Merge tag 'f2fs-for-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs update from Jaegeuk Kim:
 "In this round, we've mainly modified to support non-power-of-two zone
  size, which is not required for f2fs by design. In order to avoid arch
  dependency, we refactored the messy rb_entry structure shared across
  different extent_cache. In addition to the improvement, we've also
  fixed several subtle bugs and error cases.

  Enhancements:
   - support non-power-of-two zone size for zoned device
   - remove sharing the rb_entry structure in extent cache
   - refactor f2fs_gc to call checkpoint in urgent condition
   - support iopoll

  Bug fixes:
   - fix potential corruption when moving a directory
   - fix to avoid use-after-free for cached IPU bio
   - fix the folio private usage
   - avoid kernel warnings or panics in the cp_error case
   - fix to recover quota data correctly
   - fix some bugs in atomic operations
   - fix system crash due to lack of free space in LFS
   - fix null pointer panic in tracepoint in __replace_atomic_write_block
   - fix iostat lock protection
   - fix scheduling while atomic in decompression path
   - preserve direct write semantics when buffering is forced
   - fix to call f2fs_wait_on_page_writeback() in f2fs_write_raw_pages()"

* tag 'f2fs-for-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (52 commits)
  f2fs: remove unnessary comment in __may_age_extent_tree
  f2fs: allocate node blocks for atomic write block replacement
  f2fs: use cow inode data when updating atomic write
  f2fs: remove power-of-two limitation of zoned device
  f2fs: allocate trace path buffer from names_cache
  f2fs: add has_enough_free_secs()
  f2fs: relax sanity check if checkpoint is corrupted
  f2fs: refactor f2fs_gc to call checkpoint in urgent condition
  f2fs: remove folio_detach_private() in .invalidate_folio and .release_folio
  f2fs: remove bulk remove_proc_entry() and unnecessary kobject_del()
  f2fs: support iopoll method
  f2fs: remove batched_trim_sections node description
  f2fs: fix to check return value of inc_valid_block_count()
  f2fs: fix to check return value of f2fs_do_truncate_blocks()
  f2fs: fix passing relative address when discard zones
  f2fs: fix potential corruption when moving a directory
  f2fs: add radix_tree_preload_end in error case
  f2fs: fix to recover quota data correctly
  f2fs: fix to check readonly condition correctly
  docs: f2fs: Correct instruction to disable checkpoint
  ...

22 files changed, 899 insertions, 897 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 94132745ecbe..8140fc98f5ae 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -190,12 +190,6 @@ Description:	Controls the memory footprint used by free nids and cached
 		nat entries. By default, 1 is set, which indicates
 		10 MB / 1 GB RAM.
 
-What:		/sys/fs/f2fs/<disk>/batched_trim_sections
-Date:		February 2015
-Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:	Controls the trimming rate in batch mode.
-		<deprecated>
-
 What:		/sys/fs/f2fs/<disk>/cp_interval
 Date:		October 2015
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
@@ -729,3 +723,20 @@ What:		/sys/fs/f2fs/<disk>/last_age_weight
 Date:		January 2023
 Contact:	"Ping Xiong" <xiongping1@xiaomi.com>
 Description:	When DATA SEPARATION is on, it controls the weight of last data block age.
+
+What:		/sys/fs/f2fs/<disk>/compress_watermark
+Date:		February 2023
+Contact:	"Yangtao Li" <frank.li@vivo.com>
+Description:	When compress cache is on, it controls free memory watermark
+		in order to limit caching compress page. If free memory is lower
+		than watermark, then deny caching compress page. The value should be in
+		range of (0, 100], by default it was initialized as 20(%).
+
+What:		/sys/fs/f2fs/<disk>/compress_percent
+Date:		February 2023
+Contact:	"Yangtao Li" <frank.li@vivo.com>
+Description:	When compress cache is on, it controls cached page
+		percent(compress pages / free_ram) in order to limit caching compress page.
+		If cached page percent exceed threshold, then deny caching compress page.
+		The value should be in range of (0, 100], by default it was initialized
+		as 20(%).
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 2055e72871fe..c57745375edb 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -264,7 +264,7 @@ checkpoint=%s[:%u[%]]	 Set to "disable" to turn off checkpointing. Set to "enabl
 			 disabled, any unmounting or unexpected shutdowns will cause
 			 the filesystem contents to appear as they did when the
 			 filesystem was mounted with that option.
-			 While mounting with checkpoint=disabled, the filesystem must
+			 While mounting with checkpoint=disable, the filesystem must
 			 run garbage collection to ensure that all available space can
 			 be used. If this takes too much time, the mount may return
 			 EAGAIN. You may optionally add a value to indicate how much
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index c3e058e0a018..64b3860f50ee 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -152,6 +152,11 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 	se = get_seg_entry(sbi, segno);
 
 	exist = f2fs_test_bit(offset, se->cur_valid_map);
+
+	/* skip data, if we already have an error in checkpoint. */
+	if (unlikely(f2fs_cp_error(sbi)))
+		return exist;
+
 	if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) {
 		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
 			 blkaddr, exist);
@@ -202,6 +207,11 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 	case DATA_GENERIC_ENHANCE_UPDATE:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 				blkaddr < MAIN_BLKADDR(sbi))) {
+
+			/* Skip to emit an error message. */
+			if (unlikely(f2fs_cp_error(sbi)))
+				return false;
+
 			f2fs_warn(sbi, "access invalid blkaddr:%u",
 				  blkaddr);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -325,8 +335,15 @@ static int __f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
+			ClearPageUptodate(page);
+			dec_page_count(sbi, F2FS_DIRTY_META);
+			unlock_page(page);
+			return 0;
+		}
 		goto redirty_out;
+	}
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
@@ -508,6 +525,7 @@ retry:
 	if (!e) {
 		if (!new) {
 			spin_unlock(&im->ino_lock);
+			radix_tree_preload_end();
 			goto retry;
 		}
 		e = new;
@@ -706,32 +724,18 @@ err_out:
 int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 {
 	block_t start_blk, orphan_blocks, i, j;
-	unsigned int s_flags = sbi->sb->s_flags;
 	int err = 0;
-#ifdef CONFIG_QUOTA
-	int quota_enabled;
-#endif
 
 	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
 
-	if (bdev_read_only(sbi->sb->s_bdev)) {
+	if (f2fs_hw_is_readonly(sbi)) {
 		f2fs_info(sbi, "write access unavailable, skipping orphan cleanup");
 		return 0;
 	}
 
-	if (s_flags & SB_RDONLY) {
+	if (is_sbi_flag_set(sbi, SBI_IS_WRITABLE))
 		f2fs_info(sbi, "orphan cleanup on readonly fs");
-		sbi->sb->s_flags &= ~SB_RDONLY;
-	}
-
-#ifdef CONFIG_QUOTA
-	/*
-	 * Turn on quotas which were not enabled for read-only mounts if
-	 * filesystem has quota feature, so that they are updated correctly.
-	 */
-	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
-#endif
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
 	orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
@@ -765,13 +769,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 out:
 	set_sbi_flag(sbi, SBI_IS_RECOVERED);
 
-#ifdef CONFIG_QUOTA
-	/* Turn quotas off */
-	if (quota_enabled)
-		f2fs_quota_off_umount(sbi->sb);
-#endif
-	sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
-
 	return err;
 }
 
@@ -982,7 +979,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 
 	cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
 	if (cur_page == cp2)
-		cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+		cp_blk_no += BIT(le32_to_cpu(fsb->log_blocks_per_seg));
 
 	for (i = 1; i < cp_blks; i++) {
 		void *sit_bitmap_ptr;
@@ -1133,7 +1130,7 @@ retry:
 	goto retry;
 }
 
-int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
+static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head = &sbi->inode_list[DIRTY_META];
 	struct inode *inode;
@@ -1306,7 +1303,8 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
 		if (!get_pages(sbi, type))
 			break;
 
-		if (unlikely(f2fs_cp_error(sbi)))
+		if (unlikely(f2fs_cp_error(sbi) &&
+			!is_sbi_flag_set(sbi, SBI_IS_CLOSE)))
 			break;
 
 		if (type == F2FS_DIRTY_META)
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index b40dec3d7f79..11653fa79289 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -264,35 +264,21 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
 	cc->private = NULL;
 }
 
-#ifdef CONFIG_F2FS_FS_LZ4HC
-static int lz4hc_compress_pages(struct compress_ctx *cc)
+static int lz4_compress_pages(struct compress_ctx *cc)
 {
+	int len = -EINVAL;
 	unsigned char level = F2FS_I(cc->inode)->i_compress_level;
-	int len;
 
-	if (level)
-		len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen,
-					cc->clen, level, cc->private);
-	else
+	if (!level)
 		len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
 						cc->clen, cc->private);
-	if (!len)
-		return -EAGAIN;
-
-	cc->clen = len;
-	return 0;
-}
-#endif
-
-static int lz4_compress_pages(struct compress_ctx *cc)
-{
-	int len;
-
 #ifdef CONFIG_F2FS_FS_LZ4HC
-	return lz4hc_compress_pages(cc);
+	else
+		len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+					cc->clen, level, cc->private);
 #endif
-	len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
-						cc->clen, cc->private);
+	if (len < 0)
+		return len;
 	if (!len)
 		return -EAGAIN;
 
@@ -670,7 +656,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
 
-	if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)
+	if (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))
 		chksum = f2fs_crc32(F2FS_I_SB(cc->inode),
 					cc->cbuf->cdata, cc->clen);
 	cc->cbuf->chksum = cpu_to_le32(chksum);
@@ -755,13 +741,18 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task)
 
 	if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) {
 		ret = -EFSCORRUPTED;
-		f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
+
+		/* Avoid f2fs_commit_super in irq context */
+		if (in_task)
+			f2fs_save_errors(sbi, ERROR_FAIL_DECOMPRESSION);
+		else
+			f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
 		goto out_release;
 	}
 
 	ret = cops->decompress_pages(dic);
 
-	if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) {
+	if (!ret && (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))) {
 		u32 provided = le32_to_cpu(dic->cbuf->chksum);
 		u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen);
 
@@ -1456,6 +1447,12 @@ continue_unlock:
 		if (!PageDirty(cc->rpages[i]))
 			goto continue_unlock;
 
+		if (PageWriteback(cc->rpages[i])) {
+			if (wbc->sync_mode == WB_SYNC_NONE)
+				goto continue_unlock;
+			f2fs_wait_on_page_writeback(cc->rpages[i], DATA, true, true);
+		}
+
 		if (!clear_page_dirty_for_io(cc->rpages[i]))
 			goto continue_unlock;
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 06b552a0aba2..7165b1202f53 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -93,17 +93,17 @@ static enum count_type __read_io_type(struct page *page)
 /* postprocessing steps for read bios */
 enum bio_post_read_step {
 #ifdef CONFIG_FS_ENCRYPTION
-	STEP_DECRYPT	= 1 << 0,
+	STEP_DECRYPT	= BIT(0),
 #else
 	STEP_DECRYPT	= 0,	/* compile out the decryption-related code */
 #endif
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-	STEP_DECOMPRESS	= 1 << 1,
+	STEP_DECOMPRESS	= BIT(1),
 #else
 	STEP_DECOMPRESS	= 0,	/* compile out the decompression-related code */
 #endif
 #ifdef CONFIG_FS_VERITY
-	STEP_VERITY	= 1 << 2,
+	STEP_VERITY	= BIT(2),
 #else
 	STEP_VERITY	= 0,	/* compile out the verity-related code */
 #endif
@@ -420,7 +420,7 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
 {
-	unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
+	unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0);
 	unsigned int fua_flag, meta_flag, io_flag;
 	blk_opf_t op_flags = 0;
 
@@ -442,9 +442,9 @@ static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
 	 *    5 |    4 |   3 |    2 |    1 |   0 |
 	 * Cold | Warm | Hot | Cold | Warm | Hot |
 	 */
-	if ((1 << fio->temp) & meta_flag)
+	if (BIT(fio->temp) & meta_flag)
 		op_flags |= REQ_META;
-	if ((1 << fio->temp) & fua_flag)
+	if (BIT(fio->temp) & fua_flag)
 		op_flags |= REQ_FUA;
 	return op_flags;
 }
@@ -874,6 +874,8 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
 	bool found = false;
 	struct bio *target = bio ? *bio : NULL;
 
+	f2fs_bug_on(sbi, !target && !page);
+
 	for (temp = HOT; temp < NR_TEMP_TYPE && !found; temp++) {
 		struct f2fs_bio_info *io = sbi->write_io[DATA] + temp;
 		struct list_head *head = &io->bio_list;
@@ -2235,6 +2237,10 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 	if (ret)
 		goto out;
 
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
+		goto out_put_dnode;
+	}
 	f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
 
 skip_reading_dnode:
@@ -2798,7 +2804,8 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 		 * don't drop any dirty dentry pages for keeping lastest
 		 * directory structure.
 		 */
-		if (S_ISDIR(inode->i_mode))
+		if (S_ISDIR(inode->i_mode) &&
+				!is_sbi_flag_set(sbi, SBI_IS_CLOSE))
 			goto redirty_out;
 		goto out;
 	}
@@ -2898,7 +2905,8 @@ out:
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_submit_merged_write(sbi, DATA);
-		f2fs_submit_merged_ipu_write(sbi, bio, NULL);
+		if (bio && *bio)
+			f2fs_submit_merged_ipu_write(sbi, bio, NULL);
 		submitted = NULL;
 	}
 
@@ -3123,12 +3131,9 @@ continue_unlock:
 			}
 
 			if (folio_test_writeback(folio)) {
-				if (wbc->sync_mode != WB_SYNC_NONE)
-					f2fs_wait_on_page_writeback(
-							&folio->page,
-							DATA, true, true);
-				else
+				if (wbc->sync_mode == WB_SYNC_NONE)
 					goto continue_unlock;
+				f2fs_wait_on_page_writeback(&folio->page, DATA, true, true);
 			}
 
 			if (!folio_clear_dirty_for_io(folio))
@@ -3486,7 +3491,7 @@ unlock_out:
 
 static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
 			struct page *page, loff_t pos, unsigned int len,
-			block_t *blk_addr, bool *node_changed)
+			block_t *blk_addr, bool *node_changed, bool *use_cow)
 {
 	struct inode *inode = page->mapping->host;
 	struct inode *cow_inode = F2FS_I(inode)->cow_inode;
@@ -3500,10 +3505,12 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
 
 	/* Look for the block in COW inode first */
 	err = __find_data_block(cow_inode, index, blk_addr);
-	if (err)
+	if (err) {
 		return err;
-	else if (*blk_addr != NULL_ADDR)
+	} else if (*blk_addr != NULL_ADDR) {
+		*use_cow = true;
 		return 0;
+	}
 
 	if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE))
 		goto reserve_block;
@@ -3533,6 +3540,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct page *page = NULL;
 	pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
 	bool need_balance = false;
+	bool use_cow = false;
 	block_t blkaddr = NULL_ADDR;
 	int err = 0;
 
@@ -3592,7 +3600,7 @@ repeat:
 
 	if (f2fs_is_atomic_file(inode))
 		err = prepare_atomic_write_begin(sbi, page, pos, len,
-					&blkaddr, &need_balance);
+					&blkaddr, &need_balance, &use_cow);
 	else
 		err = prepare_write_begin(sbi, page, pos, len,
 					&blkaddr, &need_balance);
@@ -3632,7 +3640,9 @@ repeat:
 			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 			goto fail;
 		}
-		err = f2fs_submit_page_read(inode, page, blkaddr, 0, true);
+		err = f2fs_submit_page_read(use_cow ?
+				F2FS_I(inode)->cow_inode : inode, page,
+				blkaddr, 0, true);
 		if (err)
 			goto fail;
 
@@ -3725,37 +3735,16 @@ void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
 			f2fs_remove_dirty_inode(inode);
 		}
 	}
-
-	clear_page_private_reference(&folio->page);
-	clear_page_private_gcing(&folio->page);
-
-	if (test_opt(sbi, COMPRESS_CACHE) &&
-			inode->i_ino == F2FS_COMPRESS_INO(sbi))
-		clear_page_private_data(&folio->page);
-
-	folio_detach_private(folio);
+	clear_page_private_all(&folio->page);
 }
 
 bool f2fs_release_folio(struct folio *folio, gfp_t wait)
 {
-	struct f2fs_sb_info *sbi;
-
 	/* If this is dirty folio, keep private data */
 	if (folio_test_dirty(folio))
 		return false;
 
-	sbi = F2FS_M_SB(folio->mapping);
-	if (test_opt(sbi, COMPRESS_CACHE)) {
-		struct inode *inode = folio->mapping->host;
-
-		if (inode->i_ino == F2FS_COMPRESS_INO(sbi))
-			clear_page_private_data(&folio->page);
-	}
-
-	clear_page_private_reference(&folio->page);
-	clear_page_private_gcing(&folio->page);
-
-	folio_detach_private(folio);
+	clear_page_private_all(&folio->page);
 	return true;
 }
 
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 30a77936e3c5..61c35b59126e 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -336,22 +336,23 @@ get_cache:
 #endif
 }
 
-static char *s_flag[] = {
-	[SBI_IS_DIRTY]		= " fs_dirty",
-	[SBI_IS_CLOSE]		= " closing",
-	[SBI_NEED_FSCK]		= " need_fsck",
-	[SBI_POR_DOING]		= " recovering",
-	[SBI_NEED_SB_WRITE]	= " sb_dirty",
-	[SBI_NEED_CP]		= " need_cp",
-	[SBI_IS_SHUTDOWN]	= " shutdown",
-	[SBI_IS_RECOVERED]	= " recovered",
-	[SBI_CP_DISABLED]	= " cp_disabled",
-	[SBI_CP_DISABLED_QUICK]	= " cp_disabled_quick",
-	[SBI_QUOTA_NEED_FLUSH]	= " quota_need_flush",
-	[SBI_QUOTA_SKIP_FLUSH]	= " quota_skip_flush",
-	[SBI_QUOTA_NEED_REPAIR]	= " quota_need_repair",
-	[SBI_IS_RESIZEFS]	= " resizefs",
-	[SBI_IS_FREEZING]	= " freezefs",
+static const char *s_flag[MAX_SBI_FLAG] = {
+	[SBI_IS_DIRTY]		= "fs_dirty",
+	[SBI_IS_CLOSE]		= "closing",
+	[SBI_NEED_FSCK]		= "need_fsck",
+	[SBI_POR_DOING]		= "recovering",
+	[SBI_NEED_SB_WRITE]	= "sb_dirty",
+	[SBI_NEED_CP]		= "need_cp",
+	[SBI_IS_SHUTDOWN]	= "shutdown",
+	[SBI_IS_RECOVERED]	= "recovered",
+	[SBI_CP_DISABLED]	= "cp_disabled",
+	[SBI_CP_DISABLED_QUICK]	= "cp_disabled_quick",
+	[SBI_QUOTA_NEED_FLUSH]	= "quota_need_flush",
+	[SBI_QUOTA_SKIP_FLUSH]	= "quota_skip_flush",
+	[SBI_QUOTA_NEED_REPAIR]	= "quota_need_repair",
+	[SBI_IS_RESIZEFS]	= "resizefs",
+	[SBI_IS_FREEZING]	= "freezefs",
+	[SBI_IS_WRITABLE]	= "writable",
 };
 
 static const char *ipu_mode_names[F2FS_IPU_MAX] = {
@@ -384,8 +385,8 @@ static int stat_show(struct seq_file *s, void *v)
 			"Disabled" : (f2fs_cp_error(sbi) ? "Error" : "Good"));
 		if (sbi->s_flag) {
 			seq_puts(s, "[SBI:");
-			for_each_set_bit(j, &sbi->s_flag, 32)
-				seq_puts(s, s_flag[j]);
+			for_each_set_bit(j, &sbi->s_flag, MAX_SBI_FLAG)
+				seq_printf(s, " %s", s_flag[j]);
 			seq_puts(s, "]\n");
 		}
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 9ccdbe120425..887e55988450 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -29,7 +29,7 @@ static unsigned long dir_blocks(struct inode *inode)
 static unsigned int dir_buckets(unsigned int level, int dir_level)
 {
 	if (level + dir_level < MAX_DIR_HASH_DEPTH / 2)
-		return 1 << (level + dir_level);
+		return BIT(level + dir_level);
 	else
 		return MAX_DIR_BUCKETS;
 }
@@ -42,39 +42,6 @@ static unsigned int bucket_blocks(unsigned int level)
 		return 4;
 }
 
-static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
-	[F2FS_FT_UNKNOWN]	= DT_UNKNOWN,
-	[F2FS_FT_REG_FILE]	= DT_REG,
-	[F2FS_FT_DIR]		= DT_DIR,
-	[F2FS_FT_CHRDEV]	= DT_CHR,
-	[F2FS_FT_BLKDEV]	= DT_BLK,
-	[F2FS_FT_FIFO]		= DT_FIFO,
-	[F2FS_FT_SOCK]		= DT_SOCK,
-	[F2FS_FT_SYMLINK]	= DT_LNK,
-};
-
-static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
-	[S_IFREG >> S_SHIFT]	= F2FS_FT_REG_FILE,
-	[S_IFDIR >> S_SHIFT]	= F2FS_FT_DIR,
-	[S_IFCHR >> S_SHIFT]	= F2FS_FT_CHRDEV,
-	[S_IFBLK >> S_SHIFT]	= F2FS_FT_BLKDEV,
-	[S_IFIFO >> S_SHIFT]	= F2FS_FT_FIFO,
-	[S_IFSOCK >> S_SHIFT]	= F2FS_FT_SOCK,
-	[S_IFLNK >> S_SHIFT]	= F2FS_FT_SYMLINK,
-};
-
-static void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
-{
-	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
-}
-
-unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
-{
-	if (de->file_type < F2FS_FT_MAX)
-		return f2fs_filetype_table[de->file_type];
-	return DT_UNKNOWN;
-}
-
 /* If @dir is casefolded, initialize @fname->cf_name from @fname->usr_fname. */
 int f2fs_init_casefolded_name(const struct inode *dir,
 			      struct f2fs_filename *fname)
@@ -485,7 +452,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 	lock_page(page);
 	f2fs_wait_on_page_writeback(page, type, true, true);
 	de->ino = cpu_to_le32(inode->i_ino);
-	set_de_type(de, inode->i_mode);
+	de->file_type = fs_umode_to_ftype(inode->i_mode);
 	set_page_dirty(page);
 
 	dir->i_mtime = dir->i_ctime = current_time(dir);
@@ -699,7 +666,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 	de->name_len = cpu_to_le16(name->len);
 	memcpy(d->filename[bit_pos], name->name, name->len);
 	de->ino = cpu_to_le32(ino);
-	set_de_type(de, mode);
+	de->file_type = fs_umode_to_ftype(mode);
 	for (i = 0; i < slots; i++) {
 		__set_bit_le(bit_pos + i, (void *)d->bitmap);
 		/* avoid wrong garbage data for readdir */
@@ -938,14 +905,10 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		f2fs_clear_page_cache_dirty_tag(page);
 		clear_page_dirty_for_io(page);
 		ClearPageUptodate(page);
-
-		clear_page_private_gcing(page);
+		clear_page_private_all(page);
 
 		inode_dec_dirty_pages(dir);
 		f2fs_remove_dirty_inode(dir);
-
-		detach_page_private(page);
-		set_page_private(page, 0);
 	}
 	f2fs_put_page(page, 1);
 
@@ -1036,7 +999,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			continue;
 		}
 
-		d_type = f2fs_get_de_type(de);
+		d_type = fs_ftype_to_dtype(de->file_type);
 
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 28b12553f2b3..0e2d49140c07 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -23,18 +23,26 @@ bool sanity_check_extent_cache(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct extent_tree *et = fi->extent_tree[EX_READ];
 	struct extent_info *ei;
 
-	if (!fi->extent_tree[EX_READ])
+	if (!et)
+		return true;
+
+	ei = &et->largest;
+	if (!ei->len)
 		return true;
 
-	ei = &fi->extent_tree[EX_READ]->largest;
+	/* Let's drop, if checkpoint got corrupted. */
+	if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) {
+		ei->len = 0;
+		et->largest_updated = true;
+		return true;
+	}
 
-	if (ei->len &&
-		(!f2fs_is_valid_blkaddr(sbi, ei->blk,
-					DATA_GENERIC_ENHANCE) ||
-		!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
-					DATA_GENERIC_ENHANCE))) {
+	if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) ||
+	    !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+					DATA_GENERIC_ENHANCE)) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
 			  __func__, inode->i_ino,
@@ -86,7 +94,6 @@ static bool __may_age_extent_tree(struct inode *inode)
 
 	if (!test_opt(sbi, AGE_EXTENT_CACHE))
 		return false;
-	/* don't cache block age info for cold file */
 	if (is_inode_flag_set(inode, FI_COMPRESSED_FILE))
 		return false;
 	if (file_is_cold(inode))
@@ -161,118 +168,52 @@ static bool __is_front_mergeable(struct extent_info *cur,
 	return __is_extent_mergeable(cur, front, type);
 }
 
-static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
-							unsigned int ofs)
-{
-	if (cached_re) {
-		if (cached_re->ofs <= ofs &&
-				cached_re->ofs + cached_re->len > ofs) {
-			return cached_re;
-		}
-	}
-	return NULL;
-}
-
-static struct rb_entry *__lookup_rb_tree_slow(struct rb_root_cached *root,
-							unsigned int ofs)
+static struct extent_node *__lookup_extent_node(struct rb_root_cached *root,
+			struct extent_node *cached_en, unsigned int fofs)
 {
 	struct rb_node *node = root->rb_root.rb_node;
-	struct rb_entry *re;
+	struct extent_node *en;
 
+	/* check a cached entry */
+	if (cached_en && cached_en->ei.fofs <= fofs &&
+			cached_en->ei.fofs + cached_en->ei.len > fofs)
+		return cached_en;
+
+	/* check rb_tree */
 	while (node) {
-		re = rb_entry(node, struct rb_entry, rb_node);
+		en = rb_entry(node, struct extent_node, rb_node);
 
-		if (ofs < re->ofs)
+		if (fofs < en->ei.fofs)
 			node = node->rb_left;
-		else if (ofs >= re->ofs + re->len)
+		else if (fofs >= en->ei.fofs + en->ei.len)
 			node = node->rb_right;
 		else
-			return re;
+			return en;
 	}
 	return NULL;
 }
 
-struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
-				struct rb_entry *cached_re, unsigned int ofs)
-{
-	struct rb_entry *re;
-
-	re = __lookup_rb_tree_fast(cached_re, ofs);
-	if (!re)
-		return __lookup_rb_tree_slow(root, ofs);
-
-	return re;
-}
-
-struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
-					struct rb_root_cached *root,
-					struct rb_node **parent,
-					unsigned long long key, bool *leftmost)
-{
-	struct rb_node **p = &root->rb_root.rb_node;
-	struct rb_entry *re;
-
-	while (*p) {
-		*parent = *p;
-		re = rb_entry(*parent, struct rb_entry, rb_node);
-
-		if (key < re->key) {
-			p = &(*p)->rb_left;
-		} else {
-			p = &(*p)->rb_right;
-			*leftmost = false;
-		}
-	}
-
-	return p;
-}
-
-struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root,
-				struct rb_node **parent,
-				unsigned int ofs, bool *leftmost)
-{
-	struct rb_node **p = &root->rb_root.rb_node;
-	struct rb_entry *re;
-
-	while (*p) {
-		*parent = *p;
-		re = rb_entry(*parent, struct rb_entry, rb_node);
-
-		if (ofs < re->ofs) {
-			p = &(*p)->rb_left;
-		} else if (ofs >= re->ofs + re->len) {
-			p = &(*p)->rb_right;
-			*leftmost = false;
-		} else {
-			f2fs_bug_on(sbi, 1);
-		}
-	}
-
-	return p;
-}
-
 /*
- * lookup rb entry in position of @ofs in rb-tree,
+ * lookup rb entry in position of @fofs in rb-tree,
  * if hit, return the entry, otherwise, return NULL
- * @prev_ex: extent before ofs
- * @next_ex: extent after ofs
- * @insert_p: insert point for new extent at ofs
+ * @prev_ex: extent before fofs
+ * @next_ex: extent after fofs
+ * @insert_p: insert point for new extent at fofs
  * in order to simplify the insertion after.
  * tree must stay unchanged between lookup and insertion.
  */
-struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
-				struct rb_entry *cached_re,
-				unsigned int ofs,
-				struct rb_entry **prev_entry,
-				struct rb_entry **next_entry,
+static struct extent_node *__lookup_extent_node_ret(struct rb_root_cached *root,
+				struct extent_node *cached_en,
+				unsigned int fofs,
+				struct extent_node **prev_entry,
+				struct extent_node **next_entry,
 				struct rb_node ***insert_p,
 				struct rb_node **insert_parent,
-				bool force, bool *leftmost)
+				bool *leftmost)
 {
 	struct rb_node **pnode = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL, *tmp_node;
-	struct rb_entry *re = cached_re;
+	struct extent_node *en = cached_en;
 
 	*insert_p = NULL;
 	*insert_parent = NULL;
@@ -282,24 +223,20 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
 	if (RB_EMPTY_ROOT(&root->rb_root))
 		return NULL;
 
-	if (re) {
-		if (re->ofs <= ofs && re->ofs + re->len > ofs)
-			goto lookup_neighbors;
-	}
+	if (en && en->ei.fofs <= fofs && en->ei.fofs + en->ei.len > fofs)
+		goto lookup_neighbors;
 
-	if (leftmost)
-		*leftmost = true;
+	*leftmost = true;
 
 	while (*pnode) {
 		parent = *pnode;
-		re = rb_entry(*pnode, struct rb_entry, rb_node);
+		en = rb_entry(*pnode, struct extent_node, rb_node);
 
-		if (ofs < re->ofs) {
+		if (fofs < en->ei.fofs) {
 			pnode = &(*pnode)->rb_left;
-		} else if (ofs >= re->ofs + re->len) {
+		} else if (fofs >= en->ei.fofs + en->ei.len) {
 			pnode = &(*pnode)->rb_right;
-			if (leftmost)
-				*leftmost = false;
+			*leftmost = false;
 		} else {
 			goto lookup_neighbors;
 		}
@@ -308,71 +245,32 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,