cleancache.c 9.86 KB
Newer Older
1
2
3
4
5
/*
 * Cleancache frontend
 *
 * This code provides the generic "frontend" layer to call a matching
 * "backend" driver implementation of cleancache.  See
6
 * Documentation/vm/cleancache.rst for more information.
7
8
9
10
11
12
13
14
15
16
17
 *
 * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
 * Author: Dan Magenheimer
 *
 * This work is licensed under the terms of the GNU GPL, version 2.
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/exportfs.h>
#include <linux/mm.h>
18
#include <linux/debugfs.h>
19
20
21
#include <linux/cleancache.h>

/*
22
 * cleancache_ops is set by cleancache_register_ops to contain the pointers
23
24
 * to the cleancache "backend" implementation functions.
 */
25
static const struct cleancache_ops *cleancache_ops __read_mostly;
26

27
/*
28
 * Counters available via /sys/kernel/debug/cleancache (if debugfs is
29
30
31
32
33
34
35
 * properly configured.  These are for information only so are not protected
 * against increment races.
 */
static u64 cleancache_succ_gets;
static u64 cleancache_failed_gets;
static u64 cleancache_puts;
static u64 cleancache_invalidates;
36

37
38
39
40
41
42
43
44
45
46
47
static void cleancache_register_ops_sb(struct super_block *sb, void *unused)
{
	switch (sb->cleancache_poolid) {
	case CLEANCACHE_NO_BACKEND:
		__cleancache_init_fs(sb);
		break;
	case CLEANCACHE_NO_BACKEND_SHARED:
		__cleancache_init_shared_fs(sb);
		break;
	}
}
48
49

/*
50
 * Register operations for cleancache. Returns 0 on success.
51
 */
52
int cleancache_register_ops(const struct cleancache_ops *ops)
53
{
54
	if (cmpxchg(&cleancache_ops, NULL, ops))
55
		return -EBUSY;
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
	 * A cleancache backend can be built as a module and hence loaded after
	 * a cleancache enabled filesystem has called cleancache_init_fs. To
	 * handle such a scenario, here we call ->init_fs or ->init_shared_fs
	 * for each active super block. To differentiate between local and
	 * shared filesystems, we temporarily initialize sb->cleancache_poolid
	 * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED
	 * respectively in case there is no backend registered at the time
	 * cleancache_init_fs or cleancache_init_shared_fs is called.
	 *
	 * Since filesystems can be mounted concurrently with cleancache
	 * backend registration, we have to be careful to guarantee that all
	 * cleancache enabled filesystems that has been mounted by the time
	 * cleancache_register_ops is called has got and all mounted later will
	 * get cleancache_poolid. This is assured by the following statements
	 * tied together:
	 *
	 * a) iterate_supers skips only those super blocks that has started
	 *    ->kill_sb
	 *
	 * b) if iterate_supers encounters a super block that has not finished
	 *    ->mount yet, it waits until it is finished
	 *
	 * c) cleancache_init_fs is called from ->mount and
	 *    cleancache_invalidate_fs is called from ->kill_sb
	 *
	 * d) we call iterate_supers after cleancache_ops has been set
	 *
	 * From a) it follows that if iterate_supers skips a super block, then
	 * either the super block is already dead, in which case we do not need
	 * to bother initializing cleancache for it, or it was mounted after we
	 * initiated iterate_supers. In the latter case, it must have seen
	 * cleancache_ops set according to d) and initialized cleancache from
	 * ->mount by itself according to c). This proves that we call
	 * ->init_fs at least once for each active super block.
	 *
	 * From b) and c) it follows that if iterate_supers encounters a super
	 * block that has already started ->init_fs, it will wait until ->mount
	 * and hence ->init_fs has finished, then check cleancache_poolid, see
	 * that it has already been set and therefore do nothing. This proves
	 * that we call ->init_fs no more than once for each super block.
	 *
	 * Combined together, the last two paragraphs prove the function
	 * correctness.
	 *
	 * Note that various cleancache callbacks may proceed before this
	 * function is called or even concurrently with it, but since
	 * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop
	 * until the corresponding ->init_fs has been actually called and
	 * cleancache_ops has been set.
107
	 */
108
	iterate_supers(cleancache_register_ops_sb, NULL);
109
	return 0;
110
111
112
113
114
115
}
EXPORT_SYMBOL(cleancache_register_ops);

/* Called by a cleancache-enabled filesystem at time of mount */
void __cleancache_init_fs(struct super_block *sb)
{
116
	int pool_id = CLEANCACHE_NO_BACKEND;
117

118
119
120
121
	if (cleancache_ops) {
		pool_id = cleancache_ops->init_fs(PAGE_SIZE);
		if (pool_id < 0)
			pool_id = CLEANCACHE_NO_POOL;
122
	}
123
	sb->cleancache_poolid = pool_id;
124
125
126
127
}
EXPORT_SYMBOL(__cleancache_init_fs);

/* Called by a cleancache-enabled clustered filesystem at time of mount */
128
void __cleancache_init_shared_fs(struct super_block *sb)
129
{
130
	int pool_id = CLEANCACHE_NO_BACKEND_SHARED;
131

132
	if (cleancache_ops) {
133
		pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE);
134
135
		if (pool_id < 0)
			pool_id = CLEANCACHE_NO_POOL;
136
	}
137
	sb->cleancache_poolid = pool_id;
138
139
140
141
142
143
144
145
146
147
}
EXPORT_SYMBOL(__cleancache_init_shared_fs);

/*
 * If the filesystem uses exportable filehandles, use the filehandle as
 * the key, else use the inode number.
 */
static int cleancache_get_key(struct inode *inode,
			      struct cleancache_filekey *key)
{
Al Viro's avatar
Al Viro committed
148
	int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *);
149
150
151
152
153
154
155
	int len = 0, maxlen = CLEANCACHE_KEY_MAX;
	struct super_block *sb = inode->i_sb;

	key->u.ino = inode->i_ino;
	if (sb->s_export_op != NULL) {
		fhfn = sb->s_export_op->encode_fh;
		if  (fhfn) {
Al Viro's avatar
Al Viro committed
156
			len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL);
157
			if (len <= FILEID_ROOT || len == FILEID_INVALID)
158
159
160
161
162
163
164
165
166
167
168
169
170
171
				return -1;
			if (maxlen > CLEANCACHE_KEY_MAX)
				return -1;
		}
	}
	return 0;
}

/*
 * "Get" data from cleancache associated with the poolid/inode/index
 * that were specified when the data was put to cleanache and, if
 * successful, use it to fill the specified page with data and return 0.
 * The pageframe is unchanged and returns -1 if the get fails.
 * Page must be locked by caller.
172
173
174
175
 *
 * The function has two checks before any action is taken - whether
 * a backend is registered and whether the sb->cleancache_poolid
 * is correct.
176
177
178
179
180
181
182
 */
int __cleancache_get_page(struct page *page)
{
	int ret = -1;
	int pool_id;
	struct cleancache_filekey key = { .u.key = { 0 } };

183
	if (!cleancache_ops) {
184
185
186
187
		cleancache_failed_gets++;
		goto out;
	}

188
	VM_BUG_ON_PAGE(!PageLocked(page), page);
189
190
	pool_id = page->mapping->host->i_sb->cleancache_poolid;
	if (pool_id < 0)
191
192
193
194
195
		goto out;

	if (cleancache_get_key(page->mapping->host, &key) < 0)
		goto out;

196
	ret = cleancache_ops->get_page(pool_id, key, page->index, page);
197
198
199
200
201
202
203
204
205
206
207
208
209
210
	if (ret == 0)
		cleancache_succ_gets++;
	else
		cleancache_failed_gets++;
out:
	return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);

/*
 * "Put" data from a page to cleancache and associate it with the
 * (previously-obtained per-filesystem) poolid and the page's,
 * inode and page index.  Page must be locked.  Note that a put_page
 * always "succeeds", though a subsequent get_page may succeed or fail.
211
212
213
214
 *
 * The function has two checks before any action is taken - whether
 * a backend is registered and whether the sb->cleancache_poolid
 * is correct.
215
216
217
218
219
220
 */
void __cleancache_put_page(struct page *page)
{
	int pool_id;
	struct cleancache_filekey key = { .u.key = { 0 } };

221
	if (!cleancache_ops) {
222
223
224
225
		cleancache_puts++;
		return;
	}

226
	VM_BUG_ON_PAGE(!PageLocked(page), page);
227
	pool_id = page->mapping->host->i_sb->cleancache_poolid;
228
	if (pool_id >= 0 &&
229
		cleancache_get_key(page->mapping->host, &key) >= 0) {
230
		cleancache_ops->put_page(pool_id, key, page->index, page);
231
232
233
234
235
236
		cleancache_puts++;
	}
}
EXPORT_SYMBOL(__cleancache_put_page);

/*
237
 * Invalidate any data from cleancache associated with the poolid and the
238
 * page's inode and page index so that a subsequent "get" will fail.
239
240
241
242
 *
 * The function has two checks before any action is taken - whether
 * a backend is registered and whether the sb->cleancache_poolid
 * is correct.
243
 */
244
245
void __cleancache_invalidate_page(struct address_space *mapping,
					struct page *page)
246
247
{
	/* careful... page->mapping is NULL sometimes when this is called */
248
	int pool_id = mapping->host->i_sb->cleancache_poolid;
249
250
	struct cleancache_filekey key = { .u.key = { 0 } };

251
	if (!cleancache_ops)
252
253
		return;

254
	if (pool_id >= 0) {
255
		VM_BUG_ON_PAGE(!PageLocked(page), page);
256
		if (cleancache_get_key(mapping->host, &key) >= 0) {
257
			cleancache_ops->invalidate_page(pool_id,
258
					key, page->index);
259
			cleancache_invalidates++;
260
261
262
		}
	}
}
263
EXPORT_SYMBOL(__cleancache_invalidate_page);
264
265

/*
266
 * Invalidate all data from cleancache associated with the poolid and the
267
268
 * mappings's inode so that all subsequent gets to this poolid/inode
 * will fail.
269
270
271
272
 *
 * The function has two checks before any action is taken - whether
 * a backend is registered and whether the sb->cleancache_poolid
 * is correct.
273
 */
274
void __cleancache_invalidate_inode(struct address_space *mapping)
275
{
276
	int pool_id = mapping->host->i_sb->cleancache_poolid;
277
278
	struct cleancache_filekey key = { .u.key = { 0 } };

279
	if (!cleancache_ops)
280
281
		return;

282
	if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
283
		cleancache_ops->invalidate_inode(pool_id, key);
284
}
285
EXPORT_SYMBOL(__cleancache_invalidate_inode);
286
287
288

/*
 * Called by any cleancache-enabled filesystem at time of unmount;
289
290
 * note that pool_id is surrendered and may be returned by a subsequent
 * cleancache_init_fs or cleancache_init_shared_fs.
291
 */
292
void __cleancache_invalidate_fs(struct super_block *sb)
293
{
294
	int pool_id;
295

296
297
298
299
300
	pool_id = sb->cleancache_poolid;
	sb->cleancache_poolid = CLEANCACHE_NO_POOL;

	if (cleancache_ops && pool_id >= 0)
		cleancache_ops->invalidate_fs(pool_id);
301
}
302
EXPORT_SYMBOL(__cleancache_invalidate_fs);
303
304
305

static int __init init_cleancache(void)
{
306
307
308
309
#ifdef CONFIG_DEBUG_FS
	struct dentry *root = debugfs_create_dir("cleancache", NULL);
	if (root == NULL)
		return -ENXIO;
310
311
312
313
	debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets);
	debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets);
	debugfs_create_u64("puts", 0444, root, &cleancache_puts);
	debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates);
314
#endif
315
316
317
	return 0;
}
module_init(init_cleancache)