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/sched/mm.h> 22#include <linux/vmalloc.h> 23#include <linux/bio.h> 24#include <linux/blkdev.h> 25#include <linux/quotaops.h> 26#include <linux/part_stat.h> 27#include <crypto/hash.h> 28 29#include <linux/fscrypt.h> 30#include <linux/fsverity.h> 31 32struct pagevec; 33 34#ifdef CONFIG_F2FS_CHECK_FS 35#define f2fs_bug_on(sbi, condition) BUG_ON(condition) 36#else 37#define f2fs_bug_on(sbi, condition) \ 38 do { \ 39 if (WARN_ON(condition)) \ 40 set_sbi_flag(sbi, SBI_NEED_FSCK); \ 41 } while (0) 42#endif 43 44enum { 45 FAULT_KMALLOC, 46 FAULT_KVMALLOC, 47 FAULT_PAGE_ALLOC, 48 FAULT_PAGE_GET, 49 FAULT_ALLOC_BIO, /* it's obsolete due to bio_alloc() will never fail */ 50 FAULT_ALLOC_NID, 51 FAULT_ORPHAN, 52 FAULT_BLOCK, 53 FAULT_DIR_DEPTH, 54 FAULT_EVICT_INODE, 55 FAULT_TRUNCATE, 56 FAULT_READ_IO, 57 FAULT_CHECKPOINT, 58 FAULT_DISCARD, 59 FAULT_WRITE_IO, 60 FAULT_SLAB_ALLOC, 61 FAULT_DQUOT_INIT, 62 FAULT_LOCK_OP, 63 FAULT_BLKADDR, 64 FAULT_MAX, 65}; 66 67#ifdef CONFIG_F2FS_FAULT_INJECTION 68#define F2FS_ALL_FAULT_TYPE (GENMASK(FAULT_MAX - 1, 0)) 69 70struct f2fs_fault_info { 71 atomic_t inject_ops; 72 unsigned int inject_rate; 73 unsigned int inject_type; 74}; 75 76extern const char *f2fs_fault_name[FAULT_MAX]; 77#define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) 78 79/* maximum retry count for injected failure */ 80#define DEFAULT_FAILURE_RETRY_COUNT 8 81#else 82#define DEFAULT_FAILURE_RETRY_COUNT 1 83#endif 84 85/* 86 * For mount options 87 */ 88#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000001 89#define F2FS_MOUNT_DISCARD 0x00000002 90#define F2FS_MOUNT_NOHEAP 0x00000004 91#define F2FS_MOUNT_XATTR_USER 0x00000008 92#define F2FS_MOUNT_POSIX_ACL 0x00000010 93#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000020 94#define F2FS_MOUNT_INLINE_XATTR 0x00000040 95#define F2FS_MOUNT_INLINE_DATA 0x00000080 96#define F2FS_MOUNT_INLINE_DENTRY 0x00000100 97#define F2FS_MOUNT_FLUSH_MERGE 0x00000200 98#define F2FS_MOUNT_NOBARRIER 0x00000400 99#define F2FS_MOUNT_FASTBOOT 0x00000800 100#define F2FS_MOUNT_READ_EXTENT_CACHE 0x00001000 101#define F2FS_MOUNT_DATA_FLUSH 0x00002000 102#define F2FS_MOUNT_FAULT_INJECTION 0x00004000 103#define F2FS_MOUNT_USRQUOTA 0x00008000 104#define F2FS_MOUNT_GRPQUOTA 0x00010000 105#define F2FS_MOUNT_PRJQUOTA 0x00020000 106#define F2FS_MOUNT_QUOTA 0x00040000 107#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00080000 108#define F2FS_MOUNT_RESERVE_ROOT 0x00100000 109#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x00200000 110#define F2FS_MOUNT_NORECOVERY 0x00400000 111#define F2FS_MOUNT_ATGC 0x00800000 112#define F2FS_MOUNT_MERGE_CHECKPOINT 0x01000000 113#define F2FS_MOUNT_GC_MERGE 0x02000000 114#define F2FS_MOUNT_COMPRESS_CACHE 0x04000000 115#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000 116 117#define F2FS_OPTION(sbi) ((sbi)->mount_opt) 118#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) 119#define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) 120#define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) 121 122#define ver_after(a, b) (typecheck(unsigned long long, a) && \ 123 typecheck(unsigned long long, b) && \ 124 ((long long)((a) - (b)) > 0)) 125 126typedef u32 block_t; /* 127 * should not change u32, since it is the on-disk block 128 * address format, __le32. 129 */ 130typedef u32 nid_t; 131 132#define COMPRESS_EXT_NUM 16 133 134/* 135 * An implementation of an rwsem that is explicitly unfair to readers. This 136 * prevents priority inversion when a low-priority reader acquires the read lock 137 * while sleeping on the write lock but the write lock is needed by 138 * higher-priority clients. 139 */ 140 141struct f2fs_rwsem { 142 struct rw_semaphore internal_rwsem; 143#ifdef CONFIG_F2FS_UNFAIR_RWSEM 144 wait_queue_head_t read_waiters; 145#endif 146}; 147 148struct f2fs_mount_info { 149 unsigned int opt; 150 int write_io_size_bits; /* Write IO size bits */ 151 block_t root_reserved_blocks; /* root reserved blocks */ 152 kuid_t s_resuid; /* reserved blocks for uid */ 153 kgid_t s_resgid; /* reserved blocks for gid */ 154 int active_logs; /* # of active logs */ 155 int inline_xattr_size; /* inline xattr size */ 156#ifdef CONFIG_F2FS_FAULT_INJECTION 157 struct f2fs_fault_info fault_info; /* For fault injection */ 158#endif 159#ifdef CONFIG_QUOTA 160 /* Names of quota files with journalled quota */ 161 char *s_qf_names[MAXQUOTAS]; 162 int s_jquota_fmt; /* Format of quota to use */ 163#endif 164 /* For which write hints are passed down to block layer */ 165 int alloc_mode; /* segment allocation policy */ 166 int fsync_mode; /* fsync policy */ 167 int fs_mode; /* fs mode: LFS or ADAPTIVE */ 168 int bggc_mode; /* bggc mode: off, on or sync */ 169 int memory_mode; /* memory mode */ 170 int errors; /* errors parameter */ 171 int discard_unit; /* 172 * discard command's offset/size should 173 * be aligned to this unit: block, 174 * segment or section 175 */ 176 struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */ 177 block_t unusable_cap_perc; /* percentage for cap */ 178 block_t unusable_cap; /* Amount of space allowed to be 179 * unusable when disabling checkpoint 180 */ 181 182 /* For compression */ 183 unsigned char compress_algorithm; /* algorithm type */ 184 unsigned char compress_log_size; /* cluster log size */ 185 unsigned char compress_level; /* compress level */ 186 bool compress_chksum; /* compressed data chksum */ 187 unsigned char compress_ext_cnt; /* extension count */ 188 unsigned char nocompress_ext_cnt; /* nocompress extension count */ 189 int compress_mode; /* compression mode */ 190 unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ 191 unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ 192}; 193 194#define F2FS_FEATURE_ENCRYPT 0x00000001 195#define F2FS_FEATURE_BLKZONED 0x00000002 196#define F2FS_FEATURE_ATOMIC_WRITE 0x00000004 197#define F2FS_FEATURE_EXTRA_ATTR 0x00000008 198#define F2FS_FEATURE_PRJQUOTA 0x00000010 199#define F2FS_FEATURE_INODE_CHKSUM 0x00000020 200#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x00000040 201#define F2FS_FEATURE_QUOTA_INO 0x00000080 202#define F2FS_FEATURE_INODE_CRTIME 0x00000100 203#define F2FS_FEATURE_LOST_FOUND 0x00000200 204#define F2FS_FEATURE_VERITY 0x00000400 205#define F2FS_FEATURE_SB_CHKSUM 0x00000800 206#define F2FS_FEATURE_CASEFOLD 0x00001000 207#define F2FS_FEATURE_COMPRESSION 0x00002000 208#define F2FS_FEATURE_RO 0x00004000 209 210#define __F2FS_HAS_FEATURE(raw_super, mask) \ 211 ((raw_super->feature & cpu_to_le32(mask)) != 0) 212#define F2FS_HAS_FEATURE(sbi, mask) __F2FS_HAS_FEATURE(sbi->raw_super, mask) 213 214/* 215 * Default values for user and/or group using reserved blocks 216 */ 217#define F2FS_DEF_RESUID 0 218#define F2FS_DEF_RESGID 0 219 220/* 221 * For checkpoint manager 222 */ 223enum { 224 NAT_BITMAP, 225 SIT_BITMAP 226}; 227 228#define CP_UMOUNT 0x00000001 229#define CP_FASTBOOT 0x00000002 230#define CP_SYNC 0x00000004 231#define CP_RECOVERY 0x00000008 232#define CP_DISCARD 0x00000010 233#define CP_TRIMMED 0x00000020 234#define CP_PAUSE 0x00000040 235#define CP_RESIZE 0x00000080 236 237#define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ 238#define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ 239#define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ 240#define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ 241#define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ 242#define DEF_CP_INTERVAL 60 /* 60 secs */ 243#define DEF_IDLE_INTERVAL 5 /* 5 secs */ 244#define DEF_DISABLE_INTERVAL 5 /* 5 secs */ 245#define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ 246#define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ 247 248struct cp_control { 249 int reason; 250 __u64 trim_start; 251 __u64 trim_end; 252 __u64 trim_minlen; 253}; 254 255/* 256 * indicate meta/data type 257 */ 258enum { 259 META_CP, 260 META_NAT, 261 META_SIT, 262 META_SSA, 263 META_MAX, 264 META_POR, 265 DATA_GENERIC, /* check range only */ 266 DATA_GENERIC_ENHANCE, /* strong check on range and segment bitmap */ 267 DATA_GENERIC_ENHANCE_READ, /* 268 * strong check on range and segment 269 * bitmap but no warning due to race 270 * condition of read on truncated area 271 * by extent_cache 272 */ 273 DATA_GENERIC_ENHANCE_UPDATE, /* 274 * strong check on range and segment 275 * bitmap for update case 276 */ 277 META_GENERIC, 278}; 279 280/* for the list of ino */ 281enum { 282 ORPHAN_INO, /* for orphan ino list */ 283 APPEND_INO, /* for append ino list */ 284 UPDATE_INO, /* for update ino list */ 285 TRANS_DIR_INO, /* for transactions dir ino list */ 286 FLUSH_INO, /* for multiple device flushing */ 287 MAX_INO_ENTRY, /* max. list */ 288}; 289 290struct ino_entry { 291 struct list_head list; /* list head */ 292 nid_t ino; /* inode number */ 293 unsigned int dirty_device; /* dirty device bitmap */ 294}; 295 296/* for the list of inodes to be GCed */ 297struct inode_entry { 298 struct list_head list; /* list head */ 299 struct inode *inode; /* vfs inode pointer */ 300}; 301 302struct fsync_node_entry { 303 struct list_head list; /* list head */ 304 struct page *page; /* warm node page pointer */ 305 unsigned int seq_id; /* sequence id */ 306}; 307 308struct ckpt_req { 309 struct completion wait; /* completion for checkpoint done */ 310 struct llist_node llnode; /* llist_node to be linked in wait queue */ 311 int ret; /* return code of checkpoint */ 312 ktime_t queue_time; /* request queued time */ 313}; 314 315struct ckpt_req_control { 316 struct task_struct *f2fs_issue_ckpt; /* checkpoint task */ 317 int ckpt_thread_ioprio; /* checkpoint merge thread ioprio */ 318 wait_queue_head_t ckpt_wait_queue; /* waiting queue for wake-up */ 319 atomic_t issued_ckpt; /* # of actually issued ckpts */ 320 atomic_t total_ckpt; /* # of total ckpts */ 321 atomic_t queued_ckpt; /* # of queued ckpts */ 322 struct llist_head issue_list; /* list for command issue */ 323 spinlock_t stat_lock; /* lock for below checkpoint time stats */ 324 unsigned int cur_time; /* cur wait time in msec for currently issued checkpoint */ 325 unsigned int peak_time; /* peak wait time in msec until now */ 326}; 327 328/* for the bitmap indicate blocks to be discarded */ 329struct discard_entry { 330 struct list_head list; /* list head */ 331 block_t start_blkaddr; /* start blockaddr of current segment */ 332 unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */ 333}; 334 335/* minimum discard granularity, unit: block count */ 336#define MIN_DISCARD_GRANULARITY 1 337/* default discard granularity of inner discard thread, unit: block count */ 338#define DEFAULT_DISCARD_GRANULARITY 16 339/* default maximum discard granularity of ordered discard, unit: block count */ 340#define DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY 16 341 342/* max discard pend list number */ 343#define MAX_PLIST_NUM 512 344#define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ 345 (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) 346 347enum { 348 D_PREP, /* initial */ 349 D_PARTIAL, /* partially submitted */ 350 D_SUBMIT, /* all submitted */ 351 D_DONE, /* finished */ 352}; 353 354struct discard_info { 355 block_t lstart; /* logical start address */ 356 block_t len; /* length */ 357 block_t start; /* actual start address in dev */ 358}; 359 360struct discard_cmd { 361 struct rb_node rb_node; /* rb node located in rb-tree */ 362 struct discard_info di; /* discard info */ 363 struct list_head list; /* command list */ 364 struct completion wait; /* compleation */ 365 struct block_device *bdev; /* bdev */ 366 unsigned short ref; /* reference count */ 367 unsigned char state; /* state */ 368 unsigned char queued; /* queued discard */ 369 int error; /* bio error */ 370 spinlock_t lock; /* for state/bio_ref updating */ 371 unsigned short bio_ref; /* bio reference count */ 372}; 373 374enum { 375 DPOLICY_BG, 376 DPOLICY_FORCE, 377 DPOLICY_FSTRIM, 378 DPOLICY_UMOUNT, 379 MAX_DPOLICY, 380}; 381 382struct discard_policy { 383 int type; /* type of discard */ 384 unsigned int min_interval; /* used for candidates exist */ 385 unsigned int mid_interval; /* used for device busy */ 386 unsigned int max_interval; /* used for candidates not exist */ 387 unsigned int max_requests; /* # of discards issued per round */ 388 unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ 389 bool io_aware; /* issue discard in idle time */ 390 bool sync; /* submit discard with REQ_SYNC flag */ 391 bool ordered; /* issue discard by lba order */ 392 bool timeout; /* discard timeout for put_super */ 393 unsigned int granularity; /* discard granularity */ 394}; 395 396struct discard_cmd_control { 397 struct task_struct *f2fs_issue_discard; /* discard thread */ 398 struct list_head entry_list; /* 4KB discard entry list */ 399 struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */ 400 struct list_head wait_list; /* store on-flushing entries */ 401 struct list_head fstrim_list; /* in-flight discard from fstrim */ 402 wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */ 403 struct mutex cmd_lock; 404 unsigned int nr_discards; /* # of discards in the list */ 405 unsigned int max_discards; /* max. discards to be issued */ 406 unsigned int max_discard_request; /* max. discard request per round */ 407 unsigned int min_discard_issue_time; /* min. interval between discard issue */ 408 unsigned int mid_discard_issue_time; /* mid. interval between discard issue */ 409 unsigned int max_discard_issue_time; /* max. interval between discard issue */ 410 unsigned int discard_io_aware_gran; /* minimum discard granularity not be aware of I/O */ 411 unsigned int discard_urgent_util; /* utilization which issue discard proactively */ 412 unsigned int discard_granularity; /* discard granularity */ 413 unsigned int max_ordered_discard; /* maximum discard granularity issued by lba order */ 414 unsigned int undiscard_blks; /* # of undiscard blocks */ 415 unsigned int next_pos; /* next discard position */ 416 atomic_t issued_discard; /* # of issued discard */ 417 atomic_t queued_discard; /* # of queued discard */ 418 atomic_t discard_cmd_cnt; /* # of cached cmd count */ 419 struct rb_root_cached root; /* root of discard rb-tree */ 420 bool rbtree_check; /* config for consistence check */ 421 bool discard_wake; /* to wake up discard thread */ 422}; 423 424/* for the list of fsync inodes, used only during recovery */ 425struct fsync_inode_entry { 426 struct list_head list; /* list head */ 427 struct inode *inode; /* vfs inode pointer */ 428 block_t blkaddr; /* block address locating the last fsync */ 429 block_t last_dentry; /* block address locating the last dentry */ 430}; 431 432#define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats)) 433#define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits)) 434 435#define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne) 436#define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid) 437#define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se) 438#define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno) 439 440#define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl)) 441#define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl)) 442 443static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i) 444{ 445 int before = nats_in_cursum(journal); 446 447 journal->n_nats = cpu_to_le16(before + i); 448 return before; 449} 450 451static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i) 452{ 453 int before = sits_in_cursum(journal); 454 455 journal->n_sits = cpu_to_le16(before + i); 456 return before; 457} 458 459static inline bool __has_cursum_space(struct f2fs_journal *journal, 460 int size, int type) 461{ 462 if (type == NAT_JOURNAL) 463 return size <= MAX_NAT_JENTRIES(journal); 464 return size <= MAX_SIT_JENTRIES(journal); 465} 466 467/* for inline stuff */ 468#define DEF_INLINE_RESERVED_SIZE 1 469static inline int get_extra_isize(struct inode *inode); 470static inline int get_inline_xattr_addrs(struct inode *inode); 471#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ 472 (CUR_ADDRS_PER_INODE(inode) - \ 473 get_inline_xattr_addrs(inode) - \ 474 DEF_INLINE_RESERVED_SIZE)) 475 476/* for inline dir */ 477#define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ 478 ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ 479 BITS_PER_BYTE + 1)) 480#define INLINE_DENTRY_BITMAP_SIZE(inode) \ 481 DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE) 482#define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \ 483 ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ 484 NR_INLINE_DENTRY(inode) + \ 485 INLINE_DENTRY_BITMAP_SIZE(inode))) 486 487/* 488 * For INODE and NODE manager 489 */ 490/* for directory operations */ 491 492struct f2fs_filename { 493 /* 494 * The filename the user specified. This is NULL for some 495 * filesystem-internal operations, e.g. converting an inline directory 496 * to a non-inline one, or roll-forward recovering an encrypted dentry. 497 */ 498 const struct qstr *usr_fname; 499 500 /* 501 * The on-disk filename. For encrypted directories, this is encrypted. 502 * This may be NULL for lookups in an encrypted dir without the key. 503 */ 504 struct fscrypt_str disk_name; 505 506 /* The dirhash of this filename */ 507 f2fs_hash_t hash; 508 509#ifdef CONFIG_FS_ENCRYPTION 510 /* 511 * For lookups in encrypted directories: either the buffer backing 512 * disk_name, or a buffer that holds the decoded no-key name. 513 */ 514 struct fscrypt_str crypto_buf; 515#endif 516#if IS_ENABLED(CONFIG_UNICODE) 517 /* 518 * For casefolded directories: the casefolded name, but it's left NULL 519 * if the original name is not valid Unicode, if the original name is 520 * "." or "..", if the directory is both casefolded and encrypted and 521 * its encryption key is unavailable, or if the filesystem is doing an 522 * internal operation where usr_fname is also NULL. In all these cases 523 * we fall back to treating the name as an opaque byte sequence. 524 */ 525 struct fscrypt_str cf_name; 526#endif 527}; 528 529struct f2fs_dentry_ptr { 530 struct inode *inode; 531 void *bitmap; 532 struct f2fs_dir_entry *dentry; 533 __u8 (*filename)[F2FS_SLOT_LEN]; 534 int max; 535 int nr_bitmap; 536}; 537 538static inline void make_dentry_ptr_block(struct inode *inode, 539 struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t) 540{ 541 d->inode = inode; 542 d->max = NR_DENTRY_IN_BLOCK; 543 d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; 544 d->bitmap = t->dentry_bitmap; 545 d->dentry = t->dentry; 546 d->filename = t->filename; 547} 548 549static inline void make_dentry_ptr_inline(struct inode *inode, 550 struct f2fs_dentry_ptr *d, void *t) 551{ 552 int entry_cnt = NR_INLINE_DENTRY(inode); 553 int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode); 554 int reserved_size = INLINE_RESERVED_SIZE(inode); 555 556 d->inode = inode; 557 d->max = entry_cnt; 558 d->nr_bitmap = bitmap_size; 559 d->bitmap = t; 560 d->dentry = t + bitmap_size + reserved_size; 561 d->filename = t + bitmap_size + reserved_size + 562 SIZE_OF_DIR_ENTRY * entry_cnt; 563} 564 565/* 566 * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 567 * as its node offset to distinguish from index node blocks. 568 * But some bits are used to mark the node block. 569 */ 570#define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ 571 >> OFFSET_BIT_SHIFT) 572enum { 573 ALLOC_NODE, /* allocate a new node page if needed */ 574 LOOKUP_NODE, /* look up a node without readahead */ 575 LOOKUP_NODE_RA, /* 576 * look up a node with readahead called 577 * by get_data_block. 578 */ 579}; 580 581#define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO or flush count */ 582 583/* congestion wait timeout value, default: 20ms */ 584#define DEFAULT_IO_TIMEOUT (msecs_to_jiffies(20)) 585 586/* maximum retry quota flush count */ 587#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 588 589/* maximum retry of EIO'ed page */ 590#define MAX_RETRY_PAGE_EIO 100 591 592#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ 593 594#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ 595 596/* dirty segments threshold for triggering CP */ 597#define DEFAULT_DIRTY_THRESHOLD 4 598 599#define RECOVERY_MAX_RA_BLOCKS BIO_MAX_VECS 600#define RECOVERY_MIN_RA_BLOCKS 1 601 602#define F2FS_ONSTACK_PAGES 16 /* nr of onstack pages */ 603 604/* for in-memory extent cache entry */ 605#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ 606 607/* number of extent info in extent cache we try to shrink */ 608#define READ_EXTENT_CACHE_SHRINK_NUMBER 128 609 610/* number of age extent info in extent cache we try to shrink */ 611#define AGE_EXTENT_CACHE_SHRINK_NUMBER 128 612#define LAST_AGE_WEIGHT 30 613#define SAME_AGE_REGION 1024 614 615/* 616 * Define data block with age less than 1GB as hot data 617 * define data block with age less than 10GB but more than 1GB as warm data 618 */ 619#define DEF_HOT_DATA_AGE_THRESHOLD 262144 620#define DEF_WARM_DATA_AGE_THRESHOLD 2621440 621 622/* extent cache type */ 623enum extent_type { 624 EX_READ, 625 EX_BLOCK_AGE, 626 NR_EXTENT_CACHES, 627}; 628 629struct extent_info { 630 unsigned int fofs; /* start offset in a file */ 631 unsigned int len; /* length of the extent */ 632 union { 633 /* read extent_cache */ 634 struct { 635 /* start block address of the extent */ 636 block_t blk; 637#ifdef CONFIG_F2FS_FS_COMPRESSION 638 /* physical extent length of compressed blocks */ 639 unsigned int c_len; 640#endif 641 }; 642 /* block age extent_cache */ 643 struct { 644 /* block age of the extent */ 645 unsigned long long age; 646 /* last total blocks allocated */ 647 unsigned long long last_blocks; 648 }; 649 }; 650}; 651 652struct extent_node { 653 struct rb_node rb_node; /* rb node located in rb-tree */ 654 struct extent_info ei; /* extent info */ 655 struct list_head list; /* node in global extent list of sbi */ 656 struct extent_tree *et; /* extent tree pointer */ 657}; 658 659struct extent_tree { 660 nid_t ino; /* inode number */ 661 enum extent_type type; /* keep the extent tree type */ 662 struct rb_root_cached root; /* root of extent info rb-tree */ 663 struct extent_node *cached_en; /* recently accessed extent node */ 664 struct list_head list; /* to be used by sbi->zombie_list */ 665 rwlock_t lock; /* protect extent info rb-tree */ 666 atomic_t node_cnt; /* # of extent node in rb-tree*/ 667 bool largest_updated; /* largest extent updated */ 668 struct extent_info largest; /* largest cached extent for EX_READ */ 669}; 670 671struct extent_tree_info { 672 struct radix_tree_root extent_tree_root;/* cache extent cache entries */ 673 struct mutex extent_tree_lock; /* locking extent radix tree */ 674 struct list_head extent_list; /* lru list for shrinker */ 675 spinlock_t extent_lock; /* locking extent lru list */ 676 atomic_t total_ext_tree; /* extent tree count */ 677 struct list_head zombie_list; /* extent zombie tree list */ 678 atomic_t total_zombie_tree; /* extent zombie tree count */ 679 atomic_t total_ext_node; /* extent info count */ 680}; 681 682/* 683 * State of block returned by f2fs_map_blocks. 684 */ 685#define F2FS_MAP_NEW (1U << 0) 686#define F2FS_MAP_MAPPED (1U << 1) 687#define F2FS_MAP_DELALLOC (1U << 2) 688#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\ 689 F2FS_MAP_DELALLOC) 690 691struct f2fs_map_blocks { 692 struct block_device *m_bdev; /* for multi-device dio */ 693 block_t m_pblk; 694 block_t m_lblk; 695 unsigned int m_len; 696 unsigned int m_flags; 697 pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */ 698 pgoff_t *m_next_extent; /* point to next possible extent */ 699 int m_seg_type; 700 bool m_may_create; /* indicate it is from write path */ 701 bool m_multidev_dio; /* indicate it allows multi-device dio */ 702}; 703 704/* for flag in get_data_block */ 705enum { 706 F2FS_GET_BLOCK_DEFAULT, 707 F2FS_GET_BLOCK_FIEMAP, 708 F2FS_GET_BLOCK_BMAP, 709 F2FS_GET_BLOCK_DIO, 710 F2FS_GET_BLOCK_PRE_DIO, 711 F2FS_GET_BLOCK_PRE_AIO, 712 F2FS_GET_BLOCK_PRECACHE, 713}; 714 715/* 716 * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. 717 */ 718#define FADVISE_COLD_BIT 0x01 719#define FADVISE_LOST_PINO_BIT 0x02 720#define FADVISE_ENCRYPT_BIT 0x04 721#define FADVISE_ENC_NAME_BIT 0x08 722#define FADVISE_KEEP_SIZE_BIT 0x10 723#define FADVISE_HOT_BIT 0x20 724#define FADVISE_VERITY_BIT 0x40 725#define FADVISE_TRUNC_BIT 0x80 726 727#define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT) 728 729#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) 730#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) 731#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) 732 733#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) 734#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) 735#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) 736 737#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT) 738#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT) 739 740#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) 741#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) 742 743#define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) 744#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) 745 746#define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT) 747#define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT) 748#define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT) 749 750#define file_is_verity(inode) is_file(inode, FADVISE_VERITY_BIT) 751#define file_set_verity(inode) set_file(inode, FADVISE_VERITY_BIT) 752 753#define file_should_truncate(inode) is_file(inode, FADVISE_TRUNC_BIT) 754#define file_need_truncate(inode) set_file(inode, FADVISE_TRUNC_BIT) 755#define file_dont_truncate(inode) clear_file(inode, FADVISE_TRUNC_BIT) 756 757#define DEF_DIR_LEVEL 0 758 759enum { 760 GC_FAILURE_PIN, 761 MAX_GC_FAILURE 762}; 763 764/* used for f2fs_inode_info->flags */ 765enum { 766 FI_NEW_INODE, /* indicate newly allocated inode */ 767 FI_DIRTY_INODE, /* indicate inode is dirty or not */ 768 FI_AUTO_RECOVER, /* indicate inode is recoverable */ 769 FI_DIRTY_DIR, /* indicate directory has dirty pages */ 770 FI_INC_LINK, /* need to increment i_nlink */ 771 FI_ACL_MODE, /* indicate acl mode */ 772 FI_NO_ALLOC, /* should not allocate any blocks */ 773 FI_FREE_NID, /* free allocated nide */ 774 FI_NO_EXTENT, /* not to use the extent cache */ 775 FI_INLINE_XATTR, /* used for inline xattr */ 776 FI_INLINE_DATA, /* used for inline data*/ 777 FI_INLINE_DENTRY, /* used for inline dentry */ 778 FI_APPEND_WRITE, /* inode has appended data */ 779 FI_UPDATE_WRITE, /* inode has in-place-update data */ 780 FI_NEED_IPU, /* used for ipu per file */ 781 FI_ATOMIC_FILE, /* indicate atomic file */ 782 FI_DATA_EXIST, /* indicate data exists */ 783 FI_INLINE_DOTS, /* indicate inline dot dentries */ 784 FI_SKIP_WRITES, /* should skip data page writeback */ 785 FI_OPU_WRITE, /* used for opu per file */ 786 FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ 787 FI_PREALLOCATED_ALL, /* all blocks for write were preallocated */ 788 FI_HOT_DATA, /* indicate file is hot */ 789 FI_EXTRA_ATTR, /* indicate file has extra attribute */ 790 FI_PROJ_INHERIT, /* indicate file inherits projectid */ 791 FI_PIN_FILE, /* indicate file should not be gced */ 792 FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ 793 FI_COMPRESSED_FILE, /* indicate file's data can be compressed */ 794 FI_COMPRESS_CORRUPT, /* indicate compressed cluster is corrupted */ 795 FI_MMAP_FILE, /* indicate file was mmapped */ 796 FI_ENABLE_COMPRESS, /* enable compression in "user" compression mode */ 797 FI_COMPRESS_RELEASED, /* compressed blocks were released */ 798 FI_ALIGNED_WRITE, /* enable aligned write */ 799 FI_COW_FILE, /* indicate COW file */ 800 FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */ 801 FI_ATOMIC_REPLACE, /* indicate atomic replace */ 802 FI_MAX, /* max flag, never be used */ 803}; 804 805struct f2fs_inode_info { 806 struct inode vfs_inode; /* serve a vfs inode */ 807 unsigned long i_flags; /* keep an inode flags for ioctl */ 808 unsigned char i_advise; /* use to give file attribute hints */ 809 unsigned char i_dir_level; /* use for dentry level for large dir */ 810 unsigned int i_current_depth; /* only for directory depth */ 811 /* for gc failure statistic */ 812 unsigned int i_gc_failures[MAX_GC_FAILURE]; 813 unsigned int i_pino; /* parent inode number */ 814 umode_t i_acl_mode; /* keep file acl mode temporarily */ 815 816 /* Use below internally in f2fs*/ 817 unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */ 818 struct f2fs_rwsem i_sem; /* protect fi info */ 819 atomic_t dirty_pages; /* # of dirty pages */ 820 f2fs_hash_t chash; /* hash value of given file name */ 821 unsigned int clevel; /* maximum level of given file name */ 822 struct task_struct *task; /* lookup and create consistency */ 823 struct task_struct *cp_task; /* separate cp/wb IO stats*/ 824 struct task_struct *wb_task; /* indicate inode is in context of writeback */ 825 nid_t i_xattr_nid; /* node id that contains xattrs */ 826 loff_t last_disk_size; /* lastly written file size */ 827 spinlock_t i_size_lock; /* protect last_disk_size */ 828 829#ifdef CONFIG_QUOTA 830 struct dquot __rcu *i_dquot[MAXQUOTAS]; 831 832 /* quota space reservation, managed internally by quota code */ 833 qsize_t i_reserved_quota; 834#endif 835 struct list_head dirty_list; /* dirty list for dirs and files */ 836 struct list_head gdirty_list; /* linked in global dirty list */ 837 struct task_struct *atomic_write_task; /* store atomic write task */ 838 struct extent_tree *extent_tree[NR_EXTENT_CACHES]; 839 /* cached extent_tree entry */ 840 struct inode *cow_inode; /* copy-on-write inode for atomic write */ 841 842 /* avoid racing between foreground op and gc */ 843 struct f2fs_rwsem i_gc_rwsem[2]; 844 struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */ 845 846 int i_extra_isize; /* size of extra space located in i_addr */ 847 kprojid_t i_projid; /* id for project quota */ 848 int i_inline_xattr_size; /* inline xattr size */ 849 struct timespec64 i_crtime; /* inode creation time */ 850 struct timespec64 i_disk_time[3];/* inode disk times */ 851 852 /* for file compress */ 853 atomic_t i_compr_blocks; /* # of compressed blocks */ 854 unsigned char i_compress_algorithm; /* algorithm type */ 855 unsigned char i_log_cluster_size; /* log of cluster size */ 856 unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ 857 unsigned char i_compress_flag; /* compress flag */ 858 unsigned int i_cluster_size; /* cluster size */ 859 860 unsigned int atomic_write_cnt; 861 loff_t original_i_size; /* original i_size before atomic write */ 862}; 863 864static inline void get_read_extent_info(struct extent_info *ext, 865 struct f2fs_extent *i_ext) 866{ 867 ext->fofs = le32_to_cpu(i_ext->fofs); 868 ext->blk = le32_to_cpu(i_ext->blk); 869 ext->len = le32_to_cpu(i_ext->len); 870} 871 872static inline void set_raw_read_extent(struct extent_info *ext, 873 struct f2fs_extent *i_ext) 874{ 875 i_ext->fofs = cpu_to_le32(ext->fofs); 876 i_ext->blk = cpu_to_le32(ext->blk); 877 i_ext->len = cpu_to_le32(ext->len); 878} 879 880static inline bool __is_discard_mergeable(struct discard_info *back, 881 struct discard_info *front, unsigned int max_len) 882{ 883 return (back->lstart + back->len == front->lstart) && 884 (back->len + front->len <= max_len); 885} 886 887static inline bool __is_discard_back_mergeable(struct discard_info *cur, 888 struct discard_info *back, unsigned int max_len) 889{ 890 return __is_discard_mergeable(back, cur, max_len); 891} 892 893static inline bool __is_discard_front_mergeable(struct discard_info *cur, 894 struct discard_info *front, unsigned int max_len) 895{ 896 return __is_discard_mergeable(cur, front, max_len); 897} 898 899/* 900 * For free nid management 901 */ 902enum nid_state { 903 FREE_NID, /* newly added to free nid list */ 904 PREALLOC_NID, /* it is preallocated */ 905 MAX_NID_STATE, 906}; 907 908enum nat_state { 909 TOTAL_NAT, 910 DIRTY_NAT, 911 RECLAIMABLE_NAT, 912 MAX_NAT_STATE, 913}; 914 915struct f2fs_nm_info { 916 block_t nat_blkaddr; /* base disk address of NAT */ 917 nid_t max_nid; /* maximum possible node ids */ 918 nid_t available_nids; /* # of available node ids */ 919 nid_t next_scan_nid; /* the next nid to be scanned */ 920 nid_t max_rf_node_blocks; /* max # of nodes for recovery */ 921 unsigned int ram_thresh; /* control the memory footprint */ 922 unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ 923 unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */ 924 925 /* NAT cache management */ 926 struct radix_tree_root nat_root;/* root of the nat entry cache */ 927 struct radix_tree_root nat_set_root;/* root of the nat set cache */ 928 struct f2fs_rwsem nat_tree_lock; /* protect nat entry tree */ 929 struct list_head nat_entries; /* cached nat entry list (clean) */ 930 spinlock_t nat_list_lock; /* protect clean nat entry list */ 931 unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */ 932 unsigned int nat_blocks; /* # of nat blocks */ 933 934 /* free node ids management */ 935 struct radix_tree_root free_nid_root;/* root of the free_nid cache */ 936 struct list_head free_nid_list; /* list for free nids excluding preallocated nids */ 937 unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */ 938 spinlock_t nid_list_lock; /* protect nid lists ops */ 939 struct mutex build_lock; /* lock for build free nids */ 940 unsigned char **free_nid_bitmap; 941 unsigned char *nat_block_bitmap; 942 unsigned short *free_nid_count; /* free nid count of NAT block */ 943 944 /* for checkpoint */ 945 char *nat_bitmap; /* NAT bitmap pointer */ 946 947 unsigned int nat_bits_blocks; /* # of nat bits blocks */ 948 unsigned char *nat_bits; /* NAT bits blocks */ 949 unsigned char *full_nat_bits; /* full NAT pages */ 950 unsigned char *empty_nat_bits; /* empty NAT pages */ 951#ifdef CONFIG_F2FS_CHECK_FS 952 char *nat_bitmap_mir; /* NAT bitmap mirror */ 953#endif 954 int bitmap_size; /* bitmap size */ 955}; 956 957/* 958 * this structure is used as one of function parameters. 959 * all the information are dedicated to a given direct node block determined 960 * by the data offset in a file. 961 */ 962struct dnode_of_data { 963 struct inode *inode; /* vfs inode pointer */ 964 struct page *inode_page; /* its inode page, NULL is possible */ 965 struct page *node_page; /* cached direct node page */ 966 nid_t nid; /* node id of the direct node block */ 967 unsigned int ofs_in_node; /* data offset in the node page */ 968 bool inode_page_locked; /* inode page is locked or not */ 969 bool node_changed; /* is node block changed */ 970 char cur_level; /* level of hole node page */ 971 char max_level; /* level of current page located */ 972 block_t data_blkaddr; /* block address of the node block */ 973}; 974 975static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode, 976 struct page *ipage, struct page *npage, nid_t nid) 977{ 978 memset(dn, 0, sizeof(*dn)); 979 dn->inode = inode; 980 dn->inode_page = ipage; 981 dn->node_page = npage; 982 dn->nid = nid; 983} 984 985/* 986 * For SIT manager 987 * 988 * By default, there are 6 active log areas across the whole main area. 989 * When considering hot and cold data separation to reduce cleaning overhead, 990 * we split 3 for data logs and 3 for node logs as hot, warm, and cold types, 991 * respectively. 992 * In the current design, you should not change the numbers intentionally. 993 * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6 994 * logs individually according to the underlying devices. (default: 6) 995 * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for 996 * data and 8 for node logs. 997 */ 998#define NR_CURSEG_DATA_TYPE (3) 999#define NR_CURSEG_NODE_TYPE (3) 1000#define NR_CURSEG_INMEM_TYPE (2) 1001#define NR_CURSEG_RO_TYPE (2) 1002#define NR_CURSEG_PERSIST_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE) 1003#define NR_CURSEG_TYPE (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE) 1004 1005enum { 1006 CURSEG_HOT_DATA = 0, /* directory entry blocks */ 1007 CURSEG_WARM_DATA, /* data blocks */ 1008 CURSEG_COLD_DATA, /* multimedia or GCed data blocks */ 1009 CURSEG_HOT_NODE, /* direct node blocks of directory files */ 1010 CURSEG_WARM_NODE, /* direct node blocks of normal files */ 1011 CURSEG_COLD_NODE, /* indirect node blocks */ 1012 NR_PERSISTENT_LOG, /* number of persistent log */ 1013 CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG, 1014 /* pinned file that needs consecutive block address */ 1015 CURSEG_ALL_DATA_ATGC, /* SSR alloctor in hot/warm/cold data area */ 1016 NO_CHECK_TYPE, /* number of persistent & inmem log */ 1017}; 1018 1019struct flush_cmd { 1020 struct completion wait; 1021 struct llist_node llnode; 1022 nid_t ino; 1023 int ret; 1024}; 1025 1026struct flush_cmd_control { 1027 struct task_struct *f2fs_issue_flush; /* flush thread */ 1028 wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ 1029 atomic_t issued_flush; /* # of issued flushes */ 1030 atomic_t queued_flush; /* # of queued flushes */ 1031 struct llist_head issue_list; /* list for command issue */ 1032 struct llist_node *dispatch_list; /* list for command dispatch */ 1033}; 1034 1035struct f2fs_sm_info { 1036 struct sit_info *sit_info; /* whole segment information */ 1037 struct free_segmap_info *free_info; /* free segment information */ 1038 struct dirty_seglist_info *dirty_info; /* dirty segment information */ 1039 struct curseg_info *curseg_array; /* active segment information */ 1040 1041 struct f2fs_rwsem curseg_lock; /* for preventing curseg change */ 1042 1043 block_t seg0_blkaddr; /* block address of 0'th segment */ 1044 block_t main_blkaddr; /* start block address of main area */ 1045 block_t ssa_blkaddr; /* start block address of SSA area */ 1046 1047 unsigned int segment_count; /* total # of segments */ 1048 unsigned int main_segments; /* # of segments in main area */ 1049 unsigned int reserved_segments; /* # of reserved segments */ 1050 unsigned int additional_reserved_segments;/* reserved segs for IO align feature */ 1051 unsigned int ovp_segments; /* # of overprovision segments */ 1052 1053 /* a threshold to reclaim prefree segments */ 1054 unsigned int rec_prefree_segments; 1055 1056 struct list_head sit_entry_set; /* sit entry set list */ 1057 1058 unsigned int ipu_policy; /* in-place-update policy */ 1059 unsigned int min_ipu_util; /* in-place-update threshold */ 1060 unsigned int min_fsync_blocks; /* threshold for fsync */ 1061 unsigned int min_seq_blocks; /* threshold for sequential blocks */ 1062 unsigned int min_hot_blocks; /* threshold for hot block allocation */ 1063 unsigned int min_ssr_sections; /* threshold to trigger SSR allocation */ 1064 1065 /* for flush command control */ 1066 struct flush_cmd_control *fcc_info; 1067 1068 /* for discard command control */ 1069 struct discard_cmd_control *dcc_info; 1070}; 1071 1072/* 1073 * For superblock 1074 */ 1075/* 1076 * COUNT_TYPE for monitoring 1077 * 1078 * f2fs monitors the number of several block types such as on-writeback, 1079 * dirty dentry blocks, dirty node blocks, and dirty meta blocks. 1080 */ 1081#define WB_DATA_TYPE(p, f) \ 1082 (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) 1083enum count_type { 1084 F2FS_DIRTY_DENTS, 1085 F2FS_DIRTY_DATA, 1086 F2FS_DIRTY_QDATA, 1087 F2FS_DIRTY_NODES, 1088 F2FS_DIRTY_META, 1089 F2FS_DIRTY_IMETA, 1090 F2FS_WB_CP_DATA, 1091 F2FS_WB_DATA, 1092 F2FS_RD_DATA, 1093 F2FS_RD_NODE, 1094 F2FS_RD_META, 1095 F2FS_DIO_WRITE, 1096 F2FS_DIO_READ, 1097 NR_COUNT_TYPE, 1098}; 1099 1100/* 1101 * The below are the page types of bios used in submit_bio(). 1102 * The available types are: 1103 * DATA User data pages. It operates as async mode. 1104 * NODE Node pages. It operates as async mode. 1105 * META FS metadata pages such as SIT, NAT, CP. 1106 * NR_PAGE_TYPE The number of page types. 1107 * META_FLUSH Make sure the previous pages are written 1108 * with waiting the bio's completion 1109 * ... Only can be used with META. 1110 */ 1111#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type)) 1112enum page_type { 1113 DATA = 0, 1114 NODE = 1, /* should not change this */ 1115 META, 1116 NR_PAGE_TYPE, 1117 META_FLUSH, 1118 IPU, /* the below types are used by tracepoints only. */ 1119 OPU, 1120}; 1121 1122enum temp_type { 1123 HOT = 0, /* must be zero for meta bio */ 1124 WARM, 1125 COLD, 1126 NR_TEMP_TYPE, 1127}; 1128 1129enum need_lock_type { 1130 LOCK_REQ = 0, 1131 LOCK_DONE, 1132 LOCK_RETRY, 1133}; 1134 1135enum cp_reason_type { 1136 CP_NO_NEEDED, 1137 CP_NON_REGULAR, 1138 CP_COMPRESSED, 1139 CP_HARDLINK, 1140 CP_SB_NEED_CP, 1141 CP_WRONG_PINO, 1142 CP_NO_SPC_ROLL, 1143 CP_NODE_NEED_CP, 1144 CP_FASTBOOT_MODE, 1145 CP_SPEC_LOG_NUM, 1146 CP_RECOVER_DIR, 1147}; 1148 1149enum iostat_type { 1150 /* WRITE IO */ 1151 APP_DIRECT_IO, /* app direct write IOs */ 1152 APP_BUFFERED_IO, /* app buffered write IOs */ 1153 APP_WRITE_IO, /* app write IOs */ 1154 APP_MAPPED_IO, /* app mapped IOs */ 1155 APP_BUFFERED_CDATA_IO, /* app buffered write IOs on compressed file */ 1156 APP_MAPPED_CDATA_IO, /* app mapped write IOs on compressed file */ 1157 FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */ 1158 FS_CDATA_IO, /* data IOs from kworker/fsync/reclaimer on compressed file */ 1159 FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */ 1160 FS_META_IO, /* meta IOs from kworker/reclaimer */ 1161 FS_GC_DATA_IO, /* data IOs from forground gc */ 1162 FS_GC_NODE_IO, /* node IOs from forground gc */ 1163 FS_CP_DATA_IO, /* data IOs from checkpoint */ 1164 FS_CP_NODE_IO, /* node IOs from checkpoint */ 1165 FS_CP_META_IO, /* meta IOs from checkpoint */ 1166 1167 /* READ IO */ 1168 APP_DIRECT_READ_IO, /* app direct read IOs */ 1169 APP_BUFFERED_READ_IO, /* app buffered read IOs */ 1170 APP_READ_IO, /* app read IOs */ 1171 APP_MAPPED_READ_IO, /* app mapped read IOs */ 1172 APP_BUFFERED_CDATA_READ_IO, /* app buffered read IOs on compressed file */ 1173 APP_MAPPED_CDATA_READ_IO, /* app mapped read IOs on compressed file */ 1174 FS_DATA_READ_IO, /* data read IOs */ 1175 FS_GDATA_READ_IO, /* data read IOs from background gc */ 1176 FS_CDATA_READ_IO, /* compressed data read IOs */ 1177 FS_NODE_READ_IO, /* node read IOs */ 1178 FS_META_READ_IO, /* meta read IOs */ 1179 1180 /* other */ 1181 FS_DISCARD_IO, /* discard */ 1182 FS_FLUSH_IO, /* flush */ 1183 FS_ZONE_RESET_IO, /* zone reset */ 1184 NR_IO_TYPE, 1185}; 1186 1187struct f2fs_io_info { 1188 struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ 1189 nid_t ino; /* inode number */ 1190 enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ 1191 enum temp_type temp; /* contains HOT/WARM/COLD */ 1192 enum req_op op; /* contains REQ_OP_ */ 1193 blk_opf_t op_flags; /* req_flag_bits */ 1194 block_t new_blkaddr; /* new block address to be written */ 1195 block_t old_blkaddr; /* old block address before Cow */ 1196 struct page *page; /* page to be written */ 1197 struct page *encrypted_page; /* encrypted page */ 1198 struct page *compressed_page; /* compressed page */ 1199 struct list_head list; /* serialize IOs */ 1200 unsigned int compr_blocks; /* # of compressed block addresses */ 1201 unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */ 1202 unsigned int version:8; /* version of the node */ 1203 unsigned int submitted:1; /* indicate IO submission */ 1204 unsigned int in_list:1; /* indicate fio is in io_list */ 1205 unsigned int is_por:1; /* indicate IO is from recovery or not */ 1206 unsigned int retry:1; /* need to reallocate block address */ 1207 unsigned int encrypted:1; /* indicate file is encrypted */ 1208 unsigned int post_read:1; /* require post read */ 1209 enum iostat_type io_type; /* io type */ 1210 struct writeback_control *io_wbc; /* writeback control */ 1211 struct bio **bio; /* bio for ipu */ 1212 sector_t *last_block; /* last block number in bio */ 1213}; 1214 1215struct bio_entry { 1216 struct bio *bio; 1217 struct list_head list; 1218}; 1219 1220#define is_read_io(rw) ((rw) == READ) 1221struct f2fs_bio_info { 1222 struct f2fs_sb_info *sbi; /* f2fs superblock */ 1223 struct bio *bio; /* bios to merge */ 1224 sector_t last_block_in_bio; /* last block number */ 1225 struct f2fs_io_info fio; /* store buffered io info. */ 1226#ifdef CONFIG_BLK_DEV_ZONED 1227 struct completion zone_wait; /* condition value for the previous open zone to close */ 1228 struct bio *zone_pending_bio; /* pending bio for the previous zone */ 1229 void *bi_private; /* previous bi_private for pending bio */ 1230#endif 1231 struct f2fs_rwsem io_rwsem; /* blocking op for bio */ 1232 spinlock_t io_lock; /* serialize DATA/NODE IOs */ 1233 struct list_head io_list; /* track fios */ 1234 struct list_head bio_list; /* bio entry list head */ 1235 struct f2fs_rwsem bio_list_lock; /* lock to protect bio entry list */ 1236}; 1237 1238#define FDEV(i) (sbi->devs[i]) 1239#define RDEV(i) (raw_super->devs[i]) 1240struct f2fs_dev_info { 1241 struct block_device *bdev; 1242 char path[MAX_PATH_LEN]; 1243 unsigned int total_segments; 1244 block_t start_blk; 1245 block_t end_blk; 1246#ifdef CONFIG_BLK_DEV_ZONED 1247 unsigned int nr_blkz; /* Total number of zones */ 1248 unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ 1249#endif 1250}; 1251 1252enum inode_type { 1253 DIR_INODE, /* for dirty dir inode */ 1254 FILE_INODE, /* for dirty regular/symlink inode */ 1255 DIRTY_META, /* for all dirtied inode metadata */ 1256 NR_INODE_TYPE, 1257}; 1258 1259/* for inner inode cache management */ 1260struct inode_management { 1261 struct radix_tree_root ino_root; /* ino entry array */ 1262 spinlock_t ino_lock; /* for ino entry lock */ 1263 struct list_head ino_list; /* inode list head */ 1264 unsigned long ino_num; /* number of entries */ 1265}; 1266 1267/* for GC_AT */ 1268struct atgc_management { 1269 bool atgc_enabled; /* ATGC is enabled or not */ 1270 struct rb_root_cached root; /* root of victim rb-tree */ 1271 struct list_head victim_list; /* linked with all victim entries */ 1272 unsigned int victim_count; /* victim count in rb-tree */ 1273 unsigned int candidate_ratio; /* candidate ratio */ 1274 unsigned int max_candidate_count; /* max candidate count */ 1275 unsigned int age_weight; /* age weight, vblock_weight = 100 - age_weight */ 1276 unsigned long long age_threshold; /* age threshold */ 1277}; 1278 1279struct f2fs_gc_control { 1280 unsigned int victim_segno; /* target victim segment number */ 1281 int init_gc_type; /* FG_GC or BG_GC */ 1282 bool no_bg_gc; /* check the space and stop bg_gc */ 1283 bool should_migrate_blocks; /* should migrate blocks */ 1284 bool err_gc_skipped; /* return EAGAIN if GC skipped */ 1285 unsigned int nr_free_secs; /* # of free sections to do GC */ 1286}; 1287 1288/* 1289 * For s_flag in struct f2fs_sb_info 1290 * Modification on enum should be synchronized with s_flag array 1291 */ 1292enum { 1293 SBI_IS_DIRTY, /* dirty flag for checkpoint */ 1294 SBI_IS_CLOSE, /* specify unmounting */ 1295 SBI_NEED_FSCK, /* need fsck.f2fs to fix */ 1296 SBI_POR_DOING, /* recovery is doing or not */ 1297 SBI_NEED_SB_WRITE, /* need to recover superblock */ 1298 SBI_NEED_CP, /* need to checkpoint */ 1299 SBI_IS_SHUTDOWN, /* shutdown by ioctl */ 1300 SBI_IS_RECOVERED, /* recovered orphan/data */ 1301 SBI_CP_DISABLED, /* CP was disabled last mount */ 1302 SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ 1303 SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ 1304 SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ 1305 SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ 1306 SBI_IS_RESIZEFS, /* resizefs is in process */ 1307 SBI_IS_FREEZING, /* freezefs is in process */ 1308 SBI_IS_WRITABLE, /* remove ro mountoption transiently */ 1309 MAX_SBI_FLAG, 1310}; 1311 1312enum { 1313 CP_TIME, 1314 REQ_TIME, 1315 DISCARD_TIME, 1316 GC_TIME, 1317 DISABLE_TIME, 1318 UMOUNT_DISCARD_TIMEOUT, 1319 MAX_TIME, 1320}; 1321 1322/* Note that you need to keep synchronization with this gc_mode_names array */ 1323enum { 1324 GC_NORMAL, 1325 GC_IDLE_CB, 1326 GC_IDLE_GREEDY, 1327 GC_IDLE_AT, 1328 GC_URGENT_HIGH, 1329 GC_URGENT_LOW, 1330 GC_URGENT_MID, 1331 MAX_GC_MODE, 1332}; 1333 1334enum { 1335 BGGC_MODE_ON, /* background gc is on */ 1336 BGGC_MODE_OFF, /* background gc is off */ 1337 BGGC_MODE_SYNC, /* 1338 * background gc is on, migrating blocks 1339 * like foreground gc 1340 */ 1341}; 1342 1343enum { 1344 FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ 1345 FS_MODE_LFS, /* use lfs allocation only */ 1346 FS_MODE_FRAGMENT_SEG, /* segment fragmentation mode */ 1347 FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */ 1348}; 1349 1350enum { 1351 ALLOC_MODE_DEFAULT, /* stay default */ 1352 ALLOC_MODE_REUSE, /* reuse segments as much as possible */ 1353}; 1354 1355enum fsync_mode { 1356 FSYNC_MODE_POSIX, /* fsync follows posix semantics */ 1357 FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ 1358 FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ 1359}; 1360 1361enum { 1362 COMPR_MODE_FS, /* 1363 * automatically compress compression 1364 * enabled files 1365 */ 1366 COMPR_MODE_USER, /* 1367 * automatical compression is disabled. 1368 * user can control the file compression 1369 * using ioctls 1370 */ 1371}; 1372 1373enum { 1374 DISCARD_UNIT_BLOCK, /* basic discard unit is block */ 1375 DISCARD_UNIT_SEGMENT, /* basic discard unit is segment */ 1376 DISCARD_UNIT_SECTION, /* basic discard unit is section */ 1377}; 1378 1379enum { 1380 MEMORY_MODE_NORMAL, /* memory mode for normal devices */ 1381 MEMORY_MODE_LOW, /* memory mode for low memry devices */ 1382}; 1383 1384enum errors_option { 1385 MOUNT_ERRORS_READONLY, /* remount fs ro on errors */ 1386 MOUNT_ERRORS_CONTINUE, /* continue on errors */ 1387 MOUNT_ERRORS_PANIC, /* panic on errors */ 1388}; 1389 1390enum { 1391 BACKGROUND, 1392 FOREGROUND, 1393 MAX_CALL_TYPE, 1394 TOTAL_CALL = FOREGROUND, 1395}; 1396 1397static inline int f2fs_test_bit(unsigned int nr, char *addr); 1398static inline void f2fs_set_bit(unsigned int nr, char *addr); 1399static inline void f2fs_clear_bit(unsigned int nr, char *addr); 1400 1401/* 1402 * Layout of f2fs page.private: 1403 * 1404 * Layout A: lowest bit should be 1 1405 * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | 1406 * bit 0 PAGE_PRIVATE_NOT_POINTER 1407 * bit 1 PAGE_PRIVATE_DUMMY_WRITE 1408 * bit 2 PAGE_PRIVATE_ONGOING_MIGRATION 1409 * bit 3 PAGE_PRIVATE_INLINE_INODE 1410 * bit 4 PAGE_PRIVATE_REF_RESOURCE 1411 * bit 5- f2fs private data 1412 * 1413 * Layout B: lowest bit should be 0 1414 * page.private is a wrapped pointer. 1415 */ 1416enum { 1417 PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */ 1418 PAGE_PRIVATE_DUMMY_WRITE, /* data page for padding aligned IO */ 1419 PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */ 1420 PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */ 1421 PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */ 1422 PAGE_PRIVATE_MAX 1423}; 1424 1425/* For compression */ 1426enum compress_algorithm_type { 1427 COMPRESS_LZO, 1428 COMPRESS_LZ4, 1429 COMPRESS_ZSTD, 1430 COMPRESS_LZORLE, 1431 COMPRESS_MAX, 1432}; 1433 1434enum compress_flag { 1435 COMPRESS_CHKSUM, 1436 COMPRESS_MAX_FLAG, 1437}; 1438 1439#define COMPRESS_WATERMARK 20 1440#define COMPRESS_PERCENT 20 1441 1442#define COMPRESS_DATA_RESERVED_SIZE 4 1443struct compress_data { 1444 __le32 clen; /* compressed data size */ 1445 __le32 chksum; /* compressed data chksum */ 1446 __le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */ 1447 u8 cdata[]; /* compressed data */ 1448}; 1449 1450#define COMPRESS_HEADER_SIZE (sizeof(struct compress_data)) 1451 1452#define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 1453 1454#define F2FS_ZSTD_DEFAULT_CLEVEL 1 1455 1456#define COMPRESS_LEVEL_OFFSET 8 1457 1458/* compress context */ 1459struct compress_ctx { 1460 struct inode *inode; /* inode the context belong to */ 1461 pgoff_t cluster_idx; /* cluster index number */ 1462 unsigned int cluster_size; /* page count in cluster */ 1463 unsigned int log_cluster_size; /* log of cluster size */ 1464 struct page **rpages; /* pages store raw data in cluster */ 1465 unsigned int nr_rpages; /* total page number in rpages */ 1466 struct page **cpages; /* pages store compressed data in cluster */ 1467 unsigned int nr_cpages; /* total page number in cpages */ 1468 unsigned int valid_nr_cpages; /* valid page number in cpages */ 1469 void *rbuf; /* virtual mapped address on rpages */ 1470 struct compress_data *cbuf; /* virtual mapped address on cpages */ 1471 size_t rlen; /* valid data length in rbuf */ 1472 size_t clen; /* valid data length in cbuf */ 1473 void *private; /* payload buffer for specified compression algorithm */ 1474 void *private2; /* extra payload buffer */ 1475}; 1476 1477/* compress context for write IO path */ 1478struct compress_io_ctx { 1479 u32 magic; /* magic number to indicate page is compressed */ 1480 struct inode *inode; /* inode the context belong to */ 1481 struct page **rpages; /* pages store raw data in cluster */ 1482 unsigned int nr_rpages; /* total page number in rpages */ 1483 atomic_t pending_pages; /* in-flight compressed page count */ 1484}; 1485 1486/* Context for decompressing one cluster on the read IO path */ 1487struct decompress_io_ctx { 1488 u32 magic; /* magic number to indicate page is compressed */ 1489 struct inode *inode; /* inode the context belong to */ 1490 pgoff_t cluster_idx; /* cluster index number */ 1491 unsigned int cluster_size; /* page count in cluster */ 1492 unsigned int log_cluster_size; /* log of cluster size */ 1493 struct page **rpages; /* pages store raw data in cluster */ 1494 unsigned int nr_rpages; /* total page number in rpages */ 1495 struct page **cpages; /* pages store compressed data in cluster */ 1496 unsigned int nr_cpages; /* total page number in cpages */ 1497 struct page **tpages; /* temp pages to pad holes in cluster */ 1498 void *rbuf; /* virtual mapped address on rpages */ 1499 struct compress_data *cbuf; /* virtual mapped address on cpages */ 1500 size_t rlen; /* valid data length in rbuf */ 1501 size_t clen; /* valid data length in cbuf */ 1502 1503 /* 1504 * The number of compressed pages remaining to be read in this cluster. 1505 * This is initially nr_cpages. It is decremented by 1 each time a page 1506 * has been read (or failed to be read). When it reaches 0, the cluster 1507 * is decompressed (or an error is reported). 1508 * 1509 * If an error occurs before all the pages have been submitted for I/O, 1510 * then this will never reach 0. In this case the I/O submitter is 1511 * responsible for calling f2fs_decompress_end_io() instead. 1512 */ 1513 atomic_t remaining_pages; 1514 1515 /* 1516 * Number of references to this decompress_io_ctx. 1517 * 1518 * One reference is held for I/O completion. This reference is dropped 1519 * after the pagecache pages are updated and unlocked -- either after 1520 * decompression (and verity if enabled), or after an error. 1521 * 1522 * In addition, each compressed page holds a reference while it is in a 1523 * bio. These references are necessary prevent compressed pages from 1524 * being freed while they are still in a bio. 1525 */ 1526 refcount_t refcnt; 1527 1528 bool failed; /* IO error occurred before decompression? */ 1529 bool need_verity; /* need fs-verity verification after decompression? */ 1530 void *private; /* payload buffer for specified decompression algorithm */ 1531 void *private2; /* extra payload buffer */ 1532 struct work_struct verity_work; /* work to verify the decompressed pages */ 1533 struct work_struct free_work; /* work for late free this structure itself */ 1534}; 1535 1536#define NULL_CLUSTER ((unsigned int)(~0)) 1537#define MIN_COMPRESS_LOG_SIZE 2 1538#define MAX_COMPRESS_LOG_SIZE 8 1539#define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size)) 1540 1541struct f2fs_sb_info { 1542 struct super_block *sb; /* pointer to VFS super block */ 1543 struct proc_dir_entry *s_proc; /* proc entry */ 1544 struct f2fs_super_block *raw_super; /* raw super block pointer */ 1545 struct f2fs_rwsem sb_lock; /* lock for raw super block */ 1546 int valid_super_block; /* valid super block no */ 1547 unsigned long s_flag; /* flags for sbi */ 1548 struct mutex writepages; /* mutex for writepages() */ 1549 1550#ifdef CONFIG_BLK_DEV_ZONED 1551 unsigned int blocks_per_blkz; /* F2FS blocks per zone */ 1552#endif 1553 1554 /* for node-related operations */ 1555 struct f2fs_nm_info *nm_info; /* node manager */ 1556 struct inode *node_inode; /* cache node blocks */ 1557 1558 /* for segment-related operations */ 1559 struct f2fs_sm_info *sm_info; /* segment manager */ 1560 1561 /* for bio operations */ 1562 struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ 1563 /* keep migration IO order for LFS mode */ 1564 struct f2fs_rwsem io_order_lock; 1565 mempool_t *write_io_dummy; /* Dummy pages */ 1566 pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */ 1567 int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */ 1568 1569 /* for checkpoint */ 1570 struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ 1571 int cur_cp_pack; /* remain current cp pack */ 1572 spinlock_t cp_lock; /* for flag in ckpt */ 1573 struct inode *meta_inode; /* cache meta blocks */ 1574 struct f2fs_rwsem cp_global_sem; /* checkpoint procedure lock */ 1575 struct f2fs_rwsem cp_rwsem; /* blocking FS operations */ 1576 struct f2fs_rwsem node_write; /* locking node writes */ 1577 struct f2fs_rwsem node_change; /* locking node change */ 1578 wait_queue_head_t cp_wait; 1579 unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ 1580 long interval_time[MAX_TIME]; /* to store thresholds */ 1581 struct ckpt_req_control cprc_info; /* for checkpoint request control */ 1582 1583 struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ 1584 1585 spinlock_t fsync_node_lock; /* for node entry lock */ 1586 struct list_head fsync_node_list; /* node list head */ 1587 unsigned int fsync_seg_id; /* sequence id */ 1588 unsigned int fsync_node_num; /* number of node entries */ 1589 1590 /* for orphan inode, use 0'th array */ 1591 unsigned int max_orphans; /* max orphan inodes */ 1592 1593 /* for inode management */ 1594 struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ 1595 spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ 1596 struct mutex flush_lock; /* for flush exclusion */ 1597 1598 /* for extent tree cache */ 1599 struct extent_tree_info extent_tree[NR_EXTENT_CACHES]; 1600 atomic64_t allocated_data_blocks; /* for block age extent_cache */ 1601 1602 /* The threshold used for hot and warm data seperation*/ 1603 unsigned int hot_data_age_threshold; 1604 unsigned int warm_data_age_threshold; 1605 unsigned int last_age_weight; 1606 1607 /* basic filesystem units */ 1608 unsigned int log_sectors_per_block; /* log2 sectors per block */ 1609 unsigned int log_blocksize; /* log2 block size */ 1610 unsigned int blocksize; /* block size */ 1611 unsigned int root_ino_num; /* root inode number*/ 1612 unsigned int node_ino_num; /* node inode number*/ 1613 unsigned int meta_ino_num; /* meta inode number*/ 1614 unsigned int log_blocks_per_seg; /* log2 blocks per segment */ 1615 unsigned int blocks_per_seg; /* blocks per segment */ 1616 unsigned int unusable_blocks_per_sec; /* unusable blocks per section */ 1617 unsigned int segs_per_sec; /* segments per section */ 1618 unsigned int secs_per_zone; /* sections per zone */ 1619 unsigned int total_sections; /* total section count */ 1620 unsigned int total_node_count; /* total node block count */ 1621 unsigned int total_valid_node_count; /* valid node block count */ 1622 int dir_level; /* directory level */ 1623 bool readdir_ra; /* readahead inode in readdir */ 1624 u64 max_io_bytes; /* max io bytes to merge IOs */ 1625 1626 block_t user_block_count; /* # of user blocks */ 1627 block_t total_valid_block_count; /* # of valid blocks */ 1628 block_t discard_blks; /* discard command candidats */ 1629 block_t last_valid_block_count; /* for recovery */ 1630 block_t reserved_blocks; /* configurable reserved blocks */ 1631 block_t current_reserved_blocks; /* current reserved blocks */ 1632 1633 /* Additional tracking for no checkpoint mode */ 1634 block_t unusable_block_count; /* # of blocks saved by last cp */ 1635 1636 unsigned int nquota_files; /* # of quota sysfile */ 1637 struct f2fs_rwsem quota_sem; /* blocking cp for flags */ 1638 1639 /* # of pages, see count_type */ 1640 atomic_t nr_pages[NR_COUNT_TYPE]; 1641 /* # of allocated blocks */ 1642 struct percpu_counter alloc_valid_block_count; 1643 /* # of node block writes as roll forward recovery */ 1644 struct percpu_counter rf_node_block_count; 1645 1646 /* writeback control */ 1647 atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ 1648 1649 /* valid inode count */ 1650 struct percpu_counter total_valid_inode_count; 1651 1652 struct f2fs_mount_info mount_opt; /* mount options */ 1653 1654 /* for cleaning operations */ 1655 struct f2fs_rwsem gc_lock; /* 1656 * semaphore for GC, avoid 1657 * race between GC and GC or CP 1658 */ 1659 struct f2fs_gc_kthread *gc_thread; /* GC thread */ 1660 struct atgc_management am; /* atgc management */ 1661 unsigned int cur_victim_sec; /* current victim section num */ 1662 unsigned int gc_mode; /* current GC state */ 1663 unsigned int next_victim_seg[2]; /* next segment in victim section */ 1664 spinlock_t gc_remaining_trials_lock; 1665 /* remaining trial count for GC_URGENT_* and GC_IDLE_* */ 1666 unsigned int gc_remaining_trials; 1667 1668 /* for skip statistic */ 1669 unsigned long long skipped_gc_rwsem; /* FG_GC only */ 1670 1671 /* threshold for gc trials on pinned files */ 1672 u64 gc_pin_file_threshold; 1673 struct f2fs_rwsem pin_sem; 1674 1675 /* maximum # of trials to find a victim segment for SSR and GC */ 1676 unsigned int max_victim_search; 1677 /* migration granularity of garbage collection, unit: segment */ 1678 unsigned int migration_granularity; 1679 1680 /* 1681 * for stat information. 1682 * one is for the LFS mode, and the other is for the SSR mode. 1683 */ 1684#ifdef CONFIG_F2FS_STAT_FS 1685 struct f2fs_stat_info *stat_info; /* FS status information */ 1686 atomic_t meta_count[META_MAX]; /* # of meta blocks */ 1687 unsigned int segment_count[2]; /* # of allocated segments */ 1688 unsigned int block_count[2]; /* # of allocated blocks */ 1689 atomic_t inplace_count; /* # of inplace update */ 1690 /* # of lookup extent cache */ 1691 atomic64_t total_hit_ext[NR_EXTENT_CACHES]; 1692 /* # of hit rbtree extent node */ 1693 atomic64_t read_hit_rbtree[NR_EXTENT_CACHES]; 1694 /* # of hit cached extent node */ 1695 atomic64_t read_hit_cached[NR_EXTENT_CACHES]; 1696 /* # of hit largest extent node in read extent cache */ 1697 atomic64_t read_hit_largest; 1698 atomic_t inline_xattr; /* # of inline_xattr inodes */ 1699 atomic_t inline_inode; /* # of inline_data inodes */ 1700 atomic_t inline_dir; /* # of inline_dentry inodes */ 1701 atomic_t compr_inode; /* # of compressed inodes */ 1702 atomic64_t compr_blocks; /* # of compressed blocks */ 1703 atomic_t swapfile_inode; /* # of swapfile inodes */ 1704 atomic_t atomic_files; /* # of opened atomic file */ 1705 atomic_t max_aw_cnt; /* max # of atomic writes */ 1706 unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ 1707 unsigned int other_skip_bggc; /* skip background gc for other reasons */ 1708 unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ 1709 atomic_t cp_call_count[MAX_CALL_TYPE]; /* # of cp call */ 1710#endif 1711 spinlock_t stat_lock; /* lock for stat operations */ 1712 1713 /* to attach REQ_META|REQ_FUA flags */ 1714 unsigned int data_io_flag; 1715 unsigned int node_io_flag; 1716 1717 /* For sysfs support */ 1718 struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */ 1719 struct completion s_kobj_unregister; 1720 1721 struct kobject s_stat_kobj; /* /sys/fs/f2fs/<devname>/stat */ 1722 struct completion s_stat_kobj_unregister; 1723 1724 struct kobject s_feature_list_kobj; /* /sys/fs/f2fs/<devname>/feature_list */ 1725 struct completion s_feature_list_kobj_unregister; 1726 1727 /* For shrinker support */ 1728 struct list_head s_list; 1729 struct mutex umount_mutex; 1730 unsigned int shrinker_run_no; 1731 1732 /* For multi devices */ 1733 int s_ndevs; /* number of devices */ 1734 struct f2fs_dev_info *devs; /* for device list */ 1735 unsigned int dirty_device; /* for checkpoint data flush */ 1736 spinlock_t dev_lock; /* protect dirty_device */ 1737 bool aligned_blksize; /* all devices has the same logical blksize */ 1738 1739 /* For write statistics */ 1740 u64 sectors_written_start; 1741 u64 kbytes_written; 1742 1743 /* Reference to checksum algorithm driver via cryptoapi */ 1744 struct crypto_shash *s_chksum_driver; 1745 1746 /* Precomputed FS UUID checksum for seeding other checksums */ 1747 __u32 s_chksum_seed; 1748 1749 struct workqueue_struct *post_read_wq; /* post read workqueue */ 1750 1751 /* 1752 * If we are in irq context, let's update error information into 1753 * on-disk superblock in the work. 1754 */ 1755 struct work_struct s_error_work; 1756 unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */ 1757 unsigned char stop_reason[MAX_STOP_REASON]; /* stop reason */ 1758 spinlock_t error_lock; /* protect errors/stop_reason array */ 1759 bool error_dirty; /* errors of sb is dirty */ 1760 1761 struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ 1762 unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ 1763 1764 /* For reclaimed segs statistics per each GC mode */ 1765 unsigned int gc_segment_mode; /* GC state for reclaimed segments */ 1766 unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ 1767 1768 unsigned long seq_file_ra_mul; /* multiplier for ra_pages of seq. files in fadvise */ 1769 1770 int max_fragment_chunk; /* max chunk size for block fragmentation mode */ 1771 int max_fragment_hole; /* max hole size for block fragmentation mode */ 1772 1773 /* For atomic write statistics */ 1774 atomic64_t current_atomic_write; 1775 s64 peak_atomic_write; 1776 u64 committed_atomic_block; 1777 u64 revoked_atomic_block; 1778 1779#ifdef CONFIG_F2FS_FS_COMPRESSION 1780 struct kmem_cache *page_array_slab; /* page array entry */ 1781 unsigned int page_array_slab_size; /* default page array slab size */ 1782 1783 /* For runtime compression statistics */ 1784 u64 compr_written_block; 1785 u64 compr_saved_block; 1786 u32 compr_new_inode; 1787 1788 /* For compressed block cache */ 1789 struct inode *compress_inode; /* cache compressed blocks */ 1790 unsigned int compress_percent; /* cache page percentage */ 1791 unsigned int compress_watermark; /* cache page watermark */ 1792 atomic_t compress_page_hit; /* cache hit count */ 1793#endif 1794 1795#ifdef CONFIG_F2FS_IOSTAT 1796 /* For app/fs IO statistics */ 1797 spinlock_t iostat_lock; 1798 unsigned long long iostat_count[NR_IO_TYPE]; 1799 unsigned long long iostat_bytes[NR_IO_TYPE]; 1800 unsigned long long prev_iostat_bytes[NR_IO_TYPE]; 1801 bool iostat_enable; 1802 unsigned long iostat_next_period; 1803 unsigned int iostat_period_ms; 1804 1805 /* For io latency related statistics info in one iostat period */ 1806 spinlock_t iostat_lat_lock; 1807 struct iostat_lat_info *iostat_io_lat; 1808#endif 1809}; 1810 1811#ifdef CONFIG_F2FS_FAULT_INJECTION 1812#define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__, \ 1813 __builtin_return_address(0)) 1814static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type, 1815 const char *func, const char *parent_func) 1816{ 1817 struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; 1818 1819 if (!ffi->inject_rate) 1820 return false; 1821 1822 if (!IS_FAULT_SET(ffi, type)) 1823 return false; 1824 1825 atomic_inc(&ffi->inject_ops); 1826 if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) { 1827 atomic_set(&ffi->inject_ops, 0); 1828 printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", 1829 KERN_INFO, sbi->sb->s_id, f2fs_fault_name[type], 1830 func, parent_func); 1831 return true; 1832 } 1833 return false; 1834} 1835#else 1836static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) 1837{ 1838 return false; 1839} 1840#endif 1841 1842/* 1843 * Test if the mounted volume is a multi-device volume. 1844 * - For a single regular disk volume, sbi->s_ndevs is 0. 1845 * - For a single zoned disk volume, sbi->s_ndevs is 1. 1846 * - For a multi-device volume, sbi->s_ndevs is always 2 or more. 1847 */ 1848static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) 1849{ 1850 return sbi->s_ndevs > 1; 1851} 1852 1853static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) 1854{ 1855 unsigned long now = jiffies; 1856 1857 sbi->last_time[type] = now; 1858 1859 /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ 1860 if (type == REQ_TIME) { 1861 sbi->last_time[DISCARD_TIME] = now; 1862 sbi->last_time[GC_TIME] = now; 1863 } 1864} 1865 1866static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) 1867{ 1868 unsigned long interval = sbi->interval_time[type] * HZ; 1869 1870 return time_after(jiffies, sbi->last_time[type] + interval); 1871} 1872 1873static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, 1874 int type) 1875{ 1876 unsigned long interval = sbi->interval_time[type] * HZ; 1877 unsigned int wait_ms = 0; 1878 long delta; 1879 1880 delta = (sbi->last_time[type] + interval) - jiffies; 1881 if (delta > 0) 1882 wait_ms = jiffies_to_msecs(delta); 1883 1884 return wait_ms; 1885} 1886 1887/* 1888 * Inline functions 1889 */ 1890static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, 1891 const void *address, unsigned int length) 1892{ 1893 struct { 1894 struct shash_desc shash; 1895 char ctx[4]; 1896 } desc; 1897 int err; 1898 1899 BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); 1900 1901 desc.shash.tfm = sbi->s_chksum_driver; 1902 *(u32 *)desc.ctx = crc; 1903 1904 err = crypto_shash_update(&desc.shash, address, length); 1905 BUG_ON(err); 1906 1907 return *(u32 *)desc.ctx; 1908} 1909 1910static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, 1911 unsigned int length) 1912{ 1913 return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length); 1914} 1915 1916static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, 1917 void *buf, size_t buf_size) 1918{ 1919 return f2fs_crc32(sbi, buf, buf_size) == blk_crc; 1920} 1921 1922static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, 1923 const void *address, unsigned int length) 1924{ 1925 return __f2fs_crc32(sbi, crc, address, length); 1926} 1927 1928static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) 1929{ 1930 return container_of(inode, struct f2fs_inode_info, vfs_inode); 1931} 1932 1933static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb) 1934{ 1935 return sb->s_fs_info; 1936} 1937 1938static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode) 1939{ 1940 return F2FS_SB(inode->i_sb); 1941} 1942 1943static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) 1944{ 1945 return F2FS_I_SB(mapping->host); 1946} 1947 1948static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) 1949{ 1950 return F2FS_M_SB(page_file_mapping(page)); 1951} 1952 1953static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) 1954{ 1955 return (struct f2fs_super_block *)(sbi->raw_super); 1956} 1957 1958static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi) 1959{ 1960 return (struct f2fs_checkpoint *)(sbi->ckpt); 1961} 1962 1963static inline struct f2fs_node *F2FS_NODE(struct page *page) 1964{ 1965 return (struct f2fs_node *)page_address(page); 1966} 1967 1968static inline struct f2fs_inode *F2FS_INODE(struct page *page) 1969{ 1970 return &((struct f2fs_node *)page_address(page))->i; 1971} 1972 1973static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi) 1974{ 1975 return (struct f2fs_nm_info *)(sbi->nm_info); 1976} 1977 1978static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi) 1979{ 1980 return (struct f2fs_sm_info *)(sbi->sm_info); 1981} 1982 1983static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi) 1984{ 1985 return (struct sit_info *)(SM_I(sbi)->sit_info); 1986} 1987 1988static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi) 1989{ 1990 return (struct free_segmap_info *)(SM_I(sbi)->free_info); 1991} 1992 1993static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi) 1994{ 1995 return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info); 1996} 1997 1998static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi) 1999{ 2000 return sbi->meta_inode->i_mapping; 2001} 2002 2003static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi) 2004{ 2005 return sbi->node_inode->i_mapping; 2006} 2007 2008static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type) 2009{ 2010 return test_bit(type, &sbi->s_flag); 2011} 2012 2013static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) 2014{ 2015 set_bit(type, &sbi->s_flag); 2016} 2017 2018static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) 2019{ 2020 clear_bit(type, &sbi->s_flag); 2021} 2022 2023static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) 2024{ 2025 return le64_to_cpu(cp->checkpoint_ver); 2026} 2027 2028static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type) 2029{ 2030 if (type < F2FS_MAX_QUOTAS) 2031 return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]); 2032 return 0; 2033} 2034 2035static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp) 2036{ 2037 size_t crc_offset = le32_to_cpu(cp->checksum_offset); 2038 return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset))); 2039} 2040 2041static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) 2042{ 2043 unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); 2044 2045 return ckpt_flags & f; 2046} 2047 2048static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) 2049{ 2050 return __is_set_ckpt_flags(F2FS_CKPT(sbi), f); 2051} 2052 2053static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) 2054{ 2055 unsigned int ckpt_flags; 2056 2057 ckpt_flags = le32_to_cpu(cp->ckpt_flags); 2058 ckpt_flags |= f; 2059 cp->ckpt_flags = cpu_to_le32(ckpt_flags); 2060} 2061 2062static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) 2063{ 2064 unsigned long flags; 2065 2066 spin_lock_irqsave(&sbi->cp_lock, flags); 2067 __set_ckpt_flags(F2FS_CKPT(sbi), f); 2068 spin_unlock_irqrestore(&sbi->cp_lock, flags); 2069} 2070 2071static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) 2072{ 2073 unsigned int ckpt_flags; 2074 2075 ckpt_flags = le32_to_cpu(cp->ckpt_flags); 2076 ckpt_flags &= (~f); 2077 cp->ckpt_flags = cpu_to_le32(ckpt_flags); 2078} 2079 2080static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) 2081{ 2082 unsigned long flags; 2083 2084 spin_lock_irqsave(&sbi->cp_lock, flags); 2085 __clear_ckpt_flags(F2FS_CKPT(sbi), f); 2086 spin_unlock_irqrestore(&sbi->cp_lock, flags); 2087} 2088 2089#define init_f2fs_rwsem(sem) \ 2090do { \ 2091 static struct lock_class_key __key; \ 2092 \ 2093 __init_f2fs_rwsem((sem), #sem, &__key); \ 2094} while (0) 2095 2096static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem, 2097 const char *sem_name, struct lock_class_key *key) 2098{ 2099 __init_rwsem(&sem->internal_rwsem, sem_name, key); 2100#ifdef CONFIG_F2FS_UNFAIR_RWSEM 2101 init_waitqueue_head(&sem->read_waiters); 2102#endif 2103} 2104 2105static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem) 2106{ 2107 return rwsem_is_locked(&sem->internal_rwsem); 2108} 2109 2110static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem) 2111{ 2112 return rwsem_is_contended(&sem->internal_rwsem); 2113} 2114 2115static inline void f2fs_down_read(struct f2fs_rwsem *sem) 2116{ 2117#ifdef CONFIG_F2FS_UNFAIR_RWSEM 2118 wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem)); 2119#else 2120 down_read(&sem->internal_rwsem); 2121#endif 2122} 2123 2124static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem) 2125{ 2126 return down_read_trylock(&sem->internal_rwsem); 2127} 2128 2129static inline void f2fs_up_read(struct f2fs_rwsem *sem) 2130{ 2131 up_read(&sem->internal_rwsem); 2132} 2133 2134static inline void f2fs_down_write(struct f2fs_rwsem *sem) 2135{ 2136 down_write(&sem->internal_rwsem); 2137} 2138 2139#ifdef CONFIG_DEBUG_LOCK_ALLOC 2140static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass) 2141{ 2142 down_read_nested(&sem->internal_rwsem, subclass); 2143} 2144 2145static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass) 2146{ 2147 down_write_nested(&sem->internal_rwsem, subclass); 2148} 2149#else 2150#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem) 2151#define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem) 2152#endif 2153 2154static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem) 2155{ 2156 return down_write_trylock(&sem->internal_rwsem); 2157} 2158 2159static inline void f2fs_up_write(struct f2fs_rwsem *sem) 2160{ 2161 up_write(&sem->internal_rwsem); 2162#ifdef CONFIG_F2FS_UNFAIR_RWSEM 2163 wake_up_all(&sem->read_waiters); 2164#endif 2165} 2166 2167static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) 2168{ 2169 f2fs_down_read(&sbi->cp_rwsem); 2170} 2171 2172static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi) 2173{ 2174 if (time_to_inject(sbi, FAULT_LOCK_OP)) 2175 return 0; 2176 return f2fs_down_read_trylock(&sbi->cp_rwsem); 2177} 2178 2179static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) 2180{ 2181 f2fs_up_read(&sbi->cp_rwsem); 2182} 2183 2184static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) 2185{ 2186 f2fs_down_write(&sbi->cp_rwsem); 2187} 2188 2189static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) 2190{ 2191 f2fs_up_write(&sbi->cp_rwsem); 2192} 2193 2194static inline int __get_cp_reason(struct f2fs_sb_info *sbi) 2195{ 2196 int reason = CP_SYNC; 2197 2198 if (test_opt(sbi, FASTBOOT)) 2199 reason = CP_FASTBOOT; 2200 if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) 2201 reason = CP_UMOUNT; 2202 return reason; 2203} 2204 2205static inline bool __remain_node_summaries(int reason) 2206{ 2207 return (reason & (CP_UMOUNT | CP_FASTBOOT)); 2208} 2209 2210static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) 2211{ 2212 return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) || 2213 is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG)); 2214} 2215 2216/* 2217 * Check whether the inode has blocks or not 2218 */ 2219static inline int F2FS_HAS_BLOCKS(struct inode *inode) 2220{ 2221 block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0; 2222 2223 return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block; 2224} 2225 2226static inline bool f2fs_has_xattr_block(unsigned int ofs) 2227{ 2228 return ofs == XATTR_NODE_OFFSET; 2229} 2230 2231static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, 2232 struct inode *inode, bool cap) 2233{ 2234 if (!inode) 2235 return true; 2236 if (!test_opt(sbi, RESERVE_ROOT)) 2237 return false; 2238 if (IS_NOQUOTA(inode)) 2239 return true; 2240 if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid())) 2241 return true; 2242 if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && 2243 in_group_p(F2FS_OPTION(sbi).s_resgid)) 2244 return true; 2245 if (cap && capable(CAP_SYS_RESOURCE)) 2246 return true; 2247 return false; 2248} 2249 2250static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); 2251static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, 2252 struct inode *inode, blkcnt_t *count, bool partial) 2253{ 2254 blkcnt_t diff = 0, release = 0; 2255 block_t avail_user_block_count; 2256 int ret; 2257 2258 ret = dquot_reserve_block(inode, *count); 2259 if (ret) 2260 return ret; 2261 2262 if (time_to_inject(sbi, FAULT_BLOCK)) { 2263 release = *count; 2264 goto release_quota; 2265 } 2266 2267 /* 2268 * let's increase this in prior to actual block count change in order 2269 * for f2fs_sync_file to avoid data races when deciding checkpoint. 2270 */ 2271 percpu_counter_add(&sbi->alloc_valid_block_count, (*count)); 2272 2273 spin_lock(&sbi->stat_lock); 2274 sbi->total_valid_block_count += (block_t)(*count); 2275 avail_user_block_count = sbi->user_block_count - 2276 sbi->current_reserved_blocks; 2277 2278 if (!__allow_reserved_blocks(sbi, inode, true)) 2279 avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; 2280 2281 if (F2FS_IO_ALIGNED(sbi)) 2282 avail_user_block_count -= sbi->blocks_per_seg * 2283 SM_I(sbi)->additional_reserved_segments; 2284 2285 if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { 2286 if (avail_user_block_count > sbi->unusable_block_count) 2287 avail_user_block_count -= sbi->unusable_block_count; 2288 else 2289 avail_user_block_count = 0; 2290 } 2291 if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { 2292 if (!partial) { 2293 spin_unlock(&sbi->stat_lock); 2294 goto enospc; 2295 } 2296 2297 diff = sbi->total_valid_block_count - avail_user_block_count; 2298 if (diff > *count) 2299 diff = *count; 2300 *count -= diff; 2301 release = diff; 2302 sbi->total_valid_block_count -= diff; 2303 if (!*count) { 2304 spin_unlock(&sbi->stat_lock); 2305 goto enospc; 2306 } 2307 } 2308 spin_unlock(&sbi->stat_lock); 2309 2310 if (unlikely(release)) { 2311 percpu_counter_sub(&sbi->alloc_valid_block_count, release); 2312 dquot_release_reservation_block(inode, release); 2313 } 2314 f2fs_i_blocks_write(inode, *count, true, true); 2315 return 0; 2316 2317enospc: 2318 percpu_counter_sub(&sbi->alloc_valid_block_count, release); 2319release_quota: 2320 dquot_release_reservation_block(inode, release); 2321 return -ENOSPC; 2322} 2323 2324__printf(2, 3) 2325void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...); 2326 2327#define f2fs_err(sbi, fmt, ...) \ 2328 f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__) 2329#define f2fs_warn(sbi, fmt, ...) \ 2330 f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__) 2331#define f2fs_notice(sbi, fmt, ...) \ 2332 f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__) 2333#define f2fs_info(sbi, fmt, ...) \ 2334 f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__) 2335#define f2fs_debug(sbi, fmt, ...) \ 2336 f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__) 2337 2338#define PAGE_PRIVATE_GET_FUNC(name, flagname) \ 2339static inline bool page_private_##name(struct page *page) \ 2340{ \ 2341 return PagePrivate(page) && \ 2342 test_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)) && \ 2343 test_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ 2344} 2345 2346#define PAGE_PRIVATE_SET_FUNC(name, flagname) \ 2347static inline void set_page_private_##name(struct page *page) \ 2348{ \ 2349 if (!PagePrivate(page)) \ 2350 attach_page_private(page, (void *)0); \ 2351 set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); \ 2352 set_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ 2353} 2354 2355#define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \ 2356static inline void clear_page_private_##name(struct page *page) \ 2357{ \ 2358 clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ 2359 if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) \ 2360 detach_page_private(page); \ 2361} 2362 2363PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER); 2364PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE); 2365PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION); 2366PAGE_PRIVATE_GET_FUNC(dummy, DUMMY_WRITE); 2367 2368PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE); 2369PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE); 2370PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION); 2371PAGE_PRIVATE_SET_FUNC(dummy, DUMMY_WRITE); 2372 2373PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE); 2374PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE); 2375PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION); 2376PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE); 2377 2378static inline unsigned long get_page_private_data(struct page *page) 2379{ 2380 unsigned long data = page_private(page); 2381 2382 if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data)) 2383 return 0; 2384 return data >> PAGE_PRIVATE_MAX; 2385} 2386 2387static inline void set_page_private_data(struct page *page, unsigned long data) 2388{ 2389 if (!PagePrivate(page)) 2390 attach_page_private(page, (void *)0); 2391 set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); 2392 page_private(page) |= data << PAGE_PRIVATE_MAX; 2393} 2394 2395static inline void clear_page_private_data(struct page *page) 2396{ 2397 page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0); 2398 if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) 2399 detach_page_private(page); 2400} 2401 2402static inline void clear_page_private_all(struct page *page) 2403{ 2404 clear_page_private_data(page); 2405 clear_page_private_reference(page); 2406 clear_page_private_gcing(page); 2407 clear_page_private_inline(page); 2408 2409 f2fs_bug_on(F2FS_P_SB(page), page_private(page)); 2410} 2411 2412static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, 2413 struct inode *inode, 2414 block_t count) 2415{ 2416 blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; 2417 2418 spin_lock(&sbi->stat_lock); 2419 f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); 2420 sbi->total_valid_block_count -= (block_t)count; 2421 if (sbi->reserved_blocks && 2422 sbi->current_reserved_blocks < sbi->reserved_blocks) 2423 sbi->current_reserved_blocks = min(sbi->reserved_blocks, 2424 sbi->current_reserved_blocks + count); 2425 spin_unlock(&sbi->stat_lock); 2426 if (unlikely(inode->i_blocks < sectors)) { 2427 f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", 2428 inode->i_ino, 2429 (unsigned long long)inode->i_blocks, 2430 (unsigned long long)sectors); 2431 set_sbi_flag(sbi, SBI_NEED_FSCK); 2432 return; 2433 } 2434 f2fs_i_blocks_write(inode, count, false, true); 2435} 2436 2437static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) 2438{ 2439 atomic_inc(&sbi->nr_pages[count_type]); 2440 2441 if (count_type == F2FS_DIRTY_DENTS || 2442 count_type == F2FS_DIRTY_NODES || 2443 count_type == F2FS_DIRTY_META || 2444 count_type == F2FS_DIRTY_QDATA || 2445 count_type == F2FS_DIRTY_IMETA) 2446 set_sbi_flag(sbi, SBI_IS_DIRTY); 2447} 2448 2449static inline void inode_inc_dirty_pages(struct inode *inode) 2450{ 2451 atomic_inc(&F2FS_I(inode)->dirty_pages); 2452 inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? 2453 F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); 2454 if (IS_NOQUOTA(inode)) 2455 inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); 2456} 2457 2458static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) 2459{ 2460 atomic_dec(&sbi->nr_pages[count_type]); 2461} 2462 2463static inline void inode_dec_dirty_pages(struct inode *inode) 2464{ 2465 if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && 2466 !S_ISLNK(inode->i_mode)) 2467 return; 2468 2469 atomic_dec(&F2FS_I(inode)->dirty_pages); 2470 dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? 2471 F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); 2472 if (IS_NOQUOTA(inode)) 2473 dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); 2474} 2475 2476static inline void inc_atomic_write_cnt(struct inode *inode) 2477{ 2478 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); 2479 struct f2fs_inode_info *fi = F2FS_I(inode); 2480 u64 current_write; 2481 2482 fi->atomic_write_cnt++; 2483 atomic64_inc(&sbi->current_atomic_write); 2484 current_write = atomic64_read(&sbi->current_atomic_write); 2485 if (current_write > sbi->peak_atomic_write) 2486 sbi->peak_atomic_write = current_write; 2487} 2488 2489static inline void release_atomic_write_cnt(struct inode *inode) 2490{ 2491 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); 2492 struct f2fs_inode_info *fi = F2FS_I(inode); 2493 2494 atomic64_sub(fi->atomic_write_cnt, &sbi->current_atomic_write); 2495 fi->atomic_write_cnt = 0; 2496} 2497 2498static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) 2499{ 2500 return atomic_read(&sbi->nr_pages[count_type]); 2501} 2502 2503static inline int get_dirty_pages(struct inode *inode) 2504{ 2505 return atomic_read(&F2FS_I(inode)->dirty_pages); 2506} 2507 2508static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) 2509{ 2510 unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg; 2511 unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >> 2512 sbi->log_blocks_per_seg; 2513 2514 return segs / sbi->segs_per_sec; 2515} 2516 2517static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) 2518{ 2519 return sbi->total_valid_block_count; 2520} 2521 2522static inline block_t discard_blocks(struct f2fs_sb_info *sbi) 2523{ 2524 return sbi->discard_blks; 2525} 2526 2527static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) 2528{ 2529 struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); 2530 2531 /* return NAT or SIT bitmap */ 2532 if (flag == NAT_BITMAP) 2533 return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); 2534 else if (flag == SIT_BITMAP) 2535 return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); 2536 2537 return 0; 2538} 2539 2540static inline block_t __cp_payload(struct f2fs_sb_info *sbi) 2541{ 2542 return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); 2543} 2544 2545static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) 2546{ 2547 struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); 2548 void *tmp_ptr = &ckpt->sit_nat_version_bitmap; 2549 int offset; 2550 2551 if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { 2552 offset = (flag == SIT_BITMAP) ? 2553 le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; 2554 /* 2555 * if large_nat_bitmap feature is enabled, leave checksum 2556 * protection for all nat/sit bitmaps. 2557 */ 2558 return tmp_ptr + offset + sizeof(__le32); 2559 } 2560 2561 if (__cp_payload(sbi) > 0) { 2562 if (flag == NAT_BITMAP) 2563 return tmp_ptr; 2564 else 2565 return (unsigned char *)ckpt + F2FS_BLKSIZE; 2566 } else { 2567 offset = (flag == NAT_BITMAP) ? 2568 le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0; 2569 return tmp_ptr + offset; 2570 } 2571} 2572 2573static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) 2574{ 2575 block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); 2576 2577 if (sbi->cur_cp_pack == 2) 2578 start_addr += sbi->blocks_per_seg; 2579 return start_addr; 2580} 2581 2582static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi) 2583{ 2584 block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); 2585 2586 if (sbi->cur_cp_pack == 1) 2587 start_addr += sbi->blocks_per_seg; 2588 return start_addr; 2589} 2590 2591static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi) 2592{ 2593 sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1; 2594} 2595 2596static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) 2597{ 2598 return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); 2599} 2600 2601extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); 2602static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, 2603 struct inode *inode, bool is_inode) 2604{ 2605 block_t valid_block_count; 2606 unsigned int valid_node_count, user_block_count; 2607 int err; 2608 2609 if (is_inode) { 2610 if (inode) { 2611 err = dquot_alloc_inode(inode); 2612 if (err) 2613 return err; 2614 } 2615 } else { 2616 err = dquot_reserve_block(inode, 1); 2617 if (err) 2618 return err; 2619 } 2620 2621 if (time_to_inject(sbi, FAULT_BLOCK)) 2622 goto enospc; 2623 2624 spin_lock(&sbi->stat_lock); 2625 2626 valid_block_count = sbi->total_valid_block_count + 2627 sbi->current_reserved_blocks + 1; 2628 2629 if (!__allow_reserved_blocks(sbi, inode, false)) 2630 valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; 2631 2632 if (F2FS_IO_ALIGNED(sbi)) 2633 valid_block_count += sbi->blocks_per_seg * 2634 SM_I(sbi)->additional_reserved_segments; 2635 2636 user_block_count = sbi->user_block_count; 2637 if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) 2638 user_block_count -= sbi->unusable_block_count; 2639 2640 if (unlikely(valid_block_count > user_block_count)) { 2641 spin_unlock(&sbi->stat_lock); 2642 goto enospc; 2643 } 2644 2645 valid_node_count = sbi->total_valid_node_count + 1; 2646 if (unlikely(valid_node_count > sbi->total_node_count)) { 2647 spin_unlock(&sbi->stat_lock); 2648 goto enospc; 2649 } 2650 2651 sbi->total_valid_node_count++; 2652 sbi->total_valid_block_count++; 2653 spin_unlock(&sbi->stat_lock); 2654 2655 if (inode) { 2656 if (is_inode) 2657 f2fs_mark_inode_dirty_sync(inode, true); 2658 else 2659 f2fs_i_blocks_write(inode, 1, true, true); 2660 } 2661 2662 percpu_counter_inc(&sbi->alloc_valid_block_count); 2663 return 0; 2664 2665enospc: 2666 if (is_inode) { 2667 if (inode) 2668 dquot_free_inode(inode); 2669 } else { 2670 dquot_release_reservation_block(inode, 1); 2671 } 2672 return -ENOSPC; 2673} 2674 2675static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, 2676 struct inode *inode, bool is_inode) 2677{ 2678 spin_lock(&sbi->stat_lock); 2679 2680 if (unlikely(!sbi->total_valid_block_count || 2681 !sbi->total_valid_node_count)) { 2682 f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u", 2683 sbi->total_valid_block_count, 2684 sbi->total_valid_node_count); 2685 set_sbi_flag(sbi, SBI_NEED_FSCK); 2686 } else { 2687 sbi->total_valid_block_count--; 2688 sbi->total_valid_node_count--; 2689 } 2690 2691 if (sbi->reserved_blocks && 2692 sbi->current_reserved_blocks < sbi->reserved_blocks) 2693 sbi->current_reserved_blocks++; 2694 2695 spin_unlock(&sbi->stat_lock); 2696 2697 if (is_inode) { 2698 dquot_free_inode(inode); 2699 } else { 2700 if (unlikely(inode->i_blocks == 0)) { 2701 f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu", 2702 inode->i_ino, 2703 (unsigned long long)inode->i_blocks); 2704 set_sbi_flag(sbi, SBI_NEED_FSCK); 2705 return; 2706 } 2707 f2fs_i_blocks_write(inode, 1, false, true); 2708 } 2709} 2710 2711static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) 2712{ 2713 return sbi->total_valid_node_count; 2714} 2715 2716static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) 2717{ 2718 percpu_counter_inc(&sbi->total_valid_inode_count); 2719} 2720 2721static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi) 2722{ 2723 percpu_counter_dec(&sbi->total_valid_inode_count); 2724} 2725 2726static inline s64 valid_inode_count(struct f2fs_sb_info *sbi) 2727{ 2728 return percpu_counter_sum_positive(&sbi->total_valid_inode_count); 2729} 2730 2731static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, 2732 pgoff_t index, bool for_write) 2733{ 2734 struct page *page; 2735 unsigned int flags; 2736 2737 if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) { 2738 if (!for_write) 2739 page = find_get_page_flags(mapping, index, 2740 FGP_LOCK | FGP_ACCESSED); 2741 else 2742 page = find_lock_page(mapping, index); 2743 if (page) 2744 return page; 2745 2746 if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) 2747 return NULL; 2748 } 2749 2750 if (!for_write) 2751 return grab_cache_page(mapping, index); 2752 2753 flags = memalloc_nofs_save(); 2754 page = grab_cache_page_write_begin(mapping, index); 2755 memalloc_nofs_restore(flags); 2756 2757 return page; 2758} 2759 2760static inline struct page *f2fs_pagecache_get_page( 2761 struct address_space *mapping, pgoff_t index, 2762 fgf_t fgp_flags, gfp_t gfp_mask) 2763{ 2764 if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) 2765 return NULL; 2766 2767 return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); 2768} 2769 2770static inline void f2fs_put_page(struct page *page, int unlock) 2771{ 2772 if (!page) 2773 return; 2774 2775 if (unlock) { 2776 f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); 2777 unlock_page(page); 2778 } 2779 put_page(page); 2780} 2781 2782static inline void f2fs_put_dnode(struct dnode_of_data *dn) 2783{ 2784 if (dn->node_page) 2785 f2fs_put_page(dn->node_page, 1); 2786 if (dn->inode_page && dn->node_page != dn->inode_page) 2787 f2fs_put_page(dn->inode_page, 0); 2788 dn->node_page = NULL; 2789 dn->inode_page = NULL; 2790} 2791 2792static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name, 2793 size_t size) 2794{ 2795 return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL); 2796} 2797 2798static inline void *f2fs_kmem_cache_alloc_nofail(struct kmem_cache *cachep, 2799 gfp_t flags) 2800{ 2801 void *entry; 2802 2803 entry = kmem_cache_alloc(cachep, flags); 2804 if (!entry) 2805 entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL); 2806 return entry; 2807} 2808 2809static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, 2810 gfp_t flags, bool nofail, struct f2fs_sb_info *sbi) 2811{ 2812 if (nofail) 2813 return f2fs_kmem_cache_alloc_nofail(cachep, flags); 2814 2815 if (time_to_inject(sbi, FAULT_SLAB_ALLOC)) 2816 return NULL; 2817 2818 return kmem_cache_alloc(cachep, flags); 2819} 2820 2821static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type) 2822{ 2823 if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || 2824 get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || 2825 get_pages(sbi, F2FS_WB_CP_DATA) || 2826 get_pages(sbi, F2FS_DIO_READ) || 2827 get_pages(sbi, F2FS_DIO_WRITE)) 2828 return true; 2829 2830 if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info && 2831 atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) 2832 return true; 2833 2834 if (SM_I(sbi) && SM_I(sbi)->fcc_info && 2835 atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) 2836 return true; 2837 return false; 2838} 2839 2840static inline bool is_idle(struct f2fs_sb_info *sbi, int type) 2841{ 2842 if (sbi->gc_mode == GC_URGENT_HIGH) 2843 return true; 2844 2845 if (is_inflight_io(sbi, type)) 2846 return false; 2847 2848 if (sbi->gc_mode == GC_URGENT_MID) 2849 return true; 2850 2851 if (sbi->gc_mode == GC_URGENT_LOW && 2852 (type == DISCARD_TIME || type == GC_TIME)) 2853 return true; 2854 2855 return f2fs_time_over(sbi, type); 2856} 2857 2858static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, 2859 unsigned long index, void *item) 2860{ 2861 while (radix_tree_insert(root, index, item)) 2862 cond_resched(); 2863} 2864 2865#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) 2866 2867static inline bool IS_INODE(struct page *page) 2868{ 2869 struct f2fs_node *p = F2FS_NODE(page); 2870 2871 return RAW_IS_INODE(p); 2872} 2873 2874static inline int offset_in_addr(struct f2fs_inode *i) 2875{ 2876 return (i->i_inline & F2FS_EXTRA_ATTR) ? 2877 (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0; 2878} 2879 2880static inline __le32 *blkaddr_in_node(struct f2fs_node *node) 2881{ 2882 return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; 2883} 2884 2885static inline int f2fs_has_extra_attr(struct inode *inode); 2886static inline block_t data_blkaddr(struct inode *inode, 2887 struct page *node_page, unsigned int offset) 2888{ 2889 struct f2fs_node *raw_node; 2890 __le32 *addr_array; 2891 int base = 0; 2892 bool is_inode = IS_INODE(node_page); 2893 2894 raw_node = F2FS_NODE(node_page); 2895 2896 if (is_inode) { 2897 if (!inode) 2898 /* from GC path only */ 2899 base = offset_in_addr(&raw_node->i); 2900 else if (f2fs_has_extra_attr(inode)) 2901 base = get_extra_isize(inode); 2902 } 2903 2904 addr_array = blkaddr_in_node(raw_node); 2905 return le32_to_cpu(addr_array[base + offset]); 2906} 2907 2908static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn) 2909{ 2910 return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node); 2911} 2912 2913static inline int f2fs_test_bit(unsigned int nr, char *addr) 2914{ 2915 int mask; 2916 2917 addr += (nr >> 3); 2918 mask = BIT(7 - (nr & 0x07)); 2919 return mask & *addr; 2920} 2921 2922static inline void f2fs_set_bit(unsigned int nr, char *addr) 2923{ 2924 int mask; 2925 2926 addr += (nr >> 3); 2927 mask = BIT(7 - (nr & 0x07)); 2928 *addr |= mask; 2929} 2930 2931static inline void f2fs_clear_bit(unsigned int nr, char *addr) 2932{ 2933 int mask; 2934 2935 addr += (nr >> 3); 2936 mask = BIT(7 - (nr & 0x07)); 2937 *addr &= ~mask; 2938} 2939 2940static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) 2941{ 2942 int mask; 2943 int ret; 2944 2945 addr += (nr >> 3); 2946 mask = BIT(7 - (nr & 0x07)); 2947 ret = mask & *addr; 2948 *addr |= mask; 2949 return ret; 2950} 2951 2952static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) 2953{ 2954 int mask; 2955 int ret; 2956 2957 addr += (nr >> 3); 2958 mask = BIT(7 - (nr & 0x07)); 2959 ret = mask & *addr; 2960 *addr &= ~mask; 2961 return ret; 2962} 2963 2964static inline void f2fs_change_bit(unsigned int nr, char *addr) 2965{ 2966 int mask; 2967 2968 addr += (nr >> 3); 2969 mask = BIT(7 - (nr & 0x07)); 2970 *addr ^= mask; 2971} 2972 2973/* 2974 * On-disk inode flags (f2fs_inode::i_flags) 2975 */ 2976#define F2FS_COMPR_FL 0x00000004 /* Compress file */ 2977#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ 2978#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ 2979#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ 2980#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ 2981#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ 2982#define F2FS_NOCOMP_FL 0x00000400 /* Don't compress */ 2983#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ 2984#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ 2985#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ 2986#define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */ 2987 2988#define F2FS_QUOTA_DEFAULT_FL (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL) 2989 2990/* Flags that should be inherited by new inodes from their parent. */ 2991#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ 2992 F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ 2993 F2FS_CASEFOLD_FL) 2994 2995/* Flags that are appropriate for regular files (all but dir-specific ones). */ 2996#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ 2997 F2FS_CASEFOLD_FL)) 2998 2999/* Flags that are appropriate for non-directories/regular files. */ 3000#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) 3001 3002static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) 3003{ 3004 if (S_ISDIR(mode)) 3005 return flags; 3006 else if (S_ISREG(mode)) 3007 return flags & F2FS_REG_FLMASK; 3008 else 3009 return flags & F2FS_OTHER_FLMASK; 3010} 3011 3012static inline void __mark_inode_dirty_flag(struct inode *inode, 3013 int flag, bool set) 3014{ 3015 switch (flag) { 3016 case FI_INLINE_XATTR: 3017 case FI_INLINE_DATA: 3018 case FI_INLINE_DENTRY: 3019 case FI_NEW_INODE: 3020 if (set) 3021 return; 3022 fallthrough; 3023 case FI_DATA_EXIST: 3024 case FI_INLINE_DOTS: 3025 case FI_PIN_FILE: 3026 case FI_COMPRESS_RELEASED: 3027 f2fs_mark_inode_dirty_sync(inode, true); 3028 } 3029} 3030 3031static inline void set_inode_flag(struct inode *inode, int flag) 3032{ 3033 set_bit(flag, F2FS_I(inode)->flags); 3034 __mark_inode_dirty_flag(inode, flag, true); 3035} 3036 3037static inline int is_inode_flag_set(struct inode *inode, int flag) 3038{ 3039 return test_bit(flag, F2FS_I(inode)->flags); 3040} 3041 3042static inline void clear_inode_flag(struct inode *inode, int flag) 3043{ 3044 clear_bit(flag, F2FS_I(inode)->flags); 3045 __mark_inode_dirty_flag(inode, flag, false); 3046} 3047 3048static inline bool f2fs_verity_in_progress(struct inode *inode) 3049{ 3050 return IS_ENABLED(CONFIG_FS_VERITY) && 3051 is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS); 3052} 3053 3054static inline void set_acl_inode(struct inode *inode, umode_t mode) 3055{ 3056 F2FS_I(inode)->i_acl_mode = mode; 3057 set_inode_flag(inode, FI_ACL_MODE); 3058 f2fs_mark_inode_dirty_sync(inode, false); 3059} 3060 3061static inline void f2fs_i_links_write(struct inode *inode, bool inc) 3062{ 3063 if (inc) 3064 inc_nlink(inode); 3065 else 3066 drop_nlink(inode); 3067 f2fs_mark_inode_dirty_sync(inode, true); 3068} 3069 3070static inline void f2fs_i_blocks_write(struct inode *inode, 3071 block_t diff, bool add, bool claim) 3072{ 3073 bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); 3074 bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); 3075 3076 /* add = 1, claim = 1 should be dquot_reserve_block in pair */ 3077 if (add) { 3078 if (claim) 3079 dquot_claim_block(inode, diff); 3080 else 3081 dquot_alloc_block_nofail(inode, diff); 3082 } else { 3083 dquot_free_block(inode, diff); 3084 } 3085 3086 f2fs_mark_inode_dirty_sync(inode, true); 3087 if (clean || recover) 3088 set_inode_flag(inode, FI_AUTO_RECOVER); 3089} 3090 3091static inline bool f2fs_is_atomic_file(struct inode *inode); 3092 3093static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size) 3094{ 3095 bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); 3096 bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); 3097 3098 if (i_size_read(inode) == i_size) 3099 return; 3100 3101 i_size_write(inode, i_size); 3102 3103 if (f2fs_is_atomic_file(inode)) 3104 return; 3105 3106 f2fs_mark_inode_dirty_sync(inode, true); 3107 if (clean || recover) 3108 set_inode_flag(inode, FI_AUTO_RECOVER); 3109} 3110 3111static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth) 3112{ 3113 F2FS_I(inode)->i_current_depth = depth; 3114 f2fs_mark_inode_dirty_sync(inode, true); 3115} 3116 3117static inline void f2fs_i_gc_failures_write(struct inode *inode, 3118 unsigned int count) 3119{ 3120 F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count; 3121 f2fs_mark_inode_dirty_sync(inode, true); 3122} 3123 3124static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid) 3125{ 3126 F2FS_I(inode)->i_xattr_nid = xnid; 3127 f2fs_mark_inode_dirty_sync(inode, true); 3128} 3129 3130static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino) 3131{ 3132 F2FS_I(inode)->i_pino = pino; 3133 f2fs_mark_inode_dirty_sync(inode, true); 3134} 3135 3136static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) 3137{ 3138 struct f2fs_inode_info *fi = F2FS_I(inode); 3139 3140 if (ri->i_inline & F2FS_INLINE_XATTR) 3141 set_bit(FI_INLINE_XATTR, fi->flags); 3142 if (ri->i_inline & F2FS_INLINE_DATA) 3143 set_bit(FI_INLINE_DATA, fi->flags); 3144 if (ri->i_inline & F2FS_INLINE_DENTRY) 3145 set_bit(FI_INLINE_DENTRY, fi->flags); 3146 if (ri->i_inline & F2FS_DATA_EXIST) 3147 set_bit(FI_DATA_EXIST, fi->flags); 3148 if (ri->i_inline & F2FS_INLINE_DOTS) 3149 set_bit(FI_INLINE_DOTS, fi->flags); 3150 if (ri->i_inline & F2FS_EXTRA_ATTR) 3151 set_bit(FI_EXTRA_ATTR, fi->flags); 3152 if (ri->i_inline & F2FS_PIN_FILE) 3153 set_bit(FI_PIN_FILE, fi->flags); 3154 if (ri->i_inline & F2FS_COMPRESS_RELEASED) 3155 set_bit(FI_COMPRESS_RELEASED, fi->flags); 3156} 3157 3158static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) 3159{ 3160 ri->i_inline = 0; 3161 3162 if (is_inode_flag_set(inode, FI_INLINE_XATTR)) 3163 ri->i_inline |= F2FS_INLINE_XATTR; 3164 if (is_inode_flag_set(inode, FI_INLINE_DATA)) 3165 ri->i_inline |= F2FS_INLINE_DATA; 3166 if (is_inode_flag_set(inode, FI_INLINE_DENTRY)) 3167 ri->i_inline |= F2FS_INLINE_DENTRY; 3168 if (is_inode_flag_set(inode, FI_DATA_EXIST)) 3169 ri->i_inline |= F2FS_DATA_EXIST; 3170 if (is_inode_flag_set(inode, FI_INLINE_DOTS)) 3171 ri->i_inline |= F2FS_INLINE_DOTS; 3172 if (is_inode_flag_set(inode, FI_EXTRA_ATTR)) 3173 ri->i_inline |= F2FS_EXTRA_ATTR; 3174 if (is_inode_flag_set(inode, FI_PIN_FILE)) 3175 ri->i_inline |= F2FS_PIN_FILE; 3176 if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) 3177 ri->i_inline |= F2FS_COMPRESS_RELEASED; 3178} 3179 3180static inline int f2fs_has_extra_attr(struct inode *inode) 3181{ 3182 return is_inode_flag_set(inode, FI_EXTRA_ATTR); 3183} 3184 3185static inline int f2fs_has_inline_xattr(struct inode *inode) 3186{ 3187 return is_inode_flag_set(inode, FI_INLINE_XATTR); 3188} 3189 3190static inline int f2fs_compressed_file(struct inode *inode) 3191{ 3192 return S_ISREG(inode->i_mode) && 3193 is_inode_flag_set(inode, FI_COMPRESSED_FILE); 3194} 3195 3196static inline bool f2fs_need_compress_data(struct inode *inode) 3197{ 3198 int compress_mode = F2FS_OPTION(F2FS_I_SB(inode)).compress_mode; 3199 3200 if (!f2fs_compressed_file(inode)) 3201 return false; 3202 3203 if (compress_mode == COMPR_MODE_FS) 3204 return true; 3205 else if (compress_mode == COMPR_MODE_USER && 3206 is_inode_flag_set(inode, FI_ENABLE_COMPRESS)) 3207 return true; 3208 3209 return false; 3210} 3211 3212static inline unsigned int addrs_per_inode(struct inode *inode) 3213{ 3214 unsigned int addrs = CUR_ADDRS_PER_INODE(inode) - 3215 get_inline_xattr_addrs(inode); 3216 3217 if (!f2fs_compressed_file(inode)) 3218 return addrs; 3219 return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size); 3220} 3221 3222static inline unsigned int addrs_per_block(struct inode *inode) 3223{ 3224 if (!f2fs_compressed_file(inode)) 3225 return DEF_ADDRS_PER_BLOCK; 3226 return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size); 3227} 3228 3229static inline void *inline_xattr_addr(struct inode *inode, struct page *page) 3230{ 3231 struct f2fs_inode *ri = F2FS_INODE(page); 3232 3233 return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - 3234 get_inline_xattr_addrs(inode)]); 3235} 3236 3237static inline int inline_xattr_size(struct inode *inode) 3238{ 3239 if (f2fs_has_inline_xattr(inode)) 3240 return get_inline_xattr_addrs(inode) * sizeof(__le32); 3241 return 0; 3242} 3243 3244/* 3245 * Notice: check inline_data flag without inode page lock is unsafe. 3246 * It could change at any time by f2fs_convert_inline_page(). 3247 */ 3248static inline int f2fs_has_inline_data(struct inode *inode) 3249{ 3250 return is_inode_flag_set(inode, FI_INLINE_DATA); 3251} 3252 3253static inline int f2fs_exist_data(struct inode *inode) 3254{ 3255 return is_inode_flag_set(inode, FI_DATA_EXIST); 3256} 3257 3258static inline int f2fs_has_inline_dots(struct inode *inode) 3259{ 3260 return is_inode_flag_set(inode, FI_INLINE_DOTS); 3261} 3262 3263static inline int f2fs_is_mmap_file(struct inode *inode) 3264{ 3265 return is_inode_flag_set(inode, FI_MMAP_FILE); 3266} 3267 3268static inline bool f2fs_is_pinned_file(struct inode *inode) 3269{ 3270 return is_inode_flag_set(inode, FI_PIN_FILE); 3271} 3272 3273static inline bool f2fs_is_atomic_file(struct inode *inode) 3274{ 3275 return is_inode_flag_set(inode, FI_ATOMIC_FILE); 3276} 3277 3278static inline bool f2fs_is_cow_file(struct inode *inode) 3279{ 3280 return is_inode_flag_set(inode, FI_COW_FILE); 3281} 3282 3283static inline __le32 *get_dnode_addr(struct inode *inode, 3284 struct page *node_page); 3285static inline void *inline_data_addr(struct inode *inode, struct page *page) 3286{ 3287 __le32 *addr = get_dnode_addr(inode, page); 3288 3289 return (void *)(addr + DEF_INLINE_RESERVED_SIZE); 3290} 3291 3292static inline int f2fs_has_inline_dentry(struct inode *inode) 3293{ 3294 return is_inode_flag_set(inode, FI_INLINE_DENTRY); 3295} 3296 3297static inline int is_file(struct inode *inode, int type) 3298{ 3299 return F2FS_I(inode)->i_advise & type; 3300} 3301 3302static inline void set_file(struct inode *inode, int type) 3303{ 3304 if (is_file(inode, type)) 3305 return; 3306 F2FS_I(inode)->i_advise |= type; 3307 f2fs_mark_inode_dirty_sync(inode, true); 3308} 3309 3310static inline void clear_file(struct inode *inode, int type) 3311{ 3312 if (!is_file(inode, type)) 3313 return; 3314 F2FS_I(inode)->i_advise &= ~type; 3315 f2fs_mark_inode_dirty_sync(inode, true); 3316} 3317 3318static inline bool f2fs_is_time_consistent(struct inode *inode) 3319{ 3320 struct timespec64 ctime = inode_get_ctime(inode); 3321 3322 if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) 3323 return false; 3324 if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &ctime)) 3325 return false; 3326 if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) 3327 return false; 3328 return true; 3329} 3330 3331static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) 3332{ 3333 bool ret; 3334 3335 if (dsync) { 3336 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); 3337 3338 spin_lock(&sbi->inode_lock[DIRTY_META]); 3339 ret = list_empty(&F2FS_I(inode)->gdirty_list); 3340 spin_unlock(&sbi->inode_lock[DIRTY_META]); 3341 return ret; 3342 } 3343 if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) || 3344 file_keep_isize(inode) || 3345 i_size_read(inode) & ~PAGE_MASK) 3346 return false; 3347 3348 if (!f2fs_is_time_consistent(inode)) 3349 return false; 3350 3351 spin_lock(&F2FS_I(inode)->i_size_lock); 3352 ret = F2FS_I(inode)->last_disk_size == i_size_read(inode); 3353 spin_unlock(&F2FS_I(inode)->i_size_lock); 3354 3355 return ret; 3356} 3357 3358static inline bool f2fs_readonly(struct super_block *sb) 3359{ 3360 return sb_rdonly(sb); 3361} 3362 3363static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) 3364{ 3365 return is_set_ckpt_flags(sbi, CP_ERROR_FLAG); 3366} 3367 3368static inline bool is_dot_dotdot(const u8 *name, size_t len) 3369{ 3370 if (len == 1 && name[0] == '.') 3371 return true; 3372 3373 if (len == 2 && name[0] == '.' && name[1] == '.') 3374 return true; 3375 3376 return false; 3377} 3378 3379static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, 3380 size_t size, gfp_t flags) 3381{ 3382 if (time_to_inject(sbi, FAULT_KMALLOC)) 3383 return NULL; 3384 3385 return kmalloc(size, flags); 3386} 3387 3388static inline void *f2fs_getname(struct f2fs_sb_info *sbi) 3389{ 3390 if (time_to_inject(sbi, FAULT_KMALLOC)) 3391 return NULL; 3392 3393 return __getname(); 3394} 3395 3396static inline void f2fs_putname(char *buf) 3397{ 3398 __putname(buf); 3399} 3400 3401static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi, 3402 size_t size, gfp_t flags) 3403{ 3404 return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO); 3405} 3406 3407static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi, 3408 size_t size, gfp_t flags) 3409{ 3410 if (time_to_inject(sbi, FAULT_KVMALLOC)) 3411 return NULL; 3412 3413 return kvmalloc(size, flags); 3414} 3415 3416static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi, 3417 size_t size, gfp_t flags) 3418{ 3419 return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO); 3420} 3421 3422static inline int get_extra_isize(struct inode *inode) 3423{ 3424 return F2FS_I(inode)->i_extra_isize / sizeof(__le32); 3425} 3426 3427static inline int get_inline_xattr_addrs(struct inode *inode) 3428{ 3429 return F2FS_I(inode)->i_inline_xattr_size; 3430} 3431 3432static inline __le32 *get_dnode_addr(struct inode *inode, 3433 struct page *node_page) 3434{ 3435 int base = 0; 3436 3437 if (IS_INODE(node_page) && f2fs_has_extra_attr(inode)) 3438 base = get_extra_isize(inode); 3439 3440 return blkaddr_in_node(F2FS_NODE(node_page)) + base; 3441} 3442 3443#define f2fs_get_inode_mode(i) \ 3444 ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ 3445 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) 3446 3447#define F2FS_MIN_EXTRA_ATTR_SIZE (sizeof(__le32)) 3448 3449#define F2FS_TOTAL_EXTRA_ATTR_SIZE \ 3450 (offsetof(struct f2fs_inode, i_extra_end) - \ 3451 offsetof(struct f2fs_inode, i_extra_isize)) \ 3452 3453#define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) 3454#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ 3455 ((offsetof(typeof(*(f2fs_inode)), field) + \ 3456 sizeof((f2fs_inode)->field)) \ 3457 <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ 3458 3459#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) 3460 3461#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META) 3462 3463bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, 3464 block_t blkaddr, int type); 3465static inline void verify_blkaddr(struct f2fs_sb_info *sbi, 3466 block_t blkaddr, int type) 3467{ 3468 if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) 3469 f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.", 3470 blkaddr, type); 3471} 3472 3473static inline bool __is_valid_data_blkaddr(block_t blkaddr) 3474{ 3475 if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR || 3476 blkaddr == COMPRESS_ADDR) 3477 return false; 3478 return true; 3479} 3480 3481/* 3482 * file.c 3483 */ 3484int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); 3485int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); 3486int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); 3487int f2fs_truncate(struct inode *inode); 3488int f2fs_getattr(struct mnt_idmap *idmap, const struct path *path, 3489 struct kstat *stat, u32 request_mask, unsigned int flags); 3490int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, 3491 struct iattr *attr); 3492int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); 3493void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); 3494int f2fs_precache_extents(struct inode *inode); 3495int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa); 3496int f2fs_fileattr_set(struct mnt_idmap *idmap, 3497 struct dentry *dentry, struct fileattr *fa); 3498long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); 3499long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); 3500int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid); 3501int f2fs_pin_file_control(struct inode *inode, bool inc); 3502 3503/* 3504 * inode.c 3505 */ 3506void f2fs_set_inode_flags(struct inode *inode); 3507bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page); 3508void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page); 3509struct inode *f2fs_iget(struct super_block *sb, unsigned long ino); 3510struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino); 3511int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); 3512void f2fs_update_inode(struct inode *inode, struct page *node_page); 3513void f2fs_update_inode_page(struct inode *inode); 3514int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc); 3515void f2fs_evict_inode(struct inode *inode); 3516void f2fs_handle_failed_inode(struct inode *inode); 3517 3518/* 3519 * namei.c 3520 */ 3521int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, 3522 bool hot, bool set); 3523struct dentry *f2fs_get_parent(struct dentry *child); 3524int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, 3525 struct inode **new_inode); 3526 3527/* 3528 * dir.c 3529 */ 3530int f2fs_init_casefolded_name(const struct inode *dir, 3531 struct f2fs_filename *fname); 3532int f2fs_setup_filename(struct inode *dir, const struct qstr *iname, 3533 int lookup, struct f2fs_filename *fname); 3534int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry, 3535 struct f2fs_filename *fname); 3536void f2fs_free_filename(struct f2fs_filename *fname); 3537struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d, 3538 const struct f2fs_filename *fname, int *max_slots); 3539int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, 3540 unsigned int start_pos, struct fscrypt_str *fstr); 3541void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, 3542 struct f2fs_dentry_ptr *d); 3543struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, 3544 const struct f2fs_filename *fname, struct page *dpage); 3545void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, 3546 unsigned int current_depth); 3547int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots); 3548void f2fs_drop_nlink(struct inode *dir, struct inode *inode); 3549struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, 3550 const struct f2fs_filename *fname, 3551 struct page **res_page); 3552struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir, 3553 const struct qstr *child, struct page **res_page); 3554struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p); 3555ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr, 3556 struct page **page); 3557void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, 3558 struct page *page, struct inode *inode); 3559bool f2fs_has_enough_room(struct inode *dir, struct page *ipage, 3560 const struct f2fs_filename *fname); 3561void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, 3562 const struct fscrypt_str *name, f2fs_hash_t name_hash, 3563 unsigned int bit_pos); 3564int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname, 3565 struct inode *inode, nid_t ino, umode_t mode); 3566int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname, 3567 struct inode *inode, nid_t ino, umode_t mode); 3568int f2fs_do_add_link(struct inode *dir, const struct qstr *name, 3569 struct inode *inode, nid_t ino, umode_t mode); 3570void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, 3571 struct inode *dir, struct inode *inode); 3572int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, 3573 struct f2fs_filename *fname); 3574bool f2fs_empty_dir(struct inode *dir); 3575 3576static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) 3577{ 3578 if (fscrypt_is_nokey_name(dentry)) 3579 return -ENOKEY; 3580 return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, 3581 inode, inode->i_ino, inode->i_mode); 3582} 3583 3584/* 3585 * super.c 3586 */ 3587int f2fs_inode_dirtied(struct inode *inode, bool sync); 3588void f2fs_inode_synced(struct inode *inode); 3589int f2fs_dquot_initialize(struct inode *inode); 3590int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); 3591int f2fs_quota_sync(struct super_block *sb, int type); 3592loff_t max_file_blocks(struct inode *inode); 3593void f2fs_quota_off_umount(struct super_block *sb); 3594void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag); 3595void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason, 3596 bool irq_context); 3597void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error); 3598void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error); 3599int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); 3600int f2fs_sync_fs(struct super_block *sb, int sync); 3601int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); 3602 3603/* 3604 * hash.c 3605 */ 3606void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname); 3607 3608/* 3609 * node.c 3610 */ 3611struct node_info; 3612 3613int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid); 3614bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type); 3615bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page); 3616void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi); 3617void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page); 3618void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi); 3619int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); 3620bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); 3621bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); 3622int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, 3623 struct node_info *ni, bool checkpoint_context); 3624pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); 3625int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); 3626int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from); 3627int f2fs_truncate_xattr_node(struct inode *inode); 3628int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, 3629 unsigned int seq_id); 3630bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi); 3631int f2fs_remove_inode_page(struct inode *inode); 3632struct page *f2fs_new_inode_page(struct inode *inode); 3633struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); 3634void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); 3635struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); 3636struct page *f2fs_get_node_page_ra(struct page *parent, int start); 3637int f2fs_move_node_page(struct page *node_page, int gc_type); 3638void f2fs_flush_inline_data(struct f2fs_sb_info *sbi); 3639int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, 3640 struct writeback_control *wbc, bool atomic, 3641 unsigned int *seq_id); 3642int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, 3643 struct writeback_control *wbc, 3644 bool do_balance, enum iostat_type io_type); 3645int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); 3646bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); 3647void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); 3648void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); 3649int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); 3650int f2fs_recover_inline_xattr(struct inode *inode, struct page *page); 3651int f2fs_recover_xattr_data(struct inode *inode, struct page *page); 3652int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); 3653int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, 3654 unsigned int segno, struct f2fs_summary_block *sum); 3655void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi); 3656int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); 3657int f2fs_build_node_manager(struct f2fs_sb_info *sbi); 3658void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); 3659int __init f2fs_create_node_manager_caches(void); 3660void f2fs_destroy_node_manager_caches(void); 3661 3662/* 3663 * segment.c 3664 */ 3665bool f2fs_need_SSR(struct f2fs_sb_info *sbi); 3666int f2fs_commit_atomic_write(struct inode *inode); 3667void f2fs_abort_atomic_write(struct inode *inode, bool clean); 3668void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need); 3669void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg); 3670int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); 3671int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); 3672int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); 3673void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); 3674void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); 3675bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); 3676int f2fs_start_discard_thread(struct f2fs_sb_info *sbi); 3677void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); 3678void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); 3679bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); 3680void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, 3681 struct cp_control *cpc); 3682void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); 3683block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi); 3684int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable); 3685void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); 3686int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); 3687bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno); 3688void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi); 3689void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi); 3690void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi); 3691void f2fs_get_new_segment(struct f2fs_sb_info *sbi, 3692 unsigned int *newseg, bool new_sec, int dir); 3693void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type, 3694 unsigned int start, unsigned int end); 3695void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force); 3696void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); 3697int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); 3698bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, 3699 struct cp_control *cpc); 3700struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); 3701void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, 3702 block_t blk_addr); 3703void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, 3704 enum iostat_type io_type); 3705void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio); 3706void f2fs_outplace_write_data(struct dnode_of_data *dn, 3707 struct f2fs_io_info *fio); 3708int f2fs_inplace_write_data(struct f2fs_io_info *fio); 3709void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, 3710 block_t old_blkaddr, block_t new_blkaddr, 3711 bool recover_curseg, bool recover_newaddr, 3712 bool from_gc); 3713void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, 3714 block_t old_addr, block_t new_addr, 3715 unsigned char version, bool recover_curseg, 3716 bool recover_newaddr); 3717void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, 3718 block_t old_blkaddr, block_t *new_blkaddr, 3719 struct f2fs_summary *sum, int type, 3720 struct f2fs_io_info *fio); 3721void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino, 3722 block_t blkaddr, unsigned int blkcnt); 3723void f2fs_wait_on_page_writeback(struct page *page, 3724 enum page_type type, bool ordered, bool locked); 3725void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); 3726void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, 3727 block_t len); 3728void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); 3729void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); 3730int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, 3731 unsigned int val, int alloc); 3732void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); 3733int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi); 3734int f2fs_check_write_pointer(struct f2fs_sb_info *sbi); 3735int f2fs_build_segment_manager(struct f2fs_sb_info *sbi); 3736void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); 3737int __init f2fs_create_segment_manager_caches(void); 3738void f2fs_destroy_segment_manager_caches(void); 3739int f2fs_rw_hint_to_seg_type(enum rw_hint hint); 3740unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi, 3741 unsigned int segno); 3742unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi, 3743 unsigned int segno); 3744 3745#define DEF_FRAGMENT_SIZE 4 3746#define MIN_FRAGMENT_SIZE 1 3747#define MAX_FRAGMENT_SIZE 512 3748 3749static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi) 3750{ 3751 return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG || 3752 F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK; 3753} 3754 3755/* 3756 * checkpoint.c 3757 */ 3758void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io, 3759 unsigned char reason); 3760void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi); 3761struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); 3762struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); 3763struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index); 3764struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); 3765bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, 3766 block_t blkaddr, int type); 3767int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, 3768 int type, bool sync); 3769void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index, 3770 unsigned int ra_blocks); 3771long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, 3772 long nr_to_write, enum iostat_type io_type); 3773void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); 3774void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); 3775void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all); 3776bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); 3777void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, 3778 unsigned int devidx, int type); 3779bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, 3780 unsigned int devidx, int type); 3781int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi); 3782void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi); 3783void f2fs_add_orphan_inode(struct inode *inode); 3784void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); 3785int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi); 3786int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); 3787void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio); 3788void f2fs_remove_dirty_inode(struct inode *inode); 3789int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type, 3790 bool from_cp); 3791void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type); 3792u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi); 3793int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); 3794void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); 3795int __init f2fs_create_checkpoint_caches(void); 3796void f2fs_destroy_checkpoint_caches(void); 3797int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi); 3798int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi); 3799void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi); 3800void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); 3801 3802/* 3803 * data.c 3804 */ 3805int __init f2fs_init_bioset(void); 3806void f2fs_destroy_bioset(void); 3807bool f2fs_is_cp_guaranteed(struct page *page); 3808int f2fs_init_bio_entry_cache(void); 3809void f2fs_destroy_bio_entry_cache(void); 3810void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, 3811 enum page_type type); 3812int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi); 3813void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); 3814void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, 3815 struct inode *inode, struct page *page, 3816 nid_t ino, enum page_type type); 3817void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi, 3818 struct bio **bio, struct page *page); 3819void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); 3820int f2fs_submit_page_bio(struct f2fs_io_info *fio); 3821int f2fs_merge_page_bio(struct f2fs_io_info *fio); 3822void f2fs_submit_page_write(struct f2fs_io_info *fio); 3823struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, 3824 block_t blk_addr, sector_t *sector); 3825int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); 3826void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); 3827void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); 3828int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); 3829int f2fs_reserve_new_block(struct dnode_of_data *dn); 3830int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index); 3831int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); 3832struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, 3833 blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs); 3834struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index, 3835 pgoff_t *next_pgofs); 3836struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, 3837 bool for_write); 3838struct page *f2fs_get_new_data_page(struct inode *inode, 3839 struct page *ipage, pgoff_t index, bool new_i_size); 3840int f2fs_do_write_data_page(struct f2fs_io_info *fio); 3841int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag); 3842int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, 3843 u64 start, u64 len); 3844int f2fs_encrypt_one_page(struct f2fs_io_info *fio); 3845bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio); 3846bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio); 3847int f2fs_write_single_data_page(struct page *page, int *submitted, 3848 struct bio **bio, sector_t *last_block, 3849 struct writeback_control *wbc, 3850 enum iostat_type io_type, 3851 int compr_blocks, bool allow_balance); 3852void f2fs_write_failed(struct inode *inode, loff_t to); 3853void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length); 3854bool f2fs_release_folio(struct folio *folio, gfp_t wait); 3855bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len); 3856void f2fs_clear_page_cache_dirty_tag(struct page *page); 3857int f2fs_init_post_read_processing(void); 3858void f2fs_destroy_post_read_processing(void); 3859int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi); 3860void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi); 3861extern const struct iomap_ops f2fs_iomap_ops; 3862 3863/* 3864 * gc.c 3865 */ 3866int f2fs_start_gc_thread(struct f2fs_sb_info *sbi); 3867void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); 3868block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); 3869int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); 3870void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); 3871int f2fs_resize_fs(struct file *filp, __u64 block_count); 3872int __init f2fs_create_garbage_collection_cache(void); 3873void f2fs_destroy_garbage_collection_cache(void); 3874/* victim selection function for cleaning and SSR */ 3875int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, 3876 int gc_type, int type, char alloc_mode, 3877 unsigned long long age); 3878 3879/* 3880 * recovery.c 3881 */ 3882int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); 3883bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi); 3884int __init f2fs_create_recovery_cache(void); 3885void f2fs_destroy_recovery_cache(void); 3886 3887/* 3888 * debug.c 3889 */ 3890#ifdef CONFIG_F2FS_STAT_FS 3891struct f2fs_stat_info { 3892 struct list_head stat_list; 3893 struct f2fs_sb_info *sbi; 3894 int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs; 3895 int main_area_segs, main_area_sections, main_area_zones; 3896 unsigned long long hit_cached[NR_EXTENT_CACHES]; 3897 unsigned long long hit_rbtree[NR_EXTENT_CACHES]; 3898 unsigned long long total_ext[NR_EXTENT_CACHES]; 3899 unsigned long long hit_total[NR_EXTENT_CACHES]; 3900 int ext_tree[NR_EXTENT_CACHES]; 3901 int zombie_tree[NR_EXTENT_CACHES]; 3902 int ext_node[NR_EXTENT_CACHES]; 3903 /* to count memory footprint */ 3904 unsigned long long ext_mem[NR_EXTENT_CACHES]; 3905 /* for read extent cache */ 3906 unsigned long long hit_largest; 3907 /* for block age extent cache */ 3908 unsigned long long allocated_data_blocks; 3909 int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta; 3910 int ndirty_data, ndirty_qdata; 3911 unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all; 3912 int nats, dirty_nats, sits, dirty_sits; 3913 int free_nids, avail_nids, alloc_nids; 3914 int total_count, utilization; 3915 int nr_wb_cp_data, nr_wb_data; 3916 int nr_rd_data, nr_rd_node, nr_rd_meta; 3917 int nr_dio_read, nr_dio_write; 3918 unsigned int io_skip_bggc, other_skip_bggc; 3919 int nr_flushing, nr_flushed, flush_list_empty; 3920 int nr_discarding, nr_discarded; 3921 int nr_discard_cmd; 3922 unsigned int undiscard_blks; 3923 int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt; 3924 unsigned int cur_ckpt_time, peak_ckpt_time; 3925 int inline_xattr, inline_inode, inline_dir, append, update, orphans; 3926 int compr_inode, swapfile_inode; 3927 unsigned long long compr_blocks; 3928 int aw_cnt, max_aw_cnt; 3929 unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks; 3930 unsigned int bimodal, avg_vblocks; 3931 int util_free, util_valid, util_invalid; 3932 int rsvd_segs, overp_segs; 3933 int dirty_count, node_pages, meta_pages, compress_pages; 3934 int compress_page_hit; 3935 int prefree_count, free_segs, free_secs; 3936 int cp_call_count[MAX_CALL_TYPE], cp_count; 3937 int gc_call_count[MAX_CALL_TYPE]; 3938 int gc_segs[2][2]; 3939 int gc_secs[2][2]; 3940 int tot_blks, data_blks, node_blks; 3941 int bg_data_blks, bg_node_blks; 3942 int curseg[NR_CURSEG_TYPE]; 3943 int cursec[NR_CURSEG_TYPE]; 3944 int curzone[NR_CURSEG_TYPE]; 3945 unsigned int dirty_seg[NR_CURSEG_TYPE]; 3946 unsigned int full_seg[NR_CURSEG_TYPE]; 3947 unsigned int valid_blks[NR_CURSEG_TYPE]; 3948 3949 unsigned int meta_count[META_MAX]; 3950 unsigned int segment_count[2]; 3951 unsigned int block_count[2]; 3952 unsigned int inplace_count; 3953 unsigned long long base_mem, cache_mem, page_mem; 3954}; 3955 3956static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) 3957{ 3958 return (struct f2fs_stat_info *)sbi->stat_info; 3959} 3960 3961#define stat_inc_cp_call_count(sbi, foreground) \ 3962 atomic_inc(&sbi->cp_call_count[(foreground)]) 3963#define stat_inc_cp_count(si) (F2FS_STAT(sbi)->cp_count++) 3964#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++) 3965#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++) 3966#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) 3967#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) 3968#define stat_inc_total_hit(sbi, type) (atomic64_inc(&(sbi)->total_hit_ext[type])) 3969#define stat_inc_rbtree_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_rbtree[type])) 3970#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest)) 3971#define stat_inc_cached_node_hit(sbi, type) (atomic64_inc(&(sbi)->read_hit_cached[type])) 3972#define stat_inc_inline_xattr(inode) \ 3973 do { \ 3974 if (f2fs_has_inline_xattr(inode)) \ 3975 (atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \ 3976 } while (0) 3977#define stat_dec_inline_xattr(inode) \ 3978 do { \ 3979 if (f2fs_has_inline_xattr(inode)) \ 3980 (atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \ 3981 } while (0) 3982#define stat_inc_inline_inode(inode) \ 3983 do { \ 3984 if (f2fs_has_inline_data(inode)) \ 3985 (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \ 3986 } while (0) 3987#define stat_dec_inline_inode(inode) \ 3988 do { \ 3989 if (f2fs_has_inline_data(inode)) \ 3990 (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \ 3991 } while (0) 3992#define stat_inc_inline_dir(inode) \ 3993 do { \ 3994 if (f2fs_has_inline_dentry(inode)) \ 3995 (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \ 3996 } while (0) 3997#define stat_dec_inline_dir(inode) \ 3998 do { \ 3999 if (f2fs_has_inline_dentry(inode)) \ 4000 (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ 4001 } while (0) 4002#define stat_inc_compr_inode(inode) \ 4003 do { \ 4004 if (f2fs_compressed_file(inode)) \ 4005 (atomic_inc(&F2FS_I_SB(inode)->compr_inode)); \ 4006 } while (0) 4007#define stat_dec_compr_inode(inode) \ 4008 do { \ 4009 if (f2fs_compressed_file(inode)) \ 4010 (atomic_dec(&F2FS_I_SB(inode)->compr_inode)); \ 4011 } while (0) 4012#define stat_add_compr_blocks(inode, blocks) \ 4013 (atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks)) 4014#define stat_sub_compr_blocks(inode, blocks) \ 4015 (atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks)) 4016#define stat_inc_swapfile_inode(inode) \ 4017 (atomic_inc(&F2FS_I_SB(inode)->swapfile_inode)) 4018#define stat_dec_swapfile_inode(inode) \ 4019 (atomic_dec(&F2FS_I_SB(inode)->swapfile_inode)) 4020#define stat_inc_atomic_inode(inode) \ 4021 (atomic_inc(&F2FS_I_SB(inode)->atomic_files)) 4022#define stat_dec_atomic_inode(inode) \ 4023 (atomic_dec(&F2FS_I_SB(inode)->atomic_files)) 4024#define stat_inc_meta_count(sbi, blkaddr) \ 4025 do { \ 4026 if (blkaddr < SIT_I(sbi)->sit_base_addr) \ 4027 atomic_inc(&(sbi)->meta_count[META_CP]); \ 4028 else if (blkaddr < NM_I(sbi)->nat_blkaddr) \ 4029 atomic_inc(&(sbi)->meta_count[META_SIT]); \ 4030 else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \ 4031 atomic_inc(&(sbi)->meta_count[META_NAT]); \ 4032 else if (blkaddr < SM_I(sbi)->main_blkaddr) \ 4033 atomic_inc(&(sbi)->meta_count[META_SSA]); \ 4034 } while (0) 4035#define stat_inc_seg_type(sbi, curseg) \ 4036 ((sbi)->segment_count[(curseg)->alloc_type]++) 4037#define stat_inc_block_count(sbi, curseg) \ 4038 ((sbi)->block_count[(curseg)->alloc_type]++) 4039#define stat_inc_inplace_blocks(sbi) \ 4040 (atomic_inc(&(sbi)->inplace_count)) 4041#define stat_update_max_atomic_write(inode) \ 4042 do { \ 4043 int cur = atomic_read(&F2FS_I_SB(inode)->atomic_files); \ 4044 int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \ 4045 if (cur > max) \ 4046 atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \ 4047 } while (0) 4048#define stat_inc_gc_call_count(sbi, foreground) \ 4049 (F2FS_STAT(sbi)->gc_call_count[(foreground)]++) 4050#define stat_inc_gc_sec_count(sbi, type, gc_type) \ 4051 (F2FS_STAT(sbi)->gc_secs[(type)][(gc_type)]++) 4052#define stat_inc_gc_seg_count(sbi, type, gc_type) \ 4053 (F2FS_STAT(sbi)->gc_segs[(type)][(gc_type)]++) 4054 4055#define stat_inc_tot_blk_count(si, blks) \ 4056 ((si)->tot_blks += (blks)) 4057 4058#define stat_inc_data_blk_count(sbi, blks, gc_type) \ 4059 do { \ 4060 struct f2fs_stat_info *si = F2FS_STAT(sbi); \ 4061 stat_inc_tot_blk_count(si, blks); \ 4062 si->data_blks += (blks); \ 4063 si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0; \ 4064 } while (0) 4065 4066#define stat_inc_node_blk_count(sbi, blks, gc_type) \ 4067 do { \ 4068 struct f2fs_stat_info *si = F2FS_STAT(sbi); \ 4069 stat_inc_tot_blk_count(si, blks); \ 4070 si->node_blks += (blks); \ 4071 si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0; \ 4072 } while (0) 4073 4074int f2fs_build_stats(struct f2fs_sb_info *sbi); 4075void f2fs_destroy_stats(struct f2fs_sb_info *sbi); 4076void __init f2fs_create_root_stats(void); 4077void f2fs_destroy_root_stats(void); 4078void f2fs_update_sit_info(struct f2fs_sb_info *sbi); 4079#else 4080#define stat_inc_cp_call_count(sbi, foreground) do { } while (0) 4081#define stat_inc_cp_count(sbi) do { } while (0) 4082#define stat_io_skip_bggc_count(sbi) do { } while (0) 4083#define stat_other_skip_bggc_count(sbi) do { } while (0) 4084#define stat_inc_dirty_inode(sbi, type) do { } while (0) 4085#define stat_dec_dirty_inode(sbi, type) do { } while (0) 4086#define stat_inc_total_hit(sbi, type) do { } while (0) 4087#define stat_inc_rbtree_node_hit(sbi, type) do { } while (0) 4088#define stat_inc_largest_node_hit(sbi) do { } while (0) 4089#define stat_inc_cached_node_hit(sbi, type) do { } while (0) 4090#define stat_inc_inline_xattr(inode) do { } while (0) 4091#define stat_dec_inline_xattr(inode) do { } while (0) 4092#define stat_inc_inline_inode(inode) do { } while (0) 4093#define stat_dec_inline_inode(inode) do { } while (0) 4094#define stat_inc_inline_dir(inode) do { } while (0) 4095#define stat_dec_inline_dir(inode) do { } while (0) 4096#define stat_inc_compr_inode(inode) do { } while (0) 4097#define stat_dec_compr_inode(inode) do { } while (0) 4098#define stat_add_compr_blocks(inode, blocks) do { } while (0) 4099#define stat_sub_compr_blocks(inode, blocks) do { } while (0) 4100#define stat_inc_swapfile_inode(inode) do { } while (0) 4101#define stat_dec_swapfile_inode(inode) do { } while (0) 4102#define stat_inc_atomic_inode(inode) do { } while (0) 4103#define stat_dec_atomic_inode(inode) do { } while (0) 4104#define stat_update_max_atomic_write(inode) do { } while (0) 4105#define stat_inc_meta_count(sbi, blkaddr) do { } while (0) 4106#define stat_inc_seg_type(sbi, curseg) do { } while (0) 4107#define stat_inc_block_count(sbi, curseg) do { } while (0) 4108#define stat_inc_inplace_blocks(sbi) do { } while (0) 4109#define stat_inc_gc_call_count(sbi, foreground) do { } while (0) 4110#define stat_inc_gc_sec_count(sbi, type, gc_type) do { } while (0) 4111#define stat_inc_gc_seg_count(sbi, type, gc_type) do { } while (0) 4112#define stat_inc_tot_blk_count(si, blks) do { } while (0) 4113#define stat_inc_data_blk_count(sbi, blks, gc_type) do { } while (0) 4114#define stat_inc_node_blk_count(sbi, blks, gc_type) do { } while (0) 4115 4116static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } 4117static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } 4118static inline void __init f2fs_create_root_stats(void) { } 4119static inline void f2fs_destroy_root_stats(void) { } 4120static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {} 4121#endif 4122 4123extern const struct file_operations f2fs_dir_operations; 4124extern const struct file_operations f2fs_file_operations; 4125extern const struct inode_operations f2fs_file_inode_operations; 4126extern const struct address_space_operations f2fs_dblock_aops; 4127extern const struct address_space_operations f2fs_node_aops; 4128extern const struct address_space_operations f2fs_meta_aops; 4129extern const struct inode_operations f2fs_dir_inode_operations; 4130extern const struct inode_operations f2fs_symlink_inode_operations; 4131extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; 4132extern const struct inode_operations f2fs_special_inode_operations; 4133extern struct kmem_cache *f2fs_inode_entry_slab; 4134 4135/* 4136 * inline.c 4137 */ 4138bool f2fs_may_inline_data(struct inode *inode); 4139bool f2fs_sanity_check_inline_data(struct inode *inode); 4140bool f2fs_may_inline_dentry(struct inode *inode); 4141void f2fs_do_read_inline_data(struct page *page, struct page *ipage); 4142void f2fs_truncate_inline_inode(struct inode *inode, 4143 struct page *ipage, u64 from); 4144int f2fs_read_inline_data(struct inode *inode, struct page *page); 4145int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); 4146int f2fs_convert_inline_inode(struct inode *inode); 4147int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry); 4148int f2fs_write_inline_data(struct inode *inode, struct page *page); 4149int f2fs_recover_inline_data(struct inode *inode, struct page *npage); 4150struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, 4151 const struct f2fs_filename *fname, 4152 struct page **res_page); 4153int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, 4154 struct page *ipage); 4155int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname, 4156 struct inode *inode, nid_t ino, umode_t mode); 4157void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, 4158 struct page *page, struct inode *dir, 4159 struct inode *inode); 4160bool f2fs_empty_inline_dir(struct inode *dir); 4161int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, 4162 struct fscrypt_str *fstr); 4163int f2fs_inline_data_fiemap(struct inode *inode, 4164 struct fiemap_extent_info *fieinfo, 4165 __u64 start, __u64 len); 4166 4167/* 4168 * shrinker.c 4169 */ 4170unsigned long f2fs_shrink_count(struct shrinker *shrink, 4171 struct shrink_control *sc); 4172unsigned long f2fs_shrink_scan(struct shrinker *shrink, 4173 struct shrink_control *sc); 4174void f2fs_join_shrinker(struct f2fs_sb_info *sbi); 4175void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); 4176 4177/* 4178 * extent_cache.c 4179 */ 4180bool sanity_check_extent_cache(struct inode *inode); 4181void f2fs_init_extent_tree(struct inode *inode); 4182void f2fs_drop_extent_tree(struct inode *inode); 4183void f2fs_destroy_extent_node(struct inode *inode); 4184void f2fs_destroy_extent_tree(struct inode *inode); 4185void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi); 4186int __init f2fs_create_extent_cache(void); 4187void f2fs_destroy_extent_cache(void); 4188 4189/* read extent cache ops */ 4190void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage); 4191bool f2fs_lookup_read_extent_cache(struct inode *inode, pgoff_t pgofs, 4192 struct extent_info *ei); 4193bool f2fs_lookup_read_extent_cache_block(struct inode *inode, pgoff_t index, 4194 block_t *blkaddr); 4195void f2fs_update_read_extent_cache(struct dnode_of_data *dn); 4196void f2fs_update_read_extent_cache_range(struct dnode_of_data *dn, 4197 pgoff_t fofs, block_t blkaddr, unsigned int len); 4198unsigned int f2fs_shrink_read_extent_tree(struct f2fs_sb_info *sbi, 4199 int nr_shrink); 4200 4201/* block age extent cache ops */ 4202void f2fs_init_age_extent_tree(struct inode *inode); 4203bool f2fs_lookup_age_extent_cache(struct inode *inode, pgoff_t pgofs, 4204 struct extent_info *ei); 4205void f2fs_update_age_extent_cache(struct dnode_of_data *dn); 4206void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn, 4207 pgoff_t fofs, unsigned int len); 4208unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, 4209 int nr_shrink); 4210 4211/* 4212 * sysfs.c 4213 */ 4214#define MIN_RA_MUL 2 4215#define MAX_RA_MUL 256 4216 4217int __init f2fs_init_sysfs(void); 4218void f2fs_exit_sysfs(void); 4219int f2fs_register_sysfs(struct f2fs_sb_info *sbi); 4220void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi); 4221 4222/* verity.c */ 4223extern const struct fsverity_operations f2fs_verityops; 4224 4225/* 4226 * crypto support 4227 */ 4228static inline bool f2fs_encrypted_file(struct inode *inode) 4229{ 4230 return IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); 4231} 4232 4233static inline void f2fs_set_encrypted_inode(struct inode *inode) 4234{ 4235#ifdef CONFIG_FS_ENCRYPTION 4236 file_set_encrypt(inode); 4237 f2fs_set_inode_flags(inode); 4238#endif 4239} 4240 4241/* 4242 * Returns true if the reads of the inode's data need to undergo some 4243 * postprocessing step, like decryption or authenticity verification. 4244 */ 4245static inline bool f2fs_post_read_required(struct inode *inode) 4246{ 4247 return f2fs_encrypted_file(inode) || fsverity_active(inode) || 4248 f2fs_compressed_file(inode); 4249} 4250 4251/* 4252 * compress.c 4253 */ 4254#ifdef CONFIG_F2FS_FS_COMPRESSION 4255bool f2fs_is_compressed_page(struct page *page); 4256struct page *f2fs_compress_control_page(struct page *page); 4257int f2fs_prepare_compress_overwrite(struct inode *inode, 4258 struct page **pagep, pgoff_t index, void **fsdata); 4259bool f2fs_compress_write_end(struct inode *inode, void *fsdata, 4260 pgoff_t index, unsigned copied); 4261int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); 4262void f2fs_compress_write_end_io(struct bio *bio, struct page *page); 4263bool f2fs_is_compress_backend_ready(struct inode *inode); 4264bool f2fs_is_compress_level_valid(int alg, int lvl); 4265int __init f2fs_init_compress_mempool(void); 4266void f2fs_destroy_compress_mempool(void); 4267void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); 4268void f2fs_end_read_compressed_page(struct page *page, bool failed, 4269 block_t blkaddr, bool in_task); 4270bool f2fs_cluster_is_empty(struct compress_ctx *cc); 4271bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index); 4272bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, 4273 int index, int nr_pages, bool uptodate); 4274bool f2fs_sanity_check_cluster(struct dnode_of_data *dn); 4275void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page); 4276int f2fs_write_multi_pages(struct compress_ctx *cc, 4277 int *submitted, 4278 struct writeback_control *wbc, 4279 enum iostat_type io_type); 4280int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index); 4281void f2fs_update_read_extent_tree_range_compressed(struct inode *inode, 4282 pgoff_t fofs, block_t blkaddr, 4283 unsigned int llen, unsigned int c_len); 4284int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret, 4285 unsigned nr_pages, sector_t *last_block_in_bio, 4286 bool is_readahead, bool for_write); 4287struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); 4288void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, 4289 bool in_task); 4290void f2fs_put_page_dic(struct page *page, bool in_task); 4291unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, 4292 unsigned int ofs_in_node); 4293int f2fs_init_compress_ctx(struct compress_ctx *cc); 4294void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); 4295void f2fs_init_compress_info(struct f2fs_sb_info *sbi); 4296int f2fs_init_compress_inode(struct f2fs_sb_info *sbi); 4297void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi); 4298int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi); 4299void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi); 4300int __init f2fs_init_compress_cache(void); 4301void f2fs_destroy_compress_cache(void); 4302struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi); 4303void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr); 4304void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page, 4305 nid_t ino, block_t blkaddr); 4306bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page, 4307 block_t blkaddr); 4308void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino); 4309#define inc_compr_inode_stat(inode) \ 4310 do { \ 4311 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \ 4312 sbi->compr_new_inode++; \ 4313 } while (0) 4314#define add_compr_block_stat(inode, blocks) \ 4315 do { \ 4316 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); \ 4317 int diff = F2FS_I(inode)->i_cluster_size - blocks; \ 4318 sbi->compr_written_block += blocks; \ 4319 sbi->compr_saved_block += diff; \ 4320 } while (0) 4321#else 4322static inline bool f2fs_is_compressed_page(struct page *page) { return false; } 4323static inline bool f2fs_is_compress_backend_ready(struct inode *inode) 4324{ 4325 if (!f2fs_compressed_file(inode)) 4326 return true; 4327 /* not support compression */ 4328 return false; 4329} 4330static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } 4331static inline struct page *f2fs_compress_control_page(struct page *page) 4332{ 4333 WARN_ON_ONCE(1); 4334 return ERR_PTR(-EINVAL); 4335} 4336static inline int __init f2fs_init_compress_mempool(void) { return 0; } 4337static inline void f2fs_destroy_compress_mempool(void) { } 4338static inline void f2fs_decompress_cluster(struct decompress_io_ctx *dic, 4339 bool in_task) { } 4340static inline void f2fs_end_read_compressed_page(struct page *page, 4341 bool failed, block_t blkaddr, bool in_task) 4342{ 4343 WARN_ON_ONCE(1); 4344} 4345static inline void f2fs_put_page_dic(struct page *page, bool in_task) 4346{ 4347 WARN_ON_ONCE(1); 4348} 4349static inline unsigned int f2fs_cluster_blocks_are_contiguous( 4350 struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } 4351static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } 4352static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } 4353static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } 4354static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return 0; } 4355static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { } 4356static inline int __init f2fs_init_compress_cache(void) { return 0; } 4357static inline void f2fs_destroy_compress_cache(void) { } 4358static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, 4359 block_t blkaddr) { } 4360static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, 4361 struct page *page, nid_t ino, block_t blkaddr) { } 4362static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, 4363 struct page *page, block_t blkaddr) { return false; } 4364static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, 4365 nid_t ino) { } 4366#define inc_compr_inode_stat(inode) do { } while (0) 4367static inline void f2fs_update_read_extent_tree_range_compressed( 4368 struct inode *inode, 4369 pgoff_t fofs, block_t blkaddr, 4370 unsigned int llen, unsigned int c_len) { } 4371#endif 4372 4373static inline int set_compress_context(struct inode *inode) 4374{ 4375#ifdef CONFIG_F2FS_FS_COMPRESSION 4376 struct f2fs_sb_info *sbi = F2FS_I_SB(inode); 4377 4378 F2FS_I(inode)->i_compress_algorithm = 4379 F2FS_OPTION(sbi).compress_algorithm; 4380 F2FS_I(inode)->i_log_cluster_size = 4381 F2FS_OPTION(sbi).compress_log_size; 4382 F2FS_I(inode)->i_compress_flag = 4383 F2FS_OPTION(sbi).compress_chksum ? 4384 BIT(COMPRESS_CHKSUM) : 0; 4385 F2FS_I(inode)->i_cluster_size = 4386 BIT(F2FS_I(inode)->i_log_cluster_size); 4387 if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 || 4388 F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) && 4389 F2FS_OPTION(sbi).compress_level) 4390 F2FS_I(inode)->i_compress_level = 4391 F2FS_OPTION(sbi).compress_level; 4392 F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; 4393 set_inode_flag(inode, FI_COMPRESSED_FILE); 4394 stat_inc_compr_inode(inode); 4395 inc_compr_inode_stat(inode); 4396 f2fs_mark_inode_dirty_sync(inode, true); 4397 return 0; 4398#else 4399 return -EOPNOTSUPP; 4400#endif 4401} 4402 4403static inline bool f2fs_disable_compressed_file(struct inode *inode) 4404{ 4405 struct f2fs_inode_info *fi = F2FS_I(inode); 4406 4407 f2fs_down_write(&F2FS_I(inode)->i_sem); 4408 4409 if (!f2fs_compressed_file(inode)) { 4410 f2fs_up_write(&F2FS_I(inode)->i_sem); 4411 return true; 4412 } 4413 if (f2fs_is_mmap_file(inode) || 4414 (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { 4415 f2fs_up_write(&F2FS_I(inode)->i_sem); 4416 return false; 4417 } 4418 4419 fi->i_flags &= ~F2FS_COMPR_FL; 4420 stat_dec_compr_inode(inode); 4421 clear_inode_flag(inode, FI_COMPRESSED_FILE); 4422 f2fs_mark_inode_dirty_sync(inode, true); 4423 4424 f2fs_up_write(&F2FS_I(inode)->i_sem); 4425 return true; 4426} 4427 4428#define F2FS_FEATURE_FUNCS(name, flagname) \ 4429static inline bool f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \ 4430{ \ 4431 return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \ 4432} 4433 4434F2FS_FEATURE_FUNCS(encrypt, ENCRYPT); 4435F2FS_FEATURE_FUNCS(blkzoned, BLKZONED); 4436F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR); 4437F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA); 4438F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM); 4439F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); 4440F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); 4441F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); 4442F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); 4443F2FS_FEATURE_FUNCS(verity, VERITY); 4444F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); 4445F2FS_FEATURE_FUNCS(casefold, CASEFOLD); 4446F2FS_FEATURE_FUNCS(compression, COMPRESSION); 4447F2FS_FEATURE_FUNCS(readonly, RO); 4448 4449#ifdef CONFIG_BLK_DEV_ZONED 4450static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, 4451 block_t blkaddr) 4452{ 4453 unsigned int zno = blkaddr / sbi->blocks_per_blkz; 4454 4455 return test_bit(zno, FDEV(devi).blkz_seq); 4456} 4457#endif 4458 4459static inline int f2fs_bdev_index(struct f2fs_sb_info *sbi, 4460 struct block_device *bdev) 4461{ 4462 int i; 4463 4464 if (!f2fs_is_multi_device(sbi)) 4465 return 0; 4466 4467 for (i = 0; i < sbi->s_ndevs; i++) 4468 if (FDEV(i).bdev == bdev) 4469 return i; 4470 4471 WARN_ON(1); 4472 return -1; 4473} 4474 4475static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) 4476{ 4477 return f2fs_sb_has_blkzoned(sbi); 4478} 4479 4480static inline bool f2fs_bdev_support_discard(struct block_device *bdev) 4481{ 4482 return bdev_max_discard_sectors(bdev) || bdev_is_zoned(bdev); 4483} 4484 4485static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) 4486{ 4487 int i; 4488 4489 if (!f2fs_is_multi_device(sbi)) 4490 return f2fs_bdev_support_discard(sbi->sb->s_bdev); 4491 4492 for (i = 0; i < sbi->s_ndevs; i++) 4493 if (f2fs_bdev_support_discard(FDEV(i).bdev)) 4494 return true; 4495 return false; 4496} 4497 4498static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) 4499{ 4500 return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || 4501 f2fs_hw_should_discard(sbi); 4502} 4503 4504static inline bool f2fs_hw_is_readonly(struct f2fs_sb_info *sbi) 4505{ 4506 int i; 4507 4508 if (!f2fs_is_multi_device(sbi)) 4509 return bdev_read_only(sbi->sb->s_bdev); 4510 4511 for (i = 0; i < sbi->s_ndevs; i++) 4512 if (bdev_read_only(FDEV(i).bdev)) 4513 return true; 4514 return false; 4515} 4516 4517static inline bool f2fs_dev_is_readonly(struct f2fs_sb_info *sbi) 4518{ 4519 return f2fs_sb_has_readonly(sbi) || f2fs_hw_is_readonly(sbi); 4520} 4521 4522static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi) 4523{ 4524 return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS; 4525} 4526 4527static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi) 4528{ 4529 return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW; 4530} 4531 4532static inline bool f2fs_may_compress(struct inode *inode) 4533{ 4534 if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) || 4535 f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode) || 4536 f2fs_is_mmap_file(inode)) 4537 return false; 4538 return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); 4539} 4540 4541static inline void f2fs_i_compr_blocks_update(struct inode *inode, 4542 u64 blocks, bool add) 4543{ 4544 struct f2fs_inode_info *fi = F2FS_I(inode); 4545 int diff = fi->i_cluster_size - blocks; 4546 4547 /* don't update i_compr_blocks if saved blocks were released */ 4548 if (!add && !atomic_read(&fi->i_compr_blocks)) 4549 return; 4550 4551 if (add) { 4552 atomic_add(diff, &fi->i_compr_blocks); 4553 stat_add_compr_blocks(inode, diff); 4554 } else { 4555 atomic_sub(diff, &fi->i_compr_blocks); 4556 stat_sub_compr_blocks(inode, diff); 4557 } 4558 f2fs_mark_inode_dirty_sync(inode, true); 4559} 4560 4561static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi, 4562 int flag) 4563{ 4564 if (!f2fs_is_multi_device(sbi)) 4565 return false; 4566 if (flag != F2FS_GET_BLOCK_DIO) 4567 return false; 4568 return sbi->aligned_blksize; 4569} 4570 4571static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx) 4572{ 4573 return fsverity_active(inode) && (idx < 4574 DIV_ROUND_UP(fsverity_get_verified_data_size(inode), PAGE_SIZE)); 4575} 4576 4577#ifdef CONFIG_F2FS_FAULT_INJECTION 4578extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, 4579 unsigned int type); 4580#else 4581#define f2fs_build_fault_attr(sbi, rate, type) do { } while (0) 4582#endif 4583 4584static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) 4585{ 4586#ifdef CONFIG_QUOTA 4587 if (f2fs_sb_has_quota_ino(sbi)) 4588 return true; 4589 if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || 4590 F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || 4591 F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) 4592 return true; 4593#endif 4594 return false; 4595} 4596 4597static inline bool f2fs_block_unit_discard(struct f2fs_sb_info *sbi) 4598{ 4599 return F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_BLOCK; 4600} 4601 4602static inline void f2fs_io_schedule_timeout(long timeout) 4603{ 4604 set_current_state(TASK_UNINTERRUPTIBLE); 4605 io_schedule_timeout(timeout); 4606} 4607 4608static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi, pgoff_t ofs, 4609 enum page_type type) 4610{ 4611 if (unlikely(f2fs_cp_error(sbi))) 4612 return; 4613 4614 if (ofs == sbi->page_eio_ofs[type]) { 4615 if (sbi->page_eio_cnt[type]++ == MAX_RETRY_PAGE_EIO) 4616 set_ckpt_flags(sbi, CP_ERROR_FLAG); 4617 } else { 4618 sbi->page_eio_ofs[type] = ofs; 4619 sbi->page_eio_cnt[type] = 0; 4620 } 4621} 4622 4623static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi) 4624{ 4625 return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb); 4626} 4627 4628static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, 4629 block_t blkaddr, unsigned int cnt) 4630{ 4631 bool need_submit = false; 4632 int i = 0; 4633 4634 do { 4635 struct page *page; 4636 4637 page = find_get_page(META_MAPPING(sbi), blkaddr + i); 4638 if (page) { 4639 if (PageWriteback(page)) 4640 need_submit = true; 4641 f2fs_put_page(page, 0); 4642 } 4643 } while (++i < cnt && !need_submit); 4644 4645 if (need_submit) 4646 f2fs_submit_merged_write_cond(sbi, sbi->meta_inode, 4647 NULL, 0, DATA); 4648 4649 truncate_inode_pages_range(META_MAPPING(sbi), 4650 F2FS_BLK_TO_BYTES((loff_t)blkaddr), 4651 F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1))); 4652} 4653 4654static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi, 4655 block_t blkaddr) 4656{ 4657 f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1); 4658 f2fs_invalidate_compress_page(sbi, blkaddr); 4659} 4660 4661#define EFSBADCRC EBADMSG /* Bad CRC detected */ 4662#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ 4663 4664#endif /* _LINUX_F2FS_H */ 4665