summaryrefslogtreecommitdiff
path: root/fs/cachefiles/cache.c
blob: 9fb06dc165202cbc86d690b51a9e7354fe8fc56e (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* Manage high-level VFS aspects of a cache.
 *
 * Copyright (C) 2007, 2021 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/slab.h>
#include <linux/statfs.h>
#include <linux/namei.h>
#include <trace/events/fscache.h>
#include "internal.h"

/*
 * Bring a cache online.
 */
int cachefiles_add_cache(struct cachefiles_cache *cache)
{
	struct fscache_cache *cache_cookie;
	struct path path;
	struct kstatfs stats;
	struct dentry *graveyard, *cachedir, *root;
	const struct cred *saved_cred;
	int ret;

	_enter("");

	cache_cookie = fscache_acquire_cache(cache->tag);
	if (IS_ERR(cache_cookie))
		return PTR_ERR(cache_cookie);

	/* we want to work under the module's security ID */
	ret = cachefiles_get_security_ID(cache);
	if (ret < 0)
		goto error_getsec;

	cachefiles_begin_secure(cache, &saved_cred);

	/* look up the directory at the root of the cache */
	ret = kern_path(cache->rootdirname, LOOKUP_DIRECTORY, &path);
	if (ret < 0)
		goto error_open_root;

	cache->mnt = path.mnt;
	root = path.dentry;

	ret = -EINVAL;
	if (is_idmapped_mnt(path.mnt)) {
		pr_warn("File cache on idmapped mounts not supported");
		goto error_unsupported;
	}

	/* Check features of the backing filesystem:
	 * - Directories must support looking up and directory creation
	 * - We create tmpfiles to handle invalidation
	 * - We use xattrs to store metadata
	 * - We need to be able to query the amount of space available
	 * - We want to be able to sync the filesystem when stopping the cache
	 * - We use DIO to/from pages, so the blocksize mustn't be too big.
	 */
	ret = -EOPNOTSUPP;
	if (d_is_negative(root) ||
	    !d_backing_inode(root)->i_op->lookup ||
	    !d_backing_inode(root)->i_op->mkdir ||
	    !d_backing_inode(root)->i_op->tmpfile ||
	    !(d_backing_inode(root)->i_opflags & IOP_XATTR) ||
	    !root->d_sb->s_op->statfs ||
	    !root->d_sb->s_op->sync_fs ||
	    root->d_sb->s_blocksize > PAGE_SIZE)
		goto error_unsupported;

	ret = -EROFS;
	if (sb_rdonly(root->d_sb))
		goto error_unsupported;

	/* determine the security of the on-disk cache as this governs
	 * security ID of files we create */
	ret = cachefiles_determine_cache_security(cache, root, &saved_cred);
	if (ret < 0)
		goto error_unsupported;

	/* get the cache size and blocksize */
	ret = vfs_statfs(&path, &stats);
	if (ret < 0)
		goto error_unsupported;

	ret = -ERANGE;
	if (stats.f_bsize <= 0)
		goto error_unsupported;

	ret = -EOPNOTSUPP;
	if (stats.f_bsize > PAGE_SIZE)
		goto error_unsupported;

	cache->bsize = stats.f_bsize;
	cache->bshift = ilog2(stats.f_bsize);

	_debug("blksize %u (shift %u)",
	       cache->bsize, cache->bshift);

	_debug("size %llu, avail %llu",
	       (unsigned long long) stats.f_blocks,
	       (unsigned long long) stats.f_bavail);

	/* set up caching limits */
	do_div(stats.f_files, 100);
	cache->fstop = stats.f_files * cache->fstop_percent;
	cache->fcull = stats.f_files * cache->fcull_percent;
	cache->frun  = stats.f_files * cache->frun_percent;

	_debug("limits {%llu,%llu,%llu} files",
	       (unsigned long long) cache->frun,
	       (unsigned long long) cache->fcull,
	       (unsigned long long) cache->fstop);

	do_div(stats.f_blocks, 100);
	cache->bstop = stats.f_blocks * cache->bstop_percent;
	cache->bcull = stats.f_blocks * cache->bcull_percent;
	cache->brun  = stats.f_blocks * cache->brun_percent;

	_debug("limits {%llu,%llu,%llu} blocks",
	       (unsigned long long) cache->brun,
	       (unsigned long long) cache->bcull,
	       (unsigned long long) cache->bstop);

	/* get the cache directory and check its type */
	cachedir = cachefiles_get_directory(cache, root, "cache", NULL);
	if (IS_ERR(cachedir)) {
		ret = PTR_ERR(cachedir);
		goto error_unsupported;
	}

	cache->store = cachedir;

	/* get the graveyard directory */
	graveyard = cachefiles_get_directory(cache, root, "graveyard", NULL);
	if (IS_ERR(graveyard)) {
		ret = PTR_ERR(graveyard);
		goto error_unsupported;
	}

	cache->graveyard = graveyard;
	cache->cache = cache_cookie;

	ret = fscache_add_cache(cache_cookie, &cachefiles_cache_ops, cache);
	if (ret < 0)
		goto error_add_cache;

	/* done */
	set_bit(CACHEFILES_READY, &cache->flags);
	dput(root);

	pr_info("File cache on %s registered\n", cache_cookie->name);

	/* check how much space the cache has */
	cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check);
	cachefiles_end_secure(cache, saved_cred);
	_leave(" = 0 [%px]", cache->cache);
	return 0;

error_add_cache:
	cachefiles_put_directory(cache->graveyard);
	cache->graveyard = NULL;
error_unsupported:
	cachefiles_put_directory(cache->store);
	cache->store = NULL;
	mntput(cache->mnt);
	cache->mnt = NULL;
	dput(root);
error_open_root:
	cachefiles_end_secure(cache, saved_cred);
	put_cred(cache->cache_cred);
	cache->cache_cred = NULL;
error_getsec:
	fscache_relinquish_cache(cache_cookie);
	cache->cache = NULL;
	pr_err("Failed to register: %d\n", ret);
	return ret;
}

/*
 * See if we have space for a number of pages and/or a number of files in the
 * cache
 */
int cachefiles_has_space(struct cachefiles_cache *cache,
			 unsigned fnr, unsigned bnr,
			 enum cachefiles_has_space_for reason)
{
	struct kstatfs stats;
	u64 b_avail, b_writing;
	int ret;

	struct path path = {
		.mnt	= cache->mnt,
		.dentry	= cache->mnt->mnt_root,
	};

	//_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u",
	//       (unsigned long long) cache->frun,
	//       (unsigned long long) cache->fcull,
	//       (unsigned long long) cache->fstop,
	//       (unsigned long long) cache->brun,
	//       (unsigned long long) cache->bcull,
	//       (unsigned long long) cache->bstop,
	//       fnr, bnr);

	/* find out how many pages of blockdev are available */
	memset(&stats, 0, sizeof(stats));

	ret = vfs_statfs(&path, &stats);
	if (ret < 0) {
		trace_cachefiles_vfs_error(NULL, d_inode(path.dentry), ret,
					   cachefiles_trace_statfs_error);
		if (ret == -EIO)
			cachefiles_io_error(cache, "statfs failed");
		_leave(" = %d", ret);
		return ret;
	}

	b_avail = stats.f_bavail;
	b_writing = atomic_long_read(&cache->b_writing);
	if (b_avail > b_writing)
		b_avail -= b_writing;
	else
		b_avail = 0;

	//_debug("avail %llu,%llu",
	//       (unsigned long long)stats.f_ffree,
	//       (unsigned long long)b_avail);

	/* see if there is sufficient space */
	if (stats.f_ffree > fnr)
		stats.f_ffree -= fnr;
	else
		stats.f_ffree = 0;

	if (b_avail > bnr)
		b_avail -= bnr;
	else
		b_avail = 0;

	ret = -ENOBUFS;
	if (stats.f_ffree < cache->fstop ||
	    b_avail < cache->bstop)
		goto stop_and_begin_cull;

	ret = 0;
	if (stats.f_ffree < cache->fcull ||
	    b_avail < cache->bcull)
		goto begin_cull;

	if (test_bit(CACHEFILES_CULLING, &cache->flags) &&
	    stats.f_ffree >= cache->frun &&
	    b_avail >= cache->brun &&
	    test_and_clear_bit(CACHEFILES_CULLING, &cache->flags)
	    ) {
		_debug("cease culling");
		cachefiles_state_changed(cache);
	}

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

stop_and_begin_cull:
	switch (reason) {
	case cachefiles_has_space_for_write:
		fscache_count_no_write_space();
		break;
	case cachefiles_has_space_for_create:
		fscache_count_no_create_space();
		break;
	default:
		break;
	}
begin_cull:
	if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) {
		_debug("### CULL CACHE ###");
		cachefiles_state_changed(cache);
	}

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

/*
 * Mark all the objects as being out of service and queue them all for cleanup.
 */
static void cachefiles_withdraw_objects(struct cachefiles_cache *cache)
{
	struct cachefiles_object *object;
	unsigned int count = 0;

	_enter("");

	spin_lock(&cache->object_list_lock);

	while (!list_empty(&cache->object_list)) {
		object = list_first_entry(&cache->object_list,
					  struct cachefiles_object, cache_link);
		cachefiles_see_object(object, cachefiles_obj_see_withdrawal);
		list_del_init(&object->cache_link);
		fscache_withdraw_cookie(object->cookie);
		count++;
		if ((count & 63) == 0) {
			spin_unlock(&cache->object_list_lock);
			cond_resched();
			spin_lock(&cache->object_list_lock);
		}
	}

	spin_unlock(&cache->object_list_lock);
	_leave(" [%u objs]", count);
}

/*
 * Withdraw fscache volumes.
 */
static void cachefiles_withdraw_fscache_volumes(struct cachefiles_cache *cache)
{
	struct list_head *cur;
	struct cachefiles_volume *volume;
	struct fscache_volume *vcookie;

	_enter("");
retry:
	spin_lock(&cache->object_list_lock);
	list_for_each(cur, &cache->volumes) {
		volume = list_entry(cur, struct cachefiles_volume, cache_link);

		if (atomic_read(&volume->vcookie->n_accesses) == 0)
			continue;

		vcookie = fscache_try_get_volume(volume->vcookie,
						 fscache_volume_get_withdraw);
		if (vcookie) {
			spin_unlock(&cache->object_list_lock);
			fscache_withdraw_volume(vcookie);
			fscache_put_volume(vcookie, fscache_volume_put_withdraw);
			goto retry;
		}
	}
	spin_unlock(&cache->object_list_lock);

	_leave("");
}

/*
 * Withdraw cachefiles volumes.
 */
static void cachefiles_withdraw_volumes(struct cachefiles_cache *cache)
{
	_enter("");

	for (;;) {
		struct fscache_volume *vcookie = NULL;
		struct cachefiles_volume *volume = NULL;

		spin_lock(&cache->object_list_lock);
		if (!list_empty(&cache->volumes)) {
			volume = list_first_entry(&cache->volumes,
						  struct cachefiles_volume, cache_link);
			vcookie = fscache_try_get_volume(volume->vcookie,
							 fscache_volume_get_withdraw);
			if (!vcookie) {
				spin_unlock(&cache->object_list_lock);
				cpu_relax();
				continue;
			}
			list_del_init(&volume->cache_link);
		}
		spin_unlock(&cache->object_list_lock);
		if (!volume)
			break;

		cachefiles_withdraw_volume(volume);
		fscache_put_volume(vcookie, fscache_volume_put_withdraw);
	}

	_leave("");
}

/*
 * Sync a cache to backing disk.
 */
static void cachefiles_sync_cache(struct cachefiles_cache *cache)
{
	const struct cred *saved_cred;
	int ret;

	_enter("%s", cache->cache->name);

	/* make sure all pages pinned by operations on behalf of the netfs are
	 * written to disc */
	cachefiles_begin_secure(cache, &saved_cred);
	down_read(&cache->mnt->mnt_sb->s_umount);
	ret = sync_filesystem(cache->mnt->mnt_sb);
	up_read(&cache->mnt->mnt_sb->s_umount);
	cachefiles_end_secure(cache, saved_cred);

	if (ret == -EIO)
		cachefiles_io_error(cache,
				    "Attempt to sync backing fs superblock returned error %d",
				    ret);
}

/*
 * Withdraw cache objects.
 */
void cachefiles_withdraw_cache(struct cachefiles_cache *cache)
{
	struct fscache_cache *fscache = cache->cache;

	pr_info("File cache on %s unregistering\n", fscache->name);

	fscache_withdraw_cache(fscache);
	cachefiles_withdraw_fscache_volumes(cache);

	/* we now have to destroy all the active objects pertaining to this
	 * cache - which we do by passing them off to thread pool to be
	 * disposed of */
	cachefiles_withdraw_objects(cache);
	fscache_wait_for_objects(fscache);

	cachefiles_withdraw_volumes(cache);
	cachefiles_sync_cache(cache);
	cache->cache = NULL;
	fscache_relinquish_cache(fscache);
}