summaryrefslogtreecommitdiffstats
path: root/fs/erofs/super.c
blob: 915eefe0d7e2c51f65851933ff0b2067da70e88c (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
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include <linux/crc32c.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/dax.h>
#include "xattr.h"

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

static struct kmem_cache *erofs_inode_cachep __read_mostly;

void _erofs_err(struct super_block *sb, const char *function,
		const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);

	vaf.fmt = fmt;
	vaf.va = &args;

	pr_err("(device %s): %s: %pV", sb->s_id, function, &vaf);
	va_end(args);
}

void _erofs_info(struct super_block *sb, const char *function,
		 const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);

	vaf.fmt = fmt;
	vaf.va = &args;

	pr_info("(device %s): %pV", sb->s_id, &vaf);
	va_end(args);
}

static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
{
	struct erofs_super_block *dsb;
	u32 expected_crc, crc;

	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET,
		      EROFS_BLKSIZ - EROFS_SUPER_OFFSET, GFP_KERNEL);
	if (!dsb)
		return -ENOMEM;

	expected_crc = le32_to_cpu(dsb->checksum);
	dsb->checksum = 0;
	/* to allow for x86 boot sectors and other oddities. */
	crc = crc32c(~0, dsb, EROFS_BLKSIZ - EROFS_SUPER_OFFSET);
	kfree(dsb);

	if (crc != expected_crc) {
		erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
			  crc, expected_crc);
		return -EBADMSG;
	}
	return 0;
}

static void erofs_inode_init_once(void *ptr)
{
	struct erofs_inode *vi = ptr;

	inode_init_once(&vi->vfs_inode);
}

static struct inode *erofs_alloc_inode(struct super_block *sb)
{
	struct erofs_inode *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_inode, vfs_inode));
	return &vi->vfs_inode;
}

static void erofs_free_inode(struct inode *inode)
{
	struct erofs_inode *vi = EROFS_I(inode);

	/* be careful of RCU symlink path */
	if (inode->i_op == &erofs_fast_symlink_iops)
		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 *dsb)
{
	const unsigned int feature = le32_to_cpu(dsb->feature_incompat);

	EROFS_SB(sb)->feature_incompat = feature;

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

#ifdef CONFIG_EROFS_FS_ZIP
/* read variable-sized metadata, offset will be aligned by 4-byte */
static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
				 erofs_off_t *offset, int *lengthp)
{
	u8 *buffer, *ptr;
	int len, i, cnt;

	*offset = round_up(*offset, 4);
	ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), EROFS_KMAP);
	if (IS_ERR(ptr))
		return ptr;

	len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]);
	if (!len)
		len = U16_MAX + 1;
	buffer = kmalloc(len, GFP_KERNEL);
	if (!buffer)
		return ERR_PTR(-ENOMEM);
	*offset += sizeof(__le16);
	*lengthp = len;

	for (i = 0; i < len; i += cnt) {
		cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i);
		ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset),
					 EROFS_KMAP);
		if (IS_ERR(ptr)) {
			kfree(buffer);
			return ptr;
		}
		memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt);
		*offset += cnt;
	}
	return buffer;
}

static int erofs_load_compr_cfgs(struct super_block *sb,
				 struct erofs_super_block *dsb)
{
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
	unsigned int algs, alg;
	erofs_off_t offset;
	int size, ret = 0;

	sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs);
	if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) {
		erofs_err(sb, "try to load compressed fs with unsupported algorithms %x",
			  sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS);
		return -EINVAL;
	}

	offset = EROFS_SUPER_OFFSET + sbi->sb_size;
	alg = 0;
	for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) {
		void *data;

		if (!(algs & 1))
			continue;

		data = erofs_read_metadata(sb, &buf, &offset, &size);
		if (IS_ERR(data)) {
			ret = PTR_ERR(data);
			break;
		}

		switch (alg) {
		case Z_EROFS_COMPRESSION_LZ4:
			ret = z_erofs_load_lz4_config(sb, dsb, data, size);
			break;
		case Z_EROFS_COMPRESSION_LZMA:
			ret = z_erofs_load_lzma_config(sb, dsb, data, size);
			break;
		default:
			DBG_BUGON(1);
			ret = -EFAULT;
		}
		kfree(data);
		if (ret)
			break;
	}
	erofs_put_metabuf(&buf);
	return ret;
}
#else
static int erofs_load_compr_cfgs(struct super_block *sb,
				 struct erofs_super_block *dsb)
{
	if (dsb->u1.available_compr_algs) {
		erofs_err(sb, "try to load compressed fs when compression is disabled");
		return -EINVAL;
	}
	return 0;
}
#endif

static int erofs_init_devices(struct super_block *sb,
			      struct erofs_super_block *dsb)
{
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	unsigned int ondisk_extradevs;
	erofs_off_t pos;
	struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
	struct erofs_device_info *dif;
	struct erofs_deviceslot *dis;
	void *ptr;
	int id, err = 0;

	sbi->total_blocks = sbi->primarydevice_blocks;
	if (!erofs_sb_has_device_table(sbi))
		ondisk_extradevs = 0;
	else
		ondisk_extradevs = le16_to_cpu(dsb->extra_devices);

	if (ondisk_extradevs != sbi->devs->extra_devices) {
		erofs_err(sb, "extra devices don't match (ondisk %u, given %u)",
			  ondisk_extradevs, sbi->devs->extra_devices);
		return -EINVAL;
	}
	if (!ondisk_extradevs)
		return 0;

	sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1;
	pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE;
	down_read(&sbi->devs->rwsem);
	idr_for_each_entry(&sbi->devs->tree, dif, id) {
		struct block_device *bdev;

		ptr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos),
					 EROFS_KMAP);
		if (IS_ERR(ptr)) {
			err = PTR_ERR(ptr);
			break;
		}
		dis = ptr + erofs_blkoff(pos);

		bdev = blkdev_get_by_path(dif->path,
					  FMODE_READ | FMODE_EXCL,
					  sb->s_type);
		if (IS_ERR(bdev)) {
			err = PTR_ERR(bdev);
			break;
		}
		dif->bdev = bdev;
		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
		dif->blocks = le32_to_cpu(dis->blocks);
		dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
		sbi->total_blocks += dif->blocks;
		pos += EROFS_DEVT_SLOT_SIZE;
	}
	up_read(&sbi->devs->rwsem);
	erofs_put_metabuf(&buf);
	return err;
}

static int erofs_read_superblock(struct super_block *sb)
{
	struct erofs_sb_info *sbi;
	struct page *page;
	struct erofs_super_block *dsb;
	unsigned int blkszbits;
	void *data;
	int ret;

	page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
	if (IS_ERR(page)) {
		erofs_err(sb, "cannot read erofs superblock");
		return PTR_ERR(page);
	}

	sbi = EROFS_SB(sb);

	data = kmap(page);
	dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET);

	ret = -EINVAL;
	if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) {
		erofs_err(sb, "cannot find valid erofs superblock");
		goto out;
	}

	sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
	if (erofs_sb_has_sb_chksum(sbi)) {
		ret = erofs_superblock_csum_verify(sb, data);
		if (ret)
			goto out;
	}

	ret = -EINVAL;
	blkszbits = dsb->blkszbits;
	/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
	if (blkszbits != LOG_BLOCK_SIZE) {
		erofs_err(sb, "blkszbits %u isn't supported on this platform",
			  blkszbits);
		goto out;
	}

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

	sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
	if (sbi->sb_size > EROFS_BLKSIZ) {
		erofs_err(sb, "invalid sb_extslots %u (more than a fs block)",
			  sbi->sb_size);
		goto out;
	}
	sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks);
	sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
	sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
#endif
	sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
	sbi->root_nid = le16_to_cpu(dsb->root_nid);
	sbi->inos = le64_to_cpu(dsb->inos);

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

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

	ret = strscpy(sbi->volume_name, dsb->volume_name,
		      sizeof(dsb->volume_name));
	if (ret < 0) {	/* -E2BIG */
		erofs_err(sb, "bad volume name without NIL terminator");
		ret = -EFSCORRUPTED;
		goto out;
	}

	/* parse on-disk compression configurations */
	if (erofs_sb_has_compr_cfgs(sbi))
		ret = erofs_load_compr_cfgs(sb, dsb);
	else
		ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0);
	if (ret < 0)
		goto out;

	/* handle multiple devices */
	ret = erofs_init_devices(sb, dsb);

	if (erofs_sb_has_ztailpacking(sbi))
		erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!");
out:
	kunmap(page);
	put_page(page);
	return ret;
}

/* set up default EROFS parameters */
static void erofs_default_options(struct erofs_fs_context *ctx)
{
#ifdef CONFIG_EROFS_FS_ZIP
	ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
	ctx->opt.max_sync_decompress_pages = 3;
	ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
	set_opt(&ctx->opt, XATTR_USER);
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
	set_opt(&ctx->opt, POSIX_ACL);
#endif
}

enum {
	Opt_user_xattr,
	Opt_acl,
	Opt_cache_strategy,
	Opt_dax,
	Opt_dax_enum,
	Opt_device,
	Opt_err
};

static const struct constant_table erofs_param_cache_strategy[] = {
	{"disabled",	EROFS_ZIP_CACHE_DISABLED},
	{"readahead",	EROFS_ZIP_CACHE_READAHEAD},
	{"readaround",	EROFS_ZIP_CACHE_READAROUND},
	{}
};

static const struct constant_table erofs_dax_param_enums[] = {
	{"always",	EROFS_MOUNT_DAX_ALWAYS},
	{"never",	EROFS_MOUNT_DAX_NEVER},
	{}
};

static const struct fs_parameter_spec erofs_fs_parameters[] = {
	fsparam_flag_no("user_xattr",	Opt_user_xattr),
	fsparam_flag_no("acl",		Opt_acl),
	fsparam_enum("cache_strategy",	Opt_cache_strategy,
		     erofs_param_cache_strategy),
	fsparam_flag("dax",             Opt_dax),
	fsparam_enum("dax",		Opt_dax_enum, erofs_dax_param_enums),
	fsparam_string("device",	Opt_device),
	{}
};

static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
{
#ifdef CONFIG_FS_DAX
	struct erofs_fs_context *ctx = fc->fs_private;

	switch (mode) {
	case EROFS_MOUNT_DAX_ALWAYS:
		warnfc(fc, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
		set_opt(&ctx->opt, DAX_ALWAYS);
		clear_opt(&ctx->opt, DAX_NEVER);
		return true;
	case EROFS_MOUNT_DAX_NEVER:
		set_opt(&ctx->opt, DAX_NEVER);
		clear_opt(&ctx->opt, DAX_ALWAYS);
		return true;
	default:
		DBG_BUGON(1);
		return false;
	}
#else
	errorfc(fc, "dax options not supported");
	return false;
#endif
}

static int erofs_fc_parse_param(struct fs_context *fc,
				struct fs_parameter *param)
{
	struct erofs_fs_context *ctx = fc->fs_private;
	struct fs_parse_result result;
	struct erofs_device_info *dif;
	int opt, ret;

	opt = fs_parse(fc, erofs_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_user_xattr:
#ifdef CONFIG_EROFS_FS_XATTR
		if (result.boolean)
			set_opt(&ctx->opt, XATTR_USER);
		else
			clear_opt(&ctx->opt, XATTR_USER);
#else
		errorfc(fc, "{,no}user_xattr options not supported");
#endif
		break;
	case Opt_acl:
#ifdef CONFIG_EROFS_FS_POSIX_ACL
		if (result.boolean)
			set_opt(&ctx->opt, POSIX_ACL);
		else
			clear_opt(&ctx->opt, POSIX_ACL);
#else
		errorfc(fc, "{,no}acl options not supported");
#endif
		break;
	case Opt_cache_strategy:
#ifdef CONFIG_EROFS_FS_ZIP
		ctx->opt.cache_strategy = result.uint_32;
#else
		errorfc(fc, "compression not supported, cache_strategy ignored");
#endif
		break;
	case Opt_dax:
		if (!erofs_fc_set_dax_mode(fc, EROFS_MOUNT_DAX_ALWAYS))
			return -EINVAL;
		break;
	case Opt_dax_enum:
		if (!erofs_fc_set_dax_mode(fc, result.uint_32))
			return -EINVAL;
		break;
	case Opt_device:
		dif = kzalloc(sizeof(*dif), GFP_KERNEL);
		if (!dif)
			return -ENOMEM;
		dif->path = kstrdup(param->string, GFP_KERNEL);
		if (!dif->path) {
			kfree(dif);
			return -ENOMEM;
		}
		down_write(&ctx->devs->rwsem);
		ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL);
		up_write(&ctx->devs->rwsem);
		if (ret < 0) {
			kfree(dif->path);
			kfree(dif);
			return ret;
		}
		++ctx->devs->extra_devices;
		break;
	default:
		return -ENOPARAM;
	}
	return 0;
}

#ifdef CONFIG_EROFS_FS_ZIP
static const struct address_space_operations managed_cache_aops;

static int erofs_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(page);

	return ret;
}

static void erofs_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 (!erofs_managed_cache_releasepage(page, GFP_NOFS))
			cond_resched();
}

static const struct address_space_operations managed_cache_aops = {
	.releasepage = erofs_managed_cache_releasepage,
	.invalidatepage = erofs_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_fc_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct inode *inode;
	struct erofs_sb_info *sbi;
	struct erofs_fs_context *ctx = fc->fs_private;
	int err;

	sb->s_magic = EROFS_SUPER_MAGIC;

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

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

	sb->s_fs_info = sbi;
	sbi->opt = ctx->opt;
	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off);
	sbi->devs = ctx->devs;
	ctx->devs = NULL;

	err = erofs_read_superblock(sb);
	if (err)
		return err;

	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
		BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE);

		if (!sbi->dax_dev) {
			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
			clear_opt(&sbi->opt, DAX_ALWAYS);
		}
	}
	sb->s_flags |= SB_RDONLY | SB_NOATIME;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_time_gran = 1;

	sb->s_op = &erofs_sops;
	sb->s_xattr = erofs_xattr_handlers;

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

#ifdef CONFIG_EROFS_FS_ZIP
	xa_init(&sbi->managed_pslots);
#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)) {
		erofs_err(sb, "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;

	err = erofs_register_sysfs(sb);
	if (err)
		return err;

	erofs_info(sb, "mounted with root inode @ nid %llu.", ROOT_NID(sbi));
	return 0;
}

static int erofs_fc_get_tree(struct fs_context *fc)
{
	return get_tree_bdev(fc, erofs_fc_fill_super);
}

static int erofs_fc_reconfigure(struct fs_context *fc)
{
	struct super_block *sb = fc->root->d_sb;
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	struct erofs_fs_context *ctx = fc->fs_private;

	DBG_BUGON(!sb_rdonly(sb));

	if (test_opt(&ctx->opt, POSIX_ACL))
		fc->sb_flags |= SB_POSIXACL;
	else
		fc->sb_flags &= ~SB_POSIXACL;

	sbi->opt = ctx->opt;

	fc->sb_flags |= SB_RDONLY;
	return 0;
}

static int erofs_release_device_info(int id, void *ptr, void *data)
{
	struct erofs_device_info *dif = ptr;

	fs_put_dax(dif->dax_dev);
	if (dif->bdev)
		blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
	kfree(dif->path);
	kfree(dif);
	return 0;
}

static void erofs_free_dev_context(struct erofs_dev_context *devs)
{
	if (!devs)
		return;
	idr_for_each(&devs->tree, &erofs_release_device_info, NULL);
	idr_destroy(&devs->tree);
	kfree(devs);
}

static void erofs_fc_free(struct fs_context *fc)
{
	struct erofs_fs_context *ctx = fc->fs_private;

	erofs_free_dev_context(ctx->devs);
	kfree(ctx);
}

static const struct fs_context_operations erofs_context_ops = {
	.parse_param	= erofs_fc_parse_param,
	.get_tree       = erofs_fc_get_tree,
	.reconfigure    = erofs_fc_reconfigure,
	.free		= erofs_fc_free,
};

static int erofs_init_fs_context(struct fs_context *fc)
{
	struct erofs_fs_context *ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);

	if (!ctx)
		return -ENOMEM;
	ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
	if (!ctx->devs) {
		kfree(ctx);
		return -ENOMEM;
	}
	fc->fs_private = ctx;

	idr_init(&ctx->devs->tree);
	init_rwsem(&ctx->devs->rwsem);
	erofs_default_options(ctx);
	fc->ops = &erofs_context_ops;
	return 0;
}

/*
 * 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);

	kill_block_super(sb);

	sbi = EROFS_SB(sb);
	if (!sbi)
		return;

	erofs_free_dev_context(sbi->devs);
	fs_put_dax(sbi->dax_dev);
	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_unregister_sysfs(sb);
	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",
	.init_fs_context = erofs_init_fs_context,
	.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();

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

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

	err = z_erofs_lzma_init();
	if (err)
		goto lzma_err;

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

	err = erofs_init_sysfs();
	if (err)
		goto sysfs_err;

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

	return 0;

fs_err:
	erofs_exit_sysfs();
sysfs_err:
	z_erofs_exit_zip_subsystem();
zip_err:
	z_erofs_lzma_exit();
lzma_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);

	/* Ensure all RCU free inodes / pclusters are safe to be destroyed. */
	rcu_barrier();

	erofs_exit_sysfs();
	z_erofs_exit_zip_subsystem();
	z_erofs_lzma_exit();
	erofs_exit_shrinker();
	kmem_cache_destroy(erofs_inode_cachep);
	erofs_pcpubuf_exit();
}

/* 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->total_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    = u64_to_fsid(id);
	return 0;
}

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

#ifdef CONFIG_EROFS_FS_XATTR
	if (test_opt(opt, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	else
		seq_puts(seq, ",nouser_xattr");
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
	if (test_opt(opt, POSIX_ACL))
		seq_puts(seq, ",acl");
	else
		seq_puts(seq, ",noacl");
#endif
#ifdef CONFIG_EROFS_FS_ZIP
	if (opt->cache_strategy == EROFS_ZIP_CACHE_DISABLED)
		seq_puts(seq, ",cache_strategy=disabled");
	else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAHEAD)
		seq_puts(seq, ",cache_strategy=readahead");
	else if (opt->cache_strategy == EROFS_ZIP_CACHE_READAROUND)
		seq_puts(seq, ",cache_strategy=readaround");
#endif
	if (test_opt(opt, DAX_ALWAYS))
		seq_puts(seq, ",dax=always");
	if (test_opt(opt, DAX_NEVER))
		seq_puts(seq, ",dax=never");
	return 0;
}

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

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");