1 files changed, 571 insertions, 336 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 7965957dd0e6..a288de069164 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -86,6 +86,7 @@ static inline unsigned long __reverse_ffs(unsigned long word)
 /*
  * __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
  * f2fs_set_bit makes MSB and LSB reversed in a byte.
+ * @size must be integral times of unsigned long.
  * Example:
  *                             MSB <--> LSB
  *   f2fs_set_bit(0, bitmap) => 1000 0000
@@ -95,94 +96,73 @@ static unsigned long __find_rev_next_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-	tmp &= ~0UL >> offset;
-
-	if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG-1)) {
+
+	while (1) {
+		if (*p == 0)
+			goto pass;
+
 		tmp = __reverse_ulong((unsigned char *)p);
+
+		tmp &= ~0UL >> offset;
+		if (size < BITS_PER_LONG)
+			tmp &= (~0UL << (BITS_PER_LONG - size));
 		if (tmp)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
-		return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp &= (~0UL << (BITS_PER_LONG - size));
-	if (!tmp)		/* Are any bits set? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffs(tmp);
+	return result;
+found:
+	return result - size + __reverse_ffs(tmp);
 }
 
 static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
 			unsigned long size, unsigned long offset)
 {
 	const unsigned long *p = addr + BIT_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long result = size;
 	unsigned long tmp;
 
 	if (offset >= size)
 		return size;
 
-	size -= result;
+	size -= (offset & ~(BITS_PER_LONG - 1));
 	offset %= BITS_PER_LONG;
-	if (!offset)
-		goto aligned;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-	tmp |= ~((~0UL << offset) >> offset);
-
-	if (size < BITS_PER_LONG)
-		goto found_first;
-	if (tmp != ~0UL)
-		goto found_middle;
-
-	size -= BITS_PER_LONG;
-	result += BITS_PER_LONG;
-	p++;
-aligned:
-	while (size & ~(BITS_PER_LONG - 1)) {
+
+	while (1) {
+		if (*p == ~0UL)
+			goto pass;
+
 		tmp = __reverse_ulong((unsigned char *)p);
+
+		if (offset)
+			tmp |= ~0UL << (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			tmp |= ~0UL >> size;
 		if (tmp != ~0UL)
-			goto found_middle;
-		result += BITS_PER_LONG;
+			goto found;
+pass:
+		if (size <= BITS_PER_LONG)
+			break;
 		size -= BITS_PER_LONG;
+		offset = 0;
 		p++;
 	}
-	if (!size)
-		return result;
-
-	tmp = __reverse_ulong((unsigned char *)p);
-found_first:
-	tmp |= ~(~0UL << (BITS_PER_LONG - size));
-	if (tmp == ~0UL)	/* Are any bits zero? */
-		return result + size;   /* Nope. */
-found_middle:
-	return result + __reverse_ffz(tmp);
+	return result;
+found:
+	return result - size + __reverse_ffz(tmp);
 }
 
 void register_inmem_page(struct inode *inode, struct page *page)
@@ -211,69 +191,150 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	trace_f2fs_register_inmem_page(page, INMEM);
 }
 
-int commit_inmem_pages(struct inode *inode, bool abort)
+static int __revoke_inmem_pages(struct inode *inode,
+				struct list_head *head, bool drop, bool recover)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct inmem_pages *cur, *tmp;
+	int err = 0;
+
+	list_for_each_entry_safe(cur, tmp, head, list) {
+		struct page *page = cur->page;
+
+		if (drop)
+			trace_f2fs_commit_inmem_page(page, INMEM_DROP);
+
+		lock_page(page);
+
+		if (recover) {
+			struct dnode_of_data dn;
+			struct node_info ni;
+
+			trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
+
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+				err = -EAGAIN;
+				goto next;
+			}
+			get_node_info(sbi, dn.nid, &ni);
+			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+					cur->old_addr, ni.version, true, true);
+			f2fs_put_dnode(&dn);
+		}
+next:
+		/* we don't need to invalidate this in the sccessful status */
+		if (drop || recover)
+			ClearPageUptodate(page);
+		set_page_private(page, 0);
+		ClearPagePrivate(page);
+		f2fs_put_page(page, 1);
+
+		list_del(&cur->list);
+		kmem_cache_free(inmem_entry_slab, cur);
+		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	}
+	return err;
+}
+
+void drop_inmem_pages(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	clear_inode_flag(inode, FI_ATOMIC_FILE);
+
+	mutex_lock(&fi->inmem_lock);
+	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	mutex_unlock(&fi->inmem_lock);
+}
+
+static int __commit_inmem_pages(struct inode *inode,
+					struct list_head *revoke_list)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct inmem_pages *cur, *tmp;
-	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
+	bool submit_bio = false;
 	int err = 0;
 
-	/*
-	 * The abort is true only when f2fs_evict_inode is called.
-	 * Basically, the f2fs_evict_inode doesn't produce any data writes, so
-	 * that we don't need to call f2fs_balance_fs.
-	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
-	 * inode becomes free by iget_locked in f2fs_iget.
-	 */
-	if (!abort) {
-		f2fs_balance_fs(sbi);
-		f2fs_lock_op(sbi);
-	}
-
-	mutex_lock(&fi->inmem_lock);
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-		lock_page(cur->page);
-		if (!abort) {
-			if (cur->page->mapping == inode->i_mapping) {
-				set_page_dirty(cur->page);
-				f2fs_wait_on_page_writeback(cur->page, DATA);
-				if (clear_page_dirty_for_io(cur->page))
-					inode_dec_dirty_pages(inode);
-				trace_f2fs_commit_inmem_page(cur->page, INMEM);
-				fio.page = cur->page;
-				err = do_write_data_page(&fio);
-				if (err) {
-					unlock_page(cur->page);
-					break;
-				}
-				clear_cold_data(cur->page);
-				submit_bio = true;
+		struct page *page = cur->page;
+
+		lock_page(page);
+		if (page->mapping == inode->i_mapping) {
+			trace_f2fs_commit_inmem_page(page, INMEM);
+
+			set_page_dirty(page);
+			f2fs_wait_on_page_writeback(page, DATA, true);
+			if (clear_page_dirty_for_io(page)) {
+				inode_dec_dirty_pages(inode);
+				remove_dirty_inode(inode);
 			}
-		} else {
-			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
+
+			fio.page = page;
+			err = do_write_data_page(&fio);
+			if (err) {
+				unlock_page(page);
+				break;
+			}
+
+			/* record old blkaddr for revoking */
+			cur->old_addr = fio.old_blkaddr;
+
+			submit_bio = true;
 		}
-		set_page_private(cur->page, 0);
-		ClearPagePrivate(cur->page);
-		f2fs_put_page(cur->page, 1);
+		unlock_page(page);
+		list_move_tail(&cur->list, revoke_list);
+	}
 
-		list_del(&cur->list);
-		kmem_cache_free(inmem_entry_slab, cur);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	if (submit_bio)
+		f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+
+	if (!err)
+		__revoke_inmem_pages(inode, revoke_list, false, false);
+
+	return err;
+}
+
+int commit_inmem_pages(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct list_head revoke_list;
+	int err;
+
+	INIT_LIST_HEAD(&revoke_list);
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+
+	mutex_lock(&fi->inmem_lock);
+	err = __commit_inmem_pages(inode, &revoke_list);
+	if (err) {
+		int ret;
+		/*
+		 * try to revoke all committed pages, but still we could fail
+		 * due to no memory or other reason, if that happened, EAGAIN
+		 * will be returned, which means in such case, transaction is
+		 * already not integrity, caller should use journal to do the
+		 * recovery or rewrite & commit last transaction. For other
+		 * error number, revoking was done by filesystem itself.
+		 */
+		ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
+		if (ret)
+			err = ret;
+
+		/* drop all uncommitted pages */
+		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	}
 	mutex_unlock(&fi->inmem_lock);
 
-	if (!abort) {
-		f2fs_unlock_op(sbi);
-		if (submit_bio)
-			f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	}
+	f2fs_unlock_op(sbi);
 	return err;
 }
 
@@ -281,15 +342,27 @@ int commit_inmem_pages(struct inode *inode, bool abort)
  * This function balances dirty node and dentry pages.
  * In addition, it controls garbage collection.
  */
-void f2fs_balance_fs(struct f2fs_sb_info *sbi)
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_CHECKPOINT))
+		f2fs_stop_checkpoint(sbi, false);
+#endif
+
+	if (!need)
+		return;
+
+	/* balance_fs_bg is able to be pending */
+	if (excess_cached_nats(sbi))
+		f2fs_balance_fs_bg(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)) {
+	if (has_not_enough_free_secs(sbi, 0, 0)) {
 		mutex_lock(&sbi->gc_mutex);
-		f2fs_gc(sbi, false);
+		f2fs_gc(sbi, false, false);
 	}
 }
 
@@ -304,14 +377,55 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 		try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
 
 	if (!available_free_memory(sbi, FREE_NIDS))
-		try_to_free_nids(sbi, NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES);
+		try_to_free_nids(sbi, MAX_FREE_NIDS);
+	else
+		build_free_nids(sbi, false);
+
+	if (!is_idle(sbi))
+		return;
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
-			excess_prefree_segs(sbi) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
-			jiffies > sbi->cp_expires)
+			excess_prefree_segs(sbi) ||
+			excess_dirty_nats(sbi) ||
+			f2fs_time_over(sbi, CP_TIME)) {
+		if (test_opt(sbi, DATA_FLUSH)) {
+			struct blk_plug plug;
+
+			blk_start_plug(&plug);
+			sync_dirty_inodes(sbi, FILE_INODE);
+			blk_finish_plug(&plug);
+		}
 		f2fs_sync_fs(sbi->sb, true);
+		stat_inc_bg_cp_count(sbi->stat_info);
+	}
+}
+
+static int __submit_flush_wait(struct block_device *bdev)
+{
+	struct bio *bio = f2fs_bio_alloc(0);
+	int ret;
+
+	bio->bi_bdev = bdev;
+	ret = submit_bio_wait(WRITE_FLUSH, bio);
+	bio_put(bio);
+	return ret;
+}
+
+static int submit_flush_wait(struct f2fs_sb_info *sbi)
+{
+	int ret = __submit_flush_wait(sbi->sb->s_bdev);
+	int i;
+
+	if (sbi->s_ndevs && !ret) {
+		for (i = 1; i < sbi->s_ndevs; i++) {
+			ret = __submit_flush_wait(FDEV(i).bdev);
+			if (ret)
+				break;
+		}
+	}
+	return ret;
 }
 
 static int issue_flush_thread(void *data)
@@ -324,24 +438,18 @@ repeat:
 		return 0;
 
 	if (!llist_empty(&fcc->issue_list)) {
-		struct bio *bio;
 		struct flush_cmd *cmd, *next;
 		int ret;
 
-		bio = f2fs_bio_alloc(0);
-
 		fcc->dispatch_list = llist_del_all(&fcc->issue_list);
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
-		bio->bi_bdev = sbi->sb->s_bdev;
-		ret = submit_bio_wait(WRITE_FLUSH, bio);
-
+		ret = submit_flush_wait(sbi);
 		llist_for_each_entry_safe(cmd, next,
 					  fcc->dispatch_list, llnode) {
 			cmd->ret = ret;
 			complete(&cmd->wait);
 		}
-		bio_put(bio);
 		fcc->dispatch_list = NULL;
 	}
 
@@ -361,24 +469,30 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 	if (test_opt(sbi, NOBARRIER))
 		return 0;
 
-	if (!test_opt(sbi, FLUSH_MERGE)) {
-		struct bio *bio = f2fs_bio_alloc(0);
+	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
 		int ret;
 
-		bio->bi_bdev = sbi->sb->s_bdev;
-		ret = submit_bio_wait(WRITE_FLUSH, bio);
-		bio_put(bio);
+		atomic_inc(&fcc->submit_flush);
+		ret = submit_flush_wait(sbi);
+		atomic_dec(&fcc->submit_flush);
 		return ret;
 	}
 
 	init_completion(&cmd.wait);
 
+	atomic_inc(&fcc->submit_flush);
 	llist_add(&cmd.llnode, &fcc->issue_list);
 
 	if (!fcc->dispatch_list)
 		wake_up(&fcc->flush_wait_queue);
 
-	wait_for_completion(&cmd.wait);
+	if (fcc->f2fs_issue_flush) {
+		wait_for_completion(&cmd.wait);
+		atomic_dec(&fcc->submit_flush);
+	} else {
+		llist_del_all(&fcc->issue_list);
+		atomic_set(&fcc->submit_flush, 0);
+	}
 
 	return cmd.ret;
 }
@@ -389,12 +503,19 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	struct flush_cmd_control *fcc;
 	int err = 0;
 
+	if (SM_I(sbi)->cmd_control_info) {
+		fcc = SM_I(sbi)->cmd_control_info;
+		goto init_thread;
+	}
+
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
+	atomic_set(&fcc->submit_flush, 0);
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
 	SM_I(sbi)->cmd_control_info = fcc;
+init_thread:
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
@@ -407,14 +528,20 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	return err;
 }
 
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 {
 	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
 
-	if (fcc && fcc->f2fs_issue_flush)
-		kthread_stop(fcc->f2fs_issue_flush);
-	kfree(fcc);
-	SM_I(sbi)->cmd_control_info = NULL;
+	if (fcc && fcc->f2fs_issue_flush) {
+		struct task_struct *flush_thread = fcc->f2fs_issue_flush;
+
+		fcc->f2fs_issue_flush = NULL;
+		kthread_stop(flush_thread);
+	}
+	if (free) {
+		kfree(fcc);
+		SM_I(sbi)->cmd_control_info = NULL;
+	}
 }
 
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -493,46 +620,107 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
-				block_t blkstart, block_t blklen)
+#ifdef CONFIG_BLK_DEV_ZONED
+static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+	sector_t nr_sects = SECTOR_FROM_BLOCK(blklen);
+	sector_t sector;
+	int devi = 0;
+
+	if (sbi->s_ndevs) {
+		devi = f2fs_target_device_index(sbi, blkstart);
+		blkstart -= FDEV(devi).start_blk;
+	}
+	sector = SECTOR_FROM_BLOCK(blkstart);
+
+	if (sector & (bdev_zone_size(bdev) - 1) ||
+				nr_sects != bdev_zone_size(bdev)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"(%d) %s: Unaligned discard attempted (block %x + %x)",
+			devi, sbi->s_ndevs ? FDEV(devi).path: "",
+			blkstart, blklen);
+		return -EIO;
+	}
+
+	/*
+	 * We need to know the type of the zone: for conventional zones,
+	 * use regular discard if the drive supports it. For sequential
+	 * zones, reset the zone write pointer.
+	 */
+	switch (get_blkz_type(sbi, bdev, blkstart)) {
+
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (!blk_queue_discard(bdev_get_queue(bdev)))
+			return 0;
+		return blkdev_issue_discard(bdev, sector, nr_sects,
+						GFP_NOFS, 0);
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		trace_f2fs_issue_reset_zone(sbi->sb, blkstart);
+		return blkdev_reset_zones(bdev, sector,
+					  nr_sects, GFP_NOFS);
+	default:
+		/* Unknown zone type: broken device ? */
+		return -EIO;
+	}
+}
+#endif
+
+static int __issue_discard_async(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
 	sector_t start = SECTOR_FROM_BLOCK(blkstart);
 	sector_t len = SECTOR_FROM_BLOCK(blklen);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
+				bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+		return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
+#endif
+	return blkdev_issue_discard(bdev, start, len, GFP_NOFS, 0);
+}
+
+static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
+				block_t blkstart, block_t blklen)
+{
+	sector_t start = blkstart, len = 0;
+	struct block_device *bdev;
 	struct seg_entry *se;
 	unsigned int offset;
 	block_t i;
+	int err = 0;
+
+	bdev = f2fs_target_device(sbi, blkstart, NULL);
+
+	for (i = blkstart; i < blkstart + blklen; i++, len++) {
+		if (i != start) {
+			struct block_device *bdev2 =
+				f2fs_target_device(sbi, i, NULL);
+
+			if (bdev2 != bdev) {
+				err = __issue_discard_async(sbi, bdev,
+						start, len);
+				if (err)
+					return err;
+				bdev = bdev2;
+				start = i;
+				len = 0;
+			}
+		}
 
-	for (i = blkstart; i < blkstart + blklen; i++) {
 		se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
 		offset = GET_BLKOFF_FROM_SEG0(sbi, i);
 
 		if (!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
 	}
-	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
-	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
-}
-
-bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
-{
-	int err = -ENOTSUPP;
-
-	if (test_opt(sbi, DISCARD)) {
-		struct seg_entry *se = get_seg_entry(sbi,
-				GET_SEGNO(sbi, blkaddr));
-		unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
 
-		if (f2fs_test_bit(offset, se->discard_map))
-			return false;
-
-		err = f2fs_issue_discard(sbi, blkaddr, 1);
-	}
+	if (len)
+		err = __issue_discard_async(sbi, bdev, start, len);
 
-	if (err) {
-		update_meta_page(sbi, NULL, blkaddr);
-		return true;
-	}
-	return false;
+	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+	return err;
 }
 
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
@@ -573,7 +761,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	bool force = (cpc->reason == CP_DISCARD);
 	int i;
 
-	if (se->valid_blocks == max_blocks)
+	if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
 		return;
 
 	if (!force) {
@@ -593,6 +781,10 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			break;
 
 		end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
+		if (force && start && end != max_blocks
+					&& (end - start) < cpc->trim_minlen)
+			continue;
+
 		__add_discard_entry(sbi, cpc, se, start, end);
 	}
 }
@@ -630,6 +822,8 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
 	unsigned int start = 0, end = -1;
+	unsigned int secno, start_segno;
+	bool force = (cpc->reason == CP_DISCARD);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -646,17 +840,31 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 		dirty_i->nr_dirty[PRE] -= end - start;
 
-		if (!test_opt(sbi, DISCARD))
+		if (force || !test_opt(sbi, DISCARD))
 			continue;
 
-		f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
+			continue;
+		}
+next:
+		secno = GET_SECNO(sbi, start);
+		start_segno = secno * sbi->segs_per_sec;
+		if (!IS_CURSEC(sbi, secno) &&
+			!get_valid_blocks(sbi, start, sbi->segs_per_sec))
+			f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+				sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+		start = start_segno + sbi->segs_per_sec;
+		if (start < end)
+			goto next;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
-		if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+		if (force && entry->len < cpc->trim_minlen)
 			goto skip;
 		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
 		cpc->trimmed += entry->len;
@@ -711,12 +919,14 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 	if (del > 0) {
 		if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
-		if (!f2fs_test_and_set_bit(offset, se->discard_map))
+		if (f2fs_discard_en(sbi) &&
+			!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
 	} else {
 		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
-		if (f2fs_test_and_clear_bit(offset, se->discard_map))
+		if (f2fs_discard_en(sbi) &&
+			f2fs_test_and_clear_bit(offset, se->discard_map))
 			sbi->discard_blks++;
 	}
 	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
@@ -817,12 +1027,12 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
 		}
 	}
 
-	sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
+	sum_in_page = (PAGE_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)
+		(PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
 		return 2;
 	return 3;
 }
@@ -841,9 +1051,9 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
 	void *dst = page_address(page);
 
 	if (src)
-		memcpy(dst, src, PAGE_CACHE_SIZE);
+		memcpy(dst, src, PAGE_SIZE);
 	else
-		memset(dst, 0, PAGE_CACHE_SIZE);
+		memset(dst, 0, PAGE_SIZE);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
 }
@@ -854,6 +1064,31 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
 	update_meta_page(sbi, (void *)sum_blk, blk_addr);
 }
 
+static void write_current_sum_page(struct f2fs_sb_info *sbi,
+						int type, block_t blk_addr)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	struct page *page = grab_meta_page(sbi, blk_addr);
+	struct f2fs_summary_block *src = curseg->sum_blk;
+	struct f2fs_summary_block *dst;
+
+	dst = (struct f2fs_summary_block *)page_address(page);
+
+	mutex_lock(&curseg->curseg_mutex);
+
+	down_read(&curseg->journal_rwsem);
+	memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
+	up_read(&curseg->journal_rwsem);
+
+	memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
+	memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
+
+	mutex_unlock(&curseg->curseg_mutex);
+
+	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);
@@ -886,9 +1121,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
-					MAIN_SEGS(sbi), *newseg + 1);
-		if (segno - *newseg < sbi->segs_per_sec -
-					(*newseg % sbi->segs_per_sec))
+				(hint + 1) * sbi->segs_per_sec, *newseg + 1);
+		if (segno < (hint + 1) * sbi->segs_per_sec)
 			goto got_it;
 	}
 find_other_zone:
@@ -1071,7 +1305,7 @@ 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))
+	if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0, 0))
 		return v_ops->get_victim(sbi,
 				&(curseg)->next_segno, BG_GC, type, SSR);
 
@@ -1106,22 +1340,21 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	stat_inc_seg_type(sbi, curseg);
 }
 
-static void __allocate_new_segments(struct f2fs_sb_info *sbi, int type)
-{
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	unsigned int old_segno;
-
-	old_segno = curseg->segno;
-	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
-	locate_dirty_segment(sbi, old_segno);
-}
-
 void allocate_new_segments(struct f2fs_sb_info *sbi)
 {
+	struct curseg_info *curseg;
+	unsigned int old_segno;
 	int i;
 
-	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
-		__allocate_new_segments(sbi, i);
+	if (test_opt(sbi, LFS))
+		return;
+
+	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
+		curseg = CURSEG_I(sbi, i);
+		old_segno = curseg->segno;
+		SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
+		locate_dirty_segment(sbi, old_segno);
+	}
 }
 
 static const struct segment_allocation default_salloc_ops = {
@@ -1134,6 +1367,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	__u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
+	int err = 0;
 
 	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
@@ -1142,6 +1376,12 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	if (end <= MAIN_BLKADDR(sbi))
 		goto out;
 
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"Found FS corruption, run fsck to fix.");
+		goto out;
+	}
+
 	/* start/end segment number in main_area */
 	start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
@@ -1164,12 +1404,16 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 				sbi->segs_per_sec) - 1, end_segno);
 
 		mutex_lock(&sbi->gc_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 		mutex_unlock(&sbi->gc_mutex);
+		if (err)
+			break;
+
+		schedule();
 	}
 out:
 	range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
-	return 0;
+	return err;
 }
 
 static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
@@ -1244,21 +1488,11 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		struct f2fs_summary *sum, int type)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	struct curseg_info *curseg;
-	bool direct_io = (type == CURSEG_DIRECT_IO);
-
-	type = direct_io ? CURSEG_WARM_DATA : type;
-
-	curseg = CURSEG_I(sbi, type);
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
 
 	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
-	/* direct_io'ed data is aligned to the segment for better performance */
-	if (direct_io && curseg->next_blkoff &&
-				!has_not_enough_free_secs(sbi, 0))
-		__allocate_new_segments(sbi, type);
-
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/*
@@ -1292,11 +1526,17 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
-					&fio->blk_addr, sum, type);
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+
+	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
+
+	if (fio->type == NODE || fio->type == DATA)
+		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -1305,7 +1545,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = page->index,
+		.old_blkaddr = page->index,
+		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1335,19 +1576,19 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	do_write_page(&sum, fio);
-	dn->data_blkaddr = fio->blk_addr;
+	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 }
 
 void rewrite_data_page(struct f2fs_io_info *fio)
 {
+	fio->new_blkaddr = fio->old_blkaddr;
 	stat_inc_inplace_blocks(fio->sbi);
 	f2fs_submit_page_mbio(fio);
 }
 
-static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
-				struct f2fs_summary *sum,
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
-				bool recover_curseg)
+				bool recover_curseg, bool recover_newaddr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
@@ -1390,7 +1631,7 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
 	__add_sum_entry(sbi, type, sum);
 
-	if (!recover_curseg)
+	if (!recover_curseg || recover_newaddr)
 		update_sit_entry(sbi, new_blkaddr, 1);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -1414,66 +1655,30 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 				block_t old_addr, block_t new_addr,
-				unsigned char version, bool recover_curseg)
+				unsigned char version, bool recover_curseg,
+				bool recover_newaddr)
 {
 	struct f2fs_summary sum;
 
 	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
 
-	__f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
-
-	dn->data_blkaddr = new_addr;
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-}
-
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
-					struct page *page, enum page_type type)
-{
-	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	struct bio_vec *bvec;
-	struct page *target;
-	int i;
-
-	down_read(&io->io_rwsem);
-	if (!io->bio) {
-		up_read(&io->io_rwsem);
-		return false;
-	}
-
-	bio_for_each_segment_all(bvec, io->bio, i) {
-
-		if (bvec->bv_page->mapping) {
-			target = bvec->bv_page;
-		} else {
-			struct f2fs_crypto_ctx *ctx;
-
-			/* encrypted page */
-			ctx = (struct f2fs_crypto_ctx *)page_private(
-								bvec->bv_page);
-			target = ctx->w.control_page;
-		}
-
-		if (page == target) {
-			up_read(&io->io_rwsem);
-			return true;
-		}
-	}
+	__f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+					recover_curseg, recover_newaddr);
 
-	up_read(&io->io_rwsem);
-	return false;
+	f2fs_update_data_blkaddr(dn, new_addr);
 }
 
 void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type)
+				enum page_type type, bool ordered)
 {
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		if (is_merged_page(sbi, page, type))
-			f2fs_submit_merged_bio(sbi, type, WRITE);
-		wait_on_page_writeback(page);
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+		if (ordered)
+			wait_on_page_writeback(page);
+		else
+			wait_for_stable_page(page);
 	}
 }
 
@@ -1482,14 +1687,12 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
 {
 	struct page *cpage;
 
-	if (blkaddr == NEW_ADDR)
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
 		return;
 
-	f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
-
 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
 	if (cpage) {
-		f2fs_wait_on_page_writeback(cpage, DATA);
+		f2fs_wait_on_page_writeback(cpage, DATA, true);
 		f2fs_put_page(cpage, 1);
 	}
 }
@@ -1510,12 +1713,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 
 	/* Step 1: restore nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, 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);
+	memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
 	offset = 2 * SUM_JOURNAL_SIZE;
 
 	/* Step 3: restore summary entries */
@@ -1539,7 +1741,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 			s = (struct f2fs_summary *)(kaddr + offset);
 			seg_i->sum_blk->entries[j] = *s;
 			offset += SUMMARY_SIZE;
-			if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+			if (offset + SUMMARY_SIZE <= PAGE_SIZE -
 						SUM_FOOTER_SIZE)
 				continue;
 
@@ -1611,7 +1813,14 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	/* set uncompleted segment to curseg */
 	curseg = CURSEG_I(sbi, type);
 	mutex_lock(&curseg->curseg_mutex);
-	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+
+	/* update journal info */
+	down_write(&curseg->journal_rwsem);
+	memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
+	up_write(&curseg->journal_rwsem);
+
+	memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
+	memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 0);
 	curseg->alloc_type = ckpt->alloc_type[type];
@@ -1623,14 +1832,10 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 
 static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_summary_block *s_sits =
-		CURSEG_I(sbi, CURSEG_COLD_DATA)->sum_blk;
-	struct f2fs_summary_block *s_nats =
-		CURSEG_I(sbi, CURSEG_HOT_DATA)->sum_blk;
 	int type = CURSEG_HOT_DATA;
 	int err;
 
-	if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+	if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
 		int npages = npages_for_summary_flush(sbi, true);
 
 		if (npages >= 2)
@@ -1653,11 +1858,6 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 			return err;
 	}
 
-	/* sanity check for summary blocks */
-	if (nats_in_cursum(s_nats) > NAT_JOURNAL_ENTRIES ||
-			sits_in_cursum(s_sits) > SIT_JOURNAL_ENTRIES)
-		return -EINVAL;
-
 	return 0;
 }
 
@@ -1675,13 +1875,12 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 	/* Step 1: write nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+	memcpy(kaddr, seg_i->journal, 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);
+	memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 3: write summary entries */
@@ -1703,7 +1902,7 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 			*summary = seg_i->sum_blk->entries[j];
 			written_size += SUMMARY_SIZE;
 
-			if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+			if (written_size + SUMMARY_SIZE <= PAGE_SIZE -
 							SUM_FOOTER_SIZE)
 				continue;
 
@@ -1727,17 +1926,13 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 	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);
-	}
+	for (i = type; i < end; i++)
+		write_current_sum_page(sbi, i, blkaddr + (i - type));
 }
 
 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))
+	if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
 		write_compacted_summaries(sbi, start_blk);
 	else
 		write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
@@ -1748,24 +1943,24 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
-int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+int lookup_journal_in_cursum(struct f2fs_journal *journal, 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)
+		for (i = 0; i < nats_in_cursum(journal); i++) {
+			if (le32_to_cpu(nid_in_journal(journal, i)) == val)
 				return i;
 		}
-		if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
-			return update_nats_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
+			return update_nats_in_cursum(journal, 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)
+		for (i = 0; i < sits_in_cursum(journal); i++)
+			if (le32_to_cpu(segno_in_journal(journal, i)) == val)
 				return i;
-		if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
-			return update_sits_in_cursum(sum, 1);
+		if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
+			return update_sits_in_cursum(journal, 1);
 	}
 	return -1;
 }
@@ -1794,7 +1989,7 @@ static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
 
 	src_addr = page_address(src_page);
 	dst_addr = page_address(dst_page);
-	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+	memcpy(dst_addr, src_addr, PAGE_SIZE);
 
 	set_page_dirty(dst_page);
 	f2fs_put_page(src_page, 1);
@@ -1869,20 +2064,22 @@ static void add_sits_in_set(struct f2fs_sb_info *sbi)
 static void remove_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;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < sits_in_cursum(journal); i++) {
 		unsigned int segno;
 		bool dirtied;
 
-		segno = le32_to_cpu(segno_in_journal(sum, i));
+		segno = le32_to_cpu(segno_in_journal(journal, i));
 		dirtied = __mark_sit_entry_dirty(sbi, segno);
 
 		if (!dirtied)
 			add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
 	}
-	update_sits_in_cursum(sum, -sits_in_cursum(sum));
+	update_sits_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 /*
@@ -1894,13 +2091,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	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;
+	struct f2fs_journal *journal = curseg->journal;
 	struct sit_entry_set *ses, *tmp;
 	struct list_head *head = &SM_I(sbi)->sit_entry_set;
 	bool to_journal = true;
 	struct seg_entry *se;
 
-	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
 	if (!sit_i->dirty_sentries)
@@ -1917,7 +2113,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * entries, remove all entries from journal and add and account
 	 * them in sit entry set.
 	 */
-	if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+	if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
 		remove_sits_in_journal(sbi);
 
 	/*
@@ -1934,10 +2130,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		unsigned int segno = start_segno;
 
 		if (to_journal &&
-			!__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+			!__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
 			to_journal = false;
 
-		if (!to_journal) {
+		if (to_journal) {
+			down_write(&curseg->journal_rwsem);
+		} else {
 			page = get_next_sit_page(sbi, start_segno);
 			raw_sit = page_address(page);
 		}
@@ -1955,13 +2153,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			}
 
 			if (to_journal) {
-				offset = lookup_journal_in_cursum(sum,
+				offset = lookup_journal_in_cursum(journal,
 							SIT_JOURNAL, segno, 1);
 				f2fs_bug_on(sbi, offset < 0);
-				segno_in_journal(sum, offset) =
+				segno_in_journal(journal, offset) =
 							cpu_to_le32(segno);
 				seg_info_to_raw_sit(se,
-						&sit_in_journal(sum, offset));
+					&sit_in_journal(journal, offset));
 			} else {
 				sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
 				seg_info_to_raw_sit(se,
@@ -1973,7 +2171,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			ses->entry_cnt--;
 		}
 
-		if (!to_journal)
+		if (to_journal)
+			up_write(&curseg->journal_rwsem);
+		else
 			f2fs_put_page(page, 1);
 
 		f2fs_bug_on(sbi, ses->entry_cnt);
@@ -1988,7 +2188,6 @@ out:
 			add_discard_addrs(sbi, cpc);
 	}
 	mutex_unlock(&sit_i->sentry_lock);
-	mutex_unlock(&curseg->curseg_mutex);
 
 	set_prefree_as_free_segments(sbi);
 }
@@ -1996,7 +2195,6 @@ out:
 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;
@@ -2024,12 +2222,16 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
 		sit_i->sentries[start].ckpt_valid_map
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
-		sit_i->sentries[start].discard_map
-			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
 		if (!sit_i->sentries[start].cur_valid_map ||
-				!sit_i->sentries[start].ckpt_valid_map ||
-				!sit_i->sentries[start].discard_map)
+				!sit_i->sentries[start].ckpt_valid_map)
 			return -ENOMEM;
+
+		if (f2fs_discard_en(sbi)) {
+			sit_i->sentries[start].discard_map
+				= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+			if (!sit_i->sentries[start].discard_map)
+				return -ENOMEM;
+		}
 	}
 
 	sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
@@ -2059,7 +2261,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 
 	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->written_valid_blocks = 0;
 	sit_i->sit_bitmap = dst_bitmap;
 	sit_i->bitmap_size = bitmap_size;
 	sit_i->dirty_sentries = 0;
@@ -2117,9 +2319,14 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 
 	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		mutex_init(&array[i].curseg_mutex);
-		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+		array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
 		if (!array[i].sum_blk)
 			return -ENOMEM;
+		init_rwsem(&array[i].journal_rwsem);
+		array[i].journal = kzalloc(sizeof(struct f2fs_journal),
+							GFP_KERNEL);
+		if (!array[i].journal)
+			return -ENOMEM;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
 	}
@@ -2130,54 +2337,73 @@ 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;
+	struct f2fs_journal *journal = curseg->journal;
+	struct seg_entry *se;
+	struct f2fs_sit_entry sit;
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi);
 
 	do {
-		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
+		readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+							META_SIT, true);
 
 		start = start_blk * sit_i->sents_per_block;
 		end = (start_blk + readed) * sit_i->sents_per_block;
 
 		for (; start < end && start < MAIN_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;
 
-			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);
-
+			se = &sit_i->sentries[start];
 			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);
 
 			/* build discard map only one time */
-			memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
-			sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
-
-			if (sbi->segs_per_sec > 1) {
-				struct sec_entry *e = get_sec_entry(sbi, start);
-				e->valid_blocks += se->valid_blocks;
+			if (f2fs_discard_en(sbi)) {
+				memcpy(se->discard_map, se->cur_valid_map,
+							SIT_VBLOCK_MAP_SIZE);
+				sbi->discard_blks += sbi->blocks_per_seg -
+							se->valid_blocks;
 			}
+
+			if (sbi->segs_per_sec > 1)
+				get_sec_entry(sbi, start)->valid_blocks +=
+							se->valid_blocks;
 		}
 		start_blk += readed;
 	} while (start_blk < sit_blk_cnt);
+
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < sits_in_cursum(journal); i++) {
+		unsigned int old_valid_blocks;
+
+		start = le32_to_cpu(segno_in_journal(journal, i));
+		se = &sit_i->sentries[start];
+		sit = sit_in_journal(journal, i);
+
+		old_valid_blocks = se->valid_blocks;
+
+		check_block_count(sbi, start, &sit);
+		seg_info_from_raw_sit(se, &sit);
+
+		if (f2fs_discard_en(sbi)) {
+			memcpy(se->discard_map, se->cur_valid_map,
+						SIT_VBLOCK_MAP_SIZE);
+			sbi->discard_blks += old_valid_blocks -
+						se->valid_blocks;
+		}
+
+		if (sbi->segs_per_sec > 1)
+			get_sec_entry(sbi, start)->valid_blocks +=
+				se->valid_blocks - old_valid_blocks;
+	}
+	up_read(&curseg->journal_rwsem);
 }
 
 static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -2189,6 +2415,9 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 		struct seg_entry *sentry = get_seg_entry(sbi, start);
 		if (!sentry->valid_blocks)
 			__set_free(sbi, start);
+		else
+			SIT_I(sbi)->written_valid_blocks +=
+						sentry->valid_blocks;
 	}
 
 	/* set use the current segments */
@@ -2310,7 +2539,11 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
 	sm_info->rec_prefree_segments = sm_info->main_segments *
 					DEF_RECLAIM_PREFREE_SEGMENTS / 100;
-	sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
+	if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
+		sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
+
+	if (!test_opt(sbi, LFS))
+		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
 
@@ -2392,8 +2625,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 	if (!array)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
-	for (i = 0; i < NR_CURSEG_TYPE; i++)
+	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		kfree(array[i].sum_blk);
+		kfree(array[i].journal);
+	}
 	kfree(array);
 }
 
@@ -2440,7 +2675,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
 
 	if (!sm_info)
 		return;
-	destroy_flush_cmd_control(sbi);
+	destroy_flush_cmd_control(sbi, true);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);
@@ -2459,7 +2694,7 @@ int __init create_segment_manager_caches(void)
 	sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
 			sizeof(struct sit_entry_set));
 	if (!sit_entry_set_slab)
-		goto destory_discard_entry;
+		goto destroy_discard_entry;
 
 	inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
 			sizeof(struct inmem_pages));
@@ -2469,7 +2704,7 @@ int __init create_segment_manager_caches(void)
 
 destroy_sit_entry_set:
 	kmem_cache_destroy(sit_entry_set_slab);
-destory_discard_entry:
+destroy_discard_entry:
 	kmem_cache_destroy(discard_entry_slab);
 fail:
 	return -ENOMEM;