Commit d615b541 authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'f2fs-fix-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs fixes from Jaegeuk Kim:
 "This includes major bug fixes introduced in 5.18-rc1 and 5.17+:

   - Remove obsolete whint_mode (5.18-rc1)

   - Fix IO split issue caused by op_flags change in f2fs (5.18-rc1)

   - Fix a wrong condition check to detect IO failure loop (5.18-rc1)

   - Fix wrong data truncation during roll-forward (5.17+)"

* tag 'f2fs-fix-5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs:
  f2fs: should not truncate blocks during roll-forward recovery
  f2fs: fix wrong condition check when failing metapage read
  f2fs: keep io_flags to avoid IO split due to different op_flags in two fio holders
  f2fs: remove obsolete whint_mode
parents 0fc74d82 4d8ec912
......@@ -235,12 +235,6 @@ offgrpjquota Turn off group journalled quota.
offprjjquota Turn off project journalled quota.
quota Enable plain user disk quota accounting.
noquota Disable all plain disk quota option.
whint_mode=%s Control which write hints are passed down to block
layer. This supports "off", "user-based", and
"fs-based". In "off" mode (default), f2fs does not pass
down hints. In "user-based" mode, f2fs tries to pass
down hints given by users. And in "fs-based" mode, f2fs
passes down hints with its policy.
alloc_mode=%s Adjust block allocation policy, which supports "reuse"
and "default".
fsync_mode=%s Control the policy of fsync. Currently supports "posix",
......@@ -751,70 +745,6 @@ In order to identify whether the data in the victim segment are valid or not,
F2FS manages a bitmap. Each bit represents the validity of a block, and the
bitmap is composed of a bit stream covering whole blocks in main area.
Write-hint Policy
-----------------
1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
2) whint_mode=user-based. F2FS tries to pass down hints given by
users.
===================== ======================== ===================
User F2FS Block
===================== ======================== ===================
N/A META WRITE_LIFE_NOT_SET
N/A HOT_NODE "
N/A WARM_NODE "
N/A COLD_NODE "
ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
extension list " "
-- buffered io
WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
WRITE_LIFE_NONE " "
WRITE_LIFE_MEDIUM " "
WRITE_LIFE_LONG " "
-- direct io
WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
WRITE_LIFE_NONE " WRITE_LIFE_NONE
WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
WRITE_LIFE_LONG " WRITE_LIFE_LONG
===================== ======================== ===================
3) whint_mode=fs-based. F2FS passes down hints with its policy.
===================== ======================== ===================
User F2FS Block
===================== ======================== ===================
N/A META WRITE_LIFE_MEDIUM;
N/A HOT_NODE WRITE_LIFE_NOT_SET
N/A WARM_NODE "
N/A COLD_NODE WRITE_LIFE_NONE
ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
extension list " "
-- buffered io
WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
WRITE_LIFE_NONE " "
WRITE_LIFE_MEDIUM " "
WRITE_LIFE_LONG " "
-- direct io
WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
WRITE_LIFE_NONE " WRITE_LIFE_NONE
WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
WRITE_LIFE_LONG " WRITE_LIFE_LONG
===================== ======================== ===================
Fallocate(2) Policy
-------------------
......
......@@ -98,9 +98,9 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
}
if (unlikely(!PageUptodate(page))) {
if (page->index == sbi->metapage_eio_ofs &&
sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO) {
set_ckpt_flags(sbi, CP_ERROR_FLAG);
if (page->index == sbi->metapage_eio_ofs) {
if (sbi->metapage_eio_cnt++ == MAX_RETRY_META_PAGE_EIO)
set_ckpt_flags(sbi, CP_ERROR_FLAG);
} else {
sbi->metapage_eio_ofs = page->index;
sbi->metapage_eio_cnt = 0;
......
......@@ -388,11 +388,23 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
return 0;
}
static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag)
static unsigned int f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
unsigned int fua_flag = io_flag & temp_mask;
unsigned int meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
unsigned int fua_flag, meta_flag, io_flag;
unsigned int op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
if (fio->type == DATA)
io_flag = fio->sbi->data_io_flag;
else if (fio->type == NODE)
io_flag = fio->sbi->node_io_flag;
else
return 0;
fua_flag = io_flag & temp_mask;
meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
/*
* data/node io flag bits per temp:
......@@ -401,9 +413,10 @@ static void __attach_io_flag(struct f2fs_io_info *fio, unsigned int io_flag)
* Cold | Warm | Hot | Cold | Warm | Hot |
*/
if ((1 << fio->temp) & meta_flag)
fio->op_flags |= REQ_META;
op_flags |= REQ_META;
if ((1 << fio->temp) & fua_flag)
fio->op_flags |= REQ_FUA;
op_flags |= REQ_FUA;
return op_flags;
}
static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
......@@ -413,14 +426,10 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
sector_t sector;
struct bio *bio;
if (fio->type == DATA)
__attach_io_flag(fio, sbi->data_io_flag);
else if (fio->type == NODE)
__attach_io_flag(fio, sbi->node_io_flag);
bdev = f2fs_target_device(sbi, fio->new_blkaddr, &sector);
bio = bio_alloc_bioset(bdev, npages, fio->op | fio->op_flags, GFP_NOIO,
&f2fs_bioset);
bio = bio_alloc_bioset(bdev, npages,
fio->op | fio->op_flags | f2fs_io_flags(fio),
GFP_NOIO, &f2fs_bioset);
bio->bi_iter.bi_sector = sector;
if (is_read_io(fio->op)) {
bio->bi_end_io = f2fs_read_end_io;
......
......@@ -154,7 +154,6 @@ struct f2fs_mount_info {
int s_jquota_fmt; /* Format of quota to use */
#endif
/* For which write hints are passed down to block layer */
int whint_mode;
int alloc_mode; /* segment allocation policy */
int fsync_mode; /* fsync policy */
int fs_mode; /* fs mode: LFS or ADAPTIVE */
......@@ -1333,12 +1332,6 @@ enum {
FS_MODE_FRAGMENT_BLK, /* block fragmentation mode */
};
enum {
WHINT_MODE_OFF, /* not pass down write hints */
WHINT_MODE_USER, /* try to pass down hints given by users */
WHINT_MODE_FS, /* pass down hints with F2FS policy */
};
enum {
ALLOC_MODE_DEFAULT, /* stay default */
ALLOC_MODE_REUSE, /* reuse segments as much as possible */
......@@ -3657,8 +3650,6 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp);
unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
unsigned int segno);
unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
......
......@@ -550,7 +550,8 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
}
f2fs_set_inode_flags(inode);
if (file_should_truncate(inode)) {
if (file_should_truncate(inode) &&
!is_sbi_flag_set(sbi, SBI_POR_DOING)) {
ret = f2fs_truncate(inode);
if (ret)
goto bad_inode;
......
......@@ -3243,101 +3243,6 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
}
}
/* This returns write hints for each segment type. This hints will be
* passed down to block layer. There are mapping tables which depend on
* the mount option 'whint_mode'.
*
* 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET.
*
* 2) whint_mode=user-based. F2FS tries to pass down hints given by users.
*
* User F2FS Block
* ---- ---- -----
* META WRITE_LIFE_NOT_SET
* HOT_NODE "
* WARM_NODE "
* COLD_NODE "
* ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
* extension list " "
*
* -- buffered io
* WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
* WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
* WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
* WRITE_LIFE_NONE " "
* WRITE_LIFE_MEDIUM " "
* WRITE_LIFE_LONG " "
*
* -- direct io
* WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
* WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
* WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
* WRITE_LIFE_NONE " WRITE_LIFE_NONE
* WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
* WRITE_LIFE_LONG " WRITE_LIFE_LONG
*
* 3) whint_mode=fs-based. F2FS passes down hints with its policy.
*
* User F2FS Block
* ---- ---- -----
* META WRITE_LIFE_MEDIUM;
* HOT_NODE WRITE_LIFE_NOT_SET
* WARM_NODE "
* COLD_NODE WRITE_LIFE_NONE
* ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
* extension list " "
*
* -- buffered io
* WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
* WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
* WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG
* WRITE_LIFE_NONE " "
* WRITE_LIFE_MEDIUM " "
* WRITE_LIFE_LONG " "
*
* -- direct io
* WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
* WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
* WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
* WRITE_LIFE_NONE " WRITE_LIFE_NONE
* WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
* WRITE_LIFE_LONG " WRITE_LIFE_LONG
*/
enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
enum page_type type, enum temp_type temp)
{
if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) {
if (type == DATA) {
if (temp == WARM)
return WRITE_LIFE_NOT_SET;
else if (temp == HOT)
return WRITE_LIFE_SHORT;
else if (temp == COLD)
return WRITE_LIFE_EXTREME;
} else {
return WRITE_LIFE_NOT_SET;
}
} else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) {
if (type == DATA) {
if (temp == WARM)
return WRITE_LIFE_LONG;
else if (temp == HOT)
return WRITE_LIFE_SHORT;
else if (temp == COLD)
return WRITE_LIFE_EXTREME;
} else if (type == NODE) {
if (temp == WARM || temp == HOT)
return WRITE_LIFE_NOT_SET;
else if (temp == COLD)
return WRITE_LIFE_NONE;
} else if (type == META) {
return WRITE_LIFE_MEDIUM;
}
}
return WRITE_LIFE_NOT_SET;
}
static int __get_segment_type_2(struct f2fs_io_info *fio)
{
if (fio->type == DATA)
......
......@@ -138,7 +138,6 @@ enum {
Opt_jqfmt_vfsold,
Opt_jqfmt_vfsv0,
Opt_jqfmt_vfsv1,
Opt_whint,
Opt_alloc,
Opt_fsync,
Opt_test_dummy_encryption,
......@@ -214,7 +213,6 @@ static match_table_t f2fs_tokens = {
{Opt_jqfmt_vfsold, "jqfmt=vfsold"},
{Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
{Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_whint, "whint_mode=%s"},
{Opt_alloc, "alloc_mode=%s"},
{Opt_fsync, "fsync_mode=%s"},
{Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
......@@ -975,22 +973,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
f2fs_info(sbi, "quota operations not supported");
break;
#endif
case Opt_whint:
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
if (!strcmp(name, "user-based")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER;
} else if (!strcmp(name, "off")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
} else if (!strcmp(name, "fs-based")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
} else {
kfree(name);
return -EINVAL;
}
kfree(name);
break;
case Opt_alloc:
name = match_strdup(&args[0]);
if (!name)
......@@ -1328,12 +1310,6 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
return -EINVAL;
}
/* Not pass down write hints if the number of active logs is lesser
* than NR_CURSEG_PERSIST_TYPE.
*/
if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE)
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
f2fs_err(sbi, "Allow to mount readonly mode only");
return -EROFS;
......@@ -1978,10 +1954,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",prjquota");
#endif
f2fs_show_quota_options(seq, sbi->sb);
if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER)
seq_printf(seq, ",whint_mode=%s", "user-based");
else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS)
seq_printf(seq, ",whint_mode=%s", "fs-based");
fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb);
......@@ -2033,7 +2005,6 @@ static void default_options(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).active_logs = NR_CURSEG_PERSIST_TYPE;
F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
......@@ -2314,8 +2285,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
need_stop_gc = true;
}
if (*flags & SB_RDONLY ||
F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) {
if (*flags & SB_RDONLY) {
sync_inodes_sb(sb);
set_sbi_flag(sbi, SBI_IS_DIRTY);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment