summaryrefslogtreecommitdiff
path: root/fs/erofs/internal.h
blob: a6a53d22dfd6d94168d306188c889ede5c5a6299 (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#ifndef __EROFS_INTERNAL_H
#define __EROFS_INTERNAL_H

#include <linux/fs.h>
#include <linux/dcache.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/iomap.h>
#include "erofs_fs.h"

/* redefine pr_fmt "erofs: " */
#undef pr_fmt
#define pr_fmt(fmt) "erofs: " fmt

__printf(3, 4) void _erofs_err(struct super_block *sb,
			       const char *function, const char *fmt, ...);
#define erofs_err(sb, fmt, ...)	\
	_erofs_err(sb, __func__, fmt "\n", ##__VA_ARGS__)
__printf(3, 4) void _erofs_info(struct super_block *sb,
			       const char *function, const char *fmt, ...);
#define erofs_info(sb, fmt, ...) \
	_erofs_info(sb, __func__, fmt "\n", ##__VA_ARGS__)
#ifdef CONFIG_EROFS_FS_DEBUG
#define erofs_dbg(x, ...)       pr_debug(x "\n", ##__VA_ARGS__)
#define DBG_BUGON               BUG_ON
#else
#define erofs_dbg(x, ...)       ((void)0)
#define DBG_BUGON(x)            ((void)(x))
#endif	/* !CONFIG_EROFS_FS_DEBUG */

/* EROFS_SUPER_MAGIC_V1 to represent the whole file system */
#define EROFS_SUPER_MAGIC   EROFS_SUPER_MAGIC_V1

typedef u64 erofs_nid_t;
typedef u64 erofs_off_t;
/* data type for filesystem-wide blocks number */
typedef u32 erofs_blk_t;

struct erofs_device_info {
	char *path;
	struct block_device *bdev;
	struct dax_device *dax_dev;

	u32 blocks;
	u32 mapped_blkaddr;
};

struct erofs_mount_opts {
#ifdef CONFIG_EROFS_FS_ZIP
	/* current strategy of how to use managed cache */
	unsigned char cache_strategy;
	/* strategy of sync decompression (false - auto, true - force on) */
	bool readahead_sync_decompress;

	/* threshold for decompression synchronously */
	unsigned int max_sync_decompress_pages;
#endif
	unsigned int mount_opt;
};

struct erofs_dev_context {
	struct idr tree;
	struct rw_semaphore rwsem;

	unsigned int extra_devices;
};

struct erofs_fs_context {
	struct erofs_mount_opts opt;
	struct erofs_dev_context *devs;
};

/* all filesystem-wide lz4 configurations */
struct erofs_sb_lz4_info {
	/* # of pages needed for EROFS lz4 rolling decompression */
	u16 max_distance_pages;
	/* maximum possible blocks for pclusters in the filesystem */
	u16 max_pclusterblks;
};

struct erofs_sb_info {
	struct erofs_mount_opts opt;	/* options */
#ifdef CONFIG_EROFS_FS_ZIP
	/* list for all registered superblocks, mainly for shrinker */
	struct list_head list;
	struct mutex umount_mutex;

	/* managed XArray arranged in physical block number */
	struct xarray managed_pslots;

	unsigned int shrinker_run_no;
	u16 available_compr_algs;

	/* pseudo inode to manage cached pages */
	struct inode *managed_cache;

	struct erofs_sb_lz4_info lz4;
#endif	/* CONFIG_EROFS_FS_ZIP */
	struct erofs_dev_context *devs;
	struct dax_device *dax_dev;
	u64 total_blocks;
	u32 primarydevice_blocks;

	u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
	u32 xattr_blkaddr;
#endif
	u16 device_id_mask;	/* valid bits of device id to be used */

	/* inode slot unit size in bit shift */
	unsigned char islotbits;

	u32 sb_size;			/* total superblock size */
	u32 build_time_nsec;
	u64 build_time;

	/* what we really care is nid, rather than ino.. */
	erofs_nid_t root_nid;
	/* used for statfs, f_files - f_favail */
	u64 inos;

	u8 uuid[16];                    /* 128-bit uuid for volume */
	u8 volume_name[16];             /* volume name */
	u32 feature_compat;
	u32 feature_incompat;
};

#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
#define EROFS_I_SB(inode) ((struct erofs_sb_info *)(inode)->i_sb->s_fs_info)

/* Mount flags set via mount options or defaults */
#define EROFS_MOUNT_XATTR_USER		0x00000010
#define EROFS_MOUNT_POSIX_ACL		0x00000020
#define EROFS_MOUNT_DAX_ALWAYS		0x00000040
#define EROFS_MOUNT_DAX_NEVER		0x00000080

#define clear_opt(opt, option)	((opt)->mount_opt &= ~EROFS_MOUNT_##option)
#define set_opt(opt, option)	((opt)->mount_opt |= EROFS_MOUNT_##option)
#define test_opt(opt, option)	((opt)->mount_opt & EROFS_MOUNT_##option)

enum {
	EROFS_ZIP_CACHE_DISABLED,
	EROFS_ZIP_CACHE_READAHEAD,
	EROFS_ZIP_CACHE_READAROUND
};

#ifdef CONFIG_EROFS_FS_ZIP
#define EROFS_LOCKED_MAGIC     (INT_MIN | 0xE0F510CCL)

/* basic unit of the workstation of a super_block */
struct erofs_workgroup {
	/* the workgroup index in the workstation */
	pgoff_t index;

	/* overall workgroup reference count */
	atomic_t refcount;
};

#if defined(CONFIG_SMP)
static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
						 int val)
{
	preempt_disable();
	if (val != atomic_cmpxchg(&grp->refcount, val, EROFS_LOCKED_MAGIC)) {
		preempt_enable();
		return false;
	}
	return true;
}

static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
					    int orig_val)
{
	/*
	 * other observers should notice all modifications
	 * in the freezing period.
	 */
	smp_mb();
	atomic_set(&grp->refcount, orig_val);
	preempt_enable();
}

static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
{
	return atomic_cond_read_relaxed(&grp->refcount,
					VAL != EROFS_LOCKED_MAGIC);
}
#else
static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
						 int val)
{
	preempt_disable();
	/* no need to spin on UP platforms, let's just disable preemption. */
	if (val != atomic_read(&grp->refcount)) {
		preempt_enable();
		return false;
	}
	return true;
}

static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
					    int orig_val)
{
	preempt_enable();
}

static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
{
	int v = atomic_read(&grp->refcount);

	/* workgroup is never freezed on uniprocessor systems */
	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
	return v;
}
#endif	/* !CONFIG_SMP */
#endif	/* !CONFIG_EROFS_FS_ZIP */

/* we strictly follow PAGE_SIZE and no buffer head yet */
#define LOG_BLOCK_SIZE		PAGE_SHIFT

#undef LOG_SECTORS_PER_BLOCK
#define LOG_SECTORS_PER_BLOCK	(PAGE_SHIFT - 9)

#undef SECTORS_PER_BLOCK
#define SECTORS_PER_BLOCK	(1 << SECTORS_PER_BLOCK)

#define EROFS_BLKSIZ		(1 << LOG_BLOCK_SIZE)

#if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ)
#error erofs cannot be used in this platform
#endif

#define ROOT_NID(sb)		((sb)->root_nid)

#define erofs_blknr(addr)       ((addr) / EROFS_BLKSIZ)
#define erofs_blkoff(addr)      ((addr) % EROFS_BLKSIZ)
#define blknr_to_addr(nr)       ((erofs_off_t)(nr) * EROFS_BLKSIZ)

static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
{
	return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
}

#define EROFS_FEATURE_FUNCS(name, compat, feature) \
static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
{ \
	return sbi->feature_##compat & EROFS_FEATURE_##feature; \
}

EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE)
EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)

/* atomic flag definitions */
#define EROFS_I_EA_INITED_BIT	0
#define EROFS_I_Z_INITED_BIT	1

/* bitlock definitions (arranged in reverse order) */
#define EROFS_I_BL_XATTR_BIT	(BITS_PER_LONG - 1)
#define EROFS_I_BL_Z_BIT	(BITS_PER_LONG - 2)

struct erofs_inode {
	erofs_nid_t nid;

	/* atomic flags (including bitlocks) */
	unsigned long flags;

	unsigned char datalayout;
	unsigned char inode_isize;
	unsigned short xattr_isize;

	unsigned int xattr_shared_count;
	unsigned int *xattr_shared_xattrs;

	union {
		erofs_blk_t raw_blkaddr;
		struct {
			unsigned short	chunkformat;
			unsigned char	chunkbits;
		};
#ifdef CONFIG_EROFS_FS_ZIP
		struct {
			unsigned short z_advise;
			unsigned char  z_algorithmtype[2];
			unsigned char  z_logical_clusterbits;
		};
#endif	/* CONFIG_EROFS_FS_ZIP */
	};
	/* the corresponding vfs inode */
	struct inode vfs_inode;
};

#define EROFS_I(ptr)	\
	container_of(ptr, struct erofs_inode, vfs_inode)

static inline unsigned long erofs_inode_datablocks(struct inode *inode)
{
	/* since i_size cannot be changed */
	return DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
}

static inline unsigned int erofs_bitrange(unsigned int value, unsigned int bit,
					  unsigned int bits)
{

	return (value >> bit) & ((1 << bits) - 1);
}


static inline unsigned int erofs_inode_version(unsigned int value)
{
	return erofs_bitrange(value, EROFS_I_VERSION_BIT,
			      EROFS_I_VERSION_BITS);
}

static inline unsigned int erofs_inode_datalayout(unsigned int value)
{
	return erofs_bitrange(value, EROFS_I_DATALAYOUT_BIT,
			      EROFS_I_DATALAYOUT_BITS);
}

/*
 * Different from grab_cache_page_nowait(), reclaiming is never triggered
 * when allocating new pages.
 */
static inline
struct page *erofs_grab_cache_page_nowait(struct address_space *mapping,
					  pgoff_t index)
{
	return pagecache_get_page(mapping, index,
			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
			readahead_gfp_mask(mapping) & ~__GFP_RECLAIM);
}

extern const struct super_operations erofs_sops;

extern const struct address_space_operations erofs_raw_access_aops;
extern const struct address_space_operations z_erofs_aops;

/*
 * Logical to physical block mapping
 *
 * Different with other file systems, it is used for 2 access modes:
 *
 * 1) RAW access mode:
 *
 * Users pass a valid (m_lblk, m_lofs -- usually 0) pair,
 * and get the valid m_pblk, m_pofs and the longest m_len(in bytes).
 *
 * Note that m_lblk in the RAW access mode refers to the number of
 * the compressed ondisk block rather than the uncompressed
 * in-memory block for the compressed file.
 *
 * m_pofs equals to m_lofs except for the inline data page.
 *
 * 2) Normal access mode:
 *
 * If the inode is not compressed, it has no difference with
 * the RAW access mode. However, if the inode is compressed,
 * users should pass a valid (m_lblk, m_lofs) pair, and get
 * the needed m_pblk, m_pofs, m_len to get the compressed data
 * and the updated m_lblk, m_lofs which indicates the start
 * of the corresponding uncompressed data in the file.
 */
enum {
	BH_Encoded = BH_PrivateStart,
	BH_FullMapped,
};

/* Has a disk mapping */
#define EROFS_MAP_MAPPED	(1 << BH_Mapped)
/* Located in metadata (could be copied from bd_inode) */
#define EROFS_MAP_META		(1 << BH_Meta)
/* The extent is encoded */
#define EROFS_MAP_ENCODED	(1 << BH_Encoded)
/* The length of extent is full */
#define EROFS_MAP_FULL_MAPPED	(1 << BH_FullMapped)

struct erofs_map_blocks {
	erofs_off_t m_pa, m_la;
	u64 m_plen, m_llen;

	unsigned short m_deviceid;
	char m_algorithmformat;
	unsigned int m_flags;

	struct page *mpage;
};

/* Flags used by erofs_map_blocks_flatmode() */
#define EROFS_GET_BLOCKS_RAW    0x0001
/*
 * Used to get the exact decompressed length, e.g. fiemap (consider lookback
 * approach instead if possible since it's more metadata lightweight.)
 */
#define EROFS_GET_BLOCKS_FIEMAP	0x0002
/* Used to map the whole extent if non-negligible data is requested for LZMA */
#define EROFS_GET_BLOCKS_READMORE	0x0004

enum {
	Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
	Z_EROFS_COMPRESSION_RUNTIME_MAX
};

/* zmap.c */
extern const struct iomap_ops z_erofs_iomap_report_ops;

#ifdef CONFIG_EROFS_FS_ZIP
int z_erofs_fill_inode(struct inode *inode);
int z_erofs_map_blocks_iter(struct inode *inode,
			    struct erofs_map_blocks *map,
			    int flags);
#else
static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; }
static inline int z_erofs_map_blocks_iter(struct inode *inode,
					  struct erofs_map_blocks *map,
					  int flags)
{
	return -EOPNOTSUPP;
}
#endif	/* !CONFIG_EROFS_FS_ZIP */

struct erofs_map_dev {
	struct block_device *m_bdev;
	struct dax_device *m_daxdev;

	erofs_off_t m_pa;
	unsigned int m_deviceid;
};

/* data.c */
extern const struct file_operations erofs_file_fops;
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr);
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		 u64 start, u64 len);

/* inode.c */
static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
{
#if BITS_PER_LONG == 32
	return (nid >> 32) ^ (nid & 0xffffffff);
#else
	return nid;
#endif
}

extern const struct inode_operations erofs_generic_iops;
extern const struct inode_operations erofs_symlink_iops;
extern const struct inode_operations erofs_fast_symlink_iops;

struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir);
int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
		  struct kstat *stat, u32 request_mask,
		  unsigned int query_flags);

/* namei.c */
extern const struct inode_operations erofs_dir_iops;

int erofs_namei(struct inode *dir, struct qstr *name,
		erofs_nid_t *nid, unsigned int *d_type);

/* dir.c */
extern const struct file_operations erofs_dir_fops;

static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
{
	int retried = 0;

	while (1) {
		void *p = vm_map_ram(pages, count, -1);

		/* retry two more times (totally 3 times) */
		if (p || ++retried >= 3)
			return p;
		vm_unmap_aliases();
	}
	return NULL;
}

/* pcpubuf.c */
void *erofs_get_pcpubuf(unsigned int requiredpages);
void erofs_put_pcpubuf(void *ptr);
int erofs_pcpubuf_growsize(unsigned int nrpages);
void erofs_pcpubuf_init(void);
void erofs_pcpubuf_exit(void);

/* utils.c / zdata.c */
struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);

#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
					     pgoff_t index);
struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
					       struct erofs_workgroup *grp);
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
void erofs_shrinker_register(struct super_block *sb);
void erofs_shrinker_unregister(struct super_block *sb);
int __init erofs_init_shrinker(void);
void erofs_exit_shrinker(void);
int __init z_erofs_init_zip_subsystem(void);
void z_erofs_exit_zip_subsystem(void);
int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
				       struct erofs_workgroup *egrp);
int erofs_try_to_free_cached_page(struct page *page);
int z_erofs_load_lz4_config(struct super_block *sb,
			    struct erofs_super_block *dsb,
			    struct z_erofs_lz4_cfgs *lz4, int len);
#else
static inline void erofs_shrinker_register(struct super_block *sb) {}
static inline void erofs_shrinker_unregister(struct super_block *sb) {}
static inline int erofs_init_shrinker(void) { return 0; }
static inline void erofs_exit_shrinker(void) {}
static inline int z_erofs_init_zip_subsystem(void) { return 0; }
static inline void z_erofs_exit_zip_subsystem(void) {}
static inline int z_erofs_load_lz4_config(struct super_block *sb,
				  struct erofs_super_block *dsb,
				  struct z_erofs_lz4_cfgs *lz4, int len)
{
	if (lz4 || dsb->u1.lz4_max_distance) {
		erofs_err(sb, "lz4 algorithm isn't enabled");
		return -EINVAL;
	}
	return 0;
}
#endif	/* !CONFIG_EROFS_FS_ZIP */

#ifdef CONFIG_EROFS_FS_ZIP_LZMA
int z_erofs_lzma_init(void);
void z_erofs_lzma_exit(void);
int z_erofs_load_lzma_config(struct super_block *sb,
			     struct erofs_super_block *dsb,
			     struct z_erofs_lzma_cfgs *lzma, int size);
#else
static inline int z_erofs_lzma_init(void) { return 0; }
static inline int z_erofs_lzma_exit(void) { return 0; }
static inline int z_erofs_load_lzma_config(struct super_block *sb,
			     struct erofs_super_block *dsb,
			     struct z_erofs_lzma_cfgs *lzma, int size) {
	if (lzma) {
		erofs_err(sb, "lzma algorithm isn't enabled");
		return -EINVAL;
	}
	return 0;
}
#endif	/* !CONFIG_EROFS_FS_ZIP */

#define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */

#endif	/* __EROFS_INTERNAL_H */