && length == thp_size(page))
		goto full_invalidate;

	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
	  * and we don't get another notification to tell us to expand it
	  * again.
	  */
	if (afs_is_page_dirty_mmapped(priv))
		return;

	/* We may need to shorten the dirty region */
	f = afs_page_dirty_from(priv);
	t = afs_page_dirty_to(priv);

	if (t <= offset || f >= end)
		return; /* Doesn't overlap */

	if (f < offset && t > end)
		return; /* Splits the dirty region - just absorb it */

	if (f >= offset && t <= end)
		goto undirty;

	if (f < offset)
		t = offset;
	else
		f = end;
	if (f == t)
		goto undirty;

	priv = afs_page_dirty(f, t);
	set_page_private(page, priv);
	trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page->index, priv);
	return;

undirty:
	trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page->index, priv);
	clear_page_dirty_for_io(page);
full_invalidate:
	priv = (unsigned long)detach_page_private(page);
	trace_afs_page_dirty(vnode, tracepoint_string("inval"), page->index, priv);
}

/*
 * invalidate part or all of a page
 * - release a page and clean up its private data if offset is 0 (indicating
 *   the entire page)
 */
static void afs_invalidatepage(struct page *page, unsigned int offset,
			       unsigned int length)
{
	_enter("{%lu},%u,%u", page->index, offset, length);

	BUG_ON(!PageLocked(page));

#ifdef CONFIG_AFS_FSCACHE
	/* we clean up only if the entire page is being invalidated */
	if (offset == 0 && length == PAGE_SIZE) {
		if (PageFsCache(page)) {
			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
			fscache_wait_on_page_write(vnode->cache, page);
			fscache_uncache_page(vnode->cache, page);
		}
	}
#endif

	if (PagePrivate(page))
		afs_invalidate_dirty(page, offset, length);

	_leave("");
}

/*
 * release a page and clean up its private state if it's not busy
 * - return true if the page can now be released, false if not
 */
static int afs_releasepage(struct page *page, gfp_t gfp_flags)
{
	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
	unsigned long priv;

	_enter("{{%llx:%llu}[%lu],%lx},%x",
	       vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
	       gfp_flags);

	/* deny if page is being written to the cache and the caller hasn't
	 * elected to wait */
#ifdef CONFIG_AFS_FSCACHE
	if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
		_leave(" = F [cache busy]");
		return 0;
	}
#endif

	if (PagePrivate(page)) {
		priv = (unsigned long)detach_page_private(page);
		trace_afs_page_dirty(vnode, tracepoint_string("rel"),
				     page->index, priv);
	}

	/* indicate that the page can be released */
	_leave(" = T");
	return 1;
}

/*
 * Handle setting up a memory mapping on an AFS file.
 */
static int afs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	int ret;

	ret = generic_file_mmap(file, vma);
	if (ret == 0)
		vma->vm_ops = &afs_vm_ops;
	return ret;
}