OpenCloudOS-Kernel/fs/f2fs/f2fs.h

1555 lines
47 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>
#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
#define f2fs_down_write(x, y) down_write_nest_lock(x, y)
#else
#define f2fs_bug_on(sbi, condition) \
do { \
if (unlikely(condition)) { \
WARN_ON(1); \
sbi->need_fsck = true; \
} \
} while (0)
#define f2fs_down_write(x, y) down_write(x)
#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 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 CRCPOLY_LE 0xedb88320
static inline __u32 f2fs_crc32(void *buf, size_t len)
{
unsigned char *p = (unsigned char *)buf;
__u32 crc = F2FS_SUPER_MAGIC;
int i;
while (len--) {
crc ^= *p++;
for (i = 0; i < 8; i++)
crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
}
return crc;
}
static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
{
return f2fs_crc32(buf, buf_size) == blk_crc;
}
/*
* For checkpoint manager
*/
enum {
NAT_BITMAP,
SIT_BITMAP
};
enum {
CP_UMOUNT,
CP_SYNC,
CP_DISCARD,
};
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 directory inodes */
struct dir_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 */
};
/* 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 */
block_t last_inode; /* block address locating the last inode */
};
#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats))
#define sits_in_cursum(sum) (le16_to_cpu(sum->n_sits))
#define nat_in_journal(sum, i) (sum->nat_j.entries[i].ne)
#define nid_in_journal(sum, i) (sum->nat_j.entries[i].nid)
#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se)
#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno)
#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
{
int before = nats_in_cursum(rs);
rs->n_nats = cpu_to_le16(before + i);
return before;
}
static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
{
int before = sits_in_cursum(rs);
rs->n_sits = cpu_to_le16(before + i);
return before;
}
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 18:13:01 +08:00
static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
int type)
{
if (type == NAT_JOURNAL)
return size <= MAX_NAT_JENTRIES(sum);
return size <= MAX_SIT_JENTRIES(sum);
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 18:13:01 +08:00
}
/*
* ioctl commands
*/
#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
#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)
#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
#endif
/*
* For INODE and NODE manager
*/
/*
* 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 32000 /* maximum link count per file */
#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
/* for in-memory extent cache entry */
#define F2FS_MIN_EXTENT_LEN 16 /* minimum extent length */
struct extent_info {
rwlock_t ext_lock; /* rwlock for consistency */
unsigned int fofs; /* start offset in a file */
u32 blk_addr; /* start block address of the extent */
unsigned int len; /* length of the extent */
};
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
*/
#define FADVISE_COLD_BIT 0x01
#define FADVISE_LOST_PINO_BIT 0x02
#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 17:20:00 +08:00
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 */
nid_t i_xattr_nid; /* node id that contains xattrs */
unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
struct radix_tree_root inmem_root; /* radix tree for inmem pages */
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct mutex inmem_lock; /* lock for inmemory pages */
};
static inline void get_extent_info(struct extent_info *ext,
struct f2fs_extent i_ext)
{
write_lock(&ext->ext_lock);
ext->fofs = le32_to_cpu(i_ext.fofs);
ext->blk_addr = le32_to_cpu(i_ext.blk_addr);
ext->len = le32_to_cpu(i_ext.len);
write_unlock(&ext->ext_lock);
}
static inline void set_raw_extent(struct extent_info *ext,
struct f2fs_extent *i_ext)
{
read_lock(&ext->ext_lock);
i_ext->fofs = cpu_to_le32(ext->fofs);
i_ext->blk_addr = cpu_to_le32(ext->blk_addr);
i_ext->len = cpu_to_le32(ext->len);
read_unlock(&ext->ext_lock);
}
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; /* maximum available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
unsigned int ram_thresh; /* control the memory footprint */
/* 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 */
rwlock_t 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 09:18:20 +08:00
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
/* free node ids management */
struct radix_tree_root free_nid_root;/* root of the free_nid cache */
struct list_head free_nid_list; /* a list for free nids */
spinlock_t free_nid_list_lock; /* protect free nid list */
unsigned int fcnt; /* the number of free node id */
struct mutex build_lock; /* lock for build free nids */
/* for checkpoint */
char *nat_bitmap; /* NAT bitmap pointer */
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 */
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 */
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 small discard management */
struct list_head discard_list; /* 4KB discard list */
int nr_discards; /* # of discards in the list */
int max_discards; /* max. discards to be issued */
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 18:13:01 +08:00
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 *cmd_control_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.
*/
enum count_type {
F2FS_WRITEBACK,
F2FS_DIRTY_DENTS,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
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,
};
struct f2fs_io_info {
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */
};
#define is_read_io(rw) (((rw) & 1) == 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 */
};
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
struct buffer_head *raw_super_buf; /* buffer head of raw sb */
struct f2fs_super_block *raw_super; /* raw super block pointer */
int s_dirty; /* dirty flag for checkpoint */
bool need_fsck; /* need fsck.f2fs to fix */
/* 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 completion *wait_io; /* for completion bios */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
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 15:21:29 +08:00
struct mutex cp_mutex; /* checkpoint procedure lock */
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 18:08:30 +08:00
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
struct mutex writepages; /* mutex for writepages() */
bool por_doing; /* recovery is doing or not */
wait_queue_head_t cp_wait;
/* for inode management */
struct radix_tree_root ino_root[MAX_INO_ENTRY]; /* ino entry array */
spinlock_t ino_lock[MAX_INO_ENTRY]; /* for ino entry lock */
struct list_head ino_list[MAX_INO_ENTRY]; /* inode list head */
/* for orphan inode, use 0'th array */
unsigned int n_orphans; /* # of orphan inodes */
unsigned int max_orphans; /* max orphan inodes */
/* for directory inode management */
struct list_head dir_inode_list; /* dir inode list */
spinlock_t dir_inode_lock; /* for dir inode list lock */
/* 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 */
unsigned int total_valid_inode_count; /* valid inode count */
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 alloc_valid_block_count; /* # of allocated blocks */
block_t last_valid_block_count; /* for recovery */
u32 s_next_generation; /* for NFS support */
atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */
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 */
/* 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 */
int total_hit_ext, read_hit_ext; /* extent cache hit ratio */
int inline_inode; /* # of inline_data inodes */
int bg_gc; /* background gc calls */
unsigned int n_dirty_dirs; /* # of dir 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;
};
/*
* Inline functions
*/
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 void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
{
sbi->s_dirty = 1;
}
static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
{
sbi->s_dirty = 0;
}
static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
{
return le64_to_cpu(cp->checkpoint_ver);
}
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 void set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
unsigned int 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_checkpoint *cp, unsigned int f)
{
unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
ckpt_flags &= (~f);
cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}
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 18:08:30 +08:00
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 15:21:29 +08:00
{
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 18:08:30 +08:00
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 15:21:29 +08:00
}
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 18:08:30 +08:00
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
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 18:08:30 +08:00
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 18:08:30 +08:00
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
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 15:21:29 +08:00
}
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 18:08:30 +08:00
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 15:21:29 +08:00
{
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 18:08:30 +08:00
up_write(&sbi->cp_rwsem);
}
/*
* 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 bool inc_valid_block_count(struct f2fs_sb_info *sbi,
struct inode *inode, blkcnt_t count)
{
block_t valid_block_count;
spin_lock(&sbi->stat_lock);
valid_block_count =
sbi->total_valid_block_count + (block_t)count;
if (unlikely(valid_block_count > sbi->user_block_count)) {
spin_unlock(&sbi->stat_lock);
return false;
}
inode->i_blocks += count;
sbi->total_valid_block_count = valid_block_count;
sbi->alloc_valid_block_count += (block_t)count;
spin_unlock(&sbi->stat_lock);
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);
inode->i_blocks -= count;
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
}
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
atomic_inc(&sbi->nr_pages[count_type]);
F2FS_SET_SB_DIRT(sbi);
}
static inline void inode_inc_dirty_pages(struct inode *inode)
{
atomic_inc(&F2FS_I(inode)->dirty_pages);
if (S_ISDIR(inode->i_mode))
inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
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))
return;
atomic_dec(&F2FS_I(inode)->dirty_pages);
if (S_ISDIR(inode->i_mode))
dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
}
static inline int 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 *
(1 << sbi->log_blocks_per_seg);
return ((get_pages(sbi, block_type) + pages_per_sec - 1)
>> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
}
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
return sbi->total_valid_block_count;
}
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 void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
int offset;
if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 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;
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_version = cur_cp_version(ckpt);
start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
/*
* odd numbered checkpoint should at cp segment 0
* and even segment must be at cp segment 1
*/
if (!(ckpt_version & 1))
start_addr += sbi->blocks_per_seg;
return start_addr;
}
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)
inode->i_blocks++;
sbi->alloc_valid_block_count++;
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
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);
inode->i_blocks--;
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)
{
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
sbi->total_valid_inode_count++;
spin_unlock(&sbi->stat_lock);
}
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
sbi->total_valid_inode_count--;
spin_unlock(&sbi->stat_lock);
}
static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
{
return sbi->total_valid_inode_count;
}
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);
}
page_cache_release(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;
retry:
entry = kmem_cache_alloc(cachep, flags);
if (!entry) {
cond_resched();
goto retry;
}
return entry;
}
#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 int f2fs_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_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;
}
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
FI_DIRTY_INODE, /* indicate inode is dirty or not */
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_UPDATE_DIR, /* should update inode block for consistency */
FI_DELAY_IPUT, /* used for the recovery */
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_VOLATILE_FILE, /* indicate volatile file */
};
static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
{
if (!test_bit(flag, &fi->flags))
set_bit(flag, &fi->flags);
}
static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag)
{
return test_bit(flag, &fi->flags);
}
static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag)
{
if (test_bit(flag, &fi->flags))
clear_bit(flag, &fi->flags);
}
static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode)
{
fi->i_acl_mode = mode;
set_inode_flag(fi, FI_ACL_MODE);
}
static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
{
if (is_inode_flag_set(fi, FI_ACL_MODE)) {
clear_inode_flag(fi, FI_ACL_MODE);
return 1;
}
return 0;
}
static inline void get_inline_info(struct f2fs_inode_info *fi,
struct f2fs_inode *ri)
{
if (ri->i_inline & F2FS_INLINE_XATTR)
set_inode_flag(fi, FI_INLINE_XATTR);
if (ri->i_inline & F2FS_INLINE_DATA)
set_inode_flag(fi, FI_INLINE_DATA);
if (ri->i_inline & F2FS_INLINE_DENTRY)
set_inode_flag(fi, FI_INLINE_DENTRY);
}
static inline void set_raw_inline(struct f2fs_inode_info *fi,
struct f2fs_inode *ri)
{
ri->i_inline = 0;
if (is_inode_flag_set(fi, FI_INLINE_XATTR))
ri->i_inline |= F2FS_INLINE_XATTR;
if (is_inode_flag_set(fi, FI_INLINE_DATA))
ri->i_inline |= F2FS_INLINE_DATA;
if (is_inode_flag_set(fi, FI_INLINE_DENTRY))
ri->i_inline |= F2FS_INLINE_DENTRY;
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
}
static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
{
if (f2fs_has_inline_xattr(&fi->vfs_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(F2FS_I(inode), FI_INLINE_DATA);
}
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
}
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
}
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(F2FS_I(inode), FI_INLINE_DENTRY);
}
static inline void *inline_dentry_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
return (void *)&(ri->i_addr[1]);
}
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->ckpt, CP_ERROR_FLAG);
}
static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
{
set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
sbi->sb->s_flags |= MS_RDONLY;
}
#define get_inode_mode(i) \
((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
/* get offset of first page in next direct node */
#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \
((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \
(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
/*
* file.c
*/
int f2fs_sync_file(struct file *, loff_t, loff_t, int);
void truncate_data_blocks(struct dnode_of_data *);
int truncate_blocks(struct inode *, u64, bool);
void f2fs_truncate(struct inode *);
int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
int f2fs_setattr(struct dentry *, struct iattr *);
int truncate_hole(struct inode *, pgoff_t, pgoff_t);
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-22 07:02:02 +08:00
int truncate_data_blocks_range(struct dnode_of_data *, int);
long f2fs_ioctl(struct file *, unsigned int, unsigned long);
long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
/*
* inode.c
*/
void f2fs_set_inode_flags(struct inode *);
struct inode *f2fs_iget(struct super_block *, unsigned long);
int try_to_free_nats(struct f2fs_sb_info *, int);
void update_inode(struct inode *, struct page *);
void update_inode_page(struct inode *);
int f2fs_write_inode(struct inode *, struct writeback_control *);
void f2fs_evict_inode(struct inode *);
void handle_failed_inode(struct inode *);
/*
* namei.c
*/
struct dentry *f2fs_get_parent(struct dentry *child);
/*
* dir.c
*/
extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
bool early_match_name(size_t, f2fs_hash_t, struct f2fs_dir_entry *);
void set_de_type(struct f2fs_dir_entry *, struct inode *);
struct page *init_inode_metadata(struct inode *, struct inode *,
const struct qstr *);
void update_parent_metadata(struct inode *, struct inode *, unsigned int);
void f2fs_drop_nlink(struct inode *, struct inode *, struct page *);
struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
struct page **);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
struct page *, struct inode *);
int update_dent_inode(struct inode *, const struct qstr *);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
struct inode *);
int f2fs_do_tmpfile(struct inode *, struct inode *);
int f2fs_make_empty(struct inode *, struct inode *);
bool f2fs_empty_dir(struct inode *);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name,
inode);
}
/*
* super.c
*/
int f2fs_sync_fs(struct super_block *, int);
extern __printf(3, 4)
void f2fs_msg(struct super_block *, const char *, const char *, ...);
/*
* hash.c
*/
f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
/*
* node.c
*/
struct dnode_of_data;
struct node_info;
bool available_free_memory(struct f2fs_sb_info *, int);
f2fs: fix conditions to remain recovery information in f2fs_sync_file This patch revisited whole the recovery information during the f2fs_sync_file. In this patch, there are three information to make a decision. a) IS_CHECKPOINTED, /* is it checkpointed before? */ b) HAS_FSYNCED_INODE, /* is the inode fsynced before? */ c) HAS_LAST_FSYNC, /* has the latest node fsync mark? */ And, the scenarios for our rule are based on: [Term] F: fsync_mark, D: dentry_mark 1. inode(x) | CP | inode(x) | dnode(F) 2. inode(x) | CP | inode(F) | dnode(F) 3. inode(x) | CP | dnode(F) | inode(x) | inode(F) 4. inode(x) | CP | dnode(F) | inode(F) 5. CP | inode(x) | dnode(F) | inode(DF) 6. CP | inode(DF) | dnode(F) 7. CP | dnode(F) | inode(DF) 8. CP | dnode(F) | inode(x) | inode(DF) For example, #3, the three conditions should be changed as follows. inode(x) | CP | dnode(F) | inode(x) | inode(F) a) x o o o o b) x x x x o c) x o o x o If f2fs_sync_file stops ------^, it should write inode(F) --------------^ So, the need_inode_block_update should return true, since c) get_nat_flag(e, HAS_LAST_FSYNC), is false. For example, #8, CP | alloc | dnode(F) | inode(x) | inode(DF) a) o x x x x b) x x x o c) o o x o If f2fs_sync_file stops -------^, it should write inode(DF) --------------^ Note that, the roll-forward policy should follow this rule, which means, if there are any missing blocks, we doesn't need to recover that inode. Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-16 05:50:48 +08:00
bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
bool has_fsynced_inode(struct f2fs_sb_info *, nid_t);
bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
int truncate_xattr_node(struct inode *, struct page *);
int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t);
void remove_inode_page(struct inode *);
struct page *new_inode_page(struct inode *);
struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
void ra_node_page(struct f2fs_sb_info *, nid_t);
struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_node_page_ra(struct page *, int);
void sync_inode_page(struct dnode_of_data *);
int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
bool alloc_nid(struct f2fs_sb_info *, nid_t *);
void alloc_nid_done(struct f2fs_sb_info *, nid_t);
void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
void recover_inline_xattr(struct inode *, struct page *);
void recover_xattr_data(struct inode *, struct page *, block_t);
int recover_inode_page(struct f2fs_sb_info *, struct page *);
int restore_node_summary(struct f2fs_sb_info *, unsigned int,
struct f2fs_summary_block *);
void flush_nat_entries(struct f2fs_sb_info *);
int build_node_manager(struct f2fs_sb_info *);
void destroy_node_manager(struct f2fs_sb_info *);
int __init create_node_manager_caches(void);
void destroy_node_manager_caches(void);
/*
* segment.c
*/
void register_inmem_page(struct inode *, struct page *);
void invalidate_inmem_page(struct inode *, struct page *);
void commit_inmem_pages(struct inode *, bool);
void f2fs_balance_fs(struct f2fs_sb_info *);
void f2fs_balance_fs_bg(struct f2fs_sb_info *);
int f2fs_issue_flush(struct f2fs_sb_info *);
int create_flush_cmd_control(struct f2fs_sb_info *);
void destroy_flush_cmd_control(struct f2fs_sb_info *);
void invalidate_blocks(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *);
void release_discard_addrs(struct f2fs_sb_info *);
void discard_next_dnode(struct f2fs_sb_info *, block_t);
int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *,
struct f2fs_io_info *, unsigned int, block_t, block_t *);
void write_data_page(struct page *, struct dnode_of_data *, block_t *,
struct f2fs_io_info *);
void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
void recover_data_page(struct f2fs_sb_info *, struct page *,
struct f2fs_summary *, block_t, block_t);
void allocate_data_block(struct f2fs_sb_info *, struct page *,
block_t, block_t *, struct f2fs_summary *, int);
void f2fs_wait_on_page_writeback(struct page *, enum page_type);
void write_data_summaries(struct f2fs_sb_info *, block_t);
void write_node_summaries(struct f2fs_sb_info *, block_t);
int lookup_journal_in_cursum(struct f2fs_summary_block *,
int, unsigned int, int);
void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
int build_segment_manager(struct f2fs_sb_info *);
void destroy_segment_manager(struct f2fs_sb_info *);
int __init create_segment_manager_caches(void);
void destroy_segment_manager_caches(void);
/*
* checkpoint.c
*/
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page_ra(struct f2fs_sb_info *, pgoff_t);
int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
void release_dirty_inode(struct f2fs_sb_info *);
bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
int acquire_orphan_inode(struct f2fs_sb_info *);
void release_orphan_inode(struct f2fs_sb_info *);
void add_orphan_inode(struct f2fs_sb_info *, nid_t);
void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
void recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void update_dirty_page(struct inode *, struct page *);
void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
void init_ino_entry_info(struct f2fs_sb_info *);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
/*
* data.c
*/
void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
struct f2fs_io_info *);
int reserve_new_block(struct dnode_of_data *);
int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
void update_extent_cache(block_t, struct dnode_of_data *);
f2fs: give a chance to merge IOs by IO scheduler Previously, background GC submits many 4KB read requests to load victim blocks and/or its (i)node blocks. ... f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb61, blkaddr = 0x3b964ed f2fs_gc : block_rq_complete: 8,16 R () 499854968 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb6f, blkaddr = 0x3b964ee f2fs_gc : block_rq_complete: 8,16 R () 499854976 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb79, blkaddr = 0x3b964ef f2fs_gc : block_rq_complete: 8,16 R () 499854984 + 8 [0] ... However, by the fact that many IOs are sequential, we can give a chance to merge the IOs by IO scheduler. In order to do that, let's use blk_plug. ... f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c6, blkaddr = 0x2e6ee f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c7, blkaddr = 0x2e6ef <idle> : block_rq_complete: 8,16 R () 1519616 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1519848 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1520432 + 96 [0] <idle> : block_rq_complete: 8,16 R () 1520536 + 104 [0] <idle> : block_rq_complete: 8,16 R () 1521008 + 112 [0] <idle> : block_rq_complete: 8,16 R () 1521440 + 152 [0] <idle> : block_rq_complete: 8,16 R () 1521688 + 144 [0] <idle> : block_rq_complete: 8,16 R () 1522128 + 192 [0] <idle> : block_rq_complete: 8,16 R () 1523256 + 328 [0] ... Note that this issue should be addressed in checkpoint, and some readahead flows too. Reviewed-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-04-24 12:19:56 +08:00
struct page *find_data_page(struct inode *, pgoff_t, bool);
struct page *get_lock_data_page(struct inode *, pgoff_t);
struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int do_write_data_page(struct page *, struct f2fs_io_info *);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
/*
* gc.c
*/
int start_gc_thread(struct f2fs_sb_info *);
void stop_gc_thread(struct f2fs_sb_info *);
block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
int f2fs_gc(struct f2fs_sb_info *);
void build_gc_manager(struct f2fs_sb_info *);
int __init create_gc_caches(void);
void destroy_gc_caches(void);
/*
* recovery.c
*/
int recover_fsync_data(struct f2fs_sb_info *);
bool space_for_roll_forward(struct f2fs_sb_info *);
/*
* 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;
int hit_ext, total_ext;
int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
int nats, sits, fnids;
int total_count, utilization;
int bg_gc, inline_inode;
unsigned int valid_count, valid_node_count, valid_inode_count;
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;
int tot_segs, node_segs, data_segs, free_segs, free_secs;
int tot_blks, data_blks, 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 base_mem, cache_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_call_count(si) ((si)->call_count++)
#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++)
#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--)
#define stat_inc_total_hit(sb) ((F2FS_SB(sb))->total_hit_ext++)
#define stat_inc_read_hit(sb) ((F2FS_SB(sb))->read_hit_ext++)
#define stat_inc_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
((F2FS_I_SB(inode))->inline_inode++); \
} while (0)
#define stat_dec_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
((F2FS_I_SB(inode))->inline_inode--); \
} 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_seg_count(sbi, type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
(si)->tot_segs++; \
if (type == SUM_TYPE_DATA) \
si->data_segs++; \
else \
si->node_segs++; \
} while (0)
#define stat_inc_tot_blk_count(si, blks) \
(si->tot_blks += (blks))
#define stat_inc_data_blk_count(sbi, blks) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->data_blks += (blks); \
} while (0)
#define stat_inc_node_blk_count(sbi, blks) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->node_blks += (blks); \
} while (0)
int f2fs_build_stats(struct f2fs_sb_info *);
void f2fs_destroy_stats(struct f2fs_sb_info *);
void __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
#else
#define stat_inc_cp_count(si)
#define stat_inc_call_count(si)
#define stat_inc_bggc_count(si)
#define stat_inc_dirty_dir(sbi)
#define stat_dec_dirty_dir(sbi)
#define stat_inc_total_hit(sb)
#define stat_inc_read_hit(sb)
#define stat_inc_inline_inode(inode)
#define stat_dec_inline_inode(inode)
#define stat_inc_seg_type(sbi, curseg)
#define stat_inc_block_count(sbi, curseg)
#define stat_inc_seg_count(si, type)
#define stat_inc_tot_blk_count(si, blks)
#define stat_inc_data_blk_count(si, blks)
#define stat_inc_node_blk_count(sbi, blks)
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 void __init f2fs_create_root_stats(void) { }
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_special_inode_operations;
/*
* inline.c
*/
bool f2fs_may_inline(struct inode *);
int f2fs_read_inline_data(struct inode *, struct page *);
int f2fs_convert_inline_data(struct inode *, pgoff_t, struct page *);
int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
void truncate_inline_data(struct inode *, u64);
bool recover_inline_data(struct inode *, struct page *);
#endif