linux_dsm_epyc7002/fs/f2fs/f2fs.h

2629 lines
80 KiB
C
Raw Normal View History

/*
* fs/f2fs/f2fs.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.
*/
#ifndef _LINUX_F2FS_H
#define _LINUX_F2FS_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/vmalloc.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#ifdef CONFIG_F2FS_FS_ENCRYPTION
#include <linux/fscrypt_supp.h>
#else
#include <linux/fscrypt_notsupp.h>
#endif
#include <crypto/hash.h>
#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
#else
#define f2fs_bug_on(sbi, condition) \
do { \
if (unlikely(condition)) { \
WARN_ON(1); \
set_sbi_flag(sbi, SBI_NEED_FSCK); \
} \
} while (0)
#endif
#ifdef CONFIG_F2FS_FAULT_INJECTION
enum {
FAULT_KMALLOC,
FAULT_PAGE_ALLOC,
FAULT_ALLOC_NID,
FAULT_ORPHAN,
FAULT_BLOCK,
FAULT_DIR_DEPTH,
FAULT_EVICT_INODE,
FAULT_TRUNCATE,
FAULT_IO,
FAULT_CHECKPOINT,
FAULT_MAX,
};
struct f2fs_fault_info {
atomic_t inject_ops;
unsigned int inject_rate;
unsigned int inject_type;
};
extern char *fault_name[FAULT_MAX];
#define IS_FAULT_SET(fi, type) (fi->inject_type & (1 << (type)))
#endif
/*
* For mount options
*/
#define F2FS_MOUNT_BG_GC 0x00000001
#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000002
#define F2FS_MOUNT_DISCARD 0x00000004
#define F2FS_MOUNT_NOHEAP 0x00000008
#define F2FS_MOUNT_XATTR_USER 0x00000010
#define F2FS_MOUNT_POSIX_ACL 0x00000020
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040
#define F2FS_MOUNT_INLINE_XATTR 0x00000080
#define F2FS_MOUNT_INLINE_DATA 0x00000100
#define F2FS_MOUNT_INLINE_DENTRY 0x00000200
#define F2FS_MOUNT_FLUSH_MERGE 0x00000400
#define F2FS_MOUNT_NOBARRIER 0x00000800
#define F2FS_MOUNT_FASTBOOT 0x00001000
#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
#define F2FS_MOUNT_FORCE_FG_GC 0x00004000
#define F2FS_MOUNT_DATA_FLUSH 0x00008000
#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
#define F2FS_MOUNT_ADAPTIVE 0x00020000
#define F2FS_MOUNT_LFS 0x00040000
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
#define test_opt(sbi, option) (sbi->mount_opt.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;
struct f2fs_mount_info {
unsigned int opt;
};
#define F2FS_FEATURE_ENCRYPT 0x0001
#define F2FS_FEATURE_BLKZONED 0x0002
#define F2FS_HAS_FEATURE(sb, mask) \
((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
#define F2FS_SET_FEATURE(sb, mask) \
(F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask))
#define F2FS_CLEAR_FEATURE(sb, mask) \
(F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
/*
* For checkpoint manager
*/
enum {
NAT_BITMAP,
SIT_BITMAP
};
enum {
CP_UMOUNT,
CP_FASTBOOT,
CP_SYNC,
CP_RECOVERY,
CP_DISCARD,
};
#define DEF_BATCHED_TRIM_SECTIONS 2048
#define BATCHED_TRIM_SEGMENTS(sbi) \
(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
#define BATCHED_TRIM_BLOCKS(sbi) \
(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
#define MAX_DISCARD_BLOCKS(sbi) \
((1 << (sbi)->log_blocks_per_seg) * (sbi)->segs_per_sec)
#define DISCARD_ISSUE_RATE 8
#define DEF_CP_INTERVAL 60 /* 60 secs */
#define DEF_IDLE_INTERVAL 5 /* 5 secs */
struct cp_control {
int reason;
__u64 trim_start;
__u64 trim_end;
__u64 trim_minlen;
__u64 trimmed;
};
/*
* For CP/NAT/SIT/SSA readahead
*/
enum {
META_CP,
META_NAT,
META_SIT,
META_SSA,
META_POR,
};
/* for the list of ino */
enum {
ORPHAN_INO, /* for orphan ino list */
APPEND_INO, /* for append ino list */
UPDATE_INO, /* for update ino list */
MAX_INO_ENTRY, /* max. list */
};
struct ino_entry {
struct list_head list; /* list head */
nid_t ino; /* inode number */
};
/* for the list of inodes to be GCed */
struct inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
};
/* for the list of blockaddresses to be discarded */
struct discard_entry {
struct list_head list; /* list head */
block_t blkaddr; /* block address to be discarded */
int len; /* # of consecutive blocks of the discard */
};
enum {
D_PREP,
D_SUBMIT,
D_DONE,
};
struct discard_cmd {
struct list_head list; /* command list */
struct completion wait; /* compleation */
struct block_device *bdev; /* bdev */
block_t lstart; /* logical start address */
block_t start; /* actual start address in dev */
block_t len; /* length */
int state; /* state */
int error; /* bio error */
};
struct discard_cmd_control {
struct task_struct *f2fs_issue_discard; /* discard thread */
struct list_head discard_entry_list; /* 4KB discard entry list */
int nr_discards; /* # of discards in the list */
struct list_head discard_cmd_list; /* discard cmd list */
wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */
struct mutex cmd_lock;
int max_discards; /* max. discards to be issued */
atomic_t submit_discard; /* # of issued discard */
};
/* 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)
f2fs: refactor flush_sit_entries codes for reducing SIT writes In commit aec71382c681 ("f2fs: refactor flush_nat_entries codes for reducing NAT writes"), we descripte the issue as below: "Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time." Actually, we have the same problem in using SIT journal area. In this patch, firstly we will update sit journal with dirty entries as many as possible. Secondly if there is no space in sit journal, we will remove all entries in journal and walk through the whole dirty entry bitmap of sit, accounting dirty sit entries located in same SIT block to sit entry set. All entry sets are linked to list sit_entry_set in sm_info, sorted ascending order by count of entries in set. Later we flush entries in set which have fewest entries into journal as many as we can, and then flush dense set with merged entries to disk. In this way we can use sit journal area more effectively, also we will reduce SIT update, result in gaining in performance and saving lifetime of flash device. In my testing environment, it shows this patch can help to reduce SIT block update obviously. virtual machine + hard disk: fsstress -p 20 -n 400 -l 5 sit page num cp count sit pages/cp based 2006.50 1349.75 1.486 patched 1566.25 1463.25 1.070 Our latency of merging op is small when handling a great number of dirty SIT entries in flush_sit_entries: latency(ns) dirty sit count 36038 2151 49168 2123 37174 2232 Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-04 17:13:01 +07:00
{
if (type == NAT_JOURNAL)
return size <= MAX_NAT_JENTRIES(journal);
return size <= MAX_SIT_JENTRIES(journal);
f2fs: refactor flush_sit_entries codes for reducing SIT writes In commit aec71382c681 ("f2fs: refactor flush_nat_entries codes for reducing NAT writes"), we descripte the issue as below: "Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time." Actually, we have the same problem in using SIT journal area. In this patch, firstly we will update sit journal with dirty entries as many as possible. Secondly if there is no space in sit journal, we will remove all entries in journal and walk through the whole dirty entry bitmap of sit, accounting dirty sit entries located in same SIT block to sit entry set. All entry sets are linked to list sit_entry_set in sm_info, sorted ascending order by count of entries in set. Later we flush entries in set which have fewest entries into journal as many as we can, and then flush dense set with merged entries to disk. In this way we can use sit journal area more effectively, also we will reduce SIT update, result in gaining in performance and saving lifetime of flash device. In my testing environment, it shows this patch can help to reduce SIT block update obviously. virtual machine + hard disk: fsstress -p 20 -n 400 -l 5 sit page num cp count sit pages/cp based 2006.50 1349.75 1.486 patched 1566.25 1463.25 1.070 Our latency of merging op is small when handling a great number of dirty SIT entries in flush_sit_entries: latency(ns) dirty sit count 36038 2151 49168 2123 37174 2232 Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-04 17:13:01 +07:00
}
/*
* ioctl commands
*/
#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
#define F2FS_IOCTL_MAGIC 0xf5
#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
#define F2FS_IOC_GARBAGE_COLLECT _IO(F2FS_IOCTL_MAGIC, 6)
#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
#define F2FS_IOC_DEFRAGMENT _IO(F2FS_IOCTL_MAGIC, 8)
#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
struct f2fs_move_range)
#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT
/*
* should be same as XFS_IOC_GOINGDOWN.
* Flags for going down operation used by FS_IOC_GOINGDOWN
*/
#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */
#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */
#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */
#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
#endif
struct f2fs_defragment {
u64 start;
u64 len;
};
struct f2fs_move_range {
u32 dst_fd; /* destination fd */
u64 pos_in; /* start position in src_fd */
u64 pos_out; /* start position in dst_fd */
u64 len; /* size to move */
};
/*
* For INODE and NODE manager
*/
/* for directory operations */
struct f2fs_dentry_ptr {
struct inode *inode;
const void *bitmap;
struct f2fs_dir_entry *dentry;
__u8 (*filename)[F2FS_SLOT_LEN];
int max;
};
static inline void make_dentry_ptr(struct inode *inode,
struct f2fs_dentry_ptr *d, void *src, int type)
{
d->inode = inode;
if (type == 1) {
struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src;
d->max = NR_DENTRY_IN_BLOCK;
d->bitmap = &t->dentry_bitmap;
d->dentry = t->dentry;
d->filename = t->filename;
} else {
struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src;
d->max = NR_INLINE_DENTRY;
d->bitmap = &t->dentry_bitmap;
d->dentry = t->dentry;
d->filename = t->filename;
}
}
/*
* 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 F2FS_LINK_MAX 0xffffffff /* maximum link count per file */
#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
/* vector size for gang look-up from extent cache that consists of radix tree */
#define EXT_TREE_VEC_SIZE 64
/* 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 EXTENT_CACHE_SHRINK_NUMBER 128
struct extent_info {
unsigned int fofs; /* start offset in a file */
u32 blk; /* start block address of the extent */
unsigned int len; /* length of the extent */
};
struct extent_node {
struct rb_node rb_node; /* rb node located in rb-tree */
struct list_head list; /* node in global extent list of sbi */
struct extent_info ei; /* extent info */
struct extent_tree *et; /* extent tree pointer */
};
struct extent_tree {
nid_t ino; /* inode number */
struct rb_root root; /* root of extent info rb-tree */
struct extent_node *cached_en; /* recently accessed extent node */
struct extent_info largest; /* largested extent info */
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*/
};
/*
* This structure is taken from ext4_map_blocks.
*
* Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
*/
#define F2FS_MAP_NEW (1 << BH_New)
#define F2FS_MAP_MAPPED (1 << BH_Mapped)
#define F2FS_MAP_UNWRITTEN (1 << BH_Unwritten)
#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
F2FS_MAP_UNWRITTEN)
struct f2fs_map_blocks {
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 */
};
/* for flag in get_data_block */
#define F2FS_GET_BLOCK_READ 0
#define F2FS_GET_BLOCK_DIO 1
#define F2FS_GET_BLOCK_FIEMAP 2
#define F2FS_GET_BLOCK_BMAP 3
#define F2FS_GET_BLOCK_PRE_DIO 4
#define F2FS_GET_BLOCK_PRE_AIO 5
/*
* 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 file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_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_clear_encrypt(inode) clear_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 DEF_DIR_LEVEL 0
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 */
f2fs: introduce large directory support This patch introduces an i_dir_level field to support large directory. Previously, f2fs maintains multi-level hash tables to find a dentry quickly from a bunch of chiild dentries in a directory, and the hash tables consist of the following tree structure as below. In Documentation/filesystems/f2fs.txt, ---------------------- A : bucket B : block N : MAX_DIR_HASH_DEPTH ---------------------- level #0 | A(2B) | level #1 | A(2B) - A(2B) | level #2 | A(2B) - A(2B) - A(2B) - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) But, if we can guess that a directory will handle a number of child files, we don't need to traverse the tree from level #0 to #N all the time. Since the lower level tables contain relatively small number of dentries, the miss ratio of the target dentry is likely to be high. In order to avoid that, we can configure the hash tables sparsely from level #0 like this. level #0 | A(2B) - A(2B) - A(2B) - A(2B) level #1 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) With this structure, we can skip the ineffective tree searches in lower level hash tables. This patch adds just a facility for this by introducing i_dir_level in f2fs_inode. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2014-02-27 16:20:00 +07:00
unsigned char i_dir_level; /* use for dentry level for large dir */
unsigned int i_current_depth; /* use only in directory structure */
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; /* use to pass per-file flags */
struct rw_semaphore 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 */
nid_t i_xattr_nid; /* node id that contains xattrs */
loff_t last_disk_size; /* lastly written file size */
struct list_head dirty_list; /* dirty list for dirs and files */
struct list_head gdirty_list; /* linked in global dirty list */
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct mutex inmem_lock; /* lock for inmemory pages */
struct extent_tree *extent_tree; /* cached extent_tree entry */
struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
};
static inline void get_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_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 void set_extent_info(struct extent_info *ei, unsigned int fofs,
u32 blk, unsigned int len)
{
ei->fofs = fofs;
ei->blk = blk;
ei->len = len;
}
static inline bool __is_extent_mergeable(struct extent_info *back,
struct extent_info *front)
{
return (back->fofs + back->len == front->fofs &&
back->blk + back->len == front->blk);
}
static inline bool __is_back_mergeable(struct extent_info *cur,
struct extent_info *back)
{
return __is_extent_mergeable(back, cur);
}
static inline bool __is_front_mergeable(struct extent_info *cur,
struct extent_info *front)
{
return __is_extent_mergeable(cur, front);
}
extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
static inline void __try_update_largest_extent(struct inode *inode,
struct extent_tree *et, struct extent_node *en)
{
if (en->ei.len > et->largest.len) {
et->largest = en->ei;
f2fs_mark_inode_dirty_sync(inode, true);
}
}
enum nid_list {
FREE_NID_LIST,
ALLOC_NID_LIST,
MAX_NID_LIST,
};
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 */
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 rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
f2fs: refactor flush_nat_entries codes for reducing NAT writes Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time. In this patch we merge dirty entries located in same NAT block to nat entry set, and linked all set to list, sorted ascending order by entries' count of set. Later we flush entries in sparse set into journal as many as we can, and then flush merged entries to disk. In this way we can not only gain in performance, but also save lifetime of flash device. In my testing environment, it shows this patch can help to reduce NAT block writes obviously. In hard disk test case: cost time of fsstress is stablely reduced by about 5%. 1. virtual machine + hard disk: fsstress -p 20 -n 200 -l 5 node num cp count nodes/cp based 4599.6 1803.0 2.551 patched 2714.6 1829.6 1.483 2. virtual machine + 32g micro SD card: fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0 -f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5 -f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S node num cp count nodes/cp based 84.5 43.7 1.933 patched 49.2 40.0 1.23 Our latency of merging op shows not bad when handling extreme case like: merging a great number of dirty nats: latency(ns) dirty nat count 3089219 24922 5129423 27422 4000250 24523 change log from v1: o fix wrong logic in add_nat_entry when grab a new nat entry set. o swith to create slab cache in create_node_manager_caches. o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency. change log from v2: o make comment position more appropriate suggested by Jaegeuk Kim. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-24 08:18:20 +07:00
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
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 nid_list[MAX_NID_LIST];/* lists for free nids */
unsigned int nid_cnt[MAX_NID_LIST]; /* 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)[NAT_ENTRY_BITMAP_SIZE];
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_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_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 */
NO_CHECK_TYPE,
};
struct flush_cmd {
struct completion wait;
struct llist_node llnode;
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 submit_flush; /* # of issued 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 */
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 ovp_segments; /* # of overprovision segments */
/* a threshold to reclaim prefree segments */
unsigned int rec_prefree_segments;
/* for batched trimming */
unsigned int trim_sections; /* # of sections to trim */
f2fs: refactor flush_sit_entries codes for reducing SIT writes In commit aec71382c681 ("f2fs: refactor flush_nat_entries codes for reducing NAT writes"), we descripte the issue as below: "Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time." Actually, we have the same problem in using SIT journal area. In this patch, firstly we will update sit journal with dirty entries as many as possible. Secondly if there is no space in sit journal, we will remove all entries in journal and walk through the whole dirty entry bitmap of sit, accounting dirty sit entries located in same SIT block to sit entry set. All entry sets are linked to list sit_entry_set in sm_info, sorted ascending order by count of entries in set. Later we flush entries in set which have fewest entries into journal as many as we can, and then flush dense set with merged entries to disk. In this way we can use sit journal area more effectively, also we will reduce SIT update, result in gaining in performance and saving lifetime of flash device. In my testing environment, it shows this patch can help to reduce SIT block update obviously. virtual machine + hard disk: fsstress -p 20 -n 400 -l 5 sit page num cp count sit pages/cp based 2006.50 1349.75 1.486 patched 1566.25 1463.25 1.070 Our latency of merging op is small when handling a great number of dirty SIT entries in flush_sit_entries: latency(ns) dirty sit count 36038 2151 49168 2123 37174 2232 Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-04 17:13:01 +07:00
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 */
/* 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) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
enum count_type {
F2FS_DIRTY_DENTS,
F2FS_DIRTY_DATA,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
F2FS_INMEM_PAGES,
F2FS_DIRTY_IMETA,
F2FS_WB_CP_DATA,
F2FS_WB_DATA,
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))
enum page_type {
DATA,
NODE,
META,
NR_PAGE_TYPE,
META_FLUSH,
INMEM, /* the below types are used by tracepoints only. */
INMEM_DROP,
f2fs: fix stale ATOMIC_WRITTEN_PAGE private pointer When I forced to enable atomic operations intentionally, I could hit the below panic, since we didn't clear page->private in f2fs_invalidate_page called by file truncation. The panic occurs due to NULL mapping having page->private. BUG: unable to handle kernel paging request at ffffffffffffffff IP: drop_buffers+0x38/0xe0 PGD 5d00c067 PUD 5d00e067 PMD 0 CPU: 3 PID: 1648 Comm: fsstress Tainted: G D OE 4.10.0+ #5 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 task: ffff9151952863c0 task.stack: ffffaaec40db4000 RIP: 0010:drop_buffers+0x38/0xe0 RSP: 0018:ffffaaec40db74c8 EFLAGS: 00010292 Call Trace: ? page_referenced+0x8b/0x170 try_to_free_buffers+0xc5/0xe0 try_to_release_page+0x49/0x50 shrink_page_list+0x8bc/0x9f0 shrink_inactive_list+0x1dd/0x500 ? shrink_active_list+0x2c0/0x430 shrink_node_memcg+0x5eb/0x7c0 shrink_node+0xe1/0x320 do_try_to_free_pages+0xef/0x2e0 try_to_free_pages+0xe9/0x190 __alloc_pages_slowpath+0x390/0xe70 __alloc_pages_nodemask+0x291/0x2b0 alloc_pages_current+0x95/0x140 __page_cache_alloc+0xc4/0xe0 pagecache_get_page+0xab/0x2a0 grab_cache_page_write_begin+0x20/0x40 get_read_data_page+0x2e6/0x4c0 [f2fs] ? f2fs_mark_inode_dirty_sync+0x16/0x30 [f2fs] ? truncate_data_blocks_range+0x238/0x2b0 [f2fs] get_lock_data_page+0x30/0x190 [f2fs] __exchange_data_block+0xaaf/0xf40 [f2fs] f2fs_fallocate+0x418/0xd00 [f2fs] vfs_fallocate+0x157/0x220 SyS_fallocate+0x48/0x80 Signed-off-by: Yunlei He <heyunlei@huawei.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> [Chao Yu: use INMEM_INVALIDATE for better tracing] Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-03-17 08:55:52 +07:00
INMEM_INVALIDATE,
INMEM_REVOKE,
IPU,
OPU,
};
struct f2fs_io_info {
struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
int op; /* contains REQ_OP_ */
int 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 */
bool submitted; /* indicate IO submission */
};
#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. */
struct rw_semaphore io_rwsem; /* blocking op for bio */
};
#define FDEV(i) (sbi->devs[i])
#define RDEV(i) (raw_super->devs[i])
struct f2fs_dev_info {
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 */
u8 *blkz_type; /* Array of zones type */
#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 s_flag in struct f2fs_sb_info */
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 */
};
enum {
CP_TIME,
REQ_TIME,
MAX_TIME,
};
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 */
int valid_super_block; /* valid super block no */
unsigned long s_flag; /* flags for sbi */
#ifdef CONFIG_BLK_DEV_ZONED
unsigned int blocks_per_blkz; /* F2FS blocks per zone */
unsigned int log_blocks_per_blkz; /* log2 F2FS blocks per zone */
#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 read_io; /* for read bios */
struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */
struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */
int write_io_size_bits; /* Write IO size bits */
mempool_t *write_io_dummy; /* Dummy pages */
/* 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 */
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 14:21:29 +07:00
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
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 inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
/* 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 */
/* for extent tree cache */
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 */
/* 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 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 */
loff_t max_file_blocks; /* max block index of file */
int active_logs; /* # of active logs */
int dir_level; /* directory level */
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 */
u32 s_next_generation; /* for NFS support */
/* # of pages, see count_type */
atomic_t nr_pages[NR_COUNT_TYPE];
/* # of allocated blocks */
struct percpu_counter alloc_valid_block_count;
/* valid inode count */
struct percpu_counter total_valid_inode_count;
struct f2fs_mount_info mount_opt; /* mount options */
/* for cleaning operations */
struct mutex gc_mutex; /* mutex for GC */
struct f2fs_gc_kthread *gc_thread; /* GC thread */
unsigned int cur_victim_sec; /* current victim section num */
/* threshold for converting bg victims for fg */
u64 fggc_threshold;
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
/*
* 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 */
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
atomic_t inplace_count; /* # of inplace update */
atomic64_t total_hit_ext; /* # of lookup extent cache */
atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */
atomic64_t read_hit_largest; /* # of hit largest extent node */
atomic64_t read_hit_cached; /* # of hit cached extent node */
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 aw_cnt; /* # of atomic writes */
atomic_t max_aw_cnt; /* max # of atomic writes */
int bg_gc; /* background gc calls */
unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */
#endif
unsigned int last_victim[2]; /* last victim segment # */
spinlock_t stat_lock; /* lock for stat operations */
/* For sysfs suppport */
struct kobject s_kobj;
struct completion s_kobj_unregister;
/* For shrinker support */
struct list_head s_list;
int s_ndevs; /* number of devices */
struct f2fs_dev_info *devs; /* for device list */
struct mutex umount_mutex;
unsigned int shrinker_run_no;
/* For write statistics */
u64 sectors_written_start;
u64 kbytes_written;
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
/* For fault injection */
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct f2fs_fault_info fault_info;
#endif
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
#define f2fs_show_injection_info(type) \
printk("%sF2FS-fs : inject %s in %s of %pF\n", \
KERN_INFO, fault_name[type], \
__func__, __builtin_return_address(0))
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
struct f2fs_fault_info *ffi = &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);
return true;
}
return false;
}
#endif
/* For write statistics. Suppose sector size is 512 bytes,
* and the return value is in kbytes. s is of struct f2fs_sb_info.
*/
#define BD_PART_WRITTEN(s) \
(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) - \
s->sectors_written_start) >> 1)
static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
{
sbi->last_time[type] = jiffies;
}
static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
{
struct timespec ts = {sbi->interval_time[type], 0};
unsigned long interval = timespec_to_jiffies(&ts);
return time_after(jiffies, sbi->last_time[type] + interval);
}
static inline bool is_idle(struct f2fs_sb_info *sbi)
{
struct block_device *bdev = sbi->sb->s_bdev;
struct request_queue *q = bdev_get_queue(bdev);
struct request_list *rl = &q->root_rl;
if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC])
return 0;
return f2fs_time_over(sbi, REQ_TIME);
}
/*
* Inline functions
*/
static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
unsigned int length)
{
SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
u32 *ctx = (u32 *)shash_desc_ctx(shash);
int err;
shash->tfm = sbi->s_chksum_driver;
shash->flags = 0;
*ctx = F2FS_SUPER_MAGIC;
err = crypto_shash_update(shash, address, length);
BUG_ON(err);
return *ctx;
}
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 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->mapping);
}
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 __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)
{
spin_lock(&sbi->cp_lock);
__set_ckpt_flags(F2FS_CKPT(sbi), f);
spin_unlock(&sbi->cp_lock);
}
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)
{
spin_lock(&sbi->cp_lock);
__clear_ckpt_flags(F2FS_CKPT(sbi), f);
spin_unlock(&sbi->cp_lock);
}
static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
{
set_sbi_flag(sbi, SBI_NEED_FSCK);
if (lock)
spin_lock(&sbi->cp_lock);
__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
kfree(NM_I(sbi)->nat_bits);
NM_I(sbi)->nat_bits = NULL;
if (lock)
spin_unlock(&sbi->cp_lock);
}
static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
struct cp_control *cpc)
{
bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
return (cpc) ? (cpc->reason == CP_UMOUNT) && set : set;
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 17:08:30 +07:00
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 14:21:29 +07:00
{
down_read(&sbi->cp_rwsem);
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 14:21:29 +07:00
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 17:08:30 +07:00
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
up_read(&sbi->cp_rwsem);
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 17:08:30 +07:00
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
down_write(&sbi->cp_rwsem);
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 14:21:29 +07:00
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 17:08:30 +07:00
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 14:21:29 +07:00
{
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 || reason == 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 given nid is within node id range.
*/
static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
{
if (unlikely(nid < F2FS_ROOT_INO(sbi)))
return -EINVAL;
if (unlikely(nid >= NM_I(sbi)->max_nid))
return -EINVAL;
return 0;
}
#define F2FS_DEFAULT_ALLOCATED_BLOCKS 1
/*
* Check whether the inode has blocks or not
*/
static inline int F2FS_HAS_BLOCKS(struct inode *inode)
{
if (F2FS_I(inode)->i_xattr_nid)
return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1;
else
return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS;
}
static inline bool f2fs_has_xattr_block(unsigned int ofs)
{
return ofs == XATTR_NODE_OFFSET;
}
static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
struct inode *inode, blkcnt_t *count)
{
blkcnt_t diff;
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_BLOCK)) {
f2fs_show_injection_info(FAULT_BLOCK);
return false;
}
#endif
/*
* 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);
sbi->total_valid_block_count += (block_t)(*count);
if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
diff = sbi->total_valid_block_count - sbi->user_block_count;
*count -= diff;
sbi->total_valid_block_count = sbi->user_block_count;
if (!*count) {
spin_unlock(&sbi->stat_lock);
percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
return false;
}
}
spin_unlock(&sbi->stat_lock);
f2fs_i_blocks_write(inode, *count, true);
return true;
}
static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
struct inode *inode,
blkcnt_t count)
{
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
f2fs_bug_on(sbi, inode->i_blocks < count);
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
f2fs_i_blocks_write(inode, count, false);
}
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_DATA || count_type == F2FS_INMEM_PAGES ||
count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA)
return;
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);
}
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);
}
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)
{
unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
sbi->log_blocks_per_seg;
return segs / sbi->segs_per_sec;
}
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);
int offset;
if (__cp_payload(sbi) > 0) {
if (flag == NAT_BITMAP)
return &ckpt->sit_nat_version_bitmap;
else
return (unsigned char *)ckpt + F2FS_BLKSIZE;
} else {
offset = (flag == NAT_BITMAP) ?
le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
return &ckpt->sit_nat_version_bitmap + 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 += sbi->blocks_per_seg;
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 += sbi->blocks_per_seg;
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);
}
static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
struct inode *inode)
{
block_t valid_block_count;
unsigned int valid_node_count;
spin_lock(&sbi->stat_lock);
valid_block_count = sbi->total_valid_block_count + 1;
if (unlikely(valid_block_count > sbi->user_block_count)) {
spin_unlock(&sbi->stat_lock);
return false;
}
valid_node_count = sbi->total_valid_node_count + 1;
if (unlikely(valid_node_count > sbi->total_node_count)) {
spin_unlock(&sbi->stat_lock);
return false;
}
if (inode)
f2fs_i_blocks_write(inode, 1, true);
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
percpu_counter_inc(&sbi->alloc_valid_block_count);
return true;
}
static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
struct inode *inode)
{
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, !sbi->total_valid_block_count);
f2fs_bug_on(sbi, !sbi->total_valid_node_count);
f2fs_bug_on(sbi, !inode->i_blocks);
f2fs_i_blocks_write(inode, 1, false);
sbi->total_valid_node_count--;
sbi->total_valid_block_count--;
spin_unlock(&sbi->stat_lock);
}
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)
{
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct page *page = find_lock_page(mapping, index);
if (page)
return page;
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
f2fs_show_injection_info(FAULT_PAGE_ALLOC);
return NULL;
}
#endif
if (!for_write)
return grab_cache_page(mapping, index);
return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
}
static inline void f2fs_copy_page(struct page *src, struct page *dst)
{
char *src_kaddr = kmap(src);
char *dst_kaddr = kmap(dst);
memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
kunmap(dst);
kunmap(src);
}
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);
}
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 19:29:47 +07:00
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(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 struct bio *f2fs_bio_alloc(int npages)
{
struct bio *bio;
/* No failure on bio allocation */
bio = bio_alloc(GFP_NOIO, npages);
if (!bio)
bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
return bio;
}
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 __le32 *blkaddr_in_node(struct f2fs_node *node)
{
return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}
static inline block_t datablock_addr(struct page *node_page,
unsigned int offset)
{
struct f2fs_node *raw_node;
__le32 *addr_array;
raw_node = F2FS_NODE(node_page);
addr_array = blkaddr_in_node(raw_node);
return le32_to_cpu(addr_array[offset]);
}
static inline int f2fs_test_bit(unsigned int nr, char *addr)
{
int mask;
addr += (nr >> 3);
mask = 1 << (7 - (nr & 0x07));
return mask & *addr;
}
static inline void f2fs_set_bit(unsigned int nr, char *addr)
{
int mask;
addr += (nr >> 3);
mask = 1 << (7 - (nr & 0x07));
*addr |= mask;
}
static inline void f2fs_clear_bit(unsigned int nr, char *addr)
{
int mask;
addr += (nr >> 3);
mask = 1 << (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 = 1 << (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 = 1 << (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 = 1 << (7 - (nr & 0x07));
*addr ^= mask;
}
/* 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_ATOMIC_COMMIT, /* indicate the state of atomical committing */
FI_VOLATILE_FILE, /* indicate volatile file */
FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */
FI_DROP_CACHE, /* drop dirty page cache */
FI_DATA_EXIST, /* indicate data exists */
FI_INLINE_DOTS, /* indicate inline dot dentries */
FI_DO_DEFRAG, /* indicate defragment is running */
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
FI_NO_PREALLOC, /* indicate skipped preallocated blocks */
};
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:
if (set)
return;
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
f2fs_mark_inode_dirty_sync(inode, true);
}
}
static inline void set_inode_flag(struct inode *inode, int flag)
{
if (!test_bit(flag, &F2FS_I(inode)->flags))
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)
{
if (test_bit(flag, &F2FS_I(inode)->flags))
clear_bit(flag, &F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, false);
}
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,
blkcnt_t diff, bool add)
{
bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
inode->i_blocks = add ? inode->i_blocks + diff :
inode->i_blocks - diff;
f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
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);
f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
{
F2FS_I(inode)->i_current_depth = depth;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
{
F2FS_I(inode)->i_xattr_nid = xnid;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
F2FS_I(inode)->i_pino = pino;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
if (ri->i_inline & F2FS_INLINE_XATTR)
set_bit(FI_INLINE_XATTR, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DATA)
set_bit(FI_INLINE_DATA, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DENTRY)
set_bit(FI_INLINE_DENTRY, &fi->flags);
if (ri->i_inline & F2FS_DATA_EXIST)
set_bit(FI_DATA_EXIST, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DOTS)
set_bit(FI_INLINE_DOTS, &fi->flags);
}
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
{
ri->i_inline = 0;
if (is_inode_flag_set(inode, FI_INLINE_XATTR))
ri->i_inline |= F2FS_INLINE_XATTR;
if (is_inode_flag_set(inode, FI_INLINE_DATA))
ri->i_inline |= F2FS_INLINE_DATA;
if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
ri->i_inline |= F2FS_INLINE_DENTRY;
if (is_inode_flag_set(inode, FI_DATA_EXIST))
ri->i_inline |= F2FS_DATA_EXIST;
if (is_inode_flag_set(inode, FI_INLINE_DOTS))
ri->i_inline |= F2FS_INLINE_DOTS;
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
return is_inode_flag_set(inode, FI_INLINE_XATTR);
}
static inline unsigned int addrs_per_inode(struct inode *inode)
{
if (f2fs_has_inline_xattr(inode))
return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
return DEF_ADDRS_PER_INODE;
}
static inline void *inline_xattr_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
F2FS_INLINE_XATTR_ADDRS]);
}
static inline int inline_xattr_size(struct inode *inode)
{
if (f2fs_has_inline_xattr(inode))
return F2FS_INLINE_XATTR_ADDRS << 2;
else
return 0;
}
static inline int f2fs_has_inline_data(struct inode *inode)
{
return is_inode_flag_set(inode, FI_INLINE_DATA);
}
static inline int f2fs_exist_data(struct inode *inode)
{
return is_inode_flag_set(inode, FI_DATA_EXIST);
}
static inline int f2fs_has_inline_dots(struct inode *inode)
{
return is_inode_flag_set(inode, FI_INLINE_DOTS);
}
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_ATOMIC_FILE);
}
static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
{
return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_VOLATILE_FILE);
}
static inline bool f2fs_is_first_block_written(struct inode *inode)
{
return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
}
static inline bool f2fs_is_drop_cache(struct inode *inode)
{
return is_inode_flag_set(inode, FI_DROP_CACHE);
}
static inline void *inline_data_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
return (void *)&(ri->i_addr[1]);
}
static inline int f2fs_has_inline_dentry(struct inode *inode)
{
return is_inode_flag_set(inode, FI_INLINE_DENTRY);
}
static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
{
if (!f2fs_has_inline_dentry(dir))
kunmap(page);
}
static inline int is_file(struct inode *inode, int type)
{
return F2FS_I(inode)->i_advise & type;
}
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
f2fs_mark_inode_dirty_sync(inode, true);
}
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
if (dsync) {
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
bool ret;
spin_lock(&sbi->inode_lock[DIRTY_META]);
ret = list_empty(&F2FS_I(inode)->gdirty_list);
spin_unlock(&sbi->inode_lock[DIRTY_META]);
return ret;
}
if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
file_keep_isize(inode) ||
i_size_read(inode) & PAGE_MASK)
return false;
return F2FS_I(inode)->last_disk_size == i_size_read(inode);
}
static inline int f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
}
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
}
static inline bool is_dot_dotdot(const struct qstr *str)
{
if (str->len == 1 && str->name[0] == '.')
return true;
if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
return true;
return false;
}
static inline bool f2fs_may_extent_tree(struct inode *inode)
{
if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
is_inode_flag_set(inode, FI_NO_EXTENT))
return false;
return S_ISREG(inode->i_mode);
}
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_KMALLOC)) {
f2fs_show_injection_info(FAULT_KMALLOC);
return NULL;
}
#endif
return kmalloc(size, flags);
}
static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kmalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags, PAGE_KERNEL);
return ret;
}
static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
{
void *ret;
ret = kzalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
return ret;
}
#define get_inode_mode(i) \
((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
/*
* file.c
*/
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
void truncate_data_blocks(struct dnode_of_data *dn);
int truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate(struct inode *inode);
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 23:46:22 +07:00
int f2fs_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags);
int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
/*
* inode.c
*/
void f2fs_set_inode_flags(struct inode *inode);
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
int update_inode(struct inode *inode, struct page *node_page);
int update_inode_page(struct inode *inode);
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
void f2fs_evict_inode(struct inode *inode);
void handle_failed_inode(struct inode *inode);
/*
* namei.c
*/
struct dentry *f2fs_get_parent(struct dentry *child);
/*
* dir.c
*/
void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
unsigned char get_de_type(struct f2fs_dir_entry *de);
struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
f2fs_hash_t namehash, int *max_slots,
struct f2fs_dentry_ptr *d);
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr);
void do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d);
struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
const struct qstr *new_name,
const struct qstr *orig_name, struct page *dpage);
void update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth);
int room_for_filename(const void *bitmap, int slots, int max_slots);
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page);
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
const struct qstr *child, struct page **res_page);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
struct page **page);
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
const struct qstr *name, f2fs_hash_t name_hash,
unsigned int bit_pos);
int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode);
int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
struct inode *inode, nid_t ino, umode_t mode);
int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode);
int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
bool f2fs_empty_dir(struct inode *dir);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name,
inode, inode->i_ino, inode->i_mode);
}
/*
* super.c
*/
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
extern __printf(3, 4)
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
int sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
*/
f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info);
/*
* node.c
*/
struct dnode_of_data;
struct node_info;
bool available_free_memory(struct f2fs_sb_info *sbi, int type);
int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
int truncate_inode_blocks(struct inode *inode, pgoff_t from);
int truncate_xattr_node(struct inode *inode, struct page *page);
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
int remove_inode_page(struct inode *inode);
struct page *new_inode_page(struct inode *inode);
struct page *new_node_page(struct dnode_of_data *dn,
unsigned int ofs, struct page *ipage);
void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *get_node_page_ra(struct page *parent, int start);
void move_node_page(struct page *node_page, int gc_type);
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic);
int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc);
void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
void recover_inline_xattr(struct inode *inode, struct page *page);
int recover_xattr_data(struct inode *inode, struct page *page,
block_t blkaddr);
int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum);
void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int build_node_manager(struct f2fs_sb_info *sbi);
void destroy_node_manager(struct f2fs_sb_info *sbi);
int __init create_node_manager_caches(void);
void destroy_node_manager_caches(void);
/*
* segment.c
*/
void register_inmem_page(struct inode *inode, struct page *page);
void drop_inmem_pages(struct inode *inode);
f2fs: fix stale ATOMIC_WRITTEN_PAGE private pointer When I forced to enable atomic operations intentionally, I could hit the below panic, since we didn't clear page->private in f2fs_invalidate_page called by file truncation. The panic occurs due to NULL mapping having page->private. BUG: unable to handle kernel paging request at ffffffffffffffff IP: drop_buffers+0x38/0xe0 PGD 5d00c067 PUD 5d00e067 PMD 0 CPU: 3 PID: 1648 Comm: fsstress Tainted: G D OE 4.10.0+ #5 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 task: ffff9151952863c0 task.stack: ffffaaec40db4000 RIP: 0010:drop_buffers+0x38/0xe0 RSP: 0018:ffffaaec40db74c8 EFLAGS: 00010292 Call Trace: ? page_referenced+0x8b/0x170 try_to_free_buffers+0xc5/0xe0 try_to_release_page+0x49/0x50 shrink_page_list+0x8bc/0x9f0 shrink_inactive_list+0x1dd/0x500 ? shrink_active_list+0x2c0/0x430 shrink_node_memcg+0x5eb/0x7c0 shrink_node+0xe1/0x320 do_try_to_free_pages+0xef/0x2e0 try_to_free_pages+0xe9/0x190 __alloc_pages_slowpath+0x390/0xe70 __alloc_pages_nodemask+0x291/0x2b0 alloc_pages_current+0x95/0x140 __page_cache_alloc+0xc4/0xe0 pagecache_get_page+0xab/0x2a0 grab_cache_page_write_begin+0x20/0x40 get_read_data_page+0x2e6/0x4c0 [f2fs] ? f2fs_mark_inode_dirty_sync+0x16/0x30 [f2fs] ? truncate_data_blocks_range+0x238/0x2b0 [f2fs] get_lock_data_page+0x30/0x190 [f2fs] __exchange_data_block+0xaaf/0xf40 [f2fs] f2fs_fallocate+0x418/0xd00 [f2fs] vfs_fallocate+0x157/0x220 SyS_fallocate+0x48/0x80 Signed-off-by: Yunlei He <heyunlei@huawei.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> [Chao Yu: use INMEM_INVALIDATE for better tracing] Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-03-17 08:55:52 +07:00
void drop_inmem_page(struct inode *inode, struct page *page);
int commit_inmem_pages(struct inode *inode);
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
int f2fs_issue_flush(struct f2fs_sb_info *sbi);
int create_flush_cmd_control(struct f2fs_sb_info *sbi);
void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr);
void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void release_discard_addrs(struct f2fs_sb_info *sbi);
int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
void allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page);
void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
void rewrite_data_page(struct f2fs_io_info *fio);
void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
block_t old_blkaddr, block_t new_blkaddr,
bool recover_curseg, bool recover_newaddr);
void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
block_t old_addr, block_t new_addr,
unsigned char version, bool recover_curseg,
bool recover_newaddr);
void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered);
void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
block_t blkaddr);
void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int build_segment_manager(struct f2fs_sb_info *sbi);
void destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init create_segment_manager_caches(void);
void destroy_segment_manager_caches(void);
/*
* checkpoint.c
*/
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync);
void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write);
void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
int acquire_orphan_inode(struct f2fs_sb_info *sbi);
void release_orphan_inode(struct f2fs_sb_info *sbi);
void add_orphan_inode(struct inode *inode);
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
int recover_orphan_inodes(struct f2fs_sb_info *sbi);
int get_valid_checkpoint(struct f2fs_sb_info *sbi);
void update_dirty_page(struct inode *inode, struct page *page);
void remove_dirty_inode(struct inode *inode);
int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
/*
* data.c
*/
void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
int rw);
void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
struct inode *inode, nid_t ino, pgoff_t idx,
enum page_type type, int rw);
void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
int f2fs_submit_page_bio(struct f2fs_io_info *fio);
int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio);
int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
void set_data_blkaddr(struct dnode_of_data *dn);
void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *find_data_page(struct inode *inode, pgoff_t index);
struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write);
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
int do_write_data_page(struct f2fs_io_info *fio);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
void f2fs_set_page_dirty_nobuffers(struct page *page);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
#ifdef CONFIG_MIGRATION
int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
struct page *page, enum migrate_mode mode);
#endif
/*
* gc.c
*/
int start_gc_thread(struct f2fs_sb_info *sbi);
void stop_gc_thread(struct f2fs_sb_info *sbi);
block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background);
void build_gc_manager(struct f2fs_sb_info *sbi);
/*
* recovery.c
*/
int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
bool space_for_roll_forward(struct f2fs_sb_info *sbi);
/*
* debug.c
*/
#ifdef CONFIG_F2FS_STAT_FS
struct f2fs_stat_info {
struct list_head stat_list;
struct f2fs_sb_info *sbi;
int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
int main_area_segs, main_area_sections, main_area_zones;
unsigned long long hit_largest, hit_cached, hit_rbtree;
unsigned long long hit_total, total_ext;
int ext_tree, zombie_tree, ext_node;
int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
int inmem_pages;
unsigned int ndirty_dirs, ndirty_files, ndirty_all;
int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;
int total_count, utilization;
int bg_gc, nr_wb_cp_data, nr_wb_data, nr_flush, nr_discard;
int inline_xattr, inline_inode, inline_dir, append, update, orphans;
int aw_cnt, max_aw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
int rsvd_segs, overp_segs;
int dirty_count, node_pages, meta_pages;
int prefree_count, call_count, cp_count, bg_cp_count;
int tot_segs, node_segs, data_segs, free_segs, free_secs;
int bg_node_segs, bg_data_segs;
int tot_blks, data_blks, node_blks;
int bg_data_blks, bg_node_blks;
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
unsigned int segment_count[2];
unsigned int block_count[2];
unsigned int inplace_count;
unsigned long long base_mem, cache_mem, page_mem;
};
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
{
return (struct f2fs_stat_info *)sbi->stat_info;
}
#define stat_inc_cp_count(si) ((si)->cp_count++)
#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++)
#define stat_inc_call_count(si) ((si)->call_count++)
#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--)
#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree))
#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest))
#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached))
#define stat_inc_inline_xattr(inode) \
do { \
if (f2fs_has_inline_xattr(inode)) \
(atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \
} while (0)
#define stat_dec_inline_xattr(inode) \
do { \
if (f2fs_has_inline_xattr(inode)) \
(atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \
} while (0)
#define stat_inc_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
(atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
#define stat_dec_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
(atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
#define stat_inc_inline_dir(inode) \
do { \
if (f2fs_has_inline_dentry(inode)) \
(atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \
} while (0)
#define stat_dec_inline_dir(inode) \
do { \
if (f2fs_has_inline_dentry(inode)) \
(atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \
} while (0)
#define stat_inc_seg_type(sbi, curseg) \
((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg) \
((sbi)->block_count[(curseg)->alloc_type]++)
#define stat_inc_inplace_blocks(sbi) \
(atomic_inc(&(sbi)->inplace_count))
#define stat_inc_atomic_write(inode) \
(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
#define stat_dec_atomic_write(inode) \
(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
#define stat_update_max_atomic_write(inode) \
do { \
int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt); \
int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \
if (cur > max) \
atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
} while (0)
#define stat_inc_seg_count(sbi, type, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
(si)->tot_segs++; \
if (type == SUM_TYPE_DATA) { \
si->data_segs++; \
si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0; \
} else { \
si->node_segs++; \
si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0; \
} \
} while (0)
#define stat_inc_tot_blk_count(si, blks) \
(si->tot_blks += (blks))
#define stat_inc_data_blk_count(sbi, blks, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->data_blks += (blks); \
si->bg_data_blks += (gc_type == BG_GC) ? (blks) : 0; \
} while (0)
#define stat_inc_node_blk_count(sbi, blks, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->node_blks += (blks); \
si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0; \
} while (0)
int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
int __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
#else
#define stat_inc_cp_count(si)
#define stat_inc_bg_cp_count(si)
#define stat_inc_call_count(si)
#define stat_inc_bggc_count(si)
#define stat_inc_dirty_inode(sbi, type)
#define stat_dec_dirty_inode(sbi, type)
#define stat_inc_total_hit(sb)
#define stat_inc_rbtree_node_hit(sb)
#define stat_inc_largest_node_hit(sbi)
#define stat_inc_cached_node_hit(sbi)
#define stat_inc_inline_xattr(inode)
#define stat_dec_inline_xattr(inode)
#define stat_inc_inline_inode(inode)
#define stat_dec_inline_inode(inode)
#define stat_inc_inline_dir(inode)
#define stat_dec_inline_dir(inode)
#define stat_inc_atomic_write(inode)
#define stat_dec_atomic_write(inode)
#define stat_update_max_atomic_write(inode)
#define stat_inc_seg_type(sbi, curseg)
#define stat_inc_block_count(sbi, curseg)
#define stat_inc_inplace_blocks(sbi)
#define stat_inc_seg_count(sbi, type, gc_type)
#define stat_inc_tot_blk_count(si, blks)
#define stat_inc_data_blk_count(sbi, blks, gc_type)
#define stat_inc_node_blk_count(sbi, blks, gc_type)
static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
static inline int __init f2fs_create_root_stats(void) { return 0; }
static inline void f2fs_destroy_root_stats(void) { }
#endif
extern const struct file_operations f2fs_dir_operations;
extern const struct file_operations f2fs_file_operations;
extern const struct inode_operations f2fs_file_inode_operations;
extern const struct address_space_operations f2fs_dblock_aops;
extern const struct address_space_operations f2fs_node_aops;
extern const struct address_space_operations f2fs_meta_aops;
extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
extern struct kmem_cache *inode_entry_slab;
/*
* inline.c
*/
bool f2fs_may_inline_data(struct inode *inode);
bool f2fs_may_inline_dentry(struct inode *inode);
void read_inline_data(struct page *page, struct page *ipage);
void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from);
int f2fs_read_inline_data(struct inode *inode, struct page *page);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
bool recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page);
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage);
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode);
bool f2fs_empty_inline_dir(struct inode *dir);
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr);
int f2fs_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
/*
* shrinker.c
*/
unsigned long f2fs_shrink_count(struct shrinker *shrink,
struct shrink_control *sc);
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc);
void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
/*
* extent_cache.c
*/
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
void f2fs_drop_extent_tree(struct inode *inode);
unsigned int f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
struct extent_info *ei);
void f2fs_update_extent_cache(struct dnode_of_data *dn);
f2fs: update extent tree in batches This patch introduce a new helper f2fs_update_extent_tree_range which can do extent mapping update at a specified range. The main idea is: 1) punch all mapping info in extent node(s) which are at a specified range; 2) try to merge new extent mapping with adjacent node, or failing that, insert the mapping into extent tree as a new node. In order to see the benefit, I add a function for stating time stamping count as below: uint64_t rdtsc(void) { uint32_t lo, hi; __asm__ __volatile__ ("rdtsc" : "=a" (lo), "=d" (hi)); return (uint64_t)hi << 32 | lo; } My test environment is: ubuntu, intel i7-3770, 16G memory, 256g micron ssd. truncation path: update extent cache from truncate_data_blocks_range non-truncataion path: update extent cache from other paths total: all update paths a) Removing 128MB file which has one extent node mapping whole range of file: 1. dd if=/dev/zero of=/mnt/f2fs/128M bs=1M count=128 2. sync 3. rm /mnt/f2fs/128M Before: total count average truncation: 7651022 32768 233.49 Patched: total count average truncation: 3321 33 100.64 b) fsstress: fsstress -d /mnt/f2fs -l 5 -n 100 -p 20 Test times: 5 times. Before: total count average truncation: 5812480.6 20911.6 277.95 non-truncation: 7783845.6 13440.8 579.12 total: 13596326.2 34352.4 395.79 Patched: total count average truncation: 1281283.0 3041.6 421.25 non-truncation: 7355844.4 13662.8 538.38 total: 8637127.4 16704.4 517.06 1) For the updates in truncation path: - we can see updating in batches leads total tsc and update count reducing explicitly; - besides, for a single batched updating, punching multiple extent nodes in a loop, result in executing more operations, so our average tsc increase intensively. 2) For the updates in non-truncation path: - there is a little improvement, that is because for the scenario that we just need to update in the head or tail of extent node, new interface optimize to update info in extent node directly, rather than removing original extent node for updating and then inserting that updated one into cache as new node. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-08-26 19:34:48 +07:00
void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
pgoff_t fofs, block_t blkaddr, unsigned int len);
void init_extent_cache_info(struct f2fs_sb_info *sbi);
int __init create_extent_cache(void);
void destroy_extent_cache(void);
/*
* crypto support
*/
static inline bool f2fs_encrypted_inode(struct inode *inode)
{
return file_is_encrypt(inode);
}
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_ENCRYPTION
file_set_encrypt(inode);
#endif
}
static inline bool f2fs_bio_encrypted(struct bio *bio)
{
return bio->bi_private != NULL;
}
static inline int f2fs_sb_has_crypto(struct super_block *sb)
{
return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
}
static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb)
{
return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED);
}
#ifdef CONFIG_BLK_DEV_ZONED
static inline int get_blkz_type(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkaddr)
{
unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
int i;
for (i = 0; i < sbi->s_ndevs; i++)
if (FDEV(i).bdev == bdev)
return FDEV(i).blkz_type[zno];
return -EINVAL;
}
#endif
static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi)
{
struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb);
}
static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
{
clear_opt(sbi, ADAPTIVE);
clear_opt(sbi, LFS);
switch (mt) {
case F2FS_MOUNT_ADAPTIVE:
set_opt(sbi, ADAPTIVE);
break;
case F2FS_MOUNT_LFS:
set_opt(sbi, LFS);
break;
}
}
static inline bool f2fs_may_encrypt(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_ENCRYPTION
umode_t mode = inode->i_mode;
return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
#else
return 0;
#endif
}
#endif