xref: /kernel/linux/linux-5.10/fs/f2fs/f2fs.h (revision 8c2ecf20)
1/* SPDX-License-Identifier: GPL-2.0 */
2/*
3 * fs/f2fs/f2fs.h
4 *
5 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
6 *             http://www.samsung.com/
7 */
8#ifndef _LINUX_F2FS_H
9#define _LINUX_F2FS_H
10
11#include <linux/uio.h>
12#include <linux/types.h>
13#include <linux/page-flags.h>
14#include <linux/buffer_head.h>
15#include <linux/slab.h>
16#include <linux/crc32.h>
17#include <linux/magic.h>
18#include <linux/kobject.h>
19#include <linux/sched.h>
20#include <linux/cred.h>
21#include <linux/vmalloc.h>
22#include <linux/bio.h>
23#include <linux/blkdev.h>
24#include <linux/quotaops.h>
25#include <linux/part_stat.h>
26#include <crypto/hash.h>
27
28#include <linux/fscrypt.h>
29#include <linux/fsverity.h>
30
31#ifdef CONFIG_F2FS_CHECK_FS
32#define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
33#else
34#define f2fs_bug_on(sbi, condition)					\
35	do {								\
36		if (unlikely(condition)) {				\
37			WARN_ON(1);					\
38			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
39		}							\
40	} while (0)
41#endif
42
43enum {
44	FAULT_KMALLOC,
45	FAULT_KVMALLOC,
46	FAULT_PAGE_ALLOC,
47	FAULT_PAGE_GET,
48	FAULT_ALLOC_BIO,
49	FAULT_ALLOC_NID,
50	FAULT_ORPHAN,
51	FAULT_BLOCK,
52	FAULT_DIR_DEPTH,
53	FAULT_EVICT_INODE,
54	FAULT_TRUNCATE,
55	FAULT_READ_IO,
56	FAULT_CHECKPOINT,
57	FAULT_DISCARD,
58	FAULT_WRITE_IO,
59	FAULT_MAX,
60};
61
62#ifdef CONFIG_F2FS_FAULT_INJECTION
63#define F2FS_ALL_FAULT_TYPE		((1 << FAULT_MAX) - 1)
64
65struct f2fs_fault_info {
66	atomic_t inject_ops;
67	int inject_rate;
68	unsigned int inject_type;
69};
70
71extern const char *f2fs_fault_name[FAULT_MAX];
72#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
73
74/* maximum retry count for injected failure */
75#define DEFAULT_FAILURE_RETRY_COUNT		8
76#else
77#define DEFAULT_FAILURE_RETRY_COUNT		1
78#endif
79
80/*
81 * For mount options
82 */
83#define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000002
84#define F2FS_MOUNT_DISCARD		0x00000004
85#define F2FS_MOUNT_NOHEAP		0x00000008
86#define F2FS_MOUNT_XATTR_USER		0x00000010
87#define F2FS_MOUNT_POSIX_ACL		0x00000020
88#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
89#define F2FS_MOUNT_INLINE_XATTR		0x00000080
90#define F2FS_MOUNT_INLINE_DATA		0x00000100
91#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
92#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
93#define F2FS_MOUNT_NOBARRIER		0x00000800
94#define F2FS_MOUNT_FASTBOOT		0x00001000
95#define F2FS_MOUNT_EXTENT_CACHE		0x00002000
96#define F2FS_MOUNT_DATA_FLUSH		0x00008000
97#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
98#define F2FS_MOUNT_USRQUOTA		0x00080000
99#define F2FS_MOUNT_GRPQUOTA		0x00100000
100#define F2FS_MOUNT_PRJQUOTA		0x00200000
101#define F2FS_MOUNT_QUOTA		0x00400000
102#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
103#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
104#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
105#define F2FS_MOUNT_NORECOVERY		0x04000000
106#define F2FS_MOUNT_ATGC			0x08000000
107#define	F2FS_MOUNT_GC_MERGE		0x20000000
108
109#define F2FS_OPTION(sbi)	((sbi)->mount_opt)
110#define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
111#define set_opt(sbi, option)	(F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option)
112#define test_opt(sbi, option)	(F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option)
113
114#define ver_after(a, b)	(typecheck(unsigned long long, a) &&		\
115		typecheck(unsigned long long, b) &&			\
116		((long long)((a) - (b)) > 0))
117
118typedef u32 block_t;	/*
119			 * should not change u32, since it is the on-disk block
120			 * address format, __le32.
121			 */
122typedef u32 nid_t;
123
124#define COMPRESS_EXT_NUM		16
125
126struct f2fs_mount_info {
127	unsigned int opt;
128	int write_io_size_bits;		/* Write IO size bits */
129	block_t root_reserved_blocks;	/* root reserved blocks */
130	kuid_t s_resuid;		/* reserved blocks for uid */
131	kgid_t s_resgid;		/* reserved blocks for gid */
132	int active_logs;		/* # of active logs */
133	int inline_xattr_size;		/* inline xattr size */
134#ifdef CONFIG_F2FS_FAULT_INJECTION
135	struct f2fs_fault_info fault_info;	/* For fault injection */
136#endif
137#ifdef CONFIG_QUOTA
138	/* Names of quota files with journalled quota */
139	char *s_qf_names[MAXQUOTAS];
140	int s_jquota_fmt;			/* Format of quota to use */
141#endif
142	/* For which write hints are passed down to block layer */
143	int whint_mode;
144	int alloc_mode;			/* segment allocation policy */
145	int fsync_mode;			/* fsync policy */
146	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
147	int bggc_mode;			/* bggc mode: off, on or sync */
148	struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */
149	block_t unusable_cap_perc;	/* percentage for cap */
150	block_t unusable_cap;		/* Amount of space allowed to be
151					 * unusable when disabling checkpoint
152					 */
153
154	/* For compression */
155	unsigned char compress_algorithm;	/* algorithm type */
156	unsigned compress_log_size;		/* cluster log size */
157	unsigned char compress_ext_cnt;		/* extension count */
158	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
159};
160
161#define F2FS_FEATURE_ENCRYPT		0x0001
162#define F2FS_FEATURE_BLKZONED		0x0002
163#define F2FS_FEATURE_ATOMIC_WRITE	0x0004
164#define F2FS_FEATURE_EXTRA_ATTR		0x0008
165#define F2FS_FEATURE_PRJQUOTA		0x0010
166#define F2FS_FEATURE_INODE_CHKSUM	0x0020
167#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
168#define F2FS_FEATURE_QUOTA_INO		0x0080
169#define F2FS_FEATURE_INODE_CRTIME	0x0100
170#define F2FS_FEATURE_LOST_FOUND		0x0200
171#define F2FS_FEATURE_VERITY		0x0400
172#define F2FS_FEATURE_SB_CHKSUM		0x0800
173#define F2FS_FEATURE_CASEFOLD		0x1000
174#define F2FS_FEATURE_COMPRESSION	0x2000
175
176#define __F2FS_HAS_FEATURE(raw_super, mask)				\
177	((raw_super->feature & cpu_to_le32(mask)) != 0)
178#define F2FS_HAS_FEATURE(sbi, mask)	__F2FS_HAS_FEATURE(sbi->raw_super, mask)
179#define F2FS_SET_FEATURE(sbi, mask)					\
180	(sbi->raw_super->feature |= cpu_to_le32(mask))
181#define F2FS_CLEAR_FEATURE(sbi, mask)					\
182	(sbi->raw_super->feature &= ~cpu_to_le32(mask))
183
184/*
185 * Default values for user and/or group using reserved blocks
186 */
187#define	F2FS_DEF_RESUID		0
188#define	F2FS_DEF_RESGID		0
189
190/*
191 * For checkpoint manager
192 */
193enum {
194	NAT_BITMAP,
195	SIT_BITMAP
196};
197
198#define	CP_UMOUNT	0x00000001
199#define	CP_FASTBOOT	0x00000002
200#define	CP_SYNC		0x00000004
201#define	CP_RECOVERY	0x00000008
202#define	CP_DISCARD	0x00000010
203#define CP_TRIMMED	0x00000020
204#define CP_PAUSE	0x00000040
205#define CP_RESIZE 	0x00000080
206
207#define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
208#define DEF_MAX_DISCARD_REQUEST		8	/* issue 8 discards per round */
209#define DEF_MIN_DISCARD_ISSUE_TIME	50	/* 50 ms, if exists */
210#define DEF_MID_DISCARD_ISSUE_TIME	500	/* 500 ms, if device busy */
211#define DEF_MAX_DISCARD_ISSUE_TIME	60000	/* 60 s, if no candidates */
212#define DEF_DISCARD_URGENT_UTIL		80	/* do more discard over 80% */
213#define DEF_CP_INTERVAL			60	/* 60 secs */
214#define DEF_IDLE_INTERVAL		5	/* 5 secs */
215#define DEF_DISABLE_INTERVAL		5	/* 5 secs */
216#define DEF_DISABLE_QUICK_INTERVAL	1	/* 1 secs */
217#define DEF_UMOUNT_DISCARD_TIMEOUT	5	/* 5 secs */
218
219struct cp_control {
220	int reason;
221	__u64 trim_start;
222	__u64 trim_end;
223	__u64 trim_minlen;
224};
225
226/*
227 * indicate meta/data type
228 */
229enum {
230	META_CP,
231	META_NAT,
232	META_SIT,
233	META_SSA,
234	META_MAX,
235	META_POR,
236	DATA_GENERIC,		/* check range only */
237	DATA_GENERIC_ENHANCE,	/* strong check on range and segment bitmap */
238	DATA_GENERIC_ENHANCE_READ,	/*
239					 * strong check on range and segment
240					 * bitmap but no warning due to race
241					 * condition of read on truncated area
242					 * by extent_cache
243					 */
244	DATA_GENERIC_ENHANCE_UPDATE,	/*
245					 * strong check on range and segment
246					 * bitmap for update case
247					 */
248	META_GENERIC,
249};
250
251/* for the list of ino */
252enum {
253	ORPHAN_INO,		/* for orphan ino list */
254	APPEND_INO,		/* for append ino list */
255	UPDATE_INO,		/* for update ino list */
256	TRANS_DIR_INO,		/* for trasactions dir ino list */
257	FLUSH_INO,		/* for multiple device flushing */
258	MAX_INO_ENTRY,		/* max. list */
259};
260
261struct ino_entry {
262	struct list_head list;		/* list head */
263	nid_t ino;			/* inode number */
264	unsigned int dirty_device;	/* dirty device bitmap */
265};
266
267/* for the list of inodes to be GCed */
268struct inode_entry {
269	struct list_head list;	/* list head */
270	struct inode *inode;	/* vfs inode pointer */
271};
272
273struct fsync_node_entry {
274	struct list_head list;	/* list head */
275	struct page *page;	/* warm node page pointer */
276	unsigned int seq_id;	/* sequence id */
277};
278
279/* for the bitmap indicate blocks to be discarded */
280struct discard_entry {
281	struct list_head list;	/* list head */
282	block_t start_blkaddr;	/* start blockaddr of current segment */
283	unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];	/* segment discard bitmap */
284};
285
286/* default discard granularity of inner discard thread, unit: block count */
287#define DEFAULT_DISCARD_GRANULARITY		16
288#define DISCARD_GRAN_BL		16
289#define DISCARD_GRAN_BG		512
290#define DISCARD_GRAN_FORCE	1
291
292/* max discard pend list number */
293#define MAX_PLIST_NUM		512
294#define plist_idx(blk_num)	((blk_num) >= MAX_PLIST_NUM ?		\
295					(MAX_PLIST_NUM - 1) : ((blk_num) - 1))
296#define FS_FREE_SPACE_PERCENT		20
297#define DEVICE_FREE_SPACE_PERCENT	10
298#define HUNDRED_PERCENT			100
299
300enum {
301	D_PREP,			/* initial */
302	D_PARTIAL,		/* partially submitted */
303	D_SUBMIT,		/* all submitted */
304	D_DONE,			/* finished */
305};
306
307struct discard_info {
308	block_t lstart;			/* logical start address */
309	block_t len;			/* length */
310	block_t start;			/* actual start address in dev */
311};
312
313struct discard_cmd {
314	struct rb_node rb_node;		/* rb node located in rb-tree */
315	union {
316		struct {
317			block_t lstart;	/* logical start address */
318			block_t len;	/* length */
319			block_t start;	/* actual start address in dev */
320		};
321		struct discard_info di;	/* discard info */
322
323	};
324	struct list_head list;		/* command list */
325	struct completion wait;		/* compleation */
326	struct block_device *bdev;	/* bdev */
327	unsigned short ref;		/* reference count */
328	unsigned char state;		/* state */
329	unsigned char queued;		/* queued discard */
330	int error;			/* bio error */
331	spinlock_t lock;		/* for state/bio_ref updating */
332	unsigned short bio_ref;		/* bio reference count */
333};
334
335enum {
336	DPOLICY_BG,
337	DPOLICY_BALANCE,
338	DPOLICY_FORCE,
339	DPOLICY_FSTRIM,
340	DPOLICY_UMOUNT,
341	MAX_DPOLICY,
342};
343
344enum {
345	SUB_POLICY_BIG,
346	SUB_POLICY_MID,
347	SUB_POLICY_SMALL,
348	NR_SUB_POLICY,
349};
350
351struct discard_sub_policy {
352	unsigned int max_requests;
353	int interval;
354};
355
356struct discard_policy {
357	int type;			/* type of discard */
358	unsigned int min_interval;	/* used for candidates exist */
359	unsigned int mid_interval;	/* used for device busy */
360	unsigned int max_interval;	/* used for candidates not exist */
361	unsigned int io_aware_gran;	/* minimum granularity discard not be aware of I/O */
362	bool io_aware;			/* issue discard in idle time */
363	bool sync;			/* submit discard with REQ_SYNC flag */
364	bool ordered;			/* issue discard by lba order */
365	bool timeout;			/* discard timeout for put_super */
366	unsigned int granularity;	/* discard granularity */
367	struct discard_sub_policy sub_policy[NR_SUB_POLICY];
368};
369
370struct discard_cmd_control {
371	struct task_struct *f2fs_issue_discard;	/* discard thread */
372	struct list_head entry_list;		/* 4KB discard entry list */
373	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
374	struct list_head wait_list;		/* store on-flushing entries */
375	struct list_head fstrim_list;		/* in-flight discard from fstrim */
376	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
377	unsigned int discard_wake;		/* to wake up discard thread */
378	struct mutex cmd_lock;
379	unsigned int nr_discards;		/* # of discards in the list */
380	unsigned int max_discards;		/* max. discards to be issued */
381	unsigned int discard_granularity;	/* discard granularity */
382	unsigned int undiscard_blks;		/* # of undiscard blocks */
383	unsigned int next_pos;			/* next discard position */
384	atomic_t issued_discard;		/* # of issued discard */
385	atomic_t queued_discard;		/* # of queued discard */
386	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
387	struct rb_root_cached root;		/* root of discard rb-tree */
388	bool rbtree_check;			/* config for consistence check */
389	int discard_type;                       /* discard type */
390};
391
392/* for the list of fsync inodes, used only during recovery */
393struct fsync_inode_entry {
394	struct list_head list;	/* list head */
395	struct inode *inode;	/* vfs inode pointer */
396	block_t blkaddr;	/* block address locating the last fsync */
397	block_t last_dentry;	/* block address locating the last dentry */
398};
399
400#define nats_in_cursum(jnl)		(le16_to_cpu((jnl)->n_nats))
401#define sits_in_cursum(jnl)		(le16_to_cpu((jnl)->n_sits))
402
403#define nat_in_journal(jnl, i)		((jnl)->nat_j.entries[i].ne)
404#define nid_in_journal(jnl, i)		((jnl)->nat_j.entries[i].nid)
405#define sit_in_journal(jnl, i)		((jnl)->sit_j.entries[i].se)
406#define segno_in_journal(jnl, i)	((jnl)->sit_j.entries[i].segno)
407
408#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
409#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
410
411static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
412{
413	int before = nats_in_cursum(journal);
414
415	journal->n_nats = cpu_to_le16(before + i);
416	return before;
417}
418
419static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
420{
421	int before = sits_in_cursum(journal);
422
423	journal->n_sits = cpu_to_le16(before + i);
424	return before;
425}
426
427static inline bool __has_cursum_space(struct f2fs_journal *journal,
428							int size, int type)
429{
430	if (type == NAT_JOURNAL)
431		return size <= MAX_NAT_JENTRIES(journal);
432	return size <= MAX_SIT_JENTRIES(journal);
433}
434
435/* for inline stuff */
436#define DEF_INLINE_RESERVED_SIZE	1
437static inline int get_extra_isize(struct inode *inode);
438static inline int get_inline_xattr_addrs(struct inode *inode);
439#define MAX_INLINE_DATA(inode)	(sizeof(__le32) *			\
440				(CUR_ADDRS_PER_INODE(inode) -		\
441				get_inline_xattr_addrs(inode) -	\
442				DEF_INLINE_RESERVED_SIZE))
443
444/* for inline dir */
445#define NR_INLINE_DENTRY(inode)	(MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
446				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
447				BITS_PER_BYTE + 1))
448#define INLINE_DENTRY_BITMAP_SIZE(inode) \
449	DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE)
450#define INLINE_RESERVED_SIZE(inode)	(MAX_INLINE_DATA(inode) - \
451				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
452				NR_INLINE_DENTRY(inode) + \
453				INLINE_DENTRY_BITMAP_SIZE(inode)))
454
455/*
456 * For INODE and NODE manager
457 */
458/* for directory operations */
459
460struct f2fs_filename {
461	/*
462	 * The filename the user specified.  This is NULL for some
463	 * filesystem-internal operations, e.g. converting an inline directory
464	 * to a non-inline one, or roll-forward recovering an encrypted dentry.
465	 */
466	const struct qstr *usr_fname;
467
468	/*
469	 * The on-disk filename.  For encrypted directories, this is encrypted.
470	 * This may be NULL for lookups in an encrypted dir without the key.
471	 */
472	struct fscrypt_str disk_name;
473
474	/* The dirhash of this filename */
475	f2fs_hash_t hash;
476
477#ifdef CONFIG_FS_ENCRYPTION
478	/*
479	 * For lookups in encrypted directories: either the buffer backing
480	 * disk_name, or a buffer that holds the decoded no-key name.
481	 */
482	struct fscrypt_str crypto_buf;
483#endif
484#ifdef CONFIG_UNICODE
485	/*
486	 * For casefolded directories: the casefolded name, but it's left NULL
487	 * if the original name is not valid Unicode or if the filesystem is
488	 * doing an internal operation where usr_fname is also NULL.  In these
489	 * cases we fall back to treating the name as an opaque byte sequence.
490	 */
491	struct fscrypt_str cf_name;
492#endif
493};
494
495struct f2fs_dentry_ptr {
496	struct inode *inode;
497	void *bitmap;
498	struct f2fs_dir_entry *dentry;
499	__u8 (*filename)[F2FS_SLOT_LEN];
500	int max;
501	int nr_bitmap;
502};
503
504static inline void make_dentry_ptr_block(struct inode *inode,
505		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
506{
507	d->inode = inode;
508	d->max = NR_DENTRY_IN_BLOCK;
509	d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
510	d->bitmap = t->dentry_bitmap;
511	d->dentry = t->dentry;
512	d->filename = t->filename;
513}
514
515static inline void make_dentry_ptr_inline(struct inode *inode,
516					struct f2fs_dentry_ptr *d, void *t)
517{
518	int entry_cnt = NR_INLINE_DENTRY(inode);
519	int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
520	int reserved_size = INLINE_RESERVED_SIZE(inode);
521
522	d->inode = inode;
523	d->max = entry_cnt;
524	d->nr_bitmap = bitmap_size;
525	d->bitmap = t;
526	d->dentry = t + bitmap_size + reserved_size;
527	d->filename = t + bitmap_size + reserved_size +
528					SIZE_OF_DIR_ENTRY * entry_cnt;
529}
530
531/*
532 * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
533 * as its node offset to distinguish from index node blocks.
534 * But some bits are used to mark the node block.
535 */
536#define XATTR_NODE_OFFSET	((((unsigned int)-1) << OFFSET_BIT_SHIFT) \
537				>> OFFSET_BIT_SHIFT)
538enum {
539	ALLOC_NODE,			/* allocate a new node page if needed */
540	LOOKUP_NODE,			/* look up a node without readahead */
541	LOOKUP_NODE_RA,			/*
542					 * look up a node with readahead called
543					 * by get_data_block.
544					 */
545};
546
547#define DEFAULT_RETRY_IO_COUNT	8	/* maximum retry read IO count */
548
549/* congestion wait timeout value, default: 20ms */
550#define	DEFAULT_IO_TIMEOUT	(msecs_to_jiffies(20))
551
552/* maximum retry quota flush count */
553#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT		8
554
555#define F2FS_LINK_MAX	0xffffffff	/* maximum link count per file */
556
557#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
558
559/* for in-memory extent cache entry */
560#define F2FS_MIN_EXTENT_LEN	64	/* minimum extent length */
561
562/* number of extent info in extent cache we try to shrink */
563#define EXTENT_CACHE_SHRINK_NUMBER	128
564
565struct rb_entry {
566	struct rb_node rb_node;		/* rb node located in rb-tree */
567	union {
568		struct {
569			unsigned int ofs;	/* start offset of the entry */
570			unsigned int len;	/* length of the entry */
571		};
572		unsigned long long key;		/* 64-bits key */
573	} __packed;
574};
575
576struct extent_info {
577	unsigned int fofs;		/* start offset in a file */
578	unsigned int len;		/* length of the extent */
579	u32 blk;			/* start block address of the extent */
580};
581
582struct extent_node {
583	struct rb_node rb_node;		/* rb node located in rb-tree */
584	struct extent_info ei;		/* extent info */
585	struct list_head list;		/* node in global extent list of sbi */
586	struct extent_tree *et;		/* extent tree pointer */
587};
588
589struct extent_tree {
590	nid_t ino;			/* inode number */
591	struct rb_root_cached root;	/* root of extent info rb-tree */
592	struct extent_node *cached_en;	/* recently accessed extent node */
593	struct extent_info largest;	/* largested extent info */
594	struct list_head list;		/* to be used by sbi->zombie_list */
595	rwlock_t lock;			/* protect extent info rb-tree */
596	atomic_t node_cnt;		/* # of extent node in rb-tree*/
597	bool largest_updated;		/* largest extent updated */
598};
599
600/*
601 * This structure is taken from ext4_map_blocks.
602 *
603 * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
604 */
605#define F2FS_MAP_NEW		(1 << BH_New)
606#define F2FS_MAP_MAPPED		(1 << BH_Mapped)
607#define F2FS_MAP_UNWRITTEN	(1 << BH_Unwritten)
608#define F2FS_MAP_FLAGS		(F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
609				F2FS_MAP_UNWRITTEN)
610
611struct f2fs_map_blocks {
612	block_t m_pblk;
613	block_t m_lblk;
614	unsigned int m_len;
615	unsigned int m_flags;
616	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
617	pgoff_t *m_next_extent;		/* point to next possible extent */
618	int m_seg_type;
619	bool m_may_create;		/* indicate it is from write path */
620};
621
622/* for flag in get_data_block */
623enum {
624	F2FS_GET_BLOCK_DEFAULT,
625	F2FS_GET_BLOCK_FIEMAP,
626	F2FS_GET_BLOCK_BMAP,
627	F2FS_GET_BLOCK_DIO,
628	F2FS_GET_BLOCK_PRE_DIO,
629	F2FS_GET_BLOCK_PRE_AIO,
630	F2FS_GET_BLOCK_PRECACHE,
631};
632
633/*
634 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
635 */
636#define FADVISE_COLD_BIT	0x01
637#define FADVISE_LOST_PINO_BIT	0x02
638#define FADVISE_ENCRYPT_BIT	0x04
639#define FADVISE_ENC_NAME_BIT	0x08
640#define FADVISE_KEEP_SIZE_BIT	0x10
641#define FADVISE_HOT_BIT		0x20
642#define FADVISE_VERITY_BIT	0x40
643
644#define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)
645
646#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
647#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
648#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
649#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
650#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
651#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
652#define file_is_encrypt(inode)	is_file(inode, FADVISE_ENCRYPT_BIT)
653#define file_set_encrypt(inode)	set_file(inode, FADVISE_ENCRYPT_BIT)
654#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
655#define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
656#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
657#define file_keep_isize(inode)	is_file(inode, FADVISE_KEEP_SIZE_BIT)
658#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
659#define file_is_hot(inode)	is_file(inode, FADVISE_HOT_BIT)
660#define file_set_hot(inode)	set_file(inode, FADVISE_HOT_BIT)
661#define file_clear_hot(inode)	clear_file(inode, FADVISE_HOT_BIT)
662#define file_is_verity(inode)	is_file(inode, FADVISE_VERITY_BIT)
663#define file_set_verity(inode)	set_file(inode, FADVISE_VERITY_BIT)
664
665#define DEF_DIR_LEVEL		0
666
667enum {
668	GC_FAILURE_PIN,
669	GC_FAILURE_ATOMIC,
670	MAX_GC_FAILURE
671};
672
673/* used for f2fs_inode_info->flags */
674enum {
675	FI_NEW_INODE,		/* indicate newly allocated inode */
676	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
677	FI_AUTO_RECOVER,	/* indicate inode is recoverable */
678	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
679	FI_INC_LINK,		/* need to increment i_nlink */
680	FI_ACL_MODE,		/* indicate acl mode */
681	FI_NO_ALLOC,		/* should not allocate any blocks */
682	FI_FREE_NID,		/* free allocated nide */
683	FI_NO_EXTENT,		/* not to use the extent cache */
684	FI_INLINE_XATTR,	/* used for inline xattr */
685	FI_INLINE_DATA,		/* used for inline data*/
686	FI_INLINE_DENTRY,	/* used for inline dentry */
687	FI_APPEND_WRITE,	/* inode has appended data */
688	FI_UPDATE_WRITE,	/* inode has in-place-update data */
689	FI_NEED_IPU,		/* used for ipu per file */
690	FI_ATOMIC_FILE,		/* indicate atomic file */
691	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
692	FI_VOLATILE_FILE,	/* indicate volatile file */
693	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
694	FI_DROP_CACHE,		/* drop dirty page cache */
695	FI_DATA_EXIST,		/* indicate data exists */
696	FI_INLINE_DOTS,		/* indicate inline dot dentries */
697	FI_DO_DEFRAG,		/* indicate defragment is running */
698	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
699	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
700	FI_HOT_DATA,		/* indicate file is hot */
701	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
702	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
703	FI_PIN_FILE,		/* indicate file should not be gced */
704	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
705	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
706	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
707	FI_MMAP_FILE,		/* indicate file was mmapped */
708	FI_MAX,			/* max flag, never be used */
709};
710
711struct f2fs_inode_info {
712	struct inode vfs_inode;		/* serve a vfs inode */
713	unsigned long i_flags;		/* keep an inode flags for ioctl */
714	unsigned char i_advise;		/* use to give file attribute hints */
715	unsigned char i_dir_level;	/* use for dentry level for large dir */
716	unsigned int i_current_depth;	/* only for directory depth */
717	/* for gc failure statistic */
718	unsigned int i_gc_failures[MAX_GC_FAILURE];
719	unsigned int i_pino;		/* parent inode number */
720	umode_t i_acl_mode;		/* keep file acl mode temporarily */
721
722	/* Use below internally in f2fs*/
723	unsigned long flags[BITS_TO_LONGS(FI_MAX)];	/* use to pass per-file flags */
724	struct rw_semaphore i_sem;	/* protect fi info */
725	atomic_t dirty_pages;		/* # of dirty pages */
726	f2fs_hash_t chash;		/* hash value of given file name */
727	unsigned int clevel;		/* maximum level of given file name */
728	struct task_struct *task;	/* lookup and create consistency */
729	struct task_struct *cp_task;	/* separate cp/wb IO stats*/
730	struct task_struct *wb_task;	/* indicate inode is in context of writeback */
731	nid_t i_xattr_nid;		/* node id that contains xattrs */
732	loff_t	last_disk_size;		/* lastly written file size */
733	spinlock_t i_size_lock;		/* protect last_disk_size */
734
735#ifdef CONFIG_QUOTA
736	struct dquot *i_dquot[MAXQUOTAS];
737
738	/* quota space reservation, managed internally by quota code */
739	qsize_t i_reserved_quota;
740#endif
741	struct list_head dirty_list;	/* dirty list for dirs and files */
742	struct list_head gdirty_list;	/* linked in global dirty list */
743	struct list_head inmem_ilist;	/* list for inmem inodes */
744	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
745	struct task_struct *inmem_task;	/* store inmemory task */
746	struct mutex inmem_lock;	/* lock for inmemory pages */
747	pgoff_t ra_offset;		/* ongoing readahead offset */
748	struct extent_tree *extent_tree;	/* cached extent_tree entry */
749
750	/* avoid racing between foreground op and gc */
751	struct rw_semaphore i_gc_rwsem[2];
752	struct rw_semaphore i_mmap_sem;
753	struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
754
755	int i_extra_isize;		/* size of extra space located in i_addr */
756	kprojid_t i_projid;		/* id for project quota */
757	int i_inline_xattr_size;	/* inline xattr size */
758	struct timespec64 i_crtime;	/* inode creation time */
759	struct timespec64 i_disk_time[4];/* inode disk times */
760
761	/* for file compress */
762	atomic_t i_compr_blocks;		/* # of compressed blocks */
763	unsigned char i_compress_algorithm;	/* algorithm type */
764	unsigned char i_log_cluster_size;	/* log of cluster size */
765	unsigned int i_cluster_size;		/* cluster size */
766};
767
768static inline void get_extent_info(struct extent_info *ext,
769					struct f2fs_extent *i_ext)
770{
771	ext->fofs = le32_to_cpu(i_ext->fofs);
772	ext->blk = le32_to_cpu(i_ext->blk);
773	ext->len = le32_to_cpu(i_ext->len);
774}
775
776static inline void set_raw_extent(struct extent_info *ext,
777					struct f2fs_extent *i_ext)
778{
779	i_ext->fofs = cpu_to_le32(ext->fofs);
780	i_ext->blk = cpu_to_le32(ext->blk);
781	i_ext->len = cpu_to_le32(ext->len);
782}
783
784static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
785						u32 blk, unsigned int len)
786{
787	ei->fofs = fofs;
788	ei->blk = blk;
789	ei->len = len;
790}
791
792static inline bool __is_discard_mergeable(struct discard_info *back,
793			struct discard_info *front, unsigned int max_len)
794{
795	return (back->lstart + back->len == front->lstart) &&
796		(back->len + front->len <= max_len);
797}
798
799static inline bool __is_discard_back_mergeable(struct discard_info *cur,
800			struct discard_info *back, unsigned int max_len)
801{
802	return __is_discard_mergeable(back, cur, max_len);
803}
804
805static inline bool __is_discard_front_mergeable(struct discard_info *cur,
806			struct discard_info *front, unsigned int max_len)
807{
808	return __is_discard_mergeable(cur, front, max_len);
809}
810
811static inline bool __is_extent_mergeable(struct extent_info *back,
812						struct extent_info *front)
813{
814	return (back->fofs + back->len == front->fofs &&
815			back->blk + back->len == front->blk);
816}
817
818static inline bool __is_back_mergeable(struct extent_info *cur,
819						struct extent_info *back)
820{
821	return __is_extent_mergeable(back, cur);
822}
823
824static inline bool __is_front_mergeable(struct extent_info *cur,
825						struct extent_info *front)
826{
827	return __is_extent_mergeable(cur, front);
828}
829
830extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
831static inline void __try_update_largest_extent(struct extent_tree *et,
832						struct extent_node *en)
833{
834	if (en->ei.len > et->largest.len) {
835		et->largest = en->ei;
836		et->largest_updated = true;
837	}
838}
839
840/*
841 * For free nid management
842 */
843enum nid_state {
844	FREE_NID,		/* newly added to free nid list */
845	PREALLOC_NID,		/* it is preallocated */
846	MAX_NID_STATE,
847};
848
849enum nat_state {
850	TOTAL_NAT,
851	DIRTY_NAT,
852	RECLAIMABLE_NAT,
853	MAX_NAT_STATE,
854};
855
856struct f2fs_nm_info {
857	block_t nat_blkaddr;		/* base disk address of NAT */
858	nid_t max_nid;			/* maximum possible node ids */
859	nid_t available_nids;		/* # of available node ids */
860	nid_t next_scan_nid;		/* the next nid to be scanned */
861	unsigned int ram_thresh;	/* control the memory footprint */
862	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
863	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
864
865	/* NAT cache management */
866	struct radix_tree_root nat_root;/* root of the nat entry cache */
867	struct radix_tree_root nat_set_root;/* root of the nat set cache */
868	struct rw_semaphore nat_tree_lock;	/* protect nat_tree_lock */
869	struct list_head nat_entries;	/* cached nat entry list (clean) */
870	spinlock_t nat_list_lock;	/* protect clean nat entry list */
871	unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
872	unsigned int nat_blocks;	/* # of nat blocks */
873
874	/* free node ids management */
875	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
876	struct list_head free_nid_list;		/* list for free nids excluding preallocated nids */
877	unsigned int nid_cnt[MAX_NID_STATE];	/* the number of free node id */
878	spinlock_t nid_list_lock;	/* protect nid lists ops */
879	struct mutex build_lock;	/* lock for build free nids */
880	unsigned char **free_nid_bitmap;
881	unsigned char *nat_block_bitmap;
882	unsigned short *free_nid_count;	/* free nid count of NAT block */
883
884	/* for checkpoint */
885	char *nat_bitmap;		/* NAT bitmap pointer */
886
887	unsigned int nat_bits_blocks;	/* # of nat bits blocks */
888	unsigned char *nat_bits;	/* NAT bits blocks */
889	unsigned char *full_nat_bits;	/* full NAT pages */
890	unsigned char *empty_nat_bits;	/* empty NAT pages */
891#ifdef CONFIG_F2FS_CHECK_FS
892	char *nat_bitmap_mir;		/* NAT bitmap mirror */
893#endif
894	int bitmap_size;		/* bitmap size */
895};
896
897/*
898 * this structure is used as one of function parameters.
899 * all the information are dedicated to a given direct node block determined
900 * by the data offset in a file.
901 */
902struct dnode_of_data {
903	struct inode *inode;		/* vfs inode pointer */
904	struct page *inode_page;	/* its inode page, NULL is possible */
905	struct page *node_page;		/* cached direct node page */
906	nid_t nid;			/* node id of the direct node block */
907	unsigned int ofs_in_node;	/* data offset in the node page */
908	bool inode_page_locked;		/* inode page is locked or not */
909	bool node_changed;		/* is node block changed */
910	char cur_level;			/* level of hole node page */
911	char max_level;			/* level of current page located */
912	block_t	data_blkaddr;		/* block address of the node block */
913};
914
915static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
916		struct page *ipage, struct page *npage, nid_t nid)
917{
918	memset(dn, 0, sizeof(*dn));
919	dn->inode = inode;
920	dn->inode_page = ipage;
921	dn->node_page = npage;
922	dn->nid = nid;
923}
924
925/*
926 * For SIT manager
927 *
928 * By default, there are 6 active log areas across the whole main area.
929 * When considering hot and cold data separation to reduce cleaning overhead,
930 * we split 3 for data logs and 3 for node logs as hot, warm, and cold types,
931 * respectively.
932 * In the current design, you should not change the numbers intentionally.
933 * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6
934 * logs individually according to the underlying devices. (default: 6)
935 * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for
936 * data and 8 for node logs.
937 */
938#define	NR_CURSEG_DATA_TYPE	(3)
939#define NR_CURSEG_NODE_TYPE	(3)
940#define NR_CURSEG_INMEM_TYPE	(2)
941#define NR_CURSEG_PERSIST_TYPE	(NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
942#define NR_CURSEG_TYPE		(NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
943
944enum {
945	CURSEG_HOT_DATA	= 0,	/* directory entry blocks */
946	CURSEG_WARM_DATA,	/* data blocks */
947	CURSEG_COLD_DATA,	/* multimedia or GCed data blocks */
948	CURSEG_HOT_NODE,	/* direct node blocks of directory files */
949	CURSEG_WARM_NODE,	/* direct node blocks of normal files */
950	CURSEG_COLD_NODE,	/* indirect node blocks */
951	NR_PERSISTENT_LOG,	/* number of persistent log */
952	CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG,
953				/* pinned file that needs consecutive block address */
954	CURSEG_ALL_DATA_ATGC,	/* SSR alloctor in hot/warm/cold data area */
955	NO_CHECK_TYPE,		/* number of persistent & inmem log */
956};
957
958struct flush_cmd {
959	struct completion wait;
960	struct llist_node llnode;
961	nid_t ino;
962	int ret;
963};
964
965struct flush_cmd_control {
966	struct task_struct *f2fs_issue_flush;	/* flush thread */
967	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
968	atomic_t issued_flush;			/* # of issued flushes */
969	atomic_t queued_flush;			/* # of queued flushes */
970	struct llist_head issue_list;		/* list for command issue */
971	struct llist_node *dispatch_list;	/* list for command dispatch */
972};
973
974struct f2fs_sm_info {
975	struct sit_info *sit_info;		/* whole segment information */
976	struct free_segmap_info *free_info;	/* free segment information */
977	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
978	struct curseg_info *curseg_array;	/* active segment information */
979
980	struct rw_semaphore curseg_lock;	/* for preventing curseg change */
981
982	block_t seg0_blkaddr;		/* block address of 0'th segment */
983	block_t main_blkaddr;		/* start block address of main area */
984	block_t ssa_blkaddr;		/* start block address of SSA area */
985
986	unsigned int segment_count;	/* total # of segments */
987	unsigned int main_segments;	/* # of segments in main area */
988	unsigned int reserved_segments;	/* # of reserved segments */
989	unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
990	unsigned int ovp_segments;	/* # of overprovision segments */
991
992	/* a threshold to reclaim prefree segments */
993	unsigned int rec_prefree_segments;
994
995	/* for batched trimming */
996	unsigned int trim_sections;		/* # of sections to trim */
997
998	struct list_head sit_entry_set;	/* sit entry set list */
999
1000	unsigned int ipu_policy;	/* in-place-update policy */
1001	unsigned int min_ipu_util;	/* in-place-update threshold */
1002	unsigned int min_fsync_blocks;	/* threshold for fsync */
1003	unsigned int min_seq_blocks;	/* threshold for sequential blocks */
1004	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
1005	unsigned int min_ssr_sections;	/* threshold to trigger SSR allocation */
1006
1007	/* for flush command control */
1008	struct flush_cmd_control *fcc_info;
1009
1010	/* for discard command control */
1011	struct discard_cmd_control *dcc_info;
1012};
1013
1014/*
1015 * For superblock
1016 */
1017/*
1018 * COUNT_TYPE for monitoring
1019 *
1020 * f2fs monitors the number of several block types such as on-writeback,
1021 * dirty dentry blocks, dirty node blocks, and dirty meta blocks.
1022 */
1023#define WB_DATA_TYPE(p)	(__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
1024enum count_type {
1025	F2FS_DIRTY_DENTS,
1026	F2FS_DIRTY_DATA,
1027	F2FS_DIRTY_QDATA,
1028	F2FS_DIRTY_NODES,
1029	F2FS_DIRTY_META,
1030	F2FS_INMEM_PAGES,
1031	F2FS_DIRTY_IMETA,
1032	F2FS_WB_CP_DATA,
1033	F2FS_WB_DATA,
1034	F2FS_RD_DATA,
1035	F2FS_RD_NODE,
1036	F2FS_RD_META,
1037	F2FS_DIO_WRITE,
1038	F2FS_DIO_READ,
1039	NR_COUNT_TYPE,
1040};
1041
1042/*
1043 * The below are the page types of bios used in submit_bio().
1044 * The available types are:
1045 * DATA			User data pages. It operates as async mode.
1046 * NODE			Node pages. It operates as async mode.
1047 * META			FS metadata pages such as SIT, NAT, CP.
1048 * NR_PAGE_TYPE		The number of page types.
1049 * META_FLUSH		Make sure the previous pages are written
1050 *			with waiting the bio's completion
1051 * ...			Only can be used with META.
1052 */
1053#define PAGE_TYPE_OF_BIO(type)	((type) > META ? META : (type))
1054enum page_type {
1055	DATA = 0,
1056	NODE = 1,	/* should not change this */
1057	META,
1058	NR_PAGE_TYPE,
1059	META_FLUSH,
1060	INMEM,		/* the below types are used by tracepoints only. */
1061	INMEM_DROP,
1062	INMEM_INVALIDATE,
1063	INMEM_REVOKE,
1064	IPU,
1065	OPU,
1066};
1067
1068enum temp_type {
1069	HOT = 0,	/* must be zero for meta bio */
1070	WARM,
1071	COLD,
1072	NR_TEMP_TYPE,
1073};
1074
1075enum need_lock_type {
1076	LOCK_REQ = 0,
1077	LOCK_DONE,
1078	LOCK_RETRY,
1079};
1080
1081enum cp_reason_type {
1082	CP_NO_NEEDED,
1083	CP_NON_REGULAR,
1084	CP_COMPRESSED,
1085	CP_HARDLINK,
1086	CP_SB_NEED_CP,
1087	CP_WRONG_PINO,
1088	CP_NO_SPC_ROLL,
1089	CP_NODE_NEED_CP,
1090	CP_FASTBOOT_MODE,
1091	CP_SPEC_LOG_NUM,
1092	CP_RECOVER_DIR,
1093};
1094
1095enum iostat_type {
1096	/* WRITE IO */
1097	APP_DIRECT_IO,			/* app direct write IOs */
1098	APP_BUFFERED_IO,		/* app buffered write IOs */
1099	APP_WRITE_IO,			/* app write IOs */
1100	APP_MAPPED_IO,			/* app mapped IOs */
1101	FS_DATA_IO,			/* data IOs from kworker/fsync/reclaimer */
1102	FS_NODE_IO,			/* node IOs from kworker/fsync/reclaimer */
1103	FS_META_IO,			/* meta IOs from kworker/reclaimer */
1104	FS_GC_DATA_IO,			/* data IOs from forground gc */
1105	FS_GC_NODE_IO,			/* node IOs from forground gc */
1106	FS_CP_DATA_IO,			/* data IOs from checkpoint */
1107	FS_CP_NODE_IO,			/* node IOs from checkpoint */
1108	FS_CP_META_IO,			/* meta IOs from checkpoint */
1109
1110	/* READ IO */
1111	APP_DIRECT_READ_IO,		/* app direct read IOs */
1112	APP_BUFFERED_READ_IO,		/* app buffered read IOs */
1113	APP_READ_IO,			/* app read IOs */
1114	APP_MAPPED_READ_IO,		/* app mapped read IOs */
1115	FS_DATA_READ_IO,		/* data read IOs */
1116	FS_GDATA_READ_IO,		/* data read IOs from background gc */
1117	FS_CDATA_READ_IO,		/* compressed data read IOs */
1118	FS_NODE_READ_IO,		/* node read IOs */
1119	FS_META_READ_IO,		/* meta read IOs */
1120
1121	/* other */
1122	FS_DISCARD,			/* discard */
1123	NR_IO_TYPE,
1124};
1125
1126struct f2fs_io_info {
1127	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
1128	nid_t ino;		/* inode number */
1129	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
1130	enum temp_type temp;	/* contains HOT/WARM/COLD */
1131	int op;			/* contains REQ_OP_ */
1132	int op_flags;		/* req_flag_bits */
1133	block_t new_blkaddr;	/* new block address to be written */
1134	block_t old_blkaddr;	/* old block address before Cow */
1135	struct page *page;	/* page to be written */
1136	struct page *encrypted_page;	/* encrypted page */
1137	struct page *compressed_page;	/* compressed page */
1138	struct list_head list;		/* serialize IOs */
1139	bool submitted;		/* indicate IO submission */
1140	int need_lock;		/* indicate we need to lock cp_rwsem */
1141	bool in_list;		/* indicate fio is in io_list */
1142	bool is_por;		/* indicate IO is from recovery or not */
1143	bool retry;		/* need to reallocate block address */
1144	int compr_blocks;	/* # of compressed block addresses */
1145	bool encrypted;		/* indicate file is encrypted */
1146	enum iostat_type io_type;	/* io type */
1147	struct writeback_control *io_wbc; /* writeback control */
1148	struct bio **bio;		/* bio for ipu */
1149	sector_t *last_block;		/* last block number in bio */
1150	unsigned char version;		/* version of the node */
1151};
1152
1153struct bio_entry {
1154	struct bio *bio;
1155	struct list_head list;
1156};
1157
1158#define is_read_io(rw) ((rw) == READ)
1159struct f2fs_bio_info {
1160	struct f2fs_sb_info *sbi;	/* f2fs superblock */
1161	struct bio *bio;		/* bios to merge */
1162	sector_t last_block_in_bio;	/* last block number */
1163	struct f2fs_io_info fio;	/* store buffered io info. */
1164	struct rw_semaphore io_rwsem;	/* blocking op for bio */
1165	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
1166	struct list_head io_list;	/* track fios */
1167	struct list_head bio_list;	/* bio entry list head */
1168	struct rw_semaphore bio_list_lock;	/* lock to protect bio entry list */
1169};
1170
1171#define FDEV(i)				(sbi->devs[i])
1172#define RDEV(i)				(raw_super->devs[i])
1173struct f2fs_dev_info {
1174	struct block_device *bdev;
1175	char path[MAX_PATH_LEN];
1176	unsigned int total_segments;
1177	block_t start_blk;
1178	block_t end_blk;
1179#ifdef CONFIG_BLK_DEV_ZONED
1180	unsigned int nr_blkz;		/* Total number of zones */
1181	unsigned long *blkz_seq;	/* Bitmap indicating sequential zones */
1182#endif
1183};
1184
1185enum inode_type {
1186	DIR_INODE,			/* for dirty dir inode */
1187	FILE_INODE,			/* for dirty regular/symlink inode */
1188	DIRTY_META,			/* for all dirtied inode metadata */
1189	ATOMIC_FILE,			/* for all atomic files */
1190	NR_INODE_TYPE,
1191};
1192
1193/* for inner inode cache management */
1194struct inode_management {
1195	struct radix_tree_root ino_root;	/* ino entry array */
1196	spinlock_t ino_lock;			/* for ino entry lock */
1197	struct list_head ino_list;		/* inode list head */
1198	unsigned long ino_num;			/* number of entries */
1199};
1200
1201/* for GC_AT */
1202struct atgc_management {
1203	bool atgc_enabled;			/* ATGC is enabled or not */
1204	struct rb_root_cached root;		/* root of victim rb-tree */
1205	struct list_head victim_list;		/* linked with all victim entries */
1206	unsigned int victim_count;		/* victim count in rb-tree */
1207	unsigned int candidate_ratio;		/* candidate ratio */
1208	unsigned int max_candidate_count;	/* max candidate count */
1209	unsigned int age_weight;		/* age weight, vblock_weight = 100 - age_weight */
1210	unsigned long long age_threshold;	/* age threshold */
1211};
1212
1213/* For s_flag in struct f2fs_sb_info */
1214enum {
1215	SBI_IS_DIRTY,				/* dirty flag for checkpoint */
1216	SBI_IS_CLOSE,				/* specify unmounting */
1217	SBI_NEED_FSCK,				/* need fsck.f2fs to fix */
1218	SBI_POR_DOING,				/* recovery is doing or not */
1219	SBI_NEED_SB_WRITE,			/* need to recover superblock */
1220	SBI_NEED_CP,				/* need to checkpoint */
1221	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
1222	SBI_IS_RECOVERED,			/* recovered orphan/data */
1223	SBI_CP_DISABLED,			/* CP was disabled last mount */
1224	SBI_CP_DISABLED_QUICK,			/* CP was disabled quickly */
1225	SBI_QUOTA_NEED_FLUSH,			/* need to flush quota info in CP */
1226	SBI_QUOTA_SKIP_FLUSH,			/* skip flushing quota in current CP */
1227	SBI_QUOTA_NEED_REPAIR,			/* quota file may be corrupted */
1228	SBI_IS_RESIZEFS,			/* resizefs is in process */
1229};
1230
1231enum {
1232	CP_TIME,
1233	REQ_TIME,
1234	DISCARD_TIME,
1235	GC_TIME,
1236	DISABLE_TIME,
1237	UMOUNT_DISCARD_TIMEOUT,
1238	MAX_TIME,
1239};
1240
1241enum {
1242	GC_NORMAL,
1243	GC_IDLE_CB,
1244	GC_IDLE_GREEDY,
1245	GC_IDLE_AT,
1246	GC_URGENT_HIGH,
1247	GC_URGENT_LOW,
1248};
1249
1250enum {
1251	BGGC_MODE_ON,		/* background gc is on */
1252	BGGC_MODE_OFF,		/* background gc is off */
1253	BGGC_MODE_SYNC,		/*
1254				 * background gc is on, migrating blocks
1255				 * like foreground gc
1256				 */
1257};
1258
1259enum {
1260	FS_MODE_ADAPTIVE,	/* use both lfs/ssr allocation */
1261	FS_MODE_LFS,		/* use lfs allocation only */
1262};
1263
1264enum {
1265	WHINT_MODE_OFF,		/* not pass down write hints */
1266	WHINT_MODE_USER,	/* try to pass down hints given by users */
1267	WHINT_MODE_FS,		/* pass down hints with F2FS policy */
1268};
1269
1270enum {
1271	ALLOC_MODE_DEFAULT,	/* stay default */
1272	ALLOC_MODE_REUSE,	/* reuse segments as much as possible */
1273};
1274
1275enum fsync_mode {
1276	FSYNC_MODE_POSIX,	/* fsync follows posix semantics */
1277	FSYNC_MODE_STRICT,	/* fsync behaves in line with ext4 */
1278	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
1279};
1280
1281/*
1282 * this value is set in page as a private data which indicate that
1283 * the page is atomically written, and it is in inmem_pages list.
1284 */
1285#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
1286#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
1287
1288#define IS_ATOMIC_WRITTEN_PAGE(page)			\
1289		(page_private(page) == ATOMIC_WRITTEN_PAGE)
1290#define IS_DUMMY_WRITTEN_PAGE(page)			\
1291		(page_private(page) == DUMMY_WRITTEN_PAGE)
1292
1293#ifdef CONFIG_F2FS_IO_TRACE
1294#define IS_IO_TRACED_PAGE(page)			\
1295		(page_private(page) > 0 &&		\
1296		 page_private(page) < (unsigned long)PID_MAX_LIMIT)
1297#else
1298#define IS_IO_TRACED_PAGE(page) (0)
1299#endif
1300
1301/* For compression */
1302enum compress_algorithm_type {
1303	COMPRESS_LZO,
1304	COMPRESS_LZ4,
1305	COMPRESS_ZSTD,
1306	COMPRESS_LZORLE,
1307	COMPRESS_MAX,
1308};
1309
1310#define COMPRESS_DATA_RESERVED_SIZE		5
1311struct compress_data {
1312	__le32 clen;			/* compressed data size */
1313	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
1314	u8 cdata[];			/* compressed data */
1315};
1316
1317#define COMPRESS_HEADER_SIZE	(sizeof(struct compress_data))
1318
1319#define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000
1320
1321/* compress context */
1322struct compress_ctx {
1323	struct inode *inode;		/* inode the context belong to */
1324	pgoff_t cluster_idx;		/* cluster index number */
1325	unsigned int cluster_size;	/* page count in cluster */
1326	unsigned int log_cluster_size;	/* log of cluster size */
1327	struct page **rpages;		/* pages store raw data in cluster */
1328	unsigned int nr_rpages;		/* total page number in rpages */
1329	struct page **cpages;		/* pages store compressed data in cluster */
1330	unsigned int nr_cpages;		/* total page number in cpages */
1331	void *rbuf;			/* virtual mapped address on rpages */
1332	struct compress_data *cbuf;	/* virtual mapped address on cpages */
1333	size_t rlen;			/* valid data length in rbuf */
1334	size_t clen;			/* valid data length in cbuf */
1335	void *private;			/* payload buffer for specified compression algorithm */
1336	void *private2;			/* extra payload buffer */
1337};
1338
1339/* compress context for write IO path */
1340struct compress_io_ctx {
1341	u32 magic;			/* magic number to indicate page is compressed */
1342	struct inode *inode;		/* inode the context belong to */
1343	struct page **rpages;		/* pages store raw data in cluster */
1344	unsigned int nr_rpages;		/* total page number in rpages */
1345	atomic_t pending_pages;		/* in-flight compressed page count */
1346};
1347
1348/* decompress io context for read IO path */
1349struct decompress_io_ctx {
1350	u32 magic;			/* magic number to indicate page is compressed */
1351	struct inode *inode;		/* inode the context belong to */
1352	pgoff_t cluster_idx;		/* cluster index number */
1353	unsigned int cluster_size;	/* page count in cluster */
1354	unsigned int log_cluster_size;	/* log of cluster size */
1355	struct page **rpages;		/* pages store raw data in cluster */
1356	unsigned int nr_rpages;		/* total page number in rpages */
1357	struct page **cpages;		/* pages store compressed data in cluster */
1358	unsigned int nr_cpages;		/* total page number in cpages */
1359	struct page **tpages;		/* temp pages to pad holes in cluster */
1360	void *rbuf;			/* virtual mapped address on rpages */
1361	struct compress_data *cbuf;	/* virtual mapped address on cpages */
1362	size_t rlen;			/* valid data length in rbuf */
1363	size_t clen;			/* valid data length in cbuf */
1364	atomic_t pending_pages;		/* in-flight compressed page count */
1365	atomic_t verity_pages;		/* in-flight page count for verity */
1366	bool failed;			/* indicate IO error during decompression */
1367	void *private;			/* payload buffer for specified decompression algorithm */
1368	void *private2;			/* extra payload buffer */
1369};
1370
1371#define NULL_CLUSTER			((unsigned int)(~0))
1372#define MIN_COMPRESS_LOG_SIZE		2
1373#define MAX_COMPRESS_LOG_SIZE		8
1374#define MAX_COMPRESS_WINDOW_SIZE(log_size)	((PAGE_SIZE) << (log_size))
1375
1376#ifdef CONFIG_F2FS_GRADING_SSR
1377struct f2fs_hot_cold_params {
1378	unsigned int enable;
1379	unsigned int hot_data_lower_limit;
1380	unsigned int hot_data_waterline;
1381	unsigned int warm_data_lower_limit;
1382	unsigned int warm_data_waterline;
1383	unsigned int hot_node_lower_limit;
1384	unsigned int hot_node_waterline;
1385	unsigned int warm_node_lower_limit;
1386	unsigned int warm_node_waterline;
1387};
1388#endif
1389
1390struct f2fs_sb_info {
1391	struct super_block *sb;			/* pointer to VFS super block */
1392	struct proc_dir_entry *s_proc;		/* proc entry */
1393	struct f2fs_super_block *raw_super;	/* raw super block pointer */
1394	struct rw_semaphore sb_lock;		/* lock for raw super block */
1395	int valid_super_block;			/* valid super block no */
1396	unsigned long s_flag;				/* flags for sbi */
1397	struct mutex writepages;		/* mutex for writepages() */
1398
1399#ifdef CONFIG_BLK_DEV_ZONED
1400	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
1401	unsigned int log_blocks_per_blkz;	/* log2 F2FS blocks per zone */
1402#endif
1403
1404	/* for node-related operations */
1405	struct f2fs_nm_info *nm_info;		/* node manager */
1406	struct inode *node_inode;		/* cache node blocks */
1407
1408	/* for segment-related operations */
1409	struct f2fs_sm_info *sm_info;		/* segment manager */
1410
1411	/* for bio operations */
1412	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
1413	/* keep migration IO order for LFS mode */
1414	struct rw_semaphore io_order_lock;
1415	mempool_t *write_io_dummy;		/* Dummy pages */
1416
1417	/* for checkpoint */
1418	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
1419	int cur_cp_pack;			/* remain current cp pack */
1420	spinlock_t cp_lock;			/* for flag in ckpt */
1421	struct inode *meta_inode;		/* cache meta blocks */
1422	struct mutex cp_mutex;			/* checkpoint procedure lock */
1423	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
1424	struct rw_semaphore node_write;		/* locking node writes */
1425	struct rw_semaphore node_change;	/* locking node change */
1426	wait_queue_head_t cp_wait;
1427	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
1428	long interval_time[MAX_TIME];		/* to store thresholds */
1429
1430	struct inode_management im[MAX_INO_ENTRY];	/* manage inode cache */
1431
1432	spinlock_t fsync_node_lock;		/* for node entry lock */
1433	struct list_head fsync_node_list;	/* node list head */
1434	unsigned int fsync_seg_id;		/* sequence id */
1435	unsigned int fsync_node_num;		/* number of node entries */
1436
1437	/* for orphan inode, use 0'th array */
1438	unsigned int max_orphans;		/* max orphan inodes */
1439
1440	/* for inode management */
1441	struct list_head inode_list[NR_INODE_TYPE];	/* dirty inode list */
1442	spinlock_t inode_lock[NR_INODE_TYPE];	/* for dirty inode list lock */
1443	struct mutex flush_lock;		/* for flush exclusion */
1444
1445	/* for extent tree cache */
1446	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
1447	struct mutex extent_tree_lock;	/* locking extent radix tree */
1448	struct list_head extent_list;		/* lru list for shrinker */
1449	spinlock_t extent_lock;			/* locking extent lru list */
1450	atomic_t total_ext_tree;		/* extent tree count */
1451	struct list_head zombie_list;		/* extent zombie tree list */
1452	atomic_t total_zombie_tree;		/* extent zombie tree count */
1453	atomic_t total_ext_node;		/* extent info count */
1454
1455	/* basic filesystem units */
1456	unsigned int log_sectors_per_block;	/* log2 sectors per block */
1457	unsigned int log_blocksize;		/* log2 block size */
1458	unsigned int blocksize;			/* block size */
1459	unsigned int root_ino_num;		/* root inode number*/
1460	unsigned int node_ino_num;		/* node inode number*/
1461	unsigned int meta_ino_num;		/* meta inode number*/
1462	unsigned int log_blocks_per_seg;	/* log2 blocks per segment */
1463	unsigned int blocks_per_seg;		/* blocks per segment */
1464	unsigned int unusable_blocks_per_sec;	/* unusable blocks per section */
1465	unsigned int segs_per_sec;		/* segments per section */
1466	unsigned int secs_per_zone;		/* sections per zone */
1467	unsigned int total_sections;		/* total section count */
1468	unsigned int total_node_count;		/* total node block count */
1469	unsigned int total_valid_node_count;	/* valid node block count */
1470	loff_t max_file_blocks;			/* max block index of file */
1471	int dir_level;				/* directory level */
1472	int readdir_ra;				/* readahead inode in readdir */
1473
1474	block_t user_block_count;		/* # of user blocks */
1475	block_t total_valid_block_count;	/* # of valid blocks */
1476	block_t discard_blks;			/* discard command candidats */
1477	block_t last_valid_block_count;		/* for recovery */
1478	block_t reserved_blocks;		/* configurable reserved blocks */
1479	block_t current_reserved_blocks;	/* current reserved blocks */
1480
1481	/* Additional tracking for no checkpoint mode */
1482	block_t unusable_block_count;		/* # of blocks saved by last cp */
1483
1484	unsigned int nquota_files;		/* # of quota sysfile */
1485	struct rw_semaphore quota_sem;		/* blocking cp for flags */
1486
1487	/* # of pages, see count_type */
1488	atomic_t nr_pages[NR_COUNT_TYPE];
1489	/* # of allocated blocks */
1490	struct percpu_counter alloc_valid_block_count;
1491
1492	/* writeback control */
1493	atomic_t wb_sync_req[META];	/* count # of WB_SYNC threads */
1494
1495	/* valid inode count */
1496	struct percpu_counter total_valid_inode_count;
1497
1498	struct f2fs_mount_info mount_opt;	/* mount options */
1499
1500	/* for cleaning operations */
1501	struct rw_semaphore gc_lock;		/*
1502						 * semaphore for GC, avoid
1503						 * race between GC and GC or CP
1504						 */
1505	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
1506	struct atgc_management am;		/* atgc management */
1507	unsigned int cur_victim_sec;		/* current victim section num */
1508	unsigned int gc_mode;			/* current GC state */
1509	unsigned int next_victim_seg[2];	/* next segment in victim section */
1510
1511	/* for skip statistic */
1512	unsigned int atomic_files;		/* # of opened atomic file */
1513	unsigned long long skipped_atomic_files[2];	/* FG_GC and BG_GC */
1514	unsigned long long skipped_gc_rwsem;		/* FG_GC only */
1515
1516	/* threshold for gc trials on pinned files */
1517	u64 gc_pin_file_threshold;
1518	struct rw_semaphore pin_sem;
1519
1520	/* maximum # of trials to find a victim segment for SSR and GC */
1521	unsigned int max_victim_search;
1522	/* migration granularity of garbage collection, unit: segment */
1523	unsigned int migration_granularity;
1524
1525	/*
1526	 * for stat information.
1527	 * one is for the LFS mode, and the other is for the SSR mode.
1528	 */
1529#ifdef CONFIG_F2FS_STAT_FS
1530	struct f2fs_stat_info *stat_info;	/* FS status information */
1531	atomic_t meta_count[META_MAX];		/* # of meta blocks */
1532	unsigned int segment_count[2];		/* # of allocated segments */
1533	unsigned int block_count[2];		/* # of allocated blocks */
1534	atomic_t inplace_count;		/* # of inplace update */
1535	atomic64_t total_hit_ext;		/* # of lookup extent cache */
1536	atomic64_t read_hit_rbtree;		/* # of hit rbtree extent node */
1537	atomic64_t read_hit_largest;		/* # of hit largest extent node */
1538	atomic64_t read_hit_cached;		/* # of hit cached extent node */
1539	atomic_t inline_xattr;			/* # of inline_xattr inodes */
1540	atomic_t inline_inode;			/* # of inline_data inodes */
1541	atomic_t inline_dir;			/* # of inline_dentry inodes */
1542	atomic_t compr_inode;			/* # of compressed inodes */
1543	atomic64_t compr_blocks;		/* # of compressed blocks */
1544	atomic_t vw_cnt;			/* # of volatile writes */
1545	atomic_t max_aw_cnt;			/* max # of atomic writes */
1546	atomic_t max_vw_cnt;			/* max # of volatile writes */
1547	unsigned int io_skip_bggc;		/* skip background gc for in-flight IO */
1548	unsigned int other_skip_bggc;		/* skip background gc for other reasons */
1549	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
1550#endif
1551	spinlock_t stat_lock;			/* lock for stat operations */
1552
1553	/* For app/fs IO statistics */
1554	spinlock_t iostat_lock;
1555	unsigned long long rw_iostat[NR_IO_TYPE];
1556	unsigned long long prev_rw_iostat[NR_IO_TYPE];
1557	bool iostat_enable;
1558	unsigned long iostat_next_period;
1559	unsigned int iostat_period_ms;
1560
1561	/* to attach REQ_META|REQ_FUA flags */
1562	unsigned int data_io_flag;
1563	unsigned int node_io_flag;
1564
1565	/* For sysfs suppport */
1566	struct kobject s_kobj;
1567	struct completion s_kobj_unregister;
1568
1569	/* For shrinker support */
1570	struct list_head s_list;
1571	int s_ndevs;				/* number of devices */
1572	struct f2fs_dev_info *devs;		/* for device list */
1573	unsigned int dirty_device;		/* for checkpoint data flush */
1574	spinlock_t dev_lock;			/* protect dirty_device */
1575	struct mutex umount_mutex;
1576	unsigned int shrinker_run_no;
1577
1578	/* For write statistics */
1579	u64 sectors_written_start;
1580	u64 kbytes_written;
1581
1582	/* Reference to checksum algorithm driver via cryptoapi */
1583	struct crypto_shash *s_chksum_driver;
1584
1585	/* Precomputed FS UUID checksum for seeding other checksums */
1586	__u32 s_chksum_seed;
1587
1588	struct workqueue_struct *post_read_wq;	/* post read workqueue */
1589
1590	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
1591	unsigned int inline_xattr_slab_size;	/* default inline xattr slab size */
1592
1593#ifdef CONFIG_F2FS_FS_COMPRESSION
1594	struct kmem_cache *page_array_slab;	/* page array entry */
1595	unsigned int page_array_slab_size;	/* default page array slab size */
1596#endif
1597
1598#ifdef CONFIG_F2FS_GRADING_SSR
1599	struct f2fs_hot_cold_params hot_cold_params;
1600#endif
1601};
1602
1603struct f2fs_private_dio {
1604	struct inode *inode;
1605	void *orig_private;
1606	bio_end_io_t *orig_end_io;
1607	bool write;
1608};
1609
1610#ifdef CONFIG_F2FS_FAULT_INJECTION
1611#define f2fs_show_injection_info(sbi, type)					\
1612	printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n",	\
1613		KERN_INFO, sbi->sb->s_id,				\
1614		f2fs_fault_name[type],					\
1615		__func__, __builtin_return_address(0))
1616static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
1617{
1618	struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
1619
1620	if (!ffi->inject_rate)
1621		return false;
1622
1623	if (!IS_FAULT_SET(ffi, type))
1624		return false;
1625
1626	atomic_inc(&ffi->inject_ops);
1627	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
1628		atomic_set(&ffi->inject_ops, 0);
1629		return true;
1630	}
1631	return false;
1632}
1633#else
1634#define f2fs_show_injection_info(sbi, type) do { } while (0)
1635static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
1636{
1637	return false;
1638}
1639#endif
1640
1641/*
1642 * Test if the mounted volume is a multi-device volume.
1643 *   - For a single regular disk volume, sbi->s_ndevs is 0.
1644 *   - For a single zoned disk volume, sbi->s_ndevs is 1.
1645 *   - For a multi-device volume, sbi->s_ndevs is always 2 or more.
1646 */
1647static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi)
1648{
1649	return sbi->s_ndevs > 1;
1650}
1651
1652/* For write statistics. Suppose sector size is 512 bytes,
1653 * and the return value is in kbytes. s is of struct f2fs_sb_info.
1654 */
1655#define BD_PART_WRITTEN(s)						 \
1656(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
1657		(s)->sectors_written_start) >> 1)
1658
1659static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
1660{
1661	unsigned long now = jiffies;
1662
1663	sbi->last_time[type] = now;
1664
1665	/* DISCARD_TIME and GC_TIME are based on REQ_TIME */
1666	if (type == REQ_TIME) {
1667		sbi->last_time[DISCARD_TIME] = now;
1668		sbi->last_time[GC_TIME] = now;
1669	}
1670}
1671
1672static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
1673{
1674	unsigned long interval = sbi->interval_time[type] * HZ;
1675
1676	return time_after(jiffies, sbi->last_time[type] + interval);
1677}
1678
1679static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi,
1680						int type)
1681{
1682	unsigned long interval = sbi->interval_time[type] * HZ;
1683	unsigned int wait_ms = 0;
1684	long delta;
1685
1686	delta = (sbi->last_time[type] + interval) - jiffies;
1687	if (delta > 0)
1688		wait_ms = jiffies_to_msecs(delta);
1689
1690	return wait_ms;
1691}
1692
1693/*
1694 * Inline functions
1695 */
1696static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
1697			      const void *address, unsigned int length)
1698{
1699	struct {
1700		struct shash_desc shash;
1701		char ctx[4];
1702	} desc;
1703	int err;
1704
1705	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
1706
1707	desc.shash.tfm = sbi->s_chksum_driver;
1708	*(u32 *)desc.ctx = crc;
1709
1710	err = crypto_shash_update(&desc.shash, address, length);
1711	BUG_ON(err);
1712
1713	return *(u32 *)desc.ctx;
1714}
1715
1716static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
1717			   unsigned int length)
1718{
1719	return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length);
1720}
1721
1722static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
1723				  void *buf, size_t buf_size)
1724{
1725	return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
1726}
1727
1728static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc,
1729			      const void *address, unsigned int length)
1730{
1731	return __f2fs_crc32(sbi, crc, address, length);
1732}
1733
1734static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
1735{
1736	return container_of(inode, struct f2fs_inode_info, vfs_inode);
1737}
1738
1739static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb)
1740{
1741	return sb->s_fs_info;
1742}
1743
1744static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode)
1745{
1746	return F2FS_SB(inode->i_sb);
1747}
1748
1749static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
1750{
1751	return F2FS_I_SB(mapping->host);
1752}
1753
1754static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
1755{
1756	return F2FS_M_SB(page_file_mapping(page));
1757}
1758
1759static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
1760{
1761	return (struct f2fs_super_block *)(sbi->raw_super);
1762}
1763
1764static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
1765{
1766	return (struct f2fs_checkpoint *)(sbi->ckpt);
1767}
1768
1769static inline struct f2fs_node *F2FS_NODE(struct page *page)
1770{
1771	return (struct f2fs_node *)page_address(page);
1772}
1773
1774static inline struct f2fs_inode *F2FS_INODE(struct page *page)
1775{
1776	return &((struct f2fs_node *)page_address(page))->i;
1777}
1778
1779static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
1780{
1781	return (struct f2fs_nm_info *)(sbi->nm_info);
1782}
1783
1784static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi)
1785{
1786	return (struct f2fs_sm_info *)(sbi->sm_info);
1787}
1788
1789static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi)
1790{
1791	return (struct sit_info *)(SM_I(sbi)->sit_info);
1792}
1793
1794static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi)
1795{
1796	return (struct free_segmap_info *)(SM_I(sbi)->free_info);
1797}
1798
1799static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi)
1800{
1801	return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info);
1802}
1803
1804static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi)
1805{
1806	return sbi->meta_inode->i_mapping;
1807}
1808
1809static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi)
1810{
1811	return sbi->node_inode->i_mapping;
1812}
1813
1814static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
1815{
1816	return test_bit(type, &sbi->s_flag);
1817}
1818
1819static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1820{
1821	set_bit(type, &sbi->s_flag);
1822}
1823
1824static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
1825{
1826	clear_bit(type, &sbi->s_flag);
1827}
1828
1829static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
1830{
1831	return le64_to_cpu(cp->checkpoint_ver);
1832}
1833
1834static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type)
1835{
1836	if (type < F2FS_MAX_QUOTAS)
1837		return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]);
1838	return 0;
1839}
1840
1841static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
1842{
1843	size_t crc_offset = le32_to_cpu(cp->checksum_offset);
1844	return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
1845}
1846
1847static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1848{
1849	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1850
1851	return ckpt_flags & f;
1852}
1853
1854static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1855{
1856	return __is_set_ckpt_flags(F2FS_CKPT(sbi), f);
1857}
1858
1859static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1860{
1861	unsigned int ckpt_flags;
1862
1863	ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1864	ckpt_flags |= f;
1865	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
1866}
1867
1868static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1869{
1870	unsigned long flags;
1871
1872	spin_lock_irqsave(&sbi->cp_lock, flags);
1873	__set_ckpt_flags(F2FS_CKPT(sbi), f);
1874	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1875}
1876
1877static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
1878{
1879	unsigned int ckpt_flags;
1880
1881	ckpt_flags = le32_to_cpu(cp->ckpt_flags);
1882	ckpt_flags &= (~f);
1883	cp->ckpt_flags = cpu_to_le32(ckpt_flags);
1884}
1885
1886static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
1887{
1888	unsigned long flags;
1889
1890	spin_lock_irqsave(&sbi->cp_lock, flags);
1891	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
1892	spin_unlock_irqrestore(&sbi->cp_lock, flags);
1893}
1894
1895static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
1896{
1897	unsigned long flags;
1898	unsigned char *nat_bits;
1899
1900	/*
1901	 * In order to re-enable nat_bits we need to call fsck.f2fs by
1902	 * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
1903	 * so let's rely on regular fsck or unclean shutdown.
1904	 */
1905
1906	if (lock)
1907		spin_lock_irqsave(&sbi->cp_lock, flags);
1908	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
1909	nat_bits = NM_I(sbi)->nat_bits;
1910	NM_I(sbi)->nat_bits = NULL;
1911	if (lock)
1912		spin_unlock_irqrestore(&sbi->cp_lock, flags);
1913
1914	kvfree(nat_bits);
1915}
1916
1917static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
1918					struct cp_control *cpc)
1919{
1920	bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
1921
1922	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
1923}
1924
1925static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
1926{
1927	down_read(&sbi->cp_rwsem);
1928}
1929
1930static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
1931{
1932	return down_read_trylock(&sbi->cp_rwsem);
1933}
1934
1935static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
1936{
1937	up_read(&sbi->cp_rwsem);
1938}
1939
1940static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
1941{
1942	down_write(&sbi->cp_rwsem);
1943}
1944
1945static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
1946{
1947	up_write(&sbi->cp_rwsem);
1948}
1949
1950static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
1951{
1952	int reason = CP_SYNC;
1953
1954	if (test_opt(sbi, FASTBOOT))
1955		reason = CP_FASTBOOT;
1956	if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
1957		reason = CP_UMOUNT;
1958	return reason;
1959}
1960
1961static inline bool __remain_node_summaries(int reason)
1962{
1963	return (reason & (CP_UMOUNT | CP_FASTBOOT));
1964}
1965
1966static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
1967{
1968	return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
1969			is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
1970}
1971
1972/*
1973 * Check whether the inode has blocks or not
1974 */
1975static inline int F2FS_HAS_BLOCKS(struct inode *inode)
1976{
1977	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;
1978
1979	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
1980}
1981
1982static inline bool f2fs_has_xattr_block(unsigned int ofs)
1983{
1984	return ofs == XATTR_NODE_OFFSET;
1985}
1986
1987static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
1988					struct inode *inode, bool cap)
1989{
1990	if (!inode)
1991		return true;
1992	if (!test_opt(sbi, RESERVE_ROOT))
1993		return false;
1994	if (IS_NOQUOTA(inode))
1995		return true;
1996	if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid()))
1997		return true;
1998	if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) &&
1999					in_group_p(F2FS_OPTION(sbi).s_resgid))
2000		return true;
2001	if (cap && capable(CAP_SYS_RESOURCE))
2002		return true;
2003	return false;
2004}
2005
2006static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
2007static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
2008				 struct inode *inode, blkcnt_t *count)
2009{
2010	blkcnt_t diff = 0, release = 0;
2011	block_t avail_user_block_count;
2012	int ret;
2013
2014	ret = dquot_reserve_block(inode, *count);
2015	if (ret)
2016		return ret;
2017
2018	if (time_to_inject(sbi, FAULT_BLOCK)) {
2019		f2fs_show_injection_info(sbi, FAULT_BLOCK);
2020		release = *count;
2021		goto release_quota;
2022	}
2023
2024	/*
2025	 * let's increase this in prior to actual block count change in order
2026	 * for f2fs_sync_file to avoid data races when deciding checkpoint.
2027	 */
2028	percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
2029
2030	spin_lock(&sbi->stat_lock);
2031	sbi->total_valid_block_count += (block_t)(*count);
2032	avail_user_block_count = sbi->user_block_count -
2033					sbi->current_reserved_blocks;
2034
2035	if (!__allow_reserved_blocks(sbi, inode, true))
2036		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
2037
2038	if (F2FS_IO_ALIGNED(sbi))
2039		avail_user_block_count -= sbi->blocks_per_seg *
2040				SM_I(sbi)->additional_reserved_segments;
2041
2042	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
2043		if (avail_user_block_count > sbi->unusable_block_count)
2044			avail_user_block_count -= sbi->unusable_block_count;
2045		else
2046			avail_user_block_count = 0;
2047	}
2048	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
2049		diff = sbi->total_valid_block_count - avail_user_block_count;
2050		if (diff > *count)
2051			diff = *count;
2052		*count -= diff;
2053		release = diff;
2054		sbi->total_valid_block_count -= diff;
2055		if (!*count) {
2056			spin_unlock(&sbi->stat_lock);
2057			goto enospc;
2058		}
2059	}
2060	spin_unlock(&sbi->stat_lock);
2061
2062	if (unlikely(release)) {
2063		percpu_counter_sub(&sbi->alloc_valid_block_count, release);
2064		dquot_release_reservation_block(inode, release);
2065	}
2066	f2fs_i_blocks_write(inode, *count, true, true);
2067	return 0;
2068
2069enospc:
2070	percpu_counter_sub(&sbi->alloc_valid_block_count, release);
2071release_quota:
2072	dquot_release_reservation_block(inode, release);
2073	return -ENOSPC;
2074}
2075
2076__printf(2, 3)
2077void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...);
2078
2079#define f2fs_err(sbi, fmt, ...)						\
2080	f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__)
2081#define f2fs_warn(sbi, fmt, ...)					\
2082	f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__)
2083#define f2fs_notice(sbi, fmt, ...)					\
2084	f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__)
2085#define f2fs_info(sbi, fmt, ...)					\
2086	f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__)
2087#define f2fs_debug(sbi, fmt, ...)					\
2088	f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__)
2089
2090static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
2091						struct inode *inode,
2092						block_t count)
2093{
2094	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
2095
2096	spin_lock(&sbi->stat_lock);
2097	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
2098	sbi->total_valid_block_count -= (block_t)count;
2099	if (sbi->reserved_blocks &&
2100		sbi->current_reserved_blocks < sbi->reserved_blocks)
2101		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
2102					sbi->current_reserved_blocks + count);
2103	spin_unlock(&sbi->stat_lock);
2104	if (unlikely(inode->i_blocks < sectors)) {
2105		f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu",
2106			  inode->i_ino,
2107			  (unsigned long long)inode->i_blocks,
2108			  (unsigned long long)sectors);
2109		set_sbi_flag(sbi, SBI_NEED_FSCK);
2110		return;
2111	}
2112	f2fs_i_blocks_write(inode, count, false, true);
2113}
2114
2115static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
2116{
2117	atomic_inc(&sbi->nr_pages[count_type]);
2118
2119	if (count_type == F2FS_DIRTY_DENTS ||
2120			count_type == F2FS_DIRTY_NODES ||
2121			count_type == F2FS_DIRTY_META ||
2122			count_type == F2FS_DIRTY_QDATA ||
2123			count_type == F2FS_DIRTY_IMETA)
2124		set_sbi_flag(sbi, SBI_IS_DIRTY);
2125}
2126
2127static inline void inode_inc_dirty_pages(struct inode *inode)
2128{
2129	atomic_inc(&F2FS_I(inode)->dirty_pages);
2130	inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
2131				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
2132	if (IS_NOQUOTA(inode))
2133		inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
2134}
2135
2136static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
2137{
2138	atomic_dec(&sbi->nr_pages[count_type]);
2139}
2140
2141static inline void inode_dec_dirty_pages(struct inode *inode)
2142{
2143	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
2144			!S_ISLNK(inode->i_mode))
2145		return;
2146
2147	atomic_dec(&F2FS_I(inode)->dirty_pages);
2148	dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
2149				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
2150	if (IS_NOQUOTA(inode))
2151		dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA);
2152}
2153
2154static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
2155{
2156	return atomic_read(&sbi->nr_pages[count_type]);
2157}
2158
2159static inline int get_dirty_pages(struct inode *inode)
2160{
2161	return atomic_read(&F2FS_I(inode)->dirty_pages);
2162}
2163
2164static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
2165{
2166	unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
2167	unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
2168						sbi->log_blocks_per_seg;
2169
2170	return segs / sbi->segs_per_sec;
2171}
2172
2173static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
2174{
2175	return sbi->total_valid_block_count;
2176}
2177
2178static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
2179{
2180	return sbi->discard_blks;
2181}
2182
2183static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
2184{
2185	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
2186
2187	/* return NAT or SIT bitmap */
2188	if (flag == NAT_BITMAP)
2189		return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
2190	else if (flag == SIT_BITMAP)
2191		return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
2192
2193	return 0;
2194}
2195
2196static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
2197{
2198	return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
2199}
2200
2201static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
2202{
2203	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
2204	int offset;
2205
2206	if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) {
2207		offset = (flag == SIT_BITMAP) ?
2208			le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0;
2209		/*
2210		 * if large_nat_bitmap feature is enabled, leave checksum
2211		 * protection for all nat/sit bitmaps.
2212		 */
2213		return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32);
2214	}
2215
2216	if (__cp_payload(sbi) > 0) {
2217		if (flag == NAT_BITMAP)
2218			return &ckpt->sit_nat_version_bitmap;
2219		else
2220			return (unsigned char *)ckpt + F2FS_BLKSIZE;
2221	} else {
2222		offset = (flag == NAT_BITMAP) ?
2223			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
2224		return &ckpt->sit_nat_version_bitmap + offset;
2225	}
2226}
2227
2228static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
2229{
2230	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
2231
2232	if (sbi->cur_cp_pack == 2)
2233		start_addr += sbi->blocks_per_seg;
2234	return start_addr;
2235}
2236
2237static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
2238{
2239	block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
2240
2241	if (sbi->cur_cp_pack == 1)
2242		start_addr += sbi->blocks_per_seg;
2243	return start_addr;
2244}
2245
2246static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
2247{
2248	sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
2249}
2250
2251static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
2252{
2253	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
2254}
2255
2256static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
2257					struct inode *inode, bool is_inode)
2258{
2259	block_t	valid_block_count;
2260	unsigned int valid_node_count, user_block_count;
2261	int err;
2262
2263	if (is_inode) {
2264		if (inode) {
2265			err = dquot_alloc_inode(inode);
2266			if (err)
2267				return err;
2268		}
2269	} else {
2270		err = dquot_reserve_block(inode, 1);
2271		if (err)
2272			return err;
2273	}
2274
2275	if (time_to_inject(sbi, FAULT_BLOCK)) {
2276		f2fs_show_injection_info(sbi, FAULT_BLOCK);
2277		goto enospc;
2278	}
2279
2280	spin_lock(&sbi->stat_lock);
2281
2282	valid_block_count = sbi->total_valid_block_count +
2283					sbi->current_reserved_blocks + 1;
2284
2285	if (!__allow_reserved_blocks(sbi, inode, false))
2286		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
2287
2288	if (F2FS_IO_ALIGNED(sbi))
2289		valid_block_count += sbi->blocks_per_seg *
2290				SM_I(sbi)->additional_reserved_segments;
2291
2292	user_block_count = sbi->user_block_count;
2293	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
2294		user_block_count -= sbi->unusable_block_count;
2295
2296	if (unlikely(valid_block_count > user_block_count)) {
2297		spin_unlock(&sbi->stat_lock);
2298		goto enospc;
2299	}
2300
2301	valid_node_count = sbi->total_valid_node_count + 1;
2302	if (unlikely(valid_node_count > sbi->total_node_count)) {
2303		spin_unlock(&sbi->stat_lock);
2304		goto enospc;
2305	}
2306
2307	sbi->total_valid_node_count++;
2308	sbi->total_valid_block_count++;
2309	spin_unlock(&sbi->stat_lock);
2310
2311	if (inode) {
2312		if (is_inode)
2313			f2fs_mark_inode_dirty_sync(inode, true);
2314		else
2315			f2fs_i_blocks_write(inode, 1, true, true);
2316	}
2317
2318	percpu_counter_inc(&sbi->alloc_valid_block_count);
2319	return 0;
2320
2321enospc:
2322	if (is_inode) {
2323		if (inode)
2324			dquot_free_inode(inode);
2325	} else {
2326		dquot_release_reservation_block(inode, 1);
2327	}
2328	return -ENOSPC;
2329}
2330
2331static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
2332					struct inode *inode, bool is_inode)
2333{
2334	spin_lock(&sbi->stat_lock);
2335
2336	if (unlikely(!sbi->total_valid_block_count ||
2337			!sbi->total_valid_node_count)) {
2338		f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u",
2339			  sbi->total_valid_block_count,
2340			  sbi->total_valid_node_count);
2341		set_sbi_flag(sbi, SBI_NEED_FSCK);
2342	} else {
2343		sbi->total_valid_block_count--;
2344		sbi->total_valid_node_count--;
2345	}
2346
2347	if (sbi->reserved_blocks &&
2348		sbi->current_reserved_blocks < sbi->reserved_blocks)
2349		sbi->current_reserved_blocks++;
2350
2351	spin_unlock(&sbi->stat_lock);
2352
2353	if (is_inode) {
2354		dquot_free_inode(inode);
2355	} else {
2356		if (unlikely(inode->i_blocks == 0)) {
2357			f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu",
2358				  inode->i_ino,
2359				  (unsigned long long)inode->i_blocks);
2360			set_sbi_flag(sbi, SBI_NEED_FSCK);
2361			return;
2362		}
2363		f2fs_i_blocks_write(inode, 1, false, true);
2364	}
2365}
2366
2367static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
2368{
2369	return sbi->total_valid_node_count;
2370}
2371
2372static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
2373{
2374	percpu_counter_inc(&sbi->total_valid_inode_count);
2375}
2376
2377static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
2378{
2379	percpu_counter_dec(&sbi->total_valid_inode_count);
2380}
2381
2382static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
2383{
2384	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
2385}
2386
2387static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
2388						pgoff_t index, bool for_write)
2389{
2390	struct page *page;
2391
2392	if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
2393		if (!for_write)
2394			page = find_get_page_flags(mapping, index,
2395							FGP_LOCK | FGP_ACCESSED);
2396		else
2397			page = find_lock_page(mapping, index);
2398		if (page)
2399			return page;
2400
2401		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
2402			f2fs_show_injection_info(F2FS_M_SB(mapping),
2403							FAULT_PAGE_ALLOC);
2404			return NULL;
2405		}
2406	}
2407
2408	if (!for_write)
2409		return grab_cache_page(mapping, index);
2410	return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
2411}
2412
2413static inline struct page *f2fs_pagecache_get_page(
2414				struct address_space *mapping, pgoff_t index,
2415				int fgp_flags, gfp_t gfp_mask)
2416{
2417	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
2418		f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
2419		return NULL;
2420	}
2421
2422	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
2423}
2424
2425static inline void f2fs_copy_page(struct page *src, struct page *dst)
2426{
2427	char *src_kaddr = kmap(src);
2428	char *dst_kaddr = kmap(dst);
2429
2430	memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
2431	kunmap(dst);
2432	kunmap(src);
2433}
2434
2435static inline void f2fs_put_page(struct page *page, int unlock)
2436{
2437	if (!page)
2438		return;
2439
2440	if (unlock) {
2441		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
2442		unlock_page(page);
2443	}
2444	put_page(page);
2445}
2446
2447static inline void f2fs_put_dnode(struct dnode_of_data *dn)
2448{
2449	if (dn->node_page)
2450		f2fs_put_page(dn->node_page, 1);
2451	if (dn->inode_page && dn->node_page != dn->inode_page)
2452		f2fs_put_page(dn->inode_page, 0);
2453	dn->node_page = NULL;
2454	dn->inode_page = NULL;
2455}
2456
2457static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
2458					size_t size)
2459{
2460	return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL);
2461}
2462
2463static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
2464						gfp_t flags)
2465{
2466	void *entry;
2467
2468	entry = kmem_cache_alloc(cachep, flags);
2469	if (!entry)
2470		entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
2471	return entry;
2472}
2473
2474static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
2475{
2476	if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
2477		get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) ||
2478		get_pages(sbi, F2FS_WB_CP_DATA) ||
2479		get_pages(sbi, F2FS_DIO_READ) ||
2480		get_pages(sbi, F2FS_DIO_WRITE))
2481		return true;
2482
2483	if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info &&
2484			atomic_read(&SM_I(sbi)->dcc_info->queued_discard))
2485		return true;
2486
2487	if (SM_I(sbi) && SM_I(sbi)->fcc_info &&
2488			atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
2489		return true;
2490	return false;
2491}
2492
2493static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
2494{
2495	if (sbi->gc_mode == GC_URGENT_HIGH)
2496		return true;
2497
2498	if (is_inflight_io(sbi, type))
2499		return false;
2500
2501	if (sbi->gc_mode == GC_URGENT_LOW &&
2502			(type == DISCARD_TIME || type == GC_TIME))
2503		return true;
2504
2505	return f2fs_time_over(sbi, type);
2506}
2507
2508static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
2509				unsigned long index, void *item)
2510{
2511	while (radix_tree_insert(root, index, item))
2512		cond_resched();
2513}
2514
2515#define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)
2516
2517static inline bool IS_INODE(struct page *page)
2518{
2519	struct f2fs_node *p = F2FS_NODE(page);
2520
2521	return RAW_IS_INODE(p);
2522}
2523
2524static inline int offset_in_addr(struct f2fs_inode *i)
2525{
2526	return (i->i_inline & F2FS_EXTRA_ATTR) ?
2527			(le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0;
2528}
2529
2530static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
2531{
2532	return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
2533}
2534
2535static inline int f2fs_has_extra_attr(struct inode *inode);
2536static inline block_t data_blkaddr(struct inode *inode,
2537			struct page *node_page, unsigned int offset)
2538{
2539	struct f2fs_node *raw_node;
2540	__le32 *addr_array;
2541	int base = 0;
2542	bool is_inode = IS_INODE(node_page);
2543
2544	raw_node = F2FS_NODE(node_page);
2545
2546	if (is_inode) {
2547		if (!inode)
2548			/* from GC path only */
2549			base = offset_in_addr(&raw_node->i);
2550		else if (f2fs_has_extra_attr(inode))
2551			base = get_extra_isize(inode);
2552	}
2553
2554	addr_array = blkaddr_in_node(raw_node);
2555	return le32_to_cpu(addr_array[base + offset]);
2556}
2557
2558static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn)
2559{
2560	return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node);
2561}
2562
2563static inline int f2fs_test_bit(unsigned int nr, char *addr)
2564{
2565	int mask;
2566
2567	addr += (nr >> 3);
2568	mask = 1 << (7 - (nr & 0x07));
2569	return mask & *addr;
2570}
2571
2572static inline void f2fs_set_bit(unsigned int nr, char *addr)
2573{
2574	int mask;
2575
2576	addr += (nr >> 3);
2577	mask = 1 << (7 - (nr & 0x07));
2578	*addr |= mask;
2579}
2580
2581static inline void f2fs_clear_bit(unsigned int nr, char *addr)
2582{
2583	int mask;
2584
2585	addr += (nr >> 3);
2586	mask = 1 << (7 - (nr & 0x07));
2587	*addr &= ~mask;
2588}
2589
2590static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
2591{
2592	int mask;
2593	int ret;
2594
2595	addr += (nr >> 3);
2596	mask = 1 << (7 - (nr & 0x07));
2597	ret = mask & *addr;
2598	*addr |= mask;
2599	return ret;
2600}
2601
2602static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
2603{
2604	int mask;
2605	int ret;
2606
2607	addr += (nr >> 3);
2608	mask = 1 << (7 - (nr & 0x07));
2609	ret = mask & *addr;
2610	*addr &= ~mask;
2611	return ret;
2612}
2613
2614static inline void f2fs_change_bit(unsigned int nr, char *addr)
2615{
2616	int mask;
2617
2618	addr += (nr >> 3);
2619	mask = 1 << (7 - (nr & 0x07));
2620	*addr ^= mask;
2621}
2622
2623/*
2624 * On-disk inode flags (f2fs_inode::i_flags)
2625 */
2626#define F2FS_COMPR_FL			0x00000004 /* Compress file */
2627#define F2FS_SYNC_FL			0x00000008 /* Synchronous updates */
2628#define F2FS_IMMUTABLE_FL		0x00000010 /* Immutable file */
2629#define F2FS_APPEND_FL			0x00000020 /* writes to file may only append */
2630#define F2FS_NODUMP_FL			0x00000040 /* do not dump file */
2631#define F2FS_NOATIME_FL			0x00000080 /* do not update atime */
2632#define F2FS_NOCOMP_FL			0x00000400 /* Don't compress */
2633#define F2FS_INDEX_FL			0x00001000 /* hash-indexed directory */
2634#define F2FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
2635#define F2FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
2636#define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
2637
2638/* Flags that should be inherited by new inodes from their parent. */
2639#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
2640			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
2641			   F2FS_CASEFOLD_FL | F2FS_COMPR_FL | F2FS_NOCOMP_FL)
2642
2643/* Flags that are appropriate for regular files (all but dir-specific ones). */
2644#define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
2645				F2FS_CASEFOLD_FL))
2646
2647/* Flags that are appropriate for non-directories/regular files. */
2648#define F2FS_OTHER_FLMASK	(F2FS_NODUMP_FL | F2FS_NOATIME_FL)
2649
2650static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
2651{
2652	if (S_ISDIR(mode))
2653		return flags;
2654	else if (S_ISREG(mode))
2655		return flags & F2FS_REG_FLMASK;
2656	else
2657		return flags & F2FS_OTHER_FLMASK;
2658}
2659
2660static inline void __mark_inode_dirty_flag(struct inode *inode,
2661						int flag, bool set)
2662{
2663	switch (flag) {
2664	case FI_INLINE_XATTR:
2665	case FI_INLINE_DATA:
2666	case FI_INLINE_DENTRY:
2667	case FI_NEW_INODE:
2668		if (set)
2669			return;
2670		fallthrough;
2671	case FI_DATA_EXIST:
2672	case FI_INLINE_DOTS:
2673	case FI_PIN_FILE:
2674		f2fs_mark_inode_dirty_sync(inode, true);
2675	}
2676}
2677
2678static inline void set_inode_flag(struct inode *inode, int flag)
2679{
2680	set_bit(flag, F2FS_I(inode)->flags);
2681	__mark_inode_dirty_flag(inode, flag, true);
2682}
2683
2684static inline int is_inode_flag_set(struct inode *inode, int flag)
2685{
2686	return test_bit(flag, F2FS_I(inode)->flags);
2687}
2688
2689static inline void clear_inode_flag(struct inode *inode, int flag)
2690{
2691	clear_bit(flag, F2FS_I(inode)->flags);
2692	__mark_inode_dirty_flag(inode, flag, false);
2693}
2694
2695static inline bool f2fs_verity_in_progress(struct inode *inode)
2696{
2697	return IS_ENABLED(CONFIG_FS_VERITY) &&
2698	       is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS);
2699}
2700
2701static inline void set_acl_inode(struct inode *inode, umode_t mode)
2702{
2703	F2FS_I(inode)->i_acl_mode = mode;
2704	set_inode_flag(inode, FI_ACL_MODE);
2705	f2fs_mark_inode_dirty_sync(inode, false);
2706}
2707
2708static inline void f2fs_i_links_write(struct inode *inode, bool inc)
2709{
2710	if (inc)
2711		inc_nlink(inode);
2712	else
2713		drop_nlink(inode);
2714	f2fs_mark_inode_dirty_sync(inode, true);
2715}
2716
2717static inline void f2fs_i_blocks_write(struct inode *inode,
2718					block_t diff, bool add, bool claim)
2719{
2720	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
2721	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
2722
2723	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
2724	if (add) {
2725		if (claim)
2726			dquot_claim_block(inode, diff);
2727		else
2728			dquot_alloc_block_nofail(inode, diff);
2729	} else {
2730		dquot_free_block(inode, diff);
2731	}
2732
2733	f2fs_mark_inode_dirty_sync(inode, true);
2734	if (clean || recover)
2735		set_inode_flag(inode, FI_AUTO_RECOVER);
2736}
2737
2738static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
2739{
2740	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
2741	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
2742
2743	if (i_size_read(inode) == i_size)
2744		return;
2745
2746	i_size_write(inode, i_size);
2747	f2fs_mark_inode_dirty_sync(inode, true);
2748	if (clean || recover)
2749		set_inode_flag(inode, FI_AUTO_RECOVER);
2750}
2751
2752static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
2753{
2754	F2FS_I(inode)->i_current_depth = depth;
2755	f2fs_mark_inode_dirty_sync(inode, true);
2756}
2757
2758static inline void f2fs_i_gc_failures_write(struct inode *inode,
2759					unsigned int count)
2760{
2761	F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
2762	f2fs_mark_inode_dirty_sync(inode, true);
2763}
2764
2765static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
2766{
2767	F2FS_I(inode)->i_xattr_nid = xnid;
2768	f2fs_mark_inode_dirty_sync(inode, true);
2769}
2770
2771static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
2772{
2773	F2FS_I(inode)->i_pino = pino;
2774	f2fs_mark_inode_dirty_sync(inode, true);
2775}
2776
2777static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
2778{
2779	struct f2fs_inode_info *fi = F2FS_I(inode);
2780
2781	if (ri->i_inline & F2FS_INLINE_XATTR)
2782		set_bit(FI_INLINE_XATTR, fi->flags);
2783	if (ri->i_inline & F2FS_INLINE_DATA)
2784		set_bit(FI_INLINE_DATA, fi->flags);
2785	if (ri->i_inline & F2FS_INLINE_DENTRY)
2786		set_bit(FI_INLINE_DENTRY, fi->flags);
2787	if (ri->i_inline & F2FS_DATA_EXIST)
2788		set_bit(FI_DATA_EXIST, fi->flags);
2789	if (ri->i_inline & F2FS_INLINE_DOTS)
2790		set_bit(FI_INLINE_DOTS, fi->flags);
2791	if (ri->i_inline & F2FS_EXTRA_ATTR)
2792		set_bit(FI_EXTRA_ATTR, fi->flags);
2793	if (ri->i_inline & F2FS_PIN_FILE)
2794		set_bit(FI_PIN_FILE, fi->flags);
2795}
2796
2797static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
2798{
2799	ri->i_inline = 0;
2800
2801	if (is_inode_flag_set(inode, FI_INLINE_XATTR))
2802		ri->i_inline |= F2FS_INLINE_XATTR;
2803	if (is_inode_flag_set(inode, FI_INLINE_DATA))
2804		ri->i_inline |= F2FS_INLINE_DATA;
2805	if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
2806		ri->i_inline |= F2FS_INLINE_DENTRY;
2807	if (is_inode_flag_set(inode, FI_DATA_EXIST))
2808		ri->i_inline |= F2FS_DATA_EXIST;
2809	if (is_inode_flag_set(inode, FI_INLINE_DOTS))
2810		ri->i_inline |= F2FS_INLINE_DOTS;
2811	if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
2812		ri->i_inline |= F2FS_EXTRA_ATTR;
2813	if (is_inode_flag_set(inode, FI_PIN_FILE))
2814		ri->i_inline |= F2FS_PIN_FILE;
2815}
2816
2817static inline int f2fs_has_extra_attr(struct inode *inode)
2818{
2819	return is_inode_flag_set(inode, FI_EXTRA_ATTR);
2820}
2821
2822static inline int f2fs_has_inline_xattr(struct inode *inode)
2823{
2824	return is_inode_flag_set(inode, FI_INLINE_XATTR);
2825}
2826
2827static inline int f2fs_compressed_file(struct inode *inode)
2828{
2829	return S_ISREG(inode->i_mode) &&
2830		is_inode_flag_set(inode, FI_COMPRESSED_FILE);
2831}
2832
2833static inline unsigned int addrs_per_inode(struct inode *inode)
2834{
2835	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
2836				get_inline_xattr_addrs(inode);
2837
2838	if (!f2fs_compressed_file(inode))
2839		return addrs;
2840	return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
2841}
2842
2843static inline unsigned int addrs_per_block(struct inode *inode)
2844{
2845	if (!f2fs_compressed_file(inode))
2846		return DEF_ADDRS_PER_BLOCK;
2847	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
2848}
2849
2850static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
2851{
2852	struct f2fs_inode *ri = F2FS_INODE(page);
2853
2854	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
2855					get_inline_xattr_addrs(inode)]);
2856}
2857
2858static inline int inline_xattr_size(struct inode *inode)
2859{
2860	if (f2fs_has_inline_xattr(inode))
2861		return get_inline_xattr_addrs(inode) * sizeof(__le32);
2862	return 0;
2863}
2864
2865static inline int f2fs_has_inline_data(struct inode *inode)
2866{
2867	return is_inode_flag_set(inode, FI_INLINE_DATA);
2868}
2869
2870static inline int f2fs_exist_data(struct inode *inode)
2871{
2872	return is_inode_flag_set(inode, FI_DATA_EXIST);
2873}
2874
2875static inline int f2fs_has_inline_dots(struct inode *inode)
2876{
2877	return is_inode_flag_set(inode, FI_INLINE_DOTS);
2878}
2879
2880static inline int f2fs_is_mmap_file(struct inode *inode)
2881{
2882	return is_inode_flag_set(inode, FI_MMAP_FILE);
2883}
2884
2885static inline bool f2fs_is_pinned_file(struct inode *inode)
2886{
2887	return is_inode_flag_set(inode, FI_PIN_FILE);
2888}
2889
2890static inline bool f2fs_is_atomic_file(struct inode *inode)
2891{
2892	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
2893}
2894
2895static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
2896{
2897	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
2898}
2899
2900static inline bool f2fs_is_volatile_file(struct inode *inode)
2901{
2902	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
2903}
2904
2905static inline bool f2fs_is_first_block_written(struct inode *inode)
2906{
2907	return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
2908}
2909
2910static inline bool f2fs_is_drop_cache(struct inode *inode)
2911{
2912	return is_inode_flag_set(inode, FI_DROP_CACHE);
2913}
2914
2915static inline void *inline_data_addr(struct inode *inode, struct page *page)
2916{
2917	struct f2fs_inode *ri = F2FS_INODE(page);
2918	int extra_size = get_extra_isize(inode);
2919
2920	return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
2921}
2922
2923static inline int f2fs_has_inline_dentry(struct inode *inode)
2924{
2925	return is_inode_flag_set(inode, FI_INLINE_DENTRY);
2926}
2927
2928static inline int is_file(struct inode *inode, int type)
2929{
2930	return F2FS_I(inode)->i_advise & type;
2931}
2932
2933static inline void set_file(struct inode *inode, int type)
2934{
2935	F2FS_I(inode)->i_advise |= type;
2936	f2fs_mark_inode_dirty_sync(inode, true);
2937}
2938
2939static inline void clear_file(struct inode *inode, int type)
2940{
2941	F2FS_I(inode)->i_advise &= ~type;
2942	f2fs_mark_inode_dirty_sync(inode, true);
2943}
2944
2945static inline bool f2fs_is_time_consistent(struct inode *inode)
2946{
2947	if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
2948		return false;
2949	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
2950		return false;
2951	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
2952		return false;
2953	if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
2954						&F2FS_I(inode)->i_crtime))
2955		return false;
2956	return true;
2957}
2958
2959static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
2960{
2961	bool ret;
2962
2963	if (dsync) {
2964		struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
2965
2966		spin_lock(&sbi->inode_lock[DIRTY_META]);
2967		ret = list_empty(&F2FS_I(inode)->gdirty_list);
2968		spin_unlock(&sbi->inode_lock[DIRTY_META]);
2969		return ret;
2970	}
2971	if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
2972			file_keep_isize(inode) ||
2973			i_size_read(inode) & ~PAGE_MASK)
2974		return false;
2975
2976	if (!f2fs_is_time_consistent(inode))
2977		return false;
2978
2979	spin_lock(&F2FS_I(inode)->i_size_lock);
2980	ret = F2FS_I(inode)->last_disk_size == i_size_read(inode);
2981	spin_unlock(&F2FS_I(inode)->i_size_lock);
2982
2983	return ret;
2984}
2985
2986static inline bool f2fs_readonly(struct super_block *sb)
2987{
2988	return sb_rdonly(sb);
2989}
2990
2991static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
2992{
2993	return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
2994}
2995
2996static inline bool is_dot_dotdot(const u8 *name, size_t len)
2997{
2998	if (len == 1 && name[0] == '.')
2999		return true;
3000
3001	if (len == 2 && name[0] == '.' && name[1] == '.')
3002		return true;
3003
3004	return false;
3005}
3006
3007static inline bool f2fs_may_extent_tree(struct inode *inode)
3008{
3009	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
3010
3011	if (!test_opt(sbi, EXTENT_CACHE) ||
3012			is_inode_flag_set(inode, FI_NO_EXTENT) ||
3013			is_inode_flag_set(inode, FI_COMPRESSED_FILE))
3014		return false;
3015
3016	/*
3017	 * for recovered files during mount do not create extents
3018	 * if shrinker is not registered.
3019	 */
3020	if (list_empty(&sbi->s_list))
3021		return false;
3022
3023	return S_ISREG(inode->i_mode);
3024}
3025
3026static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
3027					size_t size, gfp_t flags)
3028{
3029	if (time_to_inject(sbi, FAULT_KMALLOC)) {
3030		f2fs_show_injection_info(sbi, FAULT_KMALLOC);
3031		return NULL;
3032	}
3033
3034	return kmalloc(size, flags);
3035}
3036
3037static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
3038					size_t size, gfp_t flags)
3039{
3040	return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO);
3041}
3042
3043static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi,
3044					size_t size, gfp_t flags)
3045{
3046	if (time_to_inject(sbi, FAULT_KVMALLOC)) {
3047		f2fs_show_injection_info(sbi, FAULT_KVMALLOC);
3048		return NULL;
3049	}
3050
3051	return kvmalloc(size, flags);
3052}
3053
3054static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi,
3055					size_t size, gfp_t flags)
3056{
3057	return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO);
3058}
3059
3060static inline int get_extra_isize(struct inode *inode)
3061{
3062	return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
3063}
3064
3065static inline int get_inline_xattr_addrs(struct inode *inode)
3066{
3067	return F2FS_I(inode)->i_inline_xattr_size;
3068}
3069
3070#define f2fs_get_inode_mode(i) \
3071	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
3072	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
3073
3074#define F2FS_TOTAL_EXTRA_ATTR_SIZE			\
3075	(offsetof(struct f2fs_inode, i_extra_end) -	\
3076	offsetof(struct f2fs_inode, i_extra_isize))	\
3077
3078#define F2FS_OLD_ATTRIBUTE_SIZE	(offsetof(struct f2fs_inode, i_addr))
3079#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field)		\
3080		((offsetof(typeof(*(f2fs_inode)), field) +	\
3081		sizeof((f2fs_inode)->field))			\
3082		<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize)))	\
3083
3084#define DEFAULT_IOSTAT_PERIOD_MS	3000
3085#define MIN_IOSTAT_PERIOD_MS		100
3086/* maximum period of iostat tracing is 1 day */
3087#define MAX_IOSTAT_PERIOD_MS		8640000
3088
3089static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
3090{
3091	int i;
3092
3093	spin_lock(&sbi->iostat_lock);
3094	for (i = 0; i < NR_IO_TYPE; i++) {
3095		sbi->rw_iostat[i] = 0;
3096		sbi->prev_rw_iostat[i] = 0;
3097	}
3098	spin_unlock(&sbi->iostat_lock);
3099}
3100
3101extern void f2fs_record_iostat(struct f2fs_sb_info *sbi);
3102
3103static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
3104			enum iostat_type type, unsigned long long io_bytes)
3105{
3106	if (!sbi->iostat_enable)
3107		return;
3108	spin_lock(&sbi->iostat_lock);
3109	sbi->rw_iostat[type] += io_bytes;
3110
3111	if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
3112		sbi->rw_iostat[APP_BUFFERED_IO] =
3113			sbi->rw_iostat[APP_WRITE_IO] -
3114			sbi->rw_iostat[APP_DIRECT_IO];
3115
3116	if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
3117		sbi->rw_iostat[APP_BUFFERED_READ_IO] =
3118			sbi->rw_iostat[APP_READ_IO] -
3119			sbi->rw_iostat[APP_DIRECT_READ_IO];
3120	spin_unlock(&sbi->iostat_lock);
3121
3122	f2fs_record_iostat(sbi);
3123}
3124
3125static inline block_t fs_free_space_threshold(struct f2fs_sb_info *sbi)
3126{
3127	return (block_t)(SM_I(sbi)->main_segments * sbi->blocks_per_seg *
3128		FS_FREE_SPACE_PERCENT) / HUNDRED_PERCENT;
3129}
3130
3131static inline block_t device_free_space_threshold(struct f2fs_sb_info *sbi)
3132{
3133	return (block_t)(SM_I(sbi)->main_segments * sbi->blocks_per_seg *
3134		DEVICE_FREE_SPACE_PERCENT) / HUNDRED_PERCENT;
3135}
3136
3137#define __is_large_section(sbi)		((sbi)->segs_per_sec > 1)
3138
3139#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
3140
3141bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
3142					block_t blkaddr, int type);
3143static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
3144					block_t blkaddr, int type)
3145{
3146	if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
3147		f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
3148			 blkaddr, type);
3149		f2fs_bug_on(sbi, 1);
3150	}
3151}
3152
3153static inline bool __is_valid_data_blkaddr(block_t blkaddr)
3154{
3155	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR ||
3156			blkaddr == COMPRESS_ADDR)
3157		return false;
3158	return true;
3159}
3160
3161static inline void f2fs_set_page_private(struct page *page,
3162						unsigned long data)
3163{
3164	if (PagePrivate(page))
3165		return;
3166
3167	attach_page_private(page, (void *)data);
3168}
3169
3170static inline void f2fs_clear_page_private(struct page *page)
3171{
3172	detach_page_private(page);
3173}
3174
3175/*
3176 * file.c
3177 */
3178int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
3179void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
3180int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
3181int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
3182int f2fs_truncate(struct inode *inode);
3183int f2fs_getattr(const struct path *path, struct kstat *stat,
3184			u32 request_mask, unsigned int flags);
3185int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
3186int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
3187void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
3188int f2fs_precache_extents(struct inode *inode);
3189long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
3190long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
3191int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
3192int f2fs_pin_file_control(struct inode *inode, bool inc);
3193
3194/*
3195 * inode.c
3196 */
3197void f2fs_set_inode_flags(struct inode *inode);
3198bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
3199void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
3200struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
3201struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
3202int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
3203void f2fs_update_inode(struct inode *inode, struct page *node_page);
3204void f2fs_update_inode_page(struct inode *inode);
3205int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
3206void f2fs_evict_inode(struct inode *inode);
3207void f2fs_handle_failed_inode(struct inode *inode);
3208
3209/*
3210 * namei.c
3211 */
3212int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
3213							bool hot, bool set);
3214struct dentry *f2fs_get_parent(struct dentry *child);
3215
3216/*
3217 * dir.c
3218 */
3219unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
3220int f2fs_init_casefolded_name(const struct inode *dir,
3221			      struct f2fs_filename *fname);
3222int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
3223			int lookup, struct f2fs_filename *fname);
3224int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
3225			struct f2fs_filename *fname);
3226void f2fs_free_filename(struct f2fs_filename *fname);
3227struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
3228			const struct f2fs_filename *fname, int *max_slots);
3229int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
3230			unsigned int start_pos, struct fscrypt_str *fstr);
3231void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
3232			struct f2fs_dentry_ptr *d);
3233struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
3234			const struct f2fs_filename *fname, struct page *dpage);
3235void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
3236			unsigned int current_depth);
3237int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
3238void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
3239struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
3240					 const struct f2fs_filename *fname,
3241					 struct page **res_page);
3242struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
3243			const struct qstr *child, struct page **res_page);
3244struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
3245ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
3246			struct page **page);
3247void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
3248			struct page *page, struct inode *inode);
3249bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
3250			  const struct f2fs_filename *fname);
3251void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
3252			const struct fscrypt_str *name, f2fs_hash_t name_hash,
3253			unsigned int bit_pos);
3254int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
3255			struct inode *inode, nid_t ino, umode_t mode);
3256int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
3257			struct inode *inode, nid_t ino, umode_t mode);
3258int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
3259			struct inode *inode, nid_t ino, umode_t mode);
3260void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
3261			struct inode *dir, struct inode *inode);
3262int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
3263bool f2fs_empty_dir(struct inode *dir);
3264
3265static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
3266{
3267	if (fscrypt_is_nokey_name(dentry))
3268		return -ENOKEY;
3269	return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
3270				inode, inode->i_ino, inode->i_mode);
3271}
3272
3273/*
3274 * super.c
3275 */
3276int f2fs_inode_dirtied(struct inode *inode, bool sync);
3277void f2fs_inode_synced(struct inode *inode);
3278int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
3279int f2fs_quota_sync(struct super_block *sb, int type);
3280void f2fs_quota_off_umount(struct super_block *sb);
3281int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
3282int f2fs_sync_fs(struct super_block *sb, int sync);
3283int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
3284
3285/*
3286 * hash.c
3287 */
3288void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);
3289
3290/*
3291 * node.c
3292 */
3293struct dnode_of_data;
3294struct node_info;
3295
3296int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
3297bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
3298bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
3299void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
3300void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
3301void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
3302int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
3303bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
3304bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
3305int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
3306						struct node_info *ni);
3307pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
3308int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
3309int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
3310int f2fs_truncate_xattr_node(struct inode *inode);
3311int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
3312					unsigned int seq_id);
3313int f2fs_remove_inode_page(struct inode *inode);
3314struct page *f2fs_new_inode_page(struct inode *inode);
3315struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
3316void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
3317struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
3318struct page *f2fs_get_node_page_ra(struct page *parent, int start);
3319int f2fs_move_node_page(struct page *node_page, int gc_type);
3320void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
3321int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
3322			struct writeback_control *wbc, bool atomic,
3323			unsigned int *seq_id);
3324int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
3325			struct writeback_control *wbc,
3326			bool do_balance, enum iostat_type io_type);
3327int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
3328bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
3329void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
3330void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
3331int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
3332int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
3333int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
3334int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
3335int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
3336			unsigned int segno, struct f2fs_summary_block *sum);
3337int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
3338int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
3339void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
3340int __init f2fs_create_node_manager_caches(void);
3341void f2fs_destroy_node_manager_caches(void);
3342
3343/*
3344 * segment.c
3345 */
3346unsigned long find_rev_next_bit(const unsigned long *addr,
3347		unsigned long size, unsigned long offset);
3348unsigned long find_rev_next_zero_bit(const unsigned long *addr,
3349		unsigned long size, unsigned long offset);
3350bool f2fs_need_SSR(struct f2fs_sb_info *sbi);
3351void f2fs_register_inmem_page(struct inode *inode, struct page *page);
3352void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure);
3353void f2fs_drop_inmem_pages(struct inode *inode);
3354void f2fs_drop_inmem_page(struct inode *inode, struct page *page);
3355int f2fs_commit_inmem_pages(struct inode *inode);
3356void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
3357void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg);
3358int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
3359int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
3360int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
3361void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
3362void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
3363bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
3364void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
3365void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
3366bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
3367void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
3368					struct cp_control *cpc);
3369void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
3370block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
3371int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
3372void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
3373int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
3374bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno);
3375void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
3376void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
3377void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
3378void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
3379			unsigned int *newseg, bool new_sec, int dir);
3380void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
3381					unsigned int start, unsigned int end);
3382void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type);
3383void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
3384int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
3385bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
3386					struct cp_control *cpc);
3387struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
3388void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
3389					block_t blk_addr);
3390void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
3391						enum iostat_type io_type);
3392void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
3393void f2fs_outplace_write_data(struct dnode_of_data *dn,
3394			struct f2fs_io_info *fio);
3395int f2fs_inplace_write_data(struct f2fs_io_info *fio);
3396void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
3397			block_t old_blkaddr, block_t new_blkaddr,
3398			bool recover_curseg, bool recover_newaddr,
3399			bool from_gc);
3400void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
3401			block_t old_addr, block_t new_addr,
3402			unsigned char version, bool recover_curseg,
3403			bool recover_newaddr);
3404void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
3405			block_t old_blkaddr, block_t *new_blkaddr,
3406			struct f2fs_summary *sum, int type,
3407			struct f2fs_io_info *fio, int contig_level);
3408void f2fs_wait_on_page_writeback(struct page *page,
3409			enum page_type type, bool ordered, bool locked);
3410void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
3411void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
3412								block_t len);
3413void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
3414void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
3415int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
3416			unsigned int val, int alloc);
3417void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
3418int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
3419int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
3420int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
3421void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
3422int __init f2fs_create_segment_manager_caches(void);
3423void f2fs_destroy_segment_manager_caches(void);
3424int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
3425enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
3426			enum page_type type, enum temp_type temp);
3427unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
3428			unsigned int segno);
3429unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
3430			unsigned int segno);
3431
3432/*
3433 * checkpoint.c
3434 */
3435void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
3436struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
3437struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
3438struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
3439struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
3440bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
3441					block_t blkaddr, int type);
3442int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
3443			int type, bool sync);
3444void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
3445long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
3446			long nr_to_write, enum iostat_type io_type);
3447void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
3448void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
3449void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all);
3450bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
3451void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
3452					unsigned int devidx, int type);
3453bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
3454					unsigned int devidx, int type);
3455int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
3456int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi);
3457void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi);
3458void f2fs_add_orphan_inode(struct inode *inode);
3459void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
3460int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
3461int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
3462void f2fs_update_dirty_page(struct inode *inode, struct page *page);
3463void f2fs_remove_dirty_inode(struct inode *inode);
3464int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
3465								bool from_cp);
3466void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
3467int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
3468void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
3469int __init f2fs_create_checkpoint_caches(void);
3470void f2fs_destroy_checkpoint_caches(void);
3471
3472/*
3473 * data.c
3474 */
3475int __init f2fs_init_bioset(void);
3476void f2fs_destroy_bioset(void);
3477struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool noio);
3478int f2fs_init_bio_entry_cache(void);
3479void f2fs_destroy_bio_entry_cache(void);
3480void f2fs_submit_bio(struct f2fs_sb_info *sbi,
3481				struct bio *bio, enum page_type type);
3482void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
3483void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
3484				struct inode *inode, struct page *page,
3485				nid_t ino, enum page_type type);
3486void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
3487					struct bio **bio, struct page *page);
3488void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
3489int f2fs_submit_page_bio(struct f2fs_io_info *fio);
3490int f2fs_merge_page_bio(struct f2fs_io_info *fio);
3491void f2fs_submit_page_write(struct f2fs_io_info *fio);
3492struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
3493			block_t blk_addr, struct bio *bio);
3494int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
3495void f2fs_set_data_blkaddr(struct dnode_of_data *dn);
3496void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
3497int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
3498int f2fs_reserve_new_block(struct dnode_of_data *dn);
3499int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
3500int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
3501int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
3502struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
3503			int op_flags, bool for_write);
3504struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
3505struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
3506			bool for_write);
3507struct page *f2fs_get_new_data_page(struct inode *inode,
3508			struct page *ipage, pgoff_t index, bool new_i_size);
3509int f2fs_do_write_data_page(struct f2fs_io_info *fio);
3510void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
3511int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
3512			int create, int flag);
3513int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
3514			u64 start, u64 len);
3515int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
3516bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
3517bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
3518int f2fs_write_single_data_page(struct page *page, int *submitted,
3519				struct bio **bio, sector_t *last_block,
3520				struct writeback_control *wbc,
3521				enum iostat_type io_type,
3522				int compr_blocks, bool allow_balance);
3523void f2fs_invalidate_page(struct page *page, unsigned int offset,
3524			unsigned int length);
3525int f2fs_release_page(struct page *page, gfp_t wait);
3526#ifdef CONFIG_MIGRATION
3527int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
3528			struct page *page, enum migrate_mode mode);
3529#endif
3530bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
3531void f2fs_clear_page_cache_dirty_tag(struct page *page);
3532int f2fs_init_post_read_processing(void);
3533void f2fs_destroy_post_read_processing(void);
3534int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
3535void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
3536
3537/*
3538 * gc.c
3539 */
3540int f2fs_start_gc_thread(struct f2fs_sb_info *sbi);
3541void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
3542block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
3543int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, bool force,
3544			unsigned int segno);
3545void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
3546int f2fs_resize_fs(struct file *filp, __u64 block_count);
3547int __init f2fs_create_garbage_collection_cache(void);
3548void f2fs_destroy_garbage_collection_cache(void);
3549
3550/*
3551 * recovery.c
3552 */
3553int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
3554bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi);
3555int __init f2fs_create_recovery_cache(void);
3556void f2fs_destroy_recovery_cache(void);
3557
3558/*
3559 * debug.c
3560 */
3561#ifdef CONFIG_F2FS_STAT_FS
3562struct f2fs_stat_info {
3563	struct list_head stat_list;
3564	struct f2fs_sb_info *sbi;
3565	int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
3566	int main_area_segs, main_area_sections, main_area_zones;
3567	unsigned long long hit_largest, hit_cached, hit_rbtree;
3568	unsigned long long hit_total, total_ext;
3569	int ext_tree, zombie_tree, ext_node;
3570	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
3571	int ndirty_data, ndirty_qdata;
3572	int inmem_pages;
3573	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
3574	int nats, dirty_nats, sits, dirty_sits;
3575	int free_nids, avail_nids, alloc_nids;
3576	int total_count, utilization;
3577	int bg_gc, nr_wb_cp_data, nr_wb_data;
3578	int nr_rd_data, nr_rd_node, nr_rd_meta;
3579	int nr_dio_read, nr_dio_write;
3580	unsigned int io_skip_bggc, other_skip_bggc;
3581	int nr_flushing, nr_flushed, flush_list_empty;
3582	int nr_discarding, nr_discarded;
3583	int nr_discard_cmd;
3584	unsigned int undiscard_blks;
3585	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
3586	int compr_inode;
3587	unsigned long long compr_blocks;
3588	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
3589	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
3590	unsigned int bimodal, avg_vblocks;
3591	int util_free, util_valid, util_invalid;
3592	int rsvd_segs, overp_segs;
3593	int dirty_count, node_pages, meta_pages;
3594	int prefree_count, call_count, cp_count, bg_cp_count;
3595	int tot_segs, node_segs, data_segs, free_segs, free_secs;
3596	int bg_node_segs, bg_data_segs;
3597	int tot_blks, data_blks, node_blks;
3598	int bg_data_blks, bg_node_blks;
3599	unsigned long long skipped_atomic_files[2];
3600	int curseg[NR_CURSEG_TYPE];
3601	int cursec[NR_CURSEG_TYPE];
3602	int curzone[NR_CURSEG_TYPE];
3603	unsigned int dirty_seg[NR_CURSEG_TYPE];
3604	unsigned int full_seg[NR_CURSEG_TYPE];
3605	unsigned int valid_blks[NR_CURSEG_TYPE];
3606
3607	unsigned int meta_count[META_MAX];
3608	unsigned int segment_count[2];
3609	unsigned int block_count[2];
3610	unsigned int inplace_count;
3611	unsigned long long base_mem, cache_mem, page_mem;
3612};
3613
3614static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
3615{
3616	return (struct f2fs_stat_info *)sbi->stat_info;
3617}
3618
3619#define stat_inc_cp_count(si)		((si)->cp_count++)
3620#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
3621#define stat_inc_call_count(si)		((si)->call_count++)
3622#define stat_inc_bggc_count(si)		((si)->bg_gc++)
3623#define stat_io_skip_bggc_count(sbi)	((sbi)->io_skip_bggc++)
3624#define stat_other_skip_bggc_count(sbi)	((sbi)->other_skip_bggc++)
3625#define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
3626#define stat_dec_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]--)
3627#define stat_inc_total_hit(sbi)		(atomic64_inc(&(sbi)->total_hit_ext))
3628#define stat_inc_rbtree_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_rbtree))
3629#define stat_inc_largest_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_largest))
3630#define stat_inc_cached_node_hit(sbi)	(atomic64_inc(&(sbi)->read_hit_cached))
3631#define stat_inc_inline_xattr(inode)					\
3632	do {								\
3633		if (f2fs_has_inline_xattr(inode))			\
3634			(atomic_inc(&F2FS_I_SB(inode)->inline_xattr));	\
3635	} while (0)
3636#define stat_dec_inline_xattr(inode)					\
3637	do {								\
3638		if (f2fs_has_inline_xattr(inode))			\
3639			(atomic_dec(&F2FS_I_SB(inode)->inline_xattr));	\
3640	} while (0)
3641#define stat_inc_inline_inode(inode)					\
3642	do {								\
3643		if (f2fs_has_inline_data(inode))			\
3644			(atomic_inc(&F2FS_I_SB(inode)->inline_inode));	\
3645	} while (0)
3646#define stat_dec_inline_inode(inode)					\
3647	do {								\
3648		if (f2fs_has_inline_data(inode))			\
3649			(atomic_dec(&F2FS_I_SB(inode)->inline_inode));	\
3650	} while (0)
3651#define stat_inc_inline_dir(inode)					\
3652	do {								\
3653		if (f2fs_has_inline_dentry(inode))			\
3654			(atomic_inc(&F2FS_I_SB(inode)->inline_dir));	\
3655	} while (0)
3656#define stat_dec_inline_dir(inode)					\
3657	do {								\
3658		if (f2fs_has_inline_dentry(inode))			\
3659			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
3660	} while (0)
3661#define stat_inc_compr_inode(inode)					\
3662	do {								\
3663		if (f2fs_compressed_file(inode))			\
3664			(atomic_inc(&F2FS_I_SB(inode)->compr_inode));	\
3665	} while (0)
3666#define stat_dec_compr_inode(inode)					\
3667	do {								\
3668		if (f2fs_compressed_file(inode))			\
3669			(atomic_dec(&F2FS_I_SB(inode)->compr_inode));	\
3670	} while (0)
3671#define stat_add_compr_blocks(inode, blocks)				\
3672		(atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
3673#define stat_sub_compr_blocks(inode, blocks)				\
3674		(atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
3675#define stat_inc_meta_count(sbi, blkaddr)				\
3676	do {								\
3677		if (blkaddr < SIT_I(sbi)->sit_base_addr)		\
3678			atomic_inc(&(sbi)->meta_count[META_CP]);	\
3679		else if (blkaddr < NM_I(sbi)->nat_blkaddr)		\
3680			atomic_inc(&(sbi)->meta_count[META_SIT]);	\
3681		else if (blkaddr < SM_I(sbi)->ssa_blkaddr)		\
3682			atomic_inc(&(sbi)->meta_count[META_NAT]);	\
3683		else if (blkaddr < SM_I(sbi)->main_blkaddr)		\
3684			atomic_inc(&(sbi)->meta_count[META_SSA]);	\
3685	} while (0)
3686#define stat_inc_seg_type(sbi, curseg)					\
3687		((sbi)->segment_count[(curseg)->alloc_type]++)
3688#define stat_inc_block_count(sbi, curseg)				\
3689		((sbi)->block_count[(curseg)->alloc_type]++)
3690#define stat_inc_inplace_blocks(sbi)					\
3691		(atomic_inc(&(sbi)->inplace_count))
3692#define stat_update_max_atomic_write(inode)				\
3693	do {								\
3694		int cur = F2FS_I_SB(inode)->atomic_files;	\
3695		int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);	\
3696		if (cur > max)						\
3697			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
3698	} while (0)
3699#define stat_inc_volatile_write(inode)					\
3700		(atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
3701#define stat_dec_volatile_write(inode)					\
3702		(atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
3703#define stat_update_max_volatile_write(inode)				\
3704	do {								\
3705		int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt);	\
3706		int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt);	\
3707		if (cur > max)						\
3708			atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur);	\
3709	} while (0)
3710#define stat_inc_seg_count(sbi, type, gc_type)				\
3711	do {								\
3712		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3713		si->tot_segs++;						\
3714		if ((type) == SUM_TYPE_DATA) {				\
3715			si->data_segs++;				\
3716			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
3717		} else {						\
3718			si->node_segs++;				\
3719			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
3720		}							\
3721	} while (0)
3722
3723#define stat_inc_tot_blk_count(si, blks)				\
3724	((si)->tot_blks += (blks))
3725
3726#define stat_inc_data_blk_count(sbi, blks, gc_type)			\
3727	do {								\
3728		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3729		stat_inc_tot_blk_count(si, blks);			\
3730		si->data_blks += (blks);				\
3731		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3732	} while (0)
3733
3734#define stat_inc_node_blk_count(sbi, blks, gc_type)			\
3735	do {								\
3736		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
3737		stat_inc_tot_blk_count(si, blks);			\
3738		si->node_blks += (blks);				\
3739		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
3740	} while (0)
3741
3742int f2fs_build_stats(struct f2fs_sb_info *sbi);
3743void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
3744void __init f2fs_create_root_stats(void);
3745void f2fs_destroy_root_stats(void);
3746void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
3747#else
3748#define stat_inc_cp_count(si)				do { } while (0)
3749#define stat_inc_bg_cp_count(si)			do { } while (0)
3750#define stat_inc_call_count(si)				do { } while (0)
3751#define stat_inc_bggc_count(si)				do { } while (0)
3752#define stat_io_skip_bggc_count(sbi)			do { } while (0)
3753#define stat_other_skip_bggc_count(sbi)			do { } while (0)
3754#define stat_inc_dirty_inode(sbi, type)			do { } while (0)
3755#define stat_dec_dirty_inode(sbi, type)			do { } while (0)
3756#define stat_inc_total_hit(sbi)				do { } while (0)
3757#define stat_inc_rbtree_node_hit(sbi)			do { } while (0)
3758#define stat_inc_largest_node_hit(sbi)			do { } while (0)
3759#define stat_inc_cached_node_hit(sbi)			do { } while (0)
3760#define stat_inc_inline_xattr(inode)			do { } while (0)
3761#define stat_dec_inline_xattr(inode)			do { } while (0)
3762#define stat_inc_inline_inode(inode)			do { } while (0)
3763#define stat_dec_inline_inode(inode)			do { } while (0)
3764#define stat_inc_inline_dir(inode)			do { } while (0)
3765#define stat_dec_inline_dir(inode)			do { } while (0)
3766#define stat_inc_compr_inode(inode)			do { } while (0)
3767#define stat_dec_compr_inode(inode)			do { } while (0)
3768#define stat_add_compr_blocks(inode, blocks)		do { } while (0)
3769#define stat_sub_compr_blocks(inode, blocks)		do { } while (0)
3770#define stat_inc_atomic_write(inode)			do { } while (0)
3771#define stat_dec_atomic_write(inode)			do { } while (0)
3772#define stat_update_max_atomic_write(inode)		do { } while (0)
3773#define stat_inc_volatile_write(inode)			do { } while (0)
3774#define stat_dec_volatile_write(inode)			do { } while (0)
3775#define stat_update_max_volatile_write(inode)		do { } while (0)
3776#define stat_inc_meta_count(sbi, blkaddr)		do { } while (0)
3777#define stat_inc_seg_type(sbi, curseg)			do { } while (0)
3778#define stat_inc_block_count(sbi, curseg)		do { } while (0)
3779#define stat_inc_inplace_blocks(sbi)			do { } while (0)
3780#define stat_inc_seg_count(sbi, type, gc_type)		do { } while (0)
3781#define stat_inc_tot_blk_count(si, blks)		do { } while (0)
3782#define stat_inc_data_blk_count(sbi, blks, gc_type)	do { } while (0)
3783#define stat_inc_node_blk_count(sbi, blks, gc_type)	do { } while (0)
3784
3785static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
3786static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
3787static inline void __init f2fs_create_root_stats(void) { }
3788static inline void f2fs_destroy_root_stats(void) { }
3789static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
3790#endif
3791
3792extern const struct file_operations f2fs_dir_operations;
3793#ifdef CONFIG_UNICODE
3794extern const struct dentry_operations f2fs_dentry_ops;
3795#endif
3796extern const struct file_operations f2fs_file_operations;
3797extern const struct inode_operations f2fs_file_inode_operations;
3798extern const struct address_space_operations f2fs_dblock_aops;
3799extern const struct address_space_operations f2fs_node_aops;
3800extern const struct address_space_operations f2fs_meta_aops;
3801extern const struct inode_operations f2fs_dir_inode_operations;
3802extern const struct inode_operations f2fs_symlink_inode_operations;
3803extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
3804extern const struct inode_operations f2fs_special_inode_operations;
3805extern struct kmem_cache *f2fs_inode_entry_slab;
3806
3807/*
3808 * inline.c
3809 */
3810bool f2fs_may_inline_data(struct inode *inode);
3811bool f2fs_sanity_check_inline_data(struct inode *inode);
3812bool f2fs_may_inline_dentry(struct inode *inode);
3813void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
3814void f2fs_truncate_inline_inode(struct inode *inode,
3815						struct page *ipage, u64 from);
3816int f2fs_read_inline_data(struct inode *inode, struct page *page);
3817int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
3818int f2fs_convert_inline_inode(struct inode *inode);
3819int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
3820int f2fs_write_inline_data(struct inode *inode, struct page *page);
3821int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
3822struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
3823					const struct f2fs_filename *fname,
3824					struct page **res_page);
3825int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
3826			struct page *ipage);
3827int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
3828			struct inode *inode, nid_t ino, umode_t mode);
3829void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
3830				struct page *page, struct inode *dir,
3831				struct inode *inode);
3832bool f2fs_empty_inline_dir(struct inode *dir);
3833int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
3834			struct fscrypt_str *fstr);
3835int f2fs_inline_data_fiemap(struct inode *inode,
3836			struct fiemap_extent_info *fieinfo,
3837			__u64 start, __u64 len);
3838
3839/*
3840 * shrinker.c
3841 */
3842unsigned long f2fs_shrink_count(struct shrinker *shrink,
3843			struct shrink_control *sc);
3844unsigned long f2fs_shrink_scan(struct shrinker *shrink,
3845			struct shrink_control *sc);
3846void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
3847void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
3848
3849/*
3850 * extent_cache.c
3851 */
3852struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
3853				struct rb_entry *cached_re, unsigned int ofs);
3854struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
3855				struct rb_root_cached *root,
3856				struct rb_node **parent,
3857				unsigned long long key, bool *left_most);
3858struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
3859				struct rb_root_cached *root,
3860				struct rb_node **parent,
3861				unsigned int ofs, bool *leftmost);
3862struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
3863		struct rb_entry *cached_re, unsigned int ofs,
3864		struct rb_entry **prev_entry, struct rb_entry **next_entry,
3865		struct rb_node ***insert_p, struct rb_node **insert_parent,
3866		bool force, bool *leftmost);
3867bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
3868				struct rb_root_cached *root, bool check_key);
3869unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
3870void f2fs_init_extent_tree(struct inode *inode, struct page *ipage);
3871void f2fs_drop_extent_tree(struct inode *inode);
3872unsigned int f2fs_destroy_extent_node(struct inode *inode);
3873void f2fs_destroy_extent_tree(struct inode *inode);
3874bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
3875			struct extent_info *ei);
3876void f2fs_update_extent_cache(struct dnode_of_data *dn);
3877void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
3878			pgoff_t fofs, block_t blkaddr, unsigned int len);
3879void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi);
3880int __init f2fs_create_extent_cache(void);
3881void f2fs_destroy_extent_cache(void);
3882
3883/*
3884 * sysfs.c
3885 */
3886int __init f2fs_init_sysfs(void);
3887void f2fs_exit_sysfs(void);
3888int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
3889void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi);
3890
3891/* verity.c */
3892extern const struct fsverity_operations f2fs_verityops;
3893
3894/*
3895 * crypto support
3896 */
3897static inline bool f2fs_encrypted_file(struct inode *inode)
3898{
3899	return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode);
3900}
3901
3902static inline void f2fs_set_encrypted_inode(struct inode *inode)
3903{
3904#ifdef CONFIG_FS_ENCRYPTION
3905	file_set_encrypt(inode);
3906	f2fs_set_inode_flags(inode);
3907#endif
3908}
3909
3910/*
3911 * Returns true if the reads of the inode's data need to undergo some
3912 * postprocessing step, like decryption or authenticity verification.
3913 */
3914static inline bool f2fs_post_read_required(struct inode *inode)
3915{
3916	return f2fs_encrypted_file(inode) || fsverity_active(inode) ||
3917		f2fs_compressed_file(inode);
3918}
3919
3920/*
3921 * compress.c
3922 */
3923#ifdef CONFIG_F2FS_FS_COMPRESSION
3924bool f2fs_is_compressed_page(struct page *page);
3925struct page *f2fs_compress_control_page(struct page *page);
3926int f2fs_prepare_compress_overwrite(struct inode *inode,
3927			struct page **pagep, pgoff_t index, void **fsdata);
3928bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
3929					pgoff_t index, unsigned copied);
3930int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
3931void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
3932bool f2fs_is_compress_backend_ready(struct inode *inode);
3933int f2fs_init_compress_mempool(void);
3934void f2fs_destroy_compress_mempool(void);
3935void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
3936bool f2fs_cluster_is_empty(struct compress_ctx *cc);
3937bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
3938void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
3939int f2fs_write_multi_pages(struct compress_ctx *cc,
3940						int *submitted,
3941						struct writeback_control *wbc,
3942						enum iostat_type io_type);
3943int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
3944int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
3945				unsigned nr_pages, sector_t *last_block_in_bio,
3946				bool is_readahead, bool for_write);
3947struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
3948void f2fs_free_dic(struct decompress_io_ctx *dic);
3949void f2fs_decompress_end_io(struct page **rpages,
3950			unsigned int cluster_size, bool err, bool verity);
3951int f2fs_init_compress_ctx(struct compress_ctx *cc);
3952void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
3953void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
3954int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi);
3955void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
3956int __init f2fs_init_compress_cache(void);
3957void f2fs_destroy_compress_cache(void);
3958#else
3959static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
3960static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
3961{
3962	if (!f2fs_compressed_file(inode))
3963		return true;
3964	/* not support compression */
3965	return false;
3966}
3967static inline struct page *f2fs_compress_control_page(struct page *page)
3968{
3969	WARN_ON_ONCE(1);
3970	return ERR_PTR(-EINVAL);
3971}
3972static inline int f2fs_init_compress_mempool(void) { return 0; }
3973static inline void f2fs_destroy_compress_mempool(void) { }
3974static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; }
3975static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
3976static inline int __init f2fs_init_compress_cache(void) { return 0; }
3977static inline void f2fs_destroy_compress_cache(void) { }
3978#endif
3979
3980static inline void set_compress_context(struct inode *inode)
3981{
3982	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
3983
3984	F2FS_I(inode)->i_compress_algorithm =
3985			F2FS_OPTION(sbi).compress_algorithm;
3986	F2FS_I(inode)->i_log_cluster_size =
3987			F2FS_OPTION(sbi).compress_log_size;
3988	F2FS_I(inode)->i_cluster_size =
3989			1 << F2FS_I(inode)->i_log_cluster_size;
3990	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
3991	set_inode_flag(inode, FI_COMPRESSED_FILE);
3992	stat_inc_compr_inode(inode);
3993	f2fs_mark_inode_dirty_sync(inode, true);
3994}
3995
3996static inline bool f2fs_disable_compressed_file(struct inode *inode)
3997{
3998	struct f2fs_inode_info *fi = F2FS_I(inode);
3999
4000	if (!f2fs_compressed_file(inode))
4001		return true;
4002	if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))
4003		return false;
4004
4005	fi->i_flags &= ~F2FS_COMPR_FL;
4006	stat_dec_compr_inode(inode);
4007	clear_inode_flag(inode, FI_COMPRESSED_FILE);
4008	f2fs_mark_inode_dirty_sync(inode, true);
4009	return true;
4010}
4011
4012#define F2FS_FEATURE_FUNCS(name, flagname) \
4013static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \
4014{ \
4015	return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \
4016}
4017
4018F2FS_FEATURE_FUNCS(encrypt, ENCRYPT);
4019F2FS_FEATURE_FUNCS(blkzoned, BLKZONED);
4020F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR);
4021F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA);
4022F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM);
4023F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR);
4024F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO);
4025F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME);
4026F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
4027F2FS_FEATURE_FUNCS(verity, VERITY);
4028F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
4029F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
4030F2FS_FEATURE_FUNCS(compression, COMPRESSION);
4031
4032#ifdef CONFIG_BLK_DEV_ZONED
4033static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
4034				    block_t blkaddr)
4035{
4036	unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
4037
4038	return test_bit(zno, FDEV(devi).blkz_seq);
4039}
4040#endif
4041
4042static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
4043{
4044	return f2fs_sb_has_blkzoned(sbi);
4045}
4046
4047static inline bool f2fs_bdev_support_discard(struct block_device *bdev)
4048{
4049	return blk_queue_discard(bdev_get_queue(bdev)) ||
4050	       bdev_is_zoned(bdev);
4051}
4052
4053static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi)
4054{
4055	int i;
4056
4057	if (!f2fs_is_multi_device(sbi))
4058		return f2fs_bdev_support_discard(sbi->sb->s_bdev);
4059
4060	for (i = 0; i < sbi->s_ndevs; i++)
4061		if (f2fs_bdev_support_discard(FDEV(i).bdev))
4062			return true;
4063	return false;
4064}
4065
4066static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi)
4067{
4068	return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) ||
4069					f2fs_hw_should_discard(sbi);
4070}
4071
4072static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi)
4073{
4074	int i;
4075
4076	if (!f2fs_is_multi_device(sbi))
4077		return bdev_read_only(sbi->sb->s_bdev);
4078
4079	for (i = 0; i < sbi->s_ndevs; i++)
4080		if (bdev_read_only(FDEV(i).bdev))
4081			return true;
4082	return false;
4083}
4084
4085static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
4086{
4087	return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
4088}
4089
4090static inline bool f2fs_may_compress(struct inode *inode)
4091{
4092	if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
4093				f2fs_is_atomic_file(inode) ||
4094				f2fs_is_volatile_file(inode))
4095		return false;
4096	return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
4097}
4098
4099static inline void f2fs_i_compr_blocks_update(struct inode *inode,
4100						u64 blocks, bool add)
4101{
4102	int diff = F2FS_I(inode)->i_cluster_size - blocks;
4103	struct f2fs_inode_info *fi = F2FS_I(inode);
4104
4105	/* don't update i_compr_blocks if saved blocks were released */
4106	if (!add && !atomic_read(&fi->i_compr_blocks))
4107		return;
4108
4109	if (add) {
4110		atomic_add(diff, &fi->i_compr_blocks);
4111		stat_add_compr_blocks(inode, diff);
4112	} else {
4113		atomic_sub(diff, &fi->i_compr_blocks);
4114		stat_sub_compr_blocks(inode, diff);
4115	}
4116	f2fs_mark_inode_dirty_sync(inode, true);
4117}
4118
4119static inline int block_unaligned_IO(struct inode *inode,
4120				struct kiocb *iocb, struct iov_iter *iter)
4121{
4122	unsigned int i_blkbits = READ_ONCE(inode->i_blkbits);
4123	unsigned int blocksize_mask = (1 << i_blkbits) - 1;
4124	loff_t offset = iocb->ki_pos;
4125	unsigned long align = offset | iov_iter_alignment(iter);
4126
4127	return align & blocksize_mask;
4128}
4129
4130static inline int allow_outplace_dio(struct inode *inode,
4131				struct kiocb *iocb, struct iov_iter *iter)
4132{
4133	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
4134	int rw = iov_iter_rw(iter);
4135
4136	return (f2fs_lfs_mode(sbi) && (rw == WRITE) &&
4137				!block_unaligned_IO(inode, iocb, iter));
4138}
4139
4140static inline bool f2fs_force_buffered_io(struct inode *inode,
4141				struct kiocb *iocb, struct iov_iter *iter)
4142{
4143	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
4144	int rw = iov_iter_rw(iter);
4145
4146	if (f2fs_post_read_required(inode))
4147		return true;
4148	if (f2fs_is_multi_device(sbi))
4149		return true;
4150	/*
4151	 * for blkzoned device, fallback direct IO to buffered IO, so
4152	 * all IOs can be serialized by log-structured write.
4153	 */
4154	if (f2fs_sb_has_blkzoned(sbi))
4155		return true;
4156	if (f2fs_lfs_mode(sbi) && (rw == WRITE)) {
4157		if (block_unaligned_IO(inode, iocb, iter))
4158			return true;
4159		if (F2FS_IO_ALIGNED(sbi))
4160			return true;
4161	}
4162	if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED) &&
4163					!IS_SWAPFILE(inode))
4164		return true;
4165
4166	return false;
4167}
4168
4169#ifdef CONFIG_F2FS_FAULT_INJECTION
4170extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
4171							unsigned long type);
4172#else
4173static int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
4174							unsigned long type)
4175{
4176	return 0;
4177}
4178#endif
4179
4180static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
4181{
4182#ifdef CONFIG_QUOTA
4183	if (f2fs_sb_has_quota_ino(sbi))
4184		return true;
4185	if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] ||
4186		F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] ||
4187		F2FS_OPTION(sbi).s_qf_names[PRJQUOTA])
4188		return true;
4189#endif
4190	return false;
4191}
4192
4193#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
4194#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */
4195
4196#endif /* _LINUX_F2FS_H */
4197