summaryrefslogtreecommitdiffstats
path: root/fs/fscache/volume.c
blob: a57c6cbee858a2bfeeb87738e6268631a724c738 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* Volume-level cache cookie handling.
 *
 * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#define FSCACHE_DEBUG_LEVEL COOKIE
#include <linux/export.h>
#include <linux/slab.h>
#include "internal.h"

#define fscache_volume_hash_shift 10
static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift];
static atomic_t fscache_volume_debug_id;
static LIST_HEAD(fscache_volumes);

static void fscache_create_volume_work(struct work_struct *work);

struct fscache_volume *fscache_get_volume(struct fscache_volume *volume,
					  enum fscache_volume_trace where)
{
	int ref;

	__refcount_inc(&volume->ref, &ref);
	trace_fscache_volume(volume->debug_id, ref + 1, where);
	return volume;
}

static void fscache_see_volume(struct fscache_volume *volume,
			       enum fscache_volume_trace where)
{
	int ref = refcount_read(&volume->ref);

	trace_fscache_volume(volume->debug_id, ref, where);
}

/*
 * Pin the cache behind a volume so that we can access it.
 */
static void __fscache_begin_volume_access(struct fscache_volume *volume,
					  struct fscache_cookie *cookie,
					  enum fscache_access_trace why)
{
	int n_accesses;

	n_accesses = atomic_inc_return(&volume->n_accesses);
	smp_mb__after_atomic();
	trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0,
				    refcount_read(&volume->ref),
				    n_accesses, why);
}

/**
 * fscache_begin_volume_access - Pin a cache so a volume can be accessed
 * @volume: The volume cookie
 * @cookie: A datafile cookie for a tracing reference (or NULL)
 * @why: An indication of the circumstances of the access for tracing
 *
 * Attempt to pin the cache to prevent it from going away whilst we're
 * accessing a volume and returns true if successful.  This works as follows:
 *
 *  (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE),
 *      then we return false to indicate access was not permitted.
 *
 *  (2) If the cache tests as live, then we increment the volume's n_accesses
 *      count and then recheck the cache liveness, ending the access if it
 *      ceased to be live.
 *
 *  (3) When we end the access, we decrement the volume's n_accesses and wake
 *      up the any waiters if it reaches 0.
 *
 *  (4) Whilst the cache is caching, the volume's n_accesses is kept
 *      artificially incremented to prevent wakeups from happening.
 *
 *  (5) When the cache is taken offline, the state is changed to prevent new
 *      accesses, the volume's n_accesses is decremented and we wait for it to
 *      become 0.
 *
 * The datafile @cookie and the @why indicator are merely provided for tracing
 * purposes.
 */
bool fscache_begin_volume_access(struct fscache_volume *volume,
				 struct fscache_cookie *cookie,
				 enum fscache_access_trace why)
{
	if (!fscache_cache_is_live(volume->cache))
		return false;
	__fscache_begin_volume_access(volume, cookie, why);
	if (!fscache_cache_is_live(volume->cache)) {
		fscache_end_volume_access(volume, cookie, fscache_access_unlive);
		return false;
	}
	return true;
}

/**
 * fscache_end_volume_access - Unpin a cache at the end of an access.
 * @volume: The volume cookie
 * @cookie: A datafile cookie for a tracing reference (or NULL)
 * @why: An indication of the circumstances of the access for tracing
 *
 * Unpin a cache volume after we've accessed it.  The datafile @cookie and the
 * @why indicator are merely provided for tracing purposes.
 */
void fscache_end_volume_access(struct fscache_volume *volume,
			       struct fscache_cookie *cookie,
			       enum fscache_access_trace why)
{
	int n_accesses;

	smp_mb__before_atomic();
	n_accesses = atomic_dec_return(&volume->n_accesses);
	trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0,
				    refcount_read(&volume->ref),
				    n_accesses, why);
	if (n_accesses == 0)
		wake_up_var(&volume->n_accesses);
}
EXPORT_SYMBOL(fscache_end_volume_access);

static bool fscache_volume_same(const struct fscache_volume *a,
				const struct fscache_volume *b)
{
	size_t klen;

	if (a->key_hash	!= b->key_hash ||
	    a->cache	!= b->cache ||
	    a->key[0]	!= b->key[0])
		return false;

	klen = round_up(a->key[0] + 1, sizeof(__le32));
	return memcmp(a->key, b->key, klen) == 0;
}

static bool fscache_is_acquire_pending(struct fscache_volume *volume)
{
	return test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &volume->flags);
}

static void fscache_wait_on_volume_collision(struct fscache_volume *candidate,
					     unsigned int collidee_debug_id)
{
	wait_var_event_timeout(&candidate->flags,
			       fscache_is_acquire_pending(candidate), 20 * HZ);
	if (!fscache_is_acquire_pending(candidate)) {
		pr_notice("Potential volume collision new=%08x old=%08x",
			  candidate->debug_id, collidee_debug_id);
		fscache_stat(&fscache_n_volumes_collision);
		wait_var_event(&candidate->flags, fscache_is_acquire_pending(candidate));
	}
}

/*
 * Attempt to insert the new volume into the hash.  If there's a collision, we
 * wait for the old volume to complete if it's being relinquished and an error
 * otherwise.
 */
static bool fscache_hash_volume(struct fscache_volume *candidate)
{
	struct fscache_volume *cursor;
	struct hlist_bl_head *h;
	struct hlist_bl_node *p;
	unsigned int bucket, collidee_debug_id = 0;

	bucket = candidate->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1);
	h = &fscache_volume_hash[bucket];

	hlist_bl_lock(h);
	hlist_bl_for_each_entry(cursor, p, h, hash_link) {
		if (fscache_volume_same(candidate, cursor)) {
			if (!test_bit(FSCACHE_VOLUME_RELINQUISHED, &cursor->flags))
				goto collision;
			fscache_see_volume(cursor, fscache_volume_get_hash_collision);
			set_bit(FSCACHE_VOLUME_COLLIDED_WITH, &cursor->flags);
			set_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags);
			collidee_debug_id = cursor->debug_id;
			break;
		}
	}

	hlist_bl_add_head(&candidate->hash_link, h);
	hlist_bl_unlock(h);

	if (test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags))
		fscache_wait_on_volume_collision(candidate, collidee_debug_id);
	return true;

collision:
	fscache_see_volume(cursor, fscache_volume_collision);
	hlist_bl_unlock(h);
	return false;
}

/*
 * Allocate and initialise a volume representation cookie.
 */
static struct fscache_volume *fscache_alloc_volume(const char *volume_key,
						   const char *cache_name,
						   const void *coherency_data,
						   size_t coherency_len)
{
	struct fscache_volume *volume;
	struct fscache_cache *cache;
	size_t klen, hlen;
	char *key;

	if (!coherency_data)
		coherency_len = 0;

	cache = fscache_lookup_cache(cache_name, false);
	if (IS_ERR(cache))
		return NULL;

	volume = kzalloc(struct_size(volume, coherency, coherency_len),
			 GFP_KERNEL);
	if (!volume)
		goto err_cache;

	volume->cache = cache;
	volume->coherency_len = coherency_len;
	if (coherency_data)
		memcpy(volume->coherency, coherency_data, coherency_len);
	INIT_LIST_HEAD(&volume->proc_link);
	INIT_WORK(&volume->work, fscache_create_volume_work);
	refcount_set(&volume->ref, 1);
	spin_lock_init(&volume->lock);

	/* Stick the length on the front of the key and pad it out to make
	 * hashing easier.
	 */
	klen = strlen(volume_key);
	hlen = round_up(1 + klen + 1, sizeof(__le32));
	key = kzalloc(hlen, GFP_KERNEL);
	if (!key)
		goto err_vol;
	key[0] = klen;
	memcpy(key + 1, volume_key, klen);

	volume->key = key;
	volume->key_hash = fscache_hash(0, key, hlen);

	volume->debug_id = atomic_inc_return(&fscache_volume_debug_id);
	down_write(&fscache_addremove_sem);
	atomic_inc(&cache->n_volumes);
	list_add_tail(&volume->proc_link, &fscache_volumes);
	fscache_see_volume(volume, fscache_volume_new_acquire);
	fscache_stat(&fscache_n_volumes);
	up_write(&fscache_addremove_sem);
	_leave(" = v=%x", volume->debug_id);
	return volume;

err_vol:
	kfree(volume);
err_cache:
	fscache_put_cache(cache, fscache_cache_put_alloc_volume);
	fscache_stat(&fscache_n_volumes_nomem);
	return NULL;
}

/*
 * Create a volume's representation on disk.  Have a volume ref and a cache
 * access we have to release.
 */
static void fscache_create_volume_work(struct work_struct *work)
{
	const struct fscache_cache_ops *ops;
	struct fscache_volume *volume =
		container_of(work, struct fscache_volume, work);

	fscache_see_volume(volume, fscache_volume_see_create_work);

	ops = volume->cache->ops;
	if (ops->acquire_volume)
		ops->acquire_volume(volume);
	fscache_end_cache_access(volume->cache,
				 fscache_access_acquire_volume_end);

	clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags);
	wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING);
	fscache_put_volume(volume, fscache_volume_put_create_work);
}

/*
 * Dispatch a worker thread to create a volume's representation on disk.
 */
void fscache_create_volume(struct fscache_volume *volume, bool wait)
{
	if (test_and_set_bit(FSCACHE_VOLUME_CREATING, &volume->flags))
		goto maybe_wait;
	if (volume->cache_priv)
		goto no_wait; /* We raced */
	if (!fscache_begin_cache_access(volume->cache,
					fscache_access_acquire_volume))
		goto no_wait;

	fscache_get_volume(volume, fscache_volume_get_create_work);
	if (!schedule_work(&volume->work))
		fscache_put_volume(volume, fscache_volume_put_create_work);

maybe_wait:
	if (wait) {
		fscache_see_volume(volume, fscache_volume_wait_create_work);
		wait_on_bit(&volume->flags, FSCACHE_VOLUME_CREATING,
			    TASK_UNINTERRUPTIBLE);
	}
	return;
no_wait:
	clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags);
	wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING);
}

/*
 * Acquire a volume representation cookie and link it to a (proposed) cache.
 */
struct fscache_volume *__fscache_acquire_volume(const char *volume_key,
						const char *cache_name,
						const void *coherency_data,
						size_t coherency_len)
{
	struct fscache_volume *volume;

	volume = fscache_alloc_volume(volume_key, cache_name,
				      coherency_data, coherency_len);
	if (!volume)
		return ERR_PTR(-ENOMEM);

	if (!fscache_hash_volume(volume)) {
		fscache_put_volume(volume, fscache_volume_put_hash_collision);
		return ERR_PTR(-EBUSY);
	}

	fscache_create_volume(volume, false);
	return volume;
}
EXPORT_SYMBOL(__fscache_acquire_volume);

static void fscache_wake_pending_volume(struct fscache_volume *volume,
					struct hlist_bl_head *h)
{
	struct fscache_volume *cursor;
	struct hlist_bl_node *p;

	hlist_bl_for_each_entry(cursor, p, h, hash_link) {
		if (fscache_volume_same(cursor, volume)) {
			fscache_see_volume(cursor, fscache_volume_see_hash_wake);
			clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags);
			wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING);
			return;
		}
	}
}

/*
 * Remove a volume cookie from the hash table.
 */
static void fscache_unhash_volume(struct fscache_volume *volume)
{
	struct hlist_bl_head *h;
	unsigned int bucket;

	bucket = volume->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1);
	h = &fscache_volume_hash[bucket];

	hlist_bl_lock(h);
	hlist_bl_del(&volume->hash_link);
	if (test_bit(FSCACHE_VOLUME_COLLIDED_WITH, &volume->flags))
		fscache_wake_pending_volume(volume, h);
	hlist_bl_unlock(h);
}

/*
 * Drop a cache's volume attachments.
 */
static void fscache_free_volume(struct fscache_volume *volume)
{
	struct fscache_cache *cache = volume->cache;

	if (volume->cache_priv) {
		__fscache_begin_volume_access(volume, NULL,
					      fscache_access_relinquish_volume);
		if (volume->cache_priv)
			cache->ops->free_volume(volume);
		fscache_end_volume_access(volume, NULL,
					  fscache_access_relinquish_volume_end);
	}

	down_write(&fscache_addremove_sem);
	list_del_init(&volume->proc_link);
	atomic_dec(&volume->cache->n_volumes);
	up_write(&fscache_addremove_sem);

	if (!hlist_bl_unhashed(&volume->hash_link))
		fscache_unhash_volume(volume);

	trace_fscache_volume(volume->debug_id, 0, fscache_volume_free);
	kfree(volume->key);
	kfree(volume);
	fscache_stat_d(&fscache_n_volumes);
	fscache_put_cache(cache, fscache_cache_put_volume);
}

/*
 * Drop a reference to a volume cookie.
 */
void fscache_put_volume(struct fscache_volume *volume,
			enum fscache_volume_trace where)
{
	if (volume) {
		unsigned int debug_id = volume->debug_id;
		bool zero;
		int ref;

		zero = __refcount_dec_and_test(&volume->ref, &ref);
		trace_fscache_volume(debug_id, ref - 1, where);
		if (zero)
			fscache_free_volume(volume);
	}
}

/*
 * Relinquish a volume representation cookie.
 */
void __fscache_relinquish_volume(struct fscache_volume *volume,
				 const void *coherency_data,
				 bool invalidate)
{
	if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags)))
		return;

	if (invalidate) {
		set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags);
	} else if (coherency_data) {
		memcpy(volume->coherency, coherency_data, volume->coherency_len);
	}

	fscache_put_volume(volume, fscache_volume_put_relinquish);
}
EXPORT_SYMBOL(__fscache_relinquish_volume);

/**
 * fscache_withdraw_volume - Withdraw a volume from being cached
 * @volume: Volume cookie
 *
 * Withdraw a cache volume from service, waiting for all accesses to complete
 * before returning.
 */
void fscache_withdraw_volume(struct fscache_volume *volume)
{
	int n_accesses;

	_debug("withdraw V=%x", volume->debug_id);

	/* Allow wakeups on dec-to-0 */
	n_accesses = atomic_dec_return(&volume->n_accesses);
	trace_fscache_access_volume(volume->debug_id, 0,
				    refcount_read(&volume->ref),
				    n_accesses, fscache_access_cache_unpin);

	wait_var_event(&volume->n_accesses,
		       atomic_read(&volume->n_accesses) == 0);
}
EXPORT_SYMBOL(fscache_withdraw_volume);

#ifdef CONFIG_PROC_FS
/*
 * Generate a list of volumes in /proc/fs/fscache/volumes
 */
static int fscache_volumes_seq_show(struct seq_file *m, void *v)
{
	struct fscache_volume *volume;

	if (v == &fscache_volumes) {
		seq_puts(m,
			 "VOLUME   REF   nCOOK ACC FL CACHE           KEY\n"
			 "======== ===== ===== === == =============== ================\n");
		return 0;
	}

	volume = list_entry(v, struct fscache_volume, proc_link);
	seq_printf(m,
		   "%08x %5d %5d %3d %02lx %-15.15s %s\n",
		   volume->debug_id,
		   refcount_read(&volume->ref),
		   atomic_read(&volume->n_cookies),
		   atomic_read(&volume->n_accesses),
		   volume->flags,
		   volume->cache->name ?: "-",
		   volume->key + 1);
	return 0;
}

static void *fscache_volumes_seq_start(struct seq_file *m, loff_t *_pos)
	__acquires(&fscache_addremove_sem)
{
	down_read(&fscache_addremove_sem);
	return seq_list_start_head(&fscache_volumes, *_pos);
}

static void *fscache_volumes_seq_next(struct seq_file *m, void *v, loff_t *_pos)
{
	return seq_list_next(v, &fscache_volumes, _pos);
}

static void fscache_volumes_seq_stop(struct seq_file *m, void *v)
	__releases(&fscache_addremove_sem)
{
	up_read(&fscache_addremove_sem);
}

const struct seq_operations fscache_volumes_seq_ops = {
	.start  = fscache_volumes_seq_start,
	.next   = fscache_volumes_seq_next,
	.stop   = fscache_volumes_seq_stop,
	.show   = fscache_volumes_seq_show,
};
#endif /* CONFIG_PROC_FS */