f2fs.h 117.9 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
#include <linux/fscrypt.h>
E
Eric Biggers 已提交
28
#include <linux/fsverity.h>
D
Dave Chinner 已提交
29

30
#ifdef CONFIG_F2FS_CHECK_FS
31
#define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
32
#else
33 34 35 36
#define f2fs_bug_on(sbi, condition)					\
	do {								\
		if (unlikely(condition)) {				\
			WARN_ON(1);					\
37
			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
38 39
		}							\
	} while (0)
40 41
#endif

J
Jaegeuk Kim 已提交
42 43
enum {
	FAULT_KMALLOC,
C
Chao Yu 已提交
44
	FAULT_KVMALLOC,
45
	FAULT_PAGE_ALLOC,
C
Chao Yu 已提交
46
	FAULT_PAGE_GET,
47
	FAULT_ALLOC_BIO,
J
Jaegeuk Kim 已提交
48 49 50 51
	FAULT_ALLOC_NID,
	FAULT_ORPHAN,
	FAULT_BLOCK,
	FAULT_DIR_DEPTH,
52
	FAULT_EVICT_INODE,
53
	FAULT_TRUNCATE,
54
	FAULT_READ_IO,
55
	FAULT_CHECKPOINT,
56
	FAULT_DISCARD,
57
	FAULT_WRITE_IO,
J
Jaegeuk Kim 已提交
58 59 60
	FAULT_MAX,
};

61
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
62 63
#define F2FS_ALL_FAULT_TYPE		((1 << FAULT_MAX) - 1)

S
Sheng Yong 已提交
64 65 66 67 68 69
struct f2fs_fault_info {
	atomic_t inject_ops;
	unsigned int inject_rate;
	unsigned int inject_type;
};

70
extern const char *f2fs_fault_name[FAULT_MAX];
71
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
J
Jaegeuk Kim 已提交
72 73
#endif

74 75 76 77 78 79 80 81 82 83
/*
 * 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
84
#define F2FS_MOUNT_INLINE_XATTR		0x00000080
85
#define F2FS_MOUNT_INLINE_DATA		0x00000100
86 87 88
#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
#define F2FS_MOUNT_NOBARRIER		0x00000800
89
#define F2FS_MOUNT_FASTBOOT		0x00001000
90
#define F2FS_MOUNT_EXTENT_CACHE		0x00002000
91
#define F2FS_MOUNT_FORCE_FG_GC		0x00004000
92
#define F2FS_MOUNT_DATA_FLUSH		0x00008000
93
#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
94 95
#define F2FS_MOUNT_ADAPTIVE		0x00020000
#define F2FS_MOUNT_LFS			0x00040000
C
Chao Yu 已提交
96 97
#define F2FS_MOUNT_USRQUOTA		0x00080000
#define F2FS_MOUNT_GRPQUOTA		0x00100000
C
Chao Yu 已提交
98
#define F2FS_MOUNT_PRJQUOTA		0x00200000
C
Chao Yu 已提交
99
#define F2FS_MOUNT_QUOTA		0x00400000
C
Chao Yu 已提交
100
#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
101
#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
D
Daniel Rosenberg 已提交
102
#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
103

104 105 106 107
#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)
108 109 110 111 112

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

113 114 115 116
typedef u32 block_t;	/*
			 * should not change u32, since it is the on-disk block
			 * address format, __le32.
			 */
117 118 119
typedef u32 nid_t;

struct f2fs_mount_info {
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
	unsigned int opt;
	int write_io_size_bits;		/* Write IO size bits */
	block_t root_reserved_blocks;	/* root reserved blocks */
	kuid_t s_resuid;		/* reserved blocks for uid */
	kgid_t s_resgid;		/* reserved blocks for gid */
	int active_logs;		/* # of active logs */
	int inline_xattr_size;		/* inline xattr size */
#ifdef CONFIG_F2FS_FAULT_INJECTION
	struct f2fs_fault_info fault_info;	/* For fault injection */
#endif
#ifdef CONFIG_QUOTA
	/* Names of quota files with journalled quota */
	char *s_qf_names[MAXQUOTAS];
	int s_jquota_fmt;			/* Format of quota to use */
#endif
	/* For which write hints are passed down to block layer */
	int whint_mode;
	int alloc_mode;			/* segment allocation policy */
	int fsync_mode;			/* fsync policy */
139
	bool test_dummy_encryption;	/* test dummy encryption */
140 141 142
	block_t unusable_cap;		/* Amount of space allowed to be
					 * unusable when disabling checkpoint
					 */
143 144
};

145 146 147 148
#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
149
#define F2FS_FEATURE_PRJQUOTA		0x0010
C
Chao Yu 已提交
150
#define F2FS_FEATURE_INODE_CHKSUM	0x0020
C
Chao Yu 已提交
151
#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
J
Jaegeuk Kim 已提交
152
#define F2FS_FEATURE_QUOTA_INO		0x0080
C
Chao Yu 已提交
153
#define F2FS_FEATURE_INODE_CRTIME	0x0100
154
#define F2FS_FEATURE_LOST_FOUND		0x0200
E
Eric Biggers 已提交
155
#define F2FS_FEATURE_VERITY		0x0400
156
#define F2FS_FEATURE_SB_CHKSUM		0x0800
157
#define F2FS_FEATURE_CASEFOLD		0x1000
158

159 160 161 162 163 164 165
#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))
166

167 168 169 170 171 172
/*
 * Default values for user and/or group using reserved blocks
 */
#define	F2FS_DEF_RESUID		0
#define	F2FS_DEF_RESGID		0

173 174 175 176 177 178 179 180
/*
 * For checkpoint manager
 */
enum {
	NAT_BITMAP,
	SIT_BITMAP
};

181 182 183 184 185
#define	CP_UMOUNT	0x00000001
#define	CP_FASTBOOT	0x00000002
#define	CP_SYNC		0x00000004
#define	CP_RECOVERY	0x00000008
#define	CP_DISCARD	0x00000010
186
#define CP_TRIMMED	0x00000020
D
Daniel Rosenberg 已提交
187
#define CP_PAUSE	0x00000040
188

189
#define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
C
Chao Yu 已提交
190
#define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
191
#define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
192
#define DEF_MID_DISCARD_ISSUE_TIME	500	/* 500 ms, if device busy */
193
#define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
194
#define DEF_DISCARD_URGENT_UTIL		80	/* do more discard over 80% */
195
#define DEF_CP_INTERVAL			60	/* 60 secs */
196
#define DEF_IDLE_INTERVAL		5	/* 5 secs */
D
Daniel Rosenberg 已提交
197
#define DEF_DISABLE_INTERVAL		5	/* 5 secs */
198
#define DEF_DISABLE_QUICK_INTERVAL	1	/* 1 secs */
199
#define DEF_UMOUNT_DISCARD_TIMEOUT	5	/* 5 secs */
J
Jaegeuk Kim 已提交
200

201 202
struct cp_control {
	int reason;
203 204 205
	__u64 trim_start;
	__u64 trim_end;
	__u64 trim_minlen;
206 207
};

208
/*
209
 * indicate meta/data type
210 211 212 213
 */
enum {
	META_CP,
	META_NAT,
214
	META_SIT,
215
	META_SSA,
C
Chao Yu 已提交
216
	META_MAX,
217
	META_POR,
C
Chao Yu 已提交
218 219 220 221 222 223 224 225
	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
					 */
226
	META_GENERIC,
227 228
};

J
Jaegeuk Kim 已提交
229 230 231
/* for the list of ino */
enum {
	ORPHAN_INO,		/* for orphan ino list */
232 233
	APPEND_INO,		/* for append ino list */
	UPDATE_INO,		/* for update ino list */
234
	TRANS_DIR_INO,		/* for trasactions dir ino list */
C
Chao Yu 已提交
235
	FLUSH_INO,		/* for multiple device flushing */
J
Jaegeuk Kim 已提交
236 237 238 239
	MAX_INO_ENTRY,		/* max. list */
};

struct ino_entry {
C
Chao Yu 已提交
240 241 242
	struct list_head list;		/* list head */
	nid_t ino;			/* inode number */
	unsigned int dirty_device;	/* dirty device bitmap */
243 244
};

245
/* for the list of inodes to be GCed */
246
struct inode_entry {
247 248 249 250
	struct list_head list;	/* list head */
	struct inode *inode;	/* vfs inode pointer */
};

251 252 253 254 255 256
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
257
/* for the bitmap indicate blocks to be discarded */
258 259
struct discard_entry {
	struct list_head list;	/* list head */
C
Chao Yu 已提交
260 261
	block_t start_blkaddr;	/* start blockaddr of current segment */
	unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];	/* segment discard bitmap */
262 263
};

264 265 266
/* default discard granularity of inner discard thread, unit: block count */
#define DEFAULT_DISCARD_GRANULARITY		16

C
Chao Yu 已提交
267 268 269
/* 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
270
					(MAX_PLIST_NUM - 1) : ((blk_num) - 1))
C
Chao Yu 已提交
271

272
enum {
273 274 275 276
	D_PREP,			/* initial */
	D_PARTIAL,		/* partially submitted */
	D_SUBMIT,		/* all submitted */
	D_DONE,			/* finished */
277 278
};

279 280 281 282 283 284
struct discard_info {
	block_t lstart;			/* logical start address */
	block_t len;			/* length */
	block_t start;			/* actual start address in dev */
};

285
struct discard_cmd {
286 287 288 289 290 291 292 293 294 295
	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 */

	};
296 297
	struct list_head list;		/* command list */
	struct completion wait;		/* compleation */
298
	struct block_device *bdev;	/* bdev */
299
	unsigned short ref;		/* reference count */
300
	unsigned char state;		/* state */
301
	unsigned char queued;		/* queued discard */
302
	int error;			/* bio error */
303 304
	spinlock_t lock;		/* for state/bio_ref updating */
	unsigned short bio_ref;		/* bio reference count */
C
Chao Yu 已提交
305 306
};

C
Chao Yu 已提交
307 308 309 310 311 312 313 314
enum {
	DPOLICY_BG,
	DPOLICY_FORCE,
	DPOLICY_FSTRIM,
	DPOLICY_UMOUNT,
	MAX_DPOLICY,
};

C
Chao Yu 已提交
315
struct discard_policy {
C
Chao Yu 已提交
316
	int type;			/* type of discard */
C
Chao Yu 已提交
317
	unsigned int min_interval;	/* used for candidates exist */
318
	unsigned int mid_interval;	/* used for device busy */
C
Chao Yu 已提交
319 320 321 322 323
	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
324
	bool ordered;			/* issue discard by lba order */
C
Chao Yu 已提交
325
	unsigned int granularity;	/* discard granularity */
326
	int timeout;			/* discard timeout for put_super */
C
Chao Yu 已提交
327 328
};

329
struct discard_cmd_control {
330
	struct task_struct *f2fs_issue_discard;	/* discard thread */
331
	struct list_head entry_list;		/* 4KB discard entry list */
C
Chao Yu 已提交
332
	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
333
	struct list_head wait_list;		/* store on-flushing entries */
334
	struct list_head fstrim_list;		/* in-flight discard from fstrim */
335
	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
336
	unsigned int discard_wake;		/* to wake up discard thread */
337
	struct mutex cmd_lock;
C
Chao Yu 已提交
338 339
	unsigned int nr_discards;		/* # of discards in the list */
	unsigned int max_discards;		/* max. discards to be issued */
340
	unsigned int discard_granularity;	/* discard granularity */
C
Chao Yu 已提交
341
	unsigned int undiscard_blks;		/* # of undiscard blocks */
C
Chao Yu 已提交
342
	unsigned int next_pos;			/* next discard position */
C
Chao Yu 已提交
343
	atomic_t issued_discard;		/* # of issued discard */
344
	atomic_t queued_discard;		/* # of queued discard */
C
Chao Yu 已提交
345
	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
C
Chao Yu 已提交
346
	struct rb_root_cached root;		/* root of discard rb-tree */
347
	bool rbtree_check;			/* config for consistence check */
C
Chao Yu 已提交
348 349
};

350 351 352 353
/* 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 */
354 355
	block_t blkaddr;	/* block address locating the last fsync */
	block_t last_dentry;	/* block address locating the last dentry */
356 357
};

358 359
#define nats_in_cursum(jnl)		(le16_to_cpu((jnl)->n_nats))
#define sits_in_cursum(jnl)		(le16_to_cpu((jnl)->n_sits))
360

361 362 363 364
#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)
365

366 367
#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
368

369
static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
370
{
371
	int before = nats_in_cursum(journal);
372

373
	journal->n_nats = cpu_to_le16(before + i);
374 375 376
	return before;
}

377
static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
378
{
379
	int before = sits_in_cursum(journal);
380

381
	journal->n_sits = cpu_to_le16(before + i);
382 383 384
	return before;
}

385 386
static inline bool __has_cursum_space(struct f2fs_journal *journal,
							int size, int type)
387 388
{
	if (type == NAT_JOURNAL)
389 390
		return size <= MAX_NAT_JENTRIES(journal);
	return size <= MAX_SIT_JENTRIES(journal);
391 392
}

393 394 395
/*
 * ioctl commands
 */
J
Jaegeuk Kim 已提交
396 397
#define F2FS_IOC_GETFLAGS		FS_IOC_GETFLAGS
#define F2FS_IOC_SETFLAGS		FS_IOC_SETFLAGS
C
Chao Yu 已提交
398
#define F2FS_IOC_GETVERSION		FS_IOC_GETVERSION
J
Jaegeuk Kim 已提交
399 400 401 402

#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)
403
#define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
404 405
#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
406
#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
407
#define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
J
Jaegeuk Kim 已提交
408 409
#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
						struct f2fs_defragment)
410 411
#define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
						struct f2fs_move_range)
412 413
#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
						struct f2fs_flush_device)
414 415
#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
						struct f2fs_gc_range)
416
#define F2FS_IOC_GET_FEATURES		_IOR(F2FS_IOCTL_MAGIC, 12, __u32)
417 418
#define F2FS_IOC_SET_PIN_FILE		_IOW(F2FS_IOCTL_MAGIC, 13, __u32)
#define F2FS_IOC_GET_PIN_FILE		_IOR(F2FS_IOCTL_MAGIC, 14, __u32)
419
#define F2FS_IOC_PRECACHE_EXTENTS	_IO(F2FS_IOCTL_MAGIC, 15)
420
#define F2FS_IOC_RESIZE_FS		_IOW(F2FS_IOCTL_MAGIC, 16, __u64)
421

C
Chao Yu 已提交
422 423 424
#define F2FS_IOC_GET_VOLUME_NAME	FS_IOC_GETFSLABEL
#define F2FS_IOC_SET_VOLUME_NAME	FS_IOC_SETFSLABEL

425 426 427
#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
428

J
Jaegeuk Kim 已提交
429 430 431 432 433 434 435 436
/*
 * 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 */
437
#define F2FS_GOING_DOWN_METAFLUSH	0x3	/* going down with meta flush */
438
#define F2FS_GOING_DOWN_NEED_FSCK	0x4	/* going down to trigger fsck */
J
Jaegeuk Kim 已提交
439

440 441 442 443
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
 * ioctl commands in 32 bit emulation
 */
444 445 446
#define F2FS_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
#define F2FS_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
#define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
447 448
#endif

449 450 451
#define F2FS_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
#define F2FS_IOC_FSSETXATTR		FS_IOC_FSSETXATTR

452 453 454 455 456 457
struct f2fs_gc_range {
	u32 sync;
	u64 start;
	u64 len;
};

C
Chao Yu 已提交
458 459 460 461 462
struct f2fs_defragment {
	u64 start;
	u64 len;
};

463 464 465 466 467 468 469
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 */
};

470 471 472 473 474
struct f2fs_flush_device {
	u32 dev_num;		/* device number to flush */
	u32 segments;		/* # of segments to flush */
};

C
Chao Yu 已提交
475 476
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE	1
477
static inline int get_extra_isize(struct inode *inode);
C
Chao Yu 已提交
478 479 480
static inline int get_inline_xattr_addrs(struct inode *inode);
#define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
				(CUR_ADDRS_PER_INODE(inode) -		\
481
				get_inline_xattr_addrs(inode) -	\
C
Chao Yu 已提交
482
				DEF_INLINE_RESERVED_SIZE))
C
Chao Yu 已提交
483 484 485 486 487

/* 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))
488 489
#define INLINE_DENTRY_BITMAP_SIZE(inode) \
	DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
C
Chao Yu 已提交
490 491 492 493 494
#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)))

495 496 497
/*
 * For INODE and NODE manager
 */
498 499
/* for directory operations */
struct f2fs_dentry_ptr {
500
	struct inode *inode;
501
	void *bitmap;
502 503 504
	struct f2fs_dir_entry *dentry;
	__u8 (*filename)[F2FS_SLOT_LEN];
	int max;
505
	int nr_bitmap;
506 507
};

508 509
static inline void make_dentry_ptr_block(struct inode *inode,
		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
510
{
511
	d->inode = inode;
512
	d->max = NR_DENTRY_IN_BLOCK;
513
	d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
514
	d->bitmap = t->dentry_bitmap;
515 516 517
	d->dentry = t->dentry;
	d->filename = t->filename;
}
518

519
static inline void make_dentry_ptr_inline(struct inode *inode,
C
Chao Yu 已提交
520
					struct f2fs_dentry_ptr *d, void *t)
521
{
C
Chao Yu 已提交
522 523 524 525
	int entry_cnt = NR_INLINE_DENTRY(inode);
	int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
	int reserved_size = INLINE_RESERVED_SIZE(inode);

526
	d->inode = inode;
C
Chao Yu 已提交
527 528 529 530 531 532
	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;
533 534
}

535 536 537 538 539 540 541
/*
 * 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)
542 543 544 545 546
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
547
					 * by get_data_block.
548
					 */
549 550
};

551 552
#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */

553 554 555
/* maximum retry quota flush count */
#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8

556
#define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
557

558 559
#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */

560
/* for in-memory extent cache entry */
561 562 563 564
#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
565

566 567 568 569 570 571
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 */
};

572
struct extent_info {
573 574
	unsigned int fofs;		/* start offset in a file */
	unsigned int len;		/* length of the extent */
575
	u32 blk;			/* start block address of the extent */
576 577 578
};

struct extent_node {
C
Chao Yu 已提交
579 580
	struct rb_node rb_node;		/* rb node located in rb-tree */
	struct extent_info ei;		/* extent info */
581
	struct list_head list;		/* node in global extent list of sbi */
582
	struct extent_tree *et;		/* extent tree pointer */
583 584 585 586
};

struct extent_tree {
	nid_t ino;			/* inode number */
C
Chao Yu 已提交
587
	struct rb_root_cached root;	/* root of extent info rb-tree */
588
	struct extent_node *cached_en;	/* recently accessed extent node */
J
Jaegeuk Kim 已提交
589
	struct extent_info largest;	/* largested extent info */
590
	struct list_head list;		/* to be used by sbi->zombie_list */
591
	rwlock_t lock;			/* protect extent info rb-tree */
592
	atomic_t node_cnt;		/* # of extent node in rb-tree*/
593
	bool largest_updated;		/* largest extent updated */
594 595
};

J
Jaegeuk Kim 已提交
596 597 598 599 600 601 602
/*
 * 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)
603 604 605
#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
606 607 608 609 610 611

struct f2fs_map_blocks {
	block_t m_pblk;
	block_t m_lblk;
	unsigned int m_len;
	unsigned int m_flags;
612
	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
613
	pgoff_t *m_next_extent;		/* point to next possible extent */
614
	int m_seg_type;
C
Chao Yu 已提交
615
	bool m_may_create;		/* indicate it is from write path */
J
Jaegeuk Kim 已提交
616 617
};

C
Chao Yu 已提交
618
/* for flag in get_data_block */
619 620 621 622
enum {
	F2FS_GET_BLOCK_DEFAULT,
	F2FS_GET_BLOCK_FIEMAP,
	F2FS_GET_BLOCK_BMAP,
623
	F2FS_GET_BLOCK_DIO,
624 625
	F2FS_GET_BLOCK_PRE_DIO,
	F2FS_GET_BLOCK_PRE_AIO,
626
	F2FS_GET_BLOCK_PRECACHE,
627
};
C
Chao Yu 已提交
628

629 630 631 632
/*
 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
 */
#define FADVISE_COLD_BIT	0x01
633
#define FADVISE_LOST_PINO_BIT	0x02
634
#define FADVISE_ENCRYPT_BIT	0x04
635
#define FADVISE_ENC_NAME_BIT	0x08
636
#define FADVISE_KEEP_SIZE_BIT	0x10
C
Chao Yu 已提交
637
#define FADVISE_HOT_BIT		0x20
E
Eric Biggers 已提交
638
#define FADVISE_VERITY_BIT	0x40
639

640 641
#define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)

642 643 644 645 646 647
#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)
648 649 650
#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)
651 652
#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)
653 654
#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
655 656 657
#define file_is_hot(inode)	is_file(inode, FADVISE_HOT_BIT)
#define file_set_hot(inode)	set_file(inode, FADVISE_HOT_BIT)
#define file_clear_hot(inode)	clear_file(inode, FADVISE_HOT_BIT)
E
Eric Biggers 已提交
658 659
#define file_is_verity(inode)	is_file(inode, FADVISE_VERITY_BIT)
#define file_set_verity(inode)	set_file(inode, FADVISE_VERITY_BIT)
660

661 662
#define DEF_DIR_LEVEL		0

663 664 665 666 667 668
enum {
	GC_FAILURE_PIN,
	GC_FAILURE_ATOMIC,
	MAX_GC_FAILURE
};

669 670 671 672
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 */
673
	unsigned char i_dir_level;	/* use for dentry level for large dir */
674 675 676
	unsigned int i_current_depth;	/* only for directory depth */
	/* for gc failure statistic */
	unsigned int i_gc_failures[MAX_GC_FAILURE];
677
	unsigned int i_pino;		/* parent inode number */
678 679 680 681
	umode_t i_acl_mode;		/* keep file acl mode temporarily */

	/* Use below internally in f2fs*/
	unsigned long flags;		/* use to pass per-file flags */
682
	struct rw_semaphore i_sem;	/* protect fi info */
683
	atomic_t dirty_pages;		/* # of dirty pages */
684 685
	f2fs_hash_t chash;		/* hash value of given file name */
	unsigned int clevel;		/* maximum level of given file name */
686
	struct task_struct *task;	/* lookup and create consistency */
C
Chao Yu 已提交
687
	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
688
	nid_t i_xattr_nid;		/* node id that contains xattrs */
689
	loff_t	last_disk_size;		/* lastly written file size */
J
Jaegeuk Kim 已提交
690

C
Chao Yu 已提交
691 692 693 694 695 696
#ifdef CONFIG_QUOTA
	struct dquot *i_dquot[MAXQUOTAS];

	/* quota space reservation, managed internally by quota code */
	qsize_t i_reserved_quota;
#endif
697 698
	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
699
	struct list_head inmem_ilist;	/* list for inmem inodes */
J
Jaegeuk Kim 已提交
700
	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
701
	struct task_struct *inmem_task;	/* store inmemory task */
J
Jaegeuk Kim 已提交
702
	struct mutex inmem_lock;	/* lock for inmemory pages */
J
Jaegeuk Kim 已提交
703
	struct extent_tree *extent_tree;	/* cached extent_tree entry */
C
Chao Yu 已提交
704 705 706

	/* avoid racing between foreground op and gc */
	struct rw_semaphore i_gc_rwsem[2];
707
	struct rw_semaphore i_mmap_sem;
708
	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
C
Chao Yu 已提交
709

710
	int i_extra_isize;		/* size of extra space located in i_addr */
C
Chao Yu 已提交
711
	kprojid_t i_projid;		/* id for project quota */
C
Chao Yu 已提交
712
	int i_inline_xattr_size;	/* inline xattr size */
713 714
	struct timespec64 i_crtime;	/* inode creation time */
	struct timespec64 i_disk_time[4];/* inode disk times */
715 716 717
};

static inline void get_extent_info(struct extent_info *ext,
C
Chao Yu 已提交
718
					struct f2fs_extent *i_ext)
719
{
C
Chao Yu 已提交
720 721 722
	ext->fofs = le32_to_cpu(i_ext->fofs);
	ext->blk = le32_to_cpu(i_ext->blk);
	ext->len = le32_to_cpu(i_ext->len);
723 724 725 726 727 728
}

static inline void set_raw_extent(struct extent_info *ext,
					struct f2fs_extent *i_ext)
{
	i_ext->fofs = cpu_to_le32(ext->fofs);
729
	i_ext->blk = cpu_to_le32(ext->blk);
730 731 732
	i_ext->len = cpu_to_le32(ext->len);
}

733 734 735 736 737 738 739 740
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;
}

741
static inline bool __is_discard_mergeable(struct discard_info *back,
742
			struct discard_info *front, unsigned int max_len)
743
{
744
	return (back->lstart + back->len == front->lstart) &&
745
		(back->len + front->len <= max_len);
746 747 748
}

static inline bool __is_discard_back_mergeable(struct discard_info *cur,
749
			struct discard_info *back, unsigned int max_len)
750
{
751
	return __is_discard_mergeable(back, cur, max_len);
752 753 754
}

static inline bool __is_discard_front_mergeable(struct discard_info *cur,
755
			struct discard_info *front, unsigned int max_len)
756
{
757
	return __is_discard_mergeable(cur, front, max_len);
758 759
}

760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778
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);
}

779
extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
780 781
static inline void __try_update_largest_extent(struct extent_tree *et,
						struct extent_node *en)
782
{
783
	if (en->ei.len > et->largest.len) {
784
		et->largest = en->ei;
785
		et->largest_updated = true;
786
	}
787 788
}

C
Chao Yu 已提交
789 790 791 792 793 794 795
/*
 * 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
796 797
};

798 799 800
struct f2fs_nm_info {
	block_t nat_blkaddr;		/* base disk address of NAT */
	nid_t max_nid;			/* maximum possible node ids */
801
	nid_t available_nids;		/* # of available node ids */
802
	nid_t next_scan_nid;		/* the next nid to be scanned */
803
	unsigned int ram_thresh;	/* control the memory footprint */
C
Chao Yu 已提交
804
	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
C
Chao Yu 已提交
805
	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
806 807 808

	/* NAT cache management */
	struct radix_tree_root nat_root;/* root of the nat entry cache */
809
	struct radix_tree_root nat_set_root;/* root of the nat set cache */
810
	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
811
	struct list_head nat_entries;	/* cached nat entry list (clean) */
812
	spinlock_t nat_list_lock;	/* protect clean nat entry list */
813
	unsigned int nat_cnt;		/* the # of cached nat entries */
814
	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
815
	unsigned int nat_blocks;	/* # of nat blocks */
816 817

	/* free node ids management */
818
	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
C
Chao Yu 已提交
819 820
	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
821
	spinlock_t nid_list_lock;	/* protect nid lists ops */
822
	struct mutex build_lock;	/* lock for build free nids */
823
	unsigned char **free_nid_bitmap;
C
Chao Yu 已提交
824
	unsigned char *nat_block_bitmap;
825
	unsigned short *free_nid_count;	/* free nid count of NAT block */
826 827 828

	/* for checkpoint */
	char *nat_bitmap;		/* NAT bitmap pointer */
829 830 831 832 833

	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 */
834 835 836
#ifdef CONFIG_F2FS_CHECK_FS
	char *nat_bitmap_mir;		/* NAT bitmap mirror */
#endif
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
	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 */
852
	bool node_changed;		/* is node block changed */
853 854
	char cur_level;			/* level of hole node page */
	char max_level;			/* level of current page located */
855 856 857 858 859 860
	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)
{
861
	memset(dn, 0, sizeof(*dn));
862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891
	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 */
892
	NO_CHECK_TYPE,
J
Jaegeuk Kim 已提交
893
	CURSEG_COLD_DATA_PINNED,/* cold data for pinned file */
894 895
};

896 897
struct flush_cmd {
	struct completion wait;
898
	struct llist_node llnode;
C
Chao Yu 已提交
899
	nid_t ino;
900 901 902
	int ret;
};

903 904 905
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
906
	atomic_t issued_flush;			/* # of issued flushes */
907
	atomic_t queued_flush;			/* # of queued flushes */
908 909
	struct llist_head issue_list;		/* list for command issue */
	struct llist_node *dispatch_list;	/* list for command dispatch */
910 911
};

912 913 914 915 916 917
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
918 919
	struct rw_semaphore curseg_lock;	/* for preventing curseg change */

920 921 922 923 924 925 926 927
	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 */
928 929 930

	/* a threshold to reclaim prefree segments */
	unsigned int rec_prefree_segments;
931

J
Jaegeuk Kim 已提交
932 933 934
	/* for batched trimming */
	unsigned int trim_sections;		/* # of sections to trim */

935 936
	struct list_head sit_entry_set;	/* sit entry set list */

937 938
	unsigned int ipu_policy;	/* in-place-update policy */
	unsigned int min_ipu_util;	/* in-place-update threshold */
939
	unsigned int min_fsync_blocks;	/* threshold for fsync */
940
	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
941
	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
C
Chao Yu 已提交
942
	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
943 944

	/* for flush command control */
945
	struct flush_cmd_control *fcc_info;
946

947 948
	/* for discard command control */
	struct discard_cmd_control *dcc_info;
949 950 951 952 953 954 955 956 957 958 959
};

/*
 * 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.
 */
960
#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
961 962
enum count_type {
	F2FS_DIRTY_DENTS,
963
	F2FS_DIRTY_DATA,
964
	F2FS_DIRTY_QDATA,
965 966
	F2FS_DIRTY_NODES,
	F2FS_DIRTY_META,
967
	F2FS_INMEM_PAGES,
968
	F2FS_DIRTY_IMETA,
969 970
	F2FS_WB_CP_DATA,
	F2FS_WB_DATA,
971 972 973
	F2FS_RD_DATA,
	F2FS_RD_NODE,
	F2FS_RD_META,
C
Chao Yu 已提交
974 975
	F2FS_DIO_WRITE,
	F2FS_DIO_READ,
976 977 978 979
	NR_COUNT_TYPE,
};

/*
A
arter97 已提交
980
 * The below are the page types of bios used in submit_bio().
981 982 983 984 985 986 987 988 989
 * 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.
 */
990
#define PAGE_TYPE_OF_BIO(type)	((type) > META ? META : (type))
991 992 993 994 995 996
enum page_type {
	DATA,
	NODE,
	META,
	NR_PAGE_TYPE,
	META_FLUSH,
997 998
	INMEM,		/* the below types are used by tracepoints only. */
	INMEM_DROP,
999
	INMEM_INVALIDATE,
1000
	INMEM_REVOKE,
1001 1002
	IPU,
	OPU,
1003 1004
};

J
Jaegeuk Kim 已提交
1005 1006 1007 1008 1009 1010 1011
enum temp_type {
	HOT = 0,	/* must be zero for meta bio */
	WARM,
	COLD,
	NR_TEMP_TYPE,
};

1012 1013 1014 1015 1016 1017
enum need_lock_type {
	LOCK_REQ = 0,
	LOCK_DONE,
	LOCK_RETRY,
};

C
Chao Yu 已提交
1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
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,
1028
	CP_RECOVER_DIR,
C
Chao Yu 已提交
1029 1030
};

C
Chao Yu 已提交
1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
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
1048
struct f2fs_io_info {
1049
	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
C
Chao Yu 已提交
1050
	nid_t ino;		/* inode number */
1051
	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
J
Jaegeuk Kim 已提交
1052
	enum temp_type temp;	/* contains HOT/WARM/COLD */
M
Mike Christie 已提交
1053
	int op;			/* contains REQ_OP_ */
1054
	int op_flags;		/* req_flag_bits */
1055
	block_t new_blkaddr;	/* new block address to be written */
1056
	block_t old_blkaddr;	/* old block address before Cow */
1057
	struct page *page;	/* page to be written */
1058
	struct page *encrypted_page;	/* encrypted page */
1059
	struct list_head list;		/* serialize IOs */
1060
	bool submitted;		/* indicate IO submission */
1061
	int need_lock;		/* indicate we need to lock cp_rwsem */
1062
	bool in_list;		/* indicate fio is in io_list */
C
Chao Yu 已提交
1063
	bool is_por;		/* indicate IO is from recovery or not */
1064
	bool retry;		/* need to reallocate block address */
C
Chao Yu 已提交
1065
	enum iostat_type io_type;	/* io type */
1066
	struct writeback_control *io_wbc; /* writeback control */
C
Chao Yu 已提交
1067 1068
	struct bio **bio;		/* bio for ipu */
	sector_t *last_block;		/* last block number in bio */
1069
	unsigned char version;		/* version of the node */
J
Jaegeuk Kim 已提交
1070 1071
};

C
Chao Yu 已提交
1072 1073 1074 1075 1076
struct bio_entry {
	struct bio *bio;
	struct list_head list;
};

1077
#define is_read_io(rw) ((rw) == READ)
1078
struct f2fs_bio_info {
J
Jaegeuk Kim 已提交
1079
	struct f2fs_sb_info *sbi;	/* f2fs superblock */
1080 1081
	struct bio *bio;		/* bios to merge */
	sector_t last_block_in_bio;	/* last block number */
J
Jaegeuk Kim 已提交
1082
	struct f2fs_io_info fio;	/* store buffered io info. */
1083
	struct rw_semaphore io_rwsem;	/* blocking op for bio */
1084 1085
	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
	struct list_head io_list;	/* track fios */
C
Chao Yu 已提交
1086 1087
	struct list_head bio_list;	/* bio entry list head */
	struct rw_semaphore bio_list_lock;	/* lock to protect bio entry list */
1088 1089
};

J
Jaegeuk Kim 已提交
1090 1091 1092 1093 1094 1095 1096 1097 1098
#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
1099 1100
	unsigned int nr_blkz;		/* Total number of zones */
	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
J
Jaegeuk Kim 已提交
1101 1102 1103
#endif
};

1104 1105 1106
enum inode_type {
	DIR_INODE,			/* for dirty dir inode */
	FILE_INODE,			/* for dirty regular/symlink inode */
1107
	DIRTY_META,			/* for all dirtied inode metadata */
J
Jaegeuk Kim 已提交
1108
	ATOMIC_FILE,			/* for all atomic files */
1109 1110 1111
	NR_INODE_TYPE,
};

1112 1113 1114 1115 1116 1117 1118 1119
/* 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 */
};

1120 1121 1122 1123 1124 1125
/* 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 */
1126
	SBI_NEED_SB_WRITE,			/* need to recover superblock */
1127
	SBI_NEED_CP,				/* need to checkpoint */
1128
	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
1129
	SBI_IS_RECOVERED,			/* recovered orphan/data */
D
Daniel Rosenberg 已提交
1130
	SBI_CP_DISABLED,			/* CP was disabled last mount */
1131
	SBI_CP_DISABLED_QUICK,			/* CP was disabled quickly */
1132 1133 1134
	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 */
1135
	SBI_IS_RESIZEFS,			/* resizefs is in process */
1136 1137
};

1138 1139
enum {
	CP_TIME,
1140
	REQ_TIME,
1141 1142
	DISCARD_TIME,
	GC_TIME,
D
Daniel Rosenberg 已提交
1143
	DISABLE_TIME,
1144
	UMOUNT_DISCARD_TIMEOUT,
1145 1146 1147
	MAX_TIME,
};

1148 1149 1150 1151 1152 1153 1154
enum {
	GC_NORMAL,
	GC_IDLE_CB,
	GC_IDLE_GREEDY,
	GC_URGENT,
};

1155 1156 1157
enum {
	WHINT_MODE_OFF,		/* not pass down write hints */
	WHINT_MODE_USER,	/* try to pass down hints given by users */
1158
	WHINT_MODE_FS,		/* pass down hints with F2FS policy */
1159 1160
};

1161 1162 1163 1164 1165
enum {
	ALLOC_MODE_DEFAULT,	/* stay default */
	ALLOC_MODE_REUSE,	/* reuse segments as much as possible */
};

1166 1167 1168
enum fsync_mode {
	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
1169
	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
1170 1171
};

1172
#ifdef CONFIG_FS_ENCRYPTION
1173 1174 1175 1176 1177 1178
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
			(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif

1179 1180
struct f2fs_sb_info {
	struct super_block *sb;			/* pointer to VFS super block */
1181
	struct proc_dir_entry *s_proc;		/* proc entry */
1182
	struct f2fs_super_block *raw_super;	/* raw super block pointer */
1183
	struct rw_semaphore sb_lock;		/* lock for raw super block */
1184
	int valid_super_block;			/* valid super block no */
1185
	unsigned long s_flag;				/* flags for sbi */
1186
	struct mutex writepages;		/* mutex for writepages() */
1187 1188 1189 1190
#ifdef CONFIG_UNICODE
	struct unicode_map *s_encoding;
	__u16 s_encoding_flags;
#endif
1191

1192 1193 1194 1195 1196
#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

1197 1198 1199 1200 1201 1202
	/* 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 */
1203 1204

	/* for bio operations */
J
Jaegeuk Kim 已提交
1205
	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
1206 1207
	/* keep migration IO order for LFS mode */
	struct rw_semaphore io_order_lock;
1208
	mempool_t *write_io_dummy;		/* Dummy pages */
1209 1210 1211

	/* for checkpoint */
	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
1212
	int cur_cp_pack;			/* remain current cp pack */
1213
	spinlock_t cp_lock;			/* for flag in ckpt */
1214
	struct inode *meta_inode;		/* cache meta blocks */
1215
	struct mutex cp_mutex;			/* checkpoint procedure lock */
1216
	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
1217
	struct rw_semaphore node_write;		/* locking node writes */
1218
	struct rw_semaphore node_change;	/* locking node change */
1219
	wait_queue_head_t cp_wait;
1220 1221
	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
	long interval_time[MAX_TIME];		/* to store thresholds */
1222

1223
	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
J
Jaegeuk Kim 已提交
1224

1225 1226 1227 1228 1229
	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
1230
	/* for orphan inode, use 0'th array */
1231
	unsigned int max_orphans;		/* max orphan inodes */
1232

1233 1234 1235
	/* 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 */
1236
	struct mutex flush_lock;		/* for flush exclusion */
1237

1238 1239
	/* for extent tree cache */
	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
1240
	struct mutex extent_tree_lock;	/* locking extent radix tree */
1241 1242
	struct list_head extent_list;		/* lru list for shrinker */
	spinlock_t extent_lock;			/* locking extent lru list */
1243
	atomic_t total_ext_tree;		/* extent tree count */
1244
	struct list_head zombie_list;		/* extent zombie tree list */
1245
	atomic_t total_zombie_tree;		/* extent zombie tree count */
1246 1247
	atomic_t total_ext_node;		/* extent info count */

A
arter97 已提交
1248
	/* basic filesystem units */
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259
	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 */
1260
	struct mutex resize_mutex;		/* for resize exclusion */
1261 1262
	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
1263
	loff_t max_file_blocks;			/* max block index of file */
1264
	int dir_level;				/* directory level */
1265
	int readdir_ra;				/* readahead inode in readdir */
1266 1267 1268

	block_t user_block_count;		/* # of user blocks */
	block_t total_valid_block_count;	/* # of valid blocks */
1269
	block_t discard_blks;			/* discard command candidats */
1270
	block_t last_valid_block_count;		/* for recovery */
1271
	block_t reserved_blocks;		/* configurable reserved blocks */
1272
	block_t current_reserved_blocks;	/* current reserved blocks */
1273

D
Daniel Rosenberg 已提交
1274 1275 1276
	/* Additional tracking for no checkpoint mode */
	block_t unusable_block_count;		/* # of blocks saved by last cp */

1277
	unsigned int nquota_files;		/* # of quota sysfile */
1278
	struct rw_semaphore quota_sem;		/* blocking cp for flags */
1279

1280
	/* # of pages, see count_type */
1281
	atomic_t nr_pages[NR_COUNT_TYPE];
1282 1283
	/* # of allocated blocks */
	struct percpu_counter alloc_valid_block_count;
1284

1285
	/* writeback control */
1286
	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
1287

1288 1289 1290
	/* valid inode count */
	struct percpu_counter total_valid_inode_count;

1291 1292 1293 1294 1295
	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 */
1296
	unsigned int cur_victim_sec;		/* current victim section num */
1297
	unsigned int gc_mode;			/* current GC state */
1298
	unsigned int next_victim_seg[2];	/* next segment in victim section */
1299
	/* for skip statistic */
1300
	unsigned int atomic_files;              /* # of opened atomic file */
1301
	unsigned long long skipped_atomic_files[2];	/* FG_GC and BG_GC */
1302
	unsigned long long skipped_gc_rwsem;		/* FG_GC only */
1303

1304 1305
	/* threshold for gc trials on pinned files */
	u64 gc_pin_file_threshold;
J
Jaegeuk Kim 已提交
1306
	struct rw_semaphore pin_sem;
1307

1308 1309
	/* maximum # of trials to find a victim segment for SSR and GC */
	unsigned int max_victim_search;
1310 1311
	/* migration granularity of garbage collection, unit: segment */
	unsigned int migration_granularity;
1312

1313 1314 1315 1316
	/*
	 * for stat information.
	 * one is for the LFS mode, and the other is for the SSR mode.
	 */
1317
#ifdef CONFIG_F2FS_STAT_FS
1318
	struct f2fs_stat_info *stat_info;	/* FS status information */
C
Chao Yu 已提交
1319
	atomic_t meta_count[META_MAX];		/* # of meta blocks */
1320 1321
	unsigned int segment_count[2];		/* # of allocated segments */
	unsigned int block_count[2];		/* # of allocated blocks */
1322
	atomic_t inplace_count;		/* # of inplace update */
1323 1324 1325 1326
	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
1327
	atomic_t inline_xattr;			/* # of inline_xattr inodes */
1328 1329
	atomic_t inline_inode;			/* # of inline_data inodes */
	atomic_t inline_dir;			/* # of inline_dentry inodes */
1330
	atomic_t aw_cnt;			/* # of atomic writes */
1331
	atomic_t vw_cnt;			/* # of volatile writes */
1332
	atomic_t max_aw_cnt;			/* max # of atomic writes */
1333
	atomic_t max_vw_cnt;			/* max # of volatile writes */
1334
	int bg_gc;				/* background gc calls */
1335 1336
	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
1337
	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
1338
#endif
1339
	spinlock_t stat_lock;			/* lock for stat operations */
1340

C
Chao Yu 已提交
1341 1342 1343 1344 1345
	/* For app/fs IO statistics */
	spinlock_t iostat_lock;
	unsigned long long write_iostat[NR_IO_TYPE];
	bool iostat_enable;

1346 1347 1348
	/* For sysfs suppport */
	struct kobject s_kobj;
	struct completion s_kobj_unregister;
1349 1350 1351

	/* For shrinker support */
	struct list_head s_list;
J
Jaegeuk Kim 已提交
1352 1353
	int s_ndevs;				/* number of devices */
	struct f2fs_dev_info *devs;		/* for device list */
1354 1355
	unsigned int dirty_device;		/* for checkpoint data flush */
	spinlock_t dev_lock;			/* protect dirty_device */
1356 1357
	struct mutex umount_mutex;
	unsigned int shrinker_run_no;
1358 1359 1360 1361

	/* For write statistics */
	u64 sectors_written_start;
	u64 kbytes_written;
K
Keith Mok 已提交
1362 1363 1364

	/* Reference to checksum algorithm driver via cryptoapi */
	struct crypto_shash *s_chksum_driver;
1365

C
Chao Yu 已提交
1366 1367
	/* Precomputed FS UUID checksum for seeding other checksums */
	__u32 s_chksum_seed;
1368 1369
};

C
Chao Yu 已提交
1370 1371 1372 1373 1374 1375 1376
struct f2fs_private_dio {
	struct inode *inode;
	void *orig_private;
	bio_end_io_t *orig_end_io;
	bool write;
};

1377
#ifdef CONFIG_F2FS_FAULT_INJECTION
1378 1379 1380 1381
#define f2fs_show_injection_info(sbi, type)					\
	printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n",	\
		KERN_INFO, sbi->sb->s_id,				\
		f2fs_fault_name[type],					\
1382
		__func__, __builtin_return_address(0))
1383 1384
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
1385
	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399

	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;
}
1400
#else
1401
#define f2fs_show_injection_info(sbi, type) do { } while (0)
1402 1403 1404 1405
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
	return false;
}
1406 1407
#endif

1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418
/*
 * 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;
}

1419 1420 1421 1422
/* 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)						 \
1423
(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
1424
		(s)->sectors_written_start) >> 1)
1425

1426 1427
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
1428 1429 1430 1431 1432 1433 1434 1435 1436
	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;
	}
1437 1438 1439 1440
}

static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
A
Arnd Bergmann 已提交
1441
	unsigned long interval = sbi->interval_time[type] * HZ;
1442 1443 1444 1445

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

1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459
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;
}

1460 1461 1462
/*
 * Inline functions
 */
C
Chao Yu 已提交
1463
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
C
Chao Yu 已提交
1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482
			      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
1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500
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);
}

1501 1502 1503 1504 1505 1506 1507 1508 1509 1510
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;
}

1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522
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
1523
	return F2FS_M_SB(page_file_mapping(page));
1524 1525
}

1526 1527 1528 1529 1530 1531 1532 1533 1534 1535
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);
}

1536 1537 1538 1539 1540
static inline struct f2fs_node *F2FS_NODE(struct page *page)
{
	return (struct f2fs_node *)page_address(page);
}

1541 1542 1543 1544 1545
static inline struct f2fs_inode *F2FS_INODE(struct page *page)
{
	return &((struct f2fs_node *)page_address(page))->i;
}

1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570
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
1571 1572 1573 1574 1575
static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->meta_inode->i_mapping;
}

1576 1577 1578 1579 1580
static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
{
	return sbi->node_inode->i_mapping;
}

1581 1582
static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
1583
	return test_bit(type, &sbi->s_flag);
1584 1585 1586
}

static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1587
{
1588
	set_bit(type, &sbi->s_flag);
1589 1590
}

1591
static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1592
{
1593
	clear_bit(type, &sbi->s_flag);
1594 1595
}

1596 1597 1598 1599 1600
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
1601 1602 1603 1604 1605 1606 1607
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;
}

1608 1609 1610 1611 1612 1613
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)));
}

1614
static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1615 1616
{
	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1617

1618 1619 1620
	return ckpt_flags & f;
}

1621
static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1622
{
1623 1624 1625 1626 1627 1628 1629 1630
	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);
1631 1632 1633 1634
	ckpt_flags |= f;
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1635
static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1636
{
1637 1638 1639
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1640
	__set_ckpt_flags(F2FS_CKPT(sbi), f);
1641
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1642 1643 1644 1645 1646 1647 1648
}

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);
1649 1650 1651 1652
	ckpt_flags &= (~f);
	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}

1653 1654
static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
1655 1656 1657
	unsigned long flags;

	spin_lock_irqsave(&sbi->cp_lock, flags);
1658
	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
1659
	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1660 1661
}

1662 1663
static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
1664
	unsigned long flags;
1665
	unsigned char *nat_bits;
1666

1667 1668 1669 1670 1671
	/*
	 * 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.
	 */
1672 1673

	if (lock)
1674
		spin_lock_irqsave(&sbi->cp_lock, flags);
1675
	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
1676
	nat_bits = NM_I(sbi)->nat_bits;
1677 1678
	NM_I(sbi)->nat_bits = NULL;
	if (lock)
1679
		spin_unlock_irqrestore(&sbi->cp_lock, flags);
1680 1681

	kvfree(nat_bits);
1682 1683 1684 1685 1686 1687 1688
}

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);

1689
	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
1690 1691
}

1692
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
1693
{
1694
	down_read(&sbi->cp_rwsem);
1695 1696
}

1697 1698 1699 1700 1701
static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
{
	return down_read_trylock(&sbi->cp_rwsem);
}

1702
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
1703
{
1704
	up_read(&sbi->cp_rwsem);
1705 1706
}

1707
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
1708
{
1709
	down_write(&sbi->cp_rwsem);
1710 1711
}

1712
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
1713
{
1714
	up_write(&sbi->cp_rwsem);
1715 1716
}

1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729
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)
{
1730
	return (reason & (CP_UMOUNT | CP_FASTBOOT));
1731 1732 1733 1734
}

static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
{
1735 1736
	return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
			is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
1737 1738
}

1739 1740 1741 1742 1743
/*
 * Check whether the inode has blocks or not
 */
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
1744 1745
	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;

1746
	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
1747 1748
}

1749 1750 1751 1752 1753
static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
	return ofs == XATTR_NODE_OFFSET;
}

1754
static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
1755
					struct inode *inode, bool cap)
1756
{
1757 1758
	if (!inode)
		return true;
1759 1760
	if (!test_opt(sbi, RESERVE_ROOT))
		return false;
1761 1762
	if (IS_NOQUOTA(inode))
		return true;
1763
	if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
1764
		return true;
1765 1766
	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
					in_group_p(F2FS_OPTION(sbi).s_resgid))
1767
		return true;
1768
	if (cap && capable(CAP_SYS_RESOURCE))
1769
		return true;
1770 1771 1772
	return false;
}

C
Chao Yu 已提交
1773 1774
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,
1775
				 struct inode *inode, blkcnt_t *count)
1776
{
C
Chao Yu 已提交
1777
	blkcnt_t diff = 0, release = 0;
1778
	block_t avail_user_block_count;
C
Chao Yu 已提交
1779 1780 1781 1782 1783
	int ret;

	ret = dquot_reserve_block(inode, *count);
	if (ret)
		return ret;
1784

1785
	if (time_to_inject(sbi, FAULT_BLOCK)) {
1786
		f2fs_show_injection_info(sbi, FAULT_BLOCK);
C
Chao Yu 已提交
1787
		release = *count;
1788
		goto release_quota;
1789
	}
1790

1791 1792 1793 1794 1795 1796
	/*
	 * 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));

1797 1798
	spin_lock(&sbi->stat_lock);
	sbi->total_valid_block_count += (block_t)(*count);
1799 1800
	avail_user_block_count = sbi->user_block_count -
					sbi->current_reserved_blocks;
1801

1802
	if (!__allow_reserved_blocks(sbi, inode, true))
1803
		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
1804 1805 1806 1807 1808 1809
	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;
	}
1810 1811
	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
		diff = sbi->total_valid_block_count - avail_user_block_count;
1812 1813
		if (diff > *count)
			diff = *count;
1814
		*count -= diff;
C
Chao Yu 已提交
1815
		release = diff;
1816
		sbi->total_valid_block_count -= diff;
1817 1818
		if (!*count) {
			spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
1819
			goto enospc;
1820
		}
1821 1822
	}
	spin_unlock(&sbi->stat_lock);
1823

1824 1825
	if (unlikely(release)) {
		percpu_counter_sub(&sbi->alloc_valid_block_count, release);
C
Chao Yu 已提交
1826
		dquot_release_reservation_block(inode, release);
1827
	}
C
Chao Yu 已提交
1828 1829 1830 1831
	f2fs_i_blocks_write(inode, *count, true, true);
	return 0;

enospc:
1832
	percpu_counter_sub(&sbi->alloc_valid_block_count, release);
1833
release_quota:
C
Chao Yu 已提交
1834 1835
	dquot_release_reservation_block(inode, release);
	return -ENOSPC;
1836 1837
}

1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851
__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__)

1852
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
1853
						struct inode *inode,
1854
						block_t count)
1855
{
1856 1857
	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;

1858
	spin_lock(&sbi->stat_lock);
1859
	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
1860
	sbi->total_valid_block_count -= (block_t)count;
1861 1862 1863 1864
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
					sbi->current_reserved_blocks + count);
1865
	spin_unlock(&sbi->stat_lock);
1866
	if (unlikely(inode->i_blocks < sectors)) {
1867 1868 1869 1870
		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);
1871 1872 1873
		set_sbi_flag(sbi, SBI_NEED_FSCK);
		return;
	}
C
Chao Yu 已提交
1874
	f2fs_i_blocks_write(inode, count, false, true);
1875 1876 1877 1878
}

static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1879
	atomic_inc(&sbi->nr_pages[count_type]);
1880

C
Chao Yu 已提交
1881 1882 1883 1884 1885 1886
	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);
1887 1888
}

1889
static inline void inode_inc_dirty_pages(struct inode *inode)
1890
{
1891
	atomic_inc(&F2FS_I(inode)->dirty_pages);
1892 1893
	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1894 1895
	if (IS_NOQUOTA(inode))
		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1896 1897 1898 1899
}

static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
{
1900
	atomic_dec(&sbi->nr_pages[count_type]);
1901 1902
}

1903
static inline void inode_dec_dirty_pages(struct inode *inode)
1904
{
1905 1906
	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
			!S_ISLNK(inode->i_mode))
1907 1908
		return;

1909
	atomic_dec(&F2FS_I(inode)->dirty_pages);
1910 1911
	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
1912 1913
	if (IS_NOQUOTA(inode))
		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
1914 1915
}

1916
static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
1917
{
1918
	return atomic_read(&sbi->nr_pages[count_type]);
1919 1920
}

1921
static inline int get_dirty_pages(struct inode *inode)
1922
{
1923
	return atomic_read(&F2FS_I(inode)->dirty_pages);
1924 1925
}

1926 1927
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
1928
	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
1929 1930 1931 1932
	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
						sbi->log_blocks_per_seg;

	return segs / sbi->segs_per_sec;
1933 1934
}

1935 1936
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
1937
	return sbi->total_valid_block_count;
1938 1939
}

1940 1941 1942 1943 1944
static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
{
	return sbi->discard_blks;
}

1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957
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
1958 1959 1960 1961 1962
static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
	return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

1963 1964 1965
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
1966 1967
	int offset;

C
Chao Yu 已提交
1968 1969 1970
	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
		offset = (flag == SIT_BITMAP) ?
			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
1971 1972 1973 1974 1975
		/*
		 * 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
1976 1977
	}

W
Wanpeng Li 已提交
1978
	if (__cp_payload(sbi) > 0) {
C
Changman Lee 已提交
1979 1980 1981
		if (flag == NAT_BITMAP)
			return &ckpt->sit_nat_version_bitmap;
		else
J
Jaegeuk Kim 已提交
1982
			return (unsigned char *)ckpt + F2FS_BLKSIZE;
C
Changman Lee 已提交
1983 1984
	} else {
		offset = (flag == NAT_BITMAP) ?
1985
			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
C
Changman Lee 已提交
1986 1987
		return &ckpt->sit_nat_version_bitmap + offset;
	}
1988 1989 1990 1991
}

static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
1992
	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
1993

1994
	if (sbi->cur_cp_pack == 2)
1995
		start_addr += sbi->blocks_per_seg;
1996 1997
	return start_addr;
}
1998

1999 2000 2001
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);
2002

2003 2004
	if (sbi->cur_cp_pack == 1)
		start_addr += sbi->blocks_per_seg;
2005 2006 2007
	return start_addr;
}

2008 2009 2010 2011 2012
static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
{
	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
}

2013 2014 2015 2016 2017
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
2018
static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
2019
					struct inode *inode, bool is_inode)
2020 2021
{
	block_t	valid_block_count;
2022
	unsigned int valid_node_count, user_block_count;
2023
	int err;
C
Chao Yu 已提交
2024

2025 2026 2027 2028 2029 2030 2031 2032 2033 2034
	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
2035
	}
2036

2037
	if (time_to_inject(sbi, FAULT_BLOCK)) {
2038
		f2fs_show_injection_info(sbi, FAULT_BLOCK);
2039 2040 2041
		goto enospc;
	}

2042 2043
	spin_lock(&sbi->stat_lock);

2044 2045 2046
	valid_block_count = sbi->total_valid_block_count +
					sbi->current_reserved_blocks + 1;

2047
	if (!__allow_reserved_blocks(sbi, inode, false))
2048
		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
2049
	user_block_count = sbi->user_block_count;
D
Daniel Rosenberg 已提交
2050
	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
2051
		user_block_count -= sbi->unusable_block_count;
2052

2053
	if (unlikely(valid_block_count > user_block_count)) {
2054
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2055
		goto enospc;
2056 2057
	}

2058
	valid_node_count = sbi->total_valid_node_count + 1;
2059
	if (unlikely(valid_node_count > sbi->total_node_count)) {
2060
		spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2061
		goto enospc;
2062 2063
	}

2064 2065
	sbi->total_valid_node_count++;
	sbi->total_valid_block_count++;
2066 2067
	spin_unlock(&sbi->stat_lock);

2068 2069 2070 2071
	if (inode) {
		if (is_inode)
			f2fs_mark_inode_dirty_sync(inode, true);
		else
C
Chao Yu 已提交
2072
			f2fs_i_blocks_write(inode, 1, true, true);
2073
	}
2074

2075
	percpu_counter_inc(&sbi->alloc_valid_block_count);
C
Chao Yu 已提交
2076 2077 2078
	return 0;

enospc:
2079 2080 2081 2082
	if (is_inode) {
		if (inode)
			dquot_free_inode(inode);
	} else {
C
Chao Yu 已提交
2083
		dquot_release_reservation_block(inode, 1);
2084
	}
C
Chao Yu 已提交
2085
	return -ENOSPC;
2086 2087 2088
}

static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
2089
					struct inode *inode, bool is_inode)
2090 2091 2092
{
	spin_lock(&sbi->stat_lock);

2093 2094
	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
2095

2096 2097
	sbi->total_valid_node_count--;
	sbi->total_valid_block_count--;
2098 2099 2100
	if (sbi->reserved_blocks &&
		sbi->current_reserved_blocks < sbi->reserved_blocks)
		sbi->current_reserved_blocks++;
2101 2102

	spin_unlock(&sbi->stat_lock);
C
Chao Yu 已提交
2103

2104
	if (is_inode) {
2105
		dquot_free_inode(inode);
2106 2107
	} else {
		if (unlikely(inode->i_blocks == 0)) {
2108 2109 2110
			f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu",
				  inode->i_ino,
				  (unsigned long long)inode->i_blocks);
2111 2112 2113
			set_sbi_flag(sbi, SBI_NEED_FSCK);
			return;
		}
C
Chao Yu 已提交
2114
		f2fs_i_blocks_write(inode, 1, false, true);
2115
	}
2116 2117 2118 2119
}

static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
{
2120
	return sbi->total_valid_node_count;
2121 2122 2123 2124
}

static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
2125
	percpu_counter_inc(&sbi->total_valid_inode_count);
2126 2127
}

2128
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
2129
{
2130
	percpu_counter_dec(&sbi->total_valid_inode_count);
2131 2132
}

2133
static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
2134
{
2135
	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
2136 2137
}

2138 2139 2140
static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
						pgoff_t index, bool for_write)
{
2141
	struct page *page;
2142

2143 2144 2145 2146 2147 2148 2149 2150
	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;
2151

2152
		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
2153 2154
			f2fs_show_injection_info(F2FS_M_SB(mapping),
							FAULT_PAGE_ALLOC);
2155 2156
			return NULL;
		}
2157
	}
2158

2159 2160 2161 2162 2163
	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
2164 2165 2166 2167 2168
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)) {
2169
		f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
C
Chao Yu 已提交
2170 2171
		return NULL;
	}
2172

C
Chao Yu 已提交
2173 2174 2175
	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}

2176 2177 2178 2179 2180 2181 2182 2183 2184 2185
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);
}

2186 2187
static inline void f2fs_put_page(struct page *page, int unlock)
{
2188
	if (!page)
2189 2190 2191
		return;

	if (unlock) {
2192
		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
2193 2194
		unlock_page(page);
	}
2195
	put_page(page);
2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208
}

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,
2209
					size_t size)
2210
{
2211
	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
2212 2213
}

2214 2215 2216 2217 2218
static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
						gfp_t flags)
{
	void *entry;

2219 2220 2221
	entry = kmem_cache_alloc(cachep, flags);
	if (!entry)
		entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
2222 2223 2224
	return entry;
}

2225 2226
static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
						int npages, bool no_fail)
J
Jaegeuk Kim 已提交
2227 2228 2229
{
	struct bio *bio;

2230 2231 2232 2233 2234 2235 2236 2237
	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)) {
2238
		f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
2239 2240
		return NULL;
	}
2241

2242
	return bio_alloc(GFP_KERNEL, npages);
J
Jaegeuk Kim 已提交
2243 2244
}

2245 2246
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
2247 2248 2249
	if (sbi->gc_mode == GC_URGENT)
		return true;

2250 2251
	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) ||
2252 2253
		get_pages(sbi, F2FS_WB_CP_DATA) ||
		get_pages(sbi, F2FS_DIO_READ) ||
2254
		get_pages(sbi, F2FS_DIO_WRITE))
2255
		return false;
2256

2257
	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
2258 2259 2260 2261 2262 2263 2264
			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;

2265 2266 2267
	return f2fs_time_over(sbi, type);
}

2268 2269 2270 2271 2272 2273 2274
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();
}

2275 2276 2277 2278
#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)

static inline bool IS_INODE(struct page *page)
{
2279
	struct f2fs_node *p = F2FS_NODE(page);
2280

2281 2282 2283
	return RAW_IS_INODE(p);
}

2284 2285 2286 2287 2288 2289
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;
}

2290 2291 2292 2293 2294
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}

2295 2296 2297
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)
2298 2299 2300
{
	struct f2fs_node *raw_node;
	__le32 *addr_array;
2301 2302
	int base = 0;
	bool is_inode = IS_INODE(node_page);
2303

2304
	raw_node = F2FS_NODE(node_page);
2305 2306

	/* from GC path only */
2307 2308
	if (is_inode) {
		if (!inode)
2309
			base = offset_in_addr(&raw_node->i);
2310 2311
		else if (f2fs_has_extra_attr(inode))
			base = get_extra_isize(inode);
2312 2313
	}

2314
	addr_array = blkaddr_in_node(raw_node);
2315
	return le32_to_cpu(addr_array[base + offset]);
2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326
}

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

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

2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344
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;
}

2345
static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356
{
	int mask;
	int ret;

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

2357
static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368
{
	int mask;
	int ret;

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

2369 2370 2371 2372 2373 2374 2375 2376 2377
static inline void f2fs_change_bit(unsigned int nr, char *addr)
{
	int mask;

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

2378
/*
2379
 * On-disk inode flags (f2fs_inode::i_flags)
2380 2381 2382 2383 2384 2385 2386 2387 2388
 */
#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 */
2389
#define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
2390 2391

/* Flags that should be inherited by new inodes from their parent. */
2392
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
2393 2394
			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
			   F2FS_CASEFOLD_FL)
2395 2396

/* Flags that are appropriate for regular files (all but dir-specific ones). */
2397 2398
#define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
				F2FS_CASEFOLD_FL))
2399 2400 2401

/* 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
2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412

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;
}

2413 2414 2415
/* used for f2fs_inode_info->flags */
enum {
	FI_NEW_INODE,		/* indicate newly allocated inode */
2416
	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
2417
	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
2418
	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
2419 2420 2421
	FI_INC_LINK,		/* need to increment i_nlink */
	FI_ACL_MODE,		/* indicate acl mode */
	FI_NO_ALLOC,		/* should not allocate any blocks */
2422
	FI_FREE_NID,		/* free allocated nide */
2423
	FI_NO_EXTENT,		/* not to use the extent cache */
J
Jaegeuk Kim 已提交
2424
	FI_INLINE_XATTR,	/* used for inline xattr */
2425
	FI_INLINE_DATA,		/* used for inline data*/
2426
	FI_INLINE_DENTRY,	/* used for inline dentry */
2427 2428
	FI_APPEND_WRITE,	/* inode has appended data */
	FI_UPDATE_WRITE,	/* inode has in-place-update data */
J
Jaegeuk Kim 已提交
2429 2430
	FI_NEED_IPU,		/* used for ipu per file */
	FI_ATOMIC_FILE,		/* indicate atomic file */
C
Chao Yu 已提交
2431
	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
2432
	FI_VOLATILE_FILE,	/* indicate volatile file */
2433
	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
2434
	FI_DROP_CACHE,		/* drop dirty page cache */
2435
	FI_DATA_EXIST,		/* indicate data exists */
2436
	FI_INLINE_DOTS,		/* indicate inline dot dentries */
C
Chao Yu 已提交
2437
	FI_DO_DEFRAG,		/* indicate defragment is running */
2438
	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
2439
	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
2440
	FI_HOT_DATA,		/* indicate file is hot */
2441
	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
C
Chao Yu 已提交
2442
	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
2443
	FI_PIN_FILE,		/* indicate file should not be gced */
2444
	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
E
Eric Biggers 已提交
2445
	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
2446 2447
};

2448 2449 2450 2451 2452 2453 2454
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:
2455
	case FI_NEW_INODE:
2456 2457
		if (set)
			return;
2458
		/* fall through */
2459 2460
	case FI_DATA_EXIST:
	case FI_INLINE_DOTS:
2461
	case FI_PIN_FILE:
2462
		f2fs_mark_inode_dirty_sync(inode, true);
2463 2464 2465
	}
}

2466
static inline void set_inode_flag(struct inode *inode, int flag)
2467
{
2468 2469
	if (!test_bit(flag, &F2FS_I(inode)->flags))
		set_bit(flag, &F2FS_I(inode)->flags);
2470
	__mark_inode_dirty_flag(inode, flag, true);
2471 2472
}

2473
static inline int is_inode_flag_set(struct inode *inode, int flag)
2474
{
2475
	return test_bit(flag, &F2FS_I(inode)->flags);
2476 2477
}

2478
static inline void clear_inode_flag(struct inode *inode, int flag)
2479
{
2480 2481
	if (test_bit(flag, &F2FS_I(inode)->flags))
		clear_bit(flag, &F2FS_I(inode)->flags);
2482
	__mark_inode_dirty_flag(inode, flag, false);
2483 2484
}

E
Eric Biggers 已提交
2485 2486 2487 2488 2489 2490
static inline bool f2fs_verity_in_progress(struct inode *inode)
{
	return IS_ENABLED(CONFIG_FS_VERITY) &&
	       is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS);
}

2491
static inline void set_acl_inode(struct inode *inode, umode_t mode)
2492
{
2493 2494
	F2FS_I(inode)->i_acl_mode = mode;
	set_inode_flag(inode, FI_ACL_MODE);
2495
	f2fs_mark_inode_dirty_sync(inode, false);
2496 2497
}

2498
static inline void f2fs_i_links_write(struct inode *inode, bool inc)
2499
{
2500 2501 2502 2503
	if (inc)
		inc_nlink(inode);
	else
		drop_nlink(inode);
2504
	f2fs_mark_inode_dirty_sync(inode, true);
2505 2506
}

2507
static inline void f2fs_i_blocks_write(struct inode *inode,
C
Chao Yu 已提交
2508
					block_t diff, bool add, bool claim)
2509
{
2510 2511 2512
	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
2513 2514 2515 2516 2517 2518 2519 2520 2521 2522
	/* 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);
	}

2523
	f2fs_mark_inode_dirty_sync(inode, true);
2524 2525
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2526 2527
}

2528 2529
static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
{
2530 2531 2532
	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);

2533 2534 2535 2536
	if (i_size_read(inode) == i_size)
		return;

	i_size_write(inode, i_size);
2537
	f2fs_mark_inode_dirty_sync(inode, true);
2538 2539
	if (clean || recover)
		set_inode_flag(inode, FI_AUTO_RECOVER);
2540 2541
}

2542
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
2543
{
2544
	F2FS_I(inode)->i_current_depth = depth;
2545
	f2fs_mark_inode_dirty_sync(inode, true);
2546 2547
}

2548 2549 2550
static inline void f2fs_i_gc_failures_write(struct inode *inode,
					unsigned int count)
{
2551
	F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
2552 2553 2554
	f2fs_mark_inode_dirty_sync(inode, true);
}

2555
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
J
Jaegeuk Kim 已提交
2556
{
2557
	F2FS_I(inode)->i_xattr_nid = xnid;
2558
	f2fs_mark_inode_dirty_sync(inode, true);
2559 2560 2561 2562 2563
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
	F2FS_I(inode)->i_pino = pino;
2564
	f2fs_mark_inode_dirty_sync(inode, true);
2565 2566
}

2567
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2568
{
2569 2570
	struct f2fs_inode_info *fi = F2FS_I(inode);

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

2587
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
J
Jaegeuk Kim 已提交
2588 2589 2590
{
	ri->i_inline = 0;

2591
	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
J
Jaegeuk Kim 已提交
2592
		ri->i_inline |= F2FS_INLINE_XATTR;
2593
	if (is_inode_flag_set(inode, FI_INLINE_DATA))
2594
		ri->i_inline |= F2FS_INLINE_DATA;
2595
	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
2596
		ri->i_inline |= F2FS_INLINE_DENTRY;
2597
	if (is_inode_flag_set(inode, FI_DATA_EXIST))
2598
		ri->i_inline |= F2FS_DATA_EXIST;
2599
	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
2600
		ri->i_inline |= F2FS_INLINE_DOTS;
2601 2602
	if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
		ri->i_inline |= F2FS_EXTRA_ATTR;
2603 2604
	if (is_inode_flag_set(inode, FI_PIN_FILE))
		ri->i_inline |= F2FS_PIN_FILE;
2605 2606 2607 2608 2609
}

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
2610 2611
}

2612 2613
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
2614
	return is_inode_flag_set(inode, FI_INLINE_XATTR);
2615 2616
}

2617
static inline unsigned int addrs_per_inode(struct inode *inode)
2618
{
2619 2620 2621 2622 2623 2624 2625 2626
	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);
2627 2628
}

C
Chao Yu 已提交
2629
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
J
Jaegeuk Kim 已提交
2630
{
2631
	struct f2fs_inode *ri = F2FS_INODE(page);
2632

J
Jaegeuk Kim 已提交
2633
	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
2634
					get_inline_xattr_addrs(inode)]);
J
Jaegeuk Kim 已提交
2635 2636 2637 2638
}

static inline int inline_xattr_size(struct inode *inode)
{
2639 2640 2641
	if (f2fs_has_inline_xattr(inode))
		return get_inline_xattr_addrs(inode) * sizeof(__le32);
	return 0;
J
Jaegeuk Kim 已提交
2642 2643
}

2644 2645
static inline int f2fs_has_inline_data(struct inode *inode)
{
2646
	return is_inode_flag_set(inode, FI_INLINE_DATA);
2647 2648
}

2649 2650
static inline int f2fs_exist_data(struct inode *inode)
{
2651
	return is_inode_flag_set(inode, FI_DATA_EXIST);
2652 2653
}

2654 2655
static inline int f2fs_has_inline_dots(struct inode *inode)
{
2656
	return is_inode_flag_set(inode, FI_INLINE_DOTS);
2657 2658
}

2659 2660 2661 2662 2663
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
2664 2665
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
2666
	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
J
Jaegeuk Kim 已提交
2667 2668
}

C
Chao Yu 已提交
2669 2670 2671 2672 2673
static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
{
	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}

2674 2675
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
2676
	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
2677 2678
}

2679 2680
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
2681
	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
2682 2683
}

2684 2685
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
2686
	return is_inode_flag_set(inode, FI_DROP_CACHE);
2687 2688
}

C
Chao Yu 已提交
2689
static inline void *inline_data_addr(struct inode *inode, struct page *page)
2690
{
2691
	struct f2fs_inode *ri = F2FS_INODE(page);
2692
	int extra_size = get_extra_isize(inode);
2693

2694
	return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
2695 2696
}

2697 2698
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
2699
	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
2700 2701
}

2702 2703 2704 2705 2706 2707 2708 2709
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;
2710
	f2fs_mark_inode_dirty_sync(inode, true);
2711 2712 2713 2714 2715
}

static inline void clear_file(struct inode *inode, int type)
{
	F2FS_I(inode)->i_advise &= ~type;
2716
	f2fs_mark_inode_dirty_sync(inode, true);
2717 2718
}

2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732
static inline bool f2fs_is_time_consistent(struct inode *inode)
{
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
		return false;
	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
						&F2FS_I(inode)->i_crtime))
		return false;
	return true;
}

2733 2734
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
2735 2736
	bool ret;

2737 2738 2739 2740 2741 2742 2743 2744 2745 2746
	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) ||
2747
			i_size_read(inode) & ~PAGE_MASK)
2748
		return false;
2749

2750
	if (!f2fs_is_time_consistent(inode))
2751 2752
		return false;

2753 2754 2755 2756 2757
	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;
2758 2759
}

2760
static inline bool f2fs_readonly(struct super_block *sb)
J
Jaegeuk Kim 已提交
2761
{
2762
	return sb_rdonly(sb);
J
Jaegeuk Kim 已提交
2763 2764
}

2765 2766
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
2767
	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
2768 2769
}

2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780
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
2781 2782
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
2783 2784 2785
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

	if (!test_opt(sbi, EXTENT_CACHE) ||
2786
			is_inode_flag_set(inode, FI_NO_EXTENT))
J
Jaegeuk Kim 已提交
2787 2788
		return false;

2789 2790 2791 2792 2793 2794 2795
	/*
	 * 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
2796
	return S_ISREG(inode->i_mode);
J
Jaegeuk Kim 已提交
2797 2798
}

2799 2800
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
2801
{
2802 2803
	void *ret;

2804
	if (time_to_inject(sbi, FAULT_KMALLOC)) {
2805
		f2fs_show_injection_info(sbi, FAULT_KMALLOC);
J
Jaegeuk Kim 已提交
2806
		return NULL;
2807
	}
2808

2809 2810 2811 2812 2813
	ret = kmalloc(size, flags);
	if (ret)
		return ret;

	return kvmalloc(size, flags);
2814 2815
}

C
Chao Yu 已提交
2816 2817 2818 2819 2820 2821
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
2822 2823 2824 2825
static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	if (time_to_inject(sbi, FAULT_KVMALLOC)) {
2826
		f2fs_show_injection_info(sbi, FAULT_KVMALLOC);
C
Chao Yu 已提交
2827 2828
		return NULL;
	}
2829

C
Chao Yu 已提交
2830 2831 2832 2833 2834 2835 2836 2837 2838
	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);
}

2839
static inline int get_extra_isize(struct inode *inode)
C
Chao Yu 已提交
2840
{
2841
	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
C
Chao Yu 已提交
2842 2843
}

C
Chao Yu 已提交
2844 2845 2846 2847 2848
static inline int get_inline_xattr_addrs(struct inode *inode)
{
	return F2FS_I(inode)->i_inline_xattr_size;
}

C
Chao Yu 已提交
2849
#define f2fs_get_inode_mode(i) \
2850
	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
2851 2852
	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))

2853 2854 2855 2856
#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
2857 2858
#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
2859
		((offsetof(typeof(*(f2fs_inode)), field) +	\
C
Chao Yu 已提交
2860
		sizeof((f2fs_inode)->field))			\
S
Sheng Yong 已提交
2861
		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
C
Chao Yu 已提交
2862

C
Chao Yu 已提交
2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887
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);
}

2888 2889
#define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)

C
Chao Yu 已提交
2890
#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
2891

2892 2893 2894 2895 2896 2897
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)) {
2898 2899
		f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
			 blkaddr, type);
2900 2901 2902 2903 2904
		f2fs_bug_on(sbi, 1);
	}
}

static inline bool __is_valid_data_blkaddr(block_t blkaddr)
C
Chao Yu 已提交
2905 2906 2907 2908 2909 2910
{
	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
		return false;
	return true;
}

2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931
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);
}

2932 2933 2934
/*
 * file.c
 */
2935
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
C
Chao Yu 已提交
2936
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
2937
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
2938
int f2fs_truncate(struct inode *inode);
2939 2940
int f2fs_getattr(const struct path *path, struct kstat *stat,
			u32 request_mask, unsigned int flags);
2941
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
C
Chao Yu 已提交
2942 2943
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);
2944
int f2fs_precache_extents(struct inode *inode);
2945 2946
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);
2947
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
2948
int f2fs_pin_file_control(struct inode *inode, bool inc);
2949 2950 2951 2952

/*
 * inode.c
 */
2953
void f2fs_set_inode_flags(struct inode *inode);
C
Chao Yu 已提交
2954 2955
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);
2956 2957
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
2958 2959 2960
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);
2961 2962
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
C
Chao Yu 已提交
2963
void f2fs_handle_failed_inode(struct inode *inode);
2964 2965 2966 2967

/*
 * namei.c
 */
C
Chao Yu 已提交
2968
int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
C
Chao Yu 已提交
2969
							bool hot, bool set);
2970 2971
struct dentry *f2fs_get_parent(struct dentry *child);

2972 2973
extern int f2fs_ci_compare(const struct inode *parent,
			   const struct qstr *name,
2974 2975
			   const struct qstr *entry,
			   bool quick);
2976

2977 2978 2979
/*
 * dir.c
 */
C
Chao Yu 已提交
2980 2981
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
2982 2983 2984 2985
			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
2986
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
2987
			struct f2fs_dentry_ptr *d);
C
Chao Yu 已提交
2988
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
2989 2990
			const struct qstr *new_name,
			const struct qstr *orig_name, struct page *dpage);
C
Chao Yu 已提交
2991
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
2992
			unsigned int current_depth);
C
Chao Yu 已提交
2993
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009
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
3010
int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
3011
			struct inode *inode, nid_t ino, umode_t mode);
C
Chao Yu 已提交
3012
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
3013 3014 3015 3016 3017
			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);
3018

3019 3020
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
C
Chao Yu 已提交
3021
	return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
3022
				inode, inode->i_ino, inode->i_mode);
3023 3024
}

3025 3026 3027
/*
 * super.c
 */
3028 3029
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
J
Jaegeuk Kim 已提交
3030
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
3031
int f2fs_quota_sync(struct super_block *sb, int type);
C
Chao Yu 已提交
3032
void f2fs_quota_off_umount(struct super_block *sb);
3033 3034
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
3035
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
3036 3037 3038 3039

/*
 * hash.c
 */
3040 3041
f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
		const struct qstr *name_info, struct fscrypt_name *fname);
3042 3043 3044 3045 3046 3047 3048

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

C
Chao Yu 已提交
3049 3050
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);
3051 3052 3053 3054
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
3055 3056 3057
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);
3058
int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
C
Chao Yu 已提交
3059 3060 3061 3062 3063
						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);
3064 3065
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
					unsigned int seq_id);
C
Chao Yu 已提交
3066 3067 3068 3069 3070 3071
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);
3072
int f2fs_move_node_page(struct page *node_page, int gc_type);
C
Chao Yu 已提交
3073
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
3074 3075
			struct writeback_control *wbc, bool atomic,
			unsigned int *seq_id);
C
Chao Yu 已提交
3076 3077
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
			struct writeback_control *wbc,
C
Chao Yu 已提交
3078
			bool do_balance, enum iostat_type io_type);
3079
int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
C
Chao Yu 已提交
3080 3081 3082 3083 3084 3085 3086
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);
3087
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
3088
			unsigned int segno, struct f2fs_summary_block *sum);
3089
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
C
Chao Yu 已提交
3090 3091 3092 3093
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);
3094 3095 3096 3097

/*
 * segment.c
 */
C
Chao Yu 已提交
3098 3099 3100 3101 3102 3103
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);
3104 3105
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
3106
int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
C
Chao Yu 已提交
3107
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
3108
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3109 3110 3111 3112 3113
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);
3114
bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3115 3116
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
					struct cp_control *cpc);
D
Daniel Rosenberg 已提交
3117
void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
3118 3119
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
3120 3121
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
3122 3123
void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
					unsigned int start, unsigned int end);
J
Jaegeuk Kim 已提交
3124
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type);
3125
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
C
Chao Yu 已提交
3126 3127 3128 3129 3130 3131
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
3132
						enum iostat_type io_type);
C
Chao Yu 已提交
3133 3134 3135 3136 3137
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,
3138 3139 3140 3141 3142 3143
			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
3144
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
3145
			block_t old_blkaddr, block_t *new_blkaddr,
3146 3147
			struct f2fs_summary *sum, int type,
			struct f2fs_io_info *fio, bool add_list);
3148
void f2fs_wait_on_page_writeback(struct page *page,
3149
			enum page_type type, bool ordered, bool locked);
3150
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
3151 3152
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
								block_t len);
C
Chao Yu 已提交
3153 3154 3155
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,
3156
			unsigned int val, int alloc);
C
Chao Yu 已提交
3157
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
3158
int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3159 3160 3161 3162 3163 3164 3165
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);
3166 3167 3168 3169

/*
 * checkpoint.c
 */
3170
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
C
Chao Yu 已提交
3171 3172
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);
3173
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
C
Chao Yu 已提交
3174
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
3175 3176
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
					block_t blkaddr, int type);
C
Chao Yu 已提交
3177
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
3178
			int type, bool sync);
C
Chao Yu 已提交
3179 3180
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
3181
			long nr_to_write, enum iostat_type io_type);
C
Chao Yu 已提交
3182 3183 3184 3185 3186
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
3187
					unsigned int devidx, int type);
C
Chao Yu 已提交
3188
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
C
Chao Yu 已提交
3189
					unsigned int devidx, int type);
3190
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3191 3192 3193 3194 3195 3196 3197 3198 3199
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);
3200
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
C
Chao Yu 已提交
3201 3202 3203 3204
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);
3205 3206 3207 3208

/*
 * data.c
 */
3209 3210
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
C
Chao Yu 已提交
3211 3212
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
3213 3214
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,
3215 3216
				struct inode *inode, struct page *page,
				nid_t ino, enum page_type type);
C
Chao Yu 已提交
3217 3218
void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
					struct bio **bio, struct page *page);
3219
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
3220
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3221
int f2fs_merge_page_bio(struct f2fs_io_info *fio);
3222
void f2fs_submit_page_write(struct f2fs_io_info *fio);
3223 3224 3225
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
3226
void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
3227
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
C
Chao Yu 已提交
3228 3229
int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
3230 3231 3232
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
3233
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
3234
			int op_flags, bool for_write);
C
Chao Yu 已提交
3235 3236
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,
3237
			bool for_write);
C
Chao Yu 已提交
3238
struct page *f2fs_get_new_data_page(struct inode *inode,
3239
			struct page *ipage, pgoff_t index, bool new_i_size);
C
Chao Yu 已提交
3240
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
C
Chao Yu 已提交
3241
void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
3242 3243 3244 3245
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
3246 3247
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);
3248 3249 3250
void f2fs_invalidate_page(struct page *page, unsigned int offset,
			unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
3251
#ifdef CONFIG_MIGRATION
3252 3253
int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
			struct page *page, enum migrate_mode mode);
3254
#endif
H
Hyunchul Lee 已提交
3255
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
M
Matthew Wilcox 已提交
3256
void f2fs_clear_page_cache_dirty_tag(struct page *page);
3257 3258 3259 3260

/*
 * gc.c
 */
C
Chao Yu 已提交
3261 3262 3263
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);
3264 3265
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
			unsigned int segno);
C
Chao Yu 已提交
3266
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
3267
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
3268 3269 3270 3271

/*
 * recovery.c
 */
C
Chao Yu 已提交
3272 3273
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
3274 3275 3276 3277 3278 3279 3280 3281 3282 3283

/*
 * 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;
3284 3285
	unsigned long long hit_largest, hit_cached, hit_rbtree;
	unsigned long long hit_total, total_ext;
J
Jaegeuk Kim 已提交
3286
	int ext_tree, zombie_tree, ext_node;
3287 3288
	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
	int ndirty_data, ndirty_qdata;
3289
	int inmem_pages;
3290
	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
3291 3292
	int nats, dirty_nats, sits, dirty_sits;
	int free_nids, avail_nids, alloc_nids;
3293
	int total_count, utilization;
C
Chao Yu 已提交
3294
	int bg_gc, nr_wb_cp_data, nr_wb_data;
3295
	int nr_rd_data, nr_rd_node, nr_rd_meta;
C
Chao Yu 已提交
3296
	int nr_dio_read, nr_dio_write;
3297
	unsigned int io_skip_bggc, other_skip_bggc;
C
Chao Yu 已提交
3298 3299
	int nr_flushing, nr_flushed, flush_list_empty;
	int nr_discarding, nr_discarded;
C
Chao Yu 已提交
3300
	int nr_discard_cmd;
C
Chao Yu 已提交
3301
	unsigned int undiscard_blks;
3302
	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
3303
	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
3304
	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
3305 3306 3307 3308
	unsigned int bimodal, avg_vblocks;
	int util_free, util_valid, util_invalid;
	int rsvd_segs, overp_segs;
	int dirty_count, node_pages, meta_pages;
3309
	int prefree_count, call_count, cp_count, bg_cp_count;
3310
	int tot_segs, node_segs, data_segs, free_segs, free_secs;
3311
	int bg_node_segs, bg_data_segs;
3312
	int tot_blks, data_blks, node_blks;
3313
	int bg_data_blks, bg_node_blks;
3314
	unsigned long long skipped_atomic_files[2];
3315 3316 3317 3318
	int curseg[NR_CURSEG_TYPE];
	int cursec[NR_CURSEG_TYPE];
	int curzone[NR_CURSEG_TYPE];

C
Chao Yu 已提交
3319
	unsigned int meta_count[META_MAX];
3320 3321
	unsigned int segment_count[2];
	unsigned int block_count[2];
3322
	unsigned int inplace_count;
C
Chao Yu 已提交
3323
	unsigned long long base_mem, cache_mem, page_mem;
3324 3325
};

3326 3327
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
C
Chris Fries 已提交
3328
	return (struct f2fs_stat_info *)sbi->stat_info;
3329 3330
}

3331
#define stat_inc_cp_count(si)		((si)->cp_count++)
3332
#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
3333 3334
#define stat_inc_call_count(si)		((si)->call_count++)
#define stat_inc_bggc_count(sbi)	((sbi)->bg_gc++)
3335 3336
#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
3337 3338
#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
3339 3340 3341 3342
#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
3343 3344 3345 3346 3347 3348 3349 3350 3351 3352
#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)
3353 3354 3355
#define stat_inc_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3356
			(atomic_inc(&F2FS_I_SB(inode)->inline_inode));	\
3357 3358 3359 3360
	} while (0)
#define stat_dec_inline_inode(inode)					\
	do {								\
		if (f2fs_has_inline_data(inode))			\
3361
			(atomic_dec(&F2FS_I_SB(inode)->inline_inode));	\
3362
	} while (0)
3363 3364 3365
#define stat_inc_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3366
			(atomic_inc(&F2FS_I_SB(inode)->inline_dir));	\
3367 3368 3369 3370
	} while (0)
#define stat_dec_inline_dir(inode)					\
	do {								\
		if (f2fs_has_inline_dentry(inode))			\
3371
			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
3372
	} while (0)
C
Chao Yu 已提交
3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383
#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)
3384 3385 3386 3387
#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]++)
3388 3389
#define stat_inc_inplace_blocks(sbi)					\
		(atomic_inc(&(sbi)->inplace_count))
3390
#define stat_inc_atomic_write(inode)					\
3391
		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
3392
#define stat_dec_atomic_write(inode)					\
3393
		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
3394 3395 3396 3397 3398 3399 3400
#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)
3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411
#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)
3412
#define stat_inc_seg_count(sbi, type, gc_type)				\
3413
	do {								\
3414
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3415 3416
		si->tot_segs++;						\
		if ((type) == SUM_TYPE_DATA) {				\
3417
			si->data_segs++;				\
3418 3419
			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
		} else {						\
3420
			si->node_segs++;				\
3421 3422
			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
		}							\
3423 3424 3425
	} while (0)

#define stat_inc_tot_blk_count(si, blks)				\
3426
	((si)->tot_blks += (blks))
3427

3428
#define stat_inc_data_blk_count(sbi, blks, gc_type)			\
3429
	do {								\
3430
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3431 3432
		stat_inc_tot_blk_count(si, blks);			\
		si->data_blks += (blks);				\
3433
		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3434 3435
	} while (0)

3436
#define stat_inc_node_blk_count(sbi, blks, gc_type)			\
3437
	do {								\
3438
		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3439 3440
		stat_inc_tot_blk_count(si, blks);			\
		si->node_blks += (blks);				\
3441
		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3442 3443
	} while (0)

3444 3445
int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
3446
void __init f2fs_create_root_stats(void);
3447
void f2fs_destroy_root_stats(void);
3448
#else
3449 3450 3451 3452
#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)
3453 3454
#define stat_io_skip_bggc_count(sbi)			do { } while (0)
#define stat_other_skip_bggc_count(sbi)			do { } while (0)
3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472
#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
3473
#define stat_inc_meta_count(sbi, blkaddr)		do { } while (0)
3474 3475 3476 3477 3478 3479 3480
#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)
3481 3482 3483

static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
3484
static inline void __init f2fs_create_root_stats(void) { }
3485
static inline void f2fs_destroy_root_stats(void) { }
3486 3487 3488
#endif

extern const struct file_operations f2fs_dir_operations;
3489 3490 3491
#ifdef CONFIG_UNICODE
extern const struct dentry_operations f2fs_dentry_ops;
#endif
3492 3493 3494 3495 3496 3497 3498
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;
3499
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
3500
extern const struct inode_operations f2fs_special_inode_operations;
C
Chao Yu 已提交
3501
extern struct kmem_cache *f2fs_inode_entry_slab;
3502

3503 3504 3505
/*
 * inline.c
 */
3506 3507
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
C
Chao Yu 已提交
3508 3509 3510
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);
3511 3512 3513 3514
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
3515 3516
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
3517
			struct fscrypt_name *fname, struct page **res_page);
C
Chao Yu 已提交
3518
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
3519 3520 3521 3522
			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
3523 3524 3525
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
				struct page *page, struct inode *dir,
				struct inode *inode);
3526 3527 3528 3529 3530 3531
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);
3532

3533 3534 3535
/*
 * shrinker.c
 */
3536 3537 3538 3539 3540 3541
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);
3542

3543 3544 3545
/*
 * extent_cache.c
 */
C
Chao Yu 已提交
3546
struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
3547
				struct rb_entry *cached_re, unsigned int ofs);
C
Chao Yu 已提交
3548
struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3549 3550 3551 3552
				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,
3553 3554 3555
		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
3556
		bool force, bool *leftmost);
C
Chao Yu 已提交
3557
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
C
Chao Yu 已提交
3558
						struct rb_root_cached *root);
3559 3560 3561 3562 3563 3564 3565 3566
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
3567
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
3568
			pgoff_t fofs, block_t blkaddr, unsigned int len);
C
Chao Yu 已提交
3569 3570 3571
void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_extent_cache(void);
void f2fs_destroy_extent_cache(void);
3572

3573 3574 3575
/*
 * sysfs.c
 */
3576 3577 3578 3579
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);
3580

E
Eric Biggers 已提交
3581 3582 3583
/* verity.c */
extern const struct fsverity_operations f2fs_verityops;

3584 3585 3586
/*
 * crypto support
 */
3587 3588
static inline bool f2fs_encrypted_file(struct inode *inode)
{
3589
	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
3590 3591
}

3592 3593
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
3594
#ifdef CONFIG_FS_ENCRYPTION
3595
	file_set_encrypt(inode);
C
Chao Yu 已提交
3596
	f2fs_set_inode_flags(inode);
3597 3598 3599
#endif
}

3600 3601 3602 3603 3604
/*
 * 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)
3605
{
E
Eric Biggers 已提交
3606
	return f2fs_encrypted_file(inode) || fsverity_active(inode);
3607 3608
}

3609
#define F2FS_FEATURE_FUNCS(name, flagname) \
3610
static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
3611
{ \
3612
	return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
3613 3614
}

3615 3616 3617 3618 3619 3620 3621 3622
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);
3623
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
E
Eric Biggers 已提交
3624
F2FS_FEATURE_FUNCS(verity, VERITY);
3625
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
3626
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
C
Chao Yu 已提交
3627

3628
#ifdef CONFIG_BLK_DEV_ZONED
3629 3630
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
				    block_t blkaddr)
3631 3632 3633
{
	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;

3634
	return test_bit(zno, FDEV(devi).blkz_seq);
3635 3636 3637
}
#endif

3638
static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
3639
{
3640
	return f2fs_sb_has_blkzoned(sbi);
3641
}
3642

3643 3644 3645 3646 3647 3648
static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
{
	return blk_queue_discard(bdev_get_queue(bdev)) ||
	       bdev_is_zoned(bdev);
}

3649 3650
static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
{
3651 3652 3653 3654 3655 3656 3657 3658 3659
	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;
3660 3661 3662 3663 3664 3665
}

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);
3666 3667
}

3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681
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;
}


3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696
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;
	}
}

3697 3698
static inline bool f2fs_may_encrypt(struct inode *inode)
{
3699
#ifdef CONFIG_FS_ENCRYPTION
A
Al Viro 已提交
3700
	umode_t mode = inode->i_mode;
3701 3702 3703

	return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
#else
3704
	return false;
3705 3706 3707
#endif
}

3708 3709
static inline int block_unaligned_IO(struct inode *inode,
				struct kiocb *iocb, struct iov_iter *iter)
H
Hyunchul Lee 已提交
3710
{
3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736
	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;
3737
	if (f2fs_is_multi_device(sbi))
3738 3739 3740 3741 3742
		return true;
	/*
	 * for blkzoned device, fallback direct IO to buffered IO, so
	 * all IOs can be serialized by log-structured write.
	 */
3743
	if (f2fs_sb_has_blkzoned(sbi))
3744
		return true;
3745 3746 3747 3748 3749 3750
	if (test_opt(sbi, LFS) && (rw == WRITE)) {
		if (block_unaligned_IO(inode, iocb, iter))
			return true;
		if (F2FS_IO_ALIGNED(sbi))
			return true;
	}
J
Jaegeuk Kim 已提交
3751
	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
C
Chao Yu 已提交
3752
					!IS_SWAPFILE(inode))
D
Daniel Rosenberg 已提交
3753 3754
		return true;

3755
	return false;
H
Hyunchul Lee 已提交
3756 3757
}

3758
#ifdef CONFIG_F2FS_FAULT_INJECTION
C
Chao Yu 已提交
3759 3760
extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
							unsigned int type);
3761
#else
C
Chao Yu 已提交
3762
#define f2fs_build_fault_attr(sbi, rate, type)		do { } while (0)
3763 3764
#endif

3765 3766 3767
static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
{
#ifdef CONFIG_QUOTA
3768
	if (f2fs_sb_has_quota_ino(sbi))
3769 3770 3771 3772 3773 3774 3775 3776
		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
3777

3778 3779 3780
#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

3781
#endif /* _LINUX_F2FS_H */