aboutsummaryrefslogtreecommitdiff
path: root/fs/logfs/inode.c
blob: 33ec1aeaeec4f9d614a75140042753d441558f1a (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
/*
 * fs/logfs/inode.c	- inode handling code
 *
 * As should be obvious for Linux kernel code, license is GPLv2
 *
 * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
 */
#include "logfs.h"
#include <linux/writeback.h>
#include <linux/backing-dev.h>

/*
 * How soon to reuse old inode numbers?  LogFS doesn't store deleted inodes
 * on the medium.  It therefore also lacks a method to store the previous
 * generation number for deleted inodes.  Instead a single generation number
 * is stored which will be used for new inodes.  Being just a 32bit counter,
 * this can obvious wrap relatively quickly.  So we only reuse inodes if we
 * know that a fair number of inodes can be created before we have to increment
 * the generation again - effectively adding some bits to the counter.
 * But being too aggressive here means we keep a very large and very sparse
 * inode file, wasting space on indirect blocks.
 * So what is a good value?  Beats me.  64k seems moderately bad on both
 * fronts, so let's use that for now...
 *
 * NFS sucks, as everyone already knows.
 */
#define INOS_PER_WRAP (0x10000)

/*
 * Logfs' requirement to read inodes for garbage collection makes life a bit
 * harder.  GC may have to read inodes that are in I_FREEING state, when they
 * are being written out - and waiting for GC to make progress, naturally.
 *
 * So we cannot just call iget() or some variant of it, but first have to check
 * wether the inode in question might be in I_FREEING state.  Therefore we
 * maintain our own per-sb list of "almost deleted" inodes and check against
 * that list first.  Normally this should be at most 1-2 entries long.
 *
 * Also, inodes have logfs-specific reference counting on top of what the vfs
 * does.  When .destroy_inode is called, normally the reference count will drop
 * to zero and the inode gets deleted.  But if GC accessed the inode, its
 * refcount will remain nonzero and final deletion will have to wait.
 *
 * As a result we have two sets of functions to get/put inodes:
 * logfs_safe_iget/logfs_safe_iput	- safe to call from GC context
 * logfs_iget/iput			- normal version
 */
static struct kmem_cache *logfs_inode_cache;

static DEFINE_SPINLOCK(logfs_inode_lock);

static void logfs_inode_setops(struct inode *inode)
{
	switch (inode->i_mode & S_IFMT) {
	case S_IFDIR:
		inode->i_op = &logfs_dir_iops;
		inode->i_fop = &logfs_dir_fops;
		inode->i_mapping->a_ops = &logfs_reg_aops;
		break;
	case S_IFREG:
		inode->i_op = &logfs_reg_iops;
		inode->i_fop = &logfs_reg_fops;
		inode->i_mapping->a_ops = &logfs_reg_aops;
		break;
	case S_IFLNK:
		inode->i_op = &logfs_symlink_iops;
		inode->i_mapping->a_ops = &logfs_reg_aops;
		break;
	case S_IFSOCK:	/* fall through */
	case S_IFBLK:	/* fall through */
	case S_IFCHR:	/* fall through */
	case S_IFIFO:
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
		break;
	default:
		BUG();
	}
}

static struct inode *__logfs_iget(struct super_block *sb, ino_t ino)
{
	struct inode *inode = iget_locked(sb, ino);
	int err;

	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	err = logfs_read_inode(inode);
	if (err || inode->i_nlink == 0) {
		/* inode->i_nlink == 0 can be true when called from
		 * block validator */
		/* set i_nlink to 0 to prevent caching */
		inode->i_nlink = 0;
		logfs_inode(inode)->li_flags |= LOGFS_IF_ZOMBIE;
		iget_failed(inode);
		if (!err)
			err = -ENOENT;
		return ERR_PTR(err);
	}

	logfs_inode_setops(inode);
	unlock_new_inode(inode);
	return inode;
}

struct inode *logfs_iget(struct super_block *sb, ino_t ino)
{
	BUG_ON(ino == LOGFS_INO_MASTER);
	BUG_ON(ino == LOGFS_INO_SEGFILE);
	return __logfs_iget(sb, ino);
}

/*
 * is_cached is set to 1 if we hand out a cached inode, 0 otherwise.
 * this allows logfs_iput to do the right thing later
 */
struct inode *logfs_safe_iget(struct super_block *sb, ino_t ino, int *is_cached)
{
	struct logfs_super *super = logfs_super(sb);
	struct logfs_inode *li;

	if (ino == LOGFS_INO_MASTER)
		return super->s_master_inode;
	if (ino == LOGFS_INO_SEGFILE)
		return super->s_segfile_inode;

	spin_lock(&logfs_inode_lock);
	list_for_each_entry(li, &super->s_freeing_list, li_freeing_list)
		if (li->vfs_inode.i_ino == ino) {
			li->li_refcount++;
			spin_unlock(&logfs_inode_lock);
			*is_cached = 1;
			return &li->vfs_inode;
		}
	spin_unlock(&logfs_inode_lock);

	*is_cached = 0;
	return __logfs_iget(sb, ino);
}

static void __logfs_destroy_inode(struct inode *inode)
{
	struct logfs_inode *li = logfs_inode(inode);

	BUG_ON(li->li_block);
	list_del(&li->li_freeing_list);
	kmem_cache_free(logfs_inode_cache, li);
}

static void logfs_destroy_inode(struct inode *inode)
{
	struct logfs_inode *li = logfs_inode(inode);

	BUG_ON(list_empty(&li->li_freeing_list));
	spin_lock(&logfs_inode_lock);
	li->li_refcount--;
	if (li->li_refcount == 0)
		__logfs_destroy_inode(inode);
	spin_unlock(&logfs_inode_lock);
}

void logfs_safe_iput(struct inode *inode, int is_cached)
{
	if (inode->i_ino == LOGFS_INO_MASTER)
		return;
	if (inode->i_ino == LOGFS_INO_SEGFILE)
		return;

	if (is_cached) {
		logfs_destroy_inode(inode);
		return;
	}

	iput(inode);
}

static void logfs_init_inode(struct super_block *sb, struct inode *inode)
{
	struct logfs_inode *li = logfs_inode(inode);
	int i;

	li->li_flags	= 0;
	li->li_height	= 0;
	li->li_used_bytes = 0;
	li->li_block	= NULL;
	inode->i_uid	= 0;
	inode->i_gid	= 0;
	inode->i_size	= 0;
	inode->i_blocks	= 0;
	inode->i_ctime	= CURRENT_TIME;
	inode->i_mtime	= CURRENT_TIME;
	inode->i_nlink	= 1;
	INIT_LIST_HEAD(&li->li_freeing_list);

	for (i = 0; i < LOGFS_EMBEDDED_FIELDS; i++)
		li->li_data[i] = 0;

	return;
}

static struct inode *logfs_alloc_inode(struct super_block *sb)
{
	struct logfs_inode *li;

	li = kmem_cache_alloc(logfs_inode_cache, GFP_NOFS);
	if (!li)
		return NULL;
	logfs_init_inode(sb, &li->vfs_inode);
	return &li->vfs_inode;
}

/*
 * In logfs inodes are written to an inode file.  The inode file, like any
 * other file, is managed with a inode.  The inode file's inode, aka master
 * inode, requires special handling in several respects.  First, it cannot be
 * written to the inode file, so it is stored in the journal instead.
 *
 * Secondly, this inode cannot be written back and destroyed before all other
 * inodes have been written.  The ordering is important.  Linux' VFS is happily
 * unaware of the ordering constraint and would ordinarily destroy the master
 * inode at umount time while other inodes are still in use and dirty.  Not
 * good.
 *
 * So logfs makes sure the master inode is not written until all other inodes
 * have been destroyed.  Sadly, this method has another side-effect.  The VFS
 * will notice one remaining inode and print a frightening warning message.
 * Worse, it is impossible to judge whether such a warning was caused by the
 * master inode or any other inodes have leaked as well.
 *
 * Our attempt of solving this is with logfs_new_meta_inode() below.  Its
 * purpose is to create a new inode that will not trigger the warning if such
 * an inode is still in use.  An ugly hack, no doubt.  Suggections for
 * improvement are welcome.
 */
struct inode *logfs_new_meta_inode(struct super_block *sb, u64 ino)
{
	struct inode *inode;

	inode = logfs_alloc_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);

	inode->i_mode = S_IFREG;
	inode->i_ino = ino;
	inode->i_sb = sb;

	/* This is a blatant copy of alloc_inode code.  We'd need alloc_inode
	 * to be nonstatic, alas. */
	{
		struct address_space * const mapping = &inode->i_data;

		mapping->a_ops = &logfs_reg_aops;
		mapping->host = inode;
		mapping->flags = 0;
		mapping_set_gfp_mask(mapping, GFP_NOFS);
		mapping->assoc_mapping = NULL;
		mapping->backing_dev_info = &default_backing_dev_info;
		inode->i_mapping = mapping;
		inode->i_nlink = 1;
	}

	return inode;
}

struct inode *logfs_read_meta_inode(struct super_block *sb, u64 ino)
{
	struct inode *inode;
	int err;

	inode = logfs_new_meta_inode(sb, ino);
	if (IS_ERR(inode))
		return inode;

	err = logfs_read_inode(inode);
	if (err) {
		destroy_meta_inode(inode);
		return ERR_PTR(err);
	}
	logfs_inode_setops(inode);
	return inode;
}

static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	int ret;
	long flags = WF_LOCK;

	/* Can only happen if creat() failed.  Safe to skip. */
	if (logfs_inode(inode)->li_flags & LOGFS_IF_STILLBORN)
		return 0;

	ret = __logfs_write_inode(inode, flags);
	LOGFS_BUG_ON(ret, inode->i_sb);
	return ret;
}

void destroy_meta_inode(struct inode *inode)
{
	if (inode) {
		if (inode->i_data.nrpages)
			truncate_inode_pages(&inode->i_data, 0);
		logfs_clear_inode(inode);
		kmem_cache_free(logfs_inode_cache, logfs_inode(inode));
	}
}

/* called with inode_lock held */
static void logfs_drop_inode(struct inode *inode)
{
	struct logfs_super *super = logfs_super(inode->i_sb);
	struct logfs_inode *li = logfs_inode(inode);

	spin_lock(&logfs_inode_lock);
	list_move(&li->li_freeing_list, &super->s_freeing_list);
	spin_unlock(&logfs_inode_lock);
	generic_drop_inode(inode);
}

static void logfs_set_ino_generation(struct super_block *sb,
		struct inode *inode)
{
	struct logfs_super *super = logfs_super(sb);
	u64 ino;

	mutex_lock(&super->s_journal_mutex);
	ino = logfs_seek_hole(super->s_master_inode, super->s_last_ino);
	super->s_last_ino = ino;
	super->s_inos_till_wrap--;
	if (super->s_inos_till_wrap < 0) {
		super->s_last_ino = LOGFS_RESERVED_INOS;
		super->s_generation++;
		super->s_inos_till_wrap = INOS_PER_WRAP;
	}
	inode->i_ino = ino;
	inode->i_generation = super->s_generation;
	mutex_unlock(&super->s_journal_mutex);
}

struct inode *logfs_new_inode(struct inode *dir, int mode)
{
	struct super_block *sb = dir->i_sb;
	struct inode *inode;

	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);

	logfs_init_inode(sb, inode);

	/* inherit parent flags */
	logfs_inode(inode)->li_flags |=
		logfs_inode(dir)->li_flags & LOGFS_FL_INHERITED;

	inode->i_mode = mode;
	logfs_set_ino_generation(sb, inode);

	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			inode->i_mode |= S_ISGID;
	}

	logfs_inode_setops(inode);
	insert_inode_hash(inode);

	return inode;
}

static void logfs_init_once(void *_li)
{
	struct logfs_inode *li = _li;
	int i;

	li->li_flags = 0;
	li->li_used_bytes = 0;
	li->li_refcount = 1;
	for (i = 0; i < LOGFS_EMBEDDED_FIELDS; i++)
		li->li_data[i] = 0;
	inode_init_once(&li->vfs_inode);
}

static int logfs_sync_fs(struct super_block *sb, int wait)
{
	/* FIXME: write anchor */
	logfs_super(sb)->s_devops->sync(sb);
	return 0;
}

const struct super_operations logfs_super_operations = {
	.alloc_inode	= logfs_alloc_inode,
	.clear_inode	= logfs_clear_inode,
	.delete_inode	= logfs_delete_inode,
	.destroy_inode	= logfs_destroy_inode,
	.drop_inode	= logfs_drop_inode,
	.write_inode	= logfs_write_inode,
	.statfs		= logfs_statfs,
	.sync_fs	= logfs_sync_fs,
};

int logfs_init_inode_cache(void)
{
	logfs_inode_cache = kmem_cache_create("logfs_inode_cache",
			sizeof(struct logfs_inode), 0, SLAB_RECLAIM_ACCOUNT,
			logfs_init_once);
	if (!logfs_inode_cache)
		return -ENOMEM;
	return 0;
}

void logfs_destroy_inode_cache(void)
{
	kmem_cache_destroy(logfs_inode_cache);
}