f2fs.h 116.4 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

421 422 423
#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
424

J
Jaegeuk Kim 已提交
425 426 427 428 429 430 431 432
/*
 * 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 */
433
#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
434
#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
J
Jaegeuk Kim 已提交
435

436 437 438 439
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
 * ioctl commands in 32 bit emulation
 */
440 441 442
#define F2FS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
#define F2FS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
#define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
443 444
#endif

445 446 447
#define F2FS_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
#define F2FS_IOC_FSSETXATTR		FS_IOC_FSSETXATTR

448 449 450 451 452 453
struct f2fs_gc_range {
	u32 sync;
	u64 start;
	u64 len;
};

C
Chao Yu 已提交
454 455 456 457 458
struct f2fs_defragment {
	u64 start;
	u64 len;
};

459 460 461 462 463 464 465
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 */
};

466 467 468 469 470
struct f2fs_flush_device {
	u32 dev_num;		/* device number to flush */
	u32 segments;		/* # of segments to flush */
};

C
Chao Yu 已提交
471 472
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE	1
473
static inline int get_extra_isize(struct inode *inode);
C
Chao Yu 已提交
474 475 476
static inline int get_inline_xattr_addrs(struct inode *inode);
#define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
				(CUR_ADDRS_PER_INODE(inode) -		\
477
				get_inline_xattr_addrs(inode) -	\
C
Chao Yu 已提交
478
				DEF_INLINE_RESERVED_SIZE))
C
Chao Yu 已提交
479 480 481 482 483

/* 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))
484 485
#define INLINE_DENTRY_BITMAP_SIZE(inode) \
	DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
C
Chao Yu 已提交
486 487 488 489 490
#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)))

491 492 493
/*
 * For INODE and NODE manager
 */
494 495
/* for directory operations */
struct f2fs_dentry_ptr {
496
	struct inode *inode;
497
	void *bitmap;
498 499 500
	struct f2fs_dir_entry *dentry;
	__u8 (*filename)[F2FS_SLOT_LEN];
	int max;
501
	int nr_bitmap;
502 503
};

504 505
static inline void make_dentry_ptr_block(struct inode *inode,
		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
506
{
507
	d->inode = inode;
508
	d->max = NR_DENTRY_IN_BLOCK;
509
	d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
510
	d->bitmap = t->dentry_bitmap;
511 512 513
	d->dentry = t->dentry;
	d->filename = t->filename;
}
514

515
static inline void make_dentry_ptr_inline(struct inode *inode,
C
Chao Yu 已提交
516
					struct f2fs_dentry_ptr *d, void *t)
517
{
C
Chao Yu 已提交
518 519 520 521
	int entry_cnt = NR_INLINE_DENTRY(inode);
	int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
	int reserved_size = INLINE_RESERVED_SIZE(inode);

522
	d->inode = inode;
C
Chao Yu 已提交
523 524 525 526 527 528
	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;
529 530
}

531 532 533 534 535 536 537
/*
 * 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)
538 539 540 541 542
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
543
					 * by get_data_block.
544
					 */
545 546
};

547 548
#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */

549 550 551
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8

552
#define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
553

554 555
#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */

556
/* for in-memory extent cache entry */
557 558 559 560
#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
561

562 563 564 565 566 567
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 */
};

568
struct extent_info {
569 570
	unsigned int fofs;		/* start offset in a file */
	unsigned int len;		/* length of the extent */
571
	u32 blk;			/* start block address of the extent */
572 573 574
};

struct extent_node {
C
Chao Yu 已提交
575 576
	struct rb_node rb_node;		/* rb node located in rb-tree */
	struct extent_info ei;		/* extent info */
577
	struct list_head list;		/* node in global extent list of sbi */
578
	struct extent_tree *et;		/* extent tree pointer */
579 580 581 582
};

struct extent_tree {
	nid_t ino;			/* inode number */
C
Chao Yu 已提交
583
	struct rb_root_cached root;	/* root of extent info rb-tree */
584
	struct extent_node *cached_en;	/* recently accessed extent node */
J
Jaegeuk Kim 已提交
585
	struct extent_info largest;	/* largested extent info */
586
	struct list_head list;		/* to be used by sbi->zombie_list */
587
	rwlock_t lock;			/* protect extent info rb-tree */
588
	atomic_t node_cnt;		/* # of extent node in rb-tree*/
589
	bool largest_updated;		/* largest extent updated */
590 591
};

J
Jaegeuk Kim 已提交
592 593 594 595 596 597 598
/*
 * 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)
599 600 601
#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
602 603 604 605 606 607

struct f2fs_map_blocks {
	block_t m_pblk;
	block_t m_lblk;
	unsigned int m_len;
	unsigned int m_flags;
608
	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
609
	pgoff_t *m_next_extent;		/* point to next possible extent */
610
	int m_seg_type;
C
Chao Yu 已提交
611
	bool m_may_create;		/* indicate it is from write path */
J
Jaegeuk Kim 已提交
612 613
};

C
Chao Yu 已提交
614
/* for flag in get_data_block */
615 616 617 618
enum {
	F2FS_GET_BLOCK_DEFAULT,
	F2FS_GET_BLOCK_FIEMAP,
	F2FS_GET_BLOCK_BMAP,
619
	F2FS_GET_BLOCK_DIO,
620 621
	F2FS_GET_BLOCK_PRE_DIO,
	F2FS_GET_BLOCK_PRE_AIO,
622
	F2FS_GET_BLOCK_PRECACHE,
623
};
C
Chao Yu 已提交
624

625 626 627 628
/*
 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
 */
#define FADVISE_COLD_BIT	0x01
629
#define FADVISE_LOST_PINO_BIT	0x02
630
#define FADVISE_ENCRYPT_BIT	0x04
631
#define FADVISE_ENC_NAME_BIT	0x08
632
#define FADVISE_KEEP_SIZE_BIT	0x10
C
Chao Yu 已提交
633
#define FADVISE_HOT_BIT		0x20
E
Eric Biggers 已提交
634
#define FADVISE_VERITY_BIT	0x40	/* reserved */
635

636 637
#define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)

638 639 640 641 642 643
#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)
644 645 646
#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)
647 648
#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)
649 650
#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
651 652 653
#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)
654

655 656
#define DEF_DIR_LEVEL		0

657 658 659 660 661 662
enum {
	GC_FAILURE_PIN,
	GC_FAILURE_ATOMIC,
	MAX_GC_FAILURE
};

663 664 665 666
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 */
667
	unsigned char i_dir_level;	/* use for dentry level for large dir */
668 669 670
	unsigned int i_current_depth;	/* only for directory depth */
	/* for gc failure statistic */
	unsigned int i_gc_failures[MAX_GC_FAILURE];
671
	unsigned int i_pino;		/* parent inode number */
672 673 674 675
	umode_t i_acl_mode;		/* keep file acl mode temporarily */

	/* Use below internally in f2fs*/
	unsigned long flags;		/* use to pass per-file flags */
676
	struct rw_semaphore i_sem;	/* protect fi info */
677
	atomic_t dirty_pages;		/* # of dirty pages */
678 679
	f2fs_hash_t chash;		/* hash value of given file name */
	unsigned int clevel;		/* maximum level of given file name */
680
	struct task_struct *task;	/* lookup and create consistency */
C
Chao Yu 已提交
681
	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
682
	nid_t i_xattr_nid;		/* node id that contains xattrs */
683
	loff_t	last_disk_size;		/* lastly written file size */
J
Jaegeuk Kim 已提交
684

C
Chao Yu 已提交
685 686 687 688 689 690
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];

	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
691 692
	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
693
	struct list_head inmem_ilist;	/* list for inmem inodes */
J
Jaegeuk Kim 已提交
694
	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
695
	struct task_struct *inmem_task;	/* store inmemory task */
J
Jaegeuk Kim 已提交
696
	struct mutex inmem_lock;	/* lock for inmemory pages */
J
Jaegeuk Kim 已提交
697
	struct extent_tree *extent_tree;	/* cached extent_tree entry */
C
Chao Yu 已提交
698 699 700

	/* avoid racing between foreground op and gc */
	struct rw_semaphore i_gc_rwsem[2];
701
	struct rw_semaphore i_mmap_sem;
702
	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
C
Chao Yu 已提交
703

704
	int i_extra_isize;		/* size of extra space located in i_addr */
C
Chao Yu 已提交
705
	kprojid_t i_projid;		/* id for project quota */
C
Chao Yu 已提交
706
	int i_inline_xattr_size;	/* inline xattr size */
707 708
	struct timespec64 i_crtime;	/* inode creation time */
	struct timespec64 i_disk_time[4];/* inode disk times */
709 710 711
};

static inline void get_extent_info(struct extent_info *ext,
C
Chao Yu 已提交
712
					struct f2fs_extent *i_ext)
713
{
C
Chao Yu 已提交
714 715 716
	ext->fofs = le32_to_cpu(i_ext->fofs);
	ext->blk = le32_to_cpu(i_ext->blk);
	ext->len = le32_to_cpu(i_ext->len);
717 718 719 720 721 722
}

static inline void set_raw_extent(struct extent_info *ext,
					struct f2fs_extent *i_ext)
{
	i_ext->fofs = cpu_to_le32(ext->fofs);
723
	i_ext->blk = cpu_to_le32(ext->blk);
724 725 726
	i_ext->len = cpu_to_le32(ext->len);
}

727 728 729 730 731 732 733 734
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;
}

735
static inline bool __is_discard_mergeable(struct discard_info *back,
736
			struct discard_info *front, unsigned int max_len)
737
{
738
	return (back->lstart + back->len == front->lstart) &&
739
		(back->len + front->len <= max_len);
740 741 742
}

static inline bool __is_discard_back_mergeable(struct discard_info *cur,
743
			struct discard_info *back, unsigned int max_len)
744
{
745
	return __is_discard_mergeable(back, cur, max_len);
746 747 748
}

static inline bool __is_discard_front_mergeable(struct discard_info *cur,
749
			struct discard_info *front, unsigned int max_len)
750
{
751
	return __is_discard_mergeable(cur, front, max_len);
752 753
}

754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772
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);
}

773
extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
774 775
static inline void __try_update_largest_extent(struct extent_tree *et,
						struct extent_node *en)
776
{
777
	if (en->ei.len > et->largest.len) {
778
		et->largest = en->ei;
779
		et->largest_updated = true;
780
	}
781 782
}

C
Chao Yu 已提交
783 784 785 786 787 788 789
/*
 * 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
790 791
};

792 793 794
struct f2fs_nm_info {
	block_t nat_blkaddr;		/* base disk address of NAT */
	nid_t max_nid;			/* maximum possible node ids */
795
	nid_t available_nids;		/* # of available node ids */
796
	nid_t next_scan_nid;		/* the next nid to be scanned */
797
	unsigned int ram_thresh;	/* control the memory footprint */
C
Chao Yu 已提交
798
	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
C
Chao Yu 已提交
799
	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
800 801 802

	/* NAT cache management */
	struct radix_tree_root nat_root;/* root of the nat entry cache */
803
	struct radix_tree_root nat_set_root;/* root of the nat set cache */
804
	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
805
	struct list_head nat_entries;	/* cached nat entry list (clean) */
806
	spinlock_t nat_list_lock;	/* protect clean nat entry list */
807
	unsigned int nat_cnt;		/* the # of cached nat entries */
808
	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
809
	unsigned int nat_blocks;	/* # of nat blocks */
810 811

	/* free node ids management */
812
	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
C
Chao Yu 已提交
813 814
	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
815
	spinlock_t nid_list_lock;	/* protect nid lists ops */
816
	struct mutex build_lock;	/* lock for build free nids */
817
	unsigned char **free_nid_bitmap;
C
Chao Yu 已提交
818
	unsigned char *nat_block_bitmap;
819
	unsigned short *free_nid_count;	/* free nid count of NAT block */
820 821 822

	/* for checkpoint */
	char *nat_bitmap;		/* NAT bitmap pointer */
823 824 825 826 827

	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 */
828 829 830
#ifdef CONFIG_F2FS_CHECK_FS
	char *nat_bitmap_mir;		/* NAT bitmap mirror */
#endif
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845
	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 */
846
	bool node_changed;		/* is node block changed */
847 848
	char cur_level;			/* level of hole node page */
	char max_level;			/* level of current page located */
849 850 851 852 853 854
	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)
{
855
	memset(dn, 0, sizeof(*dn));
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885
	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 */
886
	NO_CHECK_TYPE,
887 888
};

889 890
struct flush_cmd {
	struct completion wait;
891
	struct llist_node llnode;
C
Chao Yu 已提交
892
	nid_t ino;
893 894 895
	int ret;
};

896 897 898
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
899
	atomic_t issued_flush;			/* # of issued flushes */
900
	atomic_t queued_flush;			/* # of queued flushes */
901 902
	struct llist_head issue_list;		/* list for command issue */
	struct llist_node *dispatch_list;	/* list for command dispatch */
903 904
};

905 906 907 908 909 910
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
911 912
	struct rw_semaphore curseg_lock;	/* for preventing curseg change */

913 914 915 916 917 918 919 920
	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 */
921 922 923

	/* a threshold to reclaim prefree segments */
	unsigned int rec_prefree_segments;
924

J
Jaegeuk Kim 已提交
925 926 927
	/* for batched trimming */
	unsigned int trim_sections;		/* # of sections to trim */

928 929
	struct list_head sit_entry_set;	/* sit entry set list */

930 931
	unsigned int ipu_policy;	/* in-place-update policy */
	unsigned int min_ipu_util;	/* in-place-update threshold */
932
	unsigned int min_fsync_blocks;	/* threshold for fsync */
933
	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
934
	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
C
Chao Yu 已提交
935
	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
936 937

	/* for flush command control */
938
	struct flush_cmd_control *fcc_info;
939

940 941
	/* for discard command control */
	struct discard_cmd_control *dcc_info;
942 943 944 945 946 947 948 949 950 951 952
};

/*
 * 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.
 */
953
#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
954 955
enum count_type {
	F2FS_DIRTY_DENTS,
956
	F2FS_DIRTY_DATA,
957
	F2FS_DIRTY_QDATA,
958 959
	F2FS_DIRTY_NODES,
	F2FS_DIRTY_META,
960
	F2FS_INMEM_PAGES,
961
	F2FS_DIRTY_IMETA,
962 963
	F2FS_WB_CP_DATA,
	F2FS_WB_DATA,
964 965 966
	F2FS_RD_DATA,
	F2FS_RD_NODE,
	F2FS_RD_META,
C
Chao Yu 已提交
967 968
	F2FS_DIO_WRITE,
	F2FS_DIO_READ,
969 970 971 972
	NR_COUNT_TYPE,
};

/*
A
arter97 已提交
973
 * The below are the page types of bios used in submit_bio().
974 975 976 977 978 979 980 981 982
 * 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.
 */
983
#define PAGE_TYPE_OF_BIO(type)	((type) > META ? META : (type))
984 985 986 987 988 989
enum page_type {
	DATA,
	NODE,
	META,
	NR_PAGE_TYPE,
	META_FLUSH,
990 991
	INMEM,		/* the below types are used by tracepoints only. */
	INMEM_DROP,
992
	INMEM_INVALIDATE,
993
	INMEM_REVOKE,
994 995
	IPU,
	OPU,
996 997
};

J
Jaegeuk Kim 已提交
998 999 1000 1001 1002 1003 1004
enum temp_type {
	HOT = 0,	/* must be zero for meta bio */
	WARM,
	COLD,
	NR_TEMP_TYPE,
};

1005 1006 1007 1008 1009 1010
enum need_lock_type {
	LOCK_REQ = 0,
	LOCK_DONE,
	LOCK_RETRY,
};

C
Chao Yu 已提交
1011 1012 1013 1014 1015 1016 1017 1018 1019 1020
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,
1021
	CP_RECOVER_DIR,
C
Chao Yu 已提交
1022 1023
};

C
Chao Yu 已提交
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040
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
1041
struct f2fs_io_info {
1042
	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
C
Chao Yu 已提交
1043
	nid_t ino;		/* inode number */
1044
	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
J
Jaegeuk Kim 已提交
1045
	enum temp_type temp;	/* contains HOT/WARM/COLD */
M
Mike Christie 已提交
1046
	int op;			/* contains REQ_OP_ */
1047
	int op_flags;		/* req_flag_bits */
1048
	block_t new_blkaddr;	/* new block address to be written */
1049
	block_t old_blkaddr;	/* old block address before Cow */
1050
	struct page *page;	/* page to be written */
1051
	struct page *encrypted_page;	/* encrypted page */
1052
	struct list_head list;		/* serialize IOs */
1053
	bool submitted;		/* indicate IO submission */
1054
	int need_lock;		/* indicate we need to lock cp_rwsem */
1055
	bool in_list;		/* indicate fio is in io_list */
C
Chao Yu 已提交
1056
	bool is_por;		/* indicate IO is from recovery or not */
1057
	bool retry;		/* need to reallocate block address */
C
Chao Yu 已提交
1058
	enum iostat_type io_type;	/* io type */
1059
	struct writeback_control *io_wbc; /* writeback control */
C
Chao Yu 已提交
1060 1061
	struct bio **bio;		/* bio for ipu */
	sector_t *last_block;		/* last block number in bio */
1062
	unsigned char version;		/* version of the node */
J
Jaegeuk Kim 已提交
1063 1064
};

1065
#define is_read_io(rw) ((rw) == READ)
1066
struct f2fs_bio_info {
J
Jaegeuk Kim 已提交
1067
	struct f2fs_sb_info *sbi;	/* f2fs superblock */
1068 1069
	struct bio *bio;		/* bios to merge */
	sector_t last_block_in_bio;	/* last block number */
J
Jaegeuk Kim 已提交
1070
	struct f2fs_io_info fio;	/* store buffered io info. */
1071
	struct rw_semaphore io_rwsem;	/* blocking op for bio */
1072 1073
	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
	struct list_head io_list;	/* track fios */
1074 1075
};

J
Jaegeuk Kim 已提交
1076 1077 1078 1079 1080 1081 1082 1083 1084
#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
1085 1086
	unsigned int nr_blkz;		/* Total number of zones */
	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
J
Jaegeuk Kim 已提交
1087 1088 1089
#endif
};

1090 1091 1092
enum inode_type {
	DIR_INODE,			/* for dirty dir inode */
	FILE_INODE,			/* for dirty regular/symlink inode */
1093
	DIRTY_META,			/* for all dirtied inode metadata */
J
Jaegeuk Kim 已提交
1094
	ATOMIC_FILE,			/* for all atomic files */
1095 1096 1097
	NR_INODE_TYPE,
};

1098 1099 1100 1101 1102 1103 1104 1105
/* 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 */
};

1106 1107 1108 1109 1110 1111
/* 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 */
1112
	SBI_NEED_SB_WRITE,			/* need to recover superblock */
1113
	SBI_NEED_CP,				/* need to checkpoint */
1114
	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
1115
	SBI_IS_RECOVERED,			/* recovered orphan/data */
D
Daniel Rosenberg 已提交
1116
	SBI_CP_DISABLED,			/* CP was disabled last mount */
1117
	SBI_CP_DISABLED_QUICK,			/* CP was disabled quickly */
1118 1119 1120
	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 */
1121
	SBI_IS_RESIZEFS,			/* resizefs is in process */
1122 1123
};

1124 1125
enum {
	CP_TIME,
1126
	REQ_TIME,
1127 1128
	DISCARD_TIME,
	GC_TIME,
D
Daniel Rosenberg 已提交
1129
	DISABLE_TIME,
1130
	UMOUNT_DISCARD_TIMEOUT,
1131 1132 1133
	MAX_TIME,
};

1134 1135 1136 1137 1138 1139 1140
enum {
	GC_NORMAL,
	GC_IDLE_CB,
	GC_IDLE_GREEDY,
	GC_URGENT,
};

1141 1142 1143
enum {
	WHINT_MODE_OFF,		/* not pass down write hints */
	WHINT_MODE_USER,	/* try to pass down hints given by users */
1144
	WHINT_MODE_FS,		/* pass down hints with F2FS policy */
1145 1146
};

1147 1148 1149 1150 1151
enum {
	ALLOC_MODE_DEFAULT,	/* stay default */
	ALLOC_MODE_REUSE,	/* reuse segments as much as possible */
};

1152 1153 1154
enum fsync_mode {
	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
1155
	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
1156 1157
};

1158
#ifdef CONFIG_FS_ENCRYPTION
1159 1160 1161 1162 1163 1164
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
			(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif

1165 1166
struct f2fs_sb_info {
	struct super_block *sb;			/* pointer to VFS super block */
1167
	struct proc_dir_entry *s_proc;		/* proc entry */
1168
	struct f2fs_super_block *raw_super;	/* raw super block pointer */
1169
	struct rw_semaphore sb_lock;		/* lock for raw super block */
1170
	int valid_super_block;			/* valid super block no */
1171
	unsigned long s_flag;				/* flags for sbi */
1172
	struct mutex writepages;		/* mutex for writepages() */
1173 1174 1175 1176
#ifdef CONFIG_UNICODE
	struct unicode_map *s_encoding;
	__u16 s_encoding_flags;
#endif
1177

1178 1179 1180 1181 1182
#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

1183 1184 1185 1186 1187 1188
	/* 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 */
1189 1190

	/* for bio operations */
J
Jaegeuk Kim 已提交
1191
	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
1192 1193
	/* keep migration IO order for LFS mode */
	struct rw_semaphore io_order_lock;
1194
	mempool_t *write_io_dummy;		/* Dummy pages */
1195 1196 1197

	/* for checkpoint */
	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
1198
	int cur_cp_pack;			/* remain current cp pack */
1199
	spinlock_t cp_lock;			/* for flag in ckpt */
1200
	struct inode *meta_inode;		/* cache meta blocks */
1201
	struct mutex cp_mutex;			/* checkpoint procedure lock */
1202
	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
1203
	struct rw_semaphore node_write;		/* locking node writes */
1204
	struct rw_semaphore node_change;	/* locking node change */
1205
	wait_queue_head_t cp_wait;
1206 1207
	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
	long interval_time[MAX_TIME];		/* to store thresholds */
1208

1209
	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
J
Jaegeuk Kim 已提交
1210

1211 1212 1213 1214 1215
	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
1216
	/* for orphan inode, use 0'th array */
1217
	unsigned int max_orphans;		/* max orphan inodes */
1218

1219 1220 1221
	/* 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 */
1222
	struct mutex flush_lock;		/* for flush exclusion */
1223

1224 1225
	/* for extent tree cache */
	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
1226
	struct mutex extent_tree_lock;	/* locking extent radix tree */
1227 1228
	struct list_head extent_list;		/* lru list for shrinker */
	spinlock_t extent_lock;			/* locking extent lru list */
1229
	atomic_t total_ext_tree;		/* extent tree count */
1230
	struct list_head zombie_list;		/* extent zombie tree list */
1231
	atomic_t total_zombie_tree;		/* extent zombie tree count */
1232 1233
	atomic_t total_ext_node;		/* extent info count */

A
arter97 已提交
1234
	/* basic filesystem units */
1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
	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 */
1246
	struct mutex resize_mutex;		/* for resize exclusion */
1247 1248
	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
1249
	loff_t max_file_blocks;			/* max block index of file */
1250
	int dir_level;				/* directory level */
1251
	int readdir_ra;				/* readahead inode in readdir */
1252 1253 1254

	block_t user_block_count;		/* # of user blocks */
	block_t total_valid_block_count;	/* # of valid blocks */
1255
	block_t discard_blks;			/* discard command candidats */
1256
	block_t last_valid_block_count;		/* for recovery */
1257
	block_t reserved_blocks;		/* configurable reserved blocks */
1258
	block_t current_reserved_blocks;	/* current reserved blocks */
1259

D
Daniel Rosenberg 已提交
1260 1261 1262
	/* Additional tracking for no checkpoint mode */
	block_t unusable_block_count;		/* # of blocks saved by last cp */

1263
	unsigned int nquota_files;		/* # of quota sysfile */
1264
	struct rw_semaphore quota_sem;		/* blocking cp for flags */
1265

1266
	/* # of pages, see count_type */
1267
	atomic_t nr_pages[NR_COUNT_TYPE];
1268 1269
	/* # of allocated blocks */
	struct percpu_counter alloc_valid_block_count;
1270

1271
	/* writeback control */
1272
	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
1273

1274 1275 1276
	/* valid inode count */
	struct percpu_counter total_valid_inode_count;

1277 1278 1279 1280 1281
	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 */
1282
	unsigned int cur_victim_sec;		/* current victim section num */
1283
	unsigned int gc_mode;			/* current GC state */
1284
	unsigned int next_victim_seg[2];	/* next segment in victim section */
1285 1286
	/* for skip statistic */
	unsigned long long skipped_atomic_files[2];	/* FG_GC and BG_GC */
1287
	unsigned long long skipped_gc_rwsem;		/* FG_GC only */
1288

1289 1290 1291
	/* threshold for gc trials on pinned files */
	u64 gc_pin_file_threshold;

1292 1293
	/* maximum # of trials to find a victim segment for SSR and GC */
	unsigned int max_victim_search;
1294 1295
	/* migration granularity of garbage collection, unit: segment */
	unsigned int migration_granularity;
1296

1297 1298 1299 1300
	/*
	 * for stat information.
	 * one is for the LFS mode, and the other is for the SSR mode.
	 */
1301
#ifdef CONFIG_F2FS_STAT_FS
1302
	struct f2fs_stat_info *stat_info;	/* FS status information */
C
Chao Yu 已提交
1303
	atomic_t meta_count[META_MAX];		/* # of meta blocks */
1304 1305
	unsigned int segment_count[2];		/* # of allocated segments */
	unsigned int block_count[2];		/* # of allocated blocks */
1306
	atomic_t inplace_count;		/* # of inplace update */
1307 1308 1309 1310
	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
1311
	atomic_t inline_xattr;			/* # of inline_xattr inodes */
1312 1313
	atomic_t inline_inode;			/* # of inline_data inodes */
	atomic_t inline_dir;			/* # of inline_dentry inodes */
1314
	atomic_t aw_cnt;			/* # of atomic writes */
1315
	atomic_t vw_cnt;			/* # of volatile writes */
1316
	atomic_t max_aw_cnt;			/* max # of atomic writes */
1317
	atomic_t max_vw_cnt;			/* max # of volatile writes */
1318
	int bg_gc;				/* background gc calls */
1319 1320
	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
1321
	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
1322
#endif
1323
	spinlock_t stat_lock;			/* lock for stat operations */
1324

C
Chao Yu 已提交
1325 1326 1327 1328 1329
	/* For app/fs IO statistics */
	spinlock_t iostat_lock;
	unsigned long long write_iostat[NR_IO_TYPE];
	bool iostat_enable;

1330 1331 1332
	/* For sysfs suppport */
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1333 1334 1335

	/* For shrinker support */
	struct list_head s_list;
J
Jaegeuk Kim 已提交
1336 1337
	int s_ndevs;				/* number of devices */
	struct f2fs_dev_info *devs;		/* for device list */
1338 1339
	unsigned int dirty_device;		/* for checkpoint data flush */
	spinlock_t dev_lock;			/* protect dirty_device */
1340 1341
	struct mutex umount_mutex;
	unsigned int shrinker_run_no;
1342 1343 1344 1345

	/* For write statistics */
	u64 sectors_written_start;
	u64 kbytes_written;
K
Keith Mok 已提交
1346 1347 1348

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1349

C
Chao Yu 已提交
1350 1351
	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_chksum_seed;
1352 1353
};

C
Chao Yu 已提交
1354 1355 1356 1357 1358 1359 1360
struct f2fs_private_dio {
	struct inode *inode;
	void *orig_private;
	bio_end_io_t *orig_end_io;
	bool write;
};

1361
#ifdef CONFIG_F2FS_FAULT_INJECTION
1362
#define f2fs_show_injection_info(type)					\
1363
	printk_ratelimited("%sF2FS-fs : inject %s in %s of %pS\n",	\
1364
		KERN_INFO, f2fs_fault_name[type],			\
1365
		__func__, __builtin_return_address(0))
1366 1367
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
1368
	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382

	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;
}
1383 1384 1385 1386 1387 1388
#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;
}
1389 1390
#endif

1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
/*
 * 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;
}

1402 1403 1404 1405
/* 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)						 \
1406
(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
1407
		(s)->sectors_written_start) >> 1)
1408

1409 1410
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
1411 1412 1413 1414 1415 1416 1417 1418 1419
	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;
	}
1420 1421 1422 1423
}

static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
A
Arnd Bergmann 已提交
1424
	unsigned long interval = sbi->interval_time[type] * HZ;
1425 1426 1427 1428

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

1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442
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;
}

1443 1444 1445
/*
 * Inline functions
 */
C
Chao Yu 已提交
1446
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
C
Chao Yu 已提交
1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465
			      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
1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483
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);
}

1484 1485 1486 1487 1488 1489 1490 1491 1492 1493
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;
}

1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505
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
1506
	return F2FS_M_SB(page_file_mapping(page));
1507 1508
}

1509 1510 1511 1512 1513 1514 1515 1516 1517 1518
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);
}

1519 1520 1521 1522 1523
static inline struct f2fs_node *F2FS_NODE(struct page *page)
{
	return (struct f2fs_node *)page_address(page);
}

1524 1525 1526 1527 1528
static inline struct f2fs_inode *F2FS_INODE(struct page *page)
{
	return &((struct f2fs_node *)page_address(page))->i;
}

1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553
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
1554 1555 1556 1557 1558
static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->meta_inode->i_mapping;
}

1559 1560 1561 1562 1563
static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->node_inode->i_mapping;
}

1564 1565
static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
1566
	return test_bit(type, &sbi->s_flag);
1567 1568 1569
}

static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1570
{
1571
	set_bit(type, &sbi->s_flag);
1572 1573
}

1574
static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1575
{
1576
	clear_bit(type, &sbi->s_flag);
1577 1578
}

1579 1580 1581 1582 1583
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
1584 1585 1586 1587 1588 1589 1590
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;
}

1591 1592 1593 1594 1595 1596
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)));
}

1597
static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1598 1599
{
	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1600

1601 1602 1603
	return ckpt_flags & f;
}

1604
static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1605
{
1606 1607 1608 1609 1610 1611 1612 1613
	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);
1614 1615 1616 1617
	ckpt_flags |= f;
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1618
static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1619
{
1620 1621 1622
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1623
	__set_ckpt_flags(F2FS_CKPT(sbi), f);
1624
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1625 1626 1627 1628 1629 1630 1631
}

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);
1632 1633 1634 1635
	ckpt_flags &= (~f);
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1636 1637
static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
1638 1639 1640
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1641
	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
1642
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1643 1644
}

1645 1646
static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
1647
	unsigned long flags;
1648
	unsigned char *nat_bits;
1649

1650 1651 1652 1653 1654
	/*
	 * 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.
	 */
1655 1656

	if (lock)
1657
		spin_lock_irqsave(&sbi->cp_lock, flags);
1658
	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
1659
	nat_bits = NM_I(sbi)->nat_bits;
1660 1661
	NM_I(sbi)->nat_bits = NULL;
	if (lock)
1662
		spin_unlock_irqrestore(&sbi->cp_lock, flags);
1663 1664

	kvfree(nat_bits);
1665 1666 1667 1668 1669 1670 1671
}

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);

1672
	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
1673 1674
}

1675
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
1676
{
1677
	down_read(&sbi->cp_rwsem);
1678 1679
}

1680 1681 1682 1683 1684
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
	return down_read_trylock(&sbi->cp_rwsem);
}

1685
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
1686
{
1687
	up_read(&sbi->cp_rwsem);
1688 1689
}

1690
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
1691
{
1692
	down_write(&sbi->cp_rwsem);
1693 1694
}

1695
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
1696
{
1697
	up_write(&sbi->cp_rwsem);
1698 1699
}

1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712
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)
{
1713
	return (reason & (CP_UMOUNT | CP_FASTBOOT));
1714 1715 1716 1717
}

static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
{
1718 1719
	return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
			is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
1720 1721
}

1722 1723 1724 1725 1726
/*
 * Check whether the inode has blocks or not
 */
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
1727 1728
	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;

1729
	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
1730 1731
}

1732 1733 1734 1735 1736
static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
	return ofs == XATTR_NODE_OFFSET;
}

1737
static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
1738
					struct inode *inode, bool cap)
1739
{
1740 1741
	if (!inode)
		return true;
1742 1743
	if (!test_opt(sbi, RESERVE_ROOT))
		return false;
1744 1745
	if (IS_NOQUOTA(inode))
		return true;
1746
	if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
1747
		return true;
1748 1749
	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
					in_group_p(F2FS_OPTION(sbi).s_resgid))
1750
		return true;
1751
	if (cap && capable(CAP_SYS_RESOURCE))
1752
		return true;
1753 1754 1755
	return false;
}

C
Chao Yu 已提交
1756 1757
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,
1758
				 struct inode *inode, blkcnt_t *count)
1759
{
C
Chao Yu 已提交
1760
	blkcnt_t diff = 0, release = 0;
1761
	block_t avail_user_block_count;
C
Chao Yu 已提交
1762 1763 1764 1765 1766
	int ret;

	ret = dquot_reserve_block(inode, *count);
	if (ret)
		return ret;
1767

1768 1769
	if (time_to_inject(sbi, FAULT_BLOCK)) {
		f2fs_show_injection_info(FAULT_BLOCK);
C
Chao Yu 已提交
1770 1771
		release = *count;
		goto enospc;
1772
	}
1773

1774 1775 1776 1777 1778 1779
	/*
	 * 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));

1780 1781
	spin_lock(&sbi->stat_lock);
	sbi->total_valid_block_count += (block_t)(*count);
1782 1783
	avail_user_block_count = sbi->user_block_count -
					sbi->current_reserved_blocks;
1784

1785
	if (!__allow_reserved_blocks(sbi, inode, true))
1786
		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
1787 1788 1789 1790 1791 1792
	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;
	}
1793 1794
	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
		diff = sbi->total_valid_block_count - avail_user_block_count;
1795 1796
		if (diff > *count)
			diff = *count;
1797
		*count -= diff;
C
Chao Yu 已提交
1798
		release = diff;
1799
		sbi->total_valid_block_count -= diff;
1800 1801
		if (!*count) {
			spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
1802
			goto enospc;
1803
		}
1804 1805
	}
	spin_unlock(&sbi->stat_lock);
1806

1807 1808
	if (unlikely(release)) {
		percpu_counter_sub(&sbi->alloc_valid_block_count, release);
C
Chao Yu 已提交
1809
		dquot_release_reservation_block(inode, release);
1810
	}
C
Chao Yu 已提交
1811 1812 1813 1814
	f2fs_i_blocks_write(inode, *count, true, true);
	return 0;

enospc:
1815
	percpu_counter_sub(&sbi->alloc_valid_block_count, release);
C
Chao Yu 已提交
1816 1817
	dquot_release_reservation_block(inode, release);
	return -ENOSPC;
1818 1819
}

1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833
__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__)

1834
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
1835
						struct inode *inode,
1836
						block_t count)
1837
{
1838 1839
	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;

1840
	spin_lock(&sbi->stat_lock);
1841
	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
1842
	sbi->total_valid_block_count -= (block_t)count;
1843 1844 1845 1846
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
					sbi->current_reserved_blocks + count);
1847
	spin_unlock(&sbi->stat_lock);
1848
	if (unlikely(inode->i_blocks < sectors)) {
1849 1850 1851 1852
		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);
1853 1854 1855
		set_sbi_flag(sbi, SBI_NEED_FSCK);
		return;
	}
C
Chao Yu 已提交
1856
	f2fs_i_blocks_write(inode, count, false, true);
1857 1858 1859 1860
}

static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1861
	atomic_inc(&sbi->nr_pages[count_type]);
1862

C
Chao Yu 已提交
1863 1864 1865 1866 1867 1868
	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);
1869 1870
}

1871
static inline void inode_inc_dirty_pages(struct inode *inode)
1872
{
1873
	atomic_inc(&F2FS_I(inode)->dirty_pages);
1874 1875
	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1876 1877
	if (IS_NOQUOTA(inode))
		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1878 1879 1880 1881
}

static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1882
	atomic_dec(&sbi->nr_pages[count_type]);
1883 1884
}

1885
static inline void inode_dec_dirty_pages(struct inode *inode)
1886
{
1887 1888
	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
			!S_ISLNK(inode->i_mode))
1889 1890
		return;

1891
	atomic_dec(&F2FS_I(inode)->dirty_pages);
1892 1893
	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1894 1895
	if (IS_NOQUOTA(inode))
		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1896 1897
}

1898
static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
1899
{
1900
	return atomic_read(&sbi->nr_pages[count_type]);
1901 1902
}

1903
static inline int get_dirty_pages(struct inode *inode)
1904
{
1905
	return atomic_read(&F2FS_I(inode)->dirty_pages);
1906 1907
}

1908 1909
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
1910
	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
1911 1912 1913 1914
	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
						sbi->log_blocks_per_seg;

	return segs / sbi->segs_per_sec;
1915 1916
}

1917 1918
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
1919
	return sbi->total_valid_block_count;
1920 1921
}

1922 1923 1924 1925 1926
static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
{
	return sbi->discard_blks;
}

1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939
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
1940 1941 1942 1943 1944
static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
	return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

1945 1946 1947
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
1948 1949
	int offset;

C
Chao Yu 已提交
1950 1951 1952
	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
		offset = (flag == SIT_BITMAP) ?
			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
1953 1954 1955 1956 1957
		/*
		 * 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
1958 1959
	}

W
Wanpeng Li 已提交
1960
	if (__cp_payload(sbi) > 0) {
C
Changman Lee 已提交
1961 1962 1963
		if (flag == NAT_BITMAP)
			return &ckpt->sit_nat_version_bitmap;
		else
J
Jaegeuk Kim 已提交
1964
			return (unsigned char *)ckpt + F2FS_BLKSIZE;
C
Changman Lee 已提交
1965 1966
	} else {
		offset = (flag == NAT_BITMAP) ?
1967
			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
C
Changman Lee 已提交
1968 1969
		return &ckpt->sit_nat_version_bitmap + offset;
	}
1970 1971 1972 1973
}

static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
1974
	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
1975

1976
	if (sbi->cur_cp_pack == 2)
1977
		start_addr += sbi->blocks_per_seg;
1978 1979
	return start_addr;
}
1980

1981 1982 1983
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);
1984

1985 1986
	if (sbi->cur_cp_pack == 1)
		start_addr += sbi->blocks_per_seg;
1987 1988 1989
	return start_addr;
}

1990 1991 1992 1993 1994
static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
{
	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
}

1995 1996 1997 1998 1999
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
2000
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
2001
					struct inode *inode, bool is_inode)
2002 2003
{
	block_t	valid_block_count;
2004
	unsigned int valid_node_count, user_block_count;
2005
	int err;
C
Chao Yu 已提交
2006

2007 2008 2009 2010 2011 2012 2013 2014 2015 2016
	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
2017
	}
2018

2019 2020 2021 2022 2023
	if (time_to_inject(sbi, FAULT_BLOCK)) {
		f2fs_show_injection_info(FAULT_BLOCK);
		goto enospc;
	}

2024 2025
	spin_lock(&sbi->stat_lock);

2026 2027 2028
	valid_block_count = sbi->total_valid_block_count +
					sbi->current_reserved_blocks + 1;

2029
	if (!__allow_reserved_blocks(sbi, inode, false))
2030
		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
2031
	user_block_count = sbi->user_block_count;
D
Daniel Rosenberg 已提交
2032
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
2033
		user_block_count -= sbi->unusable_block_count;
2034

2035
	if (unlikely(valid_block_count > user_block_count)) {
2036
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2037
		goto enospc;
2038 2039
	}

2040
	valid_node_count = sbi->total_valid_node_count + 1;
2041
	if (unlikely(valid_node_count > sbi->total_node_count)) {
2042
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2043
		goto enospc;
2044 2045
	}

2046 2047
	sbi->total_valid_node_count++;
	sbi->total_valid_block_count++;
2048 2049
	spin_unlock(&sbi->stat_lock);

2050 2051 2052 2053
	if (inode) {
		if (is_inode)
			f2fs_mark_inode_dirty_sync(inode, true);
		else
C
Chao Yu 已提交
2054
			f2fs_i_blocks_write(inode, 1, true, true);
2055
	}
2056

2057
	percpu_counter_inc(&sbi->alloc_valid_block_count);
C
Chao Yu 已提交
2058 2059 2060
	return 0;

enospc:
2061 2062 2063 2064
	if (is_inode) {
		if (inode)
			dquot_free_inode(inode);
	} else {
C
Chao Yu 已提交
2065
		dquot_release_reservation_block(inode, 1);
2066
	}
C
Chao Yu 已提交
2067
	return -ENOSPC;
2068 2069 2070
}

static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
2071
					struct inode *inode, bool is_inode)
2072 2073 2074
{
	spin_lock(&sbi->stat_lock);

2075 2076
	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
2077

2078 2079
	sbi->total_valid_node_count--;
	sbi->total_valid_block_count--;
2080 2081 2082
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks++;
2083 2084

	spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2085

2086
	if (is_inode) {
2087
		dquot_free_inode(inode);
2088 2089
	} else {
		if (unlikely(inode->i_blocks == 0)) {
2090 2091 2092
			f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
				  inode->i_ino,
				  (unsigned long long)inode->i_blocks);
2093 2094 2095
			set_sbi_flag(sbi, SBI_NEED_FSCK);
			return;
		}
C
Chao Yu 已提交
2096
		f2fs_i_blocks_write(inode, 1, false, true);
2097
	}
2098 2099 2100 2101
}

static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
{
2102
	return sbi->total_valid_node_count;
2103 2104 2105 2106
}

static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
2107
	percpu_counter_inc(&sbi->total_valid_inode_count);
2108 2109
}

2110
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
2111
{
2112
	percpu_counter_dec(&sbi->total_valid_inode_count);
2113 2114
}

2115
static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
2116
{
2117
	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
2118 2119
}

2120 2121 2122
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
						pgoff_t index, bool for_write)
{
2123
	struct page *page;
2124

2125 2126 2127 2128 2129 2130 2131 2132
	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;
2133

2134 2135 2136 2137
		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
			f2fs_show_injection_info(FAULT_PAGE_ALLOC);
			return NULL;
		}
2138
	}
2139

2140 2141 2142 2143 2144
	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
2145 2146 2147 2148 2149 2150 2151 2152
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;
	}
2153

C
Chao Yu 已提交
2154 2155 2156
	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}

2157 2158 2159 2160 2161 2162 2163 2164 2165 2166
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);
}

2167 2168
static inline void f2fs_put_page(struct page *page, int unlock)
{
2169
	if (!page)
2170 2171 2172
		return;

	if (unlock) {
2173
		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
2174 2175
		unlock_page(page);
	}
2176
	put_page(page);
2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189
}

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,
2190
					size_t size)
2191
{
2192
	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
2193 2194
}

2195 2196 2197 2198 2199
static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
						gfp_t flags)
{
	void *entry;

2200 2201 2202
	entry = kmem_cache_alloc(cachep, flags);
	if (!entry)
		entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
2203 2204 2205
	return entry;
}

2206 2207
static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
						int npages, bool no_fail)
J
Jaegeuk Kim 已提交
2208 2209 2210
{
	struct bio *bio;

2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221
	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;
	}
2222

2223
	return bio_alloc(GFP_KERNEL, npages);
J
Jaegeuk Kim 已提交
2224 2225
}

2226 2227
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
2228 2229 2230
	if (sbi->gc_mode == GC_URGENT)
		return true;

2231 2232
	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) ||
2233 2234
		get_pages(sbi, F2FS_WB_CP_DATA) ||
		get_pages(sbi, F2FS_DIO_READ) ||
2235
		get_pages(sbi, F2FS_DIO_WRITE))
2236
		return false;
2237

2238
	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
2239 2240 2241 2242 2243 2244 2245
			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;

2246 2247 2248
	return f2fs_time_over(sbi, type);
}

2249 2250 2251 2252 2253 2254 2255
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();
}

2256 2257 2258 2259
#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)

static inline bool IS_INODE(struct page *page)
{
2260
	struct f2fs_node *p = F2FS_NODE(page);
2261

2262 2263 2264
	return RAW_IS_INODE(p);
}

2265 2266 2267 2268 2269 2270
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;
}

2271 2272 2273 2274 2275
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}

2276 2277 2278
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)
2279 2280 2281
{
	struct f2fs_node *raw_node;
	__le32 *addr_array;
2282 2283
	int base = 0;
	bool is_inode = IS_INODE(node_page);
2284

2285
	raw_node = F2FS_NODE(node_page);
2286 2287

	/* from GC path only */
2288 2289
	if (is_inode) {
		if (!inode)
2290
			base = offset_in_addr(&raw_node->i);
2291 2292
		else if (f2fs_has_extra_attr(inode))
			base = get_extra_isize(inode);
2293 2294
	}

2295
	addr_array = blkaddr_in_node(raw_node);
2296
	return le32_to_cpu(addr_array[base + offset]);
2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307
}

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

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

2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325
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;
}

2326
static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337
{
	int mask;
	int ret;

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

2338
static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349
{
	int mask;
	int ret;

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

2350 2351 2352 2353 2354 2355 2356 2357 2358
static inline void f2fs_change_bit(unsigned int nr, char *addr)
{
	int mask;

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

2359
/*
2360
 * On-disk inode flags (f2fs_inode::i_flags)
2361 2362 2363 2364 2365 2366 2367 2368 2369
 */
#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 */
2370
#define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
2371 2372

/* Flags that should be inherited by new inodes from their parent. */
2373
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
2374 2375
			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
			   F2FS_CASEFOLD_FL)
2376 2377

/* Flags that are appropriate for regular files (all but dir-specific ones). */
2378 2379
#define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
				F2FS_CASEFOLD_FL))
2380 2381 2382

/* 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
2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393

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;
}

2394 2395 2396
/* used for f2fs_inode_info->flags */
enum {
	FI_NEW_INODE,		/* indicate newly allocated inode */
2397
	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
2398
	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
2399
	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
2400 2401 2402
	FI_INC_LINK,		/* need to increment i_nlink */
	FI_ACL_MODE,		/* indicate acl mode */
	FI_NO_ALLOC,		/* should not allocate any blocks */
2403
	FI_FREE_NID,		/* free allocated nide */
2404
	FI_NO_EXTENT,		/* not to use the extent cache */
J
Jaegeuk Kim 已提交
2405
	FI_INLINE_XATTR,	/* used for inline xattr */
2406
	FI_INLINE_DATA,		/* used for inline data*/
2407
	FI_INLINE_DENTRY,	/* used for inline dentry */
2408 2409
	FI_APPEND_WRITE,	/* inode has appended data */
	FI_UPDATE_WRITE,	/* inode has in-place-update data */
J
Jaegeuk Kim 已提交
2410 2411
	FI_NEED_IPU,		/* used for ipu per file */
	FI_ATOMIC_FILE,		/* indicate atomic file */
C
Chao Yu 已提交
2412
	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
2413
	FI_VOLATILE_FILE,	/* indicate volatile file */
2414
	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
2415
	FI_DROP_CACHE,		/* drop dirty page cache */
2416
	FI_DATA_EXIST,		/* indicate data exists */
2417
	FI_INLINE_DOTS,		/* indicate inline dot dentries */
C
Chao Yu 已提交
2418
	FI_DO_DEFRAG,		/* indicate defragment is running */
2419
	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
2420
	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
2421
	FI_HOT_DATA,		/* indicate file is hot */
2422
	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
C
Chao Yu 已提交
2423
	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
2424
	FI_PIN_FILE,		/* indicate file should not be gced */
2425
	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
2426 2427
};

2428 2429 2430 2431 2432 2433 2434
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:
2435
	case FI_NEW_INODE:
2436 2437
		if (set)
			return;
2438
		/* fall through */
2439 2440
	case FI_DATA_EXIST:
	case FI_INLINE_DOTS:
2441
	case FI_PIN_FILE:
2442
		f2fs_mark_inode_dirty_sync(inode, true);
2443 2444 2445
	}
}

2446
static inline void set_inode_flag(struct inode *inode, int flag)
2447
{
2448 2449
	if (!test_bit(flag, &F2FS_I(inode)->flags))
		set_bit(flag, &F2FS_I(inode)->flags);
2450
	__mark_inode_dirty_flag(inode, flag, true);
2451 2452
}

2453
static inline int is_inode_flag_set(struct inode *inode, int flag)
2454
{
2455
	return test_bit(flag, &F2FS_I(inode)->flags);
2456 2457
}

2458
static inline void clear_inode_flag(struct inode *inode, int flag)
2459
{
2460 2461
	if (test_bit(flag, &F2FS_I(inode)->flags))
		clear_bit(flag, &F2FS_I(inode)->flags);
2462
	__mark_inode_dirty_flag(inode, flag, false);
2463 2464
}

2465
static inline void set_acl_inode(struct inode *inode, umode_t mode)
2466
{
2467 2468
	F2FS_I(inode)->i_acl_mode = mode;
	set_inode_flag(inode, FI_ACL_MODE);
2469
	f2fs_mark_inode_dirty_sync(inode, false);
2470 2471
}

2472
static inline void f2fs_i_links_write(struct inode *inode, bool inc)
2473
{
2474 2475 2476 2477
	if (inc)
		inc_nlink(inode);
	else
		drop_nlink(inode);
2478
	f2fs_mark_inode_dirty_sync(inode, true);
2479 2480
}

2481
static inline void f2fs_i_blocks_write(struct inode *inode,
C
Chao Yu 已提交
2482
					block_t diff, bool add, bool claim)
2483
{
2484 2485 2486
	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
2487 2488 2489 2490 2491 2492 2493 2494 2495 2496
	/* 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);
	}

2497
	f2fs_mark_inode_dirty_sync(inode, true);
2498 2499
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2500 2501
}

2502 2503
static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
2504 2505 2506
	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

2507 2508 2509 2510
	if (i_size_read(inode) == i_size)
		return;

	i_size_write(inode, i_size);
2511
	f2fs_mark_inode_dirty_sync(inode, true);
2512 2513
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2514 2515
}

2516
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
2517
{
2518
	F2FS_I(inode)->i_current_depth = depth;
2519
	f2fs_mark_inode_dirty_sync(inode, true);
2520 2521
}

2522 2523 2524
static inline void f2fs_i_gc_failures_write(struct inode *inode,
					unsigned int count)
{
2525
	F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
2526 2527 2528
	f2fs_mark_inode_dirty_sync(inode, true);
}

2529
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
J
Jaegeuk Kim 已提交
2530
{
2531
	F2FS_I(inode)->i_xattr_nid = xnid;
2532
	f2fs_mark_inode_dirty_sync(inode, true);
2533 2534 2535 2536 2537
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
	F2FS_I(inode)->i_pino = pino;
2538
	f2fs_mark_inode_dirty_sync(inode, true);
2539 2540
}

2541
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2542
{
2543 2544
	struct f2fs_inode_info *fi = F2FS_I(inode);

J
Jaegeuk Kim 已提交
2545
	if (ri->i_inline & F2FS_INLINE_XATTR)
2546
		set_bit(FI_INLINE_XATTR, &fi->flags);
2547
	if (ri->i_inline & F2FS_INLINE_DATA)
2548
		set_bit(FI_INLINE_DATA, &fi->flags);
2549
	if (ri->i_inline & F2FS_INLINE_DENTRY)
2550
		set_bit(FI_INLINE_DENTRY, &fi->flags);
2551
	if (ri->i_inline & F2FS_DATA_EXIST)
2552
		set_bit(FI_DATA_EXIST, &fi->flags);
2553
	if (ri->i_inline & F2FS_INLINE_DOTS)
2554
		set_bit(FI_INLINE_DOTS, &fi->flags);
2555 2556
	if (ri->i_inline & F2FS_EXTRA_ATTR)
		set_bit(FI_EXTRA_ATTR, &fi->flags);
2557 2558
	if (ri->i_inline & F2FS_PIN_FILE)
		set_bit(FI_PIN_FILE, &fi->flags);
J
Jaegeuk Kim 已提交
2559 2560
}

2561
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2562 2563 2564
{
	ri->i_inline = 0;

2565
	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
J
Jaegeuk Kim 已提交
2566
		ri->i_inline |= F2FS_INLINE_XATTR;
2567
	if (is_inode_flag_set(inode, FI_INLINE_DATA))
2568
		ri->i_inline |= F2FS_INLINE_DATA;
2569
	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
2570
		ri->i_inline |= F2FS_INLINE_DENTRY;
2571
	if (is_inode_flag_set(inode, FI_DATA_EXIST))
2572
		ri->i_inline |= F2FS_DATA_EXIST;
2573
	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
2574
		ri->i_inline |= F2FS_INLINE_DOTS;
2575 2576
	if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
		ri->i_inline |= F2FS_EXTRA_ATTR;
2577 2578
	if (is_inode_flag_set(inode, FI_PIN_FILE))
		ri->i_inline |= F2FS_PIN_FILE;
2579 2580 2581 2582 2583
}

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
2584 2585
}

2586 2587
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
2588
	return is_inode_flag_set(inode, FI_INLINE_XATTR);
2589 2590
}

2591
static inline unsigned int addrs_per_inode(struct inode *inode)
2592
{
2593 2594 2595 2596 2597 2598 2599 2600
	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);
2601 2602
}

C
Chao Yu 已提交
2603
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
J
Jaegeuk Kim 已提交
2604
{
2605
	struct f2fs_inode *ri = F2FS_INODE(page);
2606

J
Jaegeuk Kim 已提交
2607
	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
2608
					get_inline_xattr_addrs(inode)]);
J
Jaegeuk Kim 已提交
2609 2610 2611 2612
}

static inline int inline_xattr_size(struct inode *inode)
{
2613 2614 2615
	if (f2fs_has_inline_xattr(inode))
		return get_inline_xattr_addrs(inode) * sizeof(__le32);
	return 0;
J
Jaegeuk Kim 已提交
2616 2617
}

2618 2619
static inline int f2fs_has_inline_data(struct inode *inode)
{
2620
	return is_inode_flag_set(inode, FI_INLINE_DATA);
2621 2622
}

2623 2624
static inline int f2fs_exist_data(struct inode *inode)
{
2625
	return is_inode_flag_set(inode, FI_DATA_EXIST);
2626 2627
}

2628 2629
static inline int f2fs_has_inline_dots(struct inode *inode)
{
2630
	return is_inode_flag_set(inode, FI_INLINE_DOTS);
2631 2632
}

2633 2634 2635 2636 2637
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
2638 2639
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
2640
	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
J
Jaegeuk Kim 已提交
2641 2642
}

C
Chao Yu 已提交
2643 2644 2645 2646 2647
static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}

2648 2649
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
2650
	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
2651 2652
}

2653 2654
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
2655
	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
2656 2657
}

2658 2659
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
2660
	return is_inode_flag_set(inode, FI_DROP_CACHE);
2661 2662
}

C
Chao Yu 已提交
2663
static inline void *inline_data_addr(struct inode *inode, struct page *page)
2664
{
2665
	struct f2fs_inode *ri = F2FS_INODE(page);
2666
	int extra_size = get_extra_isize(inode);
2667

2668
	return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
2669 2670
}

2671 2672
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
2673
	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
2674 2675
}

2676 2677 2678 2679 2680 2681 2682 2683
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;
2684
	f2fs_mark_inode_dirty_sync(inode, true);
2685 2686 2687 2688 2689
}

static inline void clear_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise &= ~type;
2690
	f2fs_mark_inode_dirty_sync(inode, true);
2691 2692
}

2693 2694
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
2695 2696
	bool ret;

2697 2698 2699 2700 2701 2702 2703 2704 2705 2706
	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) ||
2707
			i_size_read(inode) & ~PAGE_MASK)
2708
		return false;
2709

2710
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
2711
		return false;
2712
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
2713
		return false;
2714
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
2715
		return false;
2716
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
2717 2718 2719
						&F2FS_I(inode)->i_crtime))
		return false;

2720 2721 2722 2723 2724
	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;
2725 2726
}

2727
static inline bool f2fs_readonly(struct super_block *sb)
J
Jaegeuk Kim 已提交
2728
{
2729
	return sb_rdonly(sb);
J
Jaegeuk Kim 已提交
2730 2731
}

2732 2733
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
2734
	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
2735 2736
}

2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747
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
2748 2749
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
2750 2751 2752
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	if (!test_opt(sbi, EXTENT_CACHE) ||
2753
			is_inode_flag_set(inode, FI_NO_EXTENT))
J
Jaegeuk Kim 已提交
2754 2755
		return false;

2756 2757 2758 2759 2760 2761 2762
	/*
	 * 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
2763
	return S_ISREG(inode->i_mode);
J
Jaegeuk Kim 已提交
2764 2765
}

2766 2767
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
2768
{
2769 2770
	void *ret;

2771 2772
	if (time_to_inject(sbi, FAULT_KMALLOC)) {
		f2fs_show_injection_info(FAULT_KMALLOC);
J
Jaegeuk Kim 已提交
2773
		return NULL;
2774
	}
2775

2776 2777 2778 2779 2780
	ret = kmalloc(size, flags);
	if (ret)
		return ret;

	return kvmalloc(size, flags);
2781 2782
}

C
Chao Yu 已提交
2783 2784 2785 2786 2787 2788
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
2789 2790 2791 2792 2793 2794 2795
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;
	}
2796

C
Chao Yu 已提交
2797 2798 2799 2800 2801 2802 2803 2804 2805
	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);
}

2806
static inline int get_extra_isize(struct inode *inode)
C
Chao Yu 已提交
2807
{
2808
	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
C
Chao Yu 已提交
2809 2810
}

C
Chao Yu 已提交
2811 2812 2813 2814 2815
static inline int get_inline_xattr_addrs(struct inode *inode)
{
	return F2FS_I(inode)->i_inline_xattr_size;
}

C
Chao Yu 已提交
2816
#define f2fs_get_inode_mode(i) \
2817
	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
2818 2819
	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))

2820 2821 2822 2823
#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
2824 2825
#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
2826
		((offsetof(typeof(*(f2fs_inode)), field) +	\
C
Chao Yu 已提交
2827
		sizeof((f2fs_inode)->field))			\
S
Sheng Yong 已提交
2828
		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
C
Chao Yu 已提交
2829

C
Chao Yu 已提交
2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854
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);
}

2855 2856
#define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)

C
Chao Yu 已提交
2857
#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
2858

2859 2860 2861 2862 2863 2864
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)) {
2865 2866
		f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
			 blkaddr, type);
2867 2868 2869 2870 2871
		f2fs_bug_on(sbi, 1);
	}
}

static inline bool __is_valid_data_blkaddr(block_t blkaddr)
C
Chao Yu 已提交
2872 2873 2874 2875 2876 2877
{
	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
		return false;
	return true;
}

2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898
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);
}

2899 2900 2901
/*
 * file.c
 */
2902
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
C
Chao Yu 已提交
2903
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
2904
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
2905
int f2fs_truncate(struct inode *inode);
2906 2907
int f2fs_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
2908
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
C
Chao Yu 已提交
2909 2910
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);
2911
int f2fs_precache_extents(struct inode *inode);
2912 2913
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);
2914
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
2915
int f2fs_pin_file_control(struct inode *inode, bool inc);
2916 2917 2918 2919

/*
 * inode.c
 */
2920
void f2fs_set_inode_flags(struct inode *inode);
C
Chao Yu 已提交
2921 2922
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);
2923 2924
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
2925 2926 2927
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);
2928 2929
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
C
Chao Yu 已提交
2930
void f2fs_handle_failed_inode(struct inode *inode);
2931 2932 2933 2934

/*
 * namei.c
 */
C
Chao Yu 已提交
2935
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
C
Chao Yu 已提交
2936
							bool hot, bool set);
2937 2938
struct dentry *f2fs_get_parent(struct dentry *child);

2939 2940 2941 2942
extern int f2fs_ci_compare(const struct inode *parent,
			   const struct qstr *name,
			   const struct qstr *entry);

2943 2944 2945
/*
 * dir.c
 */
C
Chao Yu 已提交
2946 2947
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
2948 2949 2950 2951
			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
2952
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
2953
			struct f2fs_dentry_ptr *d);
C
Chao Yu 已提交
2954
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
2955 2956
			const struct qstr *new_name,
			const struct qstr *orig_name, struct page *dpage);
C
Chao Yu 已提交
2957
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
2958
			unsigned int current_depth);
C
Chao Yu 已提交
2959
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975
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
2976
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
2977
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
2978
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
2979 2980 2981 2982 2983
			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);
2984

2985 2986
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
C
Chao Yu 已提交
2987
	return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
2988
				inode, inode->i_ino, inode->i_mode);
2989 2990
}

2991 2992 2993
/*
 * super.c
 */
2994 2995
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
J
Jaegeuk Kim 已提交
2996
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
2997
int f2fs_quota_sync(struct super_block *sb, int type);
C
Chao Yu 已提交
2998
void f2fs_quota_off_umount(struct super_block *sb);
2999 3000
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
3001
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
3002 3003 3004 3005

/*
 * hash.c
 */
3006 3007
f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
		const struct qstr *name_info, struct fscrypt_name *fname);
3008 3009 3010 3011 3012 3013 3014

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

C
Chao Yu 已提交
3015 3016
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);
3017 3018 3019 3020
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
3021 3022 3023
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);
3024
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
C
Chao Yu 已提交
3025 3026 3027 3028 3029
						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);
3030 3031
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
					unsigned int seq_id);
C
Chao Yu 已提交
3032 3033 3034 3035 3036 3037
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);
3038
int f2fs_move_node_page(struct page *node_page, int gc_type);
C
Chao Yu 已提交
3039
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
3040 3041
			struct writeback_control *wbc, bool atomic,
			unsigned int *seq_id);
C
Chao Yu 已提交
3042 3043
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
			struct writeback_control *wbc,
C
Chao Yu 已提交
3044
			bool do_balance, enum iostat_type io_type);
3045
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
C
Chao Yu 已提交
3046 3047 3048 3049 3050 3051 3052
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);
3053
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
3054
			unsigned int segno, struct f2fs_summary_block *sum);
3055
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
C
Chao Yu 已提交
3056 3057 3058 3059
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);
3060 3061 3062 3063

/*
 * segment.c
 */
C
Chao Yu 已提交
3064 3065 3066 3067 3068 3069
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);
3070 3071
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
3072
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
C
Chao Yu 已提交
3073
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
3074
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3075 3076 3077 3078 3079
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);
3080
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3081 3082
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
					struct cp_control *cpc);
D
Daniel Rosenberg 已提交
3083
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
3084 3085
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
3086 3087
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
3088 3089
void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
					unsigned int start, unsigned int end);
C
Chao Yu 已提交
3090
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
3091
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
C
Chao Yu 已提交
3092 3093 3094 3095 3096 3097
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
3098
						enum iostat_type io_type);
C
Chao Yu 已提交
3099 3100 3101 3102 3103
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,
3104 3105 3106 3107 3108 3109
			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
3110
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
3111
			block_t old_blkaddr, block_t *new_blkaddr,
3112 3113
			struct f2fs_summary *sum, int type,
			struct f2fs_io_info *fio, bool add_list);
3114
void f2fs_wait_on_page_writeback(struct page *page,
3115
			enum page_type type, bool ordered, bool locked);
3116
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
3117 3118
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
								block_t len);
C
Chao Yu 已提交
3119 3120 3121
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,
3122
			unsigned int val, int alloc);
C
Chao Yu 已提交
3123 3124 3125 3126 3127 3128 3129 3130
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);
3131 3132 3133 3134

/*
 * checkpoint.c
 */
3135
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
C
Chao Yu 已提交
3136 3137
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);
3138
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
C
Chao Yu 已提交
3139
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
3140 3141
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type);
C
Chao Yu 已提交
3142
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
3143
			int type, bool sync);
C
Chao Yu 已提交
3144 3145
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
3146
			long nr_to_write, enum iostat_type io_type);
C
Chao Yu 已提交
3147 3148 3149 3150 3151
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
3152
					unsigned int devidx, int type);
C
Chao Yu 已提交
3153
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
C
Chao Yu 已提交
3154
					unsigned int devidx, int type);
3155
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3156 3157 3158 3159 3160 3161 3162 3163 3164
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);
3165
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3166 3167 3168 3169
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);
3170 3171 3172 3173

/*
 * data.c
 */
3174 3175
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
3176 3177
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,
3178 3179
				struct inode *inode, struct page *page,
				nid_t ino, enum page_type type);
3180
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
3181
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3182
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
3183
void f2fs_submit_page_write(struct f2fs_io_info *fio);
3184 3185 3186
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
3187
void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
3188
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
C
Chao Yu 已提交
3189 3190
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
3191 3192 3193
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
3194
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
3195
			int op_flags, bool for_write);
C
Chao Yu 已提交
3196 3197
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,
3198
			bool for_write);
C
Chao Yu 已提交
3199
struct page *f2fs_get_new_data_page(struct inode *inode,
3200
			struct page *ipage, pgoff_t index, bool new_i_size);
C
Chao Yu 已提交
3201
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3202
void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
3203 3204 3205 3206
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
3207 3208
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);
3209 3210 3211
void f2fs_invalidate_page(struct page *page, unsigned int offset,
			unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
3212
#ifdef CONFIG_MIGRATION
3213 3214
int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
			struct page *page, enum migrate_mode mode);
3215
#endif
H
Hyunchul Lee 已提交
3216
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
M
Matthew Wilcox 已提交
3217
void f2fs_clear_page_cache_dirty_tag(struct page *page);
3218 3219 3220 3221

/*
 * gc.c
 */
C
Chao Yu 已提交
3222 3223 3224
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);
3225 3226
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
			unsigned int segno);
C
Chao Yu 已提交
3227
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
3228
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
3229 3230 3231 3232

/*
 * recovery.c
 */
C
Chao Yu 已提交
3233 3234
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
3235 3236 3237 3238 3239 3240 3241 3242 3243 3244

/*
 * 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;
3245 3246
	unsigned long long hit_largest, hit_cached, hit_rbtree;
	unsigned long long hit_total, total_ext;
J
Jaegeuk Kim 已提交
3247
	int ext_tree, zombie_tree, ext_node;
3248 3249
	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
	int ndirty_data, ndirty_qdata;
3250
	int inmem_pages;
3251
	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
3252 3253
	int nats, dirty_nats, sits, dirty_sits;
	int free_nids, avail_nids, alloc_nids;
3254
	int total_count, utilization;
C
Chao Yu 已提交
3255
	int bg_gc, nr_wb_cp_data, nr_wb_data;
3256
	int nr_rd_data, nr_rd_node, nr_rd_meta;
C
Chao Yu 已提交
3257
	int nr_dio_read, nr_dio_write;
3258
	unsigned int io_skip_bggc, other_skip_bggc;
C
Chao Yu 已提交
3259 3260
	int nr_flushing, nr_flushed, flush_list_empty;
	int nr_discarding, nr_discarded;
C
Chao Yu 已提交
3261
	int nr_discard_cmd;
C
Chao Yu 已提交
3262
	unsigned int undiscard_blks;
3263
	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
3264
	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
3265
	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
3266 3267 3268 3269
	unsigned int bimodal, avg_vblocks;
	int util_free, util_valid, util_invalid;
	int rsvd_segs, overp_segs;
	int dirty_count, node_pages, meta_pages;
3270
	int prefree_count, call_count, cp_count, bg_cp_count;
3271
	int tot_segs, node_segs, data_segs, free_segs, free_secs;
3272
	int bg_node_segs, bg_data_segs;
3273
	int tot_blks, data_blks, node_blks;
3274
	int bg_data_blks, bg_node_blks;
3275
	unsigned long long skipped_atomic_files[2];
3276 3277 3278 3279
	int curseg[NR_CURSEG_TYPE];
	int cursec[NR_CURSEG_TYPE];
	int curzone[NR_CURSEG_TYPE];

C
Chao Yu 已提交
3280
	unsigned int meta_count[META_MAX];
3281 3282
	unsigned int segment_count[2];
	unsigned int block_count[2];
3283
	unsigned int inplace_count;
C
Chao Yu 已提交
3284
	unsigned long long base_mem, cache_mem, page_mem;
3285 3286
};

3287 3288
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
3289
	return (struct f2fs_stat_info *)sbi->stat_info;
3290 3291
}

3292
#define stat_inc_cp_count(si)		((si)->cp_count++)
3293
#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
3294 3295
#define stat_inc_call_count(si)		((si)->call_count++)
#define stat_inc_bggc_count(sbi)	((sbi)->bg_gc++)
3296 3297
#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
3298 3299
#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
3300 3301 3302 3303
#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
3304 3305 3306 3307 3308 3309 3310 3311 3312 3313
#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)
3314 3315 3316
#define stat_inc_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3317
			(atomic_inc(&F2FS_I_SB(inode)->inline_inode));	\
3318 3319 3320 3321
	} while (0)
#define stat_dec_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3322
			(atomic_dec(&F2FS_I_SB(inode)->inline_inode));	\
3323
	} while (0)
3324 3325 3326
#define stat_inc_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3327
			(atomic_inc(&F2FS_I_SB(inode)->inline_dir));	\
3328 3329 3330 3331
	} while (0)
#define stat_dec_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3332
			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
3333
	} while (0)
C
Chao Yu 已提交
3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344
#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)
3345 3346 3347 3348
#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]++)
3349 3350
#define stat_inc_inplace_blocks(sbi)					\
		(atomic_inc(&(sbi)->inplace_count))
3351
#define stat_inc_atomic_write(inode)					\
3352
		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
3353
#define stat_dec_atomic_write(inode)					\
3354
		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
3355 3356 3357 3358 3359 3360 3361
#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)
3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372
#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)
3373
#define stat_inc_seg_count(sbi, type, gc_type)				\
3374
	do {								\
3375
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3376 3377
		si->tot_segs++;						\
		if ((type) == SUM_TYPE_DATA) {				\
3378
			si->data_segs++;				\
3379 3380
			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
		} else {						\
3381
			si->node_segs++;				\
3382 3383
			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
		}							\
3384 3385 3386
	} while (0)

#define stat_inc_tot_blk_count(si, blks)				\
3387
	((si)->tot_blks += (blks))
3388

3389
#define stat_inc_data_blk_count(sbi, blks, gc_type)			\
3390
	do {								\
3391
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3392 3393
		stat_inc_tot_blk_count(si, blks);			\
		si->data_blks += (blks);				\
3394
		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3395 3396
	} while (0)

3397
#define stat_inc_node_blk_count(sbi, blks, gc_type)			\
3398
	do {								\
3399
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3400 3401
		stat_inc_tot_blk_count(si, blks);			\
		si->node_blks += (blks);				\
3402
		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3403 3404
	} while (0)

3405 3406
int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
3407
void __init f2fs_create_root_stats(void);
3408
void f2fs_destroy_root_stats(void);
3409
#else
3410 3411 3412 3413
#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)
3414 3415
#define stat_io_skip_bggc_count(sbi)			do { } while (0)
#define stat_other_skip_bggc_count(sbi)			do { } while (0)
3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433
#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
3434
#define stat_inc_meta_count(sbi, blkaddr)		do { } while (0)
3435 3436 3437 3438 3439 3440 3441
#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)
3442 3443 3444

static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
3445
static inline void __init f2fs_create_root_stats(void) { }
3446
static inline void f2fs_destroy_root_stats(void) { }
3447 3448 3449
#endif

extern const struct file_operations f2fs_dir_operations;
3450 3451 3452
#ifdef CONFIG_UNICODE
extern const struct dentry_operations f2fs_dentry_ops;
#endif
3453 3454 3455 3456 3457 3458 3459
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;
3460
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
3461
extern const struct inode_operations f2fs_special_inode_operations;
C
Chao Yu 已提交
3462
extern struct kmem_cache *f2fs_inode_entry_slab;
3463

3464 3465 3466
/*
 * inline.c
 */
3467 3468
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
C
Chao Yu 已提交
3469 3470 3471
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);
3472 3473 3474 3475
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
3476 3477
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
3478
			struct fscrypt_name *fname, struct page **res_page);
C
Chao Yu 已提交
3479
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
3480 3481 3482 3483
			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
3484 3485 3486
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
				struct page *page, struct inode *dir,
				struct inode *inode);
3487 3488 3489 3490 3491 3492
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);
3493

3494 3495 3496
/*
 * shrinker.c
 */
3497 3498 3499 3500 3501 3502
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);
3503

3504 3505 3506
/*
 * extent_cache.c
 */
C
Chao Yu 已提交
3507
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
3508
				struct rb_entry *cached_re, unsigned int ofs);
C
Chao Yu 已提交
3509
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3510 3511 3512 3513
				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,
3514 3515 3516
		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
3517
		bool force, bool *leftmost);
C
Chao Yu 已提交
3518
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3519
						struct rb_root_cached *root);
3520 3521 3522 3523 3524 3525 3526 3527
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
3528
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
3529
			pgoff_t fofs, block_t blkaddr, unsigned int len);
C
Chao Yu 已提交
3530 3531 3532
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
3533

3534 3535 3536
/*
 * sysfs.c
 */
3537 3538 3539 3540
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);
3541

3542 3543 3544
/*
 * crypto support
 */
3545 3546
static inline bool f2fs_encrypted_file(struct inode *inode)
{
3547
	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
3548 3549
}

3550 3551
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
3552
#ifdef CONFIG_FS_ENCRYPTION
3553
	file_set_encrypt(inode);
C
Chao Yu 已提交
3554
	f2fs_set_inode_flags(inode);
3555 3556 3557
#endif
}

3558 3559 3560 3561 3562
/*
 * 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)
3563
{
3564
	return f2fs_encrypted_file(inode);
3565 3566
}

3567
#define F2FS_FEATURE_FUNCS(name, flagname) \
3568
static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
3569
{ \
3570
	return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
3571 3572
}

3573 3574 3575 3576 3577 3578 3579 3580
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);
3581
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
3582
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
3583
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
C
Chao Yu 已提交
3584

3585
#ifdef CONFIG_BLK_DEV_ZONED
3586 3587
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
				    block_t blkaddr)
3588 3589 3590
{
	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;

3591
	return test_bit(zno, FDEV(devi).blkz_seq);
3592 3593 3594
}
#endif

3595
static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
3596
{
3597
	return f2fs_sb_has_blkzoned(sbi);
3598
}
3599

3600 3601 3602 3603 3604 3605
static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
{
	return blk_queue_discard(bdev_get_queue(bdev)) ||
	       bdev_is_zoned(bdev);
}

3606 3607
static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
{
3608 3609 3610 3611 3612 3613 3614 3615 3616
	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;
3617 3618 3619 3620 3621 3622
}

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);
3623 3624
}

3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638
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;
}


3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653
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;
	}
}

3654 3655
static inline bool f2fs_may_encrypt(struct inode *inode)
{
3656
#ifdef CONFIG_FS_ENCRYPTION
A
Al Viro 已提交
3657
	umode_t mode = inode->i_mode;
3658 3659 3660

	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
#else
3661
	return false;
3662 3663 3664
#endif
}

3665 3666
static inline int block_unaligned_IO(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
H
Hyunchul Lee 已提交
3667
{
3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693
	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;
3694
	if (f2fs_is_multi_device(sbi))
3695 3696 3697 3698 3699
		return true;
	/*
	 * for blkzoned device, fallback direct IO to buffered IO, so
	 * all IOs can be serialized by log-structured write.
	 */
3700
	if (f2fs_sb_has_blkzoned(sbi))
3701 3702 3703 3704
		return true;
	if (test_opt(sbi, LFS) && (rw == WRITE) &&
				block_unaligned_IO(inode, iocb, iter))
		return true;
J
Jaegeuk Kim 已提交
3705
	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
C
Chao Yu 已提交
3706
					!IS_SWAPFILE(inode))
D
Daniel Rosenberg 已提交
3707 3708
		return true;

3709
	return false;
H
Hyunchul Lee 已提交
3710 3711
}

3712
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
3713 3714
extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
							unsigned int type);
3715
#else
C
Chao Yu 已提交
3716
#define f2fs_build_fault_attr(sbi, rate, type)		do { } while (0)
3717 3718
#endif

3719 3720 3721
static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_QUOTA
3722
	if (f2fs_sb_has_quota_ino(sbi))
3723 3724 3725 3726 3727 3728 3729 3730
		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
3731

3732 3733 3734
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3735
#endif /* _LINUX_F2FS_H */