f2fs.h 132.1 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
J
Jaegeuk Kim 已提交
2
/*
3 4 5 6 7 8 9 10
 * fs/f2fs/f2fs.h
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 */
#ifndef _LINUX_F2FS_H
#define _LINUX_F2FS_H

11
#include <linux/uio.h>
12 13 14 15 16 17
#include <linux/types.h>
#include <linux/page-flags.h>
#include <linux/buffer_head.h>
#include <linux/slab.h>
#include <linux/crc32.h>
#include <linux/magic.h>
18
#include <linux/kobject.h>
19
#include <linux/sched.h>
20
#include <linux/cred.h>
21
#include <linux/vmalloc.h>
J
Jaegeuk Kim 已提交
22
#include <linux/bio.h>
23
#include <linux/blkdev.h>
C
Chao Yu 已提交
24
#include <linux/quotaops.h>
25
#include <linux/part_stat.h>
K
Keith Mok 已提交
26
#include <crypto/hash.h>
27

D
Dave Chinner 已提交
28
#include <linux/fscrypt.h>
E
Eric Biggers 已提交
29
#include <linux/fsverity.h>
D
Dave Chinner 已提交
30

31
#ifdef CONFIG_F2FS_CHECK_FS
32
#define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
33
#else
34 35 36 37
#define f2fs_bug_on(sbi, condition)					\
	do {								\
		if (unlikely(condition)) {				\
			WARN_ON(1);					\
38
			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
39 40
		}							\
	} while (0)
41 42
#endif

J
Jaegeuk Kim 已提交
43 44
enum {
	FAULT_KMALLOC,
C
Chao Yu 已提交
45
	FAULT_KVMALLOC,
46
	FAULT_PAGE_ALLOC,
C
Chao Yu 已提交
47
	FAULT_PAGE_GET,
48
	FAULT_ALLOC_BIO,
J
Jaegeuk Kim 已提交
49 50 51 52
	FAULT_ALLOC_NID,
	FAULT_ORPHAN,
	FAULT_BLOCK,
	FAULT_DIR_DEPTH,
53
	FAULT_EVICT_INODE,
54
	FAULT_TRUNCATE,
55
	FAULT_READ_IO,
56
	FAULT_CHECKPOINT,
57
	FAULT_DISCARD,
58
	FAULT_WRITE_IO,
J
Jaegeuk Kim 已提交
59 60 61
	FAULT_MAX,
};

62
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
63 64
#define F2FS_ALL_FAULT_TYPE		((1 << FAULT_MAX) - 1)

S
Sheng Yong 已提交
65 66 67 68 69 70
struct f2fs_fault_info {
	atomic_t inject_ops;
	unsigned int inject_rate;
	unsigned int inject_type;
};

71
extern const char *f2fs_fault_name[FAULT_MAX];
72
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
J
Jaegeuk Kim 已提交
73 74
#endif

75 76 77 78 79 80 81 82 83
/*
 * For mount options
 */
#define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000002
#define F2FS_MOUNT_DISCARD		0x00000004
#define F2FS_MOUNT_NOHEAP		0x00000008
#define F2FS_MOUNT_XATTR_USER		0x00000010
#define F2FS_MOUNT_POSIX_ACL		0x00000020
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
J
Jaegeuk Kim 已提交
84
#define F2FS_MOUNT_INLINE_XATTR		0x00000080
85
#define F2FS_MOUNT_INLINE_DATA		0x00000100
86 87 88
#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
#define F2FS_MOUNT_NOBARRIER		0x00000800
89
#define F2FS_MOUNT_FASTBOOT		0x00001000
90
#define F2FS_MOUNT_EXTENT_CACHE		0x00002000
91
#define F2FS_MOUNT_DATA_FLUSH		0x00008000
92
#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
C
Chao Yu 已提交
93 94
#define F2FS_MOUNT_USRQUOTA		0x00080000
#define F2FS_MOUNT_GRPQUOTA		0x00100000
C
Chao Yu 已提交
95
#define F2FS_MOUNT_PRJQUOTA		0x00200000
C
Chao Yu 已提交
96
#define F2FS_MOUNT_QUOTA		0x00400000
C
Chao Yu 已提交
97
#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
98
#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
D
Daniel Rosenberg 已提交
99
#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
100
#define F2FS_MOUNT_NORECOVERY		0x04000000
101

102 103 104 105
#define F2FS_OPTION(sbi)	((sbi)->mount_opt)
#define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option)	(F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option)
#define test_opt(sbi, option)	(F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option)
106 107 108 109 110

#define ver_after(a, b)	(typecheck(unsigned long long, a) &&		\
		typecheck(unsigned long long, b) &&			\
		((long long)((a) - (b)) > 0))

111 112 113 114
typedef u32 block_t;	/*
			 * should not change u32, since it is the on-disk block
			 * address format, __le32.
			 */
115 116
typedef u32 nid_t;

C
Chao Yu 已提交
117 118
#define COMPRESS_EXT_NUM		16

119
struct f2fs_mount_info {
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
	unsigned int opt;
	int write_io_size_bits;		/* Write IO size bits */
	block_t root_reserved_blocks;	/* root reserved blocks */
	kuid_t s_resuid;		/* reserved blocks for uid */
	kgid_t s_resgid;		/* reserved blocks for gid */
	int active_logs;		/* # of active logs */
	int inline_xattr_size;		/* inline xattr size */
#ifdef CONFIG_F2FS_FAULT_INJECTION
	struct f2fs_fault_info fault_info;	/* For fault injection */
#endif
#ifdef CONFIG_QUOTA
	/* Names of quota files with journalled quota */
	char *s_qf_names[MAXQUOTAS];
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	/* For which write hints are passed down to block layer */
	int whint_mode;
	int alloc_mode;			/* segment allocation policy */
	int fsync_mode;			/* fsync policy */
139
	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
C
Chao Yu 已提交
140
	int bggc_mode;			/* bggc mode: off, on or sync */
141
	struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
J
Jaegeuk Kim 已提交
142
	block_t unusable_cap_perc;	/* percentage for cap */
143 144 145
	block_t unusable_cap;		/* Amount of space allowed to be
					 * unusable when disabling checkpoint
					 */
C
Chao Yu 已提交
146 147 148 149 150 151

	/* For compression */
	unsigned char compress_algorithm;	/* algorithm type */
	unsigned compress_log_size;		/* cluster log size */
	unsigned char compress_ext_cnt;		/* extension count */
	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
152 153
};

154 155 156 157
#define F2FS_FEATURE_ENCRYPT		0x0001
#define F2FS_FEATURE_BLKZONED		0x0002
#define F2FS_FEATURE_ATOMIC_WRITE	0x0004
#define F2FS_FEATURE_EXTRA_ATTR		0x0008
C
Chao Yu 已提交
158
#define F2FS_FEATURE_PRJQUOTA		0x0010
C
Chao Yu 已提交
159
#define F2FS_FEATURE_INODE_CHKSUM	0x0020
C
Chao Yu 已提交
160
#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
J
Jaegeuk Kim 已提交
161
#define F2FS_FEATURE_QUOTA_INO		0x0080
C
Chao Yu 已提交
162
#define F2FS_FEATURE_INODE_CRTIME	0x0100
163
#define F2FS_FEATURE_LOST_FOUND		0x0200
E
Eric Biggers 已提交
164
#define F2FS_FEATURE_VERITY		0x0400
165
#define F2FS_FEATURE_SB_CHKSUM		0x0800
166
#define F2FS_FEATURE_CASEFOLD		0x1000
C
Chao Yu 已提交
167
#define F2FS_FEATURE_COMPRESSION	0x2000
168

169 170 171 172 173 174 175
#define __F2FS_HAS_FEATURE(raw_super, mask)				\
	((raw_super->feature & cpu_to_le32(mask)) != 0)
#define F2FS_HAS_FEATURE(sbi, mask)	__F2FS_HAS_FEATURE(sbi->raw_super, mask)
#define F2FS_SET_FEATURE(sbi, mask)					\
	(sbi->raw_super->feature |= cpu_to_le32(mask))
#define F2FS_CLEAR_FEATURE(sbi, mask)					\
	(sbi->raw_super->feature &= ~cpu_to_le32(mask))
176

177 178 179 180 181 182
/*
 * Default values for user and/or group using reserved blocks
 */
#define	F2FS_DEF_RESUID		0
#define	F2FS_DEF_RESGID		0

183 184 185 186 187 188 189 190
/*
 * For checkpoint manager
 */
enum {
	NAT_BITMAP,
	SIT_BITMAP
};

191 192 193 194 195
#define	CP_UMOUNT	0x00000001
#define	CP_FASTBOOT	0x00000002
#define	CP_SYNC		0x00000004
#define	CP_RECOVERY	0x00000008
#define	CP_DISCARD	0x00000010
196
#define CP_TRIMMED	0x00000020
D
Daniel Rosenberg 已提交
197
#define CP_PAUSE	0x00000040
198
#define CP_RESIZE 	0x00000080
199

200
#define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
C
Chao Yu 已提交
201
#define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
202
#define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
203
#define DEF_MID_DISCARD_ISSUE_TIME	500	/* 500 ms, if device busy */
204
#define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
205
#define DEF_DISCARD_URGENT_UTIL		80	/* do more discard over 80% */
206
#define DEF_CP_INTERVAL			60	/* 60 secs */
207
#define DEF_IDLE_INTERVAL		5	/* 5 secs */
D
Daniel Rosenberg 已提交
208
#define DEF_DISABLE_INTERVAL		5	/* 5 secs */
209
#define DEF_DISABLE_QUICK_INTERVAL	1	/* 1 secs */
210
#define DEF_UMOUNT_DISCARD_TIMEOUT	5	/* 5 secs */
J
Jaegeuk Kim 已提交
211

212 213
struct cp_control {
	int reason;
214 215 216
	__u64 trim_start;
	__u64 trim_end;
	__u64 trim_minlen;
217 218
};

219
/*
220
 * indicate meta/data type
221 222 223 224
 */
enum {
	META_CP,
	META_NAT,
225
	META_SIT,
226
	META_SSA,
C
Chao Yu 已提交
227
	META_MAX,
228
	META_POR,
C
Chao Yu 已提交
229 230 231 232 233 234 235 236
	DATA_GENERIC,		/* check range only */
	DATA_GENERIC_ENHANCE,	/* strong check on range and segment bitmap */
	DATA_GENERIC_ENHANCE_READ,	/*
					 * strong check on range and segment
					 * bitmap but no warning due to race
					 * condition of read on truncated area
					 * by extent_cache
					 */
237
	META_GENERIC,
238 239
};

J
Jaegeuk Kim 已提交
240 241 242
/* for the list of ino */
enum {
	ORPHAN_INO,		/* for orphan ino list */
243 244
	APPEND_INO,		/* for append ino list */
	UPDATE_INO,		/* for update ino list */
245
	TRANS_DIR_INO,		/* for trasactions dir ino list */
C
Chao Yu 已提交
246
	FLUSH_INO,		/* for multiple device flushing */
J
Jaegeuk Kim 已提交
247 248 249 250
	MAX_INO_ENTRY,		/* max. list */
};

struct ino_entry {
C
Chao Yu 已提交
251 252 253
	struct list_head list;		/* list head */
	nid_t ino;			/* inode number */
	unsigned int dirty_device;	/* dirty device bitmap */
254 255
};

256
/* for the list of inodes to be GCed */
257
struct inode_entry {
258 259 260 261
	struct list_head list;	/* list head */
	struct inode *inode;	/* vfs inode pointer */
};

262 263 264 265 266 267
struct fsync_node_entry {
	struct list_head list;	/* list head */
	struct page *page;	/* warm node page pointer */
	unsigned int seq_id;	/* sequence id */
};

C
Chao Yu 已提交
268
/* for the bitmap indicate blocks to be discarded */
269 270
struct discard_entry {
	struct list_head list;	/* list head */
C
Chao Yu 已提交
271 272
	block_t start_blkaddr;	/* start blockaddr of current segment */
	unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];	/* segment discard bitmap */
273 274
};

275 276 277
/* default discard granularity of inner discard thread, unit: block count */
#define DEFAULT_DISCARD_GRANULARITY		16

C
Chao Yu 已提交
278 279 280
/* max discard pend list number */
#define MAX_PLIST_NUM		512
#define plist_idx(blk_num)	((blk_num) >= MAX_PLIST_NUM ?		\
S
Sheng Yong 已提交
281
					(MAX_PLIST_NUM - 1) : ((blk_num) - 1))
C
Chao Yu 已提交
282

283
enum {
284 285 286 287
	D_PREP,			/* initial */
	D_PARTIAL,		/* partially submitted */
	D_SUBMIT,		/* all submitted */
	D_DONE,			/* finished */
288 289
};

290 291 292 293 294 295
struct discard_info {
	block_t lstart;			/* logical start address */
	block_t len;			/* length */
	block_t start;			/* actual start address in dev */
};

296
struct discard_cmd {
297 298 299 300 301 302 303 304 305 306
	struct rb_node rb_node;		/* rb node located in rb-tree */
	union {
		struct {
			block_t lstart;	/* logical start address */
			block_t len;	/* length */
			block_t start;	/* actual start address in dev */
		};
		struct discard_info di;	/* discard info */

	};
307 308
	struct list_head list;		/* command list */
	struct completion wait;		/* compleation */
309
	struct block_device *bdev;	/* bdev */
310
	unsigned short ref;		/* reference count */
311
	unsigned char state;		/* state */
312
	unsigned char queued;		/* queued discard */
313
	int error;			/* bio error */
314 315
	spinlock_t lock;		/* for state/bio_ref updating */
	unsigned short bio_ref;		/* bio reference count */
C
Chao Yu 已提交
316 317
};

C
Chao Yu 已提交
318 319 320 321 322 323 324 325
enum {
	DPOLICY_BG,
	DPOLICY_FORCE,
	DPOLICY_FSTRIM,
	DPOLICY_UMOUNT,
	MAX_DPOLICY,
};

C
Chao Yu 已提交
326
struct discard_policy {
C
Chao Yu 已提交
327
	int type;			/* type of discard */
C
Chao Yu 已提交
328
	unsigned int min_interval;	/* used for candidates exist */
329
	unsigned int mid_interval;	/* used for device busy */
C
Chao Yu 已提交
330 331 332 333 334
	unsigned int max_interval;	/* used for candidates not exist */
	unsigned int max_requests;	/* # of discards issued per round */
	unsigned int io_aware_gran;	/* minimum granularity discard not be aware of I/O */
	bool io_aware;			/* issue discard in idle time */
	bool sync;			/* submit discard with REQ_SYNC flag */
C
Chao Yu 已提交
335
	bool ordered;			/* issue discard by lba order */
336
	bool timeout;			/* discard timeout for put_super */
C
Chao Yu 已提交
337
	unsigned int granularity;	/* discard granularity */
C
Chao Yu 已提交
338 339
};

340
struct discard_cmd_control {
341
	struct task_struct *f2fs_issue_discard;	/* discard thread */
342
	struct list_head entry_list;		/* 4KB discard entry list */
C
Chao Yu 已提交
343
	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
344
	struct list_head wait_list;		/* store on-flushing entries */
345
	struct list_head fstrim_list;		/* in-flight discard from fstrim */
346
	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
347
	unsigned int discard_wake;		/* to wake up discard thread */
348
	struct mutex cmd_lock;
C
Chao Yu 已提交
349 350
	unsigned int nr_discards;		/* # of discards in the list */
	unsigned int max_discards;		/* max. discards to be issued */
351
	unsigned int discard_granularity;	/* discard granularity */
C
Chao Yu 已提交
352
	unsigned int undiscard_blks;		/* # of undiscard blocks */
C
Chao Yu 已提交
353
	unsigned int next_pos;			/* next discard position */
C
Chao Yu 已提交
354
	atomic_t issued_discard;		/* # of issued discard */
355
	atomic_t queued_discard;		/* # of queued discard */
C
Chao Yu 已提交
356
	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
C
Chao Yu 已提交
357
	struct rb_root_cached root;		/* root of discard rb-tree */
358
	bool rbtree_check;			/* config for consistence check */
C
Chao Yu 已提交
359 360
};

361 362 363 364
/* for the list of fsync inodes, used only during recovery */
struct fsync_inode_entry {
	struct list_head list;	/* list head */
	struct inode *inode;	/* vfs inode pointer */
365 366
	block_t blkaddr;	/* block address locating the last fsync */
	block_t last_dentry;	/* block address locating the last dentry */
367 368
};

369 370
#define nats_in_cursum(jnl)		(le16_to_cpu((jnl)->n_nats))
#define sits_in_cursum(jnl)		(le16_to_cpu((jnl)->n_sits))
371

372 373 374 375
#define nat_in_journal(jnl, i)		((jnl)->nat_j.entries[i].ne)
#define nid_in_journal(jnl, i)		((jnl)->nat_j.entries[i].nid)
#define sit_in_journal(jnl, i)		((jnl)->sit_j.entries[i].se)
#define segno_in_journal(jnl, i)	((jnl)->sit_j.entries[i].segno)
376

377 378
#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
379

380
static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
381
{
382
	int before = nats_in_cursum(journal);
383

384
	journal->n_nats = cpu_to_le16(before + i);
385 386 387
	return before;
}

388
static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
389
{
390
	int before = sits_in_cursum(journal);
391

392
	journal->n_sits = cpu_to_le16(before + i);
393 394 395
	return before;
}

396 397
static inline bool __has_cursum_space(struct f2fs_journal *journal,
							int size, int type)
398 399
{
	if (type == NAT_JOURNAL)
400 401
		return size <= MAX_NAT_JENTRIES(journal);
	return size <= MAX_SIT_JENTRIES(journal);
402 403
}

404
/*
405
 * f2fs-specific ioctl commands
406
 */
J
Jaegeuk Kim 已提交
407 408 409
#define F2FS_IOCTL_MAGIC		0xf5
#define F2FS_IOC_START_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 1)
#define F2FS_IOC_COMMIT_ATOMIC_WRITE	_IO(F2FS_IOCTL_MAGIC, 2)
410
#define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
411 412
#define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
#define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
J
Jaegeuk Kim 已提交
413
#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
414
#define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
J
Jaegeuk Kim 已提交
415 416
#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
						struct f2fs_defragment)
417 418
#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
						struct f2fs_move_range)
419 420
#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
						struct f2fs_flush_device)
421 422
#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
						struct f2fs_gc_range)
423
#define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
424 425
#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
426
#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
427
#define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
428
#define F2FS_IOC_GET_COMPRESS_BLOCKS	_IOR(F2FS_IOCTL_MAGIC, 17, __u64)
429 430
#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS				\
					_IOR(F2FS_IOCTL_MAGIC, 18, __u64)
431 432
#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS				\
					_IOR(F2FS_IOCTL_MAGIC, 19, __u64)
433 434
#define F2FS_IOC_SEC_TRIM_FILE		_IOW(F2FS_IOCTL_MAGIC, 20,	\
						struct f2fs_sectrim_range)
435

J
Jaegeuk Kim 已提交
436 437 438 439 440 441 442 443
/*
 * should be same as XFS_IOC_GOINGDOWN.
 * Flags for going down operation used by FS_IOC_GOINGDOWN
 */
#define F2FS_IOC_SHUTDOWN	_IOR('X', 125, __u32)	/* Shutdown */
#define F2FS_GOING_DOWN_FULLSYNC	0x0	/* going down with full sync */
#define F2FS_GOING_DOWN_METASYNC	0x1	/* going down with metadata */
#define F2FS_GOING_DOWN_NOSYNC		0x2	/* going down */
444
#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
445
#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
J
Jaegeuk Kim 已提交
446

447 448 449 450 451 452 453
/*
 * Flags used by F2FS_IOC_SEC_TRIM_FILE
 */
#define F2FS_TRIM_FILE_DISCARD		0x1	/* send discard command */
#define F2FS_TRIM_FILE_ZEROOUT		0x2	/* zero out */
#define F2FS_TRIM_FILE_MASK		0x3

454 455 456 457 458 459
struct f2fs_gc_range {
	u32 sync;
	u64 start;
	u64 len;
};

C
Chao Yu 已提交
460 461 462 463 464
struct f2fs_defragment {
	u64 start;
	u64 len;
};

465 466 467 468 469 470 471
struct f2fs_move_range {
	u32 dst_fd;		/* destination fd */
	u64 pos_in;		/* start position in src_fd */
	u64 pos_out;		/* start position in dst_fd */
	u64 len;		/* size to move */
};

472 473 474 475 476
struct f2fs_flush_device {
	u32 dev_num;		/* device number to flush */
	u32 segments;		/* # of segments to flush */
};

477 478 479 480 481 482
struct f2fs_sectrim_range {
	u64 start;
	u64 len;
	u64 flags;
};

C
Chao Yu 已提交
483 484
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE	1
485
static inline int get_extra_isize(struct inode *inode);
C
Chao Yu 已提交
486 487 488
static inline int get_inline_xattr_addrs(struct inode *inode);
#define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
				(CUR_ADDRS_PER_INODE(inode) -		\
489
				get_inline_xattr_addrs(inode) -	\
C
Chao Yu 已提交
490
				DEF_INLINE_RESERVED_SIZE))
C
Chao Yu 已提交
491 492 493 494 495

/* for inline dir */
#define NR_INLINE_DENTRY(inode)	(MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
				BITS_PER_BYTE + 1))
496 497
#define INLINE_DENTRY_BITMAP_SIZE(inode) \
	DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
C
Chao Yu 已提交
498 499 500 501 502
#define INLINE_RESERVED_SIZE(inode)	(MAX_INLINE_DATA(inode) - \
				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
				NR_INLINE_DENTRY(inode) + \
				INLINE_DENTRY_BITMAP_SIZE(inode)))

503 504 505
/*
 * For INODE and NODE manager
 */
506
/* for directory operations */
E
Eric Biggers 已提交
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

struct f2fs_filename {
	/*
	 * The filename the user specified.  This is NULL for some
	 * filesystem-internal operations, e.g. converting an inline directory
	 * to a non-inline one, or roll-forward recovering an encrypted dentry.
	 */
	const struct qstr *usr_fname;

	/*
	 * The on-disk filename.  For encrypted directories, this is encrypted.
	 * This may be NULL for lookups in an encrypted dir without the key.
	 */
	struct fscrypt_str disk_name;

	/* The dirhash of this filename */
	f2fs_hash_t hash;

#ifdef CONFIG_FS_ENCRYPTION
	/*
	 * For lookups in encrypted directories: either the buffer backing
	 * disk_name, or a buffer that holds the decoded no-key name.
	 */
	struct fscrypt_str crypto_buf;
#endif
#ifdef CONFIG_UNICODE
	/*
	 * For casefolded directories: the casefolded name, but it's left NULL
	 * if the original name is not valid Unicode or if the filesystem is
	 * doing an internal operation where usr_fname is also NULL.  In these
	 * cases we fall back to treating the name as an opaque byte sequence.
	 */
	struct fscrypt_str cf_name;
#endif
};

543
struct f2fs_dentry_ptr {
544
	struct inode *inode;
545
	void *bitmap;
546 547 548
	struct f2fs_dir_entry *dentry;
	__u8 (*filename)[F2FS_SLOT_LEN];
	int max;
549
	int nr_bitmap;
550 551
};

552 553
static inline void make_dentry_ptr_block(struct inode *inode,
		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
554
{
555
	d->inode = inode;
556
	d->max = NR_DENTRY_IN_BLOCK;
557
	d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
558
	d->bitmap = t->dentry_bitmap;
559 560 561
	d->dentry = t->dentry;
	d->filename = t->filename;
}
562

563
static inline void make_dentry_ptr_inline(struct inode *inode,
C
Chao Yu 已提交
564
					struct f2fs_dentry_ptr *d, void *t)
565
{
C
Chao Yu 已提交
566 567 568 569
	int entry_cnt = NR_INLINE_DENTRY(inode);
	int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
	int reserved_size = INLINE_RESERVED_SIZE(inode);

570
	d->inode = inode;
C
Chao Yu 已提交
571 572 573 574 575 576
	d->max = entry_cnt;
	d->nr_bitmap = bitmap_size;
	d->bitmap = t;
	d->dentry = t + bitmap_size + reserved_size;
	d->filename = t + bitmap_size + reserved_size +
					SIZE_OF_DIR_ENTRY * entry_cnt;
577 578
}

579 580 581 582 583 584 585
/*
 * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
 * as its node offset to distinguish from index node blocks.
 * But some bits are used to mark the node block.
 */
#define XATTR_NODE_OFFSET	((((unsigned int)-1) << OFFSET_BIT_SHIFT) \
				>> OFFSET_BIT_SHIFT)
586 587 588 589 590
enum {
	ALLOC_NODE,			/* allocate a new node page if needed */
	LOOKUP_NODE,			/* look up a node without readahead */
	LOOKUP_NODE_RA,			/*
					 * look up a node with readahead called
C
Chao Yu 已提交
591
					 * by get_data_block.
592
					 */
593 594
};

595 596
#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */

C
Chao Yu 已提交
597 598 599
/* congestion wait timeout value, default: 20ms */
#define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))

600 601 602
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8

603
#define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
604

605 606
#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */

607
/* for in-memory extent cache entry */
608 609 610 611
#define F2FS_MIN_EXTENT_LEN	64	/* minimum extent length */

/* number of extent info in extent cache we try to shrink */
#define EXTENT_CACHE_SHRINK_NUMBER	128
612

613 614
struct rb_entry {
	struct rb_node rb_node;		/* rb node located in rb-tree */
615 616 617 618 619 620 621
	union {
		struct {
			unsigned int ofs;	/* start offset of the entry */
			unsigned int len;	/* length of the entry */
		};
		unsigned long long key;		/* 64-bits key */
	};
622 623
};

624
struct extent_info {
625 626
	unsigned int fofs;		/* start offset in a file */
	unsigned int len;		/* length of the extent */
627
	u32 blk;			/* start block address of the extent */
628 629 630
};

struct extent_node {
C
Chao Yu 已提交
631 632
	struct rb_node rb_node;		/* rb node located in rb-tree */
	struct extent_info ei;		/* extent info */
633
	struct list_head list;		/* node in global extent list of sbi */
634
	struct extent_tree *et;		/* extent tree pointer */
635 636 637 638
};

struct extent_tree {
	nid_t ino;			/* inode number */
C
Chao Yu 已提交
639
	struct rb_root_cached root;	/* root of extent info rb-tree */
640
	struct extent_node *cached_en;	/* recently accessed extent node */
J
Jaegeuk Kim 已提交
641
	struct extent_info largest;	/* largested extent info */
642
	struct list_head list;		/* to be used by sbi->zombie_list */
643
	rwlock_t lock;			/* protect extent info rb-tree */
644
	atomic_t node_cnt;		/* # of extent node in rb-tree*/
645
	bool largest_updated;		/* largest extent updated */
646 647
};

J
Jaegeuk Kim 已提交
648 649 650 651 652 653 654
/*
 * This structure is taken from ext4_map_blocks.
 *
 * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
 */
#define F2FS_MAP_NEW		(1 << BH_New)
#define F2FS_MAP_MAPPED		(1 << BH_Mapped)
655 656 657
#define F2FS_MAP_UNWRITTEN	(1 << BH_Unwritten)
#define F2FS_MAP_FLAGS		(F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
				F2FS_MAP_UNWRITTEN)
J
Jaegeuk Kim 已提交
658 659 660 661 662 663

struct f2fs_map_blocks {
	block_t m_pblk;
	block_t m_lblk;
	unsigned int m_len;
	unsigned int m_flags;
664
	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
665
	pgoff_t *m_next_extent;		/* point to next possible extent */
666
	int m_seg_type;
C
Chao Yu 已提交
667
	bool m_may_create;		/* indicate it is from write path */
J
Jaegeuk Kim 已提交
668 669
};

C
Chao Yu 已提交
670
/* for flag in get_data_block */
671 672 673 674
enum {
	F2FS_GET_BLOCK_DEFAULT,
	F2FS_GET_BLOCK_FIEMAP,
	F2FS_GET_BLOCK_BMAP,
675
	F2FS_GET_BLOCK_DIO,
676 677
	F2FS_GET_BLOCK_PRE_DIO,
	F2FS_GET_BLOCK_PRE_AIO,
678
	F2FS_GET_BLOCK_PRECACHE,
679
};
C
Chao Yu 已提交
680

681 682 683 684
/*
 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
 */
#define FADVISE_COLD_BIT	0x01
685
#define FADVISE_LOST_PINO_BIT	0x02
686
#define FADVISE_ENCRYPT_BIT	0x04
687
#define FADVISE_ENC_NAME_BIT	0x08
688
#define FADVISE_KEEP_SIZE_BIT	0x10
C
Chao Yu 已提交
689
#define FADVISE_HOT_BIT		0x20
E
Eric Biggers 已提交
690
#define FADVISE_VERITY_BIT	0x40
691

692 693
#define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)

694 695 696 697 698 699
#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
700 701 702
#define file_is_encrypt(inode)	is_file(inode, FADVISE_ENCRYPT_BIT)
#define file_set_encrypt(inode)	set_file(inode, FADVISE_ENCRYPT_BIT)
#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
703 704
#define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
705 706
#define file_keep_isize(inode)	is_file(inode, FADVISE_KEEP_SIZE_BIT)
#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
C
Chao Yu 已提交
707 708 709
#define file_is_hot(inode)	is_file(inode, FADVISE_HOT_BIT)
#define file_set_hot(inode)	set_file(inode, FADVISE_HOT_BIT)
#define file_clear_hot(inode)	clear_file(inode, FADVISE_HOT_BIT)
E
Eric Biggers 已提交
710 711
#define file_is_verity(inode)	is_file(inode, FADVISE_VERITY_BIT)
#define file_set_verity(inode)	set_file(inode, FADVISE_VERITY_BIT)
712

713 714
#define DEF_DIR_LEVEL		0

715 716 717 718 719 720
enum {
	GC_FAILURE_PIN,
	GC_FAILURE_ATOMIC,
	MAX_GC_FAILURE
};

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
/* used for f2fs_inode_info->flags */
enum {
	FI_NEW_INODE,		/* indicate newly allocated inode */
	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
	FI_INC_LINK,		/* need to increment i_nlink */
	FI_ACL_MODE,		/* indicate acl mode */
	FI_NO_ALLOC,		/* should not allocate any blocks */
	FI_FREE_NID,		/* free allocated nide */
	FI_NO_EXTENT,		/* not to use the extent cache */
	FI_INLINE_XATTR,	/* used for inline xattr */
	FI_INLINE_DATA,		/* used for inline data*/
	FI_INLINE_DENTRY,	/* used for inline dentry */
	FI_APPEND_WRITE,	/* inode has appended data */
	FI_UPDATE_WRITE,	/* inode has in-place-update data */
	FI_NEED_IPU,		/* used for ipu per file */
	FI_ATOMIC_FILE,		/* indicate atomic file */
	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
	FI_VOLATILE_FILE,	/* indicate volatile file */
	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
	FI_DROP_CACHE,		/* drop dirty page cache */
	FI_DATA_EXIST,		/* indicate data exists */
	FI_INLINE_DOTS,		/* indicate inline dot dentries */
	FI_DO_DEFRAG,		/* indicate defragment is running */
	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
	FI_HOT_DATA,		/* indicate file is hot */
	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
	FI_PIN_FILE,		/* indicate file should not be gced */
	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
	FI_MMAP_FILE,		/* indicate file was mmapped */
	FI_MAX,			/* max flag, never be used */
};

759 760 761 762
struct f2fs_inode_info {
	struct inode vfs_inode;		/* serve a vfs inode */
	unsigned long i_flags;		/* keep an inode flags for ioctl */
	unsigned char i_advise;		/* use to give file attribute hints */
763
	unsigned char i_dir_level;	/* use for dentry level for large dir */
764 765 766
	unsigned int i_current_depth;	/* only for directory depth */
	/* for gc failure statistic */
	unsigned int i_gc_failures[MAX_GC_FAILURE];
767
	unsigned int i_pino;		/* parent inode number */
768 769 770
	umode_t i_acl_mode;		/* keep file acl mode temporarily */

	/* Use below internally in f2fs*/
771
	unsigned long flags[BITS_TO_LONGS(FI_MAX)];	/* use to pass per-file flags */
772
	struct rw_semaphore i_sem;	/* protect fi info */
773
	atomic_t dirty_pages;		/* # of dirty pages */
774 775
	f2fs_hash_t chash;		/* hash value of given file name */
	unsigned int clevel;		/* maximum level of given file name */
776
	struct task_struct *task;	/* lookup and create consistency */
C
Chao Yu 已提交
777
	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
778
	nid_t i_xattr_nid;		/* node id that contains xattrs */
779
	loff_t	last_disk_size;		/* lastly written file size */
780
	spinlock_t i_size_lock;		/* protect last_disk_size */
J
Jaegeuk Kim 已提交
781

C
Chao Yu 已提交
782 783 784 785 786 787
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];

	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
788 789
	struct list_head dirty_list;	/* dirty list for dirs and files */
	struct list_head gdirty_list;	/* linked in global dirty list */
J
Jaegeuk Kim 已提交
790
	struct list_head inmem_ilist;	/* list for inmem inodes */
J
Jaegeuk Kim 已提交
791
	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
792
	struct task_struct *inmem_task;	/* store inmemory task */
J
Jaegeuk Kim 已提交
793
	struct mutex inmem_lock;	/* lock for inmemory pages */
794
	pgoff_t ra_offset;		/* ongoing readahead offset */
J
Jaegeuk Kim 已提交
795
	struct extent_tree *extent_tree;	/* cached extent_tree entry */
C
Chao Yu 已提交
796 797 798

	/* avoid racing between foreground op and gc */
	struct rw_semaphore i_gc_rwsem[2];
799
	struct rw_semaphore i_mmap_sem;
800
	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
C
Chao Yu 已提交
801

802
	int i_extra_isize;		/* size of extra space located in i_addr */
C
Chao Yu 已提交
803
	kprojid_t i_projid;		/* id for project quota */
C
Chao Yu 已提交
804
	int i_inline_xattr_size;	/* inline xattr size */
805 806
	struct timespec64 i_crtime;	/* inode creation time */
	struct timespec64 i_disk_time[4];/* inode disk times */
C
Chao Yu 已提交
807 808 809 810 811 812

	/* for file compress */
	u64 i_compr_blocks;			/* # of compressed blocks */
	unsigned char i_compress_algorithm;	/* algorithm type */
	unsigned char i_log_cluster_size;	/* log of cluster size */
	unsigned int i_cluster_size;		/* cluster size */
813 814 815
};

static inline void get_extent_info(struct extent_info *ext,
C
Chao Yu 已提交
816
					struct f2fs_extent *i_ext)
817
{
C
Chao Yu 已提交
818 819 820
	ext->fofs = le32_to_cpu(i_ext->fofs);
	ext->blk = le32_to_cpu(i_ext->blk);
	ext->len = le32_to_cpu(i_ext->len);
821 822 823 824 825 826
}

static inline void set_raw_extent(struct extent_info *ext,
					struct f2fs_extent *i_ext)
{
	i_ext->fofs = cpu_to_le32(ext->fofs);
827
	i_ext->blk = cpu_to_le32(ext->blk);
828 829 830
	i_ext->len = cpu_to_le32(ext->len);
}

831 832 833 834 835 836 837 838
static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
						u32 blk, unsigned int len)
{
	ei->fofs = fofs;
	ei->blk = blk;
	ei->len = len;
}

839
static inline bool __is_discard_mergeable(struct discard_info *back,
840
			struct discard_info *front, unsigned int max_len)
841
{
842
	return (back->lstart + back->len == front->lstart) &&
843
		(back->len + front->len <= max_len);
844 845 846
}

static inline bool __is_discard_back_mergeable(struct discard_info *cur,
847
			struct discard_info *back, unsigned int max_len)
848
{
849
	return __is_discard_mergeable(back, cur, max_len);
850 851 852
}

static inline bool __is_discard_front_mergeable(struct discard_info *cur,
853
			struct discard_info *front, unsigned int max_len)
854
{
855
	return __is_discard_mergeable(cur, front, max_len);
856 857
}

858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876
static inline bool __is_extent_mergeable(struct extent_info *back,
						struct extent_info *front)
{
	return (back->fofs + back->len == front->fofs &&
			back->blk + back->len == front->blk);
}

static inline bool __is_back_mergeable(struct extent_info *cur,
						struct extent_info *back)
{
	return __is_extent_mergeable(back, cur);
}

static inline bool __is_front_mergeable(struct extent_info *cur,
						struct extent_info *front)
{
	return __is_extent_mergeable(cur, front);
}

877
extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
878 879
static inline void __try_update_largest_extent(struct extent_tree *et,
						struct extent_node *en)
880
{
881
	if (en->ei.len > et->largest.len) {
882
		et->largest = en->ei;
883
		et->largest_updated = true;
884
	}
885 886
}

C
Chao Yu 已提交
887 888 889 890 891 892 893
/*
 * For free nid management
 */
enum nid_state {
	FREE_NID,		/* newly added to free nid list */
	PREALLOC_NID,		/* it is preallocated */
	MAX_NID_STATE,
C
Chao Yu 已提交
894 895
};

896 897 898
struct f2fs_nm_info {
	block_t nat_blkaddr;		/* base disk address of NAT */
	nid_t max_nid;			/* maximum possible node ids */
899
	nid_t available_nids;		/* # of available node ids */
900
	nid_t next_scan_nid;		/* the next nid to be scanned */
901
	unsigned int ram_thresh;	/* control the memory footprint */
C
Chao Yu 已提交
902
	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
C
Chao Yu 已提交
903
	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
904 905 906

	/* NAT cache management */
	struct radix_tree_root nat_root;/* root of the nat entry cache */
907
	struct radix_tree_root nat_set_root;/* root of the nat set cache */
908
	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
909
	struct list_head nat_entries;	/* cached nat entry list (clean) */
910
	spinlock_t nat_list_lock;	/* protect clean nat entry list */
911
	unsigned int nat_cnt;		/* the # of cached nat entries */
912
	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
913
	unsigned int nat_blocks;	/* # of nat blocks */
914 915

	/* free node ids management */
916
	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
C
Chao Yu 已提交
917 918
	struct list_head free_nid_list;		/* list for free nids excluding preallocated nids */
	unsigned int nid_cnt[MAX_NID_STATE];	/* the number of free node id */
C
Chao Yu 已提交
919
	spinlock_t nid_list_lock;	/* protect nid lists ops */
920
	struct mutex build_lock;	/* lock for build free nids */
921
	unsigned char **free_nid_bitmap;
C
Chao Yu 已提交
922
	unsigned char *nat_block_bitmap;
923
	unsigned short *free_nid_count;	/* free nid count of NAT block */
924 925 926

	/* for checkpoint */
	char *nat_bitmap;		/* NAT bitmap pointer */
927 928 929 930 931

	unsigned int nat_bits_blocks;	/* # of nat bits blocks */
	unsigned char *nat_bits;	/* NAT bits blocks */
	unsigned char *full_nat_bits;	/* full NAT pages */
	unsigned char *empty_nat_bits;	/* empty NAT pages */
932 933 934
#ifdef CONFIG_F2FS_CHECK_FS
	char *nat_bitmap_mir;		/* NAT bitmap mirror */
#endif
935 936 937 938 939 940 941 942 943 944 945 946 947 948 949
	int bitmap_size;		/* bitmap size */
};

/*
 * this structure is used as one of function parameters.
 * all the information are dedicated to a given direct node block determined
 * by the data offset in a file.
 */
struct dnode_of_data {
	struct inode *inode;		/* vfs inode pointer */
	struct page *inode_page;	/* its inode page, NULL is possible */
	struct page *node_page;		/* cached direct node page */
	nid_t nid;			/* node id of the direct node block */
	unsigned int ofs_in_node;	/* data offset in the node page */
	bool inode_page_locked;		/* inode page is locked or not */
950
	bool node_changed;		/* is node block changed */
951 952
	char cur_level;			/* level of hole node page */
	char max_level;			/* level of current page located */
953 954 955 956 957 958
	block_t	data_blkaddr;		/* block address of the node block */
};

static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
		struct page *ipage, struct page *npage, nid_t nid)
{
959
	memset(dn, 0, sizeof(*dn));
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980
	dn->inode = inode;
	dn->inode_page = ipage;
	dn->node_page = npage;
	dn->nid = nid;
}

/*
 * For SIT manager
 *
 * By default, there are 6 active log areas across the whole main area.
 * When considering hot and cold data separation to reduce cleaning overhead,
 * we split 3 for data logs and 3 for node logs as hot, warm, and cold types,
 * respectively.
 * In the current design, you should not change the numbers intentionally.
 * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6
 * logs individually according to the underlying devices. (default: 6)
 * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for
 * data and 8 for node logs.
 */
#define	NR_CURSEG_DATA_TYPE	(3)
#define NR_CURSEG_NODE_TYPE	(3)
C
Chao Yu 已提交
981 982 983
#define NR_CURSEG_INMEM_TYPE	(1)
#define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
#define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
984 985 986 987 988 989 990 991

enum {
	CURSEG_HOT_DATA	= 0,	/* directory entry blocks */
	CURSEG_WARM_DATA,	/* data blocks */
	CURSEG_COLD_DATA,	/* multimedia or GCed data blocks */
	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
	CURSEG_COLD_NODE,	/* indirect node blocks */
C
Chao Yu 已提交
992 993 994 995
	NR_PERSISTENT_LOG,	/* number of persistent log */
	CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
				/* pinned file that needs consecutive block address */
	NO_CHECK_TYPE,		/* number of persistent & inmem log */
996 997
};

998 999
struct flush_cmd {
	struct completion wait;
1000
	struct llist_node llnode;
C
Chao Yu 已提交
1001
	nid_t ino;
1002 1003 1004
	int ret;
};

1005 1006 1007
struct flush_cmd_control {
	struct task_struct *f2fs_issue_flush;	/* flush thread */
	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
C
Chao Yu 已提交
1008
	atomic_t issued_flush;			/* # of issued flushes */
1009
	atomic_t queued_flush;			/* # of queued flushes */
1010 1011
	struct llist_head issue_list;		/* list for command issue */
	struct llist_node *dispatch_list;	/* list for command dispatch */
1012 1013
};

1014 1015 1016 1017 1018 1019
struct f2fs_sm_info {
	struct sit_info *sit_info;		/* whole segment information */
	struct free_segmap_info *free_info;	/* free segment information */
	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
	struct curseg_info *curseg_array;	/* active segment information */

C
Chao Yu 已提交
1020 1021
	struct rw_semaphore curseg_lock;	/* for preventing curseg change */

1022 1023 1024 1025 1026 1027 1028 1029
	block_t seg0_blkaddr;		/* block address of 0'th segment */
	block_t main_blkaddr;		/* start block address of main area */
	block_t ssa_blkaddr;		/* start block address of SSA area */

	unsigned int segment_count;	/* total # of segments */
	unsigned int main_segments;	/* # of segments in main area */
	unsigned int reserved_segments;	/* # of reserved segments */
	unsigned int ovp_segments;	/* # of overprovision segments */
1030 1031 1032

	/* a threshold to reclaim prefree segments */
	unsigned int rec_prefree_segments;
1033

J
Jaegeuk Kim 已提交
1034 1035 1036
	/* for batched trimming */
	unsigned int trim_sections;		/* # of sections to trim */

1037 1038
	struct list_head sit_entry_set;	/* sit entry set list */

1039 1040
	unsigned int ipu_policy;	/* in-place-update policy */
	unsigned int min_ipu_util;	/* in-place-update threshold */
1041
	unsigned int min_fsync_blocks;	/* threshold for fsync */
1042
	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
1043
	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
C
Chao Yu 已提交
1044
	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
1045 1046

	/* for flush command control */
1047
	struct flush_cmd_control *fcc_info;
1048

1049 1050
	/* for discard command control */
	struct discard_cmd_control *dcc_info;
1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
};

/*
 * For superblock
 */
/*
 * COUNT_TYPE for monitoring
 *
 * f2fs monitors the number of several block types such as on-writeback,
 * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
 */
1062
#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
1063 1064
enum count_type {
	F2FS_DIRTY_DENTS,
1065
	F2FS_DIRTY_DATA,
1066
	F2FS_DIRTY_QDATA,
1067 1068
	F2FS_DIRTY_NODES,
	F2FS_DIRTY_META,
1069
	F2FS_INMEM_PAGES,
1070
	F2FS_DIRTY_IMETA,
1071 1072
	F2FS_WB_CP_DATA,
	F2FS_WB_DATA,
1073 1074 1075
	F2FS_RD_DATA,
	F2FS_RD_NODE,
	F2FS_RD_META,
C
Chao Yu 已提交
1076 1077
	F2FS_DIO_WRITE,
	F2FS_DIO_READ,
1078 1079 1080 1081
	NR_COUNT_TYPE,
};

/*
A
arter97 已提交
1082
 * The below are the page types of bios used in submit_bio().
1083 1084 1085 1086 1087 1088 1089 1090 1091
 * The available types are:
 * DATA			User data pages. It operates as async mode.
 * NODE			Node pages. It operates as async mode.
 * META			FS metadata pages such as SIT, NAT, CP.
 * NR_PAGE_TYPE		The number of page types.
 * META_FLUSH		Make sure the previous pages are written
 *			with waiting the bio's completion
 * ...			Only can be used with META.
 */
1092
#define PAGE_TYPE_OF_BIO(type)	((type) > META ? META : (type))
1093 1094 1095 1096 1097 1098
enum page_type {
	DATA,
	NODE,
	META,
	NR_PAGE_TYPE,
	META_FLUSH,
1099 1100
	INMEM,		/* the below types are used by tracepoints only. */
	INMEM_DROP,
1101
	INMEM_INVALIDATE,
1102
	INMEM_REVOKE,
1103 1104
	IPU,
	OPU,
1105 1106
};

J
Jaegeuk Kim 已提交
1107 1108 1109 1110 1111 1112 1113
enum temp_type {
	HOT = 0,	/* must be zero for meta bio */
	WARM,
	COLD,
	NR_TEMP_TYPE,
};

1114 1115 1116 1117 1118 1119
enum need_lock_type {
	LOCK_REQ = 0,
	LOCK_DONE,
	LOCK_RETRY,
};

C
Chao Yu 已提交
1120 1121 1122
enum cp_reason_type {
	CP_NO_NEEDED,
	CP_NON_REGULAR,
C
Chao Yu 已提交
1123
	CP_COMPRESSED,
C
Chao Yu 已提交
1124 1125 1126 1127 1128 1129 1130
	CP_HARDLINK,
	CP_SB_NEED_CP,
	CP_WRONG_PINO,
	CP_NO_SPC_ROLL,
	CP_NODE_NEED_CP,
	CP_FASTBOOT_MODE,
	CP_SPEC_LOG_NUM,
1131
	CP_RECOVER_DIR,
C
Chao Yu 已提交
1132 1133
};

C
Chao Yu 已提交
1134
enum iostat_type {
C
Chao Yu 已提交
1135 1136 1137
	/* WRITE IO */
	APP_DIRECT_IO,			/* app direct write IOs */
	APP_BUFFERED_IO,		/* app buffered write IOs */
C
Chao Yu 已提交
1138 1139 1140 1141 1142 1143 1144 1145 1146 1147
	APP_WRITE_IO,			/* app write IOs */
	APP_MAPPED_IO,			/* app mapped IOs */
	FS_DATA_IO,			/* data IOs from kworker/fsync/reclaimer */
	FS_NODE_IO,			/* node IOs from kworker/fsync/reclaimer */
	FS_META_IO,			/* meta IOs from kworker/reclaimer */
	FS_GC_DATA_IO,			/* data IOs from forground gc */
	FS_GC_NODE_IO,			/* node IOs from forground gc */
	FS_CP_DATA_IO,			/* data IOs from checkpoint */
	FS_CP_NODE_IO,			/* node IOs from checkpoint */
	FS_CP_META_IO,			/* meta IOs from checkpoint */
C
Chao Yu 已提交
1148 1149 1150 1151 1152 1153 1154

	/* READ IO */
	APP_DIRECT_READ_IO,		/* app direct read IOs */
	APP_BUFFERED_READ_IO,		/* app buffered read IOs */
	APP_READ_IO,			/* app read IOs */
	APP_MAPPED_READ_IO,		/* app mapped read IOs */
	FS_DATA_READ_IO,		/* data read IOs */
1155 1156
	FS_GDATA_READ_IO,		/* data read IOs from background gc */
	FS_CDATA_READ_IO,		/* compressed data read IOs */
C
Chao Yu 已提交
1157 1158 1159 1160
	FS_NODE_READ_IO,		/* node read IOs */
	FS_META_READ_IO,		/* meta read IOs */

	/* other */
C
Chao Yu 已提交
1161 1162 1163 1164
	FS_DISCARD,			/* discard */
	NR_IO_TYPE,
};

J
Jaegeuk Kim 已提交
1165
struct f2fs_io_info {
1166
	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
C
Chao Yu 已提交
1167
	nid_t ino;		/* inode number */
1168
	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
J
Jaegeuk Kim 已提交
1169
	enum temp_type temp;	/* contains HOT/WARM/COLD */
M
Mike Christie 已提交
1170
	int op;			/* contains REQ_OP_ */
1171
	int op_flags;		/* req_flag_bits */
1172
	block_t new_blkaddr;	/* new block address to be written */
1173
	block_t old_blkaddr;	/* old block address before Cow */
1174
	struct page *page;	/* page to be written */
1175
	struct page *encrypted_page;	/* encrypted page */
C
Chao Yu 已提交
1176
	struct page *compressed_page;	/* compressed page */
1177
	struct list_head list;		/* serialize IOs */
1178
	bool submitted;		/* indicate IO submission */
1179
	int need_lock;		/* indicate we need to lock cp_rwsem */
1180
	bool in_list;		/* indicate fio is in io_list */
C
Chao Yu 已提交
1181
	bool is_por;		/* indicate IO is from recovery or not */
1182
	bool retry;		/* need to reallocate block address */
C
Chao Yu 已提交
1183 1184
	int compr_blocks;	/* # of compressed block addresses */
	bool encrypted;		/* indicate file is encrypted */
C
Chao Yu 已提交
1185
	enum iostat_type io_type;	/* io type */
1186
	struct writeback_control *io_wbc; /* writeback control */
C
Chao Yu 已提交
1187 1188
	struct bio **bio;		/* bio for ipu */
	sector_t *last_block;		/* last block number in bio */
1189
	unsigned char version;		/* version of the node */
J
Jaegeuk Kim 已提交
1190 1191
};

C
Chao Yu 已提交
1192 1193 1194 1195 1196
struct bio_entry {
	struct bio *bio;
	struct list_head list;
};

1197
#define is_read_io(rw) ((rw) == READ)
1198
struct f2fs_bio_info {
J
Jaegeuk Kim 已提交
1199
	struct f2fs_sb_info *sbi;	/* f2fs superblock */
1200 1201
	struct bio *bio;		/* bios to merge */
	sector_t last_block_in_bio;	/* last block number */
J
Jaegeuk Kim 已提交
1202
	struct f2fs_io_info fio;	/* store buffered io info. */
1203
	struct rw_semaphore io_rwsem;	/* blocking op for bio */
1204 1205
	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
	struct list_head io_list;	/* track fios */
C
Chao Yu 已提交
1206 1207
	struct list_head bio_list;	/* bio entry list head */
	struct rw_semaphore bio_list_lock;	/* lock to protect bio entry list */
1208 1209
};

J
Jaegeuk Kim 已提交
1210 1211 1212 1213 1214 1215 1216 1217 1218
#define FDEV(i)				(sbi->devs[i])
#define RDEV(i)				(raw_super->devs[i])
struct f2fs_dev_info {
	struct block_device *bdev;
	char path[MAX_PATH_LEN];
	unsigned int total_segments;
	block_t start_blk;
	block_t end_blk;
#ifdef CONFIG_BLK_DEV_ZONED
1219 1220
	unsigned int nr_blkz;		/* Total number of zones */
	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
1221
	block_t *zone_capacity_blocks;  /* Array of zone capacity in blks */
J
Jaegeuk Kim 已提交
1222 1223 1224
#endif
};

1225 1226 1227
enum inode_type {
	DIR_INODE,			/* for dirty dir inode */
	FILE_INODE,			/* for dirty regular/symlink inode */
1228
	DIRTY_META,			/* for all dirtied inode metadata */
J
Jaegeuk Kim 已提交
1229
	ATOMIC_FILE,			/* for all atomic files */
1230 1231 1232
	NR_INODE_TYPE,
};

1233 1234 1235 1236 1237 1238 1239 1240
/* for inner inode cache management */
struct inode_management {
	struct radix_tree_root ino_root;	/* ino entry array */
	spinlock_t ino_lock;			/* for ino entry lock */
	struct list_head ino_list;		/* inode list head */
	unsigned long ino_num;			/* number of entries */
};

1241 1242 1243 1244 1245 1246
/* For s_flag in struct f2fs_sb_info */
enum {
	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
	SBI_IS_CLOSE,				/* specify unmounting */
	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
	SBI_POR_DOING,				/* recovery is doing or not */
1247
	SBI_NEED_SB_WRITE,			/* need to recover superblock */
1248
	SBI_NEED_CP,				/* need to checkpoint */
1249
	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
1250
	SBI_IS_RECOVERED,			/* recovered orphan/data */
D
Daniel Rosenberg 已提交
1251
	SBI_CP_DISABLED,			/* CP was disabled last mount */
1252
	SBI_CP_DISABLED_QUICK,			/* CP was disabled quickly */
1253 1254 1255
	SBI_QUOTA_NEED_FLUSH,			/* need to flush quota info in CP */
	SBI_QUOTA_SKIP_FLUSH,			/* skip flushing quota in current CP */
	SBI_QUOTA_NEED_REPAIR,			/* quota file may be corrupted */
1256
	SBI_IS_RESIZEFS,			/* resizefs is in process */
1257 1258
};

1259 1260
enum {
	CP_TIME,
1261
	REQ_TIME,
1262 1263
	DISCARD_TIME,
	GC_TIME,
D
Daniel Rosenberg 已提交
1264
	DISABLE_TIME,
1265
	UMOUNT_DISCARD_TIMEOUT,
1266 1267 1268
	MAX_TIME,
};

1269 1270 1271 1272
enum {
	GC_NORMAL,
	GC_IDLE_CB,
	GC_IDLE_GREEDY,
1273 1274
	GC_URGENT_HIGH,
	GC_URGENT_LOW,
1275 1276
};

C
Chao Yu 已提交
1277 1278 1279 1280 1281 1282 1283 1284 1285
enum {
	BGGC_MODE_ON,		/* background gc is on */
	BGGC_MODE_OFF,		/* background gc is off */
	BGGC_MODE_SYNC,		/*
				 * background gc is on, migrating blocks
				 * like foreground gc
				 */
};

1286 1287 1288 1289 1290
enum {
	FS_MODE_ADAPTIVE,	/* use both lfs/ssr allocation */
	FS_MODE_LFS,		/* use lfs allocation only */
};

1291 1292 1293
enum {
	WHINT_MODE_OFF,		/* not pass down write hints */
	WHINT_MODE_USER,	/* try to pass down hints given by users */
1294
	WHINT_MODE_FS,		/* pass down hints with F2FS policy */
1295 1296
};

1297 1298 1299 1300 1301
enum {
	ALLOC_MODE_DEFAULT,	/* stay default */
	ALLOC_MODE_REUSE,	/* reuse segments as much as possible */
};

1302 1303 1304
enum fsync_mode {
	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
1305
	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
1306 1307
};

C
Chao Yu 已提交
1308 1309 1310 1311 1312 1313 1314 1315
/*
 * this value is set in page as a private data which indicate that
 * the page is atomically written, and it is in inmem_pages list.
 */
#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)

#define IS_ATOMIC_WRITTEN_PAGE(page)			\
1316
		(page_private(page) == ATOMIC_WRITTEN_PAGE)
C
Chao Yu 已提交
1317
#define IS_DUMMY_WRITTEN_PAGE(page)			\
1318
		(page_private(page) == DUMMY_WRITTEN_PAGE)
C
Chao Yu 已提交
1319

1320 1321 1322 1323 1324 1325 1326 1327
#ifdef CONFIG_F2FS_IO_TRACE
#define IS_IO_TRACED_PAGE(page)			\
		(page_private(page) > 0 &&		\
		 page_private(page) < (unsigned long)PID_MAX_LIMIT)
#else
#define IS_IO_TRACED_PAGE(page) (0)
#endif

1328
#ifdef CONFIG_FS_ENCRYPTION
1329
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
1330
	(unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL))
1331 1332 1333 1334
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif

C
Chao Yu 已提交
1335 1336 1337 1338
/* For compression */
enum compress_algorithm_type {
	COMPRESS_LZO,
	COMPRESS_LZ4,
1339
	COMPRESS_ZSTD,
1340
	COMPRESS_LZORLE,
C
Chao Yu 已提交
1341 1342 1343
	COMPRESS_MAX,
};

1344
#define COMPRESS_DATA_RESERVED_SIZE		5
C
Chao Yu 已提交
1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
struct compress_data {
	__le32 clen;			/* compressed data size */
	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
	u8 cdata[];			/* compressed data */
};

#define COMPRESS_HEADER_SIZE	(sizeof(struct compress_data))

#define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000

/* compress context */
struct compress_ctx {
	struct inode *inode;		/* inode the context belong to */
	pgoff_t cluster_idx;		/* cluster index number */
	unsigned int cluster_size;	/* page count in cluster */
	unsigned int log_cluster_size;	/* log of cluster size */
	struct page **rpages;		/* pages store raw data in cluster */
	unsigned int nr_rpages;		/* total page number in rpages */
	struct page **cpages;		/* pages store compressed data in cluster */
	unsigned int nr_cpages;		/* total page number in cpages */
	void *rbuf;			/* virtual mapped address on rpages */
	struct compress_data *cbuf;	/* virtual mapped address on cpages */
	size_t rlen;			/* valid data length in rbuf */
	size_t clen;			/* valid data length in cbuf */
	void *private;			/* payload buffer for specified compression algorithm */
1370
	void *private2;			/* extra payload buffer */
C
Chao Yu 已提交
1371 1372 1373 1374 1375 1376 1377 1378
};

/* compress context for write IO path */
struct compress_io_ctx {
	u32 magic;			/* magic number to indicate page is compressed */
	struct inode *inode;		/* inode the context belong to */
	struct page **rpages;		/* pages store raw data in cluster */
	unsigned int nr_rpages;		/* total page number in rpages */
1379
	atomic_t pending_pages;		/* in-flight compressed page count */
C
Chao Yu 已提交
1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
};

/* decompress io context for read IO path */
struct decompress_io_ctx {
	u32 magic;			/* magic number to indicate page is compressed */
	struct inode *inode;		/* inode the context belong to */
	pgoff_t cluster_idx;		/* cluster index number */
	unsigned int cluster_size;	/* page count in cluster */
	unsigned int log_cluster_size;	/* log of cluster size */
	struct page **rpages;		/* pages store raw data in cluster */
	unsigned int nr_rpages;		/* total page number in rpages */
	struct page **cpages;		/* pages store compressed data in cluster */
	unsigned int nr_cpages;		/* total page number in cpages */
	struct page **tpages;		/* temp pages to pad holes in cluster */
	void *rbuf;			/* virtual mapped address on rpages */
	struct compress_data *cbuf;	/* virtual mapped address on cpages */
	size_t rlen;			/* valid data length in rbuf */
	size_t clen;			/* valid data length in cbuf */
1398
	atomic_t pending_pages;		/* in-flight compressed page count */
C
Chao Yu 已提交
1399
	bool failed;			/* indicate IO error during decompression */
1400 1401
	void *private;			/* payload buffer for specified decompression algorithm */
	void *private2;			/* extra payload buffer */
C
Chao Yu 已提交
1402 1403 1404 1405 1406
};

#define NULL_CLUSTER			((unsigned int)(~0))
#define MIN_COMPRESS_LOG_SIZE		2
#define MAX_COMPRESS_LOG_SIZE		8
1407
#define MAX_COMPRESS_WINDOW_SIZE	((PAGE_SIZE) << MAX_COMPRESS_LOG_SIZE)
C
Chao Yu 已提交
1408

1409 1410
struct f2fs_sb_info {
	struct super_block *sb;			/* pointer to VFS super block */
1411
	struct proc_dir_entry *s_proc;		/* proc entry */
1412
	struct f2fs_super_block *raw_super;	/* raw super block pointer */
1413
	struct rw_semaphore sb_lock;		/* lock for raw super block */
1414
	int valid_super_block;			/* valid super block no */
1415
	unsigned long s_flag;				/* flags for sbi */
1416
	struct mutex writepages;		/* mutex for writepages() */
1417

1418 1419 1420 1421 1422
#ifdef CONFIG_BLK_DEV_ZONED
	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
	unsigned int log_blocks_per_blkz;	/* log2 F2FS blocks per zone */
#endif

1423 1424 1425 1426 1427 1428
	/* for node-related operations */
	struct f2fs_nm_info *nm_info;		/* node manager */
	struct inode *node_inode;		/* cache node blocks */

	/* for segment-related operations */
	struct f2fs_sm_info *sm_info;		/* segment manager */
1429 1430

	/* for bio operations */
J
Jaegeuk Kim 已提交
1431
	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
1432 1433
	/* keep migration IO order for LFS mode */
	struct rw_semaphore io_order_lock;
1434
	mempool_t *write_io_dummy;		/* Dummy pages */
1435 1436 1437

	/* for checkpoint */
	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
1438
	int cur_cp_pack;			/* remain current cp pack */
1439
	spinlock_t cp_lock;			/* for flag in ckpt */
1440
	struct inode *meta_inode;		/* cache meta blocks */
1441
	struct mutex cp_mutex;			/* checkpoint procedure lock */
1442
	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
1443
	struct rw_semaphore node_write;		/* locking node writes */
1444
	struct rw_semaphore node_change;	/* locking node change */
1445
	wait_queue_head_t cp_wait;
1446 1447
	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
	long interval_time[MAX_TIME];		/* to store thresholds */
1448

J
Jack Qiu 已提交
1449
	struct inode_management im[MAX_INO_ENTRY];	/* manage inode cache */
J
Jaegeuk Kim 已提交
1450

1451 1452 1453 1454 1455
	spinlock_t fsync_node_lock;		/* for node entry lock */
	struct list_head fsync_node_list;	/* node list head */
	unsigned int fsync_seg_id;		/* sequence id */
	unsigned int fsync_node_num;		/* number of node entries */

J
Jaegeuk Kim 已提交
1456
	/* for orphan inode, use 0'th array */
1457
	unsigned int max_orphans;		/* max orphan inodes */
1458

1459 1460 1461
	/* for inode management */
	struct list_head inode_list[NR_INODE_TYPE];	/* dirty inode list */
	spinlock_t inode_lock[NR_INODE_TYPE];	/* for dirty inode list lock */
1462
	struct mutex flush_lock;		/* for flush exclusion */
1463

1464 1465
	/* for extent tree cache */
	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
1466
	struct mutex extent_tree_lock;	/* locking extent radix tree */
1467 1468
	struct list_head extent_list;		/* lru list for shrinker */
	spinlock_t extent_lock;			/* locking extent lru list */
1469
	atomic_t total_ext_tree;		/* extent tree count */
1470
	struct list_head zombie_list;		/* extent zombie tree list */
1471
	atomic_t total_zombie_tree;		/* extent zombie tree count */
1472 1473
	atomic_t total_ext_node;		/* extent info count */

A
arter97 已提交
1474
	/* basic filesystem units */
1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487
	unsigned int log_sectors_per_block;	/* log2 sectors per block */
	unsigned int log_blocksize;		/* log2 block size */
	unsigned int blocksize;			/* block size */
	unsigned int root_ino_num;		/* root inode number*/
	unsigned int node_ino_num;		/* node inode number*/
	unsigned int meta_ino_num;		/* meta inode number*/
	unsigned int log_blocks_per_seg;	/* log2 blocks per segment */
	unsigned int blocks_per_seg;		/* blocks per segment */
	unsigned int segs_per_sec;		/* segments per section */
	unsigned int secs_per_zone;		/* sections per zone */
	unsigned int total_sections;		/* total section count */
	unsigned int total_node_count;		/* total node block count */
	unsigned int total_valid_node_count;	/* valid node block count */
C
Chao Yu 已提交
1488
	loff_t max_file_blocks;			/* max block index of file */
1489
	int dir_level;				/* directory level */
1490
	int readdir_ra;				/* readahead inode in readdir */
1491 1492 1493

	block_t user_block_count;		/* # of user blocks */
	block_t total_valid_block_count;	/* # of valid blocks */
1494
	block_t discard_blks;			/* discard command candidats */
1495
	block_t last_valid_block_count;		/* for recovery */
1496
	block_t reserved_blocks;		/* configurable reserved blocks */
1497
	block_t current_reserved_blocks;	/* current reserved blocks */
1498

D
Daniel Rosenberg 已提交
1499 1500 1501
	/* Additional tracking for no checkpoint mode */
	block_t unusable_block_count;		/* # of blocks saved by last cp */

1502
	unsigned int nquota_files;		/* # of quota sysfile */
1503
	struct rw_semaphore quota_sem;		/* blocking cp for flags */
1504

1505
	/* # of pages, see count_type */
1506
	atomic_t nr_pages[NR_COUNT_TYPE];
1507 1508
	/* # of allocated blocks */
	struct percpu_counter alloc_valid_block_count;
1509

1510
	/* writeback control */
1511
	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
1512

1513 1514 1515
	/* valid inode count */
	struct percpu_counter total_valid_inode_count;

1516 1517 1518
	struct f2fs_mount_info mount_opt;	/* mount options */

	/* for cleaning operations */
C
Chao Yu 已提交
1519 1520 1521 1522
	struct rw_semaphore gc_lock;		/*
						 * semaphore for GC, avoid
						 * race between GC and GC or CP
						 */
1523
	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
1524
	unsigned int cur_victim_sec;		/* current victim section num */
1525
	unsigned int gc_mode;			/* current GC state */
1526
	unsigned int next_victim_seg[2];	/* next segment in victim section */
1527

1528
	/* for skip statistic */
J
Jack Qiu 已提交
1529
	unsigned int atomic_files;		/* # of opened atomic file */
1530
	unsigned long long skipped_atomic_files[2];	/* FG_GC and BG_GC */
1531
	unsigned long long skipped_gc_rwsem;		/* FG_GC only */
1532

1533 1534
	/* threshold for gc trials on pinned files */
	u64 gc_pin_file_threshold;
J
Jaegeuk Kim 已提交
1535
	struct rw_semaphore pin_sem;
1536

1537 1538
	/* maximum # of trials to find a victim segment for SSR and GC */
	unsigned int max_victim_search;
1539 1540
	/* migration granularity of garbage collection, unit: segment */
	unsigned int migration_granularity;
1541

1542 1543 1544 1545
	/*
	 * for stat information.
	 * one is for the LFS mode, and the other is for the SSR mode.
	 */
1546
#ifdef CONFIG_F2FS_STAT_FS
1547
	struct f2fs_stat_info *stat_info;	/* FS status information */
C
Chao Yu 已提交
1548
	atomic_t meta_count[META_MAX];		/* # of meta blocks */
1549 1550
	unsigned int segment_count[2];		/* # of allocated segments */
	unsigned int block_count[2];		/* # of allocated blocks */
1551
	atomic_t inplace_count;		/* # of inplace update */
1552 1553 1554 1555
	atomic64_t total_hit_ext;		/* # of lookup extent cache */
	atomic64_t read_hit_rbtree;		/* # of hit rbtree extent node */
	atomic64_t read_hit_largest;		/* # of hit largest extent node */
	atomic64_t read_hit_cached;		/* # of hit cached extent node */
C
Chao Yu 已提交
1556
	atomic_t inline_xattr;			/* # of inline_xattr inodes */
1557 1558
	atomic_t inline_inode;			/* # of inline_data inodes */
	atomic_t inline_dir;			/* # of inline_dentry inodes */
C
Chao Yu 已提交
1559 1560
	atomic_t compr_inode;			/* # of compressed inodes */
	atomic_t compr_blocks;			/* # of compressed blocks */
1561
	atomic_t vw_cnt;			/* # of volatile writes */
1562
	atomic_t max_aw_cnt;			/* max # of atomic writes */
1563
	atomic_t max_vw_cnt;			/* max # of volatile writes */
1564 1565
	unsigned int io_skip_bggc;		/* skip background gc for in-flight IO */
	unsigned int other_skip_bggc;		/* skip background gc for other reasons */
C
Chao Yu 已提交
1566
	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
1567
#endif
1568
	spinlock_t stat_lock;			/* lock for stat operations */
1569

C
Chao Yu 已提交
1570 1571
	/* For app/fs IO statistics */
	spinlock_t iostat_lock;
C
Chao Yu 已提交
1572 1573
	unsigned long long rw_iostat[NR_IO_TYPE];
	unsigned long long prev_rw_iostat[NR_IO_TYPE];
C
Chao Yu 已提交
1574
	bool iostat_enable;
1575 1576
	unsigned long iostat_next_period;
	unsigned int iostat_period_ms;
C
Chao Yu 已提交
1577

1578 1579
	/* to attach REQ_META|REQ_FUA flags */
	unsigned int data_io_flag;
1580
	unsigned int node_io_flag;
C
Chao Yu 已提交
1581

1582 1583 1584
	/* For sysfs suppport */
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1585 1586 1587

	/* For shrinker support */
	struct list_head s_list;
J
Jaegeuk Kim 已提交
1588 1589
	int s_ndevs;				/* number of devices */
	struct f2fs_dev_info *devs;		/* for device list */
1590 1591
	unsigned int dirty_device;		/* for checkpoint data flush */
	spinlock_t dev_lock;			/* protect dirty_device */
1592 1593
	struct mutex umount_mutex;
	unsigned int shrinker_run_no;
1594 1595 1596 1597

	/* For write statistics */
	u64 sectors_written_start;
	u64 kbytes_written;
K
Keith Mok 已提交
1598 1599 1600

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1601

C
Chao Yu 已提交
1602 1603
	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_chksum_seed;
C
Chao Yu 已提交
1604 1605

	struct workqueue_struct *post_read_wq;	/* post read workqueue */
1606 1607 1608

	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
	unsigned int inline_xattr_slab_size;	/* default inline xattr slab size */
1609 1610
};

C
Chao Yu 已提交
1611 1612 1613 1614 1615 1616 1617
struct f2fs_private_dio {
	struct inode *inode;
	void *orig_private;
	bio_end_io_t *orig_end_io;
	bool write;
};

1618
#ifdef CONFIG_F2FS_FAULT_INJECTION
1619 1620 1621 1622
#define f2fs_show_injection_info(sbi, type)					\
	printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n",	\
		KERN_INFO, sbi->sb->s_id,				\
		f2fs_fault_name[type],					\
1623
		__func__, __builtin_return_address(0))
1624 1625
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
1626
	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640

	if (!ffi->inject_rate)
		return false;

	if (!IS_FAULT_SET(ffi, type))
		return false;

	atomic_inc(&ffi->inject_ops);
	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
		atomic_set(&ffi->inject_ops, 0);
		return true;
	}
	return false;
}
1641
#else
1642
#define f2fs_show_injection_info(sbi, type) do { } while (0)
1643 1644 1645 1646
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
	return false;
}
1647 1648
#endif

1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659
/*
 * Test if the mounted volume is a multi-device volume.
 *   - For a single regular disk volume, sbi->s_ndevs is 0.
 *   - For a single zoned disk volume, sbi->s_ndevs is 1.
 *   - For a multi-device volume, sbi->s_ndevs is always 2 or more.
 */
static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
{
	return sbi->s_ndevs > 1;
}

1660 1661 1662 1663
/* For write statistics. Suppose sector size is 512 bytes,
 * and the return value is in kbytes. s is of struct f2fs_sb_info.
 */
#define BD_PART_WRITTEN(s)						 \
1664
(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
1665
		(s)->sectors_written_start) >> 1)
1666

1667 1668
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
1669 1670 1671 1672 1673 1674 1675 1676 1677
	unsigned long now = jiffies;

	sbi->last_time[type] = now;

	/* DISCARD_TIME and GC_TIME are based on REQ_TIME */
	if (type == REQ_TIME) {
		sbi->last_time[DISCARD_TIME] = now;
		sbi->last_time[GC_TIME] = now;
	}
1678 1679 1680 1681
}

static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
A
Arnd Bergmann 已提交
1682
	unsigned long interval = sbi->interval_time[type] * HZ;
1683 1684 1685 1686

	return time_after(jiffies, sbi->last_time[type] + interval);
}

1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700
static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi,
						int type)
{
	unsigned long interval = sbi->interval_time[type] * HZ;
	unsigned int wait_ms = 0;
	long delta;

	delta = (sbi->last_time[type] + interval) - jiffies;
	if (delta > 0)
		wait_ms = jiffies_to_msecs(delta);

	return wait_ms;
}

1701 1702 1703
/*
 * Inline functions
 */
C
Chao Yu 已提交
1704
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
C
Chao Yu 已提交
1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
		char ctx[4];
	} desc;
	int err;

	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));

	desc.shash.tfm = sbi->s_chksum_driver;
	*(u32 *)desc.ctx = crc;

	err = crypto_shash_update(&desc.shash, address, length);
	BUG_ON(err);

	return *(u32 *)desc.ctx;
}

C
Chao Yu 已提交
1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
			   unsigned int length)
{
	return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length);
}

static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
				  void *buf, size_t buf_size)
{
	return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
}

static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc,
			      const void *address, unsigned int length)
{
	return __f2fs_crc32(sbi, crc, address, length);
}

1742 1743 1744 1745 1746 1747 1748 1749 1750 1751
static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
	return container_of(inode, struct f2fs_inode_info, vfs_inode);
}

static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb)
{
	return sb->s_fs_info;
}

1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763
static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode)
{
	return F2FS_SB(inode->i_sb);
}

static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
{
	return F2FS_I_SB(mapping->host);
}

static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
{
J
Jaegeuk Kim 已提交
1764
	return F2FS_M_SB(page_file_mapping(page));
1765 1766
}

1767 1768 1769 1770 1771 1772 1773 1774 1775 1776
static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
{
	return (struct f2fs_super_block *)(sbi->raw_super);
}

static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
{
	return (struct f2fs_checkpoint *)(sbi->ckpt);
}

1777 1778 1779 1780 1781
static inline struct f2fs_node *F2FS_NODE(struct page *page)
{
	return (struct f2fs_node *)page_address(page);
}

1782 1783 1784 1785 1786
static inline struct f2fs_inode *F2FS_INODE(struct page *page)
{
	return &((struct f2fs_node *)page_address(page))->i;
}

1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811
static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
{
	return (struct f2fs_nm_info *)(sbi->nm_info);
}

static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi)
{
	return (struct f2fs_sm_info *)(sbi->sm_info);
}

static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi)
{
	return (struct sit_info *)(SM_I(sbi)->sit_info);
}

static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi)
{
	return (struct free_segmap_info *)(SM_I(sbi)->free_info);
}

static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi)
{
	return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info);
}

G
Gu Zheng 已提交
1812 1813 1814 1815 1816
static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->meta_inode->i_mapping;
}

1817 1818 1819 1820 1821
static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->node_inode->i_mapping;
}

1822 1823
static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
1824
	return test_bit(type, &sbi->s_flag);
1825 1826 1827
}

static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1828
{
1829
	set_bit(type, &sbi->s_flag);
1830 1831
}

1832
static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1833
{
1834
	clear_bit(type, &sbi->s_flag);
1835 1836
}

1837 1838 1839 1840 1841
static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
{
	return le64_to_cpu(cp->checkpoint_ver);
}

J
Jaegeuk Kim 已提交
1842 1843 1844 1845 1846 1847 1848
static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type)
{
	if (type < F2FS_MAX_QUOTAS)
		return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]);
	return 0;
}

1849 1850 1851 1852 1853 1854
static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
{
	size_t crc_offset = le32_to_cpu(cp->checksum_offset);
	return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
}

1855
static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1856 1857
{
	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1858

1859 1860 1861
	return ckpt_flags & f;
}

1862
static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1863
{
1864 1865 1866 1867 1868 1869 1870 1871
	return __is_set_ckpt_flags(F2FS_CKPT(sbi), f);
}

static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
	unsigned int ckpt_flags;

	ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1872 1873 1874 1875
	ckpt_flags |= f;
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1876
static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1877
{
1878 1879 1880
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1881
	__set_ckpt_flags(F2FS_CKPT(sbi), f);
1882
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1883 1884 1885 1886 1887 1888 1889
}

static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
	unsigned int ckpt_flags;

	ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1890 1891 1892 1893
	ckpt_flags &= (~f);
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1894 1895
static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
1896 1897 1898
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1899
	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
1900
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1901 1902
}

1903 1904
static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
1905
	unsigned long flags;
1906
	unsigned char *nat_bits;
1907

1908 1909 1910 1911 1912
	/*
	 * In order to re-enable nat_bits we need to call fsck.f2fs by
	 * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
	 * so let's rely on regular fsck or unclean shutdown.
	 */
1913 1914

	if (lock)
1915
		spin_lock_irqsave(&sbi->cp_lock, flags);
1916
	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
1917
	nat_bits = NM_I(sbi)->nat_bits;
1918 1919
	NM_I(sbi)->nat_bits = NULL;
	if (lock)
1920
		spin_unlock_irqrestore(&sbi->cp_lock, flags);
1921 1922

	kvfree(nat_bits);
1923 1924 1925 1926 1927 1928 1929
}

static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
					struct cp_control *cpc)
{
	bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);

1930
	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
1931 1932
}

1933
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
1934
{
1935
	down_read(&sbi->cp_rwsem);
1936 1937
}

1938 1939 1940 1941 1942
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
	return down_read_trylock(&sbi->cp_rwsem);
}

1943
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
1944
{
1945
	up_read(&sbi->cp_rwsem);
1946 1947
}

1948
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
1949
{
1950
	down_write(&sbi->cp_rwsem);
1951 1952
}

1953
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
1954
{
1955
	up_write(&sbi->cp_rwsem);
1956 1957
}

1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
{
	int reason = CP_SYNC;

	if (test_opt(sbi, FASTBOOT))
		reason = CP_FASTBOOT;
	if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
		reason = CP_UMOUNT;
	return reason;
}

static inline bool __remain_node_summaries(int reason)
{
1971
	return (reason & (CP_UMOUNT | CP_FASTBOOT));
1972 1973 1974 1975
}

static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
{
1976 1977
	return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
			is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
1978 1979
}

1980 1981 1982 1983 1984
/*
 * Check whether the inode has blocks or not
 */
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
1985 1986
	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;

1987
	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
1988 1989
}

1990 1991 1992 1993 1994
static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
	return ofs == XATTR_NODE_OFFSET;
}

1995
static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
1996
					struct inode *inode, bool cap)
1997
{
1998 1999
	if (!inode)
		return true;
2000 2001
	if (!test_opt(sbi, RESERVE_ROOT))
		return false;
2002 2003
	if (IS_NOQUOTA(inode))
		return true;
2004
	if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
2005
		return true;
2006 2007
	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
					in_group_p(F2FS_OPTION(sbi).s_resgid))
2008
		return true;
2009
	if (cap && capable(CAP_SYS_RESOURCE))
2010
		return true;
2011 2012 2013
	return false;
}

C
Chao Yu 已提交
2014 2015
static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
2016
				 struct inode *inode, blkcnt_t *count)
2017
{
C
Chao Yu 已提交
2018
	blkcnt_t diff = 0, release = 0;
2019
	block_t avail_user_block_count;
C
Chao Yu 已提交
2020 2021 2022 2023 2024
	int ret;

	ret = dquot_reserve_block(inode, *count);
	if (ret)
		return ret;
2025

2026
	if (time_to_inject(sbi, FAULT_BLOCK)) {
2027
		f2fs_show_injection_info(sbi, FAULT_BLOCK);
C
Chao Yu 已提交
2028
		release = *count;
2029
		goto release_quota;
2030
	}
2031

2032 2033 2034 2035 2036 2037
	/*
	 * let's increase this in prior to actual block count change in order
	 * for f2fs_sync_file to avoid data races when deciding checkpoint.
	 */
	percpu_counter_add(&sbi->alloc_valid_block_count, (*count));

2038 2039
	spin_lock(&sbi->stat_lock);
	sbi->total_valid_block_count += (block_t)(*count);
2040 2041
	avail_user_block_count = sbi->user_block_count -
					sbi->current_reserved_blocks;
2042

2043
	if (!__allow_reserved_blocks(sbi, inode, true))
2044
		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
2045 2046 2047 2048 2049 2050
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
		if (avail_user_block_count > sbi->unusable_block_count)
			avail_user_block_count -= sbi->unusable_block_count;
		else
			avail_user_block_count = 0;
	}
2051 2052
	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
		diff = sbi->total_valid_block_count - avail_user_block_count;
2053 2054
		if (diff > *count)
			diff = *count;
2055
		*count -= diff;
C
Chao Yu 已提交
2056
		release = diff;
2057
		sbi->total_valid_block_count -= diff;
2058 2059
		if (!*count) {
			spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2060
			goto enospc;
2061
		}
2062 2063
	}
	spin_unlock(&sbi->stat_lock);
2064

2065 2066
	if (unlikely(release)) {
		percpu_counter_sub(&sbi->alloc_valid_block_count, release);
C
Chao Yu 已提交
2067
		dquot_release_reservation_block(inode, release);
2068
	}
C
Chao Yu 已提交
2069 2070 2071 2072
	f2fs_i_blocks_write(inode, *count, true, true);
	return 0;

enospc:
2073
	percpu_counter_sub(&sbi->alloc_valid_block_count, release);
2074
release_quota:
C
Chao Yu 已提交
2075 2076
	dquot_release_reservation_block(inode, release);
	return -ENOSPC;
2077 2078
}

2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092
__printf(2, 3)
void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...);

#define f2fs_err(sbi, fmt, ...)						\
	f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__)
#define f2fs_warn(sbi, fmt, ...)					\
	f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__)
#define f2fs_notice(sbi, fmt, ...)					\
	f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__)
#define f2fs_info(sbi, fmt, ...)					\
	f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__)
#define f2fs_debug(sbi, fmt, ...)					\
	f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__)

2093
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
2094
						struct inode *inode,
2095
						block_t count)
2096
{
2097 2098
	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;

2099
	spin_lock(&sbi->stat_lock);
2100
	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
2101
	sbi->total_valid_block_count -= (block_t)count;
2102 2103 2104 2105
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
					sbi->current_reserved_blocks + count);
2106
	spin_unlock(&sbi->stat_lock);
2107
	if (unlikely(inode->i_blocks < sectors)) {
2108 2109 2110 2111
		f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu",
			  inode->i_ino,
			  (unsigned long long)inode->i_blocks,
			  (unsigned long long)sectors);
2112 2113 2114
		set_sbi_flag(sbi, SBI_NEED_FSCK);
		return;
	}
C
Chao Yu 已提交
2115
	f2fs_i_blocks_write(inode, count, false, true);
2116 2117 2118 2119
}

static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
2120
	atomic_inc(&sbi->nr_pages[count_type]);
2121

C
Chao Yu 已提交
2122 2123 2124 2125 2126 2127
	if (count_type == F2FS_DIRTY_DENTS ||
			count_type == F2FS_DIRTY_NODES ||
			count_type == F2FS_DIRTY_META ||
			count_type == F2FS_DIRTY_QDATA ||
			count_type == F2FS_DIRTY_IMETA)
		set_sbi_flag(sbi, SBI_IS_DIRTY);
2128 2129
}

2130
static inline void inode_inc_dirty_pages(struct inode *inode)
2131
{
2132
	atomic_inc(&F2FS_I(inode)->dirty_pages);
2133 2134
	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
2135 2136
	if (IS_NOQUOTA(inode))
		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
2137 2138 2139 2140
}

static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
2141
	atomic_dec(&sbi->nr_pages[count_type]);
2142 2143
}

2144
static inline void inode_dec_dirty_pages(struct inode *inode)
2145
{
2146 2147
	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
			!S_ISLNK(inode->i_mode))
2148 2149
		return;

2150
	atomic_dec(&F2FS_I(inode)->dirty_pages);
2151 2152
	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
2153 2154
	if (IS_NOQUOTA(inode))
		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
2155 2156
}

2157
static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
2158
{
2159
	return atomic_read(&sbi->nr_pages[count_type]);
2160 2161
}

2162
static inline int get_dirty_pages(struct inode *inode)
2163
{
2164
	return atomic_read(&F2FS_I(inode)->dirty_pages);
2165 2166
}

2167 2168
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
2169
	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
2170 2171 2172 2173
	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
						sbi->log_blocks_per_seg;

	return segs / sbi->segs_per_sec;
2174 2175
}

2176 2177
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
2178
	return sbi->total_valid_block_count;
2179 2180
}

2181 2182 2183 2184 2185
static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
{
	return sbi->discard_blks;
}

2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198
static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);

	/* return NAT or SIT bitmap */
	if (flag == NAT_BITMAP)
		return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
	else if (flag == SIT_BITMAP)
		return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);

	return 0;
}

W
Wanpeng Li 已提交
2199 2200 2201 2202 2203
static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
	return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

2204 2205 2206
static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
C
Changman Lee 已提交
2207 2208
	int offset;

C
Chao Yu 已提交
2209 2210 2211
	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
		offset = (flag == SIT_BITMAP) ?
			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
2212 2213 2214 2215 2216
		/*
		 * if large_nat_bitmap feature is enabled, leave checksum
		 * protection for all nat/sit bitmaps.
		 */
		return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32);
C
Chao Yu 已提交
2217 2218
	}

W
Wanpeng Li 已提交
2219
	if (__cp_payload(sbi) > 0) {
C
Changman Lee 已提交
2220 2221 2222
		if (flag == NAT_BITMAP)
			return &ckpt->sit_nat_version_bitmap;
		else
J
Jaegeuk Kim 已提交
2223
			return (unsigned char *)ckpt + F2FS_BLKSIZE;
C
Changman Lee 已提交
2224 2225
	} else {
		offset = (flag == NAT_BITMAP) ?
2226
			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
C
Changman Lee 已提交
2227 2228
		return &ckpt->sit_nat_version_bitmap + offset;
	}
2229 2230 2231 2232
}

static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
2233
	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
2234

2235
	if (sbi->cur_cp_pack == 2)
2236
		start_addr += sbi->blocks_per_seg;
2237 2238
	return start_addr;
}
2239

2240 2241 2242
static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
{
	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
2243

2244 2245
	if (sbi->cur_cp_pack == 1)
		start_addr += sbi->blocks_per_seg;
2246 2247 2248
	return start_addr;
}

2249 2250 2251 2252 2253
static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
{
	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
}

2254 2255 2256 2257 2258
static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
{
	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}

C
Chao Yu 已提交
2259
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
2260
					struct inode *inode, bool is_inode)
2261 2262
{
	block_t	valid_block_count;
2263
	unsigned int valid_node_count, user_block_count;
2264
	int err;
C
Chao Yu 已提交
2265

2266 2267 2268 2269 2270 2271 2272 2273 2274 2275
	if (is_inode) {
		if (inode) {
			err = dquot_alloc_inode(inode);
			if (err)
				return err;
		}
	} else {
		err = dquot_reserve_block(inode, 1);
		if (err)
			return err;
C
Chao Yu 已提交
2276
	}
2277

2278
	if (time_to_inject(sbi, FAULT_BLOCK)) {
2279
		f2fs_show_injection_info(sbi, FAULT_BLOCK);
2280 2281 2282
		goto enospc;
	}

2283 2284
	spin_lock(&sbi->stat_lock);

2285 2286 2287
	valid_block_count = sbi->total_valid_block_count +
					sbi->current_reserved_blocks + 1;

2288
	if (!__allow_reserved_blocks(sbi, inode, false))
2289
		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
2290
	user_block_count = sbi->user_block_count;
D
Daniel Rosenberg 已提交
2291
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
2292
		user_block_count -= sbi->unusable_block_count;
2293

2294
	if (unlikely(valid_block_count > user_block_count)) {
2295
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2296
		goto enospc;
2297 2298
	}

2299
	valid_node_count = sbi->total_valid_node_count + 1;
2300
	if (unlikely(valid_node_count > sbi->total_node_count)) {
2301
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2302
		goto enospc;
2303 2304
	}

2305 2306
	sbi->total_valid_node_count++;
	sbi->total_valid_block_count++;
2307 2308
	spin_unlock(&sbi->stat_lock);

2309 2310 2311 2312
	if (inode) {
		if (is_inode)
			f2fs_mark_inode_dirty_sync(inode, true);
		else
C
Chao Yu 已提交
2313
			f2fs_i_blocks_write(inode, 1, true, true);
2314
	}
2315

2316
	percpu_counter_inc(&sbi->alloc_valid_block_count);
C
Chao Yu 已提交
2317 2318 2319
	return 0;

enospc:
2320 2321 2322 2323
	if (is_inode) {
		if (inode)
			dquot_free_inode(inode);
	} else {
C
Chao Yu 已提交
2324
		dquot_release_reservation_block(inode, 1);
2325
	}
C
Chao Yu 已提交
2326
	return -ENOSPC;
2327 2328 2329
}

static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
2330
					struct inode *inode, bool is_inode)
2331 2332 2333
{
	spin_lock(&sbi->stat_lock);

2334 2335
	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
2336

2337 2338
	sbi->total_valid_node_count--;
	sbi->total_valid_block_count--;
2339 2340 2341
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks++;
2342 2343

	spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2344

2345
	if (is_inode) {
2346
		dquot_free_inode(inode);
2347 2348
	} else {
		if (unlikely(inode->i_blocks == 0)) {
2349
			f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu",
2350 2351
				  inode->i_ino,
				  (unsigned long long)inode->i_blocks);
2352 2353 2354
			set_sbi_flag(sbi, SBI_NEED_FSCK);
			return;
		}
C
Chao Yu 已提交
2355
		f2fs_i_blocks_write(inode, 1, false, true);
2356
	}
2357 2358 2359 2360
}

static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
{
2361
	return sbi->total_valid_node_count;
2362 2363 2364 2365
}

static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
2366
	percpu_counter_inc(&sbi->total_valid_inode_count);
2367 2368
}

2369
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
2370
{
2371
	percpu_counter_dec(&sbi->total_valid_inode_count);
2372 2373
}

2374
static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
2375
{
2376
	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
2377 2378
}

2379 2380 2381
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
						pgoff_t index, bool for_write)
{
2382
	struct page *page;
2383

2384 2385 2386 2387 2388 2389 2390 2391
	if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
		if (!for_write)
			page = find_get_page_flags(mapping, index,
							FGP_LOCK | FGP_ACCESSED);
		else
			page = find_lock_page(mapping, index);
		if (page)
			return page;
2392

2393
		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
2394 2395
			f2fs_show_injection_info(F2FS_M_SB(mapping),
							FAULT_PAGE_ALLOC);
2396 2397
			return NULL;
		}
2398
	}
2399

2400 2401 2402 2403 2404
	if (!for_write)
		return grab_cache_page(mapping, index);
	return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
}

C
Chao Yu 已提交
2405 2406 2407 2408 2409
static inline struct page *f2fs_pagecache_get_page(
				struct address_space *mapping, pgoff_t index,
				int fgp_flags, gfp_t gfp_mask)
{
	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
2410
		f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
C
Chao Yu 已提交
2411 2412
		return NULL;
	}
2413

C
Chao Yu 已提交
2414 2415 2416
	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}

2417 2418 2419 2420 2421 2422 2423 2424 2425 2426
static inline void f2fs_copy_page(struct page *src, struct page *dst)
{
	char *src_kaddr = kmap(src);
	char *dst_kaddr = kmap(dst);

	memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
	kunmap(dst);
	kunmap(src);
}

2427 2428
static inline void f2fs_put_page(struct page *page, int unlock)
{
2429
	if (!page)
2430 2431 2432
		return;

	if (unlock) {
2433
		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
2434 2435
		unlock_page(page);
	}
2436
	put_page(page);
2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449
}

static inline void f2fs_put_dnode(struct dnode_of_data *dn)
{
	if (dn->node_page)
		f2fs_put_page(dn->node_page, 1);
	if (dn->inode_page && dn->node_page != dn->inode_page)
		f2fs_put_page(dn->inode_page, 0);
	dn->node_page = NULL;
	dn->inode_page = NULL;
}

static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
2450
					size_t size)
2451
{
2452
	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
2453 2454
}

2455 2456 2457 2458 2459
static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
						gfp_t flags)
{
	void *entry;

2460 2461 2462
	entry = kmem_cache_alloc(cachep, flags);
	if (!entry)
		entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
2463 2464 2465
	return entry;
}

2466 2467
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
2468
	if (sbi->gc_mode == GC_URGENT_HIGH)
2469 2470
		return true;

2471 2472
	if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
		get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
2473 2474
		get_pages(sbi, F2FS_WB_CP_DATA) ||
		get_pages(sbi, F2FS_DIO_READ) ||
2475
		get_pages(sbi, F2FS_DIO_WRITE))
2476
		return false;
2477

2478
	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
2479 2480 2481 2482 2483 2484 2485
			atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
		return false;

	if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
			atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
		return false;

2486 2487 2488 2489
	if (sbi->gc_mode == GC_URGENT_LOW &&
			(type == DISCARD_TIME || type == GC_TIME))
		return true;

2490 2491 2492
	return f2fs_time_over(sbi, type);
}

2493 2494 2495 2496 2497 2498 2499
static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
				unsigned long index, void *item)
{
	while (radix_tree_insert(root, index, item))
		cond_resched();
}

2500 2501 2502 2503
#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)

static inline bool IS_INODE(struct page *page)
{
2504
	struct f2fs_node *p = F2FS_NODE(page);
2505

2506 2507 2508
	return RAW_IS_INODE(p);
}

2509 2510 2511 2512 2513 2514
static inline int offset_in_addr(struct f2fs_inode *i)
{
	return (i->i_inline & F2FS_EXTRA_ATTR) ?
			(le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0;
}

2515 2516 2517 2518 2519
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}

2520
static inline int f2fs_has_extra_attr(struct inode *inode);
2521
static inline block_t data_blkaddr(struct inode *inode,
2522
			struct page *node_page, unsigned int offset)
2523 2524 2525
{
	struct f2fs_node *raw_node;
	__le32 *addr_array;
2526 2527
	int base = 0;
	bool is_inode = IS_INODE(node_page);
2528

2529
	raw_node = F2FS_NODE(node_page);
2530

2531 2532
	if (is_inode) {
		if (!inode)
C
Chao Yu 已提交
2533
			/* from GC path only */
2534
			base = offset_in_addr(&raw_node->i);
2535 2536
		else if (f2fs_has_extra_attr(inode))
			base = get_extra_isize(inode);
2537 2538
	}

2539
	addr_array = blkaddr_in_node(raw_node);
2540
	return le32_to_cpu(addr_array[base + offset]);
2541 2542
}

2543 2544 2545 2546 2547
static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn)
{
	return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node);
}

2548 2549 2550 2551 2552 2553 2554 2555 2556
static inline int f2fs_test_bit(unsigned int nr, char *addr)
{
	int mask;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	return mask & *addr;
}

2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574
static inline void f2fs_set_bit(unsigned int nr, char *addr)
{
	int mask;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	*addr |= mask;
}

static inline void f2fs_clear_bit(unsigned int nr, char *addr)
{
	int mask;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	*addr &= ~mask;
}

2575
static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586
{
	int mask;
	int ret;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	ret = mask & *addr;
	*addr |= mask;
	return ret;
}

2587
static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598
{
	int mask;
	int ret;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	ret = mask & *addr;
	*addr &= ~mask;
	return ret;
}

2599 2600 2601 2602 2603 2604 2605 2606 2607
static inline void f2fs_change_bit(unsigned int nr, char *addr)
{
	int mask;

	addr += (nr >> 3);
	mask = 1 << (7 - (nr & 0x07));
	*addr ^= mask;
}

2608
/*
2609
 * On-disk inode flags (f2fs_inode::i_flags)
2610
 */
C
Chao Yu 已提交
2611
#define F2FS_COMPR_FL			0x00000004 /* Compress file */
2612 2613 2614 2615 2616
#define F2FS_SYNC_FL			0x00000008 /* Synchronous updates */
#define F2FS_IMMUTABLE_FL		0x00000010 /* Immutable file */
#define F2FS_APPEND_FL			0x00000020 /* writes to file may only append */
#define F2FS_NODUMP_FL			0x00000040 /* do not dump file */
#define F2FS_NOATIME_FL			0x00000080 /* do not update atime */
C
Chao Yu 已提交
2617
#define F2FS_NOCOMP_FL			0x00000400 /* Don't compress */
2618 2619 2620
#define F2FS_INDEX_FL			0x00001000 /* hash-indexed directory */
#define F2FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
#define F2FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
2621
#define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
2622 2623

/* Flags that should be inherited by new inodes from their parent. */
2624
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
2625
			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
C
Chao Yu 已提交
2626
			   F2FS_CASEFOLD_FL | F2FS_COMPR_FL | F2FS_NOCOMP_FL)
2627 2628

/* Flags that are appropriate for regular files (all but dir-specific ones). */
2629 2630
#define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
				F2FS_CASEFOLD_FL))
2631 2632 2633

/* Flags that are appropriate for non-directories/regular files. */
#define F2FS_OTHER_FLMASK	(F2FS_NODUMP_FL | F2FS_NOATIME_FL)
C
Chao Yu 已提交
2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644

static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & F2FS_REG_FLMASK;
	else
		return flags & F2FS_OTHER_FLMASK;
}

2645 2646 2647 2648 2649 2650 2651
static inline void __mark_inode_dirty_flag(struct inode *inode,
						int flag, bool set)
{
	switch (flag) {
	case FI_INLINE_XATTR:
	case FI_INLINE_DATA:
	case FI_INLINE_DENTRY:
2652
	case FI_NEW_INODE:
2653 2654
		if (set)
			return;
2655
		fallthrough;
2656 2657
	case FI_DATA_EXIST:
	case FI_INLINE_DOTS:
2658
	case FI_PIN_FILE:
2659
		f2fs_mark_inode_dirty_sync(inode, true);
2660 2661 2662
	}
}

2663
static inline void set_inode_flag(struct inode *inode, int flag)
2664
{
2665
	set_bit(flag, F2FS_I(inode)->flags);
2666
	__mark_inode_dirty_flag(inode, flag, true);
2667 2668
}

2669
static inline int is_inode_flag_set(struct inode *inode, int flag)
2670
{
2671
	return test_bit(flag, F2FS_I(inode)->flags);
2672 2673
}

2674
static inline void clear_inode_flag(struct inode *inode, int flag)
2675
{
2676
	clear_bit(flag, F2FS_I(inode)->flags);
2677
	__mark_inode_dirty_flag(inode, flag, false);
2678 2679
}

E
Eric Biggers 已提交
2680 2681 2682 2683 2684 2685
static inline bool f2fs_verity_in_progress(struct inode *inode)
{
	return IS_ENABLED(CONFIG_FS_VERITY) &&
	       is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS);
}

2686
static inline void set_acl_inode(struct inode *inode, umode_t mode)
2687
{
2688 2689
	F2FS_I(inode)->i_acl_mode = mode;
	set_inode_flag(inode, FI_ACL_MODE);
2690
	f2fs_mark_inode_dirty_sync(inode, false);
2691 2692
}

2693
static inline void f2fs_i_links_write(struct inode *inode, bool inc)
2694
{
2695 2696 2697 2698
	if (inc)
		inc_nlink(inode);
	else
		drop_nlink(inode);
2699
	f2fs_mark_inode_dirty_sync(inode, true);
2700 2701
}

2702
static inline void f2fs_i_blocks_write(struct inode *inode,
C
Chao Yu 已提交
2703
					block_t diff, bool add, bool claim)
2704
{
2705 2706 2707
	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

C
Chao Yu 已提交
2708 2709 2710 2711 2712 2713 2714 2715 2716 2717
	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
	if (add) {
		if (claim)
			dquot_claim_block(inode, diff);
		else
			dquot_alloc_block_nofail(inode, diff);
	} else {
		dquot_free_block(inode, diff);
	}

2718
	f2fs_mark_inode_dirty_sync(inode, true);
2719 2720
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2721 2722
}

2723 2724
static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
2725 2726 2727
	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

2728 2729 2730 2731
	if (i_size_read(inode) == i_size)
		return;

	i_size_write(inode, i_size);
2732
	f2fs_mark_inode_dirty_sync(inode, true);
2733 2734
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2735 2736
}

2737
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
2738
{
2739
	F2FS_I(inode)->i_current_depth = depth;
2740
	f2fs_mark_inode_dirty_sync(inode, true);
2741 2742
}

2743 2744 2745
static inline void f2fs_i_gc_failures_write(struct inode *inode,
					unsigned int count)
{
2746
	F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
2747 2748 2749
	f2fs_mark_inode_dirty_sync(inode, true);
}

2750
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
J
Jaegeuk Kim 已提交
2751
{
2752
	F2FS_I(inode)->i_xattr_nid = xnid;
2753
	f2fs_mark_inode_dirty_sync(inode, true);
2754 2755 2756 2757 2758
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
	F2FS_I(inode)->i_pino = pino;
2759
	f2fs_mark_inode_dirty_sync(inode, true);
2760 2761
}

2762
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2763
{
2764 2765
	struct f2fs_inode_info *fi = F2FS_I(inode);

J
Jaegeuk Kim 已提交
2766
	if (ri->i_inline & F2FS_INLINE_XATTR)
2767
		set_bit(FI_INLINE_XATTR, fi->flags);
2768
	if (ri->i_inline & F2FS_INLINE_DATA)
2769
		set_bit(FI_INLINE_DATA, fi->flags);
2770
	if (ri->i_inline & F2FS_INLINE_DENTRY)
2771
		set_bit(FI_INLINE_DENTRY, fi->flags);
2772
	if (ri->i_inline & F2FS_DATA_EXIST)
2773
		set_bit(FI_DATA_EXIST, fi->flags);
2774
	if (ri->i_inline & F2FS_INLINE_DOTS)
2775
		set_bit(FI_INLINE_DOTS, fi->flags);
2776
	if (ri->i_inline & F2FS_EXTRA_ATTR)
2777
		set_bit(FI_EXTRA_ATTR, fi->flags);
2778
	if (ri->i_inline & F2FS_PIN_FILE)
2779
		set_bit(FI_PIN_FILE, fi->flags);
J
Jaegeuk Kim 已提交
2780 2781
}

2782
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2783 2784 2785
{
	ri->i_inline = 0;

2786
	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
J
Jaegeuk Kim 已提交
2787
		ri->i_inline |= F2FS_INLINE_XATTR;
2788
	if (is_inode_flag_set(inode, FI_INLINE_DATA))
2789
		ri->i_inline |= F2FS_INLINE_DATA;
2790
	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
2791
		ri->i_inline |= F2FS_INLINE_DENTRY;
2792
	if (is_inode_flag_set(inode, FI_DATA_EXIST))
2793
		ri->i_inline |= F2FS_DATA_EXIST;
2794
	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
2795
		ri->i_inline |= F2FS_INLINE_DOTS;
2796 2797
	if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
		ri->i_inline |= F2FS_EXTRA_ATTR;
2798 2799
	if (is_inode_flag_set(inode, FI_PIN_FILE))
		ri->i_inline |= F2FS_PIN_FILE;
2800 2801 2802 2803 2804
}

static inline int f2fs_has_extra_attr(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_EXTRA_ATTR);
J
Jaegeuk Kim 已提交
2805 2806
}

2807 2808
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
2809
	return is_inode_flag_set(inode, FI_INLINE_XATTR);
2810 2811
}

C
Chao Yu 已提交
2812 2813 2814 2815 2816 2817
static inline int f2fs_compressed_file(struct inode *inode)
{
	return S_ISREG(inode->i_mode) &&
		is_inode_flag_set(inode, FI_COMPRESSED_FILE);
}

2818
static inline unsigned int addrs_per_inode(struct inode *inode)
2819
{
2820 2821
	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
				get_inline_xattr_addrs(inode);
C
Chao Yu 已提交
2822 2823 2824 2825

	if (!f2fs_compressed_file(inode))
		return addrs;
	return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
2826 2827 2828 2829
}

static inline unsigned int addrs_per_block(struct inode *inode)
{
C
Chao Yu 已提交
2830 2831 2832
	if (!f2fs_compressed_file(inode))
		return DEF_ADDRS_PER_BLOCK;
	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
2833 2834
}

C
Chao Yu 已提交
2835
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
J
Jaegeuk Kim 已提交
2836
{
2837
	struct f2fs_inode *ri = F2FS_INODE(page);
2838

J
Jaegeuk Kim 已提交
2839
	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
2840
					get_inline_xattr_addrs(inode)]);
J
Jaegeuk Kim 已提交
2841 2842 2843 2844
}

static inline int inline_xattr_size(struct inode *inode)
{
2845 2846 2847
	if (f2fs_has_inline_xattr(inode))
		return get_inline_xattr_addrs(inode) * sizeof(__le32);
	return 0;
J
Jaegeuk Kim 已提交
2848 2849
}

2850 2851
static inline int f2fs_has_inline_data(struct inode *inode)
{
2852
	return is_inode_flag_set(inode, FI_INLINE_DATA);
2853 2854
}

2855 2856
static inline int f2fs_exist_data(struct inode *inode)
{
2857
	return is_inode_flag_set(inode, FI_DATA_EXIST);
2858 2859
}

2860 2861
static inline int f2fs_has_inline_dots(struct inode *inode)
{
2862
	return is_inode_flag_set(inode, FI_INLINE_DOTS);
2863 2864
}

C
Chao Yu 已提交
2865 2866 2867 2868 2869
static inline int f2fs_is_mmap_file(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_MMAP_FILE);
}

2870 2871 2872 2873 2874
static inline bool f2fs_is_pinned_file(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_PIN_FILE);
}

J
Jaegeuk Kim 已提交
2875 2876
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
2877
	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
J
Jaegeuk Kim 已提交
2878 2879
}

C
Chao Yu 已提交
2880 2881 2882 2883 2884
static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}

2885 2886
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
2887
	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
2888 2889
}

2890 2891
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
2892
	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
2893 2894
}

2895 2896
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
2897
	return is_inode_flag_set(inode, FI_DROP_CACHE);
2898 2899
}

C
Chao Yu 已提交
2900
static inline void *inline_data_addr(struct inode *inode, struct page *page)
2901
{
2902
	struct f2fs_inode *ri = F2FS_INODE(page);
2903
	int extra_size = get_extra_isize(inode);
2904

2905
	return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
2906 2907
}

2908 2909
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
2910
	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
2911 2912
}

2913 2914 2915 2916 2917 2918 2919 2920
static inline int is_file(struct inode *inode, int type)
{
	return F2FS_I(inode)->i_advise & type;
}

static inline void set_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise |= type;
2921
	f2fs_mark_inode_dirty_sync(inode, true);
2922 2923 2924 2925 2926
}

static inline void clear_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise &= ~type;
2927
	f2fs_mark_inode_dirty_sync(inode, true);
2928 2929
}

2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943
static inline bool f2fs_is_time_consistent(struct inode *inode)
{
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
						&F2FS_I(inode)->i_crtime))
		return false;
	return true;
}

2944 2945
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
2946 2947
	bool ret;

2948 2949 2950 2951 2952 2953 2954 2955 2956 2957
	if (dsync) {
		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

		spin_lock(&sbi->inode_lock[DIRTY_META]);
		ret = list_empty(&F2FS_I(inode)->gdirty_list);
		spin_unlock(&sbi->inode_lock[DIRTY_META]);
		return ret;
	}
	if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
			file_keep_isize(inode) ||
2958
			i_size_read(inode) & ~PAGE_MASK)
2959
		return false;
2960

2961
	if (!f2fs_is_time_consistent(inode))
2962 2963
		return false;

2964
	spin_lock(&F2FS_I(inode)->i_size_lock);
2965
	ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
2966
	spin_unlock(&F2FS_I(inode)->i_size_lock);
2967 2968

	return ret;
2969 2970
}

2971
static inline bool f2fs_readonly(struct super_block *sb)
J
Jaegeuk Kim 已提交
2972
{
2973
	return sb_rdonly(sb);
J
Jaegeuk Kim 已提交
2974 2975
}

2976 2977
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
2978
	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
2979 2980
}

E
Eric Biggers 已提交
2981
static inline bool is_dot_dotdot(const u8 *name, size_t len)
2982
{
E
Eric Biggers 已提交
2983
	if (len == 1 && name[0] == '.')
2984 2985
		return true;

E
Eric Biggers 已提交
2986
	if (len == 2 && name[0] == '.' && name[1] == '.')
2987 2988 2989 2990 2991
		return true;

	return false;
}

J
Jaegeuk Kim 已提交
2992 2993
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
2994 2995 2996
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	if (!test_opt(sbi, EXTENT_CACHE) ||
C
Chao Yu 已提交
2997 2998
			is_inode_flag_set(inode, FI_NO_EXTENT) ||
			is_inode_flag_set(inode, FI_COMPRESSED_FILE))
J
Jaegeuk Kim 已提交
2999 3000
		return false;

3001 3002 3003 3004 3005 3006 3007
	/*
	 * for recovered files during mount do not create extents
	 * if shrinker is not registered.
	 */
	if (list_empty(&sbi->s_list))
		return false;

A
Al Viro 已提交
3008
	return S_ISREG(inode->i_mode);
J
Jaegeuk Kim 已提交
3009 3010
}

3011 3012
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
3013
{
3014
	if (time_to_inject(sbi, FAULT_KMALLOC)) {
3015
		f2fs_show_injection_info(sbi, FAULT_KMALLOC);
J
Jaegeuk Kim 已提交
3016
		return NULL;
3017
	}
3018

3019
	return kmalloc(size, flags);
3020 3021
}

C
Chao Yu 已提交
3022 3023 3024 3025 3026 3027
static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO);
}

C
Chao Yu 已提交
3028 3029 3030 3031
static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	if (time_to_inject(sbi, FAULT_KVMALLOC)) {
3032
		f2fs_show_injection_info(sbi, FAULT_KVMALLOC);
C
Chao Yu 已提交
3033 3034
		return NULL;
	}
3035

C
Chao Yu 已提交
3036 3037 3038 3039 3040 3041 3042 3043 3044
	return kvmalloc(size, flags);
}

static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO);
}

3045
static inline int get_extra_isize(struct inode *inode)
C
Chao Yu 已提交
3046
{
3047
	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
C
Chao Yu 已提交
3048 3049
}

C
Chao Yu 已提交
3050 3051 3052 3053 3054
static inline int get_inline_xattr_addrs(struct inode *inode)
{
	return F2FS_I(inode)->i_inline_xattr_size;
}

C
Chao Yu 已提交
3055
#define f2fs_get_inode_mode(i) \
3056
	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
3057 3058
	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))

3059 3060 3061 3062
#define F2FS_TOTAL_EXTRA_ATTR_SIZE			\
	(offsetof(struct f2fs_inode, i_extra_end) -	\
	offsetof(struct f2fs_inode, i_extra_isize))	\

C
Chao Yu 已提交
3063 3064
#define F2FS_OLD_ATTRIBUTE_SIZE	(offsetof(struct f2fs_inode, i_addr))
#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field)		\
S
Sheng Yong 已提交
3065
		((offsetof(typeof(*(f2fs_inode)), field) +	\
C
Chao Yu 已提交
3066
		sizeof((f2fs_inode)->field))			\
S
Sheng Yong 已提交
3067
		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
C
Chao Yu 已提交
3068

3069 3070 3071 3072 3073
#define DEFAULT_IOSTAT_PERIOD_MS	3000
#define MIN_IOSTAT_PERIOD_MS		100
/* maximum period of iostat tracing is 1 day */
#define MAX_IOSTAT_PERIOD_MS		8640000

C
Chao Yu 已提交
3074 3075 3076 3077 3078
static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
{
	int i;

	spin_lock(&sbi->iostat_lock);
3079
	for (i = 0; i < NR_IO_TYPE; i++) {
C
Chao Yu 已提交
3080 3081
		sbi->rw_iostat[i] = 0;
		sbi->prev_rw_iostat[i] = 0;
3082
	}
C
Chao Yu 已提交
3083 3084 3085
	spin_unlock(&sbi->iostat_lock);
}

3086 3087
extern void f2fs_record_iostat(struct f2fs_sb_info *sbi);

C
Chao Yu 已提交
3088 3089 3090 3091 3092 3093
static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
			enum iostat_type type, unsigned long long io_bytes)
{
	if (!sbi->iostat_enable)
		return;
	spin_lock(&sbi->iostat_lock);
C
Chao Yu 已提交
3094
	sbi->rw_iostat[type] += io_bytes;
C
Chao Yu 已提交
3095 3096

	if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
C
Chao Yu 已提交
3097 3098 3099 3100 3101 3102 3103 3104
		sbi->rw_iostat[APP_BUFFERED_IO] =
			sbi->rw_iostat[APP_WRITE_IO] -
			sbi->rw_iostat[APP_DIRECT_IO];

	if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
		sbi->rw_iostat[APP_BUFFERED_READ_IO] =
			sbi->rw_iostat[APP_READ_IO] -
			sbi->rw_iostat[APP_DIRECT_READ_IO];
C
Chao Yu 已提交
3105
	spin_unlock(&sbi->iostat_lock);
3106 3107

	f2fs_record_iostat(sbi);
C
Chao Yu 已提交
3108 3109
}

3110 3111
#define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)

C
Chao Yu 已提交
3112
#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
3113

3114 3115 3116 3117 3118 3119
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type);
static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type)
{
	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
3120 3121
		f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
			 blkaddr, type);
3122 3123 3124 3125 3126
		f2fs_bug_on(sbi, 1);
	}
}

static inline bool __is_valid_data_blkaddr(block_t blkaddr)
C
Chao Yu 已提交
3127
{
C
Chao Yu 已提交
3128 3129
	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR ||
			blkaddr == COMPRESS_ADDR)
C
Chao Yu 已提交
3130 3131 3132 3133
		return false;
	return true;
}

3134 3135 3136 3137 3138 3139
static inline void f2fs_set_page_private(struct page *page,
						unsigned long data)
{
	if (PagePrivate(page))
		return;

3140
	attach_page_private(page, (void *)data);
3141 3142 3143 3144
}

static inline void f2fs_clear_page_private(struct page *page)
{
3145
	detach_page_private(page);
3146 3147
}

3148 3149 3150
/*
 * file.c
 */
3151
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
C
Chao Yu 已提交
3152
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
3153
int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
3154
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
3155
int f2fs_truncate(struct inode *inode);
3156 3157
int f2fs_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
3158
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
C
Chao Yu 已提交
3159 3160
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
3161
int f2fs_precache_extents(struct inode *inode);
3162 3163
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
3164
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
3165
int f2fs_pin_file_control(struct inode *inode, bool inc);
3166 3167 3168 3169

/*
 * inode.c
 */
3170
void f2fs_set_inode_flags(struct inode *inode);
C
Chao Yu 已提交
3171 3172
bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
3173 3174
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
C
Chao Yu 已提交
3175 3176 3177
int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
void f2fs_update_inode(struct inode *inode, struct page *node_page);
void f2fs_update_inode_page(struct inode *inode);
3178 3179
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
C
Chao Yu 已提交
3180
void f2fs_handle_failed_inode(struct inode *inode);
3181 3182 3183 3184

/*
 * namei.c
 */
C
Chao Yu 已提交
3185
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
C
Chao Yu 已提交
3186
							bool hot, bool set);
3187 3188 3189 3190 3191
struct dentry *f2fs_get_parent(struct dentry *child);

/*
 * dir.c
 */
C
Chao Yu 已提交
3192
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
E
Eric Biggers 已提交
3193 3194 3195 3196 3197 3198 3199 3200 3201
int f2fs_init_casefolded_name(const struct inode *dir,
			      struct f2fs_filename *fname);
int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
			int lookup, struct f2fs_filename *fname);
int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
			struct f2fs_filename *fname);
void f2fs_free_filename(struct f2fs_filename *fname);
struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
			const struct f2fs_filename *fname, int *max_slots);
3202 3203
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
			unsigned int start_pos, struct fscrypt_str *fstr);
C
Chao Yu 已提交
3204
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
3205
			struct f2fs_dentry_ptr *d);
C
Chao Yu 已提交
3206
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
E
Eric Biggers 已提交
3207
			const struct f2fs_filename *fname, struct page *dpage);
C
Chao Yu 已提交
3208
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
3209
			unsigned int current_depth);
C
Chao Yu 已提交
3210
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
3211 3212
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
E
Eric Biggers 已提交
3213 3214
					 const struct f2fs_filename *fname,
					 struct page **res_page);
3215 3216 3217 3218 3219 3220 3221
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
			const struct qstr *child, struct page **res_page);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
			struct page **page);
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
			struct page *page, struct inode *inode);
3222
bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
E
Eric Biggers 已提交
3223
			  const struct f2fs_filename *fname);
3224
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
E
Eric Biggers 已提交
3225
			const struct fscrypt_str *name, f2fs_hash_t name_hash,
3226
			unsigned int bit_pos);
E
Eric Biggers 已提交
3227
int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
3228
			struct inode *inode, nid_t ino, umode_t mode);
E
Eric Biggers 已提交
3229
int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
3230
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
3231
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
3232 3233 3234 3235 3236
			struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
			struct inode *dir, struct inode *inode);
int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
bool f2fs_empty_dir(struct inode *dir);
3237

3238 3239
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
C
Chao Yu 已提交
3240
	return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
3241
				inode, inode->i_ino, inode->i_mode);
3242 3243
}

3244 3245 3246
/*
 * super.c
 */
3247 3248
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
J
Jaegeuk Kim 已提交
3249
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
3250
int f2fs_quota_sync(struct super_block *sb, int type);
C
Chao Yu 已提交
3251
void f2fs_quota_off_umount(struct super_block *sb);
3252 3253
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
C
Chao Yu 已提交
3254
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
3255 3256 3257 3258

/*
 * hash.c
 */
E
Eric Biggers 已提交
3259
void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);
3260 3261 3262 3263 3264 3265 3266

/*
 * node.c
 */
struct dnode_of_data;
struct node_info;

C
Chao Yu 已提交
3267 3268
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
3269 3270 3271 3272
bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3273 3274 3275
int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
3276
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
C
Chao Yu 已提交
3277 3278 3279 3280 3281
						struct node_info *ni);
pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
int f2fs_truncate_xattr_node(struct inode *inode);
3282 3283
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
					unsigned int seq_id);
C
Chao Yu 已提交
3284 3285 3286 3287 3288 3289
int f2fs_remove_inode_page(struct inode *inode);
struct page *f2fs_new_inode_page(struct inode *inode);
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
3290
int f2fs_move_node_page(struct page *node_page, int gc_type);
3291
void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3292
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
3293 3294
			struct writeback_control *wbc, bool atomic,
			unsigned int *seq_id);
C
Chao Yu 已提交
3295 3296
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
			struct writeback_control *wbc,
C
Chao Yu 已提交
3297
			bool do_balance, enum iostat_type io_type);
3298
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
C
Chao Yu 已提交
3299 3300 3301 3302
bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
3303
int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
C
Chao Yu 已提交
3304 3305
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
3306
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
3307
			unsigned int segno, struct f2fs_summary_block *sum);
3308
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
C
Chao Yu 已提交
3309 3310 3311 3312
int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_node_manager_caches(void);
void f2fs_destroy_node_manager_caches(void);
3313 3314 3315 3316

/*
 * segment.c
 */
C
Chao Yu 已提交
3317 3318 3319 3320 3321 3322
bool f2fs_need_SSR(struct f2fs_sb_info *sbi);
void f2fs_register_inmem_page(struct inode *inode, struct page *page);
void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure);
void f2fs_drop_inmem_pages(struct inode *inode);
void f2fs_drop_inmem_page(struct inode *inode, struct page *page);
int f2fs_commit_inmem_pages(struct inode *inode);
3323
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
3324
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg);
C
Chao Yu 已提交
3325
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
C
Chao Yu 已提交
3326
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
3327
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3328 3329 3330 3331 3332
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
3333
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3334 3335
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
					struct cp_control *cpc);
D
Daniel Rosenberg 已提交
3336
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
3337 3338
block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
C
Chao Yu 已提交
3339 3340
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
C
Chao Yu 已提交
3341 3342
void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type);
void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type);
C
Chao Yu 已提交
3343
void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
3344
					unsigned int start, unsigned int end);
3345 3346
void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
3347
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
C
Chao Yu 已提交
3348 3349 3350 3351 3352 3353
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
					struct cp_control *cpc);
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
					block_t blk_addr);
void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
C
Chao Yu 已提交
3354
						enum iostat_type io_type);
C
Chao Yu 已提交
3355 3356 3357 3358 3359
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void f2fs_outplace_write_data(struct dnode_of_data *dn,
			struct f2fs_io_info *fio);
int f2fs_inplace_write_data(struct f2fs_io_info *fio);
void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
3360
			block_t old_blkaddr, block_t new_blkaddr,
3361 3362
			bool recover_curseg, bool recover_newaddr,
			bool from_gc);
3363 3364 3365 3366
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
			block_t old_addr, block_t new_addr,
			unsigned char version, bool recover_curseg,
			bool recover_newaddr);
C
Chao Yu 已提交
3367
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
3368
			block_t old_blkaddr, block_t *new_blkaddr,
3369
			struct f2fs_summary *sum, int type,
3370
			struct f2fs_io_info *fio, bool from_gc);
3371
void f2fs_wait_on_page_writeback(struct page *page,
3372
			enum page_type type, bool ordered, bool locked);
3373
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
3374 3375
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
								block_t len);
C
Chao Yu 已提交
3376 3377 3378
void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
3379
			unsigned int val, int alloc);
C
Chao Yu 已提交
3380
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
3381
int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
3382
int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3383 3384 3385 3386 3387 3388 3389
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
			enum page_type type, enum temp_type temp);
3390 3391 3392 3393
unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
			unsigned int segno);
unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
			unsigned int segno);
3394 3395 3396 3397

/*
 * checkpoint.c
 */
3398
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
C
Chao Yu 已提交
3399 3400
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
3401
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
C
Chao Yu 已提交
3402
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
3403 3404
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type);
C
Chao Yu 已提交
3405
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
3406
			int type, bool sync);
C
Chao Yu 已提交
3407 3408
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
C
Chao Yu 已提交
3409
			long nr_to_write, enum iostat_type io_type);
C
Chao Yu 已提交
3410 3411 3412 3413 3414
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all);
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
C
Chao Yu 已提交
3415
					unsigned int devidx, int type);
C
Chao Yu 已提交
3416
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
C
Chao Yu 已提交
3417
					unsigned int devidx, int type);
3418
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3419 3420 3421 3422 3423 3424 3425 3426 3427
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi);
void f2fs_add_orphan_inode(struct inode *inode);
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
3428
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
C
Chao Yu 已提交
3429 3430 3431 3432
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);
void f2fs_destroy_checkpoint_caches(void);
3433 3434 3435 3436

/*
 * data.c
 */
C
Chao Yu 已提交
3437 3438
int __init f2fs_init_bioset(void);
void f2fs_destroy_bioset(void);
3439
struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio);
C
Chao Yu 已提交
3440 3441
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
C
Chao Yu 已提交
3442 3443
void f2fs_submit_bio(struct f2fs_sb_info *sbi,
				struct bio *bio, enum page_type type);
3444 3445
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
3446 3447
				struct inode *inode, struct page *page,
				nid_t ino, enum page_type type);
C
Chao Yu 已提交
3448 3449
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
					struct bio **bio, struct page *page);
3450
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
3451
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3452
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
3453
void f2fs_submit_page_write(struct f2fs_io_info *fio);
3454 3455 3456
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
			block_t blk_addr, struct bio *bio);
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
C
Chao Yu 已提交
3457
void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
3458
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
C
Chao Yu 已提交
3459 3460
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
3461 3462 3463
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
C
Chao Yu 已提交
3464
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
3465
			int op_flags, bool for_write);
C
Chao Yu 已提交
3466 3467
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
3468
			bool for_write);
C
Chao Yu 已提交
3469
struct page *f2fs_get_new_data_page(struct inode *inode,
3470
			struct page *ipage, pgoff_t index, bool new_i_size);
C
Chao Yu 已提交
3471
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3472
void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
3473 3474 3475 3476
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
			int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			u64 start, u64 len);
C
Chao Yu 已提交
3477
int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3478 3479
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
C
Chao Yu 已提交
3480 3481 3482 3483 3484
int f2fs_write_single_data_page(struct page *page, int *submitted,
				struct bio **bio, sector_t *last_block,
				struct writeback_control *wbc,
				enum iostat_type io_type,
				int compr_blocks);
3485 3486 3487
void f2fs_invalidate_page(struct page *page, unsigned int offset,
			unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
3488
#ifdef CONFIG_MIGRATION
3489 3490
int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
			struct page *page, enum migrate_mode mode);
3491
#endif
H
Hyunchul Lee 已提交
3492
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
M
Matthew Wilcox 已提交
3493
void f2fs_clear_page_cache_dirty_tag(struct page *page);
C
Chao Yu 已提交
3494 3495 3496 3497
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
3498 3499 3500 3501

/*
 * gc.c
 */
C
Chao Yu 已提交
3502 3503 3504
int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
3505 3506
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
			unsigned int segno);
C
Chao Yu 已提交
3507
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
3508
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
3509 3510 3511 3512

/*
 * recovery.c
 */
C
Chao Yu 已提交
3513 3514
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
3515 3516 3517 3518 3519 3520 3521 3522 3523 3524

/*
 * debug.c
 */
#ifdef CONFIG_F2FS_STAT_FS
struct f2fs_stat_info {
	struct list_head stat_list;
	struct f2fs_sb_info *sbi;
	int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
	int main_area_segs, main_area_sections, main_area_zones;
3525 3526
	unsigned long long hit_largest, hit_cached, hit_rbtree;
	unsigned long long hit_total, total_ext;
J
Jaegeuk Kim 已提交
3527
	int ext_tree, zombie_tree, ext_node;
3528 3529
	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
	int ndirty_data, ndirty_qdata;
3530
	int inmem_pages;
3531
	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
3532 3533
	int nats, dirty_nats, sits, dirty_sits;
	int free_nids, avail_nids, alloc_nids;
3534
	int total_count, utilization;
C
Chao Yu 已提交
3535
	int bg_gc, nr_wb_cp_data, nr_wb_data;
3536
	int nr_rd_data, nr_rd_node, nr_rd_meta;
C
Chao Yu 已提交
3537
	int nr_dio_read, nr_dio_write;
3538
	unsigned int io_skip_bggc, other_skip_bggc;
C
Chao Yu 已提交
3539 3540
	int nr_flushing, nr_flushed, flush_list_empty;
	int nr_discarding, nr_discarded;
C
Chao Yu 已提交
3541
	int nr_discard_cmd;
C
Chao Yu 已提交
3542
	unsigned int undiscard_blks;
3543
	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
C
Chao Yu 已提交
3544
	int compr_inode, compr_blocks;
3545
	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
3546
	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
3547 3548 3549 3550
	unsigned int bimodal, avg_vblocks;
	int util_free, util_valid, util_invalid;
	int rsvd_segs, overp_segs;
	int dirty_count, node_pages, meta_pages;
3551
	int prefree_count, call_count, cp_count, bg_cp_count;
3552
	int tot_segs, node_segs, data_segs, free_segs, free_secs;
3553
	int bg_node_segs, bg_data_segs;
3554
	int tot_blks, data_blks, node_blks;
3555
	int bg_data_blks, bg_node_blks;
3556
	unsigned long long skipped_atomic_files[2];
3557 3558 3559
	int curseg[NR_CURSEG_TYPE];
	int cursec[NR_CURSEG_TYPE];
	int curzone[NR_CURSEG_TYPE];
3560 3561 3562
	unsigned int dirty_seg[NR_CURSEG_TYPE];
	unsigned int full_seg[NR_CURSEG_TYPE];
	unsigned int valid_blks[NR_CURSEG_TYPE];
3563

C
Chao Yu 已提交
3564
	unsigned int meta_count[META_MAX];
3565 3566
	unsigned int segment_count[2];
	unsigned int block_count[2];
3567
	unsigned int inplace_count;
C
Chao Yu 已提交
3568
	unsigned long long base_mem, cache_mem, page_mem;
3569 3570
};

3571 3572
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
3573
	return (struct f2fs_stat_info *)sbi->stat_info;
3574 3575
}

3576
#define stat_inc_cp_count(si)		((si)->cp_count++)
3577
#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
3578
#define stat_inc_call_count(si)		((si)->call_count++)
H
Hridya Valsaraju 已提交
3579
#define stat_inc_bggc_count(si)		((si)->bg_gc++)
3580 3581
#define stat_io_skip_bggc_count(sbi)	((sbi)->io_skip_bggc++)
#define stat_other_skip_bggc_count(sbi)	((sbi)->other_skip_bggc++)
C
Chao Yu 已提交
3582 3583
#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
3584 3585 3586 3587
#define stat_inc_total_hit(sbi)		(atomic64_inc(&(sbi)->total_hit_ext))
#define stat_inc_rbtree_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_rbtree))
#define stat_inc_largest_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_largest))
#define stat_inc_cached_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_cached))
C
Chao Yu 已提交
3588 3589 3590 3591 3592 3593 3594 3595 3596 3597
#define stat_inc_inline_xattr(inode)					\
	do {								\
		if (f2fs_has_inline_xattr(inode))			\
			(atomic_inc(&F2FS_I_SB(inode)->inline_xattr));	\
	} while (0)
#define stat_dec_inline_xattr(inode)					\
	do {								\
		if (f2fs_has_inline_xattr(inode))			\
			(atomic_dec(&F2FS_I_SB(inode)->inline_xattr));	\
	} while (0)
3598 3599 3600
#define stat_inc_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3601
			(atomic_inc(&F2FS_I_SB(inode)->inline_inode));	\
3602 3603 3604 3605
	} while (0)
#define stat_dec_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3606
			(atomic_dec(&F2FS_I_SB(inode)->inline_inode));	\
3607
	} while (0)
3608 3609 3610
#define stat_inc_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3611
			(atomic_inc(&F2FS_I_SB(inode)->inline_dir));	\
3612 3613 3614 3615
	} while (0)
#define stat_dec_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3616
			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
3617
	} while (0)
C
Chao Yu 已提交
3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631
#define stat_inc_compr_inode(inode)					\
	do {								\
		if (f2fs_compressed_file(inode))			\
			(atomic_inc(&F2FS_I_SB(inode)->compr_inode));	\
	} while (0)
#define stat_dec_compr_inode(inode)					\
	do {								\
		if (f2fs_compressed_file(inode))			\
			(atomic_dec(&F2FS_I_SB(inode)->compr_inode));	\
	} while (0)
#define stat_add_compr_blocks(inode, blocks)				\
		(atomic_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_sub_compr_blocks(inode, blocks)				\
		(atomic_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
C
Chao Yu 已提交
3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642
#define stat_inc_meta_count(sbi, blkaddr)				\
	do {								\
		if (blkaddr < SIT_I(sbi)->sit_base_addr)		\
			atomic_inc(&(sbi)->meta_count[META_CP]);	\
		else if (blkaddr < NM_I(sbi)->nat_blkaddr)		\
			atomic_inc(&(sbi)->meta_count[META_SIT]);	\
		else if (blkaddr < SM_I(sbi)->ssa_blkaddr)		\
			atomic_inc(&(sbi)->meta_count[META_NAT]);	\
		else if (blkaddr < SM_I(sbi)->main_blkaddr)		\
			atomic_inc(&(sbi)->meta_count[META_SSA]);	\
	} while (0)
3643 3644 3645 3646
#define stat_inc_seg_type(sbi, curseg)					\
		((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg)				\
		((sbi)->block_count[(curseg)->alloc_type]++)
3647 3648
#define stat_inc_inplace_blocks(sbi)					\
		(atomic_inc(&(sbi)->inplace_count))
3649 3650
#define stat_update_max_atomic_write(inode)				\
	do {								\
3651
		int cur = F2FS_I_SB(inode)->atomic_files;	\
3652 3653 3654 3655
		int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);	\
		if (cur > max)						\
			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
	} while (0)
3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666
#define stat_inc_volatile_write(inode)					\
		(atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
#define stat_dec_volatile_write(inode)					\
		(atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
#define stat_update_max_volatile_write(inode)				\
	do {								\
		int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt);	\
		int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt);	\
		if (cur > max)						\
			atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur);	\
	} while (0)
3667
#define stat_inc_seg_count(sbi, type, gc_type)				\
3668
	do {								\
3669
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3670 3671
		si->tot_segs++;						\
		if ((type) == SUM_TYPE_DATA) {				\
3672
			si->data_segs++;				\
3673 3674
			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
		} else {						\
3675
			si->node_segs++;				\
3676 3677
			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
		}							\
3678 3679 3680
	} while (0)

#define stat_inc_tot_blk_count(si, blks)				\
3681
	((si)->tot_blks += (blks))
3682

3683
#define stat_inc_data_blk_count(sbi, blks, gc_type)			\
3684
	do {								\
3685
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3686 3687
		stat_inc_tot_blk_count(si, blks);			\
		si->data_blks += (blks);				\
3688
		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3689 3690
	} while (0)

3691
#define stat_inc_node_blk_count(sbi, blks, gc_type)			\
3692
	do {								\
3693
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3694 3695
		stat_inc_tot_blk_count(si, blks);			\
		si->node_blks += (blks);				\
3696
		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3697 3698
	} while (0)

3699 3700
int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
3701
void __init f2fs_create_root_stats(void);
3702
void f2fs_destroy_root_stats(void);
H
Hridya Valsaraju 已提交
3703
void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
3704
#else
3705 3706 3707 3708
#define stat_inc_cp_count(si)				do { } while (0)
#define stat_inc_bg_cp_count(si)			do { } while (0)
#define stat_inc_call_count(si)				do { } while (0)
#define stat_inc_bggc_count(si)				do { } while (0)
3709 3710
#define stat_io_skip_bggc_count(sbi)			do { } while (0)
#define stat_other_skip_bggc_count(sbi)			do { } while (0)
3711 3712
#define stat_inc_dirty_inode(sbi, type)			do { } while (0)
#define stat_dec_dirty_inode(sbi, type)			do { } while (0)
H
Hridya Valsaraju 已提交
3713 3714
#define stat_inc_total_hit(sbi)				do { } while (0)
#define stat_inc_rbtree_node_hit(sbi)			do { } while (0)
3715 3716 3717 3718 3719 3720 3721 3722
#define stat_inc_largest_node_hit(sbi)			do { } while (0)
#define stat_inc_cached_node_hit(sbi)			do { } while (0)
#define stat_inc_inline_xattr(inode)			do { } while (0)
#define stat_dec_inline_xattr(inode)			do { } while (0)
#define stat_inc_inline_inode(inode)			do { } while (0)
#define stat_dec_inline_inode(inode)			do { } while (0)
#define stat_inc_inline_dir(inode)			do { } while (0)
#define stat_dec_inline_dir(inode)			do { } while (0)
C
Chao Yu 已提交
3723 3724 3725 3726
#define stat_inc_compr_inode(inode)			do { } while (0)
#define stat_dec_compr_inode(inode)			do { } while (0)
#define stat_add_compr_blocks(inode, blocks)		do { } while (0)
#define stat_sub_compr_blocks(inode, blocks)		do { } while (0)
3727 3728 3729 3730 3731 3732
#define stat_inc_atomic_write(inode)			do { } while (0)
#define stat_dec_atomic_write(inode)			do { } while (0)
#define stat_update_max_atomic_write(inode)		do { } while (0)
#define stat_inc_volatile_write(inode)			do { } while (0)
#define stat_dec_volatile_write(inode)			do { } while (0)
#define stat_update_max_volatile_write(inode)		do { } while (0)
C
Chao Yu 已提交
3733
#define stat_inc_meta_count(sbi, blkaddr)		do { } while (0)
3734 3735 3736 3737 3738 3739 3740
#define stat_inc_seg_type(sbi, curseg)			do { } while (0)
#define stat_inc_block_count(sbi, curseg)		do { } while (0)
#define stat_inc_inplace_blocks(sbi)			do { } while (0)
#define stat_inc_seg_count(sbi, type, gc_type)		do { } while (0)
#define stat_inc_tot_blk_count(si, blks)		do { } while (0)
#define stat_inc_data_blk_count(sbi, blks, gc_type)	do { } while (0)
#define stat_inc_node_blk_count(sbi, blks, gc_type)	do { } while (0)
3741 3742 3743

static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
3744
static inline void __init f2fs_create_root_stats(void) { }
3745
static inline void f2fs_destroy_root_stats(void) { }
3746
static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
3747 3748 3749
#endif

extern const struct file_operations f2fs_dir_operations;
3750 3751 3752
#ifdef CONFIG_UNICODE
extern const struct dentry_operations f2fs_dentry_ops;
#endif
3753 3754 3755 3756 3757 3758 3759
extern const struct file_operations f2fs_file_operations;
extern const struct inode_operations f2fs_file_inode_operations;
extern const struct address_space_operations f2fs_dblock_aops;
extern const struct address_space_operations f2fs_node_aops;
extern const struct address_space_operations f2fs_meta_aops;
extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
3760
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
3761
extern const struct inode_operations f2fs_special_inode_operations;
C
Chao Yu 已提交
3762
extern struct kmem_cache *f2fs_inode_entry_slab;
3763

3764 3765 3766
/*
 * inline.c
 */
3767 3768
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
C
Chao Yu 已提交
3769 3770 3771
void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
						struct page *ipage, u64 from);
3772 3773 3774
int f2fs_read_inline_data(struct inode *inode, struct page *page);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
3775
int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
3776
int f2fs_write_inline_data(struct inode *inode, struct page *page);
3777
int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
C
Chao Yu 已提交
3778
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
E
Eric Biggers 已提交
3779 3780
					const struct f2fs_filename *fname,
					struct page **res_page);
C
Chao Yu 已提交
3781
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
3782
			struct page *ipage);
E
Eric Biggers 已提交
3783
int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
3784
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
3785 3786 3787
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
				struct page *page, struct inode *dir,
				struct inode *inode);
3788 3789 3790 3791 3792 3793
bool f2fs_empty_inline_dir(struct inode *dir);
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
			struct fscrypt_str *fstr);
int f2fs_inline_data_fiemap(struct inode *inode,
			struct fiemap_extent_info *fieinfo,
			__u64 start, __u64 len);
3794

3795 3796 3797
/*
 * shrinker.c
 */
3798 3799 3800 3801 3802 3803
unsigned long f2fs_shrink_count(struct shrinker *shrink,
			struct shrink_control *sc);
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
			struct shrink_control *sc);
void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
3804

3805 3806 3807
/*
 * extent_cache.c
 */
C
Chao Yu 已提交
3808
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
3809
				struct rb_entry *cached_re, unsigned int ofs);
3810 3811 3812 3813
struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
				struct rb_root_cached *root,
				struct rb_node **parent,
				unsigned long long key, bool *left_most);
C
Chao Yu 已提交
3814
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3815 3816 3817 3818
				struct rb_root_cached *root,
				struct rb_node **parent,
				unsigned int ofs, bool *leftmost);
struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
3819 3820 3821
		struct rb_entry *cached_re, unsigned int ofs,
		struct rb_entry **prev_entry, struct rb_entry **next_entry,
		struct rb_node ***insert_p, struct rb_node **insert_parent,
C
Chao Yu 已提交
3822
		bool force, bool *leftmost);
C
Chao Yu 已提交
3823
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
3824
				struct rb_root_cached *root, bool check_key);
3825
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
3826
void f2fs_init_extent_tree(struct inode *inode, struct page *ipage);
3827 3828 3829 3830 3831 3832
void f2fs_drop_extent_tree(struct inode *inode);
unsigned int f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
			struct extent_info *ei);
void f2fs_update_extent_cache(struct dnode_of_data *dn);
C
Chao Yu 已提交
3833
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
3834
			pgoff_t fofs, block_t blkaddr, unsigned int len);
C
Chao Yu 已提交
3835 3836 3837
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
3838

3839 3840 3841
/*
 * sysfs.c
 */
3842 3843 3844 3845
int __init f2fs_init_sysfs(void);
void f2fs_exit_sysfs(void);
int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi);
3846

E
Eric Biggers 已提交
3847 3848 3849
/* verity.c */
extern const struct fsverity_operations f2fs_verityops;

3850 3851 3852
/*
 * crypto support
 */
3853 3854
static inline bool f2fs_encrypted_file(struct inode *inode)
{
3855
	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
3856 3857
}

3858 3859
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
3860
#ifdef CONFIG_FS_ENCRYPTION
3861
	file_set_encrypt(inode);
C
Chao Yu 已提交
3862
	f2fs_set_inode_flags(inode);
3863 3864 3865
#endif
}

3866 3867 3868 3869 3870
/*
 * Returns true if the reads of the inode's data need to undergo some
 * postprocessing step, like decryption or authenticity verification.
 */
static inline bool f2fs_post_read_required(struct inode *inode)
3871
{
C
Chao Yu 已提交
3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885
	return f2fs_encrypted_file(inode) || fsverity_active(inode) ||
		f2fs_compressed_file(inode);
}

/*
 * compress.c
 */
#ifdef CONFIG_F2FS_FS_COMPRESSION
bool f2fs_is_compressed_page(struct page *page);
struct page *f2fs_compress_control_page(struct page *page);
int f2fs_prepare_compress_overwrite(struct inode *inode,
			struct page **pagep, pgoff_t index, void **fsdata);
bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
					pgoff_t index, unsigned copied);
3886
int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
C
Chao Yu 已提交
3887 3888
void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
bool f2fs_is_compress_backend_ready(struct inode *inode);
3889 3890
int f2fs_init_compress_mempool(void);
void f2fs_destroy_compress_mempool(void);
C
Chao Yu 已提交
3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901
void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
bool f2fs_cluster_is_empty(struct compress_ctx *cc);
bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
int f2fs_write_multi_pages(struct compress_ctx *cc,
						int *submitted,
						struct writeback_control *wbc,
						enum iostat_type io_type);
int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
				unsigned nr_pages, sector_t *last_block_in_bio,
3902
				bool is_readahead, bool for_write);
C
Chao Yu 已提交
3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923
struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
void f2fs_free_dic(struct decompress_io_ctx *dic);
void f2fs_decompress_end_io(struct page **rpages,
			unsigned int cluster_size, bool err, bool verity);
int f2fs_init_compress_ctx(struct compress_ctx *cc);
void f2fs_destroy_compress_ctx(struct compress_ctx *cc);
void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
#else
static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
{
	if (!f2fs_compressed_file(inode))
		return true;
	/* not support compression */
	return false;
}
static inline struct page *f2fs_compress_control_page(struct page *page)
{
	WARN_ON_ONCE(1);
	return ERR_PTR(-EINVAL);
}
3924 3925
static inline int f2fs_init_compress_mempool(void) { return 0; }
static inline void f2fs_destroy_compress_mempool(void) { }
C
Chao Yu 已提交
3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940
#endif

static inline void set_compress_context(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	F2FS_I(inode)->i_compress_algorithm =
			F2FS_OPTION(sbi).compress_algorithm;
	F2FS_I(inode)->i_log_cluster_size =
			F2FS_OPTION(sbi).compress_log_size;
	F2FS_I(inode)->i_cluster_size =
			1 << F2FS_I(inode)->i_log_cluster_size;
	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
	set_inode_flag(inode, FI_COMPRESSED_FILE);
	stat_inc_compr_inode(inode);
3941
	f2fs_mark_inode_dirty_sync(inode, true);
C
Chao Yu 已提交
3942 3943 3944 3945 3946 3947 3948 3949
}

static inline u64 f2fs_disable_compressed_file(struct inode *inode)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);

	if (!f2fs_compressed_file(inode))
		return 0;
3950 3951 3952 3953 3954 3955
	if (S_ISREG(inode->i_mode)) {
		if (get_dirty_pages(inode))
			return 1;
		if (fi->i_compr_blocks)
			return fi->i_compr_blocks;
	}
C
Chao Yu 已提交
3956 3957 3958

	fi->i_flags &= ~F2FS_COMPR_FL;
	stat_dec_compr_inode(inode);
3959
	clear_inode_flag(inode, FI_COMPRESSED_FILE);
3960
	f2fs_mark_inode_dirty_sync(inode, true);
C
Chao Yu 已提交
3961
	return 0;
3962 3963
}

3964
#define F2FS_FEATURE_FUNCS(name, flagname) \
3965
static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
3966
{ \
3967
	return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
3968 3969
}

3970 3971 3972 3973 3974 3975 3976 3977
F2FS_FEATURE_FUNCS(encrypt, ENCRYPT);
F2FS_FEATURE_FUNCS(blkzoned, BLKZONED);
F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR);
F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA);
F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM);
F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR);
F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO);
F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME);
3978
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
E
Eric Biggers 已提交
3979
F2FS_FEATURE_FUNCS(verity, VERITY);
3980
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
3981
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
C
Chao Yu 已提交
3982
F2FS_FEATURE_FUNCS(compression, COMPRESSION);
C
Chao Yu 已提交
3983

3984
#ifdef CONFIG_BLK_DEV_ZONED
3985 3986
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
				    block_t blkaddr)
3987 3988 3989
{
	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;

3990
	return test_bit(zno, FDEV(devi).blkz_seq);
3991 3992 3993
}
#endif

3994
static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
3995
{
3996
	return f2fs_sb_has_blkzoned(sbi);
3997
}
3998

3999 4000 4001 4002 4003 4004
static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
{
	return blk_queue_discard(bdev_get_queue(bdev)) ||
	       bdev_is_zoned(bdev);
}

4005 4006
static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
{
4007 4008 4009 4010 4011 4012 4013 4014 4015
	int i;

	if (!f2fs_is_multi_device(sbi))
		return f2fs_bdev_support_discard(sbi->sb->s_bdev);

	for (i = 0; i < sbi->s_ndevs; i++)
		if (f2fs_bdev_support_discard(FDEV(i).bdev))
			return true;
	return false;
4016 4017 4018 4019 4020 4021
}

static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi)
{
	return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) ||
					f2fs_hw_should_discard(sbi);
4022 4023
}

4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036
static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi)
{
	int i;

	if (!f2fs_is_multi_device(sbi))
		return bdev_read_only(sbi->sb->s_bdev);

	for (i = 0; i < sbi->s_ndevs; i++)
		if (bdev_read_only(FDEV(i).bdev))
			return true;
	return false;
}

4037
static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
4038
{
4039
	return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
4040 4041
}

C
Chao Yu 已提交
4042
static inline bool f2fs_may_encrypt(struct inode *dir, struct inode *inode)
4043
{
4044
#ifdef CONFIG_FS_ENCRYPTION
C
Chao Yu 已提交
4045
	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
A
Al Viro 已提交
4046
	umode_t mode = inode->i_mode;
4047

C
Chao Yu 已提交
4048 4049 4050 4051 4052 4053
	/*
	 * If the directory encrypted or dummy encryption enabled,
	 * then we should encrypt the inode.
	 */
	if (IS_ENCRYPTED(dir) || DUMMY_ENCRYPTION_ENABLED(sbi))
		return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
4054
#endif
C
Chao Yu 已提交
4055
	return false;
4056 4057
}

C
Chao Yu 已提交
4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071
static inline bool f2fs_may_compress(struct inode *inode)
{
	if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
				f2fs_is_atomic_file(inode) ||
				f2fs_is_volatile_file(inode))
		return false;
	return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
}

static inline void f2fs_i_compr_blocks_update(struct inode *inode,
						u64 blocks, bool add)
{
	int diff = F2FS_I(inode)->i_cluster_size - blocks;

4072 4073 4074 4075
	/* don't update i_compr_blocks if saved blocks were released */
	if (!add && !F2FS_I(inode)->i_compr_blocks)
		return;

C
Chao Yu 已提交
4076 4077 4078 4079 4080 4081 4082 4083 4084 4085
	if (add) {
		F2FS_I(inode)->i_compr_blocks += diff;
		stat_add_compr_blocks(inode, diff);
	} else {
		F2FS_I(inode)->i_compr_blocks -= diff;
		stat_sub_compr_blocks(inode, diff);
	}
	f2fs_mark_inode_dirty_sync(inode, true);
}

4086 4087
static inline int block_unaligned_IO(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
H
Hyunchul Lee 已提交
4088
{
4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102
	unsigned int i_blkbits = READ_ONCE(inode->i_blkbits);
	unsigned int blocksize_mask = (1 << i_blkbits) - 1;
	loff_t offset = iocb->ki_pos;
	unsigned long align = offset | iov_iter_alignment(iter);

	return align & blocksize_mask;
}

static inline int allow_outplace_dio(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	int rw = iov_iter_rw(iter);

4103
	return (f2fs_lfs_mode(sbi) && (rw == WRITE) &&
4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114
				!block_unaligned_IO(inode, iocb, iter));
}

static inline bool f2fs_force_buffered_io(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	int rw = iov_iter_rw(iter);

	if (f2fs_post_read_required(inode))
		return true;
4115
	if (f2fs_is_multi_device(sbi))
4116 4117 4118 4119 4120
		return true;
	/*
	 * for blkzoned device, fallback direct IO to buffered IO, so
	 * all IOs can be serialized by log-structured write.
	 */
4121
	if (f2fs_sb_has_blkzoned(sbi))
4122
		return true;
4123
	if (f2fs_lfs_mode(sbi) && (rw == WRITE)) {
4124 4125 4126 4127 4128
		if (block_unaligned_IO(inode, iocb, iter))
			return true;
		if (F2FS_IO_ALIGNED(sbi))
			return true;
	}
J
Jaegeuk Kim 已提交
4129
	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
C
Chao Yu 已提交
4130
					!IS_SWAPFILE(inode))
D
Daniel Rosenberg 已提交
4131 4132
		return true;

4133
	return false;
H
Hyunchul Lee 已提交
4134 4135
}

4136
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
4137 4138
extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
							unsigned int type);
4139
#else
C
Chao Yu 已提交
4140
#define f2fs_build_fault_attr(sbi, rate, type)		do { } while (0)
4141 4142
#endif

4143 4144 4145
static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_QUOTA
4146
	if (f2fs_sb_has_quota_ino(sbi))
4147 4148 4149 4150 4151 4152 4153 4154
		return true;
	if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] ||
		F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] ||
		F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
		return true;
#endif
	return false;
}
J
Jaegeuk Kim 已提交
4155

4156 4157 4158
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

4159
#endif /* _LINUX_F2FS_H */