f2fs: Pull in from upstream 3.13 kernel

Merge tag 'for-3.8-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull new F2FS filesystem from Jaegeuk Kim:
 "Introduce a new file system, Flash-Friendly File System (F2FS), to
  Linux 3.8.

  Highlights:
   - Add initial f2fs source codes
   - Fix an endian conversion bug
   - Fix build failures on random configs
   - Fix the power-off-recovery routine
   - Minor cleanup, coding style, and typos patches"

From the Kconfig help text:

  F2FS is based on Log-structured File System (LFS), which supports
  versatile "flash-friendly" features. The design has been focused on
  addressing the fundamental issues in LFS, which are snowball effect
  of wandering tree and high cleaning overhead.

  Since flash-based storages show different characteristics according to
  the internal geometry or flash memory management schemes aka FTL, F2FS
  and tools support various parameters not only for configuring on-disk
  layout, but also for selecting allocation and cleaning algorithms.

and there's an article by Neil Brown about it on lwn.net:

  http://lwn.net/Articles/518988/

* tag 'for-3.8-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (36 commits)
  f2fs: fix tracking parent inode number
  f2fs: cleanup the f2fs_bio_alloc routine
  f2fs: introduce accessor to retrieve number of dentry slots
  f2fs: remove redundant call to f2fs_put_page in delete entry
  f2fs: make use of GFP_F2FS_ZERO for setting gfp_mask
  f2fs: rewrite f2fs_bio_alloc to make it simpler
  f2fs: fix a typo in f2fs documentation
  f2fs: remove unused variable
  f2fs: move error condition for mkdir at proper place
  f2fs: remove unneeded initialization
  f2fs: check read only condition before beginning write out
  f2fs: remove unneeded memset from init_once
  f2fs: show error in case of invalid mount arguments
  f2fs: fix the compiler warning for uninitialized use of variable
  f2fs: resolve build failures
  f2fs: adjust kernel coding style
  f2fs: fix endian conversion bugs reported by sparse
  f2fs: remove unneeded version.h header file from f2fs.h
  f2fs: update the f2fs document
  f2fs: update Kconfig and Makefile
  ...

Conflicts:
	include/uapi/linux/magic.h

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

Pull f2fs bug fixes from Jaegeuk Kim:
 "This patch-set includes two major bug fixes:
   - incorrect IUsed provided by *df -i*, and
   - lookup failure of parent inodes in corner cases.

  [Other Bug Fixes]
   - Fix error handling routines
   - Trigger recovery process correctly
   - Resolve build failures due to missing header files

  [Etc]
   - Add a MAINTAINERS entry for f2fs
   - Fix and clean up variables, functions, and equations
   - Avoid warnings during compilation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs:
  f2fs: unify string length declarations and usage
  f2fs: clean up unused variables and return values
  f2fs: clean up the start_bidx_of_node function
  f2fs: remove unneeded variable from f2fs_sync_fs
  f2fs: fix fsync_inode list addition logic and avoid invalid access to memory
  f2fs: remove unneeded initialization of nr_dirty in dirty_seglist_info
  f2fs: handle error from f2fs_iget_nowait
  f2fs: fix equation of has_not_enough_free_secs()
  f2fs: add MAINTAINERS entry
  f2fs: return a default value for non-void function
  f2fs: invalidate the node page if allocation is failed
  f2fs: add missing #include <linux/prefetch.h>
  f2fs: do f2fs_balance_fs in front of dir operations
  f2fs: should recover orphan and fsync data
  f2fs: fix handling errors got by f2fs_write_inode
  f2fs: fix up f2fs_get_parent issue to retrieve correct parent inode number
  f2fs: fix wrong calculation on f_files in statfs
  f2fs: remove set_page_dirty for atomic f2fs_end_io_write

Merge tag 'f2fs-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs fixes from Jaegeuk Kim:
 o Support swap file and link generic_file_remap_pages
 o Enhance the bio streaming flow and free section control
 o Major bug fix on recovery routine
 o Minor bug/warning fixes and code cleanups

* tag 'f2fs-for-3.8-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (22 commits)
  f2fs: use _safe() version of list_for_each
  f2fs: add comments of start_bidx_of_node
  f2fs: avoid issuing small bios due to several dirty node pages
  f2fs: support swapfile
  f2fs: add remap_pages as generic_file_remap_pages
  f2fs: add __init to functions in init_f2fs_fs
  f2fs: fix the debugfs entry creation path
  f2fs: add global mutex_lock to protect f2fs_stat_list
  f2fs: remove the blk_plug usage in f2fs_write_data_pages
  f2fs: avoid redundant time update for parent directory in f2fs_delete_entry
  f2fs: remove redundant call to set_blocksize in f2fs_fill_super
  f2fs: move f2fs_balance_fs to punch_hole
  f2fs: add f2fs_balance_fs in several interfaces
  f2fs: revisit the f2fs_gc flow
  f2fs: check return value during recovery
  f2fs: avoid null dereference in f2fs_acl_from_disk
  f2fs: initialize newly allocated dnode structure
  f2fs: update f2fs partition info about SIT/NAT layout
  f2fs: update f2fs document to reflect SIT/NAT layout correctly
  f2fs: remove unneeded INIT_LIST_HEAD at few places
  ...

Merge tag 'f2fs-for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs update from Jaegeuk Kim:
 "[Major bug fixes]
   o Store device file information correctly
   o Fix -EIO handling with respect to power-off-recovery
   o Allocate blocks with global locks
   o Fix wrong calculation of the SSR cost

  [Cleanups]
   o Get rid of fake on-stack dentries

  [Enhancement]
   o Support (un)freeze_fs
   o Enhance the f2fs_gc flow
   o Support 32-bit binary execution on 64-bit kernel"

* tag 'f2fs-for-3.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (29 commits)
  f2fs: avoid build warning
  f2fs: add compat_ioctl to provide backward compatability
  f2fs: fix calculation of max. gc cost in the SSR case
  f2fs: clarify and enhance the f2fs_gc flow
  f2fs: optimize the return condition for has_not_enough_free_secs
  f2fs: make an accessor to get sections for particular block type
  f2fs: mark gc_thread as NULL when thread creation is failed
  f2fs: name gc task as per the block device
  f2fs: remove unnecessary gc option check and balance_fs
  f2fs: remove repeated F2FS_SET_SB_DIRT call
  f2fs: when check superblock failed, try to check another superblock
  f2fs: use F2FS_BLKSIZE to judge bloksize and page_cache_size
  f2fs: add device name in debugfs
  f2fs: stop repeated checking if cp is needed
  f2fs: avoid balanc_fs during evict_inode
  f2fs: remove the use of page_cache_release
  f2fs: fix typo mistake for data_version description
  f2fs: reorganize code for ra_node_page
  f2fs: avoid redundant call to has_not_enough_free_secs in f2fs_gc
  f2fs: add un/freeze_fs into super_operations
  ...

Merge tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches.
   - introduce a new gloabl lock scheme
   - add tracepoints on several major functions
   - fix the overall cleaning process focused on victim selection
   - apply the block plugging to merge IOs as much as possible
   - enhance management of free nids and its list
   - enhance the readahead mode for node pages
   - address several cretical deadlock conditions
   - reduce lock_page calls

  The other minor bug fixes and enhancements are as follows.
   - calculation mistakes: overflow
   - bio types: READ, READA, and READ_SYNC
   - fix the recovery flow, data races, and null pointer errors"

* tag 'f2fs-for-v3.10' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
  f2fs: cover free_nid management with spin_lock
  f2fs: optimize scan_nat_page()
  f2fs: code cleanup for scan_nat_page() and build_free_nids()
  f2fs: bugfix for alloc_nid_failed()
  f2fs: recover when journal contains deleted files
  f2fs: continue to mount after failing recovery
  f2fs: avoid deadlock during evict after f2fs_gc
  f2fs: modify the number of issued pages to merge IOs
  f2fs: remove useless #include <linux/proc_fs.h> as we're now using sysfs as debug entry.
  f2fs: fix inconsistent using of NM_WOUT_THRESHOLD
  f2fs: check truncation of mapping after lock_page
  f2fs: enhance alloc_nid and build_free_nids flows
  f2fs: add a tracepoint on f2fs_new_inode
  f2fs: check nid == 0 in add_free_nid
  f2fs: add REQ_META about metadata requests for submit
  f2fs: give a chance to merge IOs by IO scheduler
  f2fs: avoid frequent background GC
  f2fs: add tracepoints to debug checkpoint request
  f2fs: add tracepoints for write page operations
  f2fs: add tracepoints to debug the block allocation
  ...

Merge tag 'for-f2fs-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches:
   - remount_fs callback function
   - restore parent inode number to enhance the fsync performance
   - xattr security labels
   - reduce the number of redundant lock/unlock data pages
   - avoid frequent write_inode calls

  The other minor bug fixes are as follows.
   - endian conversion bugs
   - various bugs in the roll-forward recovery routine"

* tag 'for-f2fs-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (56 commits)
  f2fs: fix to recover i_size from roll-forward
  f2fs: remove the unused argument "sbi" of func destroy_fsync_dnodes()
  f2fs: remove reusing any prefree segments
  f2fs: code cleanup and simplify in func {find/add}_gc_inode
  f2fs: optimize the init_dirty_segmap function
  f2fs: fix an endian conversion bug detected by sparse
  f2fs: fix crc endian conversion
  f2fs: add remount_fs callback support
  f2fs: recover wrong pino after checkpoint during fsync
  f2fs: optimize do_write_data_page()
  f2fs: make locate_dirty_segment() as static
  f2fs: remove unnecessary parameter "offset" from __add_sum_entry()
  f2fs: avoid freqeunt write_inode calls
  f2fs: optimise the truncate_data_blocks_range() range
  f2fs: use the F2FS specific flags in f2fs_ioctl()
  f2fs: sync dir->i_size with its block allocation
  f2fs: fix i_blocks translation on various types of files
  f2fs: set sb->s_fs_info before calling parse_options()
  f2fs: support xattr security labels
  f2fs: fix iget/iput of dir during recovery
  ...

Merge tag 'for-f2fs-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches:
   - support inline xattrs
   - add sysfs support to control GCs explicitly
   - add proc entry to show the current segment usage information
   - improve the GC/SSR performance

  The other bug fixes are as follows:
   - avoid the overflow on status calculation
   - fix some error handling routines
   - fix inconsistent xattr states after power-off-recovery
   - fix incorrect xattr node offset definition
   - fix deadlock condition in fsync
   - fix the fdatasync routine for power-off-recovery"

* tag 'for-f2fs-3.12' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: optimize gc for better performance
  f2fs: merge more bios of node block writes
  f2fs: avoid an overflow during utilization calculation
  f2fs: trigger GC when there are prefree segments
  f2fs: use strncasecmp() simplify the string comparison
  f2fs: fix omitting to update inode page
  f2fs: support the inline xattrs
  f2fs: add the truncate_xattr_node function
  f2fs: introduce __find_xattr for readability
  f2fs: reserve the xattr space dynamically
  f2fs: add flags for inline xattrs
  f2fs: fix error return code in init_f2fs_fs()
  f2fs: fix wrong BUG_ON condition
  f2fs: fix memory leak when init f2fs filesystem fail
  f2fs: fix a compound statement label error
  f2fs: avoid writing inode redundantly when creating a file
  f2fs: alloc_page() doesn't return an ERR_PTR
  f2fs: should cover i_xattr_nid with its xattr node page lock
  f2fs: check the free space first in new_node_page
  f2fs: clean up the needless end 'return' of void function
  ...

Merge tag 'for-f2fs-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This patch-set includes the following major enhancement patches.
   - add a sysfs to control reclaiming free segments
   - enhance the f2fs global lock procedures
   - enhance the victim selection flow
   - wait for selected node blocks during fsync
   - add some tracepoints
   - add a config to remove abundant BUG_ONs

  The other bug fixes are as follows.
   - fix deadlock on acl operations
   - fix some bugs with respect to orphan inodes

  And, there are a bunch of cleanups"

* tag 'for-f2fs-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (42 commits)
  f2fs: issue more large discard command
  f2fs: fix memory leak after kobject init failed in fill_super
  f2fs: cleanup waiting routine for writeback pages in cp
  f2fs: avoid to use a NULL point in destroy_segment_manager
  f2fs: remove unnecessary TestClearPageError when wait pages writeback
  f2fs: update f2fs document
  f2fs: avoid to wait all the node blocks during fsync
  f2fs: check all ones or zeros bitmap with bitops for better mount performance
  f2fs: change the method of calculating the number summary blocks
  f2fs: fix calculating incorrect free size when update xattr in __f2fs_setxattr
  f2fs: add an option to avoid unnecessary BUG_ONs
  f2fs: introduce CONFIG_F2FS_CHECK_FS for BUG_ON control
  f2fs: fix a deadlock during init_acl procedure
  f2fs: clean up acl flow for better readability
  f2fs: remove unnecessary segment bitmap updates
  f2fs: add tracepoint for vm_page_mkwrite
  f2fs: add tracepoint for set_page_dirty
  f2fs: remove redundant set_page_dirty from write_compacted_summaries
  f2fs: add reclaiming control by sysfs
  f2fs: introduce f2fs_balance_fs_bg for some background jobs
  ...

Change-Id: Ied5488471d49d64ce6abb4be19237c4e90829ff6
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
new file mode 100644
index 0000000..fa284d3
--- /dev/null
+++ b/fs/f2fs/segment.c
@@ -0,0 +1,1762 @@
+/*
+ * fs/f2fs/segment.c
+ *
+ * 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.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/prefetch.h>
+#include <linux/vmalloc.h>
+
+#include "f2fs.h"
+#include "segment.h"
+#include "node.h"
+#include <trace/events/f2fs.h>
+
+/*
+ * This function balances dirty node and dentry pages.
+ * In addition, it controls garbage collection.
+ */
+void f2fs_balance_fs(struct f2fs_sb_info *sbi)
+{
+	/*
+	 * We should do GC or end up with checkpoint, if there are so many dirty
+	 * dir/node pages without enough free segments.
+	 */
+	if (has_not_enough_free_secs(sbi, 0)) {
+		mutex_lock(&sbi->gc_mutex);
+		f2fs_gc(sbi);
+	}
+}
+
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
+{
+	/* check the # of cached NAT entries and prefree segments */
+	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
+				excess_prefree_segs(sbi))
+		f2fs_sync_fs(sbi->sb, true);
+}
+
+static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
+		enum dirty_type dirty_type)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
+	/* need not be added */
+	if (IS_CURSEG(sbi, segno))
+		return;
+
+	if (!test_and_set_bit(segno, dirty_i->dirty_segmap[dirty_type]))
+		dirty_i->nr_dirty[dirty_type]++;
+
+	if (dirty_type == DIRTY) {
+		struct seg_entry *sentry = get_seg_entry(sbi, segno);
+		enum dirty_type t = sentry->type;
+
+		if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
+			dirty_i->nr_dirty[t]++;
+	}
+}
+
+static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
+		enum dirty_type dirty_type)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
+	if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
+		dirty_i->nr_dirty[dirty_type]--;
+
+	if (dirty_type == DIRTY) {
+		struct seg_entry *sentry = get_seg_entry(sbi, segno);
+		enum dirty_type t = sentry->type;
+
+		if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
+			dirty_i->nr_dirty[t]--;
+
+		if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+			clear_bit(GET_SECNO(sbi, segno),
+						dirty_i->victim_secmap);
+	}
+}
+
+/*
+ * Should not occur error such as -ENOMEM.
+ * Adding dirty entry into seglist is not critical operation.
+ * If a given segment is one of current working segments, it won't be added.
+ */
+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;
+
+	if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
+		return;
+
+	mutex_lock(&dirty_i->seglist_lock);
+
+	valid_blocks = get_valid_blocks(sbi, segno, 0);
+
+	if (valid_blocks == 0) {
+		__locate_dirty_segment(sbi, segno, PRE);
+		__remove_dirty_segment(sbi, segno, DIRTY);
+	} else if (valid_blocks < sbi->blocks_per_seg) {
+		__locate_dirty_segment(sbi, segno, DIRTY);
+	} else {
+		/* Recovery routine with SSR needs this */
+		__remove_dirty_segment(sbi, segno, DIRTY);
+	}
+
+	mutex_unlock(&dirty_i->seglist_lock);
+}
+
+/*
+ * Should call clear_prefree_segments after checkpoint is done.
+ */
+static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	unsigned int segno = -1;
+	unsigned int total_segs = TOTAL_SEGS(sbi);
+
+	mutex_lock(&dirty_i->seglist_lock);
+	while (1) {
+		segno = find_next_bit(dirty_i->dirty_segmap[PRE], total_segs,
+				segno + 1);
+		if (segno >= total_segs)
+			break;
+		__set_test_and_free(sbi, segno);
+	}
+	mutex_unlock(&dirty_i->seglist_lock);
+}
+
+void clear_prefree_segments(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
+	unsigned int total_segs = TOTAL_SEGS(sbi);
+	unsigned int start = 0, end = -1;
+
+	mutex_lock(&dirty_i->seglist_lock);
+
+	while (1) {
+		int i;
+		start = find_next_bit(prefree_map, total_segs, end + 1);
+		if (start >= total_segs)
+			break;
+		end = find_next_zero_bit(prefree_map, total_segs, start + 1);
+
+		for (i = start; i < end; i++)
+			clear_bit(i, prefree_map);
+
+		dirty_i->nr_dirty[PRE] -= end - start;
+
+		if (!test_opt(sbi, DISCARD))
+			continue;
+
+		blkdev_issue_discard(sbi->sb->s_bdev,
+				START_BLOCK(sbi, start) <<
+				sbi->log_sectors_per_block,
+				(1 << (sbi->log_sectors_per_block +
+				sbi->log_blocks_per_seg)) * (end - start),
+				GFP_NOFS, 0);
+	}
+	mutex_unlock(&dirty_i->seglist_lock);
+}
+
+static void __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	if (!__test_and_set_bit(segno, sit_i->dirty_sentries_bitmap))
+		sit_i->dirty_sentries++;
+}
+
+static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
+					unsigned int segno, int modified)
+{
+	struct seg_entry *se = get_seg_entry(sbi, segno);
+	se->type = type;
+	if (modified)
+		__mark_sit_entry_dirty(sbi, segno);
+}
+
+static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+{
+	struct seg_entry *se;
+	unsigned int segno, offset;
+	long int new_vblocks;
+
+	segno = GET_SEGNO(sbi, blkaddr);
+
+	se = get_seg_entry(sbi, segno);
+	new_vblocks = se->valid_blocks + del;
+	offset = GET_SEGOFF_FROM_SEG0(sbi, blkaddr) & (sbi->blocks_per_seg - 1);
+
+	f2fs_bug_on((new_vblocks >> (sizeof(unsigned short) << 3) ||
+				(new_vblocks > sbi->blocks_per_seg)));
+
+	se->valid_blocks = new_vblocks;
+	se->mtime = get_mtime(sbi);
+	SIT_I(sbi)->max_mtime = se->mtime;
+
+	/* Update valid block bitmap */
+	if (del > 0) {
+		if (f2fs_set_bit(offset, se->cur_valid_map))
+			BUG();
+	} else {
+		if (!f2fs_clear_bit(offset, se->cur_valid_map))
+			BUG();
+	}
+	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
+		se->ckpt_valid_blocks += del;
+
+	__mark_sit_entry_dirty(sbi, segno);
+
+	/* update total number of valid blocks to be written in ckpt area */
+	SIT_I(sbi)->written_valid_blocks += del;
+
+	if (sbi->segs_per_sec > 1)
+		get_sec_entry(sbi, segno)->valid_blocks += del;
+}
+
+static void refresh_sit_entry(struct f2fs_sb_info *sbi,
+			block_t old_blkaddr, block_t new_blkaddr)
+{
+	update_sit_entry(sbi, new_blkaddr, 1);
+	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+		update_sit_entry(sbi, old_blkaddr, -1);
+}
+
+void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+{
+	unsigned int segno = GET_SEGNO(sbi, addr);
+	struct sit_info *sit_i = SIT_I(sbi);
+
+	f2fs_bug_on(addr == NULL_ADDR);
+	if (addr == NEW_ADDR)
+		return;
+
+	/* add it into sit main buffer */
+	mutex_lock(&sit_i->sentry_lock);
+
+	update_sit_entry(sbi, addr, -1);
+
+	/* add it into dirty seglist */
+	locate_dirty_segment(sbi, segno);
+
+	mutex_unlock(&sit_i->sentry_lock);
+}
+
+/*
+ * This function should be resided under the curseg_mutex lock
+ */
+static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
+					struct f2fs_summary *sum)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	void *addr = curseg->sum_blk;
+	addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
+	memcpy(addr, sum, sizeof(struct f2fs_summary));
+}
+
+/*
+ * Calculate the number of current summary pages for writing
+ */
+int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+{
+	int valid_sum_count = 0;
+	int i, sum_in_page;
+
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		if (sbi->ckpt->alloc_type[i] == SSR)
+			valid_sum_count += sbi->blocks_per_seg;
+		else
+			valid_sum_count += curseg_blkoff(sbi, i);
+	}
+
+	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
+			SUM_FOOTER_SIZE) / SUMMARY_SIZE;
+	if (valid_sum_count <= sum_in_page)
+		return 1;
+	else if ((valid_sum_count - sum_in_page) <=
+		(PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
+		return 2;
+	return 3;
+}
+
+/*
+ * Caller should put this summary page
+ */
+struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
+}
+
+static void write_sum_page(struct f2fs_sb_info *sbi,
+			struct f2fs_summary_block *sum_blk, block_t blk_addr)
+{
+	struct page *page = grab_meta_page(sbi, blk_addr);
+	void *kaddr = page_address(page);
+	memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE);
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+}
+
+static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int segno = curseg->segno + 1;
+	struct free_segmap_info *free_i = FREE_I(sbi);
+
+	if (segno < TOTAL_SEGS(sbi) && segno % sbi->segs_per_sec)
+		return !test_bit(segno, free_i->free_segmap);
+	return 0;
+}
+
+/*
+ * Find a new segment from the free segments bitmap to right order
+ * This function should be returned with success, otherwise BUG
+ */
+static void get_new_segment(struct f2fs_sb_info *sbi,
+			unsigned int *newseg, bool new_sec, int dir)
+{
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int segno, secno, zoneno;
+	unsigned int total_zones = TOTAL_SECS(sbi) / sbi->secs_per_zone;
+	unsigned int hint = *newseg / sbi->segs_per_sec;
+	unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
+	unsigned int left_start = hint;
+	bool init = true;
+	int go_left = 0;
+	int i;
+
+	write_lock(&free_i->segmap_lock);
+
+	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
+		segno = find_next_zero_bit(free_i->free_segmap,
+					TOTAL_SEGS(sbi), *newseg + 1);
+		if (segno - *newseg < sbi->segs_per_sec -
+					(*newseg % sbi->segs_per_sec))
+			goto got_it;
+	}
+find_other_zone:
+	secno = find_next_zero_bit(free_i->free_secmap, TOTAL_SECS(sbi), hint);
+	if (secno >= TOTAL_SECS(sbi)) {
+		if (dir == ALLOC_RIGHT) {
+			secno = find_next_zero_bit(free_i->free_secmap,
+							TOTAL_SECS(sbi), 0);
+			f2fs_bug_on(secno >= TOTAL_SECS(sbi));
+		} else {
+			go_left = 1;
+			left_start = hint - 1;
+		}
+	}
+	if (go_left == 0)
+		goto skip_left;
+
+	while (test_bit(left_start, free_i->free_secmap)) {
+		if (left_start > 0) {
+			left_start--;
+			continue;
+		}
+		left_start = find_next_zero_bit(free_i->free_secmap,
+							TOTAL_SECS(sbi), 0);
+		f2fs_bug_on(left_start >= TOTAL_SECS(sbi));
+		break;
+	}
+	secno = left_start;
+skip_left:
+	hint = secno;
+	segno = secno * sbi->segs_per_sec;
+	zoneno = secno / sbi->secs_per_zone;
+
+	/* give up on finding another zone */
+	if (!init)
+		goto got_it;
+	if (sbi->secs_per_zone == 1)
+		goto got_it;
+	if (zoneno == old_zoneno)
+		goto got_it;
+	if (dir == ALLOC_LEFT) {
+		if (!go_left && zoneno + 1 >= total_zones)
+			goto got_it;
+		if (go_left && zoneno == 0)
+			goto got_it;
+	}
+	for (i = 0; i < NR_CURSEG_TYPE; i++)
+		if (CURSEG_I(sbi, i)->zone == zoneno)
+			break;
+
+	if (i < NR_CURSEG_TYPE) {
+		/* zone is in user, try another */
+		if (go_left)
+			hint = zoneno * sbi->secs_per_zone - 1;
+		else if (zoneno + 1 >= total_zones)
+			hint = 0;
+		else
+			hint = (zoneno + 1) * sbi->secs_per_zone;
+		init = false;
+		goto find_other_zone;
+	}
+got_it:
+	/* set it as dirty segment in free segmap */
+	f2fs_bug_on(test_bit(segno, free_i->free_segmap));
+	__set_inuse(sbi, segno);
+	*newseg = segno;
+	write_unlock(&free_i->segmap_lock);
+}
+
+static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	struct summary_footer *sum_footer;
+
+	curseg->segno = curseg->next_segno;
+	curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno);
+	curseg->next_blkoff = 0;
+	curseg->next_segno = NULL_SEGNO;
+
+	sum_footer = &(curseg->sum_blk->footer);
+	memset(sum_footer, 0, sizeof(struct summary_footer));
+	if (IS_DATASEG(type))
+		SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
+	if (IS_NODESEG(type))
+		SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
+	__set_sit_entry_type(sbi, type, curseg->segno, modified);
+}
+
+/*
+ * Allocate a current working segment.
+ * This function always allocates a free segment in LFS manner.
+ */
+static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int segno = curseg->segno;
+	int dir = ALLOC_LEFT;
+
+	write_sum_page(sbi, curseg->sum_blk,
+				GET_SUM_BLOCK(sbi, segno));
+	if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA)
+		dir = ALLOC_RIGHT;
+
+	if (test_opt(sbi, NOHEAP))
+		dir = ALLOC_RIGHT;
+
+	get_new_segment(sbi, &segno, new_sec, dir);
+	curseg->next_segno = segno;
+	reset_curseg(sbi, type, 1);
+	curseg->alloc_type = LFS;
+}
+
+static void __next_free_blkoff(struct f2fs_sb_info *sbi,
+			struct curseg_info *seg, block_t start)
+{
+	struct seg_entry *se = get_seg_entry(sbi, seg->segno);
+	block_t ofs;
+	for (ofs = start; ofs < sbi->blocks_per_seg; ofs++) {
+		if (!f2fs_test_bit(ofs, se->ckpt_valid_map)
+			&& !f2fs_test_bit(ofs, se->cur_valid_map))
+			break;
+	}
+	seg->next_blkoff = ofs;
+}
+
+/*
+ * If a segment is written by LFS manner, next block offset is just obtained
+ * by increasing the current block offset. However, if a segment is written by
+ * SSR manner, next block offset obtained by calling __next_free_blkoff
+ */
+static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
+				struct curseg_info *seg)
+{
+	if (seg->alloc_type == SSR)
+		__next_free_blkoff(sbi, seg, seg->next_blkoff + 1);
+	else
+		seg->next_blkoff++;
+}
+
+/*
+ * This function always allocates a used segment (from dirty seglist) by SSR
+ * manner, so it should recover the existing segment information of valid blocks
+ */
+static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned int new_segno = curseg->next_segno;
+	struct f2fs_summary_block *sum_node;
+	struct page *sum_page;
+
+	write_sum_page(sbi, curseg->sum_blk,
+				GET_SUM_BLOCK(sbi, curseg->segno));
+	__set_test_and_inuse(sbi, new_segno);
+
+	mutex_lock(&dirty_i->seglist_lock);
+	__remove_dirty_segment(sbi, new_segno, PRE);
+	__remove_dirty_segment(sbi, new_segno, DIRTY);
+	mutex_unlock(&dirty_i->seglist_lock);
+
+	reset_curseg(sbi, type, 1);
+	curseg->alloc_type = SSR;
+	__next_free_blkoff(sbi, curseg, 0);
+
+	if (reuse) {
+		sum_page = get_sum_page(sbi, new_segno);
+		sum_node = (struct f2fs_summary_block *)page_address(sum_page);
+		memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
+		f2fs_put_page(sum_page, 1);
+	}
+}
+
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+
+	if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
+		return v_ops->get_victim(sbi,
+				&(curseg)->next_segno, BG_GC, type, SSR);
+
+	/* For data segments, let's do SSR more intensively */
+	for (; type >= CURSEG_HOT_DATA; type--)
+		if (v_ops->get_victim(sbi, &(curseg)->next_segno,
+						BG_GC, type, SSR))
+			return 1;
+	return 0;
+}
+
+/*
+ * flush out current segment and replace it with new segment
+ * This function should be returned with success, otherwise BUG
+ */
+static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
+						int type, bool force)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+
+	if (force)
+		new_curseg(sbi, type, true);
+	else if (type == CURSEG_WARM_NODE)
+		new_curseg(sbi, type, false);
+	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
+		new_curseg(sbi, type, false);
+	else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
+		change_curseg(sbi, type, true);
+	else
+		new_curseg(sbi, type, false);
+
+	stat_inc_seg_type(sbi, curseg);
+}
+
+void allocate_new_segments(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg;
+	unsigned int old_curseg;
+	int i;
+
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		curseg = CURSEG_I(sbi, i);
+		old_curseg = curseg->segno;
+		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+		locate_dirty_segment(sbi, old_curseg);
+	}
+}
+
+static const struct segment_allocation default_salloc_ops = {
+	.allocate_segment = allocate_segment_by_default,
+};
+
+static void f2fs_end_io_write(struct bio *bio, int err)
+{
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct bio_private *p = bio->bi_private;
+
+	do {
+		struct page *page = bvec->bv_page;
+
+		if (--bvec >= bio->bi_io_vec)
+			prefetchw(&bvec->bv_page->flags);
+		if (!uptodate) {
+			SetPageError(page);
+			if (page->mapping)
+				set_bit(AS_EIO, &page->mapping->flags);
+			set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
+			p->sbi->sb->s_flags |= MS_RDONLY;
+		}
+		end_page_writeback(page);
+		dec_page_count(p->sbi, F2FS_WRITEBACK);
+	} while (bvec >= bio->bi_io_vec);
+
+	if (p->is_sync)
+		complete(p->wait);
+
+	if (!get_pages(p->sbi, F2FS_WRITEBACK) &&
+			!list_empty(&p->sbi->cp_wait.task_list))
+		wake_up(&p->sbi->cp_wait);
+
+	kfree(p);
+	bio_put(bio);
+}
+
+struct bio *f2fs_bio_alloc(struct block_device *bdev, int npages)
+{
+	struct bio *bio;
+
+	/* No failure on bio allocation */
+	bio = bio_alloc(GFP_NOIO, npages);
+	bio->bi_bdev = bdev;
+	bio->bi_private = NULL;
+
+	return bio;
+}
+
+static void do_submit_bio(struct f2fs_sb_info *sbi,
+				enum page_type type, bool sync)
+{
+	int rw = sync ? WRITE_SYNC : WRITE;
+	enum page_type btype = type > META ? META : type;
+
+	if (type >= META_FLUSH)
+		rw = WRITE_FLUSH_FUA;
+
+	if (btype == META)
+		rw |= REQ_META;
+
+	if (sbi->bio[btype]) {
+		struct bio_private *p = sbi->bio[btype]->bi_private;
+		p->sbi = sbi;
+		sbi->bio[btype]->bi_end_io = f2fs_end_io_write;
+
+		trace_f2fs_do_submit_bio(sbi->sb, btype, sync, sbi->bio[btype]);
+
+		if (type == META_FLUSH) {
+			DECLARE_COMPLETION_ONSTACK(wait);
+			p->is_sync = true;
+			p->wait = &wait;
+			submit_bio(rw, sbi->bio[btype]);
+			wait_for_completion(&wait);
+		} else {
+			p->is_sync = false;
+			submit_bio(rw, sbi->bio[btype]);
+		}
+		sbi->bio[btype] = NULL;
+	}
+}
+
+void f2fs_submit_bio(struct f2fs_sb_info *sbi, enum page_type type, bool sync)
+{
+	down_write(&sbi->bio_sem);
+	do_submit_bio(sbi, type, sync);
+	up_write(&sbi->bio_sem);
+}
+
+static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page,
+				block_t blk_addr, enum page_type type)
+{
+	struct block_device *bdev = sbi->sb->s_bdev;
+	int bio_blocks;
+
+	verify_block_addr(sbi, blk_addr);
+
+	down_write(&sbi->bio_sem);
+
+	inc_page_count(sbi, F2FS_WRITEBACK);
+
+	if (sbi->bio[type] && sbi->last_block_in_bio[type] != blk_addr - 1)
+		do_submit_bio(sbi, type, false);
+alloc_new:
+	if (sbi->bio[type] == NULL) {
+		struct bio_private *priv;
+retry:
+		priv = kmalloc(sizeof(struct bio_private), GFP_NOFS);
+		if (!priv) {
+			cond_resched();
+			goto retry;
+		}
+
+		bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
+		sbi->bio[type] = f2fs_bio_alloc(bdev, bio_blocks);
+		sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+		sbi->bio[type]->bi_private = priv;
+		/*
+		 * The end_io will be assigned at the sumbission phase.
+		 * Until then, let bio_add_page() merge consecutive IOs as much
+		 * as possible.
+		 */
+	}
+
+	if (bio_add_page(sbi->bio[type], page, PAGE_CACHE_SIZE, 0) <
+							PAGE_CACHE_SIZE) {
+		do_submit_bio(sbi, type, false);
+		goto alloc_new;
+	}
+
+	sbi->last_block_in_bio[type] = blk_addr;
+
+	up_write(&sbi->bio_sem);
+	trace_f2fs_submit_write_page(page, blk_addr, type);
+}
+
+void f2fs_wait_on_page_writeback(struct page *page,
+				enum page_type type, bool sync)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+	if (PageWriteback(page)) {
+		f2fs_submit_bio(sbi, type, sync);
+		wait_on_page_writeback(page);
+	}
+}
+
+static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	if (curseg->next_blkoff < sbi->blocks_per_seg)
+		return true;
+	return false;
+}
+
+static int __get_segment_type_2(struct page *page, enum page_type p_type)
+{
+	if (p_type == DATA)
+		return CURSEG_HOT_DATA;
+	else
+		return CURSEG_HOT_NODE;
+}
+
+static int __get_segment_type_4(struct page *page, enum page_type p_type)
+{
+	if (p_type == DATA) {
+		struct inode *inode = page->mapping->host;
+
+		if (S_ISDIR(inode->i_mode))
+			return CURSEG_HOT_DATA;
+		else
+			return CURSEG_COLD_DATA;
+	} else {
+		if (IS_DNODE(page) && !is_cold_node(page))
+			return CURSEG_HOT_NODE;
+		else
+			return CURSEG_COLD_NODE;
+	}
+}
+
+static int __get_segment_type_6(struct page *page, enum page_type p_type)
+{
+	if (p_type == DATA) {
+		struct inode *inode = page->mapping->host;
+
+		if (S_ISDIR(inode->i_mode))
+			return CURSEG_HOT_DATA;
+		else if (is_cold_data(page) || file_is_cold(inode))
+			return CURSEG_COLD_DATA;
+		else
+			return CURSEG_WARM_DATA;
+	} else {
+		if (IS_DNODE(page))
+			return is_cold_node(page) ? CURSEG_WARM_NODE :
+						CURSEG_HOT_NODE;
+		else
+			return CURSEG_COLD_NODE;
+	}
+}
+
+static int __get_segment_type(struct page *page, enum page_type p_type)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+	switch (sbi->active_logs) {
+	case 2:
+		return __get_segment_type_2(page, p_type);
+	case 4:
+		return __get_segment_type_4(page, p_type);
+	}
+	/* NR_CURSEG_TYPE(6) logs by default */
+	f2fs_bug_on(sbi->active_logs != NR_CURSEG_TYPE);
+	return __get_segment_type_6(page, p_type);
+}
+
+static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
+			block_t old_blkaddr, block_t *new_blkaddr,
+			struct f2fs_summary *sum, enum page_type p_type)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct curseg_info *curseg;
+	unsigned int old_cursegno;
+	int type;
+
+	type = __get_segment_type(page, p_type);
+	curseg = CURSEG_I(sbi, type);
+
+	mutex_lock(&curseg->curseg_mutex);
+
+	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+	old_cursegno = curseg->segno;
+
+	/*
+	 * __add_sum_entry should be resided under the curseg_mutex
+	 * because, this function updates a summary entry in the
+	 * current summary block.
+	 */
+	__add_sum_entry(sbi, type, sum);
+
+	mutex_lock(&sit_i->sentry_lock);
+	__refresh_next_blkoff(sbi, curseg);
+
+	stat_inc_block_count(sbi, curseg);
+
+	/*
+	 * SIT information should be updated before segment allocation,
+	 * since SSR needs latest valid block information.
+	 */
+	refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
+
+	if (!__has_curseg_space(sbi, type))
+		sit_i->s_ops->allocate_segment(sbi, type, false);
+
+	locate_dirty_segment(sbi, old_cursegno);
+	locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+	mutex_unlock(&sit_i->sentry_lock);
+
+	if (p_type == NODE)
+		fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
+
+	/* writeout dirty page into bdev */
+	submit_write_page(sbi, page, *new_blkaddr, p_type);
+
+	mutex_unlock(&curseg->curseg_mutex);
+}
+
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
+{
+	set_page_writeback(page);
+	submit_write_page(sbi, page, page->index, META);
+}
+
+void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
+		unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+{
+	struct f2fs_summary sum;
+	set_summary(&sum, nid, 0, 0);
+	do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, NODE);
+}
+
+void write_data_page(struct inode *inode, struct page *page,
+		struct dnode_of_data *dn, block_t old_blkaddr,
+		block_t *new_blkaddr)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct f2fs_summary sum;
+	struct node_info ni;
+
+	f2fs_bug_on(old_blkaddr == NULL_ADDR);
+	get_node_info(sbi, dn->nid, &ni);
+	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
+
+	do_write_page(sbi, page, old_blkaddr,
+			new_blkaddr, &sum, DATA);
+}
+
+void rewrite_data_page(struct f2fs_sb_info *sbi, struct page *page,
+					block_t old_blk_addr)
+{
+	submit_write_page(sbi, page, old_blk_addr, DATA);
+}
+
+void recover_data_page(struct f2fs_sb_info *sbi,
+			struct page *page, struct f2fs_summary *sum,
+			block_t old_blkaddr, block_t new_blkaddr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct curseg_info *curseg;
+	unsigned int segno, old_cursegno;
+	struct seg_entry *se;
+	int type;
+
+	segno = GET_SEGNO(sbi, new_blkaddr);
+	se = get_seg_entry(sbi, segno);
+	type = se->type;
+
+	if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
+		if (old_blkaddr == NULL_ADDR)
+			type = CURSEG_COLD_DATA;
+		else
+			type = CURSEG_WARM_DATA;
+	}
+	curseg = CURSEG_I(sbi, type);
+
+	mutex_lock(&curseg->curseg_mutex);
+	mutex_lock(&sit_i->sentry_lock);
+
+	old_cursegno = curseg->segno;
+
+	/* change the current segment */
+	if (segno != curseg->segno) {
+		curseg->next_segno = segno;
+		change_curseg(sbi, type, true);
+	}
+
+	curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) &
+					(sbi->blocks_per_seg - 1);
+	__add_sum_entry(sbi, type, sum);
+
+	refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
+
+	locate_dirty_segment(sbi, old_cursegno);
+	locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+
+	mutex_unlock(&sit_i->sentry_lock);
+	mutex_unlock(&curseg->curseg_mutex);
+}
+
+void rewrite_node_page(struct f2fs_sb_info *sbi,
+			struct page *page, struct f2fs_summary *sum,
+			block_t old_blkaddr, block_t new_blkaddr)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	int type = CURSEG_WARM_NODE;
+	struct curseg_info *curseg;
+	unsigned int segno, old_cursegno;
+	block_t next_blkaddr = next_blkaddr_of_node(page);
+	unsigned int next_segno = GET_SEGNO(sbi, next_blkaddr);
+
+	curseg = CURSEG_I(sbi, type);
+
+	mutex_lock(&curseg->curseg_mutex);
+	mutex_lock(&sit_i->sentry_lock);
+
+	segno = GET_SEGNO(sbi, new_blkaddr);
+	old_cursegno = curseg->segno;
+
+	/* change the current segment */
+	if (segno != curseg->segno) {
+		curseg->next_segno = segno;
+		change_curseg(sbi, type, true);
+	}
+	curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) &
+					(sbi->blocks_per_seg - 1);
+	__add_sum_entry(sbi, type, sum);
+
+	/* change the current log to the next block addr in advance */
+	if (next_segno != segno) {
+		curseg->next_segno = next_segno;
+		change_curseg(sbi, type, true);
+	}
+	curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, next_blkaddr) &
+					(sbi->blocks_per_seg - 1);
+
+	/* rewrite node page */
+	set_page_writeback(page);
+	submit_write_page(sbi, page, new_blkaddr, NODE);
+	f2fs_submit_bio(sbi, NODE, true);
+	refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
+
+	locate_dirty_segment(sbi, old_cursegno);
+	locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+
+	mutex_unlock(&sit_i->sentry_lock);
+	mutex_unlock(&curseg->curseg_mutex);
+}
+
+static int read_compacted_summaries(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct curseg_info *seg_i;
+	unsigned char *kaddr;
+	struct page *page;
+	block_t start;
+	int i, j, offset;
+
+	start = start_sum_block(sbi);
+
+	page = get_meta_page(sbi, start++);
+	kaddr = (unsigned char *)page_address(page);
+
+	/* Step 1: restore nat cache */
+	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
+	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+
+	/* Step 2: restore sit cache */
+	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
+	memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
+						SUM_JOURNAL_SIZE);
+	offset = 2 * SUM_JOURNAL_SIZE;
+
+	/* Step 3: restore summary entries */
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		unsigned short blk_off;
+		unsigned int segno;
+
+		seg_i = CURSEG_I(sbi, i);
+		segno = le32_to_cpu(ckpt->cur_data_segno[i]);
+		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[i]);
+		seg_i->next_segno = segno;
+		reset_curseg(sbi, i, 0);
+		seg_i->alloc_type = ckpt->alloc_type[i];
+		seg_i->next_blkoff = blk_off;
+
+		if (seg_i->alloc_type == SSR)
+			blk_off = sbi->blocks_per_seg;
+
+		for (j = 0; j < blk_off; j++) {
+			struct f2fs_summary *s;
+			s = (struct f2fs_summary *)(kaddr + offset);
+			seg_i->sum_blk->entries[j] = *s;
+			offset += SUMMARY_SIZE;
+			if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+						SUM_FOOTER_SIZE)
+				continue;
+
+			f2fs_put_page(page, 1);
+			page = NULL;
+
+			page = get_meta_page(sbi, start++);
+			kaddr = (unsigned char *)page_address(page);
+			offset = 0;
+		}
+	}
+	f2fs_put_page(page, 1);
+	return 0;
+}
+
+static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct f2fs_summary_block *sum;
+	struct curseg_info *curseg;
+	struct page *new;
+	unsigned short blk_off;
+	unsigned int segno = 0;
+	block_t blk_addr = 0;
+
+	/* get segment number and block addr */
+	if (IS_DATASEG(type)) {
+		segno = le32_to_cpu(ckpt->cur_data_segno[type]);
+		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
+							CURSEG_HOT_DATA]);
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
+		else
+			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
+	} else {
+		segno = le32_to_cpu(ckpt->cur_node_segno[type -
+							CURSEG_HOT_NODE]);
+		blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
+							CURSEG_HOT_NODE]);
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+			blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
+							type - CURSEG_HOT_NODE);
+		else
+			blk_addr = GET_SUM_BLOCK(sbi, segno);
+	}
+
+	new = get_meta_page(sbi, blk_addr);
+	sum = (struct f2fs_summary_block *)page_address(new);
+
+	if (IS_NODESEG(type)) {
+		if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+			struct f2fs_summary *ns = &sum->entries[0];
+			int i;
+			for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
+				ns->version = 0;
+				ns->ofs_in_node = 0;
+			}
+		} else {
+			if (restore_node_summary(sbi, segno, sum)) {
+				f2fs_put_page(new, 1);
+				return -EINVAL;
+			}
+		}
+	}
+
+	/* set uncompleted segment to curseg */
+	curseg = CURSEG_I(sbi, type);
+	mutex_lock(&curseg->curseg_mutex);
+	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+	curseg->next_segno = segno;
+	reset_curseg(sbi, type, 0);
+	curseg->alloc_type = ckpt->alloc_type[type];
+	curseg->next_blkoff = blk_off;
+	mutex_unlock(&curseg->curseg_mutex);
+	f2fs_put_page(new, 1);
+	return 0;
+}
+
+static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
+{
+	int type = CURSEG_HOT_DATA;
+
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+		/* restore for compacted data summary */
+		if (read_compacted_summaries(sbi))
+			return -EINVAL;
+		type = CURSEG_HOT_NODE;
+	}
+
+	for (; type <= CURSEG_COLD_NODE; type++)
+		if (read_normal_summaries(sbi, type))
+			return -EINVAL;
+	return 0;
+}
+
+static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	struct page *page;
+	unsigned char *kaddr;
+	struct f2fs_summary *summary;
+	struct curseg_info *seg_i;
+	int written_size = 0;
+	int i, j;
+
+	page = grab_meta_page(sbi, blkaddr++);
+	kaddr = (unsigned char *)page_address(page);
+
+	/* Step 1: write nat cache */
+	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
+	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+	written_size += SUM_JOURNAL_SIZE;
+
+	/* Step 2: write sit cache */
+	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
+	memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
+						SUM_JOURNAL_SIZE);
+	written_size += SUM_JOURNAL_SIZE;
+
+	/* Step 3: write summary entries */
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		unsigned short blkoff;
+		seg_i = CURSEG_I(sbi, i);
+		if (sbi->ckpt->alloc_type[i] == SSR)
+			blkoff = sbi->blocks_per_seg;
+		else
+			blkoff = curseg_blkoff(sbi, i);
+
+		for (j = 0; j < blkoff; j++) {
+			if (!page) {
+				page = grab_meta_page(sbi, blkaddr++);
+				kaddr = (unsigned char *)page_address(page);
+				written_size = 0;
+			}
+			summary = (struct f2fs_summary *)(kaddr + written_size);
+			*summary = seg_i->sum_blk->entries[j];
+			written_size += SUMMARY_SIZE;
+
+			if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+							SUM_FOOTER_SIZE)
+				continue;
+
+			set_page_dirty(page);
+			f2fs_put_page(page, 1);
+			page = NULL;
+		}
+	}
+	if (page) {
+		set_page_dirty(page);
+		f2fs_put_page(page, 1);
+	}
+}
+
+static void write_normal_summaries(struct f2fs_sb_info *sbi,
+					block_t blkaddr, int type)
+{
+	int i, end;
+	if (IS_DATASEG(type))
+		end = type + NR_CURSEG_DATA_TYPE;
+	else
+		end = type + NR_CURSEG_NODE_TYPE;
+
+	for (i = type; i < end; i++) {
+		struct curseg_info *sum = CURSEG_I(sbi, i);
+		mutex_lock(&sum->curseg_mutex);
+		write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
+		mutex_unlock(&sum->curseg_mutex);
+	}
+}
+
+void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+{
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG))
+		write_compacted_summaries(sbi, start_blk);
+	else
+		write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
+}
+
+void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
+{
+	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
+		write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+}
+
+int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+					unsigned int val, int alloc)
+{
+	int i;
+
+	if (type == NAT_JOURNAL) {
+		for (i = 0; i < nats_in_cursum(sum); i++) {
+			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
+				return i;
+		}
+		if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
+			return update_nats_in_cursum(sum, 1);
+	} else if (type == SIT_JOURNAL) {
+		for (i = 0; i < sits_in_cursum(sum); i++)
+			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
+				return i;
+		if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
+			return update_sits_in_cursum(sum, 1);
+	}
+	return -1;
+}
+
+static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
+					unsigned int segno)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int offset = SIT_BLOCK_OFFSET(sit_i, segno);
+	block_t blk_addr = sit_i->sit_base_addr + offset;
+
+	check_seg_range(sbi, segno);
+
+	/* calculate sit block address */
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
+		blk_addr += sit_i->sit_blocks;
+
+	return get_meta_page(sbi, blk_addr);
+}
+
+static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
+					unsigned int start)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct page *src_page, *dst_page;
+	pgoff_t src_off, dst_off;
+	void *src_addr, *dst_addr;
+
+	src_off = current_sit_addr(sbi, start);
+	dst_off = next_sit_addr(sbi, src_off);
+
+	/* get current sit block page without lock */
+	src_page = get_meta_page(sbi, src_off);
+	dst_page = grab_meta_page(sbi, dst_off);
+	f2fs_bug_on(PageDirty(src_page));
+
+	src_addr = page_address(src_page);
+	dst_addr = page_address(dst_page);
+	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+
+	set_page_dirty(dst_page);
+	f2fs_put_page(src_page, 1);
+
+	set_to_next_sit(sit_i, start);
+
+	return dst_page;
+}
+
+static bool flush_sits_in_journal(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
+	struct f2fs_summary_block *sum = curseg->sum_blk;
+	int i;
+
+	/*
+	 * If the journal area in the current summary is full of sit entries,
+	 * all the sit entries will be flushed. Otherwise the sit entries
+	 * are not able to replace with newly hot sit entries.
+	 */
+	if (sits_in_cursum(sum) >= SIT_JOURNAL_ENTRIES) {
+		for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+			unsigned int segno;
+			segno = le32_to_cpu(segno_in_journal(sum, i));
+			__mark_sit_entry_dirty(sbi, segno);
+		}
+		update_sits_in_cursum(sum, -sits_in_cursum(sum));
+		return true;
+	}
+	return false;
+}
+
+/*
+ * CP calls this function, which flushes SIT entries including sit_journal,
+ * and moves prefree segs to free segs.
+ */
+void flush_sit_entries(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
+	struct f2fs_summary_block *sum = curseg->sum_blk;
+	unsigned long nsegs = TOTAL_SEGS(sbi);
+	struct page *page = NULL;
+	struct f2fs_sit_block *raw_sit = NULL;
+	unsigned int start = 0, end = 0;
+	unsigned int segno = -1;
+	bool flushed;
+
+	mutex_lock(&curseg->curseg_mutex);
+	mutex_lock(&sit_i->sentry_lock);
+
+	/*
+	 * "flushed" indicates whether sit entries in journal are flushed
+	 * to the SIT area or not.
+	 */
+	flushed = flush_sits_in_journal(sbi);
+
+	while ((segno = find_next_bit(bitmap, nsegs, segno + 1)) < nsegs) {
+		struct seg_entry *se = get_seg_entry(sbi, segno);
+		int sit_offset, offset;
+
+		sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
+
+		if (flushed)
+			goto to_sit_page;
+
+		offset = lookup_journal_in_cursum(sum, SIT_JOURNAL, segno, 1);
+		if (offset >= 0) {
+			segno_in_journal(sum, offset) = cpu_to_le32(segno);
+			seg_info_to_raw_sit(se, &sit_in_journal(sum, offset));
+			goto flush_done;
+		}
+to_sit_page:
+		if (!page || (start > segno) || (segno > end)) {
+			if (page) {
+				f2fs_put_page(page, 1);
+				page = NULL;
+			}
+
+			start = START_SEGNO(sit_i, segno);
+			end = start + SIT_ENTRY_PER_BLOCK - 1;
+
+			/* read sit block that will be updated */
+			page = get_next_sit_page(sbi, start);
+			raw_sit = page_address(page);
+		}
+
+		/* udpate entry in SIT block */
+		seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]);
+flush_done:
+		__clear_bit(segno, bitmap);
+		sit_i->dirty_sentries--;
+	}
+	mutex_unlock(&sit_i->sentry_lock);
+	mutex_unlock(&curseg->curseg_mutex);
+
+	/* writeout last modified SIT block */
+	f2fs_put_page(page, 1);
+
+	set_prefree_as_free_segments(sbi);
+}
+
+static int build_sit_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct sit_info *sit_i;
+	unsigned int sit_segs, start;
+	char *src_bitmap, *dst_bitmap;
+	unsigned int bitmap_size;
+
+	/* allocate memory for SIT information */
+	sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL);
+	if (!sit_i)
+		return -ENOMEM;
+
+	SM_I(sbi)->sit_info = sit_i;
+
+	sit_i->sentries = vzalloc(TOTAL_SEGS(sbi) * sizeof(struct seg_entry));
+	if (!sit_i->sentries)
+		return -ENOMEM;
+
+	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!sit_i->dirty_sentries_bitmap)
+		return -ENOMEM;
+
+	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+		sit_i->sentries[start].cur_valid_map
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		sit_i->sentries[start].ckpt_valid_map
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		if (!sit_i->sentries[start].cur_valid_map
+				|| !sit_i->sentries[start].ckpt_valid_map)
+			return -ENOMEM;
+	}
+
+	if (sbi->segs_per_sec > 1) {
+		sit_i->sec_entries = vzalloc(TOTAL_SECS(sbi) *
+					sizeof(struct sec_entry));
+		if (!sit_i->sec_entries)
+			return -ENOMEM;
+	}
+
+	/* get information related with SIT */
+	sit_segs = le32_to_cpu(raw_super->segment_count_sit) >> 1;
+
+	/* setup SIT bitmap from ckeckpoint pack */
+	bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
+	src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
+
+	dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+	if (!dst_bitmap)
+		return -ENOMEM;
+
+	/* init SIT information */
+	sit_i->s_ops = &default_salloc_ops;
+
+	sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
+	sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
+	sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
+	sit_i->sit_bitmap = dst_bitmap;
+	sit_i->bitmap_size = bitmap_size;
+	sit_i->dirty_sentries = 0;
+	sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
+	sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
+	sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec;
+	mutex_init(&sit_i->sentry_lock);
+	return 0;
+}
+
+static int build_free_segmap(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	struct free_segmap_info *free_i;
+	unsigned int bitmap_size, sec_bitmap_size;
+
+	/* allocate memory for free segmap information */
+	free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL);
+	if (!free_i)
+		return -ENOMEM;
+
+	SM_I(sbi)->free_info = free_i;
+
+	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+	free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
+	if (!free_i->free_segmap)
+		return -ENOMEM;
+
+	sec_bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+	free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
+	if (!free_i->free_secmap)
+		return -ENOMEM;
+
+	/* set all segments as dirty temporarily */
+	memset(free_i->free_segmap, 0xff, bitmap_size);
+	memset(free_i->free_secmap, 0xff, sec_bitmap_size);
+
+	/* init free segmap information */
+	free_i->start_segno =
+		(unsigned int) GET_SEGNO_FROM_SEG0(sbi, sm_info->main_blkaddr);
+	free_i->free_segments = 0;
+	free_i->free_sections = 0;
+	rwlock_init(&free_i->segmap_lock);
+	return 0;
+}
+
+static int build_curseg(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *array;
+	int i;
+
+	array = kzalloc(sizeof(*array) * NR_CURSEG_TYPE, GFP_KERNEL);
+	if (!array)
+		return -ENOMEM;
+
+	SM_I(sbi)->curseg_array = array;
+
+	for (i = 0; i < NR_CURSEG_TYPE; i++) {
+		mutex_init(&array[i].curseg_mutex);
+		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+		if (!array[i].sum_blk)
+			return -ENOMEM;
+		array[i].segno = NULL_SEGNO;
+		array[i].next_blkoff = 0;
+	}
+	return restore_curseg_summaries(sbi);
+}
+
+static void build_sit_entries(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
+	struct f2fs_summary_block *sum = curseg->sum_blk;
+	unsigned int start;
+
+	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+		struct seg_entry *se = &sit_i->sentries[start];
+		struct f2fs_sit_block *sit_blk;
+		struct f2fs_sit_entry sit;
+		struct page *page;
+		int i;
+
+		mutex_lock(&curseg->curseg_mutex);
+		for (i = 0; i < sits_in_cursum(sum); i++) {
+			if (le32_to_cpu(segno_in_journal(sum, i)) == start) {
+				sit = sit_in_journal(sum, i);
+				mutex_unlock(&curseg->curseg_mutex);
+				goto got_it;
+			}
+		}
+		mutex_unlock(&curseg->curseg_mutex);
+		page = get_current_sit_page(sbi, start);
+		sit_blk = (struct f2fs_sit_block *)page_address(page);
+		sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
+		f2fs_put_page(page, 1);
+got_it:
+		check_block_count(sbi, start, &sit);
+		seg_info_from_raw_sit(se, &sit);
+		if (sbi->segs_per_sec > 1) {
+			struct sec_entry *e = get_sec_entry(sbi, start);
+			e->valid_blocks += se->valid_blocks;
+		}
+	}
+}
+
+static void init_free_segmap(struct f2fs_sb_info *sbi)
+{
+	unsigned int start;
+	int type;
+
+	for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+		struct seg_entry *sentry = get_seg_entry(sbi, start);
+		if (!sentry->valid_blocks)
+			__set_free(sbi, start);
+	}
+
+	/* set use the current segments */
+	for (type = CURSEG_HOT_DATA; type <= CURSEG_COLD_NODE; type++) {
+		struct curseg_info *curseg_t = CURSEG_I(sbi, type);
+		__set_test_and_inuse(sbi, curseg_t->segno);
+	}
+}
+
+static void init_dirty_segmap(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	struct free_segmap_info *free_i = FREE_I(sbi);
+	unsigned int segno = 0, offset = 0, total_segs = TOTAL_SEGS(sbi);
+	unsigned short valid_blocks;
+
+	while (1) {
+		/* find dirty segment based on free segmap */
+		segno = find_next_inuse(free_i, total_segs, offset);
+		if (segno >= total_segs)
+			break;
+		offset = segno + 1;
+		valid_blocks = get_valid_blocks(sbi, segno, 0);
+		if (valid_blocks >= sbi->blocks_per_seg || !valid_blocks)
+			continue;
+		mutex_lock(&dirty_i->seglist_lock);
+		__locate_dirty_segment(sbi, segno, DIRTY);
+		mutex_unlock(&dirty_i->seglist_lock);
+	}
+}
+
+static int init_victim_secmap(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	unsigned int bitmap_size = f2fs_bitmap_size(TOTAL_SECS(sbi));
+
+	dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!dirty_i->victim_secmap)
+		return -ENOMEM;
+	return 0;
+}
+
+static int build_dirty_segmap(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i;
+	unsigned int bitmap_size, i;
+
+	/* allocate memory for dirty segments list information */
+	dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL);
+	if (!dirty_i)
+		return -ENOMEM;
+
+	SM_I(sbi)->dirty_info = dirty_i;
+	mutex_init(&dirty_i->seglist_lock);
+
+	bitmap_size = f2fs_bitmap_size(TOTAL_SEGS(sbi));
+
+	for (i = 0; i < NR_DIRTY_TYPE; i++) {
+		dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
+		if (!dirty_i->dirty_segmap[i])
+			return -ENOMEM;
+	}
+
+	init_dirty_segmap(sbi);
+	return init_victim_secmap(sbi);
+}
+
+/*
+ * Update min, max modified time for cost-benefit GC algorithm
+ */
+static void init_min_max_mtime(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int segno;
+
+	mutex_lock(&sit_i->sentry_lock);
+
+	sit_i->min_mtime = LLONG_MAX;
+
+	for (segno = 0; segno < TOTAL_SEGS(sbi); segno += sbi->segs_per_sec) {
+		unsigned int i;
+		unsigned long long mtime = 0;
+
+		for (i = 0; i < sbi->segs_per_sec; i++)
+			mtime += get_seg_entry(sbi, segno + i)->mtime;
+
+		mtime = div_u64(mtime, sbi->segs_per_sec);
+
+		if (sit_i->min_mtime > mtime)
+			sit_i->min_mtime = mtime;
+	}
+	sit_i->max_mtime = get_mtime(sbi);
+	mutex_unlock(&sit_i->sentry_lock);
+}
+
+int build_segment_manager(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct f2fs_sm_info *sm_info;
+	int err;
+
+	sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL);
+	if (!sm_info)
+		return -ENOMEM;
+
+	/* init sm info */
+	sbi->sm_info = sm_info;
+	INIT_LIST_HEAD(&sm_info->wblist_head);
+	spin_lock_init(&sm_info->wblist_lock);
+	sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+	sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+	sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
+	sm_info->reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+	sm_info->ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+	sm_info->main_segments = le32_to_cpu(raw_super->segment_count_main);
+	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+	sm_info->rec_prefree_segments = DEF_RECLAIM_PREFREE_SEGMENTS;
+
+	err = build_sit_info(sbi);
+	if (err)
+		return err;
+	err = build_free_segmap(sbi);
+	if (err)
+		return err;
+	err = build_curseg(sbi);
+	if (err)
+		return err;
+
+	/* reinit free segmap based on SIT */
+	build_sit_entries(sbi);
+
+	init_free_segmap(sbi);
+	err = build_dirty_segmap(sbi);
+	if (err)
+		return err;
+
+	init_min_max_mtime(sbi);
+	return 0;
+}
+
+static void discard_dirty_segmap(struct f2fs_sb_info *sbi,
+		enum dirty_type dirty_type)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
+	mutex_lock(&dirty_i->seglist_lock);
+	kfree(dirty_i->dirty_segmap[dirty_type]);
+	dirty_i->nr_dirty[dirty_type] = 0;
+	mutex_unlock(&dirty_i->seglist_lock);
+}
+
+static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	kfree(dirty_i->victim_secmap);
+}
+
+static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
+{
+	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	int i;
+
+	if (!dirty_i)
+		return;
+
+	/* discard pre-free/dirty segments list */
+	for (i = 0; i < NR_DIRTY_TYPE; i++)
+		discard_dirty_segmap(sbi, i);
+
+	destroy_victim_secmap(sbi);
+	SM_I(sbi)->dirty_info = NULL;
+	kfree(dirty_i);
+}
+
+static void destroy_curseg(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *array = SM_I(sbi)->curseg_array;
+	int i;
+
+	if (!array)
+		return;
+	SM_I(sbi)->curseg_array = NULL;
+	for (i = 0; i < NR_CURSEG_TYPE; i++)
+		kfree(array[i].sum_blk);
+	kfree(array);
+}
+
+static void destroy_free_segmap(struct f2fs_sb_info *sbi)
+{
+	struct free_segmap_info *free_i = SM_I(sbi)->free_info;
+	if (!free_i)
+		return;
+	SM_I(sbi)->free_info = NULL;
+	kfree(free_i->free_segmap);
+	kfree(free_i->free_secmap);
+	kfree(free_i);
+}
+
+static void destroy_sit_info(struct f2fs_sb_info *sbi)
+{
+	struct sit_info *sit_i = SIT_I(sbi);
+	unsigned int start;
+
+	if (!sit_i)
+		return;
+
+	if (sit_i->sentries) {
+		for (start = 0; start < TOTAL_SEGS(sbi); start++) {
+			kfree(sit_i->sentries[start].cur_valid_map);
+			kfree(sit_i->sentries[start].ckpt_valid_map);
+		}
+	}
+	vfree(sit_i->sentries);
+	vfree(sit_i->sec_entries);
+	kfree(sit_i->dirty_sentries_bitmap);
+
+	SM_I(sbi)->sit_info = NULL;
+	kfree(sit_i->sit_bitmap);
+	kfree(sit_i);
+}
+
+void destroy_segment_manager(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_sm_info *sm_info = SM_I(sbi);
+	if (!sm_info)
+		return;
+	destroy_dirty_segmap(sbi);
+	destroy_curseg(sbi);
+	destroy_free_segmap(sbi);
+	destroy_sit_info(sbi);
+	sbi->sm_info = NULL;
+	kfree(sm_info);
+}