Files
agnos-kernel-sdm845/fs/f2fs/segment.h
Jaegeuk Kim d919765758 f2fs/fscrypt: updates to v4.17-rc1
Pull f2fs update from Jaegeuk Kim:
 "In this round, we've mainly focused on performance tuning and critical
  bug fixes occurred in low-end devices. Sheng Yong introduced
  lost_found feature to keep missing files during recovery instead of
  thrashing them. We're preparing coming fsverity implementation. And,
  we've got more features to communicate with users for better
  performance. In low-end devices, some memory-related issues were
  fixed, and subtle race condtions and corner cases were addressed as
  well.

  Enhancements:
   - large nat bitmaps for more free node ids
   - add three block allocation policies to pass down write hints given by user
   - expose extension list to user and introduce hot file extension
   - tune small devices seamlessly for low-end devices
   - set readdir_ra by default
   - give more resources under gc_urgent mode regarding to discard and cleaning
   - introduce fsync_mode to enforce posix or not
   - nowait aio support
   - add lost_found feature to keep dangling inodes
   - reserve bits for future fsverity feature
   - add test_dummy_encryption for FBE

  Bug fixes:
   - don't use highmem for dentry pages
   - align memory boundary for bitops
   - truncate preallocated blocks in write errors
   - guarantee i_times on fsync call
   - clear CP_TRIMMED_FLAG correctly
   - prevent node chain loop during recovery
   - avoid data race between atomic write and background cleaning
   - avoid unnecessary selinux violation warnings on resgid option
   - GFP_NOFS to avoid deadlock in quota and read paths
   - fix f2fs_skip_inode_update to allow i_size recovery

  In addition to the above, there are several minor bug fixes and clean-ups"

Cherry-pick from origin/upstream-f2fs-stable-linux-4.9.y:

ac389af190fb f2fs: remain written times to update inode during fsync
270deeb87125 f2fs: make assignment of t->dentry_bitmap more readable
a4fa11c8da10 f2fs: truncate preallocated blocks in error case
4478970f0e73 f2fs: fix a wrong condition in f2fs_skip_inode_update
29cead58f5ea f2fs: reserve bits for fs-verity
848b293a5d95 f2fs: Add a segment type check in inplace write
2dc8f5a3a640 f2fs: no need to initialize zero value for GFP_F2FS_ZERO
83b9bb95a628 f2fs: don't track new nat entry in nat set
a33ce03ac477 f2fs: clean up with F2FS_BLK_ALIGN
a3f8ec8082e3 f2fs: check blkaddr more accuratly before issue a bio
034f11eadb16 f2fs: Set GF_NOFS in read_cache_page_gfp while doing f2fs_quota_read
aa5bcfd8f488 f2fs: introduce a new mount option test_dummy_encryption
9b880fe6e6e2 f2fs: introduce F2FS_FEATURE_LOST_FOUND feature
80d6489a08c1 f2fs: release locks before return in f2fs_ioc_gc_range()
9f1896c490eb f2fs: align memory boundary for bitops
c7930ee88334 f2fs: remove unneeded set_cold_node()
355d2346409a f2fs: add nowait aio support
e9a50e6b9479 f2fs: wrap all options with f2fs_sb_info.mount_opt
b6d2ec83e0c0 f2fs: Don't overwrite all types of node to keep node chain
9a954816298c f2fs: introduce mount option for fsync mode
4ce4eb697068 f2fs: fix to restore old mount option in ->remount_fs
8f711c344e61 f2fs: wrap sb_rdonly with f2fs_readonly
c07478ee84bf f2fs: avoid selinux denial on CAP_SYS_RESOURCE
ac734c416fa9 f2fs: support hot file extension
f4f10221accc f2fs: fix to avoid race in between atomic write and background GC
e87b13ec160b f2fs: do gc in greedy mode for whole range if gc_urgent mode is set
e9878588de94 f2fs: issue discard aggressively in the gc_urgent mode
ad3ce479e6e4 f2fs: set readdir_ra by default
5aae2026bbd2 f2fs: add auto tuning for small devices
78c1fc2d8f27 f2fs: add mount option for segment allocation policy
ecd02f564631 f2fs: don't stop GC if GC is contended
1e72cb27d2d6 f2fs: expose extension_list sysfs entry
061839d178ab f2fs: fix to set KEEP_SIZE bit in f2fs_zero_range
4951ebcbc4e2 f2fs: introduce sb_lock to make encrypt pwsalt update exclusive
939f6be0420f f2fs: remove redundant initialization of pointer 'p'
39bea4bc8ef2 f2fs: flush cp pack except cp pack 2 page at first
770611eb2ab4 f2fs: clean up f2fs_sb_has_xxx functions
4d8e4a8965f9 f2fs: remove redundant check of page type when submit bio
e9878588de94 f2fs: issue discard aggressively in the gc_urgent mode
ad3ce479e6e4 f2fs: set readdir_ra by default
5aae2026bbd2 f2fs: add auto tuning for small devices
78c1fc2d8f27 f2fs: add mount option for segment allocation policy
ecd02f564631 f2fs: don't stop GC if GC is contended
1e72cb27d2d6 f2fs: expose extension_list sysfs entry
061839d178ab f2fs: fix to set KEEP_SIZE bit in f2fs_zero_range
4951ebcbc4e2 f2fs: introduce sb_lock to make encrypt pwsalt update exclusive
939f6be0420f f2fs: remove redundant initialization of pointer 'p'
39bea4bc8ef2 f2fs: flush cp pack except cp pack 2 page at first
770611eb2ab4 f2fs: clean up f2fs_sb_has_xxx functions
4d8e4a8965f9 f2fs: remove redundant check of page type when submit bio
b57a37f01fda f2fs: fix to handle looped node chain during recovery
9ac5b8c54083 f2fs: handle quota for orphan inodes
87c18066016a f2fs: support passing down write hints to block layer with F2FS policy
bcdc571e8d8b f2fs: support passing down write hints given by users to block layer
92413bc12e32 f2fs: fix to clear CP_TRIMMED_FLAG
a1afb55f9784 f2fs: support large nat bitmap
636039140493 f2fs: fix to check extent cache in f2fs_drop_extent_tree
7de4fccdbce1 f2fs: restrict inline_xattr_size configuration
aae506a8b704 f2fs: fix heap mode to reset it back
8fa455bb6ea0 f2fs: fix potential corruption in area before F2FS_SUPER_OFFSET
9d9cb0ef73f9 fscrypt: fix build with pre-4.6 gcc versions
401052ffc6b4 fscrypt: remove 'ci' parameter from fscrypt_put_encryption_info()
549b2061b3b5 fscrypt: fix up fscrypt_fname_encrypted_size() for internal use
c440b5091a0c fscrypt: define fscrypt_fname_alloc_buffer() to be for presented names
7d82f0e1c39a ext4: switch to fscrypt ->symlink() helper functions
ba4efe560438 ext4: switch to fscrypt_get_symlink()
b0edc2f22d24 fscrypt: calculate NUL-padding length in one place only
62cfdd9868c7 fscrypt: move fscrypt_symlink_data to fscrypt_private.h
e4e6776522bc fscrypt: remove fscrypt_fname_usr_to_disk()
45028b5aaa4e f2fs: switch to fscrypt_get_symlink()
f62d3d31e0c7 f2fs: switch to fscrypt ->symlink() helper functions
da32a1633ad3 fscrypt: new helper function - fscrypt_get_symlink()
a7e05c731d11 fscrypt: new helper functions for ->symlink()
eb9c5fd896de fscrypt: trim down fscrypt.h includes
0a02472d8ae2 fscrypt: move fscrypt_is_dot_dotdot() to fs/crypto/fname.c
9d51ca80274c fscrypt: move fscrypt_valid_enc_modes() to fscrypt_private.h
efbfa8c6a056 fscrypt: move fscrypt_operations declaration to fscrypt_supp.h
616dbd2bdc6a fscrypt: split fscrypt_dummy_context_enabled() into supp/notsupp versions
f0c472bcbf1c fscrypt: move fscrypt_ctx declaration to fscrypt_supp.h
bc76f39109b1 fscrypt: move fscrypt_info_cachep declaration to fscrypt_private.h
b67b07ec4964 fscrypt: move fscrypt_control_page() to supp/notsupp headers
d8dfb89961d0 fscrypt: move fscrypt_has_encryption_key() to supp/notsupp headers

Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
2018-04-12 09:54:41 -07:00

857 lines
26 KiB
C

/*
* fs/f2fs/segment.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
/* constant macro */
#define NULL_SEGNO ((unsigned int)(~0))
#define NULL_SECNO ((unsigned int)(~0))
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS 4096 /* 8GB in maximum */
#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno)
#define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno)
#define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA)
#define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE)
#define IS_HOT(t) ((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
#define IS_WARM(t) ((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
#define IS_COLD(t) ((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
#define IS_CURSEG(sbi, seg) \
(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
#define IS_CURSEC(sbi, secno) \
(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
(sbi)->segs_per_sec) || \
((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
(sbi)->segs_per_sec) || \
((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
(sbi)->segs_per_sec) || \
((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
(sbi)->segs_per_sec) || \
((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
(sbi)->segs_per_sec) || \
((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
(sbi)->segs_per_sec)) \
#define MAIN_BLKADDR(sbi) \
(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr))
#define SEG0_BLKADDR(sbi) \
(SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
#define MAIN_SECS(sbi) ((sbi)->total_sections)
#define TOTAL_SEGS(sbi) \
(SM_I(sbi) ? SM_I(sbi)->segment_count : \
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
#define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \
(sbi)->log_blocks_per_seg))
#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
(GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
#define NEXT_FREE_BLKADDR(sbi, curseg) \
(START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_ADDR)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
#define BLKS_PER_SEC(sbi) \
((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
#define GET_SEC_FROM_SEG(sbi, segno) \
((segno) / (sbi)->segs_per_sec)
#define GET_SEG_FROM_SEC(sbi, secno) \
((secno) * (sbi)->segs_per_sec)
#define GET_ZONE_FROM_SEC(sbi, secno) \
((secno) / (sbi)->secs_per_zone)
#define GET_ZONE_FROM_SEG(sbi, segno) \
GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
#define GET_SUM_BLOCK(sbi, segno) \
((sbi)->sm_info->ssa_blkaddr + (segno))
#define GET_SUM_TYPE(footer) ((footer)->entry_type)
#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
#define SIT_ENTRY_OFFSET(sit_i, segno) \
((segno) % (sit_i)->sents_per_block)
#define SIT_BLOCK_OFFSET(segno) \
((segno) / SIT_ENTRY_PER_BLOCK)
#define START_SEGNO(segno) \
(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi) \
((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
#define f2fs_bitmap_size(nr) \
(BITS_TO_LONGS(nr) * sizeof(unsigned long))
#define SECTOR_FROM_BLOCK(blk_addr) \
(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
#define SECTOR_TO_BLOCK(sectors) \
((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
/*
* indicate a block allocation direction: RIGHT and LEFT.
* RIGHT means allocating new sections towards the end of volume.
* LEFT means the opposite direction.
*/
enum {
ALLOC_RIGHT = 0,
ALLOC_LEFT
};
/*
* In the victim_sel_policy->alloc_mode, there are two block allocation modes.
* LFS writes data sequentially with cleaning operations.
* SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
*/
enum {
LFS = 0,
SSR
};
/*
* In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
* GC_CB is based on cost-benefit algorithm.
* GC_GREEDY is based on greedy algorithm.
*/
enum {
GC_CB = 0,
GC_GREEDY,
ALLOC_NEXT,
FLUSH_DEVICE,
MAX_GC_POLICY,
};
/*
* BG_GC means the background cleaning job.
* FG_GC means the on-demand cleaning job.
* FORCE_FG_GC means on-demand cleaning job in background.
*/
enum {
BG_GC = 0,
FG_GC,
FORCE_FG_GC,
};
/* for a function parameter to select a victim segment */
struct victim_sel_policy {
int alloc_mode; /* LFS or SSR */
int gc_mode; /* GC_CB or GC_GREEDY */
unsigned long *dirty_segmap; /* dirty segment bitmap */
unsigned int max_search; /* maximum # of segments to search */
unsigned int offset; /* last scanned bitmap offset */
unsigned int ofs_unit; /* bitmap search unit */
unsigned int min_cost; /* minimum cost */
unsigned int min_segno; /* segment # having min. cost */
};
struct seg_entry {
unsigned int type:6; /* segment type like CURSEG_XXX_TYPE */
unsigned int valid_blocks:10; /* # of valid blocks */
unsigned int ckpt_valid_blocks:10; /* # of valid blocks last cp */
unsigned int padding:6; /* padding */
unsigned char *cur_valid_map; /* validity bitmap of blocks */
#ifdef CONFIG_F2FS_CHECK_FS
unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
#endif
/*
* # of valid blocks and the validity bitmap stored in the the last
* checkpoint pack. This information is used by the SSR mode.
*/
unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
unsigned char *discard_map;
unsigned long long mtime; /* modification time of the segment */
};
struct sec_entry {
unsigned int valid_blocks; /* # of valid blocks in a section */
};
struct segment_allocation {
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};
/*
* this value is set in page as a private data which indicate that
* the page is atomically written, and it is in inmem_pages list.
*/
#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
#define IS_ATOMIC_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
#define IS_DUMMY_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
struct inmem_pages {
struct list_head list;
struct page *page;
block_t old_addr; /* for revoking when fail to commit */
};
struct sit_info {
const struct segment_allocation *s_ops;
block_t sit_base_addr; /* start block address of SIT area */
block_t sit_blocks; /* # of blocks used by SIT area */
block_t written_valid_blocks; /* # of valid blocks in main area */
char *sit_bitmap; /* SIT bitmap pointer */
#ifdef CONFIG_F2FS_CHECK_FS
char *sit_bitmap_mir; /* SIT bitmap mirror */
#endif
unsigned int bitmap_size; /* SIT bitmap size */
unsigned long *tmp_map; /* bitmap for temporal use */
unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */
unsigned int dirty_sentries; /* # of dirty sentries */
unsigned int sents_per_block; /* # of SIT entries per block */
struct rw_semaphore sentry_lock; /* to protect SIT cache */
struct seg_entry *sentries; /* SIT segment-level cache */
struct sec_entry *sec_entries; /* SIT section-level cache */
/* for cost-benefit algorithm in cleaning procedure */
unsigned long long elapsed_time; /* elapsed time after mount */
unsigned long long mounted_time; /* mount time */
unsigned long long min_mtime; /* min. modification time */
unsigned long long max_mtime; /* max. modification time */
unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
};
struct free_segmap_info {
unsigned int start_segno; /* start segment number logically */
unsigned int free_segments; /* # of free segments */
unsigned int free_sections; /* # of free sections */
spinlock_t segmap_lock; /* free segmap lock */
unsigned long *free_segmap; /* free segment bitmap */
unsigned long *free_secmap; /* free section bitmap */
};
/* Notice: The order of dirty type is same with CURSEG_XXX in f2fs.h */
enum dirty_type {
DIRTY_HOT_DATA, /* dirty segments assigned as hot data logs */
DIRTY_WARM_DATA, /* dirty segments assigned as warm data logs */
DIRTY_COLD_DATA, /* dirty segments assigned as cold data logs */
DIRTY_HOT_NODE, /* dirty segments assigned as hot node logs */
DIRTY_WARM_NODE, /* dirty segments assigned as warm node logs */
DIRTY_COLD_NODE, /* dirty segments assigned as cold node logs */
DIRTY, /* to count # of dirty segments */
PRE, /* to count # of entirely obsolete segments */
NR_DIRTY_TYPE
};
struct dirty_seglist_info {
const struct victim_selection *v_ops; /* victim selction operation */
unsigned long *dirty_segmap[NR_DIRTY_TYPE];
struct mutex seglist_lock; /* lock for segment bitmaps */
int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */
unsigned long *victim_secmap; /* background GC victims */
};
/* victim selection function for cleaning and SSR */
struct victim_selection {
int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
int, int, char);
};
/* for active log information */
struct curseg_info {
struct mutex curseg_mutex; /* lock for consistency */
struct f2fs_summary_block *sum_blk; /* cached summary block */
struct rw_semaphore journal_rwsem; /* protect journal area */
struct f2fs_journal *journal; /* cached journal info */
unsigned char alloc_type; /* current allocation type */
unsigned int segno; /* current segment number */
unsigned short next_blkoff; /* next block offset to write */
unsigned int zone; /* current zone number */
unsigned int next_segno; /* preallocated segment */
};
struct sit_entry_set {
struct list_head set_list; /* link with all sit sets */
unsigned int start_segno; /* start segno of sits in set */
unsigned int entry_cnt; /* the # of sit entries in set */
};
/*
* inline functions
*/
static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
{
return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
}
static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
return &sit_i->sentries[segno];
}
static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)];
}
static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
unsigned int segno, bool use_section)
{
/*
* In order to get # of valid blocks in a section instantly from many
* segments, f2fs manages two counting structures separately.
*/
if (use_section && sbi->segs_per_sec > 1)
return get_sec_entry(sbi, segno)->valid_blocks;
else
return get_seg_entry(sbi, segno)->valid_blocks;
}
static inline void seg_info_from_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
se->valid_blocks = GET_SIT_VBLOCKS(rs);
se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
#ifdef CONFIG_F2FS_CHECK_FS
memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
#endif
se->type = GET_SIT_TYPE(rs);
se->mtime = le64_to_cpu(rs->mtime);
}
static inline void __seg_info_to_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) |
se->valid_blocks;
rs->vblocks = cpu_to_le16(raw_vblocks);
memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
rs->mtime = cpu_to_le64(se->mtime);
}
static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
struct page *page, unsigned int start)
{
struct f2fs_sit_block *raw_sit;
struct seg_entry *se;
struct f2fs_sit_entry *rs;
unsigned int end = min(start + SIT_ENTRY_PER_BLOCK,
(unsigned long)MAIN_SEGS(sbi));
int i;
raw_sit = (struct f2fs_sit_block *)page_address(page);
for (i = 0; i < end - start; i++) {
rs = &raw_sit->entries[i];
se = get_seg_entry(sbi, start + i);
__seg_info_to_raw_sit(se, rs);
}
}
static inline void seg_info_to_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
__seg_info_to_raw_sit(se, rs);
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
se->ckpt_valid_blocks = se->valid_blocks;
}
static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
unsigned int max, unsigned int segno)
{
unsigned int ret;
spin_lock(&free_i->segmap_lock);
ret = find_next_bit(free_i->free_segmap, max, segno);
spin_unlock(&free_i->segmap_lock);
return ret;
}
static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
spin_lock(&free_i->segmap_lock);
clear_bit(segno, free_i->free_segmap);
free_i->free_segments++;
next = find_next_bit(free_i->free_segmap,
start_segno + sbi->segs_per_sec, start_segno);
if (next >= start_segno + sbi->segs_per_sec) {
clear_bit(secno, free_i->free_secmap);
free_i->free_sections++;
}
spin_unlock(&free_i->segmap_lock);
}
static inline void __set_inuse(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
set_bit(segno, free_i->free_segmap);
free_i->free_segments--;
if (!test_and_set_bit(secno, free_i->free_secmap))
free_i->free_sections--;
}
static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
spin_lock(&free_i->segmap_lock);
if (test_and_clear_bit(segno, free_i->free_segmap)) {
free_i->free_segments++;
next = find_next_bit(free_i->free_segmap,
start_segno + sbi->segs_per_sec, start_segno);
if (next >= start_segno + sbi->segs_per_sec) {
if (test_and_clear_bit(secno, free_i->free_secmap))
free_i->free_sections++;
}
}
spin_unlock(&free_i->segmap_lock);
}
static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
spin_lock(&free_i->segmap_lock);
if (!test_and_set_bit(segno, free_i->free_segmap)) {
free_i->free_segments--;
if (!test_and_set_bit(secno, free_i->free_secmap))
free_i->free_sections--;
}
spin_unlock(&free_i->segmap_lock);
}
static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
void *dst_addr)
{
struct sit_info *sit_i = SIT_I(sbi);
#ifdef CONFIG_F2FS_CHECK_FS
if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
sit_i->bitmap_size))
f2fs_bug_on(sbi, 1);
#endif
memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
}
static inline block_t written_block_count(struct f2fs_sb_info *sbi)
{
return SIT_I(sbi)->written_valid_blocks;
}
static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
{
return FREE_I(sbi)->free_segments;
}
static inline int reserved_segments(struct f2fs_sb_info *sbi)
{
return SM_I(sbi)->reserved_segments;
}
static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
{
return FREE_I(sbi)->free_sections;
}
static inline unsigned int prefree_segments(struct f2fs_sb_info *sbi)
{
return DIRTY_I(sbi)->nr_dirty[PRE];
}
static inline unsigned int dirty_segments(struct f2fs_sb_info *sbi)
{
return DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_DATA] +
DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_DATA] +
DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_DATA] +
DIRTY_I(sbi)->nr_dirty[DIRTY_HOT_NODE] +
DIRTY_I(sbi)->nr_dirty[DIRTY_WARM_NODE] +
DIRTY_I(sbi)->nr_dirty[DIRTY_COLD_NODE];
}
static inline int overprovision_segments(struct f2fs_sb_info *sbi)
{
return SM_I(sbi)->ovp_segments;
}
static inline int reserved_sections(struct f2fs_sb_info *sbi)
{
return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
}
static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
{
unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
get_pages(sbi, F2FS_DIRTY_DENTS);
unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
unsigned int segno, left_blocks;
int i;
/* check current node segment */
for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
segno = CURSEG_I(sbi, i)->segno;
left_blocks = sbi->blocks_per_seg -
get_seg_entry(sbi, segno)->ckpt_valid_blocks;
if (node_blocks > left_blocks)
return false;
}
/* check current data segment */
segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
left_blocks = sbi->blocks_per_seg -
get_seg_entry(sbi, segno)->ckpt_valid_blocks;
if (dent_blocks > left_blocks)
return false;
return true;
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
int freed, int needed)
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
has_curseg_enough_space(sbi))
return false;
return (free_sections(sbi) + freed) <=
(node_secs + 2 * dent_secs + imeta_secs +
reserved_sections(sbi) + needed);
}
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
{
return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments;
}
static inline int utilization(struct f2fs_sb_info *sbi)
{
return div_u64((u64)valid_user_blocks(sbi) * 100,
sbi->user_block_count);
}
/*
* Sometimes f2fs may be better to drop out-of-place update policy.
* And, users can control the policy through sysfs entries.
* There are five policies with triggering conditions as follows.
* F2FS_IPU_FORCE - all the time,
* F2FS_IPU_SSR - if SSR mode is activated,
* F2FS_IPU_UTIL - if FS utilization is over threashold,
* F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
* threashold,
* F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
* storages. IPU will be triggered only if the # of dirty
* pages over min_fsync_blocks.
* F2FS_IPUT_DISABLE - disable IPU. (=default option)
*/
#define DEF_MIN_IPU_UTIL 70
#define DEF_MIN_FSYNC_BLOCKS 8
#define DEF_MIN_HOT_BLOCKS 16
#define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */
enum {
F2FS_IPU_FORCE,
F2FS_IPU_SSR,
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
F2FS_IPU_FSYNC,
F2FS_IPU_ASYNC,
};
static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
return curseg->segno;
}
static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
return curseg->alloc_type;
}
static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
return curseg->next_blkoff;
}
static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
{
f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
}
static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
{
struct f2fs_sb_info *sbi = fio->sbi;
if (PAGE_TYPE_OF_BIO(fio->type) == META &&
(!is_read_io(fio->op) || fio->is_meta))
BUG_ON(blk_addr < SEG0_BLKADDR(sbi) ||
blk_addr >= MAIN_BLKADDR(sbi));
else
BUG_ON(blk_addr < MAIN_BLKADDR(sbi) ||
blk_addr >= MAX_BLKADDR(sbi));
}
/*
* Summary block is always treated as an invalid block
*/
static inline int check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
#ifdef CONFIG_F2FS_CHECK_FS
bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false;
int valid_blocks = 0;
int cur_pos = 0, next_pos;
/* check bitmap with valid block count */
do {
if (is_valid) {
next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
sbi->blocks_per_seg,
cur_pos);
valid_blocks += next_pos - cur_pos;
} else
next_pos = find_next_bit_le(&raw_sit->valid_map,
sbi->blocks_per_seg,
cur_pos);
cur_pos = next_pos;
is_valid = !is_valid;
} while (cur_pos < sbi->blocks_per_seg);
if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
f2fs_msg(sbi->sb, KERN_ERR,
"Mismatch valid blocks %d vs. %d",
GET_SIT_VBLOCKS(raw_sit), valid_blocks);
set_sbi_flag(sbi, SBI_NEED_FSCK);
return -EINVAL;
}
#endif
/* check segment usage, and check boundary of a given segment number */
if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
|| segno > TOTAL_SEGS(sbi) - 1)) {
f2fs_msg(sbi->sb, KERN_ERR,
"Wrong valid blocks %d or segno %u",
GET_SIT_VBLOCKS(raw_sit), segno);
set_sbi_flag(sbi, SBI_NEED_FSCK);
return -EINVAL;
}
return 0;
}
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
unsigned int start)
{
struct sit_info *sit_i = SIT_I(sbi);
unsigned int offset = SIT_BLOCK_OFFSET(start);
block_t blk_addr = sit_i->sit_base_addr + offset;
check_seg_range(sbi, start);
#ifdef CONFIG_F2FS_CHECK_FS
if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
f2fs_bug_on(sbi, 1);
#endif
/* calculate sit block address */
if (f2fs_test_bit(offset, sit_i->sit_bitmap))
blk_addr += sit_i->sit_blocks;
return blk_addr;
}
static inline pgoff_t next_sit_addr(struct f2fs_sb_info *sbi,
pgoff_t block_addr)
{
struct sit_info *sit_i = SIT_I(sbi);
block_addr -= sit_i->sit_base_addr;
if (block_addr < sit_i->sit_blocks)
block_addr += sit_i->sit_blocks;
else
block_addr -= sit_i->sit_blocks;
return block_addr + sit_i->sit_base_addr;
}
static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
{
unsigned int block_off = SIT_BLOCK_OFFSET(start);
f2fs_change_bit(block_off, sit_i->sit_bitmap);
#ifdef CONFIG_F2FS_CHECK_FS
f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
#endif
}
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
{
struct sit_info *sit_i = SIT_I(sbi);
time64_t now = ktime_get_real_seconds();
return sit_i->elapsed_time + now - sit_i->mounted_time;
}
static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
unsigned int ofs_in_node, unsigned char version)
{
sum->nid = cpu_to_le32(nid);
sum->ofs_in_node = cpu_to_le16(ofs_in_node);
sum->version = version;
}
static inline block_t start_sum_block(struct f2fs_sb_info *sbi)
{
return __start_cp_addr(sbi) +
le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
}
static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
{
return __start_cp_addr(sbi) +
le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_total_block_count)
- (base + 1) + type;
}
static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
unsigned int secno)
{
if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >
sbi->fggc_threshold)
return true;
return false;
}
static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
{
if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
return true;
return false;
}
/*
* It is very important to gather dirty pages and write at once, so that we can
* submit a big bio without interfering other data writes.
* By default, 512 pages for directory data,
* 512 pages (2MB) * 8 for nodes, and
* 256 pages * 8 for meta are set.
*/
static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
{
if (sbi->sb->s_bdi->wb.dirty_exceeded)
return 0;
if (type == DATA)
return sbi->blocks_per_seg;
else if (type == NODE)
return 8 * sbi->blocks_per_seg;
else if (type == META)
return 8 * BIO_MAX_PAGES;
else
return 0;
}
/*
* When writing pages, it'd better align nr_to_write for segment size.
*/
static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
struct writeback_control *wbc)
{
long nr_to_write, desired;
if (wbc->sync_mode != WB_SYNC_NONE)
return 0;
nr_to_write = wbc->nr_to_write;
desired = BIO_MAX_PAGES;
if (type == NODE)
desired <<= 1;
wbc->nr_to_write = desired;
return desired - nr_to_write;
}
static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
bool wakeup = false;
int i;
if (force)
goto wake_up;
mutex_lock(&dcc->cmd_lock);
for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
if (i + 1 < dcc->discard_granularity)
break;
if (!list_empty(&dcc->pend_list[i])) {
wakeup = true;
break;
}
}
mutex_unlock(&dcc->cmd_lock);
if (!wakeup)
return;
wake_up:
dcc->discard_wake = 1;
wake_up_interruptible_all(&dcc->discard_wait_queue);
}