summaryrefslogtreecommitdiffstats
path: root/fs/cachefiles/io.c
blob: bc7c7a7d9260090c525271ae89348d3572135df9 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* kiocb-using read/write
 *
 * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/uio.h>
#include <linux/falloc.h>
#include <linux/sched/mm.h>
#include <trace/events/fscache.h>
#include "internal.h"

struct cachefiles_kiocb {
	struct kiocb		iocb;
	refcount_t		ki_refcnt;
	loff_t			start;
	union {
		size_t		skipped;
		size_t		len;
	};
	struct cachefiles_object *object;
	netfs_io_terminated_t	term_func;
	void			*term_func_priv;
	bool			was_async;
	unsigned int		inval_counter;	/* Copy of cookie->inval_counter */
	u64			b_writing;
};

static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki)
{
	if (refcount_dec_and_test(&ki->ki_refcnt)) {
		cachefiles_put_object(ki->object, cachefiles_obj_put_ioreq);
		fput(ki->iocb.ki_filp);
		kfree(ki);
	}
}

/*
 * Handle completion of a read from the cache.
 */
static void cachefiles_read_complete(struct kiocb *iocb, long ret)
{
	struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
	struct inode *inode = file_inode(ki->iocb.ki_filp);

	_enter("%ld", ret);

	if (ret < 0)
		trace_cachefiles_io_error(ki->object, inode, ret,
					  cachefiles_trace_read_error);

	if (ki->term_func) {
		if (ret >= 0) {
			if (ki->object->cookie->inval_counter == ki->inval_counter)
				ki->skipped += ret;
			else
				ret = -ESTALE;
		}

		ki->term_func(ki->term_func_priv, ret, ki->was_async);
	}

	cachefiles_put_kiocb(ki);
}

/*
 * Initiate a read from the cache.
 */
static int cachefiles_read(struct netfs_cache_resources *cres,
			   loff_t start_pos,
			   struct iov_iter *iter,
			   enum netfs_read_from_hole read_hole,
			   netfs_io_terminated_t term_func,
			   void *term_func_priv)
{
	struct cachefiles_object *object;
	struct cachefiles_kiocb *ki;
	struct file *file;
	unsigned int old_nofs;
	ssize_t ret = -ENOBUFS;
	size_t len = iov_iter_count(iter), skipped = 0;

	if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
		goto presubmission_error;

	fscache_count_read();
	object = cachefiles_cres_object(cres);
	file = cachefiles_cres_file(cres);

	_enter("%pD,%li,%llx,%zx/%llx",
	       file, file_inode(file)->i_ino, start_pos, len,
	       i_size_read(file_inode(file)));

	/* If the caller asked us to seek for data before doing the read, then
	 * we should do that now.  If we find a gap, we fill it with zeros.
	 */
	if (read_hole != NETFS_READ_HOLE_IGNORE) {
		loff_t off = start_pos, off2;

		off2 = cachefiles_inject_read_error();
		if (off2 == 0)
			off2 = vfs_llseek(file, off, SEEK_DATA);
		if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO && off2 != -ENXIO) {
			skipped = 0;
			ret = off2;
			goto presubmission_error;
		}

		if (off2 == -ENXIO || off2 >= start_pos + len) {
			/* The region is beyond the EOF or there's no more data
			 * in the region, so clear the rest of the buffer and
			 * return success.
			 */
			ret = -ENODATA;
			if (read_hole == NETFS_READ_HOLE_FAIL)
				goto presubmission_error;

			iov_iter_zero(len, iter);
			skipped = len;
			ret = 0;
			goto presubmission_error;
		}

		skipped = off2 - off;
		iov_iter_zero(skipped, iter);
	}

	ret = -ENOMEM;
	ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
	if (!ki)
		goto presubmission_error;

	refcount_set(&ki->ki_refcnt, 2);
	ki->iocb.ki_filp	= file;
	ki->iocb.ki_pos		= start_pos + skipped;
	ki->iocb.ki_flags	= IOCB_DIRECT;
	ki->iocb.ki_ioprio	= get_current_ioprio();
	ki->skipped		= skipped;
	ki->object		= object;
	ki->inval_counter	= cres->inval_counter;
	ki->term_func		= term_func;
	ki->term_func_priv	= term_func_priv;
	ki->was_async		= true;

	if (ki->term_func)
		ki->iocb.ki_complete = cachefiles_read_complete;

	get_file(ki->iocb.ki_filp);
	cachefiles_grab_object(object, cachefiles_obj_get_ioreq);

	trace_cachefiles_read(object, file_inode(file), ki->iocb.ki_pos, len - skipped);
	old_nofs = memalloc_nofs_save();
	ret = cachefiles_inject_read_error();
	if (ret == 0)
		ret = vfs_iocb_iter_read(file, &ki->iocb, iter);
	memalloc_nofs_restore(old_nofs);
	switch (ret) {
	case -EIOCBQUEUED:
		goto in_progress;

	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/* There's no easy way to restart the syscall since other AIO's
		 * may be already running. Just fail this IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		ki->was_async = false;
		cachefiles_read_complete(&ki->iocb, ret);
		if (ret > 0)
			ret = 0;
		break;
	}

in_progress:
	cachefiles_put_kiocb(ki);
	_leave(" = %zd", ret);
	return ret;

presubmission_error:
	if (term_func)
		term_func(term_func_priv, ret < 0 ? ret : skipped, false);
	return ret;
}

/*
 * Query the occupancy of the cache in a region, returning where the next chunk
 * of data starts and how long it is.
 */
static int cachefiles_query_occupancy(struct netfs_cache_resources *cres,
				      loff_t start, size_t len, size_t granularity,
				      loff_t *_data_start, size_t *_data_len)
{
	struct cachefiles_object *object;
	struct file *file;
	loff_t off, off2;

	*_data_start = -1;
	*_data_len = 0;

	if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
		return -ENOBUFS;

	object = cachefiles_cres_object(cres);
	file = cachefiles_cres_file(cres);
	granularity = max_t(size_t, object->volume->cache->bsize, granularity);

	_enter("%pD,%li,%llx,%zx/%llx",
	       file, file_inode(file)->i_ino, start, len,
	       i_size_read(file_inode(file)));

	off = cachefiles_inject_read_error();
	if (off == 0)
		off = vfs_llseek(file, start, SEEK_DATA);
	if (off == -ENXIO)
		return -ENODATA; /* Beyond EOF */
	if (off < 0 && off >= (loff_t)-MAX_ERRNO)
		return -ENOBUFS; /* Error. */
	if (round_up(off, granularity) >= start + len)
		return -ENODATA; /* No data in range */

	off2 = cachefiles_inject_read_error();
	if (off2 == 0)
		off2 = vfs_llseek(file, off, SEEK_HOLE);
	if (off2 == -ENXIO)
		return -ENODATA; /* Beyond EOF */
	if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO)
		return -ENOBUFS; /* Error. */

	/* Round away partial blocks */
	off = round_up(off, granularity);
	off2 = round_down(off2, granularity);
	if (off2 <= off)
		return -ENODATA;

	*_data_start = off;
	if (off2 > start + len)
		*_data_len = len;
	else
		*_data_len = off2 - off;
	return 0;
}

/*
 * Handle completion of a write to the cache.
 */
static void cachefiles_write_complete(struct kiocb *iocb, long ret)
{
	struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb);
	struct cachefiles_object *object = ki->object;
	struct inode *inode = file_inode(ki->iocb.ki_filp);

	_enter("%ld", ret);

	/* Tell lockdep we inherited freeze protection from submission thread */
	__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
	__sb_end_write(inode->i_sb, SB_FREEZE_WRITE);

	if (ret < 0)
		trace_cachefiles_io_error(object, inode, ret,
					  cachefiles_trace_write_error);

	atomic_long_sub(ki->b_writing, &object->volume->cache->b_writing);
	set_bit(FSCACHE_COOKIE_HAVE_DATA, &object->cookie->flags);
	if (ki->term_func)
		ki->term_func(ki->term_func_priv, ret, ki->was_async);
	cachefiles_put_kiocb(ki);
}

/*
 * Initiate a write to the cache.
 */
static int cachefiles_write(struct netfs_cache_resources *cres,
			    loff_t start_pos,
			    struct iov_iter *iter,
			    netfs_io_terminated_t term_func,
			    void *term_func_priv)
{
	struct cachefiles_object *object;
	struct cachefiles_cache *cache;
	struct cachefiles_kiocb *ki;
	struct inode *inode;
	struct file *file;
	unsigned int old_nofs;
	ssize_t ret = -ENOBUFS;
	size_t len = iov_iter_count(iter);

	if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE))
		goto presubmission_error;
	fscache_count_write();
	object = cachefiles_cres_object(cres);
	cache = object->volume->cache;
	file = cachefiles_cres_file(cres);

	_enter("%pD,%li,%llx,%zx/%llx",
	       file, file_inode(file)->i_ino, start_pos, len,
	       i_size_read(file_inode(file)));

	ret = -ENOMEM;
	ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
	if (!ki)
		goto presubmission_error;

	refcount_set(&ki->ki_refcnt, 2);
	ki->iocb.ki_filp	= file;
	ki->iocb.ki_pos		= start_pos;
	ki->iocb.ki_flags	= IOCB_DIRECT | IOCB_WRITE;
	ki->iocb.ki_ioprio	= get_current_ioprio();
	ki->object		= object;
	ki->inval_counter	= cres->inval_counter;
	ki->start		= start_pos;
	ki->len			= len;
	ki->term_func		= term_func;
	ki->term_func_priv	= term_func_priv;
	ki->was_async		= true;
	ki->b_writing		= (len + (1 << cache->bshift) - 1) >> cache->bshift;

	if (ki->term_func)
		ki->iocb.ki_complete = cachefiles_write_complete;
	atomic_long_add(ki->b_writing, &cache->b_writing);

	/* Open-code file_start_write here to grab freeze protection, which
	 * will be released by another thread in aio_complete_rw().  Fool
	 * lockdep by telling it the lock got released so that it doesn't
	 * complain about the held lock when we return to userspace.
	 */
	inode = file_inode(file);
	__sb_start_write(inode->i_sb, SB_FREEZE_WRITE);
	__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);

	get_file(ki->iocb.ki_filp);
	cachefiles_grab_object(object, cachefiles_obj_get_ioreq);

	trace_cachefiles_write(object, inode, ki->iocb.ki_pos, len);
	old_nofs = memalloc_nofs_save();
	ret = cachefiles_inject_write_error();
	if (ret == 0)
		ret = vfs_iocb_iter_write(file, &ki->iocb, iter);
	memalloc_nofs_restore(old_nofs);
	switch (ret) {
	case -EIOCBQUEUED:
		goto in_progress;

	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/* There's no easy way to restart the syscall since other AIO's
		 * may be already running. Just fail this IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		ki->was_async = false;
		cachefiles_write_complete(&ki->iocb, ret);
		if (ret > 0)
			ret = 0;
		break;
	}

in_progress:
	cachefiles_put_kiocb(ki);
	_leave(" = %zd", ret);
	return ret;

presubmission_error:
	if (term_func)
		term_func(term_func_priv, ret, false);
	return ret;
}

/*
 * Prepare a read operation, shortening it to a cached/uncached
 * boundary as appropriate.
 */
static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subrequest *subreq,
						      loff_t i_size)
{
	enum cachefiles_prepare_read_trace why;
	struct netfs_read_request *rreq = subreq->rreq;
	struct netfs_cache_resources *cres = &rreq->cache_resources;
	struct cachefiles_object *object;
	struct cachefiles_cache *cache;
	struct fscache_cookie *cookie = fscache_cres_cookie(cres);
	const struct cred *saved_cred;
	struct file *file = cachefiles_cres_file(cres);
	enum netfs_read_source ret = NETFS_DOWNLOAD_FROM_SERVER;
	loff_t off, to;
	ino_t ino = file ? file_inode(file)->i_ino : 0;

	_enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size);

	if (subreq->start >= i_size) {
		ret = NETFS_FILL_WITH_ZEROES;
		why = cachefiles_trace_read_after_eof;
		goto out_no_object;
	}

	if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) {
		__set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags);
		why = cachefiles_trace_read_no_data;
		goto out_no_object;
	}

	/* The object and the file may be being created in the background. */
	if (!file) {
		why = cachefiles_trace_read_no_file;
		if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
			goto out_no_object;
		file = cachefiles_cres_file(cres);
		if (!file)
			goto out_no_object;
		ino = file_inode(file)->i_ino;
	}

	object = cachefiles_cres_object(cres);
	cache = object->volume->cache;
	cachefiles_begin_secure(cache, &saved_cred);

	off = cachefiles_inject_read_error();
	if (off == 0)
		off = vfs_llseek(file, subreq->start, SEEK_DATA);
	if (off < 0 && off >= (loff_t)-MAX_ERRNO) {
		if (off == (loff_t)-ENXIO) {
			why = cachefiles_trace_read_seek_nxio;
			goto download_and_store;
		}
		trace_cachefiles_io_error(object, file_inode(file), off,
					  cachefiles_trace_seek_error);
		why = cachefiles_trace_read_seek_error;
		goto out;
	}

	if (off >= subreq->start + subreq->len) {
		why = cachefiles_trace_read_found_hole;
		goto download_and_store;
	}

	if (off > subreq->start) {
		off = round_up(off, cache->bsize);
		subreq->len = off - subreq->start;
		why = cachefiles_trace_read_found_part;
		goto download_and_store;
	}

	to = cachefiles_inject_read_error();
	if (to == 0)
		to = vfs_llseek(file, subreq->start, SEEK_HOLE);
	if (to < 0 && to >= (loff_t)-MAX_ERRNO) {
		trace_cachefiles_io_error(object, file_inode(file), to,
					  cachefiles_trace_seek_error);
		why = cachefiles_trace_read_seek_error;
		goto out;
	}

	if (to < subreq->start + subreq->len) {
		if (subreq->start + subreq->len >= i_size)
			to = round_up(to, cache->bsize);
		else
			to = round_down(to, cache->bsize);
		subreq->len = to - subreq->start;
	}

	why = cachefiles_trace_read_have_data;
	ret = NETFS_READ_FROM_CACHE;
	goto out;

download_and_store:
	__set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags);
out:
	cachefiles_end_secure(cache, saved_cred);
out_no_object:
	trace_cachefiles_prep_read(subreq, ret, why, ino);
	return ret;
}

/*
 * Prepare for a write to occur.
 */
static int __cachefiles_prepare_write(struct netfs_cache_resources *cres,
				      loff_t *_start, size_t *_len, loff_t i_size,
				      bool no_space_allocated_yet)
{
	struct cachefiles_object *object = cachefiles_cres_object(cres);
	struct cachefiles_cache *cache = object->volume->cache;
	struct file *file = cachefiles_cres_file(cres);
	loff_t start = *_start, pos;
	size_t len = *_len, down;
	int ret;

	/* Round to DIO size */
	down = start - round_down(start, PAGE_SIZE);
	*_start = start - down;
	*_len = round_up(down + len, PAGE_SIZE);

	/* We need to work out whether there's sufficient disk space to perform
	 * the write - but we can skip that check if we have space already
	 * allocated.
	 */
	if (no_space_allocated_yet)
		goto check_space;

	pos = cachefiles_inject_read_error();
	if (pos == 0)
		pos = vfs_llseek(file, *_start, SEEK_DATA);
	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
		if (pos == -ENXIO)
			goto check_space; /* Unallocated tail */
		trace_cachefiles_io_error(object, file_inode(file), pos,
					  cachefiles_trace_seek_error);
		return pos;
	}
	if ((u64)pos >= (u64)*_start + *_len)
		goto check_space; /* Unallocated region */

	/* We have a block that's at least partially filled - if we're low on
	 * space, we need to see if it's fully allocated.  If it's not, we may
	 * want to cull it.
	 */
	if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE,
				 cachefiles_has_space_check) == 0)
		return 0; /* Enough space to simply overwrite the whole block */

	pos = cachefiles_inject_read_error();
	if (pos == 0)
		pos = vfs_llseek(file, *_start, SEEK_HOLE);
	if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) {
		trace_cachefiles_io_error(object, file_inode(file), pos,
					  cachefiles_trace_seek_error);
		return pos;
	}
	if ((u64)pos >= (u64)*_start + *_len)
		return 0; /* Fully allocated */

	/* Partially allocated, but insufficient space: cull. */
	fscache_count_no_write_space();
	ret = cachefiles_inject_remove_error();
	if (ret == 0)
		ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
				    *_start, *_len);
	if (ret < 0) {
		trace_cachefiles_io_error(object, file_inode(file), ret,
					  cachefiles_trace_fallocate_error);
		cachefiles_io_error_obj(object,
					"CacheFiles: fallocate failed (%d)\n", ret);
		ret = -EIO;
	}

	return ret;

check_space:
	return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE,
				    cachefiles_has_space_for_write);
}

static int cachefiles_prepare_write(struct netfs_cache_resources *cres,
				    loff_t *_start, size_t *_len, loff_t i_size,
				    bool no_space_allocated_yet)
{
	struct cachefiles_object *object = cachefiles_cres_object(cres);
	struct cachefiles_cache *cache = object->volume->cache;
	const struct cred *saved_cred;
	int ret;

	if (!cachefiles_cres_file(cres)) {
		if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE))
			return -ENOBUFS;
		if (!cachefiles_cres_file(cres))
			return -ENOBUFS;
	}

	cachefiles_begin_secure(cache, &saved_cred);
	ret = __cachefiles_prepare_write(cres, _start, _len, i_size,
					 no_space_allocated_yet);
	cachefiles_end_secure(cache, saved_cred);
	return ret;
}

/*
 * Clean up an operation.
 */
static void cachefiles_end_operation(struct netfs_cache_resources *cres)
{
	struct file *file = cachefiles_cres_file(cres);

	if (file)
		fput(file);
	fscache_end_cookie_access(fscache_cres_cookie(cres), fscache_access_io_end);
}

static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
	.end_operation		= cachefiles_end_operation,
	.read			= cachefiles_read,
	.write			= cachefiles_write,
	.prepare_read		= cachefiles_prepare_read,
	.prepare_write		= cachefiles_prepare_write,
	.query_occupancy	= cachefiles_query_occupancy,
};

/*
 * Open the cache file when beginning a cache operation.
 */
bool cachefiles_begin_operation(struct netfs_cache_resources *cres,
				enum fscache_want_state want_state)
{
	struct cachefiles_object *object = cachefiles_cres_object(cres);

	if (!cachefiles_cres_file(cres)) {
		cres->ops = &cachefiles_netfs_cache_ops;
		if (object->file) {
			spin_lock(&object->lock);
			if (!cres->cache_priv2 && object->file)
				cres->cache_priv2 = get_file(object->file);
			spin_unlock(&object->lock);
		}
	}

	if (!cachefiles_cres_file(cres) && want_state != FSCACHE_WANT_PARAMS) {
		pr_err("failed to get cres->file\n");
		return false;
	}

	return true;
}