| /* SPDX-License-Identifier: GPL-2.0 */ |
| /* |
| * fs/f2fs/f2fs.h |
| * |
| * Copyright (c) 2012 Samsung Electronics Co., Ltd. |
| * http://www.samsung.com/ |
| */ |
| #ifndef _LINUX_F2FS_H |
| #define _LINUX_F2FS_H |
| |
| #include <linux/uio.h> |
| #include <linux/types.h> |
| #include <linux/page-flags.h> |
| #include <linux/buffer_head.h> |
| #include <linux/slab.h> |
| #include <linux/crc32.h> |
| #include <linux/magic.h> |
| #include <linux/kobject.h> |
| #include <linux/sched.h> |
| #include <linux/cred.h> |
| #include <linux/sched/mm.h> |
| #include <linux/vmalloc.h> |
| #include <linux/bio.h> |
| #include <linux/blkdev.h> |
| #include <linux/quotaops.h> |
| #include <linux/part_stat.h> |
| #include <linux/rw_hint.h> |
| #include <crypto/hash.h> |
| |
| #include <linux/fscrypt.h> |
| #include <linux/fsverity.h> |
| |
| struct pagevec; |
| |
| #ifdef CONFIG_F2FS_CHECK_FS |
| #define f2fs_bug_on(sbi, condition) BUG_ON(condition) |
| #else |
| #define f2fs_bug_on(sbi, condition) \ |
| do { \ |
| if (WARN_ON(condition)) \ |
| set_sbi_flag(sbi, SBI_NEED_FSCK); \ |
| } while (0) |
| #endif |
| |
| enum { |
| FAULT_KMALLOC, |
| FAULT_KVMALLOC, |
| FAULT_PAGE_ALLOC, |
| FAULT_PAGE_GET, |
| FAULT_ALLOC_BIO, /* it's obsolete due to bio_alloc() will never fail */ |
| FAULT_ALLOC_NID, |
| FAULT_ORPHAN, |
| FAULT_BLOCK, |
| FAULT_DIR_DEPTH, |
| FAULT_EVICT_INODE, |
| FAULT_TRUNCATE, |
| FAULT_READ_IO, |
| FAULT_CHECKPOINT, |
| FAULT_DISCARD, |
| FAULT_WRITE_IO, |
| FAULT_SLAB_ALLOC, |
| FAULT_DQUOT_INIT, |
| FAULT_LOCK_OP, |
| FAULT_BLKADDR_VALIDITY, |
| FAULT_BLKADDR_CONSISTENCE, |
| FAULT_NO_SEGMENT, |
| FAULT_MAX, |
| }; |
| |
| #ifdef CONFIG_F2FS_FAULT_INJECTION |
| #define F2FS_ALL_FAULT_TYPE (GENMASK(FAULT_MAX - 1, 0)) |
| |
| struct f2fs_fault_info { |
| atomic_t inject_ops; |
| int inject_rate; |
| unsigned int inject_type; |
| }; |
| |
| extern const char *f2fs_fault_name[FAULT_MAX]; |
| #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) |
| |
| /* maximum retry count for injected failure */ |
| #define DEFAULT_FAILURE_RETRY_COUNT 8 |
| #else |
| #define DEFAULT_FAILURE_RETRY_COUNT 1 |
| #endif |
| |
| /* |
| * For mount options |
| */ |
| #define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000001 |
| #define F2FS_MOUNT_DISCARD 0x00000002 |
| #define F2FS_MOUNT_NOHEAP 0x00000004 |
| #define F2FS_MOUNT_XATTR_USER 0x00000008 |
| #define F2FS_MOUNT_POSIX_ACL 0x00000010 |
| #define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000020 |
| #define F2FS_MOUNT_INLINE_XATTR 0x00000040 |
| #define F2FS_MOUNT_INLINE_DATA 0x00000080 |
| #define F2FS_MOUNT_INLINE_DENTRY 0x00000100 |
| #define F2FS_MOUNT_FLUSH_MERGE 0x00000200 |
| #define F2FS_MOUNT_NOBARRIER 0x00000400 |
| #define F2FS_MOUNT_FASTBOOT 0x00000800 |
| #define F2FS_MOUNT_READ_EXTENT_CACHE 0x00001000 |
| #define F2FS_MOUNT_DATA_FLUSH 0x00002000 |
| #define F2FS_MOUNT_FAULT_INJECTION 0x00004000 |
| #define F2FS_MOUNT_USRQUOTA 0x00008000 |
| #define F2FS_MOUNT_GRPQUOTA 0x00010000 |
| #define F2FS_MOUNT_PRJQUOTA 0x00020000 |
| #define F2FS_MOUNT_QUOTA 0x00040000 |
| #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00080000 |
| #define F2FS_MOUNT_RESERVE_ROOT 0x00100000 |
| #define F2FS_MOUNT_DISABLE_CHECKPOINT 0x00200000 |
| #define F2FS_MOUNT_NORECOVERY 0x00400000 |
| #define F2FS_MOUNT_ATGC 0x00800000 |
| #define F2FS_MOUNT_MERGE_CHECKPOINT 0x01000000 |
| #define F2FS_MOUNT_GC_MERGE 0x02000000 |
| #define F2FS_MOUNT_COMPRESS_CACHE 0x04000000 |
| #define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000 |
| |
| #define F2FS_OPTION(sbi) ((sbi)->mount_opt) |
| #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) |
| #define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) |
| #define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) |
| |
| #define ver_after(a, b) (typecheck(unsigned long long, a) && \ |
| typecheck(unsigned long long, b) && \ |
| ((long long)((a) - (b)) > 0)) |
| |
| typedef u32 block_t; /* |
| * should not change u32, since it is the on-disk block |
| * address format, __le32. |
| */ |
| typedef u32 nid_t; |
| |
| #define COMPRESS_EXT_NUM 16 |
| |
| /* |
| * An implementation of an rwsem that is explicitly unfair to readers. This |
| * prevents priority inversion when a low-priority reader acquires the read lock |
| * while sleeping on the write lock but the write lock is needed by |
| * higher-priority clients. |
| */ |
| |
| struct f2fs_rwsem { |
| struct rw_semaphore internal_rwsem; |
| #ifdef CONFIG_F2FS_UNFAIR_RWSEM |
| wait_queue_head_t read_waiters; |
| #endif |
| }; |
| |
| struct f2fs_mount_info { |
| unsigned int opt; |
| block_t root_reserved_blocks; /* root reserved blocks */ |
| kuid_t s_resuid; /* reserved blocks for uid */ |
| kgid_t s_resgid; /* reserved blocks for gid */ |
| int active_logs; /* # of active logs */ |
| int inline_xattr_size; /* inline xattr size */ |
| #ifdef CONFIG_F2FS_FAULT_INJECTION |
| struct f2fs_fault_info fault_info; /* For fault injection */ |
| #endif |
| #ifdef CONFIG_QUOTA |
| /* Names of quota files with journalled quota */ |
| char *s_qf_names[MAXQUOTAS]; |
| int s_jquota_fmt; /* Format of quota to use */ |
| #endif |
| /* For which write hints are passed down to block layer */ |
| int alloc_mode; /* segment allocation policy */ |
| int fsync_mode; /* fsync policy */ |
| int fs_mode; /* fs mode: LFS or ADAPTIVE */ |
| int bggc_mode; /* bggc mode: off, on or sync */ |
| int memory_mode; /* memory mode */ |
| int errors; /* errors parameter */ |
| int discard_unit; /* |
| * discard command's offset/size should |
| * be aligned to this unit: block, |
| * segment or section |
| */ |
| struct fscrypt_dummy_policy dummy_enc_policy; /* test dummy encryption */ |
| block_t unusable_cap_perc; /* percentage for cap */ |
| block_t unusable_cap; /* Amount of space allowed to be |
| * unusable when disabling checkpoint |
| */ |
| |
| /* For compression */ |
| unsigned char compress_algorithm; /* algorithm type */ |
| unsigned char compress_log_size; /* cluster log size */ |
| unsigned char compress_level; /* compress level */ |
| bool compress_chksum; /* compressed data chksum */ |
| unsigned char compress_ext_cnt; /* extension count */ |
| unsigned char nocompress_ext_cnt; /* nocompress extension count */ |
| int compress_mode; /* compression mode */ |
| unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ |
| unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ |
| }; |
| |
| #define F2FS_FEATURE_ENCRYPT 0x00000001 |
| #define F2FS_FEATURE_BLKZONED 0x00000002 |
| #define F2FS_FEATURE_ATOMIC_WRITE 0x00000004 |
| #define F2FS_FEATURE_EXTRA_ATTR 0x00000008 |
| #define F2FS_FEATURE_PRJQUOTA 0x00000010 |
| #define F2FS_FEATURE_INODE_CHKSUM 0x00000020 |
| #define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x00000040 |
| #define F2FS_FEATURE_QUOTA_INO 0x00000080 |
| #define F2FS_FEATURE_INODE_CRTIME 0x00000100 |
| #define F2FS_FEATURE_LOST_FOUND 0x00000200 |
| #define F2FS_FEATURE_VERITY 0x00000400 |
| #define F2FS_FEATURE_SB_CHKSUM 0x00000800 |
| #define F2FS_FEATURE_CASEFOLD 0x00001000 |
| #define F2FS_FEATURE_COMPRESSION 0x00002000 |
| #define F2FS_FEATURE_RO 0x00004000 |
| |
| #define __F2FS_HAS_FEATURE(raw_super, mask) \ |
| ((raw_super->feature & cpu_to_le32(mask)) != 0) |
| #define F2FS_HAS_FEATURE(sbi, mask) __F2FS_HAS_FEATURE(sbi->raw_super, mask) |
| |
| /* |
| * Default values for user and/or group using reserved blocks |
| */ |
| #define F2FS_DEF_RESUID 0 |
| #define F2FS_DEF_RESGID 0 |
| |
| /* |
| * For checkpoint manager |
| */ |
| enum { |
| NAT_BITMAP, |
| SIT_BITMAP |
| }; |
| |
| #define CP_UMOUNT 0x00000001 |
| #define CP_FASTBOOT 0x00000002 |
| #define CP_SYNC 0x00000004 |
| #define CP_RECOVERY 0x00000008 |
| #define CP_DISCARD 0x00000010 |
| #define CP_TRIMMED 0x00000020 |
| #define CP_PAUSE 0x00000040 |
| #define CP_RESIZE 0x00000080 |
| |
| #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ |
| #define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ |
| #define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ |
| #define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ |
| #define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ |
| #define DEF_CP_INTERVAL 60 /* 60 secs */ |
| #define DEF_IDLE_INTERVAL 5 /* 5 secs */ |
| #define DEF_DISABLE_INTERVAL 5 /* 5 secs */ |
| #define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ |
| #define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ |
| |
| struct cp_control { |
| int reason; |
| __u64 trim_start; |
| __u64 trim_end; |
| __u64 trim_minlen; |
| }; |
| |
| /* |
| * indicate meta/data type |
| */ |
| enum { |
| META_CP, |
| META_NAT, |
| META_SIT, |
| META_SSA, |
| META_MAX, |
| META_POR, |
| DATA_GENERIC, /* check range only */ |
| DATA_GENERIC_ENHANCE, /* strong check on range and segment bitmap */ |
| DATA_GENERIC_ENHANCE_READ, /* |
| * strong check on range and segment |
| * bitmap but no warning due to race |
| * condition of read on truncated area |
| * by extent_cache |
| */ |
| DATA_GENERIC_ENHANCE_UPDATE, /* |
| * strong check on range and segment |
| * bitmap for update case |
| */ |
| META_GENERIC, |
| }; |
| |
| /* for the list of ino */ |
| enum { |
| ORPHAN_INO, /* for orphan ino list */ |
| APPEND_INO, /* for append ino list */ |
| UPDATE_INO, /* for update ino list */ |
| TRANS_DIR_INO, /* for transactions dir ino list */ |
| FLUSH_INO, /* for multiple device flushing */ |
| MAX_INO_ENTRY, /* max. list */ |
| }; |
| |
| struct ino_entry { |
| struct list_head list; /* list head */ |
| nid_t ino; /* inode number */ |
| unsigned int dirty_device; /* dirty device bitmap */ |
| }; |
| |
| /* for the list of inodes to be GCed */ |
| struct inode_entry { |
| struct list_head list; /* list head */ |
| struct inode *inode; /* vfs inode pointer */ |
| }; |
| |
| struct fsync_node_entry { |
| struct list_head list; /* list head */ |
| struct page *page; /* warm node page pointer */ |
| unsigned int seq_id; /* sequence id */ |
| }; |
| |
| struct ckpt_req { |
| struct completion wait; /* completion for checkpoint done */ |
| struct llist_node llnode; /* llist_node to be linked in wait queue */ |
| int ret; /* return code of checkpoint */ |
| ktime_t queue_time; /* request queued time */ |
| }; |
| |
| struct ckpt_req_control { |
| struct task_struct *f2fs_issue_ckpt; /* checkpoint task */ |
| int ckpt_thread_ioprio; /* checkpoint merge thread ioprio */ |
| wait_queue_head_t ckpt_wait_queue; /* waiting queue for wake-up */ |
| atomic_t issued_ckpt; /* # of actually issued ckpts */ |
| atomic_t total_ckpt; /* # of total ckpts */ |
| atomic_t queued_ckpt; /* # of queued ckpts */ |
| struct llist_head issue_list; /* list for command issue */ |
| spinlock_t stat_lock; /* lock for below checkpoint time stats */ |
| unsigned int cur_time; /* cur wait time in msec for currently issued checkpoint */ |
| unsigned int peak_time; /* peak wait time in msec until now */ |
| }; |
| |
| /* for the bitmap indicate blocks to be discarded */ |
| struct discard_entry { |
| struct list_head list; /* list head */ |
| block_t start_blkaddr; /* start blockaddr of current segment */ |
| unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */ |
| }; |
| |
| /* minimum discard granularity, unit: block count */ |
| #define MIN_DISCARD_GRANULARITY 1 |
| /* default discard granularity of inner discard thread, unit: block count */ |
| #define DEFAULT_DISCARD_GRANULARITY 16 |
| /* default maximum discard granularity of ordered discard, unit: block count */ |
| #define DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY 16 |
| |
| /* max discard pend list number */ |
| #define MAX_PLIST_NUM 512 |
| #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ |
| (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) |
| |
| enum { |
| D_PREP, /* initial */ |
| D_PARTIAL, /* partially submitted */ |
| D_SUBMIT, /* all submitted */ |
| D_DONE, /* finished */ |
| }; |
| |
| struct discard_info { |
| block_t lstart; /* logical start address */ |
| block_t len; /* length */ |
| block_t start; /* actual start address in dev */ |
| }; |
| |
| struct discard_cmd { |
| struct rb_node rb_node; /* rb node located in rb-tree */ |
| struct discard_info di; /* discard info */ |
| struct list_head list; /* command list */ |
| struct completion wait; /* compleation */ |
| struct block_device *bdev; /* bdev */ |
| unsigned short ref; /* reference count */ |
| unsigned char state; /* state */ |
| unsigned char queued; /* queued discard */ |
| int error; /* bio error */ |
| spinlock_t lock; /* for state/bio_ref updating */ |
| unsigned short bio_ref; /* bio reference count */ |
| }; |
| |
| enum { |
| DPOLICY_BG, |
| DPOLICY_FORCE, |
| DPOLICY_FSTRIM, |
| DPOLICY_UMOUNT, |
| MAX_DPOLICY, |
| }; |
| |
| enum { |
| DPOLICY_IO_AWARE_DISABLE, /* force to not be aware of IO */ |
| DPOLICY_IO_AWARE_ENABLE, /* force to be aware of IO */ |
| DPOLICY_IO_AWARE_MAX, |
| }; |
| |
| struct discard_policy { |
| int type; /* type of discard */ |
| unsigned int min_interval; /* used for candidates exist */ |
| unsigned int mid_interval; /* used for device busy */ |
| unsigned int max_interval; /* used for candidates not exist */ |
| unsigned int max_requests; /* # of discards issued per round */ |
| unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ |
| bool io_aware; /* issue discard in idle time */ |
| bool sync; /* submit discard with REQ_SYNC flag */ |
| bool ordered; /* issue discard by lba order */ |
| bool timeout; /* discard timeout for put_super */ |
| unsigned int granularity; /* discard granularity */ |
| }; |
| |
| struct discard_cmd_control { |
| struct task_struct *f2fs_issue_discard; /* discard thread */ |
| struct list_head entry_list; /* 4KB discard entry list */ |
| struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */ |
| struct list_head wait_list; /* store on-flushing entries */ |
| struct list_head fstrim_list; /* in-flight discard from fstrim */ |
| wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */ |
| struct mutex cmd_lock; |
| unsigned int nr_discards; /* # of discards in the list */ |
| unsigned int max_discards; /* max. discards to be issued */ |
| unsigned int max_discard_request; /* max. discard request per round */ |
| unsigned int min_discard_issue_time; /* min. interval between discard issue */ |
| unsigned int mid_discard_issue_time; /* mid. interval between discard issue */ |
| unsigned int max_discard_issue_time; /* max. interval between discard issue */ |
| unsigned int discard_io_aware_gran; /* minimum discard granularity not be aware of I/O */ |
| unsigned int discard_urgent_util; /* utilization which issue discard proactively */ |
| unsigned int discard_granularity; /* discard granularity */ |
| unsigned int max_ordered_discard; /* maximum discard granularity issued by lba order */ |
| unsigned int discard_io_aware; /* io_aware policy */ |
| unsigned int undiscard_blks; /* # of undiscard blocks */ |
| unsigned int next_pos; /* next discard position */ |
| atomic_t issued_discard; /* # of issued discard */ |
| atomic_t queued_discard; /* # of queued discard */ |
| atomic_t discard_cmd_cnt; /* # of cached cmd count */ |
| struct rb_root_cached root; /* root of discard rb-tree */ |
| bool rbtree_check; /* config for consistence check */ |
| bool discard_wake; /* to wake up discard thread */ |
| }; |
| |
| /* for the list of fsync inodes, used only during recovery */ |
| struct fsync_inode_entry { |
| struct list_head list; /* list head */ |
| struct inode *inode; /* vfs inode pointer */ |
| block_t blkaddr; /* block address locating the last fsync */ |
| block_t last_dentry; /* block address locating the last dentry */ |
| }; |
| |
| #define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats)) |
| #define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits)) |
| |
| #define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne) |
| #define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid) |
| #define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se) |
| #define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno) |
| |
| #define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl)) |
| #define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl)) |
| |
| static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i) |
| { |
| int before = nats_in_cursum(journal); |
| |
| journal->n_nats = cpu_to_le16(before + i); |
| return before; |
| } |
| |
| static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i) |
| { |
| int before = sits_in_cursum(journal); |
| |
| journal->n_sits = cpu_to_le16(before + i); |
| return before; |
| } |
| |
| static inline bool __has_cursum_space(struct f2fs_journal *journal, |
| int size, int type) |
| { |
| if (type == NAT_JOURNAL) |
| return size <= MAX_NAT_JENTRIES(journal); |
| return size <= MAX_SIT_JENTRIES(journal); |
| } |
| |
| /* for inline stuff */ |
| #define DEF_INLINE_RESERVED_SIZE 1 |
| static inline int get_extra_isize(struct inode *inode); |
| static inline int get_inline_xattr_addrs(struct inode *inode); |
| #define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ |
| (CUR_ADDRS_PER_INODE(inode) - \ |
| get_inline_xattr_addrs(inode) - \ |
| DEF_INLINE_RESERVED_SIZE)) |
| |
| /* for inline dir */ |
| #define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ |
| ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ |
| BITS_PER_BYTE + 1)) |
| #define INLINE_DENTRY_BITMAP_SIZE(inode) \ |
| DIV_ROUND_UP(NR_INLINE_DENTRY(inode), BITS_PER_BYTE) |
| #define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \ |
| ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ |
| NR_INLINE_DENTRY(inode) + \ |
| INLINE_DENTRY_BITMAP_SIZE(inode))) |
| |
| /* |
| * For INODE and NODE manager |
| */ |
| /* for directory operations */ |
| |
| struct f2fs_filename { |
| /* |
| * The filename the user specified. This is NULL for some |
| * filesystem-internal operations, e.g. converting an inline directory |
| * to a non-inline one, or roll-forward recovering an encrypted dentry. |
| */ |
| const struct qstr *usr_fname; |
| |
| /* |
| * The on-disk filename. For encrypted directories, this is encrypted. |
| * This may be NULL for lookups in an encrypted dir without the key. |
| */ |
| struct fscrypt_str disk_name; |
| |
| /* The dirhash of this filename */ |
| f2fs_hash_t hash; |
| |
| #ifdef CONFIG_FS_ENCRYPTION |
| /* |
| * For lookups in encrypted directories: either the buffer backing |
| * disk_name, or a buffer that holds the decoded no-key name. |
| */ |
| struct fscrypt_str crypto_buf; |
| #endif |
| #if IS_ENABLED(CONFIG_UNICODE) |
| /* |
| * For casefolded directories: the casefolded name, but it's left NULL |
| * if the original name is not valid Unicode, if the original name is |
| * "." or "..", if the directory is both casefolded and encrypted and |
| * its encryption key is unavailable, or if the filesystem is doing an |
| * internal operation where usr_fname is also NULL. In all these cases |
| * we fall back to treating the name as an opaque byte sequence. |
| */ |
| struct qstr cf_name; |
| #endif |
| }; |
| |
| struct f2fs_dentry_ptr { |
| struct inode *inode; |
| void *bitmap; |
| struct f2fs_dir_entry *dentry; |
| __u8 (*filename)[F2FS_SLOT_LEN]; |
| int max; |
| int nr_bitmap; |
| }; |
| |
| static inline void make_dentry_ptr_block(struct inode *inode, |
| struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t) |
| { |
| d->inode = inode; |
| d->max = NR_DENTRY_IN_BLOCK; |
| d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; |
| d->bitmap = t->dentry_bitmap; |
| d->dentry = t->dentry; |
| d->filename = t->filename; |
| } |
| |
| static inline void make_dentry_ptr_inline(struct inode *inode, |
| struct f2fs_dentry_ptr *d, void *t) |
| { |
| int entry_cnt = NR_INLINE_DENTRY(inode); |
| int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode); |
| int reserved_size = INLINE_RESERVED_SIZE(inode); |
| |
| d->inode = inode; |
| d->max = entry_cnt; |
| d->nr_bitmap = bitmap_size; |
| d->bitmap = t; |
| d->dentry = t + bitmap_size + reserved_size; |
| d->filename = t + bitmap_size + reserved_size + |
| SIZE_OF_DIR_ENTRY * entry_cnt; |
| } |
| |
| /* |
| * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1 |
| * as its node offset to distinguish from index node blocks. |
| * But some bits are used to mark the node block. |
| */ |
| #define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \ |
| >> OFFSET_BIT_SHIFT) |
| enum { |
| ALLOC_NODE, /* allocate a new node page if needed */ |
| LOOKUP_NODE, /* look up a node without readahead */ |
| LOOKUP_NODE_RA, /* |
| * look up a node with readahead called |
| * by get_data_block. |
| */ |
| }; |
| |
| #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO or flush count */ |
| |
| /* congestion wait timeout value, default: 20ms */ |
| #define DEFAULT_IO_TIMEOUT (msecs_to_jiffies(20)) |
| |
| /* maximum retry quota flush count */ |
| #define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 |
| |
| /* maximum retry of EIO'ed page */ |
| #define MAX_RETRY_PAGE_EIO 100 |
| |
| #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ |
| |
| #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ |
| |
| /* dirty segments threshold for triggering CP */ |
| #define DEFAULT_DIRTY_THRESHOLD 4 |
| |
| #define RECOVERY_MAX_RA_BLOCKS BIO_MAX_VECS |
| #define RECOVERY_MIN_RA_BLOCKS 1 |
| |
| #define F2FS_ONSTACK_PAGES 16 /* nr of onstack pages */ |
| |
| /* for in-memory extent cache entry */ |
| #define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ |
| |
| /* number of extent info in extent cache we try to shrink */ |
| #define READ_EXTENT_CACHE_SHRINK_NUMBER 128 |
| |
| /* number of age extent info in extent cache we try to shrink */ |
| #define AGE_EXTENT_CACHE_SHRINK_NUMBER 128 |
| #define LAST_AGE_WEIGHT 30 |
| #define SAME_AGE_REGION 1024 |
| |
| /* |
| * Define data block with age less than 1GB as hot data |
| * define data block with age less than 10GB but more than 1GB as warm data |
| */ |
| #define DEF_HOT_DATA_AGE_THRESHOLD 262144 |
| #define DEF_WARM_DATA_AGE_THRESHOLD 2621440 |
| |
| /* extent cache type */ |
| enum extent_type { |
| EX_READ, |
| EX_BLOCK_AGE, |
| NR_EXTENT_CACHES, |
| }; |
| |
| struct extent_info { |
| unsigned int fofs; /* start offset in a file */ |
| unsigned int len; /* length of the extent */ |
| union { |
| /* read extent_cache */ |
| struct { |
| /* start block address of the extent */ |
| block_t blk; |
| #ifdef CONFIG_F2FS_FS_COMPRESSION |
| /* physical extent length of compressed blocks */ |
| unsigned int c_len; |
| #endif |
| }; |
| /* block age extent_cache */ |
| struct { |
| /* block age of the extent */ |
| unsigned long long age; |
| /* last total blocks allocated */ |
| unsigned long long last_blocks; |
| }; |
| }; |
| }; |
| |
| struct extent_node { |
| struct rb_node rb_node; /* rb node located in rb-tree */ |
| struct extent_info ei; /* extent info */ |
| struct list_head list; /* node in global extent list of sbi */ |
| struct extent_tree *et; /* extent tree pointer */ |
| }; |
| |
| struct extent_tree { |
| nid_t ino; /* inode number */ |
| enum extent_type type; /* keep the extent tree type */ |
| struct rb_root_cached root; /* root of extent info rb-tree */ |
| struct extent_node *cached_en; /* recently accessed extent node */ |
| struct list_head list; /* to be used by sbi->zombie_list */ |
| rwlock_t lock; /* protect extent info rb-tree */ |
| atomic_t node_cnt; /* # of extent node in rb-tree*/ |
| bool largest_updated; /* largest extent updated */ |
| struct extent_info largest; /* largest cached extent for EX_READ */ |
| }; |
| |
| struct extent_tree_info { |
| struct radix_tree_root extent_tree_root;/* cache extent cache entries */ |
| struct mutex extent_tree_lock; /* locking extent radix tree */ |
| struct list_head extent_list; /* lru list for shrinker */ |
| spinlock_t extent_lock; /* locking extent lru list */ |
| atomic_t total_ext_tree; /* extent tree count */ |
| struct list_head zombie_list; /* extent zombie tree list */ |
| atomic_t total_zombie_tree; /* extent zombie tree count */ |
| atomic_t total_ext_node; /* extent info count */ |
| }; |
| |
| /* |
| * State of block returned by f2fs_map_blocks. |
| */ |
| #define F2FS_MAP_NEW (1U << 0) |
| #define F2FS_MAP_MAPPED (1U << 1) |
| #define F2FS_MAP_DELALLOC (1U << 2) |
| #define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\ |
| F2FS_MAP_DELALLOC) |
| |
| struct f2fs_map_blocks { |
| struct block_device *m_bdev; /* for multi-device dio */ |
| block_t m_pblk; |
| block_t m_lblk; |
| unsigned int m_len; |
| unsigned int m_flags; |
| pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */ |
| pgoff_t *m_next_extent; /* point to next possible extent */ |
| int m_seg_type; |
| bool m_may_create; /* indicate it is from write path */ |
| bool m_multidev_dio; /* indicate it allows multi-device dio */ |
| }; |
| |
| /* for flag in get_data_block */ |
| enum { |
| F2FS_GET_BLOCK_DEFAULT, |
| F2FS_GET_BLOCK_FIEMAP, |
| F2FS_GET_BLOCK_BMAP, |
| F2FS_GET_BLOCK_DIO, |
| F2FS_GET_BLOCK_PRE_DIO, |
| F2FS_GET_BLOCK_PRE_AIO, |
| F2FS_GET_BLOCK_PRECACHE, |
| }; |
| |
| /* |
| * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. |
| */ |
| #define FADVISE_COLD_BIT 0x01 |
| #define FADVISE_LOST_PINO_BIT 0x02 |
| #define FADVISE_ENCRYPT_BIT 0x04 |
| #define FADVISE_ENC_NAME_BIT 0x08 |
| #define FADVISE_KEEP_SIZE_BIT 0x10 |
| #define FADVISE_HOT_BIT 0x20 |
| #define FADVISE_VERITY_BIT 0x40 |
| #define FADVISE_TRUNC_BIT 0x80 |
| |
| #define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT) |
| |
| #define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) |
| #define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT) |
| #define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT) |
| |
| #define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) |
| #define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT) |
| #define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT) |
| |
| #define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT) |
| #define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT) |
| |
| #define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT) |
| #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) |
| |
| #define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) |
| #define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) |
| |
| #define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT) |
| #define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT) |
| #define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT) |
| |
| #define file_is_verity(inode) is_file(inode, FADVISE_VERITY_BIT) |
| #define file_set_verity(inode) set_file(inode, FADVISE_VERITY_BIT) |
| |
| #define file_should_truncate(inode) is_file(inode, FADVISE_TRUNC_BIT) |
| #define file_need_truncate(inode) set_file(inode, FADVISE_TRUNC_BIT) |
| #define file_dont_truncate(inode) clear_file(inode, FADVISE_TRUNC_BIT) |
| |
| #define DEF_DIR_LEVEL 0 |
| |
| /* used for f2fs_inode_info->flags */ |
| enum { |
| FI_NEW_INODE, /* indicate newly allocated inode */ |
| FI_DIRTY_INODE, /* indicate inode is dirty or not */ |
| FI_AUTO_RECOVER, /* indicate inode is recoverable */ |
| FI_DIRTY_DIR, /* indicate directory has dirty pages */ |
| FI_INC_LINK, /* need to increment i_nlink */ |
| FI_ACL_MODE, /* indicate acl mode */ |
| FI_NO_ALLOC, /* should not allocate any blocks */ |
| FI_FREE_NID, /* free allocated nide */ |
| FI_NO_EXTENT, /* not to use the extent cache */ |
| FI_INLINE_XATTR, /* used for inline xattr */ |
| FI_INLINE_DATA, /* used for inline data*/ |
| FI_INLINE_DENTRY, /* used for inline dentry */ |
| FI_APPEND_WRITE, /* inode has appended data */ |
| FI_UPDATE_WRITE, /* inode has in-place-update data */ |
| FI_NEED_IPU, /* used for ipu per file */ |
| FI_ATOMIC_FILE, /* indicate atomic file */ |
| FI_DATA_EXIST, /* indicate data exists */ |
| FI_INLINE_DOTS, /* indicate inline dot dentries */ |
| FI_SKIP_WRITES, /* should skip data page writeback */ |
| FI_OPU_WRITE, /* used for opu per file */ |
| FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ |
| FI_PREALLOCATED_ALL, /* all blocks for write were preallocated */ |
| FI_HOT_DATA, /* indicate file is hot */ |
| FI_EXTRA_ATTR, /* indicate file has extra attribute */ |
| FI_PROJ_INHERIT, /* indicate file inherits projectid */ |
| FI_PIN_FILE, /* indicate file should not be gced */ |
| FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */ |
| FI_COMPRESSED_FILE, /* indicate file's data can be compressed */ |
| FI_COMPRESS_CORRUPT, /* indicate compressed cluster is corrupted */ |
| FI_MMAP_FILE, /* indicate file was mmapped */ |
| FI_ENABLE_COMPRESS, /* enable compression in "user" compression mode */ |
| FI_COMPRESS_RELEASED, /* compressed blocks were released */ |
| FI_ALIGNED_WRITE, /* enable aligned write */ |
| FI_COW_FILE, /* indicate COW file */ |
| FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */ |
| FI_ATOMIC_REPLACE, /* indicate atomic replace */ |
| FI_OPENED_FILE, /* indicate file has been opened */ |
| FI_MAX, /* max flag, never be used */ |
| }; |
| |
| struct f2fs_inode_info { |
| struct inode vfs_inode; /* serve a vfs inode */ |
| unsigned long i_flags; /* keep an inode flags for ioctl */ |
| unsigned char i_advise; /* use to give file attribute hints */ |
| unsigned char i_dir_level; /* use for dentry level for large dir */ |
| union { |
| unsigned int i_current_depth; /* only for directory depth */ |
| unsigned short i_gc_failures; /* for gc failure statistic */ |
| }; |
| unsigned int i_pino; /* parent inode number */ |
| umode_t i_acl_mode; /* keep file acl mode temporarily */ |
| |
| /* Use below internally in f2fs*/ |
| unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */ |
| struct f2fs_rwsem i_sem; /* protect fi info */ |
| atomic_t dirty_pages; /* # of dirty pages */ |
| f2fs_hash_t chash; /* hash value of given file name */ |
| unsigned int clevel; /* maximum level of given file name */ |
| struct task_struct *task; /* lookup and create consistency */ |
| struct task_struct *cp_task; /* separate cp/wb IO stats*/ |
| struct task_struct *wb_task; /* indicate inode is in context of writeback */ |
| nid_t i_xattr_nid; /* node id that contains xattrs */ |
| loff_t last_disk_size; /* lastly written file size */ |
| spinlock_t i_size_lock; /* protect last_disk_size */ |
| |
| #ifdef CONFIG_QUOTA |
| struct dquot __rcu *i_dquot[MAXQUOTAS]; |
| |
| /* quota space reservation, managed internally by quota code */ |
| qsize_t i_reserved_quota; |
| #endif |
| struct list_head dirty_list; /* dirty list for dirs and files */ |
| struct list_head gdirty_list; /* linked in global dirty list */ |
| struct task_struct *atomic_write_task; /* store atomic write task */ |
| struct extent_tree *extent_tree[NR_EXTENT_CACHES]; |
| /* cached extent_tree entry */ |
| union { |
| struct inode *cow_inode; /* copy-on-write inode for atomic write */ |
| struct inode *atomic_inode; |
| /* point to atomic_inode, available only for cow_inode */ |
| }; |
| |
| /* avoid racing between foreground op and gc */ |
| struct f2fs_rwsem i_gc_rwsem[2]; |
| struct f2fs_rwsem i_xattr_sem; /* avoid racing between reading and changing EAs */ |
| |
| int i_extra_isize; /* size of extra space located in i_addr */ |
| kprojid_t i_projid; /* id for project quota */ |
| int i_inline_xattr_size; /* inline xattr size */ |
| struct timespec64 i_crtime; /* inode creation time */ |
| struct timespec64 i_disk_time[3];/* inode disk times */ |
| |
| /* for file compress */ |
| atomic_t i_compr_blocks; /* # of compressed blocks */ |
| unsigned char i_compress_algorithm; /* algorithm type */ |
| unsigned char i_log_cluster_size; /* log of cluster size */ |
| unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ |
| unsigned char i_compress_flag; /* compress flag */ |
| unsigned int i_cluster_size; /* cluster size */ |
| |
| unsigned int atomic_write_cnt; |
| loff_t original_i_size; /* original i_size before atomic write */ |
| }; |
| |
| static inline void get_read_extent_info(struct extent_info *ext, |
| struct f2fs_extent *i_ext) |
| { |
| ext->fofs = le32_to_cpu(i_ext->fofs); |
| ext->blk = le32_to_cpu(i_ext->blk); |
| ext->len = le32_to_cpu(i_ext->len); |
| } |
| |
| static inline void set_raw_read_extent(struct extent_info *ext, |
| struct f2fs_extent *i_ext) |
| { |
| i_ext->fofs = cpu_to_le32(ext->fofs); |
| i_ext->blk = cpu_to_le32(ext->blk); |
| i_ext->len = cpu_to_le32(ext->len); |
| } |
| |
| static inline bool __is_discard_mergeable(struct discard_info *back, |
| struct discard_info *front, unsigned int max_len) |
| { |
| return (back->lstart + back->len == front->lstart) && |
| (back->len + front->len <= max_len); |
| } |
| |
| static inline bool __is_discard_back_mergeable(struct discard_info *cur, |
| struct discard_info *back, unsigned int max_len) |
| { |
| return __is_discard_mergeable(back, cur, max_len); |
| } |
| |
| static inline bool __is_discard_front_mergeable(struct discard_info *cur, |
| struct discard_info *front, unsigned int max_len) |
| { |
| return __is_discard_mergeable(cur, front, max_len); |
| } |
| |
| /* |
| * For free nid management |
| */ |
| enum nid_state { |
| FREE_NID, /* newly added to free nid list */ |
| PREALLOC_NID, /* it is preallocated */ |
| MAX_NID_STATE, |
| }; |
| |
| enum nat_state { |
| TOTAL_NAT, |
| DIRTY_NAT, |
| RECLAIMABLE_NAT, |
| MAX_NAT_STATE, |
| }; |
| |
| struct f2fs_nm_info { |
| block_t nat_blkaddr; /* base disk address of NAT */ |
| nid_t max_nid; /* maximum possible node ids */ |
| nid_t available_nids; /* # of available node ids */ |
| nid_t next_scan_nid; /* the next nid to be scanned */ |
| nid_t max_rf_node_blocks; /* max # of nodes for recovery */ |
| unsigned int ram_thresh; /* control the memory footprint */ |
| unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */ |
| unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */ |
| |
| /* NAT cache management */ |
| struct radix_tree_root nat_root;/* root of the nat entry cache */ |
| struct radix_tree_root nat_set_root;/* root of the nat set cache */ |
| struct f2fs_rwsem nat_tree_lock; /* protect nat entry tree */ |
| struct list_head nat_entries; /* cached nat entry list (clean) */ |
| spinlock_t nat_list_lock; /* protect clean nat entry list */ |
| unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */ |
| unsigned int nat_blocks; /* # of nat blocks */ |
| |
| /* free node ids management */ |
| struct radix_tree_root free_nid_root;/* root of the free_nid cache */ |
| struct list_head free_nid_list; /* list for free nids excluding preallocated nids */ |
| unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */ |
| spinlock_t nid_list_lock; /* protect nid lists ops */ |
| struct mutex build_lock; /* lock for build free nids */ |
| unsigned char **free_nid_bitmap; |
| unsigned char *nat_block_bitmap; |
| unsigned short *free_nid_count; /* free nid count of NAT block */ |
| |
| /* for checkpoint */ |
| char *nat_bitmap; /* NAT bitmap pointer */ |
| |
| unsigned int nat_bits_blocks; /* # of nat bits blocks */ |
| unsigned char *nat_bits; /* NAT bits blocks */ |
| unsigned char *full_nat_bits; /* full NAT pages */ |
| unsigned char *empty_nat_bits; /* empty NAT pages */ |
| #ifdef CONFIG_F2FS_CHECK_FS |
| char *nat_bitmap_mir; /* NAT bitmap mirror */ |
| #endif |
| int bitmap_size; /* bitmap size */ |
| }; |
| |
| /* |
| * this structure is used as one of function parameters. |
| * all the information are dedicated to a given direct node block determined |
| * by the data offset in a file. |
| */ |
| struct dnode_of_data { |
| struct inode *inode; /* vfs inode pointer */ |
| struct page *inode_page; /* its inode page, NULL is possible */ |
| struct page *node_page; /* cached direct node page */ |
| nid_t nid; /* node id of the direct node block */ |
| unsigned int ofs_in_node; /* data offset in the node page */ |
| bool inode_page_locked; /* inode page is locked or not */ |
| bool node_changed; /* is node block changed */ |
| char cur_level; /* level of hole node page */ |
| char max_level; /* level of current page located */ |
| block_t data_blkaddr; /* block address of the node block */ |
| }; |
| |
| static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode, |
| struct page *ipage, struct page *npage, nid_t nid) |
| { |
| memset(dn, 0, sizeof(*dn)); |
| dn->inode = inode; |
| dn->inode_page = ipage; |
| dn->node_page = npage; |
| dn->nid = nid; |
| } |
| |
| /* |
| * For SIT manager |
| * |
| * By default, there are 6 active log areas across the whole main area. |
| * When considering hot and cold data separation to reduce cleaning overhead, |
| * we split 3 for data logs and 3 for node logs as hot, warm, and cold types, |
| * respectively. |
| * In the current design, you should not change the numbers intentionally. |
| * Instead, as a mount option such as active_logs=x, you can use 2, 4, and 6 |
| * logs individually according to the underlying devices. (default: 6) |
| * Just in case, on-disk layout covers maximum 16 logs that consist of 8 for |
| * data and 8 for node logs. |
| */ |
| #define NR_CURSEG_DATA_TYPE (3) |
| #define NR_CURSEG_NODE_TYPE (3) |
| #define NR_CURSEG_INMEM_TYPE (2) |
| #define NR_CURSEG_RO_TYPE (2) |
| #define NR_CURSEG_PERSIST_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE) |
| #define NR_CURSEG_TYPE (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE) |
| |
| enum { |
| CURSEG_HOT_DATA = 0, /* directory entry blocks */ |
| CURSEG_WARM_DATA, /* data blocks */ |
| CURSEG_COLD_DATA, /* multimedia or GCed data blocks */ |
| CURSEG_HOT_NODE, /* direct node blocks of directory files */ |
| CURSEG_WARM_NODE, /* direct node blocks of normal files */ |
| CURSEG_COLD_NODE, /* indirect node blocks */ |
| NR_PERSISTENT_LOG, /* number of persistent log */ |
| CURSEG_COLD_DATA_PINNED = NR_PERSISTENT_LOG, |
| /* pinned file that needs consecutive block address */ |
| CURSEG_ALL_DATA_ATGC, /* SSR alloctor in hot/warm/cold data area */ |
| NO_CHECK_TYPE, /* number of persistent & inmem log */ |
| }; |
| |
| struct flush_cmd { |
| struct completion wait; |
| struct llist_node llnode; |
| nid_t ino; |
| int ret; |
| }; |
| |
| struct flush_cmd_control { |
| struct task_struct *f2fs_issue_flush; /* flush thread */ |
| wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ |
| atomic_t issued_flush; /* # of issued flushes */ |
| atomic_t queued_flush; /* # of queued flushes */ |
| struct llist_head issue_list; /* list for command issue */ |
| struct llist_node *dispatch_list; /* list for command dispatch */ |
| }; |
| |
| struct f2fs_sm_info { |
| struct sit_info *sit_info; /* whole segment information */ |
| struct free_segmap_info *free_info; /* free segment information */ |
| struct dirty_seglist_info *dirty_info; /* dirty segment information */ |
| struct curseg_info *curseg_array; /* active segment information */ |
| |
| struct f2fs_rwsem curseg_lock; /* for preventing curseg change */ |
| |
| block_t seg0_blkaddr; /* block address of 0'th segment */ |
| block_t main_blkaddr; /* start block address of main area */ |
| block_t ssa_blkaddr; /* start block address of SSA area */ |
| |
| unsigned int segment_count; /* total # of segments */ |
| unsigned int main_segments; /* # of segments in main area */ |
| unsigned int reserved_segments; /* # of reserved segments */ |
| unsigned int additional_reserved_segments;/* reserved segs for IO align feature */ |
| unsigned int ovp_segments; /* # of overprovision segments */ |
| |
| /* a threshold to reclaim prefree segments */ |
| unsigned int rec_prefree_segments; |
| |
| struct list_head sit_entry_set; /* sit entry set list */ |
| |
| unsigned int ipu_policy; /* in-place-update policy */ |
| unsigned int min_ipu_util; /* in-place-update threshold */ |
| unsigned int min_fsync_blocks; /* threshold for fsync */ |
| unsigned int min_seq_blocks; /* threshold for sequential blocks */ |
| unsigned int min_hot_blocks; /* threshold for hot block allocation */ |
| unsigned int min_ssr_sections; /* threshold to trigger SSR allocation */ |
| |
| /* for flush command control */ |
| struct flush_cmd_control *fcc_info; |
| |
| /* for discard command control */ |
| struct discard_cmd_control *dcc_info; |
| }; |
| |
| /* |
| * For superblock |
| */ |
| /* |
| * COUNT_TYPE for monitoring |
| * |
| * f2fs monitors the number of several block types such as on-writeback, |
| * dirty dentry blocks, dirty node blocks, and dirty meta blocks. |
| */ |
| #define WB_DATA_TYPE(p, f) \ |
| (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) |
| enum count_type { |
| F2FS_DIRTY_DENTS, |
| F2FS_DIRTY_DATA, |
| F2FS_DIRTY_QDATA, |
| F2FS_DIRTY_NODES, |
| F2FS_DIRTY_META, |
| F2FS_DIRTY_IMETA, |
| F2FS_WB_CP_DATA, |
| F2FS_WB_DATA, |
| F2FS_RD_DATA, |
| F2FS_RD_NODE, |
| F2FS_RD_META, |
| F2FS_DIO_WRITE, |
| F2FS_DIO_READ, |
| NR_COUNT_TYPE, |
| }; |
| |
| /* |
| * The below are the page types of bios used in submit_bio(). |
| * The available types are: |
| * DATA User data pages. It operates as async mode. |
| * NODE Node pages. It operates as async mode. |
| * META FS metadata pages such as SIT, NAT, CP. |
| * NR_PAGE_TYPE The number of page types. |
| * META_FLUSH Make sure the previous pages are written |
| * with waiting the bio's completion |
| * ... Only can be used with META. |
| */ |
| #define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type)) |
| #define PAGE_TYPE_ON_MAIN(type) ((type) == DATA || (type) == NODE) |
| enum page_type { |
| DATA = 0, |
| NODE = 1, /* should not change this */ |
| META, |
| NR_PAGE_TYPE, |
| META_FLUSH, |
| IPU, /* the below types are used by tracepoints only. */ |
| OPU, |
| }; |
| |
| enum temp_type { |
| HOT = 0, /* must be zero for meta bio */ |
| WARM, |
| COLD, |
| NR_TEMP_TYPE, |
| }; |
| |
| enum need_lock_type { |
| LOCK_REQ = 0, |
| LOCK_DONE, |
| LOCK_RETRY, |
| }; |
| |
| enum cp_reason_type { |
| CP_NO_NEEDED, |
| CP_NON_REGULAR, |
| CP_COMPRESSED, |
| CP_HARDLINK, |
| CP_SB_NEED_CP, |
| CP_WRONG_PINO, |
| CP_NO_SPC_ROLL, |
| CP_NODE_NEED_CP, |
| CP_FASTBOOT_MODE, |
| CP_SPEC_LOG_NUM, |
| CP_RECOVER_DIR, |
| }; |
| |
| enum iostat_type { |
| /* WRITE IO */ |
| APP_DIRECT_IO, /* app direct write IOs */ |
| APP_BUFFERED_IO, /* app buffered write IOs */ |
| APP_WRITE_IO, /* app write IOs */ |
| APP_MAPPED_IO, /* app mapped IOs */ |
| APP_BUFFERED_CDATA_IO, /* app buffered write IOs on compressed file */ |
| APP_MAPPED_CDATA_IO, /* app mapped write IOs on compressed file */ |
| FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */ |
| FS_CDATA_IO, /* data IOs from kworker/fsync/reclaimer on compressed file */ |
| FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */ |
| FS_META_IO, /* meta IOs from kworker/reclaimer */ |
| FS_GC_DATA_IO, /* data IOs from forground gc */ |
| FS_GC_NODE_IO, /* node IOs from forground gc */ |
| FS_CP_DATA_IO, /* data IOs from checkpoint */ |
| FS_CP_NODE_IO, /* node IOs from checkpoint */ |
| FS_CP_META_IO, /* meta IOs from checkpoint */ |
| |
| /* READ IO */ |
| APP_DIRECT_READ_IO, /* app direct read IOs */ |
| APP_BUFFERED_READ_IO, /* app buffered read IOs */ |
| APP_READ_IO, /* app read IOs */ |
| APP_MAPPED_READ_IO, /* app mapped read IOs */ |
| APP_BUFFERED_CDATA_READ_IO, /* app buffered read IOs on compressed file */ |
| APP_MAPPED_CDATA_READ_IO, /* app mapped read IOs on compressed file */ |
| FS_DATA_READ_IO, /* data read IOs */ |
| FS_GDATA_READ_IO, /* data read IOs from background gc */ |
| FS_CDATA_READ_IO, /* compressed data read IOs */ |
| FS_NODE_READ_IO, /* node read IOs */ |
| FS_META_READ_IO, /* meta read IOs */ |
| |
| /* other */ |
| FS_DISCARD_IO, /* discard */ |
| FS_FLUSH_IO, /* flush */ |
| FS_ZONE_RESET_IO, /* zone reset */ |
| NR_IO_TYPE, |
| }; |
| |
| struct f2fs_io_info { |
| struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ |
| nid_t ino; /* inode number */ |
| enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ |
| enum temp_type temp; /* contains HOT/WARM/COLD */ |
| enum req_op op; /* contains REQ_OP_ */ |
| blk_opf_t op_flags; /* req_flag_bits */ |
| block_t new_blkaddr; /* new block address to be written */ |
| block_t old_blkaddr; /* old block address before Cow */ |
| struct page *page; /* page to be written */ |
| struct page *encrypted_page; /* encrypted page */ |
| struct page *compressed_page; /* compressed page */ |
| struct list_head list; /* serialize IOs */ |
| unsigned int compr_blocks; /* # of compressed block addresses */ |
| unsigned int need_lock:8; /* indicate we need to lock cp_rwsem */ |
| unsigned int version:8; /* version of the node */ |
| unsigned int submitted:1; /* indicate IO submission */ |
| unsigned int in_list:1; /* indicate fio is in io_list */ |
| unsigned int is_por:1; /* indicate IO is from recovery or not */ |
| unsigned int encrypted:1; /* indicate file is encrypted */ |
| unsigned int meta_gc:1; /* require meta inode GC */ |
| enum iostat_type io_type; /* io type */ |
| struct writeback_control *io_wbc; /* writeback control */ |
| struct bio **bio; /* bio for ipu */ |
| sector_t *last_block; /* last block number in bio */ |
| }; |
| |
| struct bio_entry { |
| struct bio *bio; |
| struct list_head list; |
| }; |
| |
| #define is_read_io(rw) ((rw) == READ) |
| struct f2fs_bio_info { |
| struct f2fs_sb_info *sbi; /* f2fs superblock */ |
| struct bio *bio; /* bios to merge */ |
| sector_t last_block_in_bio; /* last block number */ |
| struct f2fs_io_info fio; /* store buffered io info. */ |
| #ifdef CONFIG_BLK_DEV_ZONED |
| struct completion zone_wait; /* condition value for the previous open zone to close */ |
| struct bio *zone_pending_bio; /* pending bio for the previous zone */ |
| void *bi_private; /* previous bi_private for pending bio */ |
| #endif |
| struct f2fs_rwsem io_rwsem; /* blocking op for bio */ |
| spinlock_t io_lock; /* serialize DATA/NODE IOs */ |
| struct list_head io_list; /* track fios */ |
| struct list_head bio_list; /* bio entry list head */ |
| struct f2fs_rwsem bio_list_lock; /* lock to protect bio entry list */ |
| }; |
| |
| #define FDEV(i) (sbi->devs[i]) |
| #define RDEV(i) (raw_super->devs[i]) |
| struct f2fs_dev_info { |
| struct file *bdev_file; |
| struct block_device *bdev; |
| char path[MAX_PATH_LEN]; |
| unsigned int total_segments; |
| block_t start_blk; |
| block_t end_blk; |
| #ifdef CONFIG_BLK_DEV_ZONED |
| unsigned int nr_blkz; /* Total number of zones */ |
| unsigned long *blkz_seq; /* Bitmap indicating sequential zones */ |
| #endif |
| }; |
| |
| enum inode_type { |
| DIR_INODE, /* for dirty dir inode */ |
| FILE_INODE, /* for dirty regular/symlink inode */ |
| DIRTY_META, /* for all dirtied inode metadata */ |
| NR_INODE_TYPE, |
| }; |
| |
| /* for inner inode cache management */ |
| struct inode_management { |
| struct radix_tree_root ino_root; /* ino entry array */ |
| spinlock_t ino_lock; /* for ino entry lock */ |
| struct list_head ino_list; /* inode list head */ |
| unsigned long ino_num; /* number of entries */ |
| }; |
| |
| /* for GC_AT */ |
| struct atgc_management { |
| bool atgc_enabled; /* ATGC is enabled or not */ |
| struct rb_root_cached root; /* root of victim rb-tree */ |
| struct list_head victim_list; /* linked with all victim entries */ |
| unsigned int victim_count; /* victim count in rb-tree */ |
| unsigned int candidate_ratio; /* candidate ratio */ |
| unsigned int max_candidate_count; /* max candidate count */ |
| unsigned int age_weight; /* age weight, vblock_weight = 100 - age_weight */ |
| unsigned long long age_threshold; /* age threshold */ |
| }; |
| |
| struct f2fs_gc_control { |
| unsigned int victim_segno; /* target victim segment number */ |
| int init_gc_type; /* FG_GC or BG_GC */ |
| bool no_bg_gc; /* check the space and stop bg_gc */ |
| bool should_migrate_blocks; /* should migrate blocks */ |
| bool err_gc_skipped; /* return EAGAIN if GC skipped */ |
| unsigned int nr_free_secs; /* # of free sections to do GC */ |
| }; |
| |
| /* |
| * For s_flag in struct f2fs_sb_info |
| * Modification on enum should be synchronized with s_flag array |
| */ |
| enum { |
| SBI_IS_DIRTY, /* dirty flag for checkpoint */ |
| SBI_IS_CLOSE, /* specify unmounting */ |
| SBI_NEED_FSCK, /* need fsck.f2fs to fix */ |
| SBI_POR_DOING, /* recovery is doing or not */ |
| SBI_NEED_SB_WRITE, /* need to recover superblock */ |
| SBI_NEED_CP, /* need to checkpoint */ |
| SBI_IS_SHUTDOWN, /* shutdown by ioctl */ |
| SBI_IS_RECOVERED, /* recovered orphan/data */ |
| SBI_CP_DISABLED, /* CP was disabled last mount */ |
| SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ |
| SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ |
| SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ |
| SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ |
| SBI_IS_RESIZEFS, /* resizefs is in process */ |
| SBI_IS_FREEZING, /* freezefs is in process */ |
| SBI_IS_WRITABLE, /* remove ro mountoption transiently */ |
| MAX_SBI_FLAG, |
| }; |
| |
| enum { |
| CP_TIME, |
| REQ_TIME, |
| DISCARD_TIME, |
| GC_TIME, |
| DISABLE_TIME, |
| UMOUNT_DISCARD_TIMEOUT, |
| MAX_TIME, |
| }; |
| |
| /* Note that you need to keep synchronization with this gc_mode_names array */ |
| enum { |
| GC_NORMAL, |
| GC_IDLE_CB, |
| GC_IDLE_GREEDY, |
| GC_IDLE_AT, |
| GC_URGENT_HIGH, |
| GC_URGENT_LOW, |
| GC_URGENT_MID, |
| MAX_GC_MODE, |
| }; |
| |
| enum { |
| BGGC_MODE_ON, /* background gc is on */ |
| BGGC_MODE_OFF, /* background gc is off */ |
| BGGC_MODE_SYNC, /* |
| * background gc is on, migrating blocks |
| * like foreground gc |
| */ |
| }; |
| |
| enum { |
| FS_MODE_ADAPTIVE, /* use both lfs/ssr allocation */ |
| FS_MODE_LFS, /* use lfs allocation only */ |
| FS_MODE_FRAGMENT_SEG, /* segment fragmentation mode */ |
| FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */ |
| }; |
| |
| enum { |
| ALLOC_MODE_DEFAULT, /* stay default */ |
| ALLOC_MODE_REUSE, /* reuse segments as much as possible */ |
| }; |
| |
| enum fsync_mode { |
| FSYNC_MODE_POSIX, /* fsync follows posix semantics */ |
| FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ |
| FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ |
| }; |
| |
| enum { |
| COMPR_MODE_FS, /* |
| * automatically compress compression |
| * enabled files |
| */ |
| COMPR_MODE_USER, /* |
| * automatical compression is disabled. |
| * user can control the file compression |
| * using ioctls |
| */ |
| }; |
| |
| enum { |
| DISCARD_UNIT_BLOCK, /* basic discard unit is block */ |
| DISCARD_UNIT_SEGMENT, /* basic discard unit is segment */ |
| DISCARD_UNIT_SECTION, /* basic discard unit is section */ |
| }; |
| |
| enum { |
| MEMORY_MODE_NORMAL, /* memory mode for normal devices */ |
| MEMORY_MODE_LOW, /* memory mode for low memry devices */ |
| }; |
| |
| enum errors_option { |
| MOUNT_ERRORS_READONLY, /* remount fs ro on errors */ |
| MOUNT_ERRORS_CONTINUE, /* continue on errors */ |
| MOUNT_ERRORS_PANIC, /* panic on errors */ |
| }; |
| |
| enum { |
| BACKGROUND, |
| FOREGROUND, |
| MAX_CALL_TYPE, |
| TOTAL_CALL = FOREGROUND, |
| }; |
| |
| static inline int f2fs_test_bit(unsigned int nr, char *addr); |
| static inline void f2fs_set_bit(unsigned int nr, char *addr); |
| static inline void f2fs_clear_bit(unsigned int nr, char *addr); |
| |
| /* |
| * Layout of f2fs page.private: |
| * |
| * Layout A: lowest bit should be 1 |
| * | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... | |
| * bit 0 PAGE_PRIVATE_NOT_POINTER |
| * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION |
| * bit 2 PAGE_PRIVATE_INLINE_INODE |
| * bit 3 PAGE_PRIVATE_REF_RESOURCE |
| * bit 4- f2fs private data |
| * |
| * Layout B: lowest bit should be 0 |
| * page.private is a wrapped pointer. |
| */ |
| enum { |
| PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */ |
| PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */ |
| PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */ |
| PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */ |
| PAGE_PRIVATE_MAX |
| }; |
| |
| /* For compression */ |
| enum compress_algorithm_type { |
| COMPRESS_LZO, |
| COMPRESS_LZ4, |
| COMPRESS_ZSTD, |
| COMPRESS_LZORLE, |
| COMPRESS_MAX, |
| }; |
| |
| enum compress_flag { |
| COMPRESS_CHKSUM, |
| COMPRESS_MAX_FLAG, |
| }; |
| |
| #define COMPRESS_WATERMARK 20 |
| #define COMPRESS_PERCENT 20 |
| |
| #define COMPRESS_DATA_RESERVED_SIZE 4 |
| struct compress_data { |
| __le32 clen; /* compressed data size */ |
| __le32 chksum; /* compressed data chksum */ |
| __le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */ |
| u8 cdata[]; /* compressed data */ |
| }; |
| |
| #define COMPRESS_HEADER_SIZE (sizeof(struct compress_data)) |
| |
| #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 |
| |
| #define F2FS_ZSTD_DEFAULT_CLEVEL 1 |
| |
| #define COMPRESS_LEVEL_OFFSET 8 |
| |
| /* compress context */ |
| struct compress_ctx { |
| struct inode *inode; /* inode the context belong to */ |
| pgoff_t cluster_idx; /* cluster index number */ |
| unsigned int cluster_size; /* page count in cluster */ |
| unsigned int log_cluster_size; /* log of cluster size */ |
| struct page **rpages; /* pages store raw data in cluster */ |
| unsigned int nr_rpages; /* total page number in rpages */ |
| struct page **cpages; /* pages store compressed data in cluster */ |
| unsigned int nr_cpages; /* total page number in cpages */ |
| unsigned int valid_nr_cpages; /* valid page number in cpages */ |
| void *rbuf; /* virtual mapped address on rpages */ |
| struct compress_data *cbuf; /* virtual mapped address on cpages */ |
| size_t rlen; /* valid data length in rbuf */ |
| size_t clen; /* valid data length in cbuf */ |
| void *private; /* payload buffer for specified compression algorithm */ |
| void *private2; /* extra payload buffer */ |
| }; |
| |
| /* compress context for write IO path */ |
| struct compress_io_ctx { |
| u32 magic; /* magic number to indicate page is compressed */ |
| struct inode *inode; /* inode the context belong to */ |
| struct page **rpages; /* pages store raw data in cluster */ |
| unsigned int nr_rpages; /* total page number in rpages */ |
| atomic_t pending_pages; /* in-flight compressed page count */ |
| }; |
| |
| /* Context for decompressing one cluster on the read IO path */ |
| struct decompress_io_ctx { |
| u32 magic; /* magic number to indicate page is compressed */ |
| struct inode *inode; /* inode the context belong to */ |
| pgoff_t cluster_idx; /* cluster index number */ |
| unsigned int cluster_size; /* page count in cluster */ |
| unsigned int log_cluster_size; /* log of cluster size */ |
| struct page **rpages; /* pages store raw data in cluster */ |
| unsigned int nr_rpages; /* total page number in rpages */ |
| struct page **cpages; /* pages store compressed data in cluster */ |
| unsigned int nr_cpages; /* total page number in cpages */ |
| struct page **tpages; /* temp pages to pad holes in cluster */ |
| void *rbuf; /* virtual mapped address on rpages */ |
| struct compress_data *cbuf; /* virtual mapped address on cpages */ |
| size_t rlen; /* valid data length in rbuf */ |
| size_t clen; /* valid data length in cbuf */ |
| |
| /* |
| * The number of compressed pages remaining to be read in this cluster. |
| * This is initially nr_cpages. It is decremented by 1 each time a page |
| * has been read (or failed to be read). When it reaches 0, the cluster |
| * is decompressed (or an error is reported). |
| * |
| * If an error occurs before all the pages have been submitted for I/O, |
| * then this will never reach 0. In this case the I/O submitter is |
| * responsible for calling f2fs_decompress_end_io() instead. |
| */ |
| atomic_t remaining_pages; |
| |
| /* |
| * Number of references to this decompress_io_ctx. |
| * |
| * One reference is held for I/O completion. This reference is dropped |
| * after the pagecache pages are updated and unlocked -- either after |
| * decompression (and verity if enabled), or after an error. |
| * |
| * In addition, each compressed page holds a reference while it is in a |
| * bio. These references are necessary prevent compressed pages from |
| * being freed while they are still in a bio. |
| */ |
| refcount_t refcnt; |
| |
| bool failed; /* IO error occurred before decompression? */ |
| bool need_verity; /* need fs-verity verification after decompression? */ |
| void *private; /* payload buffer for specified decompression algorithm */ |
| void *private2; /* extra payload buffer */ |
| struct work_struct verity_work; /* work to verify the decompressed pages */ |
| struct work_struct free_work; /* work for late free this structure itself */ |
| }; |
| |
| #define NULL_CLUSTER ((unsigned int)(~0)) |
| #define MIN_COMPRESS_LOG_SIZE 2 |
| #define MAX_COMPRESS_LOG_SIZE 8 |
| #define MAX_COMPRESS_WINDOW_SIZE(log_size) ((PAGE_SIZE) << (log_size)) |
| |
| struct f2fs_sb_info { |
| struct super_block *sb; /* pointer to VFS super block */ |
| struct proc_dir_entry *s_proc; /* proc entry */ |
| struct f2fs_super_block *raw_super; /* raw super block pointer */ |
| struct f2fs_rwsem sb_lock; /* lock for raw super block */ |
| int valid_super_block; /* valid super block no */ |
| unsigned long s_flag; /* flags for sbi */ |
| struct mutex writepages; /* mutex for writepages() */ |
| |
| #ifdef CONFIG_BLK_DEV_ZONED |
| unsigned int blocks_per_blkz; /* F2FS blocks per zone */ |
| unsigned int max_open_zones; /* max open zone resources of the zoned device */ |
| #endif |
| |
| /* for node-related operations */ |
| struct f2fs_nm_info *nm_info; /* node manager */ |
| struct inode *node_inode; /* cache node blocks */ |
| |
| /* for segment-related operations */ |
| struct f2fs_sm_info *sm_info; /* segment manager */ |
| |
| /* for bio operations */ |
| struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ |
| /* keep migration IO order for LFS mode */ |
| struct f2fs_rwsem io_order_lock; |
| pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */ |
| int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */ |
| |
| /* for checkpoint */ |
| struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ |
| int cur_cp_pack; /* remain current cp pack */ |
| spinlock_t cp_lock; /* for flag in ckpt */ |
| struct inode *meta_inode; /* cache meta blocks */ |
| struct f2fs_rwsem cp_global_sem; /* checkpoint procedure lock */ |
| struct f2fs_rwsem cp_rwsem; /* blocking FS operations */ |
| struct f2fs_rwsem node_write; /* locking node writes */ |
| struct f2fs_rwsem node_change; /* locking node change */ |
| wait_queue_head_t cp_wait; |
| unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ |
| long interval_time[MAX_TIME]; /* to store thresholds */ |
| struct ckpt_req_control cprc_info; /* for checkpoint request control */ |
| |
| struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ |
| |
| spinlock_t fsync_node_lock; /* for node entry lock */ |
| struct list_head fsync_node_list; /* node list head */ |
| unsigned int fsync_seg_id; /* sequence id */ |
| unsigned int fsync_node_num; /* number of node entries */ |
| |
| /* for orphan inode, use 0'th array */ |
| unsigned int max_orphans; /* max orphan inodes */ |
| |
| /* for inode management */ |
| struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */ |
| spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */ |
| struct mutex flush_lock; /* for flush exclusion */ |
| |
| /* for extent tree cache */ |
| struct extent_tree_info extent_tree[NR_EXTENT_CACHES]; |
| atomic64_t allocated_data_blocks; /* for block age extent_cache */ |
| |
| /* The threshold used for hot and warm data seperation*/ |
| unsigned int hot_data_age_threshold; |
| unsigned int warm_data_age_threshold; |
| unsigned int last_age_weight; |
| |
| /* basic filesystem units */ |
| unsigned int log_sectors_per_block; /* log2 sectors per block */ |
| unsigned int log_blocksize; /* log2 block size */ |
| unsigned int blocksize; /* block size */ |
| unsigned int root_ino_num; /* root inode number*/ |
| unsigned int node_ino_num; /* node inode number*/ |
| unsigned int meta_ino_num; /* meta inode number*/ |
| unsigned int log_blocks_per_seg; /* log2 blocks per segment */ |
| unsigned int blocks_per_seg; /* blocks per segment */ |
| unsigned int unusable_blocks_per_sec; /* unusable blocks per section */ |
| unsigned int segs_per_sec; /* segments per section */ |
| unsigned int secs_per_zone; /* sections per zone */ |
| unsigned int total_sections; /* total section count */ |
| unsigned int total_node_count; /* total node block count */ |
| unsigned int total_valid_node_count; /* valid node block count */ |
| int dir_level; /* directory level */ |
| bool readdir_ra; /* readahead inode in readdir */ |
| u64 max_io_bytes; /* max io bytes to merge IOs */ |
| |
| block_t user_block_count; /* # of user blocks */ |
| block_t total_valid_block_count; /* # of valid blocks */ |
| block_t discard_blks; /* discard command candidats */ |
| block_t last_valid_block_count; /* for recovery */ |
| block_t reserved_blocks; /* configurable reserved blocks */ |
| block_t current_reserved_blocks; /* current reserved blocks */ |
| |
| /* Additional tracking for no checkpoint mode */ |
| block_t unusable_block_count; /* # of blocks saved by last cp */ |
| |
| unsigned int nquota_files; /* # of quota sysfile */ |
| struct f2fs_rwsem quota_sem; /* blocking cp for flags */ |
| |
| /* # of pages, see count_type */ |
| atomic_t nr_pages[NR_COUNT_TYPE]; |
| /* # of allocated blocks */ |
| struct percpu_counter alloc_valid_block_count; |
| /* # of node block writes as roll forward recovery */ |
| struct percpu_counter rf_node_block_count; |
| |
| /* writeback control */ |
| atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ |
| |
| /* valid inode count */ |
| struct percpu_counter total_valid_inode_count; |
| |
| struct f2fs_mount_info mount_opt; /* mount options */ |
| |
| /* for cleaning operations */ |
| struct f2fs_rwsem gc_lock; /* |
| * semaphore for GC, avoid |
| * race between GC and GC or CP |
| */ |
| struct f2fs_gc_kthread *gc_thread; /* GC thread */ |
| struct atgc_management am; /* atgc management */ |
| unsigned int cur_victim_sec; /* current victim section num */ |
| unsigned int gc_mode; /* current GC state */ |
| unsigned int next_victim_seg[2]; /* next segment in victim section */ |
| spinlock_t gc_remaining_trials_lock; |
| /* remaining trial count for GC_URGENT_* and GC_IDLE_* */ |
| unsigned int gc_remaining_trials; |
| |
| /* for skip statistic */ |
| unsigned long long skipped_gc_rwsem; /* FG_GC only */ |
| |
| /* threshold for gc trials on pinned files */ |
| unsigned short gc_pin_file_threshold; |
| struct f2fs_rwsem pin_sem; |
| |
| /* maximum # of trials to find a victim segment for SSR and GC */ |
| unsigned int max_victim_search; |
| /* migration granularity of garbage collection, unit: segment */ |
| unsigned int migration_granularity; |
| |
| /* |
| * for stat information. |
| * one is for the LFS mode, and the other is for the SSR mode. |
| */ |
| #ifdef CONFIG_F2FS_STAT_FS |
| struct f2fs_stat_info *stat_info; /* FS status information */ |
| atomic_t meta_count[META_MAX]; /* # of meta blocks */ |
| unsigned int segment_count[2]; /* # of allocated segments */ |
| unsigned int block_count[2]; /* # of allocated blocks */ |
| atomic_t inplace_count; /* # of inplace update */ |
| /* # of lookup extent cache */ |
| atomic64_t total_hit_ext[NR_EXTENT_CACHES]; |
| /* # of hit rbtree extent node */ |
| atomic64_t read_hit_rbtree[NR_EXTENT_CACHES]; |
| /* # of hit cached extent node */ |
| atomic64_t read_hit_cached[NR_EXTENT_CACHES]; |
| /* # of hit largest extent node in read extent cache */ |
| atomic64_t read_hit_largest; |
| atomic_t inline_xattr; /* # of inline_xattr inodes */ |
| atomic_t inline_inode; /* # of inline_data inodes */ |
| atomic_t inline_dir; /* # of inline_dentry inodes */ |
| atomic_t compr_inode; /* # of compressed inodes */ |
| atomic64_t compr_blocks; /* # of compressed blocks */ |
| atomic_t swapfile_inode; /* # of swapfile inodes */ |
| atomic_t atomic_files; /* # of opened atomic file */ |
| atomic_t max_aw_cnt; /* max # of atomic writes */ |
| unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ |
| unsigned int other_skip_bggc; /* skip background gc for other reasons */ |
| unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ |
| atomic_t cp_call_count[MAX_CALL_TYPE]; /* # of cp call */ |
| #endif |
| spinlock_t stat_lock; /* lock for stat operations */ |
| |
| /* to attach REQ_META|REQ_FUA flags */ |
| unsigned int data_io_flag; |
| unsigned int node_io_flag; |
| |
| /* For sysfs support */ |
| struct kobject s_kobj; /* /sys/fs/f2fs/<devname> */ |
| struct completion s_kobj_unregister; |
| |
| struct kobject s_stat_kobj; /* /sys/fs/f2fs/<devname>/stat */ |
| struct completion s_stat_kobj_unregister; |
| |
| struct kobject s_feature_list_kobj; /* /sys/fs/f2fs/<devname>/feature_list */ |
| struct completion s_feature_list_kobj_unregister; |
| |
| /* For shrinker support */ |
| struct list_head s_list; |
| struct mutex umount_mutex; |
| unsigned int shrinker_run_no; |
| |
| /* For multi devices */ |
| int s_ndevs; /* number of devices */ |
| struct f2fs_dev_info *devs; /* for device list */ |
| unsigned int dirty_device; /* for checkpoint data flush */ |
| spinlock_t dev_lock; /* protect dirty_device */ |
| bool aligned_blksize; /* all devices has the same logical blksize */ |
| |
| /* For write statistics */ |
| u64 sectors_written_start; |
| u64 kbytes_written; |
| |
| /* Reference to checksum algorithm driver via cryptoapi */ |
| struct crypto_shash *s_chksum_driver; |
| |
| /* Precomputed FS UUID checksum for seeding other checksums */ |
| __u32 s_chksum_seed; |
| |
| struct workqueue_struct *post_read_wq; /* post read workqueue */ |
| |
| /* |
| * If we are in irq context, let's update error information into |
| * on-disk superblock in the work. |
| */ |
| struct work_struct s_error_work; |
| unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */ |
| unsigned char stop_reason[MAX_STOP_REASON]; /* stop reason */ |
| spinlock_t error_lock; /* protect errors/stop_reason array */ |
| bool error_dirty; /* errors of sb is dirty */ |
| |
| struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ |
| unsigned int inline_xattr_slab_size; /* default inline xattr slab size */ |
| |
| /* For reclaimed segs statistics per each GC mode */ |
| unsigned int gc_segment_mode; /* GC state for reclaimed segments */ |
| unsigned int gc_reclaimed_segs[MAX_GC_MODE]; /* Reclaimed segs for each mode */ |
| |
| unsigned long seq_file_ra_mul; /* multiplier for ra_pages of seq. files in fadvise */ |
| |
| int max_fragment_chunk; /* max chunk size for block fragmentation mode */ |
| int max_fragment_hole; /* max hole size for block fragmentation mode */ |
| |
| /* For atomic write statistics */ |
| atomic64_t current_atomic_write; |
| s64 peak_atomic_write; |
| u64 committed_atomic_block; |
| u64 revoked_atomic_block; |
| |
| #ifdef CONFIG_F2FS_FS_COMPRESSION |
| struct kmem_cache *page_array_slab; /* page array entry */ |
| unsigned int page_array_slab_size; /* default page array slab size */ |
| |
| /* For runtime compression statistics */ |
| u64 compr_written_block; |
| u64 compr_saved_block; |
| u32 compr_new_inode; |
| |
| /* For compressed block cache */ |
| struct inode *compress_inode; /* cache compressed blocks */ |
| unsigned int compress_percent; /* cache page percentage */ |
| unsigned int compress_watermark; /* cache page watermark */ |
| atomic_t compress_page_hit; /* cache hit count */ |
| #endif |
| |
| #ifdef CONFIG_F2FS_IOSTAT |
| /* For app/fs IO statistics */ |
| spinlock_t iostat_lock; |
| unsigned long long iostat_count[NR_IO_TYPE]; |
| unsigned long long iostat_bytes[NR_IO_TYPE]; |
| unsigned long long prev_iostat_bytes[NR_IO_TYPE]; |
| bool iostat_enable; |
| unsigned long iostat_next_period; |
| unsigned int iostat_period_ms; |
| |
| /* For io latency related statistics info in one iostat period */ |
| spinlock_t iostat_lat_lock; |
| struct iostat_lat_info *iostat_io_lat; |
| #endif |
| }; |
| |
| /* Definitions to access f2fs_sb_info */ |
| #define SEGS_TO_BLKS(sbi, segs) \ |
| ((segs) << (sbi)->log_blocks_per_seg) |
| #define BLKS_TO_SEGS(sbi, blks) \ |
| ((blks) >> (sbi)->log_blocks_per_seg) |
| |
| #define BLKS_PER_SEG(sbi) ((sbi)->blocks_per_seg) |
| #define BLKS_PER_SEC(sbi) (SEGS_TO_BLKS(sbi, (sbi)->segs_per_sec)) |
| #define SEGS_PER_SEC(sbi) ((sbi)->segs_per_sec) |
| |
| __printf(3, 4) |
| void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...); |
| |
| #define f2fs_err(sbi, fmt, ...) \ |
| f2fs_printk(sbi, false, KERN_ERR fmt, ##__VA_ARGS__) |
| #define f2fs_warn(sbi, fmt, ...) \ |
| f2fs_printk(sbi, false, KERN_WARNING fmt, ##__VA_ARGS__) |
| #define f2fs_notice(sbi, fmt, ...) \ |
| f2fs_printk(sbi, false, KERN_NOTICE fmt, ##__VA_ARGS__) |
| #define f2fs_info(sbi, fmt, ...) \ |
| f2fs_printk(sbi, false, KERN_INFO fmt, ##__VA_ARGS__) |
| #define f2fs_debug(sbi, fmt, ...) \ |
| f2fs_printk(sbi, false, KERN_DEBUG fmt, ##__VA_ARGS__) |
| |
| #define f2fs_err_ratelimited(sbi, fmt, ...) \ |
| f2fs_printk(sbi, true, KERN_ERR fmt, ##__VA_ARGS__) |
| #define f2fs_warn_ratelimited(sbi, fmt, ...) \ |
| f2fs_printk(sbi, true, KERN_WARNING fmt, ##__VA_ARGS__) |
| #define f2fs_info_ratelimited(sbi, fmt, ...) \ |
| f2fs_printk(sbi, true, KERN_INFO fmt, ##__VA_ARGS__) |
| |
| #ifdef CONFIG_F2FS_FAULT_INJECTION |
| #define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__, \ |
| __builtin_return_address(0)) |
| static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type, |
| const char *func, const char *parent_func) |
| { |
| struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; |
| |
| if (!ffi->inject_rate) |
| return false; |
| |
| if (!IS_FAULT_SET(ffi, type)) |
| return false; |
| |
| atomic_inc(&ffi->inject_ops); |
| if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) { |
| atomic_set(&ffi->inject_ops, 0); |
| f2fs_info_ratelimited(sbi, "inject %s in %s of %pS", |
| f2fs_fault_name[type], func, parent_func); |
| return true; |
| } |
| return false; |
| } |
| #else |
| static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) |
| { |
| return false; |
| } |
| #endif |
| |
| /* |
| * Test if the mounted volume is a multi-device volume. |
| * - For a single regular disk volume, sbi->s_ndevs is 0. |
| * - For a single zoned disk volume, sbi->s_ndevs is 1. |
| * - For a multi-device volume, sbi->s_ndevs is always 2 or more. |
| */ |
| static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) |
| { |
| return sbi->s_ndevs > 1; |
| } |
| |
| static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) |
| { |
| unsigned long now = jiffies; |
| |
| sbi->last_time[type] = now; |
| |
| /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ |
| if (type == REQ_TIME) { |
| sbi->last_time[DISCARD_TIME] = now; |
| sbi->last_time[GC_TIME] = now; |
| } |
| } |
| |
| static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) |
| { |
| unsigned long interval = sbi->interval_time[type] * HZ; |
| |
| return time_after(jiffies, sbi->last_time[type] + interval); |
| } |
| |
| static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, |
| int type) |
| { |
| unsigned long interval = sbi->interval_time[type] * HZ; |
| unsigned int wait_ms = 0; |
| long delta; |
| |
| delta = (sbi->last_time[type] + interval) - jiffies; |
| if (delta > 0) |
| wait_ms = jiffies_to_msecs(delta); |
| |
| return wait_ms; |
| } |
| |
| /* |
| * Inline functions |
| */ |
| static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, |
| const void *address, unsigned int length) |
| { |
| struct { |
| struct shash_desc shash; |
| char ctx[4]; |
| } desc; |
| int err; |
| |
| BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); |
| |
| desc.shash.tfm = sbi->s_chksum_driver; |
| *(u32 *)desc.ctx = crc; |
| |
| err = crypto_shash_update(&desc.shash, address, length); |
| BUG_ON(err); |
| |
| return *(u32 *)desc.ctx; |
| } |
| |
| static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, |
| unsigned int length) |
| { |
| return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length); |
| } |
| |
| static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, |
| void *buf, size_t buf_size) |
| { |
| return f2fs_crc32(sbi, buf, buf_size) == blk_crc; |
| } |
| |
| static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, |
| const void *address, unsigned int length) |
| { |
| return __f2fs_crc32(sbi, crc, address, length); |
| } |
| |
| static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) |
| { |
| return container_of(inode, struct f2fs_inode_info, vfs_inode); |
| } |
| |
| static inline struct f2fs_sb_info *F2FS_SB(struct super_block *sb) |
| { |
| return sb->s_fs_info; |
| } |
| |
| static inline struct f2fs_sb_info *F2FS_I_SB(struct inode *inode) |
| { |
| return F2FS_SB(inode->i_sb); |
| } |
| |
| static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping) |
| { |
| return F2FS_I_SB(mapping->host); |
| } |
| |
| static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page) |
| { |
| return F2FS_M_SB(page_file_mapping(page)); |
| } |
| |
| static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi) |
| { |
| return (struct f2fs_super_block *)(sbi->raw_super); |
| } |
| |
| static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi) |
| { |
| return (struct f2fs_checkpoint *)(sbi->ckpt); |
| } |
| |
| static inline struct f2fs_node *F2FS_NODE(struct page *page) |
| { |
| return (struct f2fs_node *)page_address(page); |
| } |
| |
| static inline struct f2fs_inode *F2FS_INODE(struct page *page) |
| { |
| return &((struct f2fs_node *)page_address(page))->i; |
| } |
| |
| static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi) |
| { |
| return (struct f2fs_nm_info *)(sbi->nm_info); |
| } |
| |
| static inline struct f2fs_sm_info *SM_I(struct f2fs_sb_info *sbi) |
| { |
| return (struct f2fs_sm_info *)(sbi->sm_info); |
| } |
| |
| static inline struct sit_info *SIT_I(struct f2fs_sb_info *sbi) |
| { |
| return (struct sit_info *)(SM_I(sbi)->sit_info); |
| } |
| |
| static inline struct free_segmap_info *FREE_I(struct f2fs_sb_info *sbi) |
| { |
| return (struct free_segmap_info *)(SM_I(sbi)->free_info); |
| } |
| |
| static inline struct dirty_seglist_info *DIRTY_I(struct f2fs_sb_info *sbi) |
| { |
| return (struct dirty_seglist_info *)(SM_I(sbi)->dirty_info); |
| } |
| |
| static inline struct address_space *META_MAPPING(struct f2fs_sb_info *sbi) |
| { |
| return sbi->meta_inode->i_mapping; |
| } |
| |
| static inline struct address_space *NODE_MAPPING(struct f2fs_sb_info *sbi) |
| { |
| return sbi->node_inode->i_mapping; |
| } |
| |
| static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type) |
| { |
| return test_bit(type, &sbi->s_flag); |
| } |
| |
| static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) |
| { |
| set_bit(type, &sbi->s_flag); |
| } |
| |
| static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type) |
| { |
| clear_bit(type, &sbi->s_flag); |
| } |
| |
| static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) |
| { |
| return le64_to_cpu(cp->checkpoint_ver); |
| } |
| |
| static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type) |
| { |
| if (type < F2FS_MAX_QUOTAS) |
| return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]); |
| return 0; |
| } |
| |
| static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp) |
| { |
| size_t crc_offset = le32_to_cpu(cp->checksum_offset); |
| return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset))); |
| } |
| |
| static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) |
| { |
| unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags); |
| |
| return ckpt_flags & f; |
| } |
| |
| static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) |
| { |
| return __is_set_ckpt_flags(F2FS_CKPT(sbi), f); |
| } |
| |
| static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) |
| { |
| unsigned int ckpt_flags; |
| |
| ckpt_flags = le32_to_cpu(cp->ckpt_flags); |
| ckpt_flags |= f; |
| cp->ckpt_flags = cpu_to_le32(ckpt_flags); |
| } |
| |
| static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) |
| { |
| unsigned long flags; |
| |
| spin_lock_irqsave(&sbi->cp_lock, flags); |
| __set_ckpt_flags(F2FS_CKPT(sbi), f); |
| spin_unlock_irqrestore(&sbi->cp_lock, flags); |
| } |
| |
| static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) |
| { |
| unsigned int ckpt_flags; |
| |
| ckpt_flags = le32_to_cpu(cp->ckpt_flags); |
| ckpt_flags &= (~f); |
| cp->ckpt_flags = cpu_to_le32(ckpt_flags); |
| } |
| |
| static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) |
| { |
| unsigned long flags; |
| |
| spin_lock_irqsave(&sbi->cp_lock, flags); |
| __clear_ckpt_flags(F2FS_CKPT(sbi), f); |
| spin_unlock_irqrestore(&sbi->cp_lock, flags); |
| } |
| |
| #define init_f2fs_rwsem(sem) \ |
| do { \ |
| static struct lock_class_key __key; \ |
| \ |
| __init_f2fs_rwsem((sem), #sem, &__key); \ |
| } while (0) |
| |
| static inline void __init_f2fs_rwsem(struct f2fs_rwsem *sem, |
| const char *sem_name, struct lock_class_key *key) |
| { |
| __init_rwsem(&sem->internal_rwsem, sem_name, key); |
| #ifdef CONFIG_F2FS_UNFAIR_RWSEM |
| init_waitqueue_head(&sem->read_waiters); |
| #endif |
| } |
| |
| static inline int f2fs_rwsem_is_locked(struct f2fs_rwsem *sem) |
| { |
| return rwsem_is_locked(&sem->internal_rwsem); |
| } |
| |
| static inline int f2fs_rwsem_is_contended(struct f2fs_rwsem *sem) |
| { |
| return rwsem_is_contended(&sem->internal_rwsem); |
| } |
| |
| static inline void f2fs_down_read(struct f2fs_rwsem *sem) |
| { |
| #ifdef CONFIG_F2FS_UNFAIR_RWSEM |
| wait_event(sem->read_waiters, down_read_trylock(&sem->internal_rwsem)); |
| #else |
| down_read(&sem->internal_rwsem); |
| #endif |
| } |
| |
| static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem) |
| { |
| return down_read_trylock(&sem->internal_rwsem); |
| } |
| |
| static inline void f2fs_up_read(struct f2fs_rwsem *sem) |
| { |
| up_read(&sem->internal_rwsem); |
| } |
| |
| static inline void f2fs_down_write(struct f2fs_rwsem *sem) |
| { |
| down_write(&sem->internal_rwsem); |
| } |
| |
| #ifdef CONFIG_DEBUG_LOCK_ALLOC |
| static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass) |
| { |
| down_read_nested(&sem->internal_rwsem, subclass); |
| } |
| |
| static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass) |
| { |
| down_write_nested(&sem->internal_rwsem, subclass); |
| } |
| #else |
| #define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem) |
| #define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem) |
| #endif |
| |
| static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem) |
| { |
| return down_write_trylock(&sem->internal_rwsem); |
| } |
| |
| static inline void f2fs_up_write(struct f2fs_rwsem *sem) |
| { |
| up_write(&sem->internal_rwsem); |
| #ifdef CONFIG_F2FS_UNFAIR_RWSEM |
| wake_up_all(&sem->read_waiters); |
| #endif |
| } |
| |
| static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) |
| { |
| f2fs_down_read(&sbi->cp_rwsem); |
| } |
| |
| static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi) |
| { |
| if (time_to_inject(sbi, FAULT_LOCK_OP)) |
| return 0; |
| return f2fs_down_read_trylock(&sbi->cp_rwsem); |
| } |
| |
| static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) |
| { |
| f2fs_up_read(&sbi->cp_rwsem); |
| } |
| |
| static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) |
| { |
| f2fs_down_write(&sbi->cp_rwsem); |
| } |
| |
| static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) |
| { |
| f2fs_up_write(&sbi->cp_rwsem); |
| } |
| |
| static inline int __get_cp_reason(struct f2fs_sb_info *sbi) |
| { |
| int reason = CP_SYNC; |
| |
| if (test_opt(sbi, FASTBOOT)) |
| reason = CP_FASTBOOT; |
| if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) |
| reason = CP_UMOUNT; |
| return reason; |
| } |
| |
| static inline bool __remain_node_summaries(int reason) |
| { |
| return (reason & (CP_UMOUNT | CP_FASTBOOT)); |
| } |
| |
| static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi) |
| { |
| return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) || |
| is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG)); |
| } |
| |
| /* |
| * Check whether the inode has blocks or not |
| */ |
| static inline int F2FS_HAS_BLOCKS(struct inode *inode) |
| { |
| block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0; |
| |
| return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block; |
| } |
| |
| static inline bool f2fs_has_xattr_block(unsigned int ofs) |
| { |
| return ofs == XATTR_NODE_OFFSET; |
| } |
| |
| static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, |
| struct inode *inode, bool cap) |
| { |
| if (!inode) |
| return true; |
| if (!test_opt(sbi, RESERVE_ROOT)) |
| return false; |
| if (IS_NOQUOTA(inode)) |
| return true; |
| if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid())) |
| return true; |
| if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && |
| in_group_p(F2FS_OPTION(sbi).s_resgid)) |
| return true; |
| if (cap && capable(CAP_SYS_RESOURCE)) |
| return true; |
| return false; |
| } |
| |
| static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi, |
| struct inode *inode, bool cap) |
| { |
| block_t avail_user_block_count; |
| |
| avail_user_block_count = sbi->user_block_count - |
| sbi->current_reserved_blocks; |
| |
| if (!__allow_reserved_blocks(sbi, inode, cap)) |
| avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; |
| |
| if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { |
| if (avail_user_block_count > sbi->unusable_block_count) |
| avail_user_block_count -= sbi->unusable_block_count; |
| else |
| avail_user_block_count = 0; |
| } |
| |
| return avail_user_block_count; |
| } |
| |
| static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); |
| static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, |
| struct inode *inode, blkcnt_t *count, bool partial) |
| { |
| long long diff = 0, release = 0; |
| block_t avail_user_block_count; |
| int ret; |
| |
| ret = dquot_reserve_block(inode, *count); |
| if (ret) |
| return ret; |
| |
| if (time_to_inject(sbi, FAULT_BLOCK)) { |
| release = *count; |
| goto release_quota; |
| } |
| |
| /* |
| * let's increase this in prior to actual block count change in order |
| * for f2fs_sync_file to avoid data races when deciding checkpoint. |
| */ |
| percpu_counter_add(&sbi->alloc_valid_block_count, (*count)); |
| |
| spin_lock(&sbi->stat_lock); |
| |
| avail_user_block_count = get_available_block_count(sbi, inode, true); |
| diff = (long long)sbi->total_valid_block_count + *count - |
| avail_user_block_count; |
| if (unlikely(diff > 0)) { |
| if (!partial) { |
| spin_unlock(&sbi->stat_lock); |
| release = *count; |
| goto enospc; |
| } |
| if (diff > *count) |
| diff = *count; |
| *count -= diff; |
| release = diff; |
| if (!*count) { |
| spin_unlock(&sbi->stat_lock); |
| goto enospc; |
| } |
| } |
| sbi->total_valid_block_count += (block_t)(*count); |
| |
| spin_unlock(&sbi->stat_lock); |
| |
| if (unlikely(release)) { |
| percpu_counter_sub(&sbi->alloc_valid_block_count, release); |
| dquot_release_reservation_block(inode, release); |
| } |
| f2fs_i_blocks_write(inode, *count, true, true); |
| return 0; |
| |
| enospc: |
| percpu_counter_sub(&sbi->alloc_valid_block_count, release); |
| release_quota: |
| dquot_release_reservation_block(inode, release); |
| return -ENOSPC; |
| } |
| |
| #define PAGE_PRIVATE_GET_FUNC(name, flagname) \ |
| static inline bool page_private_##name(struct page *page) \ |
| { \ |
| return PagePrivate(page) && \ |
| test_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)) && \ |
| test_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ |
| } |
| |
| #define PAGE_PRIVATE_SET_FUNC(name, flagname) \ |
| static inline void set_page_private_##name(struct page *page) \ |
| { \ |
| if (!PagePrivate(page)) \ |
| attach_page_private(page, (void *)0); \ |
| set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); \ |
| set_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ |
| } |
| |
| #define PAGE_PRIVATE_CLEAR_FUNC(name, flagname) \ |
| static inline void clear_page_private_##name(struct page *page) \ |
| { \ |
| clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ |
| if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) \ |
| detach_page_private(page); \ |
| } |
| |
| PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER); |
| PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE); |
| PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION); |
| |
| PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE); |
| PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE); |
| PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION); |
| |
| PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE); |
| PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE); |
| PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION); |
| |
| static inline unsigned long get_page_private_data(struct page *page) |
| { |
| unsigned long data = page_private(page); |
| |
| if (!test_bit(PAGE_PRIVATE_NOT_POINTER, &data)) |
| return 0; |
| return data >> PAGE_PRIVATE_MAX; |
| } |
| |
| static inline void set_page_private_data(struct page *page, unsigned long data) |
| { |
| if (!PagePrivate(page)) |
| attach_page_private(page, (void *)0); |
| set_bit(PAGE_PRIVATE_NOT_POINTER, &page_private(page)); |
| page_private(page) |= data << PAGE_PRIVATE_MAX; |
| } |
| |
| static inline void clear_page_private_data(struct page *page) |
| { |
| page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0); |
| if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) |
| detach_page_private(page); |
| } |
| |
| static inline void clear_page_private_all(struct page *page) |
| { |
| clear_page_private_data(page); |
| clear_page_private_reference(page); |
| clear_page_private_gcing(page); |
| clear_page_private_inline(page); |
| |
| f2fs_bug_on(F2FS_P_SB(page), page_private(page)); |
| } |
| |
| static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, |
| struct inode *inode, |
| block_t count) |
| { |
| blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; |
| |
| spin_lock(&sbi->stat_lock); |
| f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); |
| sbi->total_valid_block_count -= (block_t)count; |
| if (sbi->reserved_blocks && |
| sbi->current_reserved_blocks < sbi->reserved_blocks) |
| sbi->current_reserved_blocks = min(sbi->reserved_blocks, |
| sbi->current_reserved_blocks + count); |
| spin_unlock(&sbi->stat_lock); |
| if (unlikely(inode->i_blocks < sectors)) { |
| f2fs_warn(sbi, "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", |
| inode->i_ino, |
| (unsigned long long)inode->i_blocks, |
| (unsigned long long)sectors); |
| set_sbi_flag(sbi, SBI_NEED_FSCK); |
| return; |
| } |
| f2fs_i_blocks_write(inode, count, false, true); |
| } |
| |
| static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) |
| { |
| atomic_inc(&sbi->nr_pages[count_type]); |
| |
| if (count_type == F2FS_DIRTY_DENTS || |
| count_type == F2FS_DIRTY_NODES || |
| count_type == F2FS_DIRTY_META || |
| count_type == F2FS_DIRTY_QDATA || |
| count_type == F2FS_DIRTY_IMETA) |
| set_sbi_flag(sbi, SBI_IS_DIRTY); |
| } |
| |
| static inline void inode_inc_dirty_pages(struct inode *inode) |
| { |
| atomic_inc(&F2FS_I(inode)->dirty_pages); |
| inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? |
| F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); |
| if (IS_NOQUOTA(inode)) |
| inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); |
| } |
| |
| static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) |
| { |
| atomic_dec(&sbi->nr_pages[count_type]); |
| } |
| |
| static inline void inode_dec_dirty_pages(struct inode *inode) |
| { |
| if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) && |
| !S_ISLNK(inode->i_mode)) |
| return; |
| |
| atomic_dec(&F2FS_I(inode)->dirty_pages); |
| dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? |
| F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); |
| if (IS_NOQUOTA(inode)) |
| dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); |
| } |
| |
| static inline void inc_atomic_write_cnt(struct inode *inode) |
| { |
| struct f2fs_sb_info *sbi = F2FS_I_SB(inode); |
| struct f2fs_inode_info *fi = F2FS_I(inode); |
| u64 current_write; |
| |
| fi->atomic_write_cnt++; |
| atomic64_inc(&sbi->current_atomic_write); |
| current_write = atomic64_read(&sbi->current_atomic_write); |
| if (current_write > sbi->peak_atomic_write) |
| sbi->peak_atomic_write = current_write; |
| } |
| |
| static inline void release_atomic_write_cnt(struct inode *inode) |
| { |
| struct f2fs_sb_info *sbi = F2FS_I_SB(inode); |
| struct f2fs_inode_info *fi = F2FS_I(inode); |
| |
| atomic64_sub(fi->atomic_write_cnt, &sbi->current_atomic_write); |
| fi->atomic_write_cnt = 0; |
| } |
| |
| static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) |
| { |
| return atomic_read(&sbi->nr_pages[count_type]); |
| } |
| |
| static inline int get_dirty_pages(struct inode *inode) |
| { |
| return atomic_read(&F2FS_I(inode)->dirty_pages); |
| } |
| |
| static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type) |
| { |
| return div_u64(get_pages(sbi, block_type) + BLKS_PER_SEC(sbi) - 1, |
| BLKS_PER_SEC(sbi)); |
| } |
| |
| static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi) |
| { |
| return sbi->total_valid_block_count; |
| } |
| |
| static inline block_t discard_blocks(struct f2fs_sb_info *sbi) |
| { |
| return sbi->discard_blks; |
| } |
| |
| static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag) |
| { |
| struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); |
| |
| /* return NAT or SIT bitmap */ |
| if (flag == NAT_BITMAP) |
| return le32_to_cpu(ckpt->nat_ver_bitmap_bytesize); |
| else if (flag == SIT_BITMAP) |
| return le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); |
| |
| return 0; |
| } |
| |
| static inline block_t __cp_payload(struct f2fs_sb_info *sbi) |
| { |
| return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload); |
| } |
| |
| static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) |
| { |
| struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); |
| void *tmp_ptr = &ckpt->sit_nat_version_bitmap; |
| int offset; |
| |
| if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { |
| offset = (flag == SIT_BITMAP) ? |
| le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; |
| /* |
| * if large_nat_bitmap feature is enabled, leave checksum |
| * protection for all nat/sit bitmaps. |
| */ |
| return tmp_ptr + offset + sizeof(__le32); |
| } |
| |
| if (__cp_payload(sbi) > 0) { |
| if (flag == NAT_BITMAP) |
| return tmp_ptr; |
| else |
| return (unsigned char *)ckpt + F2FS_BLKSIZE; |
| } else { |
| offset = (flag == NAT_BITMAP) ? |
| le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0; |
| return tmp_ptr + offset; |
| } |
| } |
| |
| static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi) |
| { |
| block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); |
| |
| if (sbi->cur_cp_pack == 2) |
| start_addr += BLKS_PER_SEG(sbi); |
| return start_addr; |
| } |
| |
| static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi) |
| { |
| block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr); |
| |
| if (sbi->cur_cp_pack == 1) |
| start_addr += BLKS_PER_SEG(sbi); |
| return start_addr; |
| } |
| |
| static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi) |
| { |
| sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1; |
| } |
| |
| static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) |
| { |
| return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); |
| } |
| |
| extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); |
| static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, |
| struct inode *inode, bool is_inode) |
| { |
| block_t valid_block_count; |
| unsigned int valid_node_count; |
| unsigned int avail_user_block_count; |
| int err; |
| |
| if (is_inode) { |
| if (inode) { |
| err = dquot_alloc_inode(inode); |
| if (err) |
| return err; |
| } |
| } else { |
| err = dquot_reserve_block(inode, 1); |
| if (err) |
| return err; |
| } |
| |
| if (time_to_inject(sbi, FAULT_BLOCK)) |
| goto enospc; |
| |
| spin_lock(&sbi->stat_lock); |
| |
| valid_block_count = sbi->total_valid_block_count + 1; |
| avail_user_block_count = get_available_block_count(sbi, inode, false); |
| |
| if (unlikely(valid_block_count > avail_user_block_count)) { |
| spin_unlock(&sbi->stat_lock); |
| goto enospc; |
| } |
| |
| valid_node_count = sbi->total_valid_node_count + 1; |
| if (unlikely(valid_node_count > sbi->total_node_count)) { |
| spin_unlock(&sbi->stat_lock); |
| goto enospc; |
| } |
| |
| sbi->total_valid_node_count++; |
| sbi->total_valid_block_count++; |
| spin_unlock(&sbi->stat_lock); |
| |
| if (inode) { |
| if (is_inode) |
| f2fs_mark_inode_dirty_sync(inode, true); |
| else |
| f2fs_i_blocks_write(inode, 1, true, true); |
| } |
| |
| percpu_counter_inc(&sbi->alloc_valid_block_count); |
| return 0; |
| |
| enospc: |
| if (is_inode) { |
| if (inode) |
| dquot_free_inode(inode); |
| } else { |
| dquot_release_reservation_block(inode, 1); |
| } |
| return -ENOSPC; |
| } |
| |
| static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, |
| struct inode *inode, bool is_inode) |
| { |
| spin_lock(&sbi->stat_lock); |
| |
| if (unlikely(!sbi->total_valid_block_count || |
| !sbi->total_valid_node_count)) { |
| f2fs_warn(sbi, "dec_valid_node_count: inconsistent block counts, total_valid_block:%u, total_valid_node:%u", |
| sbi->total_valid_block_count, |
| sbi->total_valid_node_count); |
| set_sbi_flag(sbi, SBI_NEED_FSCK); |
| } else { |
| sbi->total_valid_block_count--; |
| sbi->total_valid_node_count--; |
| } |
| |
| if (sbi->reserved_blocks && |
| sbi->current_reserved_blocks < sbi->reserved_blocks) |
| sbi->current_reserved_blocks++; |
| |
| spin_unlock(&sbi->stat_lock); |
| |
| if (is_inode) { |
| dquot_free_inode(inode); |
| } else { |
| if (unlikely(inode->i_blocks == 0)) { |
| f2fs_warn(sbi, "dec_valid_node_count: inconsistent i_blocks, ino:%lu, iblocks:%llu", |
| inode->i_ino, |
| (unsigned long long)inode->i_blocks); |
| set_sbi_flag(sbi, SBI_NEED_FSCK); |
| return; |
| } |
| f2fs_i_blocks_write(inode, 1, false, true); |
| } |
| } |
| |
| static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) |
| { |
| return sbi->total_valid_node_count; |
| } |
| |
| static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi) |
| { |
| percpu_counter_inc(&sbi->total_valid_inode_count); |
| } |
| |
| static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi) |
| { |
| percpu_counter_dec(&sbi->total_valid_inode_count); |
| } |
| |
| static inline s64 valid_inode_count(struct f2fs_sb_info *sbi) |
| { |
| return percpu_counter_sum_positive(&sbi->total_valid_inode_count); |
| } |
| |
| static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, |
| pgoff_t index, bool for_write) |
| { |
| struct page *page; |
| unsigned int flags; |
| |
| if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) { |
| if (!for_write) |
| page = find_get_page_flags(mapping, index, |
| FGP_LOCK | FGP_ACCESSED); |
| else |
| page = find_lock_page(mapping, index); |
| if (page) |
| return page; |
| |
| if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) |
| return NULL; |
| } |
| |
| if (!for_write) |
| return grab_cache_page(mapping, index); |
| |
| flags = memalloc_nofs_save(); |
| page = grab_cache_page_write_begin(mapping, index); |
| memalloc_nofs_restore(flags); |
| |
| return page; |
| } |
| |
| static inline struct page *f2fs_pagecache_get_page( |
| struct address_space *mapping, pgoff_t index, |
| fgf_t fgp_flags, gfp_t gfp_mask) |
| { |
| if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) |
| return NULL; |
| |
| return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); |
| } |
| |
| static inline void f2fs_put_page(struct page *page, int unlock) |
| { |
| if (!page) |
| return; |
| |
| if (unlock) { |
| f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page)); |
| unlock_page(page); |
| } |
| put_page(page); |
| } |
| |
| static inline void f2fs_put_dnode(struct dnode_of_data *dn) |
| { |
| if (dn->node_page) |
| f2fs_put_page(dn->node_page, 1); |
| if (dn->inode_page && dn->node_page != dn->inode_page) |
| f2fs_put_page(dn->inode_page, 0); |
| dn->node_page = NULL; |
| dn->inode_page = NULL; |
| } |
| |
| static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name, |
| size_t size) |
| { |
| return kmem_cache_create(name, size, 0, SLAB_RECLAIM_ACCOUNT, NULL); |
| } |
| |
| static inline void *f2fs_kmem_cache_alloc_nofail(struct kmem_cache *cachep, |
| gfp_t flags) |
| { |
| void *entry; |
| |
| entry = kmem_cache_alloc(cachep, flags); |
| if (!entry) |
| entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL); |
| return entry; |
| } |
| |
| static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, |
| gfp_t flags, bool nofail, struct f2fs_sb_info *sbi) |
| { |
| if (nofail) |
| return f2fs_kmem_cache_alloc_nofail(cachep, flags); |
| |
| if (time_to_inject(sbi, FAULT_SLAB_ALLOC)) |
| return NULL; |
| |
| return kmem_cache_alloc(cachep, flags); |
| } |
| |
| static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type) |
| { |
| if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || |
| get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || |
| get_pages(sbi, F2FS_WB_CP_DATA) || |
| get_pages(sbi, F2FS_DIO_READ) || |
| get_pages(sbi, F2FS_DIO_WRITE)) |
| return true; |
| |
| if (type != DISCARD_TIME && SM_I(sbi) && SM_I(sbi)->dcc_info && |
| atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) |
| return true; |
| |
| if (SM_I(sbi) && SM_I(sbi)->fcc_info && |
| atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) |
| return true; |
| return false; |
| } |
| |
| static inline bool is_idle(struct f2fs_sb_info *sbi, int type) |
| { |
| if (sbi->gc_mode == GC_URGENT_HIGH) |
| return true; |
| |
| if (is_inflight_io(sbi, type)) |
| return false; |
| |
| if (sbi->gc_mode == GC_URGENT_MID) |
| return true; |
| |
| if (sbi->gc_mode == GC_URGENT_LOW && |
| (type == DISCARD_TIME || type == GC_TIME)) |
| return true; |
| |
| return f2fs_time_over(sbi, type); |
| } |
| |
| static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, |
| unsigned long index, void *item) |
| { |
| while (radix_tree_insert(root, index, item)) |
| cond_resched(); |
| } |
| |
| #define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino) |
| |
| static inline bool IS_INODE(struct page *page) |
| { |
| struct f2fs_node *p = F2FS_NODE(page); |
| |
| return RAW_IS_INODE(p); |
| } |
| |
| static inline int offset_in_addr(struct f2fs_inode *i) |
| { |
| return (i->i_inline & F2FS_EXTRA_ATTR) ? |
| (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0; |
| } |
| |
| static inline __le32 *blkaddr_in_node(struct f2fs_node *node) |
| { |
| return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; |
| } |
| |
| static inline int f2fs_has_extra_attr(struct inode *inode); |
| static inline block_t data_blkaddr(struct inode *inode, |
| struct page *node_page, unsigned int offset) |
| { |
| struct f2fs_node *raw_node; |
| __le32 *addr_array; |
| int base = 0; |
| bool is_inode = IS_INODE(node_page); |
| |
| raw_node = F2FS_NODE(node_page); |
| |
| if (is_inode) { |
| if (!inode) |
| /* from GC path only */ |
| base = offset_in_addr(&raw_node->i); |
| else if (f2fs_has_extra_attr(inode)) |
| base = get_extra_isize(inode); |
| } |
| |
| addr_array = blkaddr_in_node(raw_node); |
| return le32_to_cpu(addr_array[base + offset]); |
| } |
| |
| static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn) |
| { |
| return data_blkaddr(dn->inode, dn->node_page, dn->ofs_in_node); |
| } |
| |
| static inline int f2fs_test_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| return mask & *addr; |
| } |
| |
| static inline void f2fs_set_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| *addr |= mask; |
| } |
| |
| static inline void f2fs_clear_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| *addr &= ~mask; |
| } |
| |
| static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| int ret; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| ret = mask & *addr; |
| *addr |= mask; |
| return ret; |
| } |
| |
| static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| int ret; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| ret = mask & *addr; |
| *addr &= ~mask; |
| return ret; |
| } |
| |
| static inline void f2fs_change_bit(unsigned int nr, char *addr) |
| { |
| int mask; |
| |
| addr += (nr >> 3); |
| mask = BIT(7 - (nr & 0x07)); |
| *addr ^= mask; |
| } |
| |
| /* |
| * On-disk inode flags (f2fs_inode::i_flags) |
| */ |
| #define F2FS_COMPR_FL 0x00000004 /* Compress file */ |
| #define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ |
| #define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ |
| #define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ |
| #define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ |
| #define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ |
| #define F2FS_NOCOMP_FL 0x00000400 /* Don't compress */ |
| #define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ |
| #define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ |
| #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ |
| #define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */ |
| |
| #define F2FS_QUOTA_DEFAULT_FL (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL) |
| |
| /* Flags that should be inherited by new inodes from their parent. */ |
| #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ |
| F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ |
| F2FS_CASEFOLD_FL) |
| |
| /* Flags that are appropriate for regular files (all but dir-specific ones). */ |
| #define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ |
| F2FS_CASEFOLD_FL)) |
| |
| /* Flags that are appropriate for non-directories/regular files. */ |
| #define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) |
| |
| static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) |
| { |
| if (S_ISDIR(mode)) |
| return flags; |
| else if (S_ISREG(mode)) |
| return flags & F2FS_REG_FLMASK; |
| else |
| return flags & F2FS_OTHER_FLMASK; |
| } |
| |
| static inline void __mark_inode_dirty_flag(struct inode *inode, |
| int flag, bool set) |
| { |
| switch (flag) { |
| case FI_INLINE_XATTR: |
| case FI_INLINE_DATA: |
| case FI_INLINE_DENTRY: |
| case FI_NEW_INODE: |
| if (set) |
| return; |
| fallthrough; |
| case FI_DATA_EXIST: |
| case FI_INLINE_DOTS: |
| case FI_PIN_FILE: |
| case FI_COMPRESS_RELEASED: |
| case FI_ATOMIC_COMMITTED: |
| f2fs_mark_inode_dirty_sync(inode, true); |
| } |
| } |
| |
| static inline void set_inode_flag(struct inode *inode, int flag) |
| { |
| set_bit(flag, F2FS_I(inode)->flags); |
| __mark_inode_dirty_flag(inode, flag, true); |
| } |
| |
| static inline int is_inode_flag_set(struct inode *inode, int flag) |
| { |
| return test_bit(flag, F2FS_I(inode)->flags); |
| } |
| |
| static inline void clear_inode_flag(struct inode *inode, int flag) |
| { |
| clear_bit(flag, F2FS_I(inode)->flags); |
| __mark_inode_dirty_flag(inode, flag, false); |
| } |
| |
| static inline bool f2fs_verity_in_progress(struct inode *inode) |
| { |
| return IS_ENABLED(CONFIG_FS_VERITY) && |
| is_inode_flag_set(inode, FI_VERITY_IN_PROGRESS); |
| } |
| |
| static inline void set_acl_inode(struct inode *inode, umode_t mode) |
| { |
| F2FS_I(inode)->i_acl_mode = mode; |
| set_inode_flag(inode, FI_ACL_MODE); |
| f2fs_mark_inode_dirty_sync(inode, false); |
| } |
| |
| static inline void f2fs_i_links_write(struct inode *inode, bool inc) |
| { |
| if (inc) |
| inc_nlink(inode); |
| else |
| drop_nlink(inode); |
| f2fs_mark_inode_dirty_sync(inode, true); |
| } |
| |
| static inline void f2fs_i_blocks_write(struct inode *inode, |
| block_t diff, bool add, bool claim) |
| { |
| bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); |
| bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); |
| |
| /* add = 1, claim = 1 should be dquot_reserve_block in pair */ |
| if (add) { |
| if (claim) |
| dquot_claim_block(inode, diff); |
| else |
| dquot_alloc_block_nofail(inode, diff); |
| } else { |
| dquot_free_block(inode, diff); |
| } |
| |
| f2fs_mark_inode_dirty_sync(inode, true); |
| if (clean || recover) |
| set_inode_flag(inode, FI_AUTO_RECOVER); |
| } |
| |
| static inline bool f2fs_is_atomic_file(struct inode *inode); |
| |
| static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size) |
| { |
| bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); |
| bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); |
| |
| if (i_size_read(inode) == i_size) |
| return; |
| |
| i_size_write(inode, i_size); |
| |
| if (f2fs_is_atomic_file(inode)) |
| return; |
| |
| f2fs_mark_inode_dirty_sync(inode, true); |
| |