summaryrefslogtreecommitdiff
path: root/fs/erofs/super.c
blob: 499dc7f5d0e6e762928c607b6ef9ffd4fc6bdf71 (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
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             http://www.huawei.com/
 * Created by Gao Xiang <gaoxiang25@huawei.com>
 */
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include "xattr.h"

#define CREATE_TRACE_POINTS
#include <trace/events/erofs.h>

static struct kmem_cache *erofs_inode_cachep __read_mostly;

static void init_once(void *ptr)
{
	struct erofs_vnode *vi = ptr;

	inode_init_once(&vi->vfs_inode);
}

static struct inode *alloc_inode(struct super_block *sb)
{
	struct erofs_vnode *vi =
		kmem_cache_alloc(erofs_inode_cachep, GFP_KERNEL);

	if (!vi)
		return NULL;

	/* zero out everything except vfs_inode */
	memset(vi, 0, offsetof(struct erofs_vnode, vfs_inode));
	return &vi->vfs_inode;
}

static void free_inode(struct inode *inode)
{
	struct erofs_vnode *vi = EROFS_V(inode);

	/* be careful RCU symlink path (see ext4_inode_info->i_data)! */
	if (is_inode_fast_symlink(inode))
		kfree(inode->i_link);

	kfree(vi->xattr_shared_xattrs);

	kmem_cache_free(erofs_inode_cachep, vi);
}

static bool check_layout_compatibility(struct super_block *sb,
				       struct erofs_super_block *layout)
{
	const unsigned int feature = le32_to_cpu(layout->feature_incompat);

	EROFS_SB(sb)->feature_incompat = feature;

	/* check if current kernel meets all mandatory requirements */
	if (feature & (~EROFS_ALL_FEATURE_INCOMPAT)) {
		errln("unidentified incompatible feature %x, please upgrade kernel version",
		      feature & ~EROFS_ALL_FEATURE_INCOMPAT);
		return false;
	}
	return true;
}

static int superblock_read(struct super_block *sb)
{
	struct erofs_sb_info *sbi;
	struct buffer_head *bh;
	struct erofs_super_block *layout;
	unsigned int blkszbits;
	int ret;

	bh = sb_bread(sb, 0);

	if (!bh) {
		errln("cannot read erofs superblock");
		return -EIO;
	}

	sbi = EROFS_SB(sb);
	layout = (struct erofs_super_block *)((u8 *)bh->b_data
		 + EROFS_SUPER_OFFSET);

	ret = -EINVAL;
	if (le32_to_cpu(layout->magic) != EROFS_SUPER_MAGIC_V1) {
		errln("cannot find valid erofs superblock");
		goto out;
	}

	blkszbits = layout->blkszbits;
	/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
	if (blkszbits != LOG_BLOCK_SIZE) {
		errln("blksize %u isn't supported on this platform",
		      1 << blkszbits);
		goto out;
	}

	if (!check_layout_compatibility(sb, layout))
		goto out;

	sbi->blocks = le32_to_cpu(layout->blocks);
	sbi->meta_blkaddr = le32_to_cpu(layout->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
	sbi->xattr_blkaddr = le32_to_cpu(layout->xattr_blkaddr);
#endif
	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
	sbi->root_nid = le16_to_cpu(layout->root_nid);
	sbi->inos = le64_to_cpu(layout->inos);

	sbi->build_time = le64_to_cpu(layout->build_time);
	sbi->build_time_nsec = le32_to_cpu(layout->build_time_nsec);

	memcpy(&sb->s_uuid, layout->uuid, sizeof(layout->uuid));

	ret = strscpy(sbi->volume_name, layout->volume_name,
		      sizeof(layout->volume_name));
	if (ret < 0) {	/* -E2BIG */
		errln("bad volume name without NIL terminator");
		ret = -EFSCORRUPTED;
		goto out;
	}
	ret = 0;
out:
	brelse(bh);
	return ret;
}

#ifdef CONFIG_EROFS_FAULT_INJECTION
const char *erofs_fault_name[FAULT_MAX] = {
	[FAULT_KMALLOC]		= "kmalloc",
	[FAULT_READ_IO]		= "read IO error",
};

static void __erofs_build_fault_attr(struct erofs_sb_info *sbi,
				     unsigned int rate)
{
	struct erofs_fault_info *ffi = &sbi->fault_info;

	if (rate) {
		atomic_set(&ffi->inject_ops, 0);
		ffi->inject_rate = rate;
		ffi->inject_type = (1 << FAULT_MAX) - 1;
	} else {
		memset(ffi, 0, sizeof(struct erofs_fault_info));
	}

	set_opt(sbi, FAULT_INJECTION);
}

static int erofs_build_fault_attr(struct erofs_sb_info *sbi,
				  substring_t *args)
{
	int rate = 0;

	if (args->from && match_int(args, &rate))
		return -EINVAL;

	__erofs_build_fault_attr(sbi, rate);
	return 0;
}

static unsigned int erofs_get_fault_rate(struct erofs_sb_info *sbi)
{
	return sbi->fault_info.inject_rate;
}
#else
static void __erofs_build_fault_attr(struct erofs_sb_info *sbi,
				     unsigned int rate)
{
}

static int erofs_build_fault_attr(struct erofs_sb_info *sbi,
				  substring_t *args)
{
	infoln("fault_injection options not supported");
	return 0;
}

static unsigned int erofs_get_fault_rate(struct erofs_sb_info *sbi)
{
	return 0;
}
#endif

#ifdef CONFIG_EROFS_FS_ZIP
static int erofs_build_cache_strategy(struct erofs_sb_info *sbi,
				      substring_t *args)
{
	const char *cs = match_strdup(args);
	int err = 0;

	if (!cs) {
		errln("Not enough memory to store cache strategy");
		return -ENOMEM;
	}

	if (!strcmp(cs, "disabled")) {
		sbi->cache_strategy = EROFS_ZIP_CACHE_DISABLED;
	} else if (!strcmp(cs, "readahead")) {
		sbi->cache_strategy = EROFS_ZIP_CACHE_READAHEAD;
	} else if (!strcmp(cs, "readaround")) {
		sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
	} else {
		errln("Unrecognized cache strategy \"%s\"", cs);
		err = -EINVAL;
	}
	kfree(cs);
	return err;
}
#else
static int erofs_build_cache_strategy(struct erofs_sb_info *sbi,
				      substring_t *args)
{
	infoln("EROFS compression is disabled, so cache strategy is ignored");
	return 0;
}
#endif

/* set up default EROFS parameters */
static void default_options(struct erofs_sb_info *sbi)
{
#ifdef CONFIG_EROFS_FS_ZIP
	sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
	sbi->max_sync_decompress_pages = 3;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
	set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
	set_opt(sbi, POSIX_ACL);
#endif
}

enum {
	Opt_user_xattr,
	Opt_nouser_xattr,
	Opt_acl,
	Opt_noacl,
	Opt_fault_injection,
	Opt_cache_strategy,
	Opt_err
};

static match_table_t erofs_tokens = {
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
	{Opt_fault_injection, "fault_injection=%u"},
	{Opt_cache_strategy, "cache_strategy=%s"},
	{Opt_err, NULL}
};

static int parse_options(struct super_block *sb, char *options)
{
	substring_t args[MAX_OPT_ARGS];
	char *p;
	int err;

	if (!options)
		return 0;

	while ((p = strsep(&options, ","))) {
		int token;

		if (!*p)
			continue;

		args[0].to = args[0].from = NULL;
		token = match_token(p, erofs_tokens, args);

		switch (token) {
#ifdef CONFIG_EROFS_FS_XATTR
		case Opt_user_xattr:
			set_opt(EROFS_SB(sb), XATTR_USER);
			break;
		case Opt_nouser_xattr:
			clear_opt(EROFS_SB(sb), XATTR_USER);
			break;
#else
		case Opt_user_xattr:
			infoln("user_xattr options not supported");
			break;
		case Opt_nouser_xattr:
			infoln("nouser_xattr options not supported");
			break;
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
		case Opt_acl:
			set_opt(EROFS_SB(sb), POSIX_ACL);
			break;
		case Opt_noacl:
			clear_opt(EROFS_SB(sb), POSIX_ACL);
			break;
#else
		case Opt_acl:
			infoln("acl options not supported");
			break;
		case Opt_noacl:
			infoln("noacl options not supported");
			break;
#endif
		case Opt_fault_injection:
			err = erofs_build_fault_attr(EROFS_SB(sb), args);
			if (err)
				return err;
			break;
		case Opt_cache_strategy:
			err = erofs_build_cache_strategy(EROFS_SB(sb), args);
			if (err)
				return err;
			break;
		default:
			errln("Unrecognized mount option \"%s\" or missing value", p);
			return -EINVAL;
		}
	}
	return 0;
}

#ifdef CONFIG_EROFS_FS_ZIP
static const struct address_space_operations managed_cache_aops;

static int managed_cache_releasepage(struct page *page, gfp_t gfp_mask)
{
	int ret = 1;	/* 0 - busy */
	struct address_space *const mapping = page->mapping;

	DBG_BUGON(!PageLocked(page));
	DBG_BUGON(mapping->a_ops != &managed_cache_aops);

	if (PagePrivate(page))
		ret = erofs_try_to_free_cached_page(mapping, page);

	return ret;
}

static void managed_cache_invalidatepage(struct page *page,
					 unsigned int offset,
					 unsigned int length)
{
	const unsigned int stop = length + offset;

	DBG_BUGON(!PageLocked(page));

	/* Check for potential overflow in debug mode */
	DBG_BUGON(stop > PAGE_SIZE || stop < length);

	if (offset == 0 && stop == PAGE_SIZE)
		while (!managed_cache_releasepage(page, GFP_NOFS))
			cond_resched();
}

static const struct address_space_operations managed_cache_aops = {
	.releasepage = managed_cache_releasepage,
	.invalidatepage = managed_cache_invalidatepage,
};

static int erofs_init_managed_cache(struct super_block *sb)
{
	struct erofs_sb_info *const sbi = EROFS_SB(sb);
	struct inode *const inode = new_inode(sb);

	if (!inode)
		return -ENOMEM;

	set_nlink(inode, 1);
	inode->i_size = OFFSET_MAX;

	inode->i_mapping->a_ops = &managed_cache_aops;
	mapping_set_gfp_mask(inode->i_mapping,
			     GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
	sbi->managed_cache = inode;
	return 0;
}
#else
static int erofs_init_managed_cache(struct super_block *sb) { return 0; }
#endif

static int erofs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *inode;
	struct erofs_sb_info *sbi;
	int err;

	infoln("fill_super, device -> %s", sb->s_id);
	infoln("options -> %s", (char *)data);

	sb->s_magic = EROFS_SUPER_MAGIC;

	if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) {
		errln("failed to set erofs blksize");
		return -EINVAL;
	}

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	sb->s_fs_info = sbi;
	err = superblock_read(sb);
	if (err)
		return err;

	sb->s_flags |= SB_RDONLY | SB_NOATIME;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_time_gran = 1;

	sb->s_op = &erofs_sops;

#ifdef CONFIG_EROFS_FS_XATTR
	sb->s_xattr = erofs_xattr_handlers;
#endif
	/* set erofs default mount options */
	default_options(sbi);

	err = parse_options(sb, data);
	if (err)
		return err;

	if (!silent)
		infoln("root inode @ nid %llu", ROOT_NID(sbi));

	if (test_opt(sbi, POSIX_ACL))
		sb->s_flags |= SB_POSIXACL;
	else
		sb->s_flags &= ~SB_POSIXACL;

#ifdef CONFIG_EROFS_FS_ZIP
	INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC);
#endif

	/* get the root inode */
	inode = erofs_iget(sb, ROOT_NID(sbi), true);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	if (!S_ISDIR(inode->i_mode)) {
		errln("rootino(nid %llu) is not a directory(i_mode %o)",
		      ROOT_NID(sbi), inode->i_mode);
		iput(inode);
		return -EINVAL;
	}

	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		return -ENOMEM;

	erofs_shrinker_register(sb);
	/* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */
	err = erofs_init_managed_cache(sb);
	if (err)
		return err;

	if (!silent)
		infoln("mounted on %s with opts: %s.", sb->s_id, (char *)data);
	return 0;
}

static struct dentry *erofs_mount(struct file_system_type *fs_type, int flags,
				  const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, erofs_fill_super);
}

/*
 * could be triggered after deactivate_locked_super()
 * is called, thus including umount and failed to initialize.
 */
static void erofs_kill_sb(struct super_block *sb)
{
	struct erofs_sb_info *sbi;

	WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);
	infoln("unmounting for %s", sb->s_id);

	kill_block_super(sb);

	sbi = EROFS_SB(sb);
	if (!sbi)
		return;
	kfree(sbi);
	sb->s_fs_info = NULL;
}

/* called when ->s_root is non-NULL */
static void erofs_put_super(struct super_block *sb)
{
	struct erofs_sb_info *const sbi = EROFS_SB(sb);

	DBG_BUGON(!sbi);

	erofs_shrinker_unregister(sb);
#ifdef CONFIG_EROFS_FS_ZIP
	iput(sbi->managed_cache);
	sbi->managed_cache = NULL;
#endif
}

static struct file_system_type erofs_fs_type = {
	.owner          = THIS_MODULE,
	.name           = "erofs",
	.mount          = erofs_mount,
	.kill_sb        = erofs_kill_sb,
	.fs_flags       = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("erofs");

static int __init erofs_module_init(void)
{
	int err;

	erofs_check_ondisk_layout_definitions();
	infoln("initializing erofs " EROFS_VERSION);

	erofs_inode_cachep = kmem_cache_create("erofs_inode",
					       sizeof(struct erofs_vnode), 0,
					       SLAB_RECLAIM_ACCOUNT,
					       init_once);
	if (!erofs_inode_cachep) {
		err = -ENOMEM;
		goto icache_err;
	}

	err = erofs_init_shrinker();
	if (err)
		goto shrinker_err;

	err = z_erofs_init_zip_subsystem();
	if (err)
		goto zip_err;

	err = register_filesystem(&erofs_fs_type);
	if (err)
		goto fs_err;

	infoln("successfully to initialize erofs");
	return 0;

fs_err:
	z_erofs_exit_zip_subsystem();
zip_err:
	erofs_exit_shrinker();
shrinker_err:
	kmem_cache_destroy(erofs_inode_cachep);
icache_err:
	return err;
}

static void __exit erofs_module_exit(void)
{
	unregister_filesystem(&erofs_fs_type);
	z_erofs_exit_zip_subsystem();
	erofs_exit_shrinker();

	/* Ensure all RCU free inodes are safe before cache is destroyed. */
	rcu_barrier();
	kmem_cache_destroy(erofs_inode_cachep);
	infoln("successfully finalize erofs");
}

/* get filesystem statistics */
static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);

	buf->f_type = sb->s_magic;
	buf->f_bsize = EROFS_BLKSIZ;
	buf->f_blocks = sbi->blocks;
	buf->f_bfree = buf->f_bavail = 0;

	buf->f_files = ULLONG_MAX;
	buf->f_ffree = ULLONG_MAX - sbi->inos;

	buf->f_namelen = EROFS_NAME_LEN;

	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);
	return 0;
}

static int erofs_show_options(struct seq_file *seq, struct dentry *root)
{
	struct erofs_sb_info *sbi __maybe_unused = EROFS_SB(root->d_sb);

#ifdef CONFIG_EROFS_FS_XATTR
	if (test_opt(sbi, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	else
		seq_puts(seq, ",nouser_xattr");
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
	if (test_opt(sbi, POSIX_ACL))
		seq_puts(seq, ",acl");
	else
		seq_puts(seq, ",noacl");
#endif
	if (test_opt(sbi, FAULT_INJECTION))
		seq_printf(seq, ",fault_injection=%u",
			   erofs_get_fault_rate(sbi));
#ifdef CONFIG_EROFS_FS_ZIP
	if (sbi->cache_strategy == EROFS_ZIP_CACHE_DISABLED) {
		seq_puts(seq, ",cache_strategy=disabled");
	} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) {
		seq_puts(seq, ",cache_strategy=readahead");
	} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAROUND) {
		seq_puts(seq, ",cache_strategy=readaround");
	} else {
		seq_puts(seq, ",cache_strategy=(unknown)");
		DBG_BUGON(1);
	}
#endif
	return 0;
}

static int erofs_remount(struct super_block *sb, int *flags, char *data)
{
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	unsigned int org_mnt_opt = sbi->mount_opt;
	unsigned int org_inject_rate = erofs_get_fault_rate(sbi);
	int err;

	DBG_BUGON(!sb_rdonly(sb));
	err = parse_options(sb, data);
	if (err)
		goto out;

	if (test_opt(sbi, POSIX_ACL))
		sb->s_flags |= SB_POSIXACL;
	else
		sb->s_flags &= ~SB_POSIXACL;

	*flags |= SB_RDONLY;
	return 0;
out:
	__erofs_build_fault_attr(sbi, org_inject_rate);
	sbi->mount_opt = org_mnt_opt;

	return err;
}

const struct super_operations erofs_sops = {
	.put_super = erofs_put_super,
	.alloc_inode = alloc_inode,
	.free_inode = free_inode,
	.statfs = erofs_statfs,
	.show_options = erofs_show_options,
	.remount_fs = erofs_remount,
};

module_init(erofs_module_init);
module_exit(erofs_module_exit);

MODULE_DESCRIPTION("Enhanced ROM File System");
MODULE_AUTHOR("Gao Xiang, Chao Yu, Miao Xie, CONSUMER BG, HUAWEI Inc.");
MODULE_LICENSE("GPL");