mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-11 21:14:07 +08:00
5cdd4c0468
In this round, we've added new features such as disk quota and statx, and modified internal bio management flow to merge more IOs depending on block types. We've also made internal threads freezeable for Android battery life. In addition to them, there are some patches to avoid lock contention as well as a couple of deadlock conditions. = Enhancement - support usrquota, grpquota, and statx - manage DATA/NODE typed bios separately to serialize more IOs - modify f2fs_lock_op/wio_mutex to avoid lock contention - prevent lock contention in migratepage = Bug fix - miss to load written inode flag - fix worst case victim selection in GC - freezeable GC and discard threads for Android battery life - sanitize f2fs metadata to deal with security hole - clean up sysfs-related code and docs -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEE00UqedjCtOrGVvQiQBSofoJIUNIFAllj6fMACgkQQBSofoJI UNJ6Ng/+PqdGV/b6KroYIXI/scFx/1t87/0W+rY9tyLr1jX7nIHn9KLPjeDdvdlk 5vEeZ/dGfW8wSI+ESzscvKberG2QlOPwJRyTB4jWR+bLatwzg7YjEblz+RX4/wfJ jKjnR7M//gRdhHdqA0xXrqguAjPbcEDK2RiVbhioMjWbZ/77j0IjcRokjMYdEf0m cJc2oMXFtlo+DJ1h9/8BmwQPTI9FfVdgbkPFTTJzV0ydQnBdxcAigrzwYZhPOVv0 n2M1dKOiQewB4OADMuepZLFqJheItlgG9wlvEjGq7zTd5epHXRIqhM6h9GikQVb9 YKAkajlKfWcwEXaEcVXtsMHC9x69Yf8xxOSQ1VrhypSUNbaynC9LDsErJx6yrF3P XC5baiqXsd/btg7tfrHJjk3gI+ck97d6TrTfUVR91X+1Tpkz7cyB226WxFKbyOG3 EYCFVMbrIN2CaHHt1xWIT2zCfX5w9ycp8kFjY6jPi0OOZrKXpFw+1AwwTu9kn4xJ iuUc8pmc0/FyPqokmLef4Qp/RRM83+f+nzW/y//lkEf3nMn6qlHzNI1RAxXnBvGV DMXzuJDcJcHGcSDr7mWyKkm6gYcak/E4DdQLQqJ6VCt6KCdCEXP/XDlig5ey5ODY uGEr1QhXIpiYAON45HUi3gmytB3J3ZdzzpsG1PEco4+hjSuFhyE= =N4GZ -----END PGP SIGNATURE----- Merge tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs Pull f2fs updates from Jaegeuk Kim: "In this round, we've added new features such as disk quota and statx, and modified internal bio management flow to merge more IOs depending on block types. We've also made internal threads freezeable for Android battery life. In addition to them, there are some patches to avoid lock contention as well as a couple of deadlock conditions. Enhancements: - support usrquota, grpquota, and statx - manage DATA/NODE typed bios separately to serialize more IOs - modify f2fs_lock_op/wio_mutex to avoid lock contention - prevent lock contention in migratepage Bug fixes: - fix missing load of written inode flag - fix worst case victim selection in GC - freezeable GC and discard threads for Android battery life - sanitize f2fs metadata to deal with security hole - clean up sysfs-related code and docs" * tag 'for-f2fs-4.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (59 commits) f2fs: support plain user/group quota f2fs: avoid deadlock caused by lock order of page and lock_op f2fs: use spin_{,un}lock_irq{save,restore} f2fs: relax migratepage for atomic written page f2fs: don't count inode block in in-memory inode.i_blocks Revert "f2fs: fix to clean previous mount option when remount_fs" f2fs: do not set LOST_PINO for renamed dir f2fs: do not set LOST_PINO for newly created dir f2fs: skip ->writepages for {mete,node}_inode during recovery f2fs: introduce __check_sit_bitmap f2fs: stop gc/discard thread in prior during umount f2fs: introduce reserved_blocks in sysfs f2fs: avoid redundant f2fs_flush after remount f2fs: report # of free inodes more precisely f2fs: add ioctl to do gc with target block address f2fs: don't need to check encrypted inode for partial truncation f2fs: measure inode.i_blocks as generic filesystem f2fs: set CP_TRIMMED_FLAG correctly f2fs: require key for truncate(2) of encrypted file f2fs: move sysfs code from super.c to fs/f2fs/sysfs.c ...
802 lines
24 KiB
C
802 lines
24 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)->main_blkaddr)
|
|
#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
|
|
|
|
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
|
|
#define MAIN_SECS(sbi) ((sbi)->total_sections)
|
|
|
|
#define TOTAL_SEGS(sbi) (SM_I(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 mutex 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);
|
|
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
|
|
se->ckpt_valid_blocks = se->valid_blocks;
|
|
rs->mtime = cpu_to_le64(se->mtime);
|
|
}
|
|
|
|
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 overprovision_sections(struct f2fs_sb_info *sbi)
|
|
{
|
|
return GET_SEC_FROM_SEG(sbi, (unsigned int)overprovision_segments(sbi));
|
|
}
|
|
|
|
static inline int reserved_sections(struct f2fs_sb_info *sbi)
|
|
{
|
|
return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
|
|
}
|
|
|
|
static inline bool need_SSR(struct f2fs_sb_info *sbi)
|
|
{
|
|
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 (test_opt(sbi, LFS))
|
|
return false;
|
|
|
|
return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
|
|
2 * reserved_sections(sbi));
|
|
}
|
|
|
|
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;
|
|
|
|
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
|
|
|
|
enum {
|
|
F2FS_IPU_FORCE,
|
|
F2FS_IPU_SSR,
|
|
F2FS_IPU_UTIL,
|
|
F2FS_IPU_SSR_UTIL,
|
|
F2FS_IPU_FSYNC,
|
|
F2FS_IPU_ASYNC,
|
|
};
|
|
|
|
static inline bool need_inplace_update_policy(struct inode *inode,
|
|
struct f2fs_io_info *fio)
|
|
{
|
|
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
|
|
unsigned int policy = SM_I(sbi)->ipu_policy;
|
|
|
|
if (test_opt(sbi, LFS))
|
|
return false;
|
|
|
|
if (policy & (0x1 << F2FS_IPU_FORCE))
|
|
return true;
|
|
if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
|
|
return true;
|
|
if (policy & (0x1 << F2FS_IPU_UTIL) &&
|
|
utilization(sbi) > SM_I(sbi)->min_ipu_util)
|
|
return true;
|
|
if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) &&
|
|
utilization(sbi) > SM_I(sbi)->min_ipu_util)
|
|
return true;
|
|
|
|
/*
|
|
* IPU for rewrite async pages
|
|
*/
|
|
if (policy & (0x1 << F2FS_IPU_ASYNC) &&
|
|
fio && fio->op == REQ_OP_WRITE &&
|
|
!(fio->op_flags & REQ_SYNC) &&
|
|
!f2fs_encrypted_inode(inode))
|
|
return true;
|
|
|
|
/* this is only set during fdatasync */
|
|
if (policy & (0x1 << F2FS_IPU_FSYNC) &&
|
|
is_inode_flag_set(inode, FI_NEED_IPU))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
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_sb_info *sbi, block_t blk_addr)
|
|
{
|
|
BUG_ON(blk_addr < SEG0_BLKADDR(sbi)
|
|
|| blk_addr >= MAX_BLKADDR(sbi));
|
|
}
|
|
|
|
/*
|
|
* Summary block is always treated as an invalid block
|
|
*/
|
|
static inline void 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);
|
|
BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
|
|
#endif
|
|
/* check segment usage, and check boundary of a given segment number */
|
|
f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
|
|
|| segno > TOTAL_SEGS(sbi) - 1);
|
|
}
|
|
|
|
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;
|
|
}
|