Re: [PATCH v2] f2fs: checkpoint disabling

From: Jaegeuk Kim
Date: Fri Sep 28 2018 - 13:36:10 EST

Note that, it requires "f2fs: return correct errno in f2fs_gc".

This adds a lightweight non-persistent snapshotting scheme to f2fs.

To use, mount with the option checkpoint=disable, and to return to
normal operation, remount with checkpoint=enable. If the filesystem
is shut down before remounting with checkpoint=enable, it will revert
back to its apparent state when it was first mounted with
checkpoint=disable. This is useful for situations where you wish to be
able to roll back the state of the disk in case of some critical
failure.

Signed-off-by: Daniel Rosenberg <drosen@xxxxxxxxxx>
Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
---
Change log from v1:
- fix fsync loop

Documentation/filesystems/f2fs.txt | 5 ++
fs/f2fs/checkpoint.c | 16 ++++
fs/f2fs/data.c | 14 +++-
fs/f2fs/debug.c | 3 +-
fs/f2fs/f2fs.h | 15 +++-
fs/f2fs/file.c | 12 ++-
fs/f2fs/gc.c | 9 ++-
fs/f2fs/inode.c | 6 +-
fs/f2fs/namei.c | 19 +++++
fs/f2fs/segment.c | 75 +++++++++++++++++-
fs/f2fs/segment.h | 15 ++++
fs/f2fs/super.c | 118 ++++++++++++++++++++++++++++-
include/linux/f2fs_fs.h | 1 +
13 files changed, 294 insertions(+), 14 deletions(-)

diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index bde3e91e5372..e46c2147ddf8 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -212,6 +212,11 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix",
non-atomic files likewise "nobarrier" mount option.
test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt
context. The fake fscrypt context is used by xfstests.
+checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable"
+ to reenable checkpointing. Is enabled by default. While
+ disabled, any unmounting or unexpected shutdowns will cause
+ the filesystem contents to appear as they did when the
+ filesystem was mounted with that option.

================================================================================
DEBUGFS ENTRIES
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index d312d2829d5a..01e0d8f5bbbe 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1214,6 +1214,11 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);

+ if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
+ __set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG);
+
/* set this flag to activate crc|cp_ver for recovery */
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
__clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
@@ -1421,6 +1426,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)

clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
+ sbi->unusable_block_count = 0;
__set_cp_next_pack(sbi);

/*
@@ -1445,6 +1451,16 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
unsigned long long ckpt_ver;
int err = 0;

+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ if (cpc->reason != CP_PAUSE) {
+ if (cpc->reason != CP_UMOUNT)
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Wrong disabled checkpoint!");
+ return 0;
+ }
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Start checkpoint disabled!");
+ }
mutex_lock(&sbi->cp_mutex);

if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index cb3ebcae0398..dc66c1948d8c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -537,7 +537,8 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
if (fio->in_list)
goto next;
out:
- if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN))
+ if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
+ f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
up_write(&io->io_rwsem);
}
@@ -1695,6 +1696,10 @@ static inline bool check_inplace_update_policy(struct inode *inode,
is_inode_flag_set(inode, FI_NEED_IPU))
return true;

+ if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
+ return true;
+
return false;
}

@@ -1725,6 +1730,9 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
return true;
if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
return true;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
+ return true;
}
return false;
}
@@ -2345,6 +2353,10 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,

trace_f2fs_write_begin(inode, pos, len, flags);

+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ goto fail;
+
if ((f2fs_is_atomic_file(inode) &&
!f2fs_available_free_memory(sbi, INMEM_PAGES)) ||
is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index d3c402183e3c..cb9e7679124b 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -267,7 +267,8 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
si->sbi->sb->s_bdev, i++,
f2fs_readonly(si->sbi->sb) ? "RO": "RW",
- f2fs_cp_error(si->sbi) ? "Error": "Good");
+ is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ?
+ "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good"));
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b32fd9f7da95..89ff070ee95a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -98,6 +98,7 @@ extern char *f2fs_fault_name[FAULT_MAX];
#define F2FS_MOUNT_QUOTA 0x00400000
#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000
#define F2FS_MOUNT_RESERVE_ROOT 0x01000000
+#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000

#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -176,6 +177,7 @@ enum {
#define CP_RECOVERY 0x00000008
#define CP_DISCARD 0x00000010
#define CP_TRIMMED 0x00000020
+#define CP_PAUSE 0x00000040

#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi)
#define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */
@@ -1089,6 +1091,7 @@ enum {
SBI_NEED_CP, /* need to checkpoint */
SBI_IS_SHUTDOWN, /* shutdown by ioctl */
SBI_IS_RECOVERED, /* recovered orphan/data */
+ SBI_CP_DISABLED, /* CP was disabled last mount */
};

enum {
@@ -1222,6 +1225,9 @@ struct f2fs_sb_info {
block_t reserved_blocks; /* configurable reserved blocks */
block_t current_reserved_blocks; /* current reserved blocks */

+ /* Additional tracking for no checkpoint mode */
+ block_t unusable_block_count; /* # of blocks saved by last cp */
+
unsigned int nquota_files; /* # of quota sysfile */

u32 s_next_generation; /* for NFS support */
@@ -1729,7 +1735,8 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,

if (!__allow_reserved_blocks(sbi, inode, true))
avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
-
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ avail_user_block_count -= sbi->unusable_block_count;
if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
diff = sbi->total_valid_block_count - avail_user_block_count;
if (diff > *count)
@@ -1936,6 +1943,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,

if (!__allow_reserved_blocks(sbi, inode, false))
valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ valid_block_count += sbi->unusable_block_count;

if (unlikely(valid_block_count > sbi->user_block_count)) {
spin_unlock(&sbi->stat_lock);
@@ -2939,6 +2948,7 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
+void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
@@ -3469,7 +3479,8 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
static inline bool f2fs_force_buffered_io(struct inode *inode, int rw)
{
return (f2fs_post_read_required(inode) ||
- (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
+ (rw == WRITE && (test_opt(F2FS_I_SB(inode), LFS) ||
+ is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED))) ||
F2FS_I_SB(inode)->s_ndevs);
}

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 357422a4c319..d68a1b00e3fd 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -211,7 +211,8 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
};
unsigned int seq_id = 0;

- if (unlikely(f2fs_readonly(inode->i_sb)))
+ if (unlikely(f2fs_readonly(inode->i_sb) ||
+ is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return 0;

trace_f2fs_sync_file_enter(inode);
@@ -2158,6 +2159,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;

+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Skipping Checkpoint. Checkpoints currently disabled.");
+ return -EINVAL;
+ }
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
@@ -2529,6 +2536,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
if (f2fs_readonly(sbi->sb))
return -EROFS;

+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return -EINVAL;
+
if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
sizeof(range)))
return -EFAULT;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index c051dc4ddf1a..5d2fa37472be 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -362,6 +362,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,

if (sec_usage_check(sbi, secno))
goto next;
+ /* Don't touch checkpointed data */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ get_ckpt_valid_blocks(sbi, segno)))
+ goto next;
if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
goto next;

@@ -1169,7 +1173,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
* threshold, we can make them free by checkpoint. Then, we
* secure free segments which doesn't need fggc any more.
*/
- if (prefree_segments(sbi)) {
+ if (prefree_segments(sbi) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
ret = f2fs_write_checkpoint(sbi, &cpc);
if (ret)
goto stop;
@@ -1221,7 +1226,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
segno = NULL_SEGNO;
goto gc_more;
}
- if (gc_type == FG_GC)
+ if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED))
ret = f2fs_write_checkpoint(sbi, &cpc);
}
stop:
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 86e7333d60c1..4ee9d6c4b719 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -607,6 +607,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;

+ if (f2fs_is_checkpoint_ready(sbi))
+ return -ENOSPC;
+
/*
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
@@ -688,7 +691,8 @@ void f2fs_evict_inode(struct inode *inode)
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);

- if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)))
+ if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
else
f2fs_inode_synced(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index ded185baa9ae..a14632744a6a 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -16,6 +16,7 @@

#include "f2fs.h"
#include "node.h"
+#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include <trace/events/f2fs.h>
@@ -269,6 +270,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

err = dquot_initialize(dir);
if (err)
@@ -315,6 +319,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

err = fscrypt_prepare_link(old_dentry, dir, dentry);
if (err)
@@ -561,6 +568,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize,
&disk_link);
@@ -690,6 +700,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

err = dquot_initialize(dir);
if (err)
@@ -824,6 +837,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
(!projid_eq(F2FS_I(new_dir)->i_projid,
@@ -1014,6 +1030,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,

if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
+ err = f2fs_is_checkpoint_ready(sbi);
+ if (err)
+ return err;

if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
!projid_eq(F2FS_I(new_dir)->i_projid,
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 97a4fae75651..471aa8821d4c 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -176,6 +176,8 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
return false;
if (sbi->gc_mode == GC_URGENT)
return true;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return true;

return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
SM_I(sbi)->min_ssr_sections + reserved_sections(sbi));
@@ -480,6 +482,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
if (need && excess_cached_nats(sbi))
f2fs_balance_fs_bg(sbi);

+ if (f2fs_is_checkpoint_ready(sbi))
+ return;
+
/*
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
@@ -796,7 +801,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned short valid_blocks;
+ unsigned short valid_blocks, ckpt_valid_blocks;

if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
return;
@@ -804,8 +809,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
mutex_lock(&dirty_i->seglist_lock);

valid_blocks = get_valid_blocks(sbi, segno, false);
+ ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);

- if (valid_blocks == 0) {
+ if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
+ ckpt_valid_blocks == sbi->blocks_per_seg)) {
__locate_dirty_segment(sbi, segno, PRE);
__remove_dirty_segment(sbi, segno, DIRTY);
} else if (valid_blocks < sbi->blocks_per_seg) {
@@ -818,6 +825,43 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
mutex_unlock(&dirty_i->seglist_lock);
}

+/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */
+void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi)
+{
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned int segno;
+
+ mutex_lock(&dirty_i->seglist_lock);
+ for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
+ if (get_valid_blocks(sbi, segno, false))
+ continue;
+ if (IS_CURSEG(sbi, segno))
+ continue;
+ __locate_dirty_segment(sbi, segno, PRE);
+ __remove_dirty_segment(sbi, segno, DIRTY);
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
+}
+
+/* This is only used by SBI_CP_DISABLED */
+static unsigned int get_free_segment(struct f2fs_sb_info *sbi)
+{
+ struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ unsigned int segno = 0;
+
+ mutex_lock(&dirty_i->seglist_lock);
+ for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
+ if (get_valid_blocks(sbi, segno, false))
+ continue;
+ if (get_ckpt_valid_blocks(sbi, segno))
+ continue;
+ mutex_unlock(&dirty_i->seglist_lock);
+ return segno;
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
+ return NULL_SEGNO;
+}
+
static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len)
@@ -2028,7 +2072,8 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
sbi->discard_blks--;

/* don't overwrite by SSR to keep node chain */
- if (IS_NODESEG(se->type)) {
+ if (IS_NODESEG(se->type) &&
+ !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks++;
}
@@ -2050,6 +2095,15 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
f2fs_bug_on(sbi, 1);
se->valid_blocks++;
del = 0;
+ } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ /*
+ * If checkpoints are off, we must not reuse data that
+ * was used in the previous checkpoint. If it was used
+ * before, we must track that to know how much space we
+ * really have.
+ */
+ if (f2fs_test_bit(offset, se->ckpt_valid_map))
+ sbi->unusable_block_count++;
}

if (f2fs_test_and_clear_bit(offset, se->discard_map))
@@ -2332,6 +2386,9 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
if (sbi->segs_per_sec != 1)
return CURSEG_I(sbi, type)->segno;

+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;
+
if (test_opt(sbi, NOHEAP) &&
(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
return 0;
@@ -2475,6 +2532,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
return 1;
}
}
+
+ /* find valid_blocks=0 in dirty list */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ segno = get_free_segment(sbi);
+ if (segno != NULL_SEGNO) {
+ curseg->next_segno = segno;
+ return 1;
+ }
+ }
return 0;
}

@@ -2492,7 +2558,8 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
type == CURSEG_WARM_NODE)
new_curseg(sbi, type, false);
- else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
+ else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) &&
+ likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
new_curseg(sbi, type, false);
else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
change_curseg(sbi, type);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 086150028c6d..ab3465faddf1 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -339,6 +339,12 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
return get_seg_entry(sbi, segno)->valid_blocks;
}

+static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
+ unsigned int segno)
+{
+ return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+}
+
static inline void seg_info_from_raw_sit(struct seg_entry *se,
struct f2fs_sit_entry *rs)
{
@@ -576,6 +582,15 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
reserved_sections(sbi) + needed);
}

+static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
+{
+ if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;
+ if (likely(!has_not_enough_free_secs(sbi, 0, 0)))
+ return 0;
+ return -ENOSPC;
+}
+
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
{
return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index c47b1ef2685a..d698e11b06e4 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -136,6 +136,7 @@ enum {
Opt_alloc,
Opt_fsync,
Opt_test_dummy_encryption,
+ Opt_checkpoint,
Opt_err,
};

@@ -194,6 +195,7 @@ static match_table_t f2fs_tokens = {
{Opt_alloc, "alloc_mode=%s"},
{Opt_fsync, "fsync_mode=%s"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
+ {Opt_checkpoint, "checkpoint=%s"},
{Opt_err, NULL},
};

@@ -769,6 +771,23 @@ static int parse_options(struct super_block *sb, char *options)
"Test dummy encryption mount option ignored");
#endif
break;
+ case Opt_checkpoint:
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+
+ if (strlen(name) == 6 &&
+ !strncmp(name, "enable", 6)) {
+ clear_opt(sbi, DISABLE_CHECKPOINT);
+ } else if (strlen(name) == 7 &&
+ !strncmp(name, "disable", 7)) {
+ set_opt(sbi, DISABLE_CHECKPOINT);
+ } else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -827,6 +846,12 @@ static int parse_options(struct super_block *sb, char *options)
}
}

+ if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) {
+ f2fs_msg(sb, KERN_ERR,
+ "LFS not compatible with checkpoint=disable\n");
+ return -EINVAL;
+ }
+
/* Not pass down write hints if the number of active logs is lesser
* than NR_CURSEG_TYPE.
*/
@@ -1014,8 +1039,8 @@ static void f2fs_put_super(struct super_block *sb)
* But, the previous checkpoint was not done by umount, it needs to do
* clean checkpoint again.
*/
- if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
- !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+ if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+ !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) {
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
@@ -1087,6 +1112,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync)

if (unlikely(f2fs_cp_error(sbi)))
return 0;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
+ return 0;

trace_f2fs_sync_fs(sb, sync);

@@ -1186,6 +1213,11 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_blocks = total_count - start_count;
buf->f_bfree = user_block_count - valid_user_blocks(sbi) -
sbi->current_reserved_blocks;
+ if (unlikely(buf->f_bfree <= sbi->unusable_block_count))
+ buf->f_bfree = 0;
+ else
+ buf->f_bfree -= sbi->unusable_block_count;
+
if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks)
buf->f_bavail = buf->f_bfree -
F2FS_OPTION(sbi).root_reserved_blocks;
@@ -1365,6 +1397,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
seq_printf(seq, ",alloc_mode=%s", "reuse");

+ if (test_opt(sbi, DISABLE_CHECKPOINT))
+ seq_puts(seq, ",checkpoint=disable");
+
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX)
seq_printf(seq, ",fsync_mode=%s", "posix");
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
@@ -1392,6 +1427,7 @@ static void default_options(struct f2fs_sb_info *sbi)
set_opt(sbi, INLINE_DENTRY);
set_opt(sbi, EXTENT_CACHE);
set_opt(sbi, NOHEAP);
+ clear_opt(sbi, DISABLE_CHECKPOINT);
sbi->sb->s_flags |= SB_LAZYTIME;
set_opt(sbi, FLUSH_MERGE);
set_opt(sbi, DISCARD);
@@ -1413,6 +1449,52 @@ static void default_options(struct f2fs_sb_info *sbi)
#ifdef CONFIG_QUOTA
static int f2fs_enable_quotas(struct super_block *sb);
#endif
+
+static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
+{
+ struct cp_control cpc;
+ int err;
+
+ sbi->sb->s_flags |= SB_ACTIVE;
+
+ mutex_lock(&sbi->gc_mutex);
+ for (; dirty_segments(sbi) > 2 * NR_CURSEG_TYPE;) {
+ err = f2fs_gc(sbi, true, false, NULL_SEGNO);
+ if (err == -ENODATA)
+ break;
+ if (err && err != -EAGAIN) {
+ mutex_unlock(&sbi->gc_mutex);
+ return err;
+ }
+ }
+ mutex_unlock(&sbi->gc_mutex);
+
+ err = sync_filesystem(sbi->sb);
+ if (err)
+ return err;
+
+ mutex_lock(&sbi->gc_mutex);
+ cpc.reason = CP_PAUSE;
+ set_sbi_flag(sbi, SBI_CP_DISABLED);
+ f2fs_write_checkpoint(sbi, &cpc);
+
+ sbi->unusable_block_count = 0;
+ mutex_unlock(&sbi->gc_mutex);
+ return 0;
+}
+
+static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
+{
+ mutex_lock(&sbi->gc_mutex);
+ f2fs_dirty_to_prefree(sbi);
+
+ clear_sbi_flag(sbi, SBI_CP_DISABLED);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ mutex_unlock(&sbi->gc_mutex);
+
+ f2fs_sync_fs(sbi->sb, 1);
+}
+
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -1422,6 +1504,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
bool need_restart_gc = false;
bool need_stop_gc = false;
bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
+ bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT);
+ bool checkpoint_changed;
#ifdef CONFIG_QUOTA
int i, j;
#endif
@@ -1466,6 +1550,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
err = parse_options(sb, data);
if (err)
goto restore_opts;
+ checkpoint_changed =
+ disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT);

/*
* Previous and new state of filesystem is RO,
@@ -1499,6 +1585,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}

+ if ((*flags & MS_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "disabling checkpoint not compatible with read-only");
+ goto restore_opts;
+ }
+
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
@@ -1527,6 +1620,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
clear_sbi_flag(sbi, SBI_IS_CLOSE);
}

+ if (checkpoint_changed) {
+ if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = f2fs_disable_checkpoint(sbi);
+ if (err)
+ goto restore_gc;
+ } else {
+ f2fs_enable_checkpoint(sbi);
+ }
+ }
+
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
@@ -3064,6 +3167,9 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto free_meta;

+ if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)))
+ goto skip_recovery;
+
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
@@ -3103,6 +3209,14 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
/* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);

+ if (test_opt(sbi, DISABLE_CHECKPOINT)) {
+ err = f2fs_disable_checkpoint(sbi);
+ if (err)
+ goto free_meta;
+ } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) {
+ f2fs_enable_checkpoint(sbi);
+ }
+
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 1d4b196291d6..9e95bbce5dd4 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -115,6 +115,7 @@ struct f2fs_super_block {
/*
* For checkpoint
*/
+#define CP_DISABLED_FLAG 0x00001000
#define CP_LARGE_NAT_BITMAP_FLAG 0x00000400
#define CP_NOCRC_RECOVERY_FLAG 0x00000200
#define CP_TRIMMED_FLAG 0x00000100
--
2.19.0.605.g01d371f741-goog