f2fs.h 116.5 KB
Newer Older
C
Chao Yu 已提交
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>
K
Keith Mok 已提交
25
#include <crypto/hash.h>
26

D
Dave Chinner 已提交
27 28
#include <linux/fscrypt.h>

29
#ifdef CONFIG_F2FS_CHECK_FS
30
#define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
31
#else
32 33 34 35
#define f2fs_bug_on(sbi, condition)					\
	do {								\
		if (unlikely(condition)) {				\
			WARN_ON(1);					\
36
			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
37 38
		}							\
	} while (0)
39 40
#endif

J
Jaegeuk Kim 已提交
41 42
enum {
	FAULT_KMALLOC,
C
Chao Yu 已提交
43
	FAULT_KVMALLOC,
44
	FAULT_PAGE_ALLOC,
C
Chao Yu 已提交
45
	FAULT_PAGE_GET,
46
	FAULT_ALLOC_BIO,
J
Jaegeuk Kim 已提交
47 48 49 50
	FAULT_ALLOC_NID,
	FAULT_ORPHAN,
	FAULT_BLOCK,
	FAULT_DIR_DEPTH,
51
	FAULT_EVICT_INODE,
52
	FAULT_TRUNCATE,
53
	FAULT_READ_IO,
54
	FAULT_CHECKPOINT,
55
	FAULT_DISCARD,
56
	FAULT_WRITE_IO,
J
Jaegeuk Kim 已提交
57 58 59
	FAULT_MAX,
};

60
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
61 62
#define F2FS_ALL_FAULT_TYPE		((1 << FAULT_MAX) - 1)

S
Sheng Yong 已提交
63 64 65 66 67 68
struct f2fs_fault_info {
	atomic_t inject_ops;
	unsigned int inject_rate;
	unsigned int inject_type;
};

69
extern const char *f2fs_fault_name[FAULT_MAX];
70
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
J
Jaegeuk Kim 已提交
71 72
#endif

73 74 75 76 77 78 79 80 81 82
/*
 * For mount options
 */
#define F2FS_MOUNT_BG_GC		0x00000001
#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
83
#define F2FS_MOUNT_INLINE_XATTR		0x00000080
84
#define F2FS_MOUNT_INLINE_DATA		0x00000100
85 86 87
#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
#define F2FS_MOUNT_NOBARRIER		0x00000800
88
#define F2FS_MOUNT_FASTBOOT		0x00001000
89
#define F2FS_MOUNT_EXTENT_CACHE		0x00002000
90
#define F2FS_MOUNT_FORCE_FG_GC		0x00004000
91
#define F2FS_MOUNT_DATA_FLUSH		0x00008000
92
#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
93 94
#define F2FS_MOUNT_ADAPTIVE		0x00020000
#define F2FS_MOUNT_LFS			0x00040000
C
Chao Yu 已提交
95 96
#define F2FS_MOUNT_USRQUOTA		0x00080000
#define F2FS_MOUNT_GRPQUOTA		0x00100000
C
Chao Yu 已提交
97
#define F2FS_MOUNT_PRJQUOTA		0x00200000
C
Chao Yu 已提交
98
#define F2FS_MOUNT_QUOTA		0x00400000
C
Chao Yu 已提交
99
#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
100
#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
D
Daniel Rosenberg 已提交
101
#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
102

103 104 105 106
#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)
107 108 109 110 111

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

112 113 114 115
typedef u32 block_t;	/*
			 * should not change u32, since it is the on-disk block
			 * address format, __le32.
			 */
116 117 118
typedef u32 nid_t;

struct f2fs_mount_info {
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
	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 */
138
	bool test_dummy_encryption;	/* test dummy encryption */
139 140 141
	block_t unusable_cap;		/* Amount of space allowed to be
					 * unusable when disabling checkpoint
					 */
142 143
};

144 145 146 147
#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
148
#define F2FS_FEATURE_PRJQUOTA		0x0010
C
Chao Yu 已提交
149
#define F2FS_FEATURE_INODE_CHKSUM	0x0020
C
Chao Yu 已提交
150
#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
J
Jaegeuk Kim 已提交
151
#define F2FS_FEATURE_QUOTA_INO		0x0080
C
Chao Yu 已提交
152
#define F2FS_FEATURE_INODE_CRTIME	0x0100
153
#define F2FS_FEATURE_LOST_FOUND		0x0200
E
Eric Biggers 已提交
154
#define F2FS_FEATURE_VERITY		0x0400	/* reserved */
155
#define F2FS_FEATURE_SB_CHKSUM		0x0800
156
#define F2FS_FEATURE_CASEFOLD		0x1000
157

158 159 160 161 162 163 164
#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))
165

166 167 168 169 170 171
/*
 * Default values for user and/or group using reserved blocks
 */
#define	F2FS_DEF_RESUID		0
#define	F2FS_DEF_RESGID		0

172 173 174 175 176 177 178 179
/*
 * For checkpoint manager
 */
enum {
	NAT_BITMAP,
	SIT_BITMAP
};

180 181 182 183 184
#define	CP_UMOUNT	0x00000001
#define	CP_FASTBOOT	0x00000002
#define	CP_SYNC		0x00000004
#define	CP_RECOVERY	0x00000008
#define	CP_DISCARD	0x00000010
185
#define CP_TRIMMED	0x00000020
D
Daniel Rosenberg 已提交
186
#define CP_PAUSE	0x00000040
187

188
#define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
C
Chao Yu 已提交
189
#define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
190
#define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
191
#define DEF_MID_DISCARD_ISSUE_TIME	500	/* 500 ms, if device busy */
192
#define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
193
#define DEF_DISCARD_URGENT_UTIL		80	/* do more discard over 80% */
194
#define DEF_CP_INTERVAL			60	/* 60 secs */
195
#define DEF_IDLE_INTERVAL		5	/* 5 secs */
D
Daniel Rosenberg 已提交
196
#define DEF_DISABLE_INTERVAL		5	/* 5 secs */
197
#define DEF_DISABLE_QUICK_INTERVAL	1	/* 1 secs */
198
#define DEF_UMOUNT_DISCARD_TIMEOUT	5	/* 5 secs */
J
Jaegeuk Kim 已提交
199

200 201
struct cp_control {
	int reason;
202 203 204
	__u64 trim_start;
	__u64 trim_end;
	__u64 trim_minlen;
205 206
};

207
/*
208
 * indicate meta/data type
209 210 211 212
 */
enum {
	META_CP,
	META_NAT,
213
	META_SIT,
214
	META_SSA,
C
Chao Yu 已提交
215
	META_MAX,
216
	META_POR,
C
Chao Yu 已提交
217 218 219 220 221 222 223 224
	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
					 */
225
	META_GENERIC,
226 227
};

J
Jaegeuk Kim 已提交
228 229 230
/* for the list of ino */
enum {
	ORPHAN_INO,		/* for orphan ino list */
231 232
	APPEND_INO,		/* for append ino list */
	UPDATE_INO,		/* for update ino list */
233
	TRANS_DIR_INO,		/* for trasactions dir ino list */
C
Chao Yu 已提交
234
	FLUSH_INO,		/* for multiple device flushing */
J
Jaegeuk Kim 已提交
235 236 237 238
	MAX_INO_ENTRY,		/* max. list */
};

struct ino_entry {
C
Chao Yu 已提交
239 240 241
	struct list_head list;		/* list head */
	nid_t ino;			/* inode number */
	unsigned int dirty_device;	/* dirty device bitmap */
242 243
};

244
/* for the list of inodes to be GCed */
245
struct inode_entry {
246 247 248 249
	struct list_head list;	/* list head */
	struct inode *inode;	/* vfs inode pointer */
};

250 251 252 253 254 255
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
256
/* for the bitmap indicate blocks to be discarded */
257 258
struct discard_entry {
	struct list_head list;	/* list head */
C
Chao Yu 已提交
259 260
	block_t start_blkaddr;	/* start blockaddr of current segment */
	unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];	/* segment discard bitmap */
261 262
};

263 264 265
/* default discard granularity of inner discard thread, unit: block count */
#define DEFAULT_DISCARD_GRANULARITY		16

C
Chao Yu 已提交
266 267 268
/* 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
269
					(MAX_PLIST_NUM - 1) : ((blk_num) - 1))
C
Chao Yu 已提交
270

271
enum {
272 273 274 275
	D_PREP,			/* initial */
	D_PARTIAL,		/* partially submitted */
	D_SUBMIT,		/* all submitted */
	D_DONE,			/* finished */
276 277
};

278 279 280 281 282 283
struct discard_info {
	block_t lstart;			/* logical start address */
	block_t len;			/* length */
	block_t start;			/* actual start address in dev */
};

284
struct discard_cmd {
285 286 287 288 289 290 291 292 293 294
	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 */

	};
295 296
	struct list_head list;		/* command list */
	struct completion wait;		/* compleation */
297
	struct block_device *bdev;	/* bdev */
298
	unsigned short ref;		/* reference count */
299
	unsigned char state;		/* state */
300
	unsigned char queued;		/* queued discard */
301
	int error;			/* bio error */
302 303
	spinlock_t lock;		/* for state/bio_ref updating */
	unsigned short bio_ref;		/* bio reference count */
C
Chao Yu 已提交
304 305
};

C
Chao Yu 已提交
306 307 308 309 310 311 312 313
enum {
	DPOLICY_BG,
	DPOLICY_FORCE,
	DPOLICY_FSTRIM,
	DPOLICY_UMOUNT,
	MAX_DPOLICY,
};

C
Chao Yu 已提交
314
struct discard_policy {
C
Chao Yu 已提交
315
	int type;			/* type of discard */
C
Chao Yu 已提交
316
	unsigned int min_interval;	/* used for candidates exist */
317
	unsigned int mid_interval;	/* used for device busy */
C
Chao Yu 已提交
318 319 320 321 322
	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
323
	bool ordered;			/* issue discard by lba order */
C
Chao Yu 已提交
324
	unsigned int granularity;	/* discard granularity */
325
	int timeout;			/* discard timeout for put_super */
C
Chao Yu 已提交
326 327
};

328
struct discard_cmd_control {
329
	struct task_struct *f2fs_issue_discard;	/* discard thread */
330
	struct list_head entry_list;		/* 4KB discard entry list */
C
Chao Yu 已提交
331
	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
332
	struct list_head wait_list;		/* store on-flushing entries */
333
	struct list_head fstrim_list;		/* in-flight discard from fstrim */
334
	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
335
	unsigned int discard_wake;		/* to wake up discard thread */
336
	struct mutex cmd_lock;
C
Chao Yu 已提交
337 338
	unsigned int nr_discards;		/* # of discards in the list */
	unsigned int max_discards;		/* max. discards to be issued */
339
	unsigned int discard_granularity;	/* discard granularity */
C
Chao Yu 已提交
340
	unsigned int undiscard_blks;		/* # of undiscard blocks */
C
Chao Yu 已提交
341
	unsigned int next_pos;			/* next discard position */
C
Chao Yu 已提交
342
	atomic_t issued_discard;		/* # of issued discard */
343
	atomic_t queued_discard;		/* # of queued discard */
C
Chao Yu 已提交
344
	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
C
Chao Yu 已提交
345
	struct rb_root_cached root;		/* root of discard rb-tree */
346
	bool rbtree_check;			/* config for consistence check */
C
Chao Yu 已提交
347 348
};

349 350 351 352
/* 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 */
353 354
	block_t blkaddr;	/* block address locating the last fsync */
	block_t last_dentry;	/* block address locating the last dentry */
355 356
};

357 358
#define nats_in_cursum(jnl)		(le16_to_cpu((jnl)->n_nats))
#define sits_in_cursum(jnl)		(le16_to_cpu((jnl)->n_sits))
359

360 361 362 363
#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)
364

365 366
#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
367

368
static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
369
{
370
	int before = nats_in_cursum(journal);
371

372
	journal->n_nats = cpu_to_le16(before + i);
373 374 375
	return before;
}

376
static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
377
{
378
	int before = sits_in_cursum(journal);
379

380
	journal->n_sits = cpu_to_le16(before + i);
381 382 383
	return before;
}

384 385
static inline bool __has_cursum_space(struct f2fs_journal *journal,
							int size, int type)
386 387
{
	if (type == NAT_JOURNAL)
388 389
		return size <= MAX_NAT_JENTRIES(journal);
	return size <= MAX_SIT_JENTRIES(journal);
390 391
}

392 393 394
/*
 * ioctl commands
 */
J
Jaegeuk Kim 已提交
395 396
#define F2FS_IOC_GETFLAGS		FS_IOC_GETFLAGS
#define F2FS_IOC_SETFLAGS		FS_IOC_SETFLAGS
C
Chao Yu 已提交
397
#define F2FS_IOC_GETVERSION		FS_IOC_GETVERSION
J
Jaegeuk Kim 已提交
398 399 400 401

#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)
402
#define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
403 404
#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
405
#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
406
#define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
J
Jaegeuk Kim 已提交
407 408
#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
						struct f2fs_defragment)
409 410
#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
						struct f2fs_move_range)
411 412
#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
						struct f2fs_flush_device)
413 414
#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
						struct f2fs_gc_range)
415
#define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
416 417
#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
418
#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
419
#define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
420

C
Chao Yu 已提交
421 422 423
#define F2FS_IOC_GET_VOLUME_NAME	FS_IOC_GETFSLABEL
#define F2FS_IOC_SET_VOLUME_NAME	FS_IOC_SETFSLABEL

424 425 426
#define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
427

J
Jaegeuk Kim 已提交
428 429 430 431 432 433 434 435
/*
 * 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 */
436
#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
437
#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
J
Jaegeuk Kim 已提交
438

439 440 441 442
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
 * ioctl commands in 32 bit emulation
 */
443 444 445
#define F2FS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
#define F2FS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
#define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
446 447
#endif

448 449 450
#define F2FS_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
#define F2FS_IOC_FSSETXATTR		FS_IOC_FSSETXATTR

451 452 453 454 455 456
struct f2fs_gc_range {
	u32 sync;
	u64 start;
	u64 len;
};

C
Chao Yu 已提交
457 458 459 460 461
struct f2fs_defragment {
	u64 start;
	u64 len;
};

462 463 464 465 466 467 468
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 */
};

469 470 471 472 473
struct f2fs_flush_device {
	u32 dev_num;		/* device number to flush */
	u32 segments;		/* # of segments to flush */
};

C
Chao Yu 已提交
474 475
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE	1
476
static inline int get_extra_isize(struct inode *inode);
C
Chao Yu 已提交
477 478 479
static inline int get_inline_xattr_addrs(struct inode *inode);
#define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
				(CUR_ADDRS_PER_INODE(inode) -		\
480
				get_inline_xattr_addrs(inode) -	\
C
Chao Yu 已提交
481
				DEF_INLINE_RESERVED_SIZE))
C
Chao Yu 已提交
482 483 484 485 486

/* 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))
487 488
#define INLINE_DENTRY_BITMAP_SIZE(inode) \
	DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
C
Chao Yu 已提交
489 490 491 492 493
#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)))

494 495 496
/*
 * For INODE and NODE manager
 */
497 498
/* for directory operations */
struct f2fs_dentry_ptr {
499
	struct inode *inode;
500
	void *bitmap;
501 502 503
	struct f2fs_dir_entry *dentry;
	__u8 (*filename)[F2FS_SLOT_LEN];
	int max;
504
	int nr_bitmap;
505 506
};

507 508
static inline void make_dentry_ptr_block(struct inode *inode,
		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
509
{
510
	d->inode = inode;
511
	d->max = NR_DENTRY_IN_BLOCK;
512
	d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
513
	d->bitmap = t->dentry_bitmap;
514 515 516
	d->dentry = t->dentry;
	d->filename = t->filename;
}
517

518
static inline void make_dentry_ptr_inline(struct inode *inode,
C
Chao Yu 已提交
519
					struct f2fs_dentry_ptr *d, void *t)
520
{
C
Chao Yu 已提交
521 522 523 524
	int entry_cnt = NR_INLINE_DENTRY(inode);
	int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
	int reserved_size = INLINE_RESERVED_SIZE(inode);

525
	d->inode = inode;
C
Chao Yu 已提交
526 527 528 529 530 531
	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;
532 533
}

534 535 536 537 538 539 540
/*
 * 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)
541 542 543 544 545
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
546
					 * by get_data_block.
547
					 */
548 549
};

550 551
#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */

552 553 554
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8

555
#define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
556

557 558
#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */

559
/* for in-memory extent cache entry */
560 561 562 563
#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
564

565 566 567 568 569 570
struct rb_entry {
	struct rb_node rb_node;		/* rb node located in rb-tree */
	unsigned int ofs;		/* start offset of the entry */
	unsigned int len;		/* length of the entry */
};

571
struct extent_info {
572 573
	unsigned int fofs;		/* start offset in a file */
	unsigned int len;		/* length of the extent */
574
	u32 blk;			/* start block address of the extent */
575 576 577
};

struct extent_node {
C
Chao Yu 已提交
578 579
	struct rb_node rb_node;		/* rb node located in rb-tree */
	struct extent_info ei;		/* extent info */
580
	struct list_head list;		/* node in global extent list of sbi */
581
	struct extent_tree *et;		/* extent tree pointer */
582 583 584 585
};

struct extent_tree {
	nid_t ino;			/* inode number */
C
Chao Yu 已提交
586
	struct rb_root_cached root;	/* root of extent info rb-tree */
587
	struct extent_node *cached_en;	/* recently accessed extent node */
J
Jaegeuk Kim 已提交
588
	struct extent_info largest;	/* largested extent info */
589
	struct list_head list;		/* to be used by sbi->zombie_list */
590
	rwlock_t lock;			/* protect extent info rb-tree */
591
	atomic_t node_cnt;		/* # of extent node in rb-tree*/
592
	bool largest_updated;		/* largest extent updated */
593 594
};

J
Jaegeuk Kim 已提交
595 596 597 598 599 600 601
/*
 * 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)
602 603 604
#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
605 606 607 608 609 610

struct f2fs_map_blocks {
	block_t m_pblk;
	block_t m_lblk;
	unsigned int m_len;
	unsigned int m_flags;
611
	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
612
	pgoff_t *m_next_extent;		/* point to next possible extent */
613
	int m_seg_type;
C
Chao Yu 已提交
614
	bool m_may_create;		/* indicate it is from write path */
J
Jaegeuk Kim 已提交
615 616
};

C
Chao Yu 已提交
617
/* for flag in get_data_block */
618 619 620 621
enum {
	F2FS_GET_BLOCK_DEFAULT,
	F2FS_GET_BLOCK_FIEMAP,
	F2FS_GET_BLOCK_BMAP,
622
	F2FS_GET_BLOCK_DIO,
623 624
	F2FS_GET_BLOCK_PRE_DIO,
	F2FS_GET_BLOCK_PRE_AIO,
625
	F2FS_GET_BLOCK_PRECACHE,
626
};
C
Chao Yu 已提交
627

628 629 630 631
/*
 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
 */
#define FADVISE_COLD_BIT	0x01
632
#define FADVISE_LOST_PINO_BIT	0x02
633
#define FADVISE_ENCRYPT_BIT	0x04
634
#define FADVISE_ENC_NAME_BIT	0x08
635
#define FADVISE_KEEP_SIZE_BIT	0x10
C
Chao Yu 已提交
636
#define FADVISE_HOT_BIT		0x20
E
Eric Biggers 已提交
637
#define FADVISE_VERITY_BIT	0x40	/* reserved */
638

639 640
#define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)

641 642 643 644 645 646
#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)
647 648 649
#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)
650 651
#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)
652 653
#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
654 655 656
#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)
657

658 659
#define DEF_DIR_LEVEL		0

660 661 662 663 664 665
enum {
	GC_FAILURE_PIN,
	GC_FAILURE_ATOMIC,
	MAX_GC_FAILURE
};

666 667 668 669
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 */
670
	unsigned char i_dir_level;	/* use for dentry level for large dir */
671 672 673
	unsigned int i_current_depth;	/* only for directory depth */
	/* for gc failure statistic */
	unsigned int i_gc_failures[MAX_GC_FAILURE];
674
	unsigned int i_pino;		/* parent inode number */
675 676 677 678
	umode_t i_acl_mode;		/* keep file acl mode temporarily */

	/* Use below internally in f2fs*/
	unsigned long flags;		/* use to pass per-file flags */
679
	struct rw_semaphore i_sem;	/* protect fi info */
680
	atomic_t dirty_pages;		/* # of dirty pages */
681 682
	f2fs_hash_t chash;		/* hash value of given file name */
	unsigned int clevel;		/* maximum level of given file name */
683
	struct task_struct *task;	/* lookup and create consistency */
C
Chao Yu 已提交
684
	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
685
	nid_t i_xattr_nid;		/* node id that contains xattrs */
686
	loff_t	last_disk_size;		/* lastly written file size */
J
Jaegeuk Kim 已提交
687

C
Chao Yu 已提交
688 689 690 691 692 693
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];

	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
694 695
	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
696
	struct list_head inmem_ilist;	/* list for inmem inodes */
J
Jaegeuk Kim 已提交
697
	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
698
	struct task_struct *inmem_task;	/* store inmemory task */
J
Jaegeuk Kim 已提交
699
	struct mutex inmem_lock;	/* lock for inmemory pages */
J
Jaegeuk Kim 已提交
700
	struct extent_tree *extent_tree;	/* cached extent_tree entry */
C
Chao Yu 已提交
701 702 703

	/* avoid racing between foreground op and gc */
	struct rw_semaphore i_gc_rwsem[2];
704
	struct rw_semaphore i_mmap_sem;
705
	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
C
Chao Yu 已提交
706

707
	int i_extra_isize;		/* size of extra space located in i_addr */
C
Chao Yu 已提交
708
	kprojid_t i_projid;		/* id for project quota */
C
Chao Yu 已提交
709
	int i_inline_xattr_size;	/* inline xattr size */
710 711
	struct timespec64 i_crtime;	/* inode creation time */
	struct timespec64 i_disk_time[4];/* inode disk times */
712 713 714
};

static inline void get_extent_info(struct extent_info *ext,
C
Chao Yu 已提交
715
					struct f2fs_extent *i_ext)
716
{
C
Chao Yu 已提交
717 718 719
	ext->fofs = le32_to_cpu(i_ext->fofs);
	ext->blk = le32_to_cpu(i_ext->blk);
	ext->len = le32_to_cpu(i_ext->len);
720 721 722 723 724 725
}

static inline void set_raw_extent(struct extent_info *ext,
					struct f2fs_extent *i_ext)
{
	i_ext->fofs = cpu_to_le32(ext->fofs);
726
	i_ext->blk = cpu_to_le32(ext->blk);
727 728 729
	i_ext->len = cpu_to_le32(ext->len);
}

730 731 732 733 734 735 736 737
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;
}

738
static inline bool __is_discard_mergeable(struct discard_info *back,
739
			struct discard_info *front, unsigned int max_len)
740
{
741
	return (back->lstart + back->len == front->lstart) &&
742
		(back->len + front->len <= max_len);
743 744 745
}

static inline bool __is_discard_back_mergeable(struct discard_info *cur,
746
			struct discard_info *back, unsigned int max_len)
747
{
748
	return __is_discard_mergeable(back, cur, max_len);
749 750 751
}

static inline bool __is_discard_front_mergeable(struct discard_info *cur,
752
			struct discard_info *front, unsigned int max_len)
753
{
754
	return __is_discard_mergeable(cur, front, max_len);
755 756
}

757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775
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);
}

776
extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
777 778
static inline void __try_update_largest_extent(struct extent_tree *et,
						struct extent_node *en)
779
{
780
	if (en->ei.len > et->largest.len) {
781
		et->largest = en->ei;
782
		et->largest_updated = true;
783
	}
784 785
}

C
Chao Yu 已提交
786 787 788 789 790 791 792
/*
 * 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
793 794
};

795 796 797
struct f2fs_nm_info {
	block_t nat_blkaddr;		/* base disk address of NAT */
	nid_t max_nid;			/* maximum possible node ids */
798
	nid_t available_nids;		/* # of available node ids */
799
	nid_t next_scan_nid;		/* the next nid to be scanned */
800
	unsigned int ram_thresh;	/* control the memory footprint */
C
Chao Yu 已提交
801
	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
C
Chao Yu 已提交
802
	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
803 804 805

	/* NAT cache management */
	struct radix_tree_root nat_root;/* root of the nat entry cache */
806
	struct radix_tree_root nat_set_root;/* root of the nat set cache */
807
	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
808
	struct list_head nat_entries;	/* cached nat entry list (clean) */
809
	spinlock_t nat_list_lock;	/* protect clean nat entry list */
810
	unsigned int nat_cnt;		/* the # of cached nat entries */
811
	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
812
	unsigned int nat_blocks;	/* # of nat blocks */
813 814

	/* free node ids management */
815
	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
C
Chao Yu 已提交
816 817
	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
818
	spinlock_t nid_list_lock;	/* protect nid lists ops */
819
	struct mutex build_lock;	/* lock for build free nids */
820
	unsigned char **free_nid_bitmap;
C
Chao Yu 已提交
821
	unsigned char *nat_block_bitmap;
822
	unsigned short *free_nid_count;	/* free nid count of NAT block */
823 824 825

	/* for checkpoint */
	char *nat_bitmap;		/* NAT bitmap pointer */
826 827 828 829 830

	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 */
831 832 833
#ifdef CONFIG_F2FS_CHECK_FS
	char *nat_bitmap_mir;		/* NAT bitmap mirror */
#endif
834 835 836 837 838 839 840 841 842 843 844 845 846 847 848
	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 */
849
	bool node_changed;		/* is node block changed */
850 851
	char cur_level;			/* level of hole node page */
	char max_level;			/* level of current page located */
852 853 854 855 856 857
	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)
{
858
	memset(dn, 0, sizeof(*dn));
859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888
	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)
#define NR_CURSEG_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)

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 */
889
	NO_CHECK_TYPE,
890 891
};

892 893
struct flush_cmd {
	struct completion wait;
894
	struct llist_node llnode;
C
Chao Yu 已提交
895
	nid_t ino;
896 897 898
	int ret;
};

899 900 901
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
902
	atomic_t issued_flush;			/* # of issued flushes */
903
	atomic_t queued_flush;			/* # of queued flushes */
904 905
	struct llist_head issue_list;		/* list for command issue */
	struct llist_node *dispatch_list;	/* list for command dispatch */
906 907
};

908 909 910 911 912 913
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
914 915
	struct rw_semaphore curseg_lock;	/* for preventing curseg change */

916 917 918 919 920 921 922 923
	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 */
924 925 926

	/* a threshold to reclaim prefree segments */
	unsigned int rec_prefree_segments;
927

J
Jaegeuk Kim 已提交
928 929 930
	/* for batched trimming */
	unsigned int trim_sections;		/* # of sections to trim */

931 932
	struct list_head sit_entry_set;	/* sit entry set list */

933 934
	unsigned int ipu_policy;	/* in-place-update policy */
	unsigned int min_ipu_util;	/* in-place-update threshold */
935
	unsigned int min_fsync_blocks;	/* threshold for fsync */
936
	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
937
	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
C
Chao Yu 已提交
938
	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
939 940

	/* for flush command control */
941
	struct flush_cmd_control *fcc_info;
942

943 944
	/* for discard command control */
	struct discard_cmd_control *dcc_info;
945 946 947 948 949 950 951 952 953 954 955
};

/*
 * 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.
 */
956
#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
957 958
enum count_type {
	F2FS_DIRTY_DENTS,
959
	F2FS_DIRTY_DATA,
960
	F2FS_DIRTY_QDATA,
961 962
	F2FS_DIRTY_NODES,
	F2FS_DIRTY_META,
963
	F2FS_INMEM_PAGES,
964
	F2FS_DIRTY_IMETA,
965 966
	F2FS_WB_CP_DATA,
	F2FS_WB_DATA,
967 968 969
	F2FS_RD_DATA,
	F2FS_RD_NODE,
	F2FS_RD_META,
C
Chao Yu 已提交
970 971
	F2FS_DIO_WRITE,
	F2FS_DIO_READ,
972 973 974 975
	NR_COUNT_TYPE,
};

/*
A
arter97 已提交
976
 * The below are the page types of bios used in submit_bio().
977 978 979 980 981 982 983 984 985
 * 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.
 */
986
#define PAGE_TYPE_OF_BIO(type)	((type) > META ? META : (type))
987 988 989 990 991 992
enum page_type {
	DATA,
	NODE,
	META,
	NR_PAGE_TYPE,
	META_FLUSH,
993 994
	INMEM,		/* the below types are used by tracepoints only. */
	INMEM_DROP,
995
	INMEM_INVALIDATE,
996
	INMEM_REVOKE,
997 998
	IPU,
	OPU,
999 1000
};

J
Jaegeuk Kim 已提交
1001 1002 1003 1004 1005 1006 1007
enum temp_type {
	HOT = 0,	/* must be zero for meta bio */
	WARM,
	COLD,
	NR_TEMP_TYPE,
};

1008 1009 1010 1011 1012 1013
enum need_lock_type {
	LOCK_REQ = 0,
	LOCK_DONE,
	LOCK_RETRY,
};

C
Chao Yu 已提交
1014 1015 1016 1017 1018 1019 1020 1021 1022 1023
enum cp_reason_type {
	CP_NO_NEEDED,
	CP_NON_REGULAR,
	CP_HARDLINK,
	CP_SB_NEED_CP,
	CP_WRONG_PINO,
	CP_NO_SPC_ROLL,
	CP_NODE_NEED_CP,
	CP_FASTBOOT_MODE,
	CP_SPEC_LOG_NUM,
1024
	CP_RECOVER_DIR,
C
Chao Yu 已提交
1025 1026
};

C
Chao Yu 已提交
1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
enum iostat_type {
	APP_DIRECT_IO,			/* app direct IOs */
	APP_BUFFERED_IO,		/* app buffered IOs */
	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 */
	FS_DISCARD,			/* discard */
	NR_IO_TYPE,
};

J
Jaegeuk Kim 已提交
1044
struct f2fs_io_info {
1045
	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
C
Chao Yu 已提交
1046
	nid_t ino;		/* inode number */
1047
	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
J
Jaegeuk Kim 已提交
1048
	enum temp_type temp;	/* contains HOT/WARM/COLD */
M
Mike Christie 已提交
1049
	int op;			/* contains REQ_OP_ */
1050
	int op_flags;		/* req_flag_bits */
1051
	block_t new_blkaddr;	/* new block address to be written */
1052
	block_t old_blkaddr;	/* old block address before Cow */
1053
	struct page *page;	/* page to be written */
1054
	struct page *encrypted_page;	/* encrypted page */
1055
	struct list_head list;		/* serialize IOs */
1056
	bool submitted;		/* indicate IO submission */
1057
	int need_lock;		/* indicate we need to lock cp_rwsem */
1058
	bool in_list;		/* indicate fio is in io_list */
C
Chao Yu 已提交
1059
	bool is_por;		/* indicate IO is from recovery or not */
1060
	bool retry;		/* need to reallocate block address */
C
Chao Yu 已提交
1061
	enum iostat_type io_type;	/* io type */
1062
	struct writeback_control *io_wbc; /* writeback control */
C
Chao Yu 已提交
1063 1064
	struct bio **bio;		/* bio for ipu */
	sector_t *last_block;		/* last block number in bio */
1065
	unsigned char version;		/* version of the node */
J
Jaegeuk Kim 已提交
1066 1067
};

1068
#define is_read_io(rw) ((rw) == READ)
1069
struct f2fs_bio_info {
J
Jaegeuk Kim 已提交
1070
	struct f2fs_sb_info *sbi;	/* f2fs superblock */
1071 1072
	struct bio *bio;		/* bios to merge */
	sector_t last_block_in_bio;	/* last block number */
J
Jaegeuk Kim 已提交
1073
	struct f2fs_io_info fio;	/* store buffered io info. */
1074
	struct rw_semaphore io_rwsem;	/* blocking op for bio */
1075 1076
	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
	struct list_head io_list;	/* track fios */
1077 1078
};

J
Jaegeuk Kim 已提交
1079 1080 1081 1082 1083 1084 1085 1086 1087
#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
1088 1089
	unsigned int nr_blkz;		/* Total number of zones */
	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
J
Jaegeuk Kim 已提交
1090 1091 1092
#endif
};

1093 1094 1095
enum inode_type {
	DIR_INODE,			/* for dirty dir inode */
	FILE_INODE,			/* for dirty regular/symlink inode */
1096
	DIRTY_META,			/* for all dirtied inode metadata */
J
Jaegeuk Kim 已提交
1097
	ATOMIC_FILE,			/* for all atomic files */
1098 1099 1100
	NR_INODE_TYPE,
};

1101 1102 1103 1104 1105 1106 1107 1108
/* 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 */
};

1109 1110 1111 1112 1113 1114
/* 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 */
1115
	SBI_NEED_SB_WRITE,			/* need to recover superblock */
1116
	SBI_NEED_CP,				/* need to checkpoint */
1117
	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
1118
	SBI_IS_RECOVERED,			/* recovered orphan/data */
D
Daniel Rosenberg 已提交
1119
	SBI_CP_DISABLED,			/* CP was disabled last mount */
1120
	SBI_CP_DISABLED_QUICK,			/* CP was disabled quickly */
1121 1122 1123
	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 */
1124
	SBI_IS_RESIZEFS,			/* resizefs is in process */
1125 1126
};

1127 1128
enum {
	CP_TIME,
1129
	REQ_TIME,
1130 1131
	DISCARD_TIME,
	GC_TIME,
D
Daniel Rosenberg 已提交
1132
	DISABLE_TIME,
1133
	UMOUNT_DISCARD_TIMEOUT,
1134 1135 1136
	MAX_TIME,
};

1137 1138 1139 1140 1141 1142 1143
enum {
	GC_NORMAL,
	GC_IDLE_CB,
	GC_IDLE_GREEDY,
	GC_URGENT,
};

1144 1145 1146
enum {
	WHINT_MODE_OFF,		/* not pass down write hints */
	WHINT_MODE_USER,	/* try to pass down hints given by users */
1147
	WHINT_MODE_FS,		/* pass down hints with F2FS policy */
1148 1149
};

1150 1151 1152 1153 1154
enum {
	ALLOC_MODE_DEFAULT,	/* stay default */
	ALLOC_MODE_REUSE,	/* reuse segments as much as possible */
};

1155 1156 1157
enum fsync_mode {
	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
1158
	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
1159 1160
};

1161
#ifdef CONFIG_FS_ENCRYPTION
1162 1163 1164 1165 1166 1167
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
			(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif

1168 1169
struct f2fs_sb_info {
	struct super_block *sb;			/* pointer to VFS super block */
1170
	struct proc_dir_entry *s_proc;		/* proc entry */
1171
	struct f2fs_super_block *raw_super;	/* raw super block pointer */
1172
	struct rw_semaphore sb_lock;		/* lock for raw super block */
1173
	int valid_super_block;			/* valid super block no */
1174
	unsigned long s_flag;				/* flags for sbi */
1175
	struct mutex writepages;		/* mutex for writepages() */
1176 1177 1178 1179
#ifdef CONFIG_UNICODE
	struct unicode_map *s_encoding;
	__u16 s_encoding_flags;
#endif
1180

1181 1182 1183 1184 1185
#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

1186 1187 1188 1189 1190 1191
	/* 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 */
1192 1193

	/* for bio operations */
J
Jaegeuk Kim 已提交
1194
	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
1195 1196
	/* keep migration IO order for LFS mode */
	struct rw_semaphore io_order_lock;
1197
	mempool_t *write_io_dummy;		/* Dummy pages */
1198 1199 1200

	/* for checkpoint */
	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
1201
	int cur_cp_pack;			/* remain current cp pack */
1202
	spinlock_t cp_lock;			/* for flag in ckpt */
1203
	struct inode *meta_inode;		/* cache meta blocks */
1204
	struct mutex cp_mutex;			/* checkpoint procedure lock */
1205
	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
1206
	struct rw_semaphore node_write;		/* locking node writes */
1207
	struct rw_semaphore node_change;	/* locking node change */
1208
	wait_queue_head_t cp_wait;
1209 1210
	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
	long interval_time[MAX_TIME];		/* to store thresholds */
1211

1212
	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
J
Jaegeuk Kim 已提交
1213

1214 1215 1216 1217 1218
	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
1219
	/* for orphan inode, use 0'th array */
1220
	unsigned int max_orphans;		/* max orphan inodes */
1221

1222 1223 1224
	/* 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 */
1225
	struct mutex flush_lock;		/* for flush exclusion */
1226

1227 1228
	/* for extent tree cache */
	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
1229
	struct mutex extent_tree_lock;	/* locking extent radix tree */
1230 1231
	struct list_head extent_list;		/* lru list for shrinker */
	spinlock_t extent_lock;			/* locking extent lru list */
1232
	atomic_t total_ext_tree;		/* extent tree count */
1233
	struct list_head zombie_list;		/* extent zombie tree list */
1234
	atomic_t total_zombie_tree;		/* extent zombie tree count */
1235 1236
	atomic_t total_ext_node;		/* extent info count */

A
arter97 已提交
1237
	/* basic filesystem units */
1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248
	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 */
1249
	struct mutex resize_mutex;		/* for resize exclusion */
1250 1251
	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
1252
	loff_t max_file_blocks;			/* max block index of file */
1253
	int dir_level;				/* directory level */
1254
	int readdir_ra;				/* readahead inode in readdir */
1255 1256 1257

	block_t user_block_count;		/* # of user blocks */
	block_t total_valid_block_count;	/* # of valid blocks */
1258
	block_t discard_blks;			/* discard command candidats */
1259
	block_t last_valid_block_count;		/* for recovery */
1260
	block_t reserved_blocks;		/* configurable reserved blocks */
1261
	block_t current_reserved_blocks;	/* current reserved blocks */
1262

D
Daniel Rosenberg 已提交
1263 1264 1265
	/* Additional tracking for no checkpoint mode */
	block_t unusable_block_count;		/* # of blocks saved by last cp */

1266
	unsigned int nquota_files;		/* # of quota sysfile */
1267
	struct rw_semaphore quota_sem;		/* blocking cp for flags */
1268

1269
	/* # of pages, see count_type */
1270
	atomic_t nr_pages[NR_COUNT_TYPE];
1271 1272
	/* # of allocated blocks */
	struct percpu_counter alloc_valid_block_count;
1273

1274
	/* writeback control */
1275
	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
1276

1277 1278 1279
	/* valid inode count */
	struct percpu_counter total_valid_inode_count;

1280 1281 1282 1283 1284
	struct f2fs_mount_info mount_opt;	/* mount options */

	/* for cleaning operations */
	struct mutex gc_mutex;			/* mutex for GC */
	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
1285
	unsigned int cur_victim_sec;		/* current victim section num */
1286
	unsigned int gc_mode;			/* current GC state */
1287
	unsigned int next_victim_seg[2];	/* next segment in victim section */
1288 1289
	/* for skip statistic */
	unsigned long long skipped_atomic_files[2];	/* FG_GC and BG_GC */
1290
	unsigned long long skipped_gc_rwsem;		/* FG_GC only */
1291

1292 1293 1294
	/* threshold for gc trials on pinned files */
	u64 gc_pin_file_threshold;

1295 1296
	/* maximum # of trials to find a victim segment for SSR and GC */
	unsigned int max_victim_search;
1297 1298
	/* migration granularity of garbage collection, unit: segment */
	unsigned int migration_granularity;
1299

1300 1301 1302 1303
	/*
	 * for stat information.
	 * one is for the LFS mode, and the other is for the SSR mode.
	 */
1304
#ifdef CONFIG_F2FS_STAT_FS
1305
	struct f2fs_stat_info *stat_info;	/* FS status information */
C
Chao Yu 已提交
1306
	atomic_t meta_count[META_MAX];		/* # of meta blocks */
1307 1308
	unsigned int segment_count[2];		/* # of allocated segments */
	unsigned int block_count[2];		/* # of allocated blocks */
1309
	atomic_t inplace_count;		/* # of inplace update */
1310 1311 1312 1313
	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
1314
	atomic_t inline_xattr;			/* # of inline_xattr inodes */
1315 1316
	atomic_t inline_inode;			/* # of inline_data inodes */
	atomic_t inline_dir;			/* # of inline_dentry inodes */
1317
	atomic_t aw_cnt;			/* # of atomic writes */
1318
	atomic_t vw_cnt;			/* # of volatile writes */
1319
	atomic_t max_aw_cnt;			/* max # of atomic writes */
1320
	atomic_t max_vw_cnt;			/* max # of volatile writes */
1321
	int bg_gc;				/* background gc calls */
1322 1323
	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
1324
	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
1325
#endif
1326
	spinlock_t stat_lock;			/* lock for stat operations */
1327

C
Chao Yu 已提交
1328 1329 1330 1331 1332
	/* For app/fs IO statistics */
	spinlock_t iostat_lock;
	unsigned long long write_iostat[NR_IO_TYPE];
	bool iostat_enable;

1333 1334 1335
	/* For sysfs suppport */
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1336 1337 1338

	/* For shrinker support */
	struct list_head s_list;
J
Jaegeuk Kim 已提交
1339 1340
	int s_ndevs;				/* number of devices */
	struct f2fs_dev_info *devs;		/* for device list */
1341 1342
	unsigned int dirty_device;		/* for checkpoint data flush */
	spinlock_t dev_lock;			/* protect dirty_device */
1343 1344
	struct mutex umount_mutex;
	unsigned int shrinker_run_no;
1345 1346 1347 1348

	/* For write statistics */
	u64 sectors_written_start;
	u64 kbytes_written;
K
Keith Mok 已提交
1349 1350 1351

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1352

C
Chao Yu 已提交
1353 1354
	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_chksum_seed;
1355 1356
};

C
Chao Yu 已提交
1357 1358 1359 1360 1361 1362 1363
struct f2fs_private_dio {
	struct inode *inode;
	void *orig_private;
	bio_end_io_t *orig_end_io;
	bool write;
};

1364
#ifdef CONFIG_F2FS_FAULT_INJECTION
1365
#define f2fs_show_injection_info(type)					\
1366
	printk_ratelimited("%sF2FS-fs : inject %s in %s of %pS\n",	\
1367
		KERN_INFO, f2fs_fault_name[type],			\
1368
		__func__, __builtin_return_address(0))
1369 1370
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
1371
	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385

	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;
}
1386 1387 1388 1389 1390 1391
#else
#define f2fs_show_injection_info(type) do { } while (0)
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
	return false;
}
1392 1393
#endif

1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404
/*
 * 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;
}

1405 1406 1407 1408
/* 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)						 \
1409
(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
1410
		(s)->sectors_written_start) >> 1)
1411

1412 1413
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
1414 1415 1416 1417 1418 1419 1420 1421 1422
	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;
	}
1423 1424 1425 1426
}

static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
A
Arnd Bergmann 已提交
1427
	unsigned long interval = sbi->interval_time[type] * HZ;
1428 1429 1430 1431

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

1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
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;
}

1446 1447 1448
/*
 * Inline functions
 */
C
Chao Yu 已提交
1449
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
C
Chao Yu 已提交
1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468
			      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
1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486
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);
}

1487 1488 1489 1490 1491 1492 1493 1494 1495 1496
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;
}

1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508
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
1509
	return F2FS_M_SB(page_file_mapping(page));
1510 1511
}

1512 1513 1514 1515 1516 1517 1518 1519 1520 1521
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);
}

1522 1523 1524 1525 1526
static inline struct f2fs_node *F2FS_NODE(struct page *page)
{
	return (struct f2fs_node *)page_address(page);
}

1527 1528 1529 1530 1531
static inline struct f2fs_inode *F2FS_INODE(struct page *page)
{
	return &((struct f2fs_node *)page_address(page))->i;
}

1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556
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
1557 1558 1559 1560 1561
static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->meta_inode->i_mapping;
}

1562 1563 1564 1565 1566
static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->node_inode->i_mapping;
}

1567 1568
static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
1569
	return test_bit(type, &sbi->s_flag);
1570 1571 1572
}

static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1573
{
1574
	set_bit(type, &sbi->s_flag);
1575 1576
}

1577
static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1578
{
1579
	clear_bit(type, &sbi->s_flag);
1580 1581
}

1582 1583 1584 1585 1586
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
1587 1588 1589 1590 1591 1592 1593
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;
}

1594 1595 1596 1597 1598 1599
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)));
}

1600
static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1601 1602
{
	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1603

1604 1605 1606
	return ckpt_flags & f;
}

1607
static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1608
{
1609 1610 1611 1612 1613 1614 1615 1616
	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);
1617 1618 1619 1620
	ckpt_flags |= f;
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1621
static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1622
{
1623 1624 1625
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1626
	__set_ckpt_flags(F2FS_CKPT(sbi), f);
1627
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1628 1629 1630 1631 1632 1633 1634
}

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);
1635 1636 1637 1638
	ckpt_flags &= (~f);
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1639 1640
static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
1641 1642 1643
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1644
	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
1645
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1646 1647
}

1648 1649
static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
1650
	unsigned long flags;
1651
	unsigned char *nat_bits;
1652

1653 1654 1655 1656 1657
	/*
	 * 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.
	 */
1658 1659

	if (lock)
1660
		spin_lock_irqsave(&sbi->cp_lock, flags);
1661
	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
1662
	nat_bits = NM_I(sbi)->nat_bits;
1663 1664
	NM_I(sbi)->nat_bits = NULL;
	if (lock)
1665
		spin_unlock_irqrestore(&sbi->cp_lock, flags);
1666 1667

	kvfree(nat_bits);
1668 1669 1670 1671 1672 1673 1674
}

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);

1675
	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
1676 1677
}

1678
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
1679
{
1680
	down_read(&sbi->cp_rwsem);
1681 1682
}

1683 1684 1685 1686 1687
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
	return down_read_trylock(&sbi->cp_rwsem);
}

1688
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
1689
{
1690
	up_read(&sbi->cp_rwsem);
1691 1692
}

1693
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
1694
{
1695
	down_write(&sbi->cp_rwsem);
1696 1697
}

1698
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
1699
{
1700
	up_write(&sbi->cp_rwsem);
1701 1702
}

1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715
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)
{
1716
	return (reason & (CP_UMOUNT | CP_FASTBOOT));
1717 1718 1719 1720
}

static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
{
1721 1722
	return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
			is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
1723 1724
}

1725 1726 1727 1728 1729
/*
 * Check whether the inode has blocks or not
 */
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
1730 1731
	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;

1732
	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
1733 1734
}

1735 1736 1737 1738 1739
static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
	return ofs == XATTR_NODE_OFFSET;
}

1740
static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
1741
					struct inode *inode, bool cap)
1742
{
1743 1744
	if (!inode)
		return true;
1745 1746
	if (!test_opt(sbi, RESERVE_ROOT))
		return false;
1747 1748
	if (IS_NOQUOTA(inode))
		return true;
1749
	if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
1750
		return true;
1751 1752
	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
					in_group_p(F2FS_OPTION(sbi).s_resgid))
1753
		return true;
1754
	if (cap && capable(CAP_SYS_RESOURCE))
1755
		return true;
1756 1757 1758
	return false;
}

C
Chao Yu 已提交
1759 1760
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,
1761
				 struct inode *inode, blkcnt_t *count)
1762
{
C
Chao Yu 已提交
1763
	blkcnt_t diff = 0, release = 0;
1764
	block_t avail_user_block_count;
C
Chao Yu 已提交
1765 1766 1767 1768 1769
	int ret;

	ret = dquot_reserve_block(inode, *count);
	if (ret)
		return ret;
1770

1771 1772
	if (time_to_inject(sbi, FAULT_BLOCK)) {
		f2fs_show_injection_info(FAULT_BLOCK);
C
Chao Yu 已提交
1773
		release = *count;
1774
		goto release_quota;
1775
	}
1776

1777 1778 1779 1780 1781 1782
	/*
	 * 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));

1783 1784
	spin_lock(&sbi->stat_lock);
	sbi->total_valid_block_count += (block_t)(*count);
1785 1786
	avail_user_block_count = sbi->user_block_count -
					sbi->current_reserved_blocks;
1787

1788
	if (!__allow_reserved_blocks(sbi, inode, true))
1789
		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
1790 1791 1792 1793 1794 1795
	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;
	}
1796 1797
	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
		diff = sbi->total_valid_block_count - avail_user_block_count;
1798 1799
		if (diff > *count)
			diff = *count;
1800
		*count -= diff;
C
Chao Yu 已提交
1801
		release = diff;
1802
		sbi->total_valid_block_count -= diff;
1803 1804
		if (!*count) {
			spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
1805
			goto enospc;
1806
		}
1807 1808
	}
	spin_unlock(&sbi->stat_lock);
1809

1810 1811
	if (unlikely(release)) {
		percpu_counter_sub(&sbi->alloc_valid_block_count, release);
C
Chao Yu 已提交
1812
		dquot_release_reservation_block(inode, release);
1813
	}
C
Chao Yu 已提交
1814 1815 1816 1817
	f2fs_i_blocks_write(inode, *count, true, true);
	return 0;

enospc:
1818
	percpu_counter_sub(&sbi->alloc_valid_block_count, release);
1819
release_quota:
C
Chao Yu 已提交
1820 1821
	dquot_release_reservation_block(inode, release);
	return -ENOSPC;
1822 1823
}

1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837
__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__)

1838
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
1839
						struct inode *inode,
1840
						block_t count)
1841
{
1842 1843
	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;

1844
	spin_lock(&sbi->stat_lock);
1845
	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
1846
	sbi->total_valid_block_count -= (block_t)count;
1847 1848 1849 1850
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
					sbi->current_reserved_blocks + count);
1851
	spin_unlock(&sbi->stat_lock);
1852
	if (unlikely(inode->i_blocks < sectors)) {
1853 1854 1855 1856
		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);
1857 1858 1859
		set_sbi_flag(sbi, SBI_NEED_FSCK);
		return;
	}
C
Chao Yu 已提交
1860
	f2fs_i_blocks_write(inode, count, false, true);
1861 1862 1863 1864
}

static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1865
	atomic_inc(&sbi->nr_pages[count_type]);
1866

C
Chao Yu 已提交
1867 1868 1869 1870 1871 1872
	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);
1873 1874
}

1875
static inline void inode_inc_dirty_pages(struct inode *inode)
1876
{
1877
	atomic_inc(&F2FS_I(inode)->dirty_pages);
1878 1879
	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1880 1881
	if (IS_NOQUOTA(inode))
		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1882 1883 1884 1885
}

static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1886
	atomic_dec(&sbi->nr_pages[count_type]);
1887 1888
}

1889
static inline void inode_dec_dirty_pages(struct inode *inode)
1890
{
1891 1892
	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
			!S_ISLNK(inode->i_mode))
1893 1894
		return;

1895
	atomic_dec(&F2FS_I(inode)->dirty_pages);
1896 1897
	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1898 1899
	if (IS_NOQUOTA(inode))
		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1900 1901
}

1902
static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
1903
{
1904
	return atomic_read(&sbi->nr_pages[count_type]);
1905 1906
}

1907
static inline int get_dirty_pages(struct inode *inode)
1908
{
1909
	return atomic_read(&F2FS_I(inode)->dirty_pages);
1910 1911
}

1912 1913
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
1914
	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
1915 1916 1917 1918
	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
						sbi->log_blocks_per_seg;

	return segs / sbi->segs_per_sec;
1919 1920
}

1921 1922
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
1923
	return sbi->total_valid_block_count;
1924 1925
}

1926 1927 1928 1929 1930
static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
{
	return sbi->discard_blks;
}

1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943
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
1944 1945 1946 1947 1948
static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
	return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

1949 1950 1951
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
1952 1953
	int offset;

C
Chao Yu 已提交
1954 1955 1956
	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
		offset = (flag == SIT_BITMAP) ?
			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
1957 1958 1959 1960 1961
		/*
		 * 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
1962 1963
	}

W
Wanpeng Li 已提交
1964
	if (__cp_payload(sbi) > 0) {
C
Changman Lee 已提交
1965 1966 1967
		if (flag == NAT_BITMAP)
			return &ckpt->sit_nat_version_bitmap;
		else
J
Jaegeuk Kim 已提交
1968
			return (unsigned char *)ckpt + F2FS_BLKSIZE;
C
Changman Lee 已提交
1969 1970
	} else {
		offset = (flag == NAT_BITMAP) ?
1971
			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
C
Changman Lee 已提交
1972 1973
		return &ckpt->sit_nat_version_bitmap + offset;
	}
1974 1975 1976 1977
}

static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
1978
	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
1979

1980
	if (sbi->cur_cp_pack == 2)
1981
		start_addr += sbi->blocks_per_seg;
1982 1983
	return start_addr;
}
1984

1985 1986 1987
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);
1988

1989 1990
	if (sbi->cur_cp_pack == 1)
		start_addr += sbi->blocks_per_seg;
1991 1992 1993
	return start_addr;
}

1994 1995 1996 1997 1998
static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
{
	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
}

1999 2000 2001 2002 2003
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
2004
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
2005
					struct inode *inode, bool is_inode)
2006 2007
{
	block_t	valid_block_count;
2008
	unsigned int valid_node_count, user_block_count;
2009
	int err;
C
Chao Yu 已提交
2010

2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
	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
2021
	}
2022

2023 2024 2025 2026 2027
	if (time_to_inject(sbi, FAULT_BLOCK)) {
		f2fs_show_injection_info(FAULT_BLOCK);
		goto enospc;
	}

2028 2029
	spin_lock(&sbi->stat_lock);

2030 2031 2032
	valid_block_count = sbi->total_valid_block_count +
					sbi->current_reserved_blocks + 1;

2033
	if (!__allow_reserved_blocks(sbi, inode, false))
2034
		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
2035
	user_block_count = sbi->user_block_count;
D
Daniel Rosenberg 已提交
2036
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
2037
		user_block_count -= sbi->unusable_block_count;
2038

2039
	if (unlikely(valid_block_count > user_block_count)) {
2040
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2041
		goto enospc;
2042 2043
	}

2044
	valid_node_count = sbi->total_valid_node_count + 1;
2045
	if (unlikely(valid_node_count > sbi->total_node_count)) {
2046
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2047
		goto enospc;
2048 2049
	}

2050 2051
	sbi->total_valid_node_count++;
	sbi->total_valid_block_count++;
2052 2053
	spin_unlock(&sbi->stat_lock);

2054 2055 2056 2057
	if (inode) {
		if (is_inode)
			f2fs_mark_inode_dirty_sync(inode, true);
		else
C
Chao Yu 已提交
2058
			f2fs_i_blocks_write(inode, 1, true, true);
2059
	}
2060

2061
	percpu_counter_inc(&sbi->alloc_valid_block_count);
C
Chao Yu 已提交
2062 2063 2064
	return 0;

enospc:
2065 2066 2067 2068
	if (is_inode) {
		if (inode)
			dquot_free_inode(inode);
	} else {
C
Chao Yu 已提交
2069
		dquot_release_reservation_block(inode, 1);
2070
	}
C
Chao Yu 已提交
2071
	return -ENOSPC;
2072 2073 2074
}

static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
2075
					struct inode *inode, bool is_inode)
2076 2077 2078
{
	spin_lock(&sbi->stat_lock);

2079 2080
	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
2081

2082 2083
	sbi->total_valid_node_count--;
	sbi->total_valid_block_count--;
2084 2085 2086
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks++;
2087 2088

	spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2089

2090
	if (is_inode) {
2091
		dquot_free_inode(inode);
2092 2093
	} else {
		if (unlikely(inode->i_blocks == 0)) {
2094 2095 2096
			f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
				  inode->i_ino,
				  (unsigned long long)inode->i_blocks);
2097 2098 2099
			set_sbi_flag(sbi, SBI_NEED_FSCK);
			return;
		}
C
Chao Yu 已提交
2100
		f2fs_i_blocks_write(inode, 1, false, true);
2101
	}
2102 2103 2104 2105
}

static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
{
2106
	return sbi->total_valid_node_count;
2107 2108 2109 2110
}

static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
2111
	percpu_counter_inc(&sbi->total_valid_inode_count);
2112 2113
}

2114
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
2115
{
2116
	percpu_counter_dec(&sbi->total_valid_inode_count);
2117 2118
}

2119
static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
2120
{
2121
	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
2122 2123
}

2124 2125 2126
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
						pgoff_t index, bool for_write)
{
2127
	struct page *page;
2128

2129 2130 2131 2132 2133 2134 2135 2136
	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;
2137

2138 2139 2140 2141
		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
			f2fs_show_injection_info(FAULT_PAGE_ALLOC);
			return NULL;
		}
2142
	}
2143

2144 2145 2146 2147 2148
	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
2149 2150 2151 2152 2153 2154 2155 2156
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)) {
		f2fs_show_injection_info(FAULT_PAGE_GET);
		return NULL;
	}
2157

C
Chao Yu 已提交
2158 2159 2160
	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}

2161 2162 2163 2164 2165 2166 2167 2168 2169 2170
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);
}

2171 2172
static inline void f2fs_put_page(struct page *page, int unlock)
{
2173
	if (!page)
2174 2175 2176
		return;

	if (unlock) {
2177
		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
2178 2179
		unlock_page(page);
	}
2180
	put_page(page);
2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193
}

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,
2194
					size_t size)
2195
{
2196
	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
2197 2198
}

2199 2200 2201 2202 2203
static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
						gfp_t flags)
{
	void *entry;

2204 2205 2206
	entry = kmem_cache_alloc(cachep, flags);
	if (!entry)
		entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
2207 2208 2209
	return entry;
}

2210 2211
static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
						int npages, bool no_fail)
J
Jaegeuk Kim 已提交
2212 2213 2214
{
	struct bio *bio;

2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225
	if (no_fail) {
		/* No failure on bio allocation */
		bio = bio_alloc(GFP_NOIO, npages);
		if (!bio)
			bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
		return bio;
	}
	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
		f2fs_show_injection_info(FAULT_ALLOC_BIO);
		return NULL;
	}
2226

2227
	return bio_alloc(GFP_KERNEL, npages);
J
Jaegeuk Kim 已提交
2228 2229
}

2230 2231
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
2232 2233 2234
	if (sbi->gc_mode == GC_URGENT)
		return true;

2235 2236
	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) ||
2237 2238
		get_pages(sbi, F2FS_WB_CP_DATA) ||
		get_pages(sbi, F2FS_DIO_READ) ||
2239
		get_pages(sbi, F2FS_DIO_WRITE))
2240
		return false;
2241

2242
	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
2243 2244 2245 2246 2247 2248 2249
			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;

2250 2251 2252
	return f2fs_time_over(sbi, type);
}

2253 2254 2255 2256 2257 2258 2259
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();
}

2260 2261 2262 2263
#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)

static inline bool IS_INODE(struct page *page)
{
2264
	struct f2fs_node *p = F2FS_NODE(page);
2265

2266 2267 2268
	return RAW_IS_INODE(p);
}

2269 2270 2271 2272 2273 2274
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;
}

2275 2276 2277 2278 2279
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}

2280 2281 2282
static inline int f2fs_has_extra_attr(struct inode *inode);
static inline block_t datablock_addr(struct inode *inode,
			struct page *node_page, unsigned int offset)
2283 2284 2285
{
	struct f2fs_node *raw_node;
	__le32 *addr_array;
2286 2287
	int base = 0;
	bool is_inode = IS_INODE(node_page);
2288

2289
	raw_node = F2FS_NODE(node_page);
2290 2291

	/* from GC path only */
2292 2293
	if (is_inode) {
		if (!inode)
2294
			base = offset_in_addr(&raw_node->i);
2295 2296
		else if (f2fs_has_extra_attr(inode))
			base = get_extra_isize(inode);
2297 2298
	}

2299
	addr_array = blkaddr_in_node(raw_node);
2300
	return le32_to_cpu(addr_array[base + offset]);
2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311
}

static inline int f2fs_test_bit(unsigned int nr, char *addr)
{
	int mask;

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

2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329
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;
}

2330
static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341
{
	int mask;
	int ret;

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

2342
static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353
{
	int mask;
	int ret;

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

2354 2355 2356 2357 2358 2359 2360 2361 2362
static inline void f2fs_change_bit(unsigned int nr, char *addr)
{
	int mask;

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

2363
/*
2364
 * On-disk inode flags (f2fs_inode::i_flags)
2365 2366 2367 2368 2369 2370 2371 2372 2373
 */
#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 */
#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 */
2374
#define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
2375 2376

/* Flags that should be inherited by new inodes from their parent. */
2377
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
2378 2379
			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
			   F2FS_CASEFOLD_FL)
2380 2381

/* Flags that are appropriate for regular files (all but dir-specific ones). */
2382 2383
#define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
				F2FS_CASEFOLD_FL))
2384 2385 2386

/* 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
2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397

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;
}

2398 2399 2400
/* used for f2fs_inode_info->flags */
enum {
	FI_NEW_INODE,		/* indicate newly allocated inode */
2401
	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
2402
	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
2403
	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
2404 2405 2406
	FI_INC_LINK,		/* need to increment i_nlink */
	FI_ACL_MODE,		/* indicate acl mode */
	FI_NO_ALLOC,		/* should not allocate any blocks */
2407
	FI_FREE_NID,		/* free allocated nide */
2408
	FI_NO_EXTENT,		/* not to use the extent cache */
J
Jaegeuk Kim 已提交
2409
	FI_INLINE_XATTR,	/* used for inline xattr */
2410
	FI_INLINE_DATA,		/* used for inline data*/
2411
	FI_INLINE_DENTRY,	/* used for inline dentry */
2412 2413
	FI_APPEND_WRITE,	/* inode has appended data */
	FI_UPDATE_WRITE,	/* inode has in-place-update data */
J
Jaegeuk Kim 已提交
2414 2415
	FI_NEED_IPU,		/* used for ipu per file */
	FI_ATOMIC_FILE,		/* indicate atomic file */
C
Chao Yu 已提交
2416
	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
2417
	FI_VOLATILE_FILE,	/* indicate volatile file */
2418
	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
2419
	FI_DROP_CACHE,		/* drop dirty page cache */
2420
	FI_DATA_EXIST,		/* indicate data exists */
2421
	FI_INLINE_DOTS,		/* indicate inline dot dentries */
C
Chao Yu 已提交
2422
	FI_DO_DEFRAG,		/* indicate defragment is running */
2423
	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
2424
	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
2425
	FI_HOT_DATA,		/* indicate file is hot */
2426
	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
C
Chao Yu 已提交
2427
	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
2428
	FI_PIN_FILE,		/* indicate file should not be gced */
2429
	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
2430 2431
};

2432 2433 2434 2435 2436 2437 2438
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:
2439
	case FI_NEW_INODE:
2440 2441
		if (set)
			return;
2442
		/* fall through */
2443 2444
	case FI_DATA_EXIST:
	case FI_INLINE_DOTS:
2445
	case FI_PIN_FILE:
2446
		f2fs_mark_inode_dirty_sync(inode, true);
2447 2448 2449
	}
}

2450
static inline void set_inode_flag(struct inode *inode, int flag)
2451
{
2452 2453
	if (!test_bit(flag, &F2FS_I(inode)->flags))
		set_bit(flag, &F2FS_I(inode)->flags);
2454
	__mark_inode_dirty_flag(inode, flag, true);
2455 2456
}

2457
static inline int is_inode_flag_set(struct inode *inode, int flag)
2458
{
2459
	return test_bit(flag, &F2FS_I(inode)->flags);
2460 2461
}

2462
static inline void clear_inode_flag(struct inode *inode, int flag)
2463
{
2464 2465
	if (test_bit(flag, &F2FS_I(inode)->flags))
		clear_bit(flag, &F2FS_I(inode)->flags);
2466
	__mark_inode_dirty_flag(inode, flag, false);
2467 2468
}

2469
static inline void set_acl_inode(struct inode *inode, umode_t mode)
2470
{
2471 2472
	F2FS_I(inode)->i_acl_mode = mode;
	set_inode_flag(inode, FI_ACL_MODE);
2473
	f2fs_mark_inode_dirty_sync(inode, false);
2474 2475
}

2476
static inline void f2fs_i_links_write(struct inode *inode, bool inc)
2477
{
2478 2479 2480 2481
	if (inc)
		inc_nlink(inode);
	else
		drop_nlink(inode);
2482
	f2fs_mark_inode_dirty_sync(inode, true);
2483 2484
}

2485
static inline void f2fs_i_blocks_write(struct inode *inode,
C
Chao Yu 已提交
2486
					block_t diff, bool add, bool claim)
2487
{
2488 2489 2490
	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
2491 2492 2493 2494 2495 2496 2497 2498 2499 2500
	/* 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);
	}

2501
	f2fs_mark_inode_dirty_sync(inode, true);
2502 2503
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2504 2505
}

2506 2507
static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
2508 2509 2510
	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

2511 2512 2513 2514
	if (i_size_read(inode) == i_size)
		return;

	i_size_write(inode, i_size);
2515
	f2fs_mark_inode_dirty_sync(inode, true);
2516 2517
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2518 2519
}

2520
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
2521
{
2522
	F2FS_I(inode)->i_current_depth = depth;
2523
	f2fs_mark_inode_dirty_sync(inode, true);
2524 2525
}

2526 2527 2528
static inline void f2fs_i_gc_failures_write(struct inode *inode,
					unsigned int count)
{
2529
	F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
2530 2531 2532
	f2fs_mark_inode_dirty_sync(inode, true);
}

2533
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
J
Jaegeuk Kim 已提交
2534
{
2535
	F2FS_I(inode)->i_xattr_nid = xnid;
2536
	f2fs_mark_inode_dirty_sync(inode, true);
2537 2538 2539 2540 2541
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
	F2FS_I(inode)->i_pino = pino;
2542
	f2fs_mark_inode_dirty_sync(inode, true);
2543 2544
}

2545
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2546
{
2547 2548
	struct f2fs_inode_info *fi = F2FS_I(inode);

J
Jaegeuk Kim 已提交
2549
	if (ri->i_inline & F2FS_INLINE_XATTR)
2550
		set_bit(FI_INLINE_XATTR, &fi->flags);
2551
	if (ri->i_inline & F2FS_INLINE_DATA)
2552
		set_bit(FI_INLINE_DATA, &fi->flags);
2553
	if (ri->i_inline & F2FS_INLINE_DENTRY)
2554
		set_bit(FI_INLINE_DENTRY, &fi->flags);
2555
	if (ri->i_inline & F2FS_DATA_EXIST)
2556
		set_bit(FI_DATA_EXIST, &fi->flags);
2557
	if (ri->i_inline & F2FS_INLINE_DOTS)
2558
		set_bit(FI_INLINE_DOTS, &fi->flags);
2559 2560
	if (ri->i_inline & F2FS_EXTRA_ATTR)
		set_bit(FI_EXTRA_ATTR, &fi->flags);
2561 2562
	if (ri->i_inline & F2FS_PIN_FILE)
		set_bit(FI_PIN_FILE, &fi->flags);
J
Jaegeuk Kim 已提交
2563 2564
}

2565
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2566 2567 2568
{
	ri->i_inline = 0;

2569
	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
J
Jaegeuk Kim 已提交
2570
		ri->i_inline |= F2FS_INLINE_XATTR;
2571
	if (is_inode_flag_set(inode, FI_INLINE_DATA))
2572
		ri->i_inline |= F2FS_INLINE_DATA;
2573
	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
2574
		ri->i_inline |= F2FS_INLINE_DENTRY;
2575
	if (is_inode_flag_set(inode, FI_DATA_EXIST))
2576
		ri->i_inline |= F2FS_DATA_EXIST;
2577
	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
2578
		ri->i_inline |= F2FS_INLINE_DOTS;
2579 2580
	if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
		ri->i_inline |= F2FS_EXTRA_ATTR;
2581 2582
	if (is_inode_flag_set(inode, FI_PIN_FILE))
		ri->i_inline |= F2FS_PIN_FILE;
2583 2584 2585 2586 2587
}

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
2588 2589
}

2590 2591
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
2592
	return is_inode_flag_set(inode, FI_INLINE_XATTR);
2593 2594
}

2595
static inline unsigned int addrs_per_inode(struct inode *inode)
2596
{
2597 2598 2599 2600 2601 2602 2603 2604
	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
				get_inline_xattr_addrs(inode);
	return ALIGN_DOWN(addrs, 1);
}

static inline unsigned int addrs_per_block(struct inode *inode)
{
	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1);
2605 2606
}

C
Chao Yu 已提交
2607
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
J
Jaegeuk Kim 已提交
2608
{
2609
	struct f2fs_inode *ri = F2FS_INODE(page);
2610

J
Jaegeuk Kim 已提交
2611
	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
2612
					get_inline_xattr_addrs(inode)]);
J
Jaegeuk Kim 已提交
2613 2614 2615 2616
}

static inline int inline_xattr_size(struct inode *inode)
{
2617 2618 2619
	if (f2fs_has_inline_xattr(inode))
		return get_inline_xattr_addrs(inode) * sizeof(__le32);
	return 0;
J
Jaegeuk Kim 已提交
2620 2621
}

2622 2623
static inline int f2fs_has_inline_data(struct inode *inode)
{
2624
	return is_inode_flag_set(inode, FI_INLINE_DATA);
2625 2626
}

2627 2628
static inline int f2fs_exist_data(struct inode *inode)
{
2629
	return is_inode_flag_set(inode, FI_DATA_EXIST);
2630 2631
}

2632 2633
static inline int f2fs_has_inline_dots(struct inode *inode)
{
2634
	return is_inode_flag_set(inode, FI_INLINE_DOTS);
2635 2636
}

2637 2638 2639 2640 2641
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
2642 2643
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
2644
	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
J
Jaegeuk Kim 已提交
2645 2646
}

C
Chao Yu 已提交
2647 2648 2649 2650 2651
static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}

2652 2653
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
2654
	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
2655 2656
}

2657 2658
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
2659
	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
2660 2661
}

2662 2663
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
2664
	return is_inode_flag_set(inode, FI_DROP_CACHE);
2665 2666
}

C
Chao Yu 已提交
2667
static inline void *inline_data_addr(struct inode *inode, struct page *page)
2668
{
2669
	struct f2fs_inode *ri = F2FS_INODE(page);
2670
	int extra_size = get_extra_isize(inode);
2671

2672
	return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
2673 2674
}

2675 2676
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
2677
	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
2678 2679
}

2680 2681 2682 2683 2684 2685 2686 2687
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;
2688
	f2fs_mark_inode_dirty_sync(inode, true);
2689 2690 2691 2692 2693
}

static inline void clear_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise &= ~type;
2694
	f2fs_mark_inode_dirty_sync(inode, true);
2695 2696
}

2697 2698
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
2699 2700
	bool ret;

2701 2702 2703 2704 2705 2706 2707 2708 2709 2710
	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) ||
2711
			i_size_read(inode) & ~PAGE_MASK)
2712
		return false;
2713

2714
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
2715
		return false;
2716
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
2717
		return false;
2718
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
2719
		return false;
2720
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
2721 2722 2723
						&F2FS_I(inode)->i_crtime))
		return false;

2724 2725 2726 2727 2728
	down_read(&F2FS_I(inode)->i_sem);
	ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
	up_read(&F2FS_I(inode)->i_sem);

	return ret;
2729 2730
}

2731
static inline bool f2fs_readonly(struct super_block *sb)
J
Jaegeuk Kim 已提交
2732
{
2733
	return sb_rdonly(sb);
J
Jaegeuk Kim 已提交
2734 2735
}

2736 2737
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
2738
	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
2739 2740
}

2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751
static inline bool is_dot_dotdot(const struct qstr *str)
{
	if (str->len == 1 && str->name[0] == '.')
		return true;

	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
		return true;

	return false;
}

J
Jaegeuk Kim 已提交
2752 2753
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
2754 2755 2756
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	if (!test_opt(sbi, EXTENT_CACHE) ||
2757
			is_inode_flag_set(inode, FI_NO_EXTENT))
J
Jaegeuk Kim 已提交
2758 2759
		return false;

2760 2761 2762 2763 2764 2765 2766
	/*
	 * 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
2767
	return S_ISREG(inode->i_mode);
J
Jaegeuk Kim 已提交
2768 2769
}

2770 2771
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
2772
{
2773 2774
	void *ret;

2775 2776
	if (time_to_inject(sbi, FAULT_KMALLOC)) {
		f2fs_show_injection_info(FAULT_KMALLOC);
J
Jaegeuk Kim 已提交
2777
		return NULL;
2778
	}
2779

2780 2781 2782 2783 2784
	ret = kmalloc(size, flags);
	if (ret)
		return ret;

	return kvmalloc(size, flags);
2785 2786
}

C
Chao Yu 已提交
2787 2788 2789 2790 2791 2792
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
2793 2794 2795 2796 2797 2798 2799
static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	if (time_to_inject(sbi, FAULT_KVMALLOC)) {
		f2fs_show_injection_info(FAULT_KVMALLOC);
		return NULL;
	}
2800

C
Chao Yu 已提交
2801 2802 2803 2804 2805 2806 2807 2808 2809
	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);
}

2810
static inline int get_extra_isize(struct inode *inode)
C
Chao Yu 已提交
2811
{
2812
	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
C
Chao Yu 已提交
2813 2814
}

C
Chao Yu 已提交
2815 2816 2817 2818 2819
static inline int get_inline_xattr_addrs(struct inode *inode)
{
	return F2FS_I(inode)->i_inline_xattr_size;
}

C
Chao Yu 已提交
2820
#define f2fs_get_inode_mode(i) \
2821
	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
2822 2823
	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))

2824 2825 2826 2827
#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
2828 2829
#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
2830
		((offsetof(typeof(*(f2fs_inode)), field) +	\
C
Chao Yu 已提交
2831
		sizeof((f2fs_inode)->field))			\
S
Sheng Yong 已提交
2832
		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
C
Chao Yu 已提交
2833

C
Chao Yu 已提交
2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858
static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
{
	int i;

	spin_lock(&sbi->iostat_lock);
	for (i = 0; i < NR_IO_TYPE; i++)
		sbi->write_iostat[i] = 0;
	spin_unlock(&sbi->iostat_lock);
}

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);
	sbi->write_iostat[type] += io_bytes;

	if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
		sbi->write_iostat[APP_BUFFERED_IO] =
			sbi->write_iostat[APP_WRITE_IO] -
			sbi->write_iostat[APP_DIRECT_IO];
	spin_unlock(&sbi->iostat_lock);
}

2859 2860
#define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)

C
Chao Yu 已提交
2861
#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
2862

2863 2864 2865 2866 2867 2868
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)) {
2869 2870
		f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
			 blkaddr, type);
2871 2872 2873 2874 2875
		f2fs_bug_on(sbi, 1);
	}
}

static inline bool __is_valid_data_blkaddr(block_t blkaddr)
C
Chao Yu 已提交
2876 2877 2878 2879 2880 2881
{
	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
		return false;
	return true;
}

2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902
static inline void f2fs_set_page_private(struct page *page,
						unsigned long data)
{
	if (PagePrivate(page))
		return;

	get_page(page);
	SetPagePrivate(page);
	set_page_private(page, data);
}

static inline void f2fs_clear_page_private(struct page *page)
{
	if (!PagePrivate(page))
		return;

	set_page_private(page, 0);
	ClearPagePrivate(page);
	f2fs_put_page(page, 0);
}

2903 2904 2905
/*
 * file.c
 */
2906
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
C
Chao Yu 已提交
2907
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
2908
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
2909
int f2fs_truncate(struct inode *inode);
2910 2911
int f2fs_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
2912
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
C
Chao Yu 已提交
2913 2914
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);
2915
int f2fs_precache_extents(struct inode *inode);
2916 2917
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);
2918
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
2919
int f2fs_pin_file_control(struct inode *inode, bool inc);
2920 2921 2922 2923

/*
 * inode.c
 */
2924
void f2fs_set_inode_flags(struct inode *inode);
C
Chao Yu 已提交
2925 2926
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);
2927 2928
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
2929 2930 2931
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);
2932 2933
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
C
Chao Yu 已提交
2934
void f2fs_handle_failed_inode(struct inode *inode);
2935 2936 2937 2938

/*
 * namei.c
 */
C
Chao Yu 已提交
2939
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
C
Chao Yu 已提交
2940
							bool hot, bool set);
2941 2942
struct dentry *f2fs_get_parent(struct dentry *child);

2943 2944
extern int f2fs_ci_compare(const struct inode *parent,
			   const struct qstr *name,
2945 2946
			   const struct qstr *entry,
			   bool quick);
2947

2948 2949 2950
/*
 * dir.c
 */
C
Chao Yu 已提交
2951 2952
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
2953 2954 2955 2956
			f2fs_hash_t namehash, int *max_slots,
			struct f2fs_dentry_ptr *d);
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
2957
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
2958
			struct f2fs_dentry_ptr *d);
C
Chao Yu 已提交
2959
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
2960 2961
			const struct qstr *new_name,
			const struct qstr *orig_name, struct page *dpage);
C
Chao Yu 已提交
2962
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
2963
			unsigned int current_depth);
C
Chao Yu 已提交
2964
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
			struct fscrypt_name *fname, struct page **res_page);
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);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
			const struct qstr *name, f2fs_hash_t name_hash,
			unsigned int bit_pos);
int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
			const struct qstr *orig_name,
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
2981
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
2982
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
2983
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
2984 2985 2986 2987 2988
			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);
2989

2990 2991
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
C
Chao Yu 已提交
2992
	return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
2993
				inode, inode->i_ino, inode->i_mode);
2994 2995
}

2996 2997 2998
/*
 * super.c
 */
2999 3000
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
J
Jaegeuk Kim 已提交
3001
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
3002
int f2fs_quota_sync(struct super_block *sb, int type);
C
Chao Yu 已提交
3003
void f2fs_quota_off_umount(struct super_block *sb);
3004 3005
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
3006
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
3007 3008 3009 3010

/*
 * hash.c
 */
3011 3012
f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
		const struct qstr *name_info, struct fscrypt_name *fname);
3013 3014 3015 3016 3017 3018 3019

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

C
Chao Yu 已提交
3020 3021
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);
3022 3023 3024 3025
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
3026 3027 3028
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);
3029
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
C
Chao Yu 已提交
3030 3031 3032 3033 3034
						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);
3035 3036
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
					unsigned int seq_id);
C
Chao Yu 已提交
3037 3038 3039 3040 3041 3042
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);
3043
int f2fs_move_node_page(struct page *node_page, int gc_type);
C
Chao Yu 已提交
3044
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
3045 3046
			struct writeback_control *wbc, bool atomic,
			unsigned int *seq_id);
C
Chao Yu 已提交
3047 3048
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
			struct writeback_control *wbc,
C
Chao Yu 已提交
3049
			bool do_balance, enum iostat_type io_type);
3050
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
C
Chao Yu 已提交
3051 3052 3053 3054 3055 3056 3057
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);
void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
3058
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
3059
			unsigned int segno, struct f2fs_summary_block *sum);
3060
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
C
Chao Yu 已提交
3061 3062 3063 3064
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);
3065 3066 3067 3068

/*
 * segment.c
 */
C
Chao Yu 已提交
3069 3070 3071 3072 3073 3074
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);
3075 3076
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3077
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
C
Chao Yu 已提交
3078
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
3079
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3080 3081 3082 3083 3084
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);
3085
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3086 3087
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
					struct cp_control *cpc);
D
Daniel Rosenberg 已提交
3088
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
3089 3090
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
3091 3092
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
3093 3094
void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
					unsigned int start, unsigned int end);
C
Chao Yu 已提交
3095
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
3096
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
C
Chao Yu 已提交
3097 3098 3099 3100 3101 3102
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
3103
						enum iostat_type io_type);
C
Chao Yu 已提交
3104 3105 3106 3107 3108
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,
3109 3110 3111 3112 3113 3114
			block_t old_blkaddr, block_t new_blkaddr,
			bool recover_curseg, bool recover_newaddr);
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
3115
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
3116
			block_t old_blkaddr, block_t *new_blkaddr,
3117 3118
			struct f2fs_summary *sum, int type,
			struct f2fs_io_info *fio, bool add_list);
3119
void f2fs_wait_on_page_writeback(struct page *page,
3120
			enum page_type type, bool ordered, bool locked);
3121
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
3122 3123
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
								block_t len);
C
Chao Yu 已提交
3124 3125 3126
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,
3127
			unsigned int val, int alloc);
C
Chao Yu 已提交
3128 3129 3130 3131 3132 3133 3134 3135
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
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);
3136 3137 3138 3139

/*
 * checkpoint.c
 */
3140
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
C
Chao Yu 已提交
3141 3142
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);
3143
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
C
Chao Yu 已提交
3144
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
3145 3146
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type);
C
Chao Yu 已提交
3147
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
3148
			int type, bool sync);
C
Chao Yu 已提交
3149 3150
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
3151
			long nr_to_write, enum iostat_type io_type);
C
Chao Yu 已提交
3152 3153 3154 3155 3156
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
3157
					unsigned int devidx, int type);
C
Chao Yu 已提交
3158
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
C
Chao Yu 已提交
3159
					unsigned int devidx, int type);
3160
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3161 3162 3163 3164 3165 3166 3167 3168 3169
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);
3170
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3171 3172 3173 3174
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);
3175 3176 3177 3178

/*
 * data.c
 */
3179 3180
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
3181 3182
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,
3183 3184
				struct inode *inode, struct page *page,
				nid_t ino, enum page_type type);
3185
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
3186
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3187
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
3188
void f2fs_submit_page_write(struct f2fs_io_info *fio);
3189 3190 3191
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
3192
void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
3193
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
C
Chao Yu 已提交
3194 3195
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
3196 3197 3198
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
3199
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
3200
			int op_flags, bool for_write);
C
Chao Yu 已提交
3201 3202
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,
3203
			bool for_write);
C
Chao Yu 已提交
3204
struct page *f2fs_get_new_data_page(struct inode *inode,
3205
			struct page *ipage, pgoff_t index, bool new_i_size);
C
Chao Yu 已提交
3206
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3207
void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
3208 3209 3210 3211
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
3212 3213
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);
3214 3215 3216
void f2fs_invalidate_page(struct page *page, unsigned int offset,
			unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
3217
#ifdef CONFIG_MIGRATION
3218 3219
int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
			struct page *page, enum migrate_mode mode);
3220
#endif
H
Hyunchul Lee 已提交
3221
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
M
Matthew Wilcox 已提交
3222
void f2fs_clear_page_cache_dirty_tag(struct page *page);
3223 3224 3225 3226

/*
 * gc.c
 */
C
Chao Yu 已提交
3227 3228 3229
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);
3230 3231
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
			unsigned int segno);
C
Chao Yu 已提交
3232
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
3233
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
3234 3235 3236 3237

/*
 * recovery.c
 */
C
Chao Yu 已提交
3238 3239
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
3240 3241 3242 3243 3244 3245 3246 3247 3248 3249

/*
 * 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;
3250 3251
	unsigned long long hit_largest, hit_cached, hit_rbtree;
	unsigned long long hit_total, total_ext;
J
Jaegeuk Kim 已提交
3252
	int ext_tree, zombie_tree, ext_node;
3253 3254
	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
	int ndirty_data, ndirty_qdata;
3255
	int inmem_pages;
3256
	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
3257 3258
	int nats, dirty_nats, sits, dirty_sits;
	int free_nids, avail_nids, alloc_nids;
3259
	int total_count, utilization;
C
Chao Yu 已提交
3260
	int bg_gc, nr_wb_cp_data, nr_wb_data;
3261
	int nr_rd_data, nr_rd_node, nr_rd_meta;
C
Chao Yu 已提交
3262
	int nr_dio_read, nr_dio_write;
3263
	unsigned int io_skip_bggc, other_skip_bggc;
C
Chao Yu 已提交
3264 3265
	int nr_flushing, nr_flushed, flush_list_empty;
	int nr_discarding, nr_discarded;
C
Chao Yu 已提交
3266
	int nr_discard_cmd;
C
Chao Yu 已提交
3267
	unsigned int undiscard_blks;
3268
	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
3269
	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
3270
	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
3271 3272 3273 3274
	unsigned int bimodal, avg_vblocks;
	int util_free, util_valid, util_invalid;
	int rsvd_segs, overp_segs;
	int dirty_count, node_pages, meta_pages;
3275
	int prefree_count, call_count, cp_count, bg_cp_count;
3276
	int tot_segs, node_segs, data_segs, free_segs, free_secs;
3277
	int bg_node_segs, bg_data_segs;
3278
	int tot_blks, data_blks, node_blks;
3279
	int bg_data_blks, bg_node_blks;
3280
	unsigned long long skipped_atomic_files[2];
3281 3282 3283 3284
	int curseg[NR_CURSEG_TYPE];
	int cursec[NR_CURSEG_TYPE];
	int curzone[NR_CURSEG_TYPE];

C
Chao Yu 已提交
3285
	unsigned int meta_count[META_MAX];
3286 3287
	unsigned int segment_count[2];
	unsigned int block_count[2];
3288
	unsigned int inplace_count;
C
Chao Yu 已提交
3289
	unsigned long long base_mem, cache_mem, page_mem;
3290 3291
};

3292 3293
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
3294
	return (struct f2fs_stat_info *)sbi->stat_info;
3295 3296
}

3297
#define stat_inc_cp_count(si)		((si)->cp_count++)
3298
#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
3299 3300
#define stat_inc_call_count(si)		((si)->call_count++)
#define stat_inc_bggc_count(sbi)	((sbi)->bg_gc++)
3301 3302
#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
3303 3304
#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
3305 3306 3307 3308
#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
3309 3310 3311 3312 3313 3314 3315 3316 3317 3318
#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)
3319 3320 3321
#define stat_inc_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3322
			(atomic_inc(&F2FS_I_SB(inode)->inline_inode));	\
3323 3324 3325 3326
	} while (0)
#define stat_dec_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3327
			(atomic_dec(&F2FS_I_SB(inode)->inline_inode));	\
3328
	} while (0)
3329 3330 3331
#define stat_inc_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3332
			(atomic_inc(&F2FS_I_SB(inode)->inline_dir));	\
3333 3334 3335 3336
	} while (0)
#define stat_dec_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3337
			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
3338
	} while (0)
C
Chao Yu 已提交
3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349
#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)
3350 3351 3352 3353
#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]++)
3354 3355
#define stat_inc_inplace_blocks(sbi)					\
		(atomic_inc(&(sbi)->inplace_count))
3356
#define stat_inc_atomic_write(inode)					\
3357
		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
3358
#define stat_dec_atomic_write(inode)					\
3359
		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
3360 3361 3362 3363 3364 3365 3366
#define stat_update_max_atomic_write(inode)				\
	do {								\
		int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt);	\
		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)
3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377
#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)
3378
#define stat_inc_seg_count(sbi, type, gc_type)				\
3379
	do {								\
3380
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3381 3382
		si->tot_segs++;						\
		if ((type) == SUM_TYPE_DATA) {				\
3383
			si->data_segs++;				\
3384 3385
			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
		} else {						\
3386
			si->node_segs++;				\
3387 3388
			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
		}							\
3389 3390 3391
	} while (0)

#define stat_inc_tot_blk_count(si, blks)				\
3392
	((si)->tot_blks += (blks))
3393

3394
#define stat_inc_data_blk_count(sbi, blks, gc_type)			\
3395
	do {								\
3396
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3397 3398
		stat_inc_tot_blk_count(si, blks);			\
		si->data_blks += (blks);				\
3399
		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3400 3401
	} while (0)

3402
#define stat_inc_node_blk_count(sbi, blks, gc_type)			\
3403
	do {								\
3404
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3405 3406
		stat_inc_tot_blk_count(si, blks);			\
		si->node_blks += (blks);				\
3407
		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3408 3409
	} while (0)

3410 3411
int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
3412
void __init f2fs_create_root_stats(void);
3413
void f2fs_destroy_root_stats(void);
3414
#else
3415 3416 3417 3418
#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)
3419 3420
#define stat_io_skip_bggc_count(sbi)			do { } while (0)
#define stat_other_skip_bggc_count(sbi)			do { } while (0)
3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438
#define stat_inc_dirty_inode(sbi, type)			do { } while (0)
#define stat_dec_dirty_inode(sbi, type)			do { } while (0)
#define stat_inc_total_hit(sb)				do { } while (0)
#define stat_inc_rbtree_node_hit(sb)			do { } while (0)
#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)
#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
3439
#define stat_inc_meta_count(sbi, blkaddr)		do { } while (0)
3440 3441 3442 3443 3444 3445 3446
#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)
3447 3448 3449

static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
3450
static inline void __init f2fs_create_root_stats(void) { }
3451
static inline void f2fs_destroy_root_stats(void) { }
3452 3453 3454
#endif

extern const struct file_operations f2fs_dir_operations;
3455 3456 3457
#ifdef CONFIG_UNICODE
extern const struct dentry_operations f2fs_dentry_ops;
#endif
3458 3459 3460 3461 3462 3463 3464
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;
3465
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
3466
extern const struct inode_operations f2fs_special_inode_operations;
C
Chao Yu 已提交
3467
extern struct kmem_cache *f2fs_inode_entry_slab;
3468

3469 3470 3471
/*
 * inline.c
 */
3472 3473
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
C
Chao Yu 已提交
3474 3475 3476
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);
3477 3478 3479 3480
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);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
C
Chao Yu 已提交
3481 3482
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
3483
			struct fscrypt_name *fname, struct page **res_page);
C
Chao Yu 已提交
3484
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
3485 3486 3487 3488
			struct page *ipage);
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
			const struct qstr *orig_name,
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
3489 3490 3491
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
				struct page *page, struct inode *dir,
				struct inode *inode);
3492 3493 3494 3495 3496 3497
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);
3498

3499 3500 3501
/*
 * shrinker.c
 */
3502 3503 3504 3505 3506 3507
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);
3508

3509 3510 3511
/*
 * extent_cache.c
 */
C
Chao Yu 已提交
3512
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
3513
				struct rb_entry *cached_re, unsigned int ofs);
C
Chao Yu 已提交
3514
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3515 3516 3517 3518
				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,
3519 3520 3521
		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
3522
		bool force, bool *leftmost);
C
Chao Yu 已提交
3523
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3524
						struct rb_root_cached *root);
3525 3526 3527 3528 3529 3530 3531 3532
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
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
3533
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
3534
			pgoff_t fofs, block_t blkaddr, unsigned int len);
C
Chao Yu 已提交
3535 3536 3537
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
3538

3539 3540 3541
/*
 * sysfs.c
 */
3542 3543 3544 3545
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);
3546

3547 3548 3549
/*
 * crypto support
 */
3550 3551
static inline bool f2fs_encrypted_file(struct inode *inode)
{
3552
	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
3553 3554
}

3555 3556
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
3557
#ifdef CONFIG_FS_ENCRYPTION
3558
	file_set_encrypt(inode);
C
Chao Yu 已提交
3559
	f2fs_set_inode_flags(inode);
3560 3561 3562
#endif
}

3563 3564 3565 3566 3567
/*
 * 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)
3568
{
3569
	return f2fs_encrypted_file(inode);
3570 3571
}

3572
#define F2FS_FEATURE_FUNCS(name, flagname) \
3573
static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
3574
{ \
3575
	return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
3576 3577
}

3578 3579 3580 3581 3582 3583 3584 3585
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);
3586
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
3587
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
3588
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
C
Chao Yu 已提交
3589

3590
#ifdef CONFIG_BLK_DEV_ZONED
3591 3592
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
				    block_t blkaddr)
3593 3594 3595
{
	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;

3596
	return test_bit(zno, FDEV(devi).blkz_seq);
3597 3598 3599
}
#endif

3600
static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
3601
{
3602
	return f2fs_sb_has_blkzoned(sbi);
3603
}
3604

3605 3606 3607 3608 3609 3610
static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
{
	return blk_queue_discard(bdev_get_queue(bdev)) ||
	       bdev_is_zoned(bdev);
}

3611 3612
static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
{
3613 3614 3615 3616 3617 3618 3619 3620 3621
	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;
3622 3623 3624 3625 3626 3627
}

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);
3628 3629
}

3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643
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;
}


3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658
static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
{
	clear_opt(sbi, ADAPTIVE);
	clear_opt(sbi, LFS);

	switch (mt) {
	case F2FS_MOUNT_ADAPTIVE:
		set_opt(sbi, ADAPTIVE);
		break;
	case F2FS_MOUNT_LFS:
		set_opt(sbi, LFS);
		break;
	}
}

3659 3660
static inline bool f2fs_may_encrypt(struct inode *inode)
{
3661
#ifdef CONFIG_FS_ENCRYPTION
A
Al Viro 已提交
3662
	umode_t mode = inode->i_mode;
3663 3664 3665

	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
#else
3666
	return false;
3667 3668 3669
#endif
}

3670 3671
static inline int block_unaligned_IO(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
H
Hyunchul Lee 已提交
3672
{
3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698
	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);

	return (test_opt(sbi, LFS) && (rw == WRITE) &&
				!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;
3699
	if (f2fs_is_multi_device(sbi))
3700 3701 3702 3703 3704
		return true;
	/*
	 * for blkzoned device, fallback direct IO to buffered IO, so
	 * all IOs can be serialized by log-structured write.
	 */
3705
	if (f2fs_sb_has_blkzoned(sbi))
3706 3707 3708 3709
		return true;
	if (test_opt(sbi, LFS) && (rw == WRITE) &&
				block_unaligned_IO(inode, iocb, iter))
		return true;
J
Jaegeuk Kim 已提交
3710
	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
C
Chao Yu 已提交
3711
					!IS_SWAPFILE(inode))
D
Daniel Rosenberg 已提交
3712 3713
		return true;

3714
	return false;
H
Hyunchul Lee 已提交
3715 3716
}

3717
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
3718 3719
extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
							unsigned int type);
3720
#else
C
Chao Yu 已提交
3721
#define f2fs_build_fault_attr(sbi, rate, type)		do { } while (0)
3722 3723
#endif

3724 3725 3726
static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_QUOTA
3727
	if (f2fs_sb_has_quota_ino(sbi))
3728 3729 3730 3731 3732 3733 3734 3735
		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
3736

3737 3738 3739
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3740
#endif /* _LINUX_F2FS_H */