Merge tag 'for-f2fs-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
"This round introduces several interesting features such as on-disk NAT
bitmaps, IO alignment, and a discard thread. And it includes a couple
of major bug fixes as below.

Enhancements:

- introduce on-disk bitmaps to avoid scanning NAT blocks when getting
free nids

- support IO alignment to prepare open-channel SSD integration in
future

- introduce a discard thread to avoid long latency during checkpoint
and fstrim

- use SSR for warm node and enable inline_xattr by default

- introduce in-memory bitmaps to check FS consistency for debugging

- improve write_begin by avoiding needless read IO

Bug fixes:

- fix broken zone_reset behavior for SMR drive

- fix wrong victim selection policy during GC

- fix missing behavior when preparing discard commands

- fix bugs in atomic write support and fiemap

- workaround to handle multiple f2fs_add_link calls having same name

... and it includes a bunch of clean-up patches as well"

* tag 'for-f2fs-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (97 commits)
f2fs: avoid to flush nat journal entries
f2fs: avoid to issue redundant discard commands
f2fs: fix a plint compile warning
f2fs: add f2fs_drop_inode tracepoint
f2fs: Fix zoned block device support
f2fs: remove redundant set_page_dirty()
f2fs: fix to enlarge size of write_io_dummy mempool
f2fs: fix memory leak of write_io_dummy mempool during umount
f2fs: fix to update F2FS_{CP_}WB_DATA count correctly
f2fs: use MAX_FREE_NIDS for the free nids target
f2fs: introduce free nid bitmap
f2fs: new helper cur_cp_crc() getting crc in f2fs_checkpoint
f2fs: update the comment of default nr_pages to skipping
f2fs: drop the duplicate pval in f2fs_getxattr
f2fs: Don't update the xattr data that same as the exist
f2fs: kill __is_extent_same
f2fs: avoid bggc->fggc when enough free segments are avaliable after cp
f2fs: select target segment with closer temperature in SSR mode
f2fs: show simple call stack in fault injection message
f2fs: no need lock_op in f2fs_write_inline_data
...

Documentation/filesystems/f2fs.txt

···
 disable_ext_identify   Disable the extension list configured by mkfs, so f2fs
                        does not aware of cold files such as media files.
 inline_xattr           Enable the inline xattrs feature.
+noinline_xattr         Disable the inline xattrs feature.
 inline_data            Enable the inline data feature: New created small(<~3.4k)
                        files can be written into inode block.
 inline_dentry          Enable the inline dir feature: data in new created
                        directory entries can be written into inode block. The
                        space of inode block which is used to store inline
                        dentries is limited to ~3.4k.
-noinline_dentry        Diable the inline dentry feature.
+noinline_dentry        Disable the inline dentry feature.
 flush_merge	       Merge concurrent cache_flush commands as much as possible
                        to eliminate redundant command issues. If the underlying
 		       device handles the cache_flush command relatively slowly,
···
 mode=%s                Control block allocation mode which supports "adaptive"
                        and "lfs". In "lfs" mode, there should be no random
                        writes towards main area.
+io_bits=%u             Set the bit size of write IO requests. It should be set
+                       with "mode=lfs".
 
 ================================================================================
 DEBUGFS ENTRIES
···
 SYSFS ENTRIES
 ================================================================================
 
-Information about mounted f2f2 file systems can be found in
+Information about mounted f2fs file systems can be found in
 /sys/fs/f2fs.  Each mounted filesystem will have a directory in
 /sys/fs/f2fs based on its device name (i.e., /sys/fs/f2fs/sda).
 The files in each per-device directory are shown in table below.

fs/f2fs/checkpoint.c

···
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
+						0, page->index, META, WRITE);
 
 	unlock_page(page);
 
···
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_ORPHAN)) {
 		spin_unlock(&im->ino_lock);
+		f2fs_show_injection_info(FAULT_ORPHAN);
 		return -ENOSPC;
 	}
 #endif
···
 		return -EINVAL;
 	}
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
-							+ crc_offset)));
+	crc = cur_cp_crc(*cp_block);
 	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
···
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 		return 0;
 	}
-	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+	fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
 	inode = igrab(&fi->vfs_inode);
 	spin_unlock(&sbi->inode_lock[type]);
 	if (inode) {
···
 			spin_unlock(&sbi->inode_lock[DIRTY_META]);
 			return 0;
 		}
-		fi = list_entry(head->next, struct f2fs_inode_info,
+		fi = list_first_entry(head, struct f2fs_inode_info,
 							gdirty_list);
 		inode = igrab(&fi->vfs_inode);
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
···
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
-
-	build_free_nids(sbi, false);
 	f2fs_unlock_all(sbi);
 }
 
···
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 
 	spin_lock(&sbi->cp_lock);
+
+	if (cpc->reason == CP_UMOUNT && ckpt->cp_pack_total_block_count >
+			sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+		disable_nat_bits(sbi, false);
 
 	if (cpc->reason == CP_UMOUNT)
 		__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
···
 
 	start_blk = __start_cp_next_addr(sbi);
 
+	/* write nat bits */
+	if (enabled_nat_bits(sbi, cpc)) {
+		__u64 cp_ver = cur_cp_version(ckpt);
+		unsigned int i;
+		block_t blk;
+
+		cp_ver |= ((__u64)crc32 << 32);
+		*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
+
+		blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+		for (i = 0; i < nm_i->nat_bits_blocks; i++)
+			update_meta_page(sbi, nm_i->nat_bits +
+					(i << F2FS_BLKSIZE_BITS), blk + i);
+
+		/* Flush all the NAT BITS pages */
+		while (get_pages(sbi, F2FS_DIRTY_META)) {
+			sync_meta_pages(sbi, META, LONG_MAX);
+			if (unlikely(f2fs_cp_error(sbi)))
+				return -EIO;
+		}
+	}
+
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
 	if (unlikely(f2fs_cp_error(sbi)))
···
 	f2fs_flush_merged_bios(sbi);
 
 	/* this is the case of multiple fstrims without any changes */
-	if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) {
-		f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt);
-		f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries);
-		f2fs_bug_on(sbi, prefree_segments(sbi));
-		flush_sit_entries(sbi, cpc);
-		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-		unblock_operations(sbi);
-		goto out;
+	if (cpc->reason == CP_DISCARD) {
+		if (!exist_trim_candidates(sbi, cpc)) {
+			unblock_operations(sbi);
+			goto out;
+		}
+
+		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+				SIT_I(sbi)->dirty_sentries == 0 &&
+				prefree_segments(sbi) == 0) {
+			flush_sit_entries(sbi, cpc);
+			clear_prefree_segments(sbi, cpc);
+			unblock_operations(sbi);
+			goto out;
+		}
 	}
 
 	/*
···
 	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
-	flush_nat_entries(sbi);
+	flush_nat_entries(sbi, cpc);
 	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	err = do_checkpoint(sbi, cpc);
-	if (err) {
+	if (err)
 		release_discard_addrs(sbi);
-	} else {
+	else
 		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-	}
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);

fs/f2fs/data.c

···
 	int i;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO))
+	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
+		f2fs_show_injection_info(FAULT_IO);
 		bio->bi_error = -EIO;
+	}
 #endif
 
 	if (f2fs_bio_encrypted(bio)) {
···
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		enum count_type type = WB_DATA_TYPE(page);
+
+		if (IS_DUMMY_WRITTEN_PAGE(page)) {
+			set_page_private(page, (unsigned long)NULL);
+			ClearPagePrivate(page);
+			unlock_page(page);
+			mempool_free(page, sbi->write_io_dummy);
+
+			if (unlikely(bio->bi_error))
+				f2fs_stop_checkpoint(sbi, true);
+			continue;
+		}
 
 		fscrypt_pullback_bio_page(&page, true);
 
···
 				struct bio *bio, enum page_type type)
 {
 	if (!is_read_io(bio_op(bio))) {
+		unsigned int start;
+
 		if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
 			current->plug && (type == DATA || type == NODE))
 			blk_finish_plug(current->plug);
+
+		if (type != DATA && type != NODE)
+			goto submit_io;
+
+		start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
+		start %= F2FS_IO_SIZE(sbi);
+
+		if (start == 0)
+			goto submit_io;
+
+		/* fill dummy pages */
+		for (; start < F2FS_IO_SIZE(sbi); start++) {
+			struct page *page =
+				mempool_alloc(sbi->write_io_dummy,
+					GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL);
+			f2fs_bug_on(sbi, !page);
+
+			SetPagePrivate(page);
+			set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
+			lock_page(page);
+			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+				f2fs_bug_on(sbi, 1);
+		}
+		/*
+		 * In the NODE case, we lose next block address chain. So, we
+		 * need to do checkpoint in f2fs_sync_file.
+		 */
+		if (type == NODE)
+			set_sbi_flag(sbi, SBI_NEED_CP);
 	}
+submit_io:
+	if (is_read_io(bio_op(bio)))
+		trace_f2fs_submit_read_bio(sbi->sb, type, bio);
+	else
+		trace_f2fs_submit_write_bio(sbi->sb, type, bio);
 	submit_bio(bio);
 }
 
···
 	if (!io->bio)
 		return;
 
-	if (is_read_io(fio->op))
-		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
-	else
-		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
-
 	bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+
+	if (is_read_io(fio->op))
+		trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
+	else
+		trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
 
 	__submit_bio(io->sbi, io->bio, fio->type);
 	io->bio = NULL;
 }
 
-static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
-						struct page *page, nid_t ino)
+static bool __has_merged_page(struct f2fs_bio_info *io,
+				struct inode *inode, nid_t ino, pgoff_t idx)
 {
 	struct bio_vec *bvec;
 	struct page *target;
···
 	if (!io->bio)
 		return false;
 
-	if (!inode && !page && !ino)
+	if (!inode && !ino)
 		return true;
 
 	bio_for_each_segment_all(bvec, io->bio, i) {
···
 		else
 			target = fscrypt_control_page(bvec->bv_page);
 
+		if (idx != target->index)
+			continue;
+
 		if (inode && inode == target->mapping->host)
-			return true;
-		if (page && page == target)
 			return true;
 		if (ino && ino == ino_of_node(target))
 			return true;
···
 }
 
 static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
-						struct page *page, nid_t ino,
-						enum page_type type)
+				nid_t ino, pgoff_t idx, enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io = &sbi->write_io[btype];
 	bool ret;
 
 	down_read(&io->io_rwsem);
-	ret = __has_merged_page(io, inode, page, ino);
+	ret = __has_merged_page(io, inode, ino, idx);
 	up_read(&io->io_rwsem);
 	return ret;
 }
 
 static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
-				struct inode *inode, struct page *page,
-				nid_t ino, enum page_type type, int rw)
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, int rw)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io;
···
 
 	down_write(&io->io_rwsem);
 
-	if (!__has_merged_page(io, inode, page, ino))
+	if (!__has_merged_page(io, inode, ino, idx))
 		goto out;
 
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
 		io->fio.op = REQ_OP_WRITE;
-		io->fio.op_flags = REQ_PREFLUSH | REQ_META | REQ_PRIO;
+		io->fio.op_flags = REQ_META | REQ_PRIO;
 		if (!test_opt(sbi, NOBARRIER))
-			io->fio.op_flags |= REQ_FUA;
+			io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 	}
 	__submit_merged_bio(io);
 out:
···
 void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
 									int rw)
 {
-	__f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+	__f2fs_submit_merged_bio(sbi, NULL, 0, 0, type, rw);
 }
 
 void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
-				struct inode *inode, struct page *page,
-				nid_t ino, enum page_type type, int rw)
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, int rw)
 {
-	if (has_merged_page(sbi, inode, page, ino, type))
-		__f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+	if (has_merged_page(sbi, inode, ino, idx, type))
+		__f2fs_submit_merged_bio(sbi, inode, ino, idx, type, rw);
 }
 
 void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
···
 	return 0;
 }
 
-void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
 	bool is_read = is_read_io(fio->op);
 	struct page *bio_page;
+	int err = 0;
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
···
 	verify_block_addr(sbi, fio->new_blkaddr);
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+	/* set submitted = 1 as a return value */
+	fio->submitted = 1;
 
 	if (!is_read)
 		inc_page_count(sbi, WB_DATA_TYPE(bio_page));
···
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
+		if ((fio->type == DATA || fio->type == NODE) &&
+				fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
+			err = -EAGAIN;
+			if (!is_read)
+				dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+			goto out_fail;
+		}
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
 						BIO_MAX_PAGES, is_read);
 		io->fio = *fio;
···
 
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
-
+out_fail:
 	up_write(&io->io_rwsem);
 	trace_f2fs_submit_page_mbio(fio->page, fio);
+	return err;
 }
 
 static void __set_data_blkaddr(struct dnode_of_data *dn)
···
 
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
 {
-	struct extent_info ei;
+	struct extent_info ei  = {0,0,0};
 	struct inode *inode = dn->inode;
 
 	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
···
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
 	struct page *page;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	int err;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
···
 	struct f2fs_map_blocks map;
 	int err = 0;
 
+	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+		return 0;
+
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
 	if (map.m_len > map.m_lblk)
···
 	int err = 0, ofs = 1;
 	unsigned int ofs_in_node, last_ofs_in_node;
 	blkcnt_t prealloc;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	block_t blkaddr;
 
 	if (!maxblocks)
···
 			}
 			if (err)
 				goto sync_out;
-			map->m_flags = F2FS_MAP_NEW;
+			map->m_flags |= F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		} else {
 			if (flag == F2FS_GET_BLOCK_BMAP) {
···
 	if (!err) {
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
-		bh->b_size = map.m_len << inode->i_blkbits;
+		bh->b_size = (u64)map.m_len << inode->i_blkbits;
 	}
 	return err;
 }
···
 
 		prefetchw(&page->flags);
 		if (pages) {
-			page = list_entry(pages->prev, struct page, lru);
+			page = list_last_entry(pages, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
 						  page->index,
···
 			struct list_head *pages, unsigned nr_pages)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct page *page = list_entry(pages->prev, struct page, lru);
+	struct page *page = list_last_entry(pages, struct page, lru);
 
 	trace_f2fs_readpages(inode, page, nr_pages);
 
···
 	return err;
 }
 
-static int f2fs_write_data_page(struct page *page,
-					struct writeback_control *wbc)
+static int __write_data_page(struct page *page, bool *submitted,
+				struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
···
 		.op_flags = wbc_to_write_flags(wbc),
 		.page = page,
 		.encrypted_page = NULL,
+		.submitted = false,
 	};
 
 	trace_f2fs_writepage(page, DATA);
···
 		goto redirty_out;
 
 	err = -EAGAIN;
-	f2fs_lock_op(sbi);
-	if (f2fs_has_inline_data(inode))
+	if (f2fs_has_inline_data(inode)) {
 		err = f2fs_write_inline_data(inode, page);
+		if (!err)
+			goto out;
+	}
+	f2fs_lock_op(sbi);
 	if (err == -EAGAIN)
 		err = do_write_data_page(&fio);
 	if (F2FS_I(inode)->last_disk_size < psize)
···
 		ClearPageUptodate(page);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+		f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index,
+						DATA, WRITE);
 		remove_dirty_inode(inode);
+		submitted = NULL;
 	}
 
 	unlock_page(page);
 	f2fs_balance_fs(sbi, need_balance_fs);
 
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		submitted = NULL;
+	}
+
+	if (submitted)
+		*submitted = fio.submitted;
 
 	return 0;
 
···
 		return AOP_WRITEPAGE_ACTIVATE;
 	unlock_page(page);
 	return err;
+}
+
+static int f2fs_write_data_page(struct page *page,
+					struct writeback_control *wbc)
+{
+	return __write_data_page(page, NULL, wbc);
 }
 
 /*
···
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
 	pgoff_t done_index;
+	pgoff_t last_idx = ULONG_MAX;
 	int cycled;
 	int range_whole = 0;
 	int tag;
-	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
···
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (page->index > end) {
 				done = 1;
···
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = mapping->a_ops->writepage(page, wbc);
+			ret = __write_data_page(page, &submitted, wbc);
 			if (unlikely(ret)) {
 				/*
 				 * keep nr_to_write, since vfs uses this to
···
 				done_index = page->index + 1;
 				done = 1;
 				break;
-			} else {
-				nwritten++;
+			} else if (submitted) {
+				last_idx = page->index;
 			}
 
 			if (--wbc->nr_to_write <= 0 &&
···
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = done_index;
 
-	if (nwritten)
+	if (last_idx != ULONG_MAX)
 		f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
-							NULL, 0, DATA, WRITE);
+						0, last_idx, DATA, WRITE);
 
 	return ret;
 }
···
 	struct dnode_of_data dn;
 	struct page *ipage;
 	bool locked = false;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	int err = 0;
 
 	/*
 	 * we already allocated all the blocks, so we don't need to get
 	 * the block addresses when there is no need to fill the page.
 	 */
-	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE)
+	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
+			!is_inode_flag_set(inode, FI_NO_PREALLOC))
 		return 0;
 
 	if (f2fs_has_inline_data(inode) ||
···
 			goto fail;
 	}
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	/*
+	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
+	 * wait_for_stable_page. Will wait that below with our IO control.
+	 */
+	page = pagecache_get_page(mapping, index,
+				FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
 	if (!page) {
 		err = -ENOMEM;
 		goto fail;
···
 
 	if (len == PAGE_SIZE || PageUptodate(page))
 		return 0;
+
+	if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+		zero_user_segment(page, len, PAGE_SIZE);
+		return 0;
+	}
 
 	if (blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
···
 	 * let generic_perform_write() try to copy data again through copied=0.
 	 */
 	if (!PageUptodate(page)) {
-		if (unlikely(copied != PAGE_SIZE))
+		if (unlikely(copied != len))
 			copied = 0;
 		else
 			SetPageUptodate(page);
···
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 
-	if (f2fs_is_atomic_file(inode)) {
+	if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
 		if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
 			register_inmem_page(inode, page);
 			return 1;

fs/f2fs/debug.c

···
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->aw_cnt = atomic_read(&sbi->aw_cnt);
+	si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
 	si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
 	si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+	if (SM_I(sbi) && SM_I(sbi)->fcc_info)
+		si->nr_flush =
+			atomic_read(&SM_I(sbi)->fcc_info->submit_flush);
+	if (SM_I(sbi) && SM_I(sbi)->dcc_info)
+		si->nr_discard =
+			atomic_read(&SM_I(sbi)->dcc_info->submit_discard);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
···
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->append = sbi->im[APPEND_INO].ino_num;
+	si->update = sbi->im[UPDATE_INO].ino_num;
 	si->orphans = sbi->im[ORPHAN_INO].ino_num;
 	si->utilization = utilization(sbi);
 
···
 	/* build nm */
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+	si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+	si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
+	si->base_mem += NM_I(sbi)->nat_blocks / 8;
 
 get_cache:
 	si->cache_mem = 0;
···
 		si->cache_mem += sizeof(struct f2fs_gc_kthread);
 
 	/* build merge flush thread */
-	if (SM_I(sbi)->cmd_control_info)
+	if (SM_I(sbi)->fcc_info)
 		si->cache_mem += sizeof(struct flush_cmd_control);
+	if (SM_I(sbi)->dcc_info)
+		si->cache_mem += sizeof(struct discard_cmd_control);
 
 	/* free nids */
 	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
···
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
-		seq_printf(s, "  - Orphan Inode: %u\n",
-			   si->orphans);
+		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
+			   si->orphans, si->append, si->update);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
 			   si->main_area_segs, si->main_area_sections,
 			   si->main_area_zones);
···
 		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
 				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d, wb_cp_data: %4d, wb_data: %4d\n",
-			   si->inmem_pages, si->nr_wb_cp_data, si->nr_wb_data);
+		seq_printf(s, "  - IO (CP: %4d, Data: %4d, Flush: %4d, Discard: %4d)\n",
+			   si->nr_wb_cp_data, si->nr_wb_data,
+			   si->nr_flush, si->nr_discard);
+		seq_printf(s, "  - inmem: %4d, atomic IO: %4d (Max. %4d)\n",
+			   si->inmem_pages, si->aw_cnt, si->max_aw_cnt);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
···
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
 	atomic_set(&sbi->inplace_count, 0);
+
+	atomic_set(&sbi->aw_cnt, 0);
+	atomic_set(&sbi->max_aw_cnt, 0);
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);

fs/f2fs/dir.c

···
 		f2fs_put_page(dentry_page, 0);
 	}
 
-	if (!de && room && F2FS_I(dir)->chash != namehash) {
-		F2FS_I(dir)->chash = namehash;
-		F2FS_I(dir)->clevel = level;
+	/* This is to increase the speed of f2fs_create */
+	if (!de && room) {
+		F2FS_I(dir)->task = current;
+		if (F2FS_I(dir)->chash != namehash) {
+			F2FS_I(dir)->chash = namehash;
+			F2FS_I(dir)->clevel = level;
+		}
 	}
 
 	return de;
···
 
 start:
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH))
+	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
+		f2fs_show_injection_info(FAULT_DIR_DEPTH);
 		return -ENOSPC;
+	}
 #endif
 	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
 		return -ENOSPC;
···
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	struct fscrypt_name fname;
+	struct page *page = NULL;
+	struct f2fs_dir_entry *de = NULL;
 	int err;
 
 	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
-	err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
-
+	/*
+	 * An immature stakable filesystem shows a race condition between lookup
+	 * and create. If we have same task when doing lookup and create, it's
+	 * definitely fine as expected by VFS normally. Otherwise, let's just
+	 * verify on-disk dentry one more time, which guarantees filesystem
+	 * consistency more.
+	 */
+	if (current != F2FS_I(dir)->task) {
+		de = __f2fs_find_entry(dir, &fname, &page);
+		F2FS_I(dir)->task = NULL;
+	}
+	if (de) {
+		f2fs_dentry_kunmap(dir, page);
+		f2fs_put_page(page, 0);
+		err = -EEXIST;
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+	} else {
+		err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+	}
 	fscrypt_free_filename(&fname);
 	return err;
 }

fs/f2fs/extent_cache.c

···
 	struct extent_tree *et;
 	nid_t ino = inode->i_ino;
 
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
 	if (!et) {
 		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
···
 		atomic_dec(&sbi->total_zombie_tree);
 		list_del_init(&et->list);
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
 	F2FS_I(inode)->extent_tree = et;
···
 	tmp_node = parent;
 	if (parent && fofs > en->ei.fofs)
 		tmp_node = rb_next(parent);
-	*next_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	*next_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 
 	tmp_node = parent;
 	if (parent && fofs < en->ei.fofs)
 		tmp_node = rb_prev(parent);
-	*prev_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	*prev_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	return NULL;
 
 lookup_neighbors:
 	if (fofs == en->ei.fofs) {
 		/* lookup prev node for merging backward later */
 		tmp_node = rb_prev(&en->rb_node);
-		*prev_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+		*prev_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	}
 	if (fofs == en->ei.fofs + en->ei.len - 1) {
 		/* lookup next node for merging frontward later */
 		tmp_node = rb_next(&en->rb_node);
-		*next_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+		*next_ex = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	}
 	return en;
 }
···
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en)
-			__release_extent_node(sbi, et, prev_ex);
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
+		if (en)
+			__release_extent_node(sbi, et, prev_ex);
+
 		en = next_ex;
 	}
 
···
 	return en;
 }
 
-static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+static void f2fs_update_extent_tree_range(struct inode *inode,
 				pgoff_t fofs, block_t blkaddr, unsigned int len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
···
 	unsigned int pos = (unsigned int)fofs;
 
 	if (!et)
-		return false;
+		return;
 
 	trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
 
···
 
 	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
 		write_unlock(&et->lock);
-		return false;
+		return;
 	}
 
 	prev = et->largest;
···
 		if (!next_en) {
 			struct rb_node *node = rb_next(&en->rb_node);
 
-			next_en = node ?
-				rb_entry(node, struct extent_node, rb_node)
-				: NULL;
+			next_en = rb_entry_safe(node, struct extent_node,
+						rb_node);
 		}
 
 		if (parts)
···
 		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
-
-	return !__is_extent_same(&prev, &et->largest);
 }
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
···
 	if (!atomic_read(&sbi->total_zombie_tree))
 		goto free_node;
 
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
···
 			goto unlock_out;
 		cond_resched();
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 free_node:
 	/* 2. remove LRU extent entries */
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	remained = nr_shrink - (node_cnt + tree_cnt);
···
 	spin_unlock(&sbi->extent_lock);
 
 unlock_out:
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 out:
 	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
 
···
 
 	if (inode->i_nlink && !is_bad_inode(inode) &&
 					atomic_read(&et->node_cnt)) {
-		down_write(&sbi->extent_tree_lock);
+		mutex_lock(&sbi->extent_tree_lock);
 		list_add_tail(&et->list, &sbi->zombie_list);
 		atomic_inc(&sbi->total_zombie_tree);
-		up_write(&sbi->extent_tree_lock);
+		mutex_unlock(&sbi->extent_tree_lock);
 		return;
 	}
 
···
 	node_cnt = f2fs_destroy_extent_node(inode);
 
 	/* delete extent tree entry in radix tree */
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
 	atomic_dec(&sbi->total_ext_tree);
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
 
···
 void init_extent_cache_info(struct f2fs_sb_info *sbi)
 {
 	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
-	init_rwsem(&sbi->extent_tree_lock);
+	mutex_init(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
 	atomic_set(&sbi->total_ext_tree, 0);

fs/f2fs/f2fs.h

···
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
 #define F2FS_SET_FEATURE(sb, mask)					\
-	F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)
+	(F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask))
 #define F2FS_CLEAR_FEATURE(sb, mask)					\
-	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
+	(F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
 
 /*
  * For checkpoint manager
···
 	CP_DISCARD,
 };
 
-#define DEF_BATCHED_TRIM_SECTIONS	2
+#define DEF_BATCHED_TRIM_SECTIONS	2048
 #define BATCHED_TRIM_SEGMENTS(sbi)	\
 		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
 #define BATCHED_TRIM_BLOCKS(sbi)	\
 		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define MAX_DISCARD_BLOCKS(sbi)						\
+		((1 << (sbi)->log_blocks_per_seg) * (sbi)->segs_per_sec)
+#define DISCARD_ISSUE_RATE	8
 #define DEF_CP_INTERVAL			60	/* 60 secs */
 #define DEF_IDLE_INTERVAL		5	/* 5 secs */
 
···
 	int len;		/* # of consecutive blocks of the discard */
 };
 
-struct bio_entry {
-	struct list_head list;
-	struct bio *bio;
-	struct completion event;
-	int error;
+enum {
+	D_PREP,
+	D_SUBMIT,
+	D_DONE,
+};
+
+struct discard_cmd {
+	struct list_head list;		/* command list */
+	struct completion wait;		/* compleation */
+	block_t lstart;			/* logical start address */
+	block_t len;			/* length */
+	struct bio *bio;		/* bio */
+	int state;			/* state */
+};
+
+struct discard_cmd_control {
+	struct task_struct *f2fs_issue_discard;	/* discard thread */
+	struct list_head discard_entry_list;	/* 4KB discard entry list */
+	int nr_discards;			/* # of discards in the list */
+	struct list_head discard_cmd_list;	/* discard cmd list */
+	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
+	struct mutex cmd_lock;
+	int max_discards;			/* max. discards to be issued */
+	atomic_t submit_discard;		/* # of issued discard */
 };
 
 /* for the list of fsync inodes, used only during recovery */
···
 static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 {
 	int before = nats_in_cursum(journal);
+
 	journal->n_nats = cpu_to_le16(before + i);
 	return before;
 }
···
 static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
 {
 	int before = sits_in_cursum(journal);
+
 	journal->n_sits = cpu_to_le16(before + i);
 	return before;
 }
···
 
 	if (type == 1) {
 		struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src;
+
 		d->max = NR_DENTRY_IN_BLOCK;
 		d->bitmap = &t->dentry_bitmap;
 		d->dentry = t->dentry;
 		d->filename = t->filename;
 	} else {
 		struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src;
+
 		d->max = NR_INLINE_DENTRY;
 		d->bitmap = &t->dentry_bitmap;
 		d->dentry = t->dentry;
···
 	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
+	struct task_struct *task;	/* lookup and create consistency */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
-	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	loff_t	last_disk_size;		/* lastly written file size */
 
 	struct list_head dirty_list;	/* dirty list for dirs and files */
···
 	ei->len = len;
 }
 
-static inline bool __is_extent_same(struct extent_info *ei1,
-						struct extent_info *ei2)
-{
-	return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk &&
-						ei1->len == ei2->len);
-}
-
 static inline bool __is_extent_mergeable(struct extent_info *back,
 						struct extent_info *front)
 {
···
 	return __is_extent_mergeable(cur, front);
 }
 
-extern void f2fs_mark_inode_dirty_sync(struct inode *, bool);
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
 static inline void __try_update_largest_extent(struct inode *inode,
 			struct extent_tree *et, struct extent_node *en)
 {
···
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	unsigned int nat_cnt;		/* the # of cached nat entries */
 	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
+	unsigned int nat_blocks;	/* # of nat blocks */
 
 	/* free node ids management */
 	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
···
 	unsigned int nid_cnt[MAX_NID_LIST];	/* the number of free node id */
 	spinlock_t nid_list_lock;	/* protect nid lists ops */
 	struct mutex build_lock;	/* lock for build free nids */
+	unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
+	unsigned char *nat_block_bitmap;
 
 	/* for checkpoint */
 	char *nat_bitmap;		/* NAT bitmap pointer */
+
+	unsigned int nat_bits_blocks;	/* # of nat bits blocks */
+	unsigned char *nat_bits;	/* NAT bits blocks */
+	unsigned char *full_nat_bits;	/* full NAT pages */
+	unsigned char *empty_nat_bits;	/* empty NAT pages */
+#ifdef CONFIG_F2FS_CHECK_FS
+	char *nat_bitmap_mir;		/* NAT bitmap mirror */
+#endif
 	int bitmap_size;		/* bitmap size */
 };
 
···
 	/* a threshold to reclaim prefree segments */
 	unsigned int rec_prefree_segments;
 
-	/* for small discard management */
-	struct list_head discard_list;		/* 4KB discard list */
-	struct list_head wait_list;		/* linked with issued discard bio */
-	int nr_discards;			/* # of discards in the list */
-	int max_discards;			/* max. discards to be issued */
-
 	/* for batched trimming */
 	unsigned int trim_sections;		/* # of sections to trim */
 
···
 	unsigned int min_fsync_blocks;	/* threshold for fsync */
 
 	/* for flush command control */
-	struct flush_cmd_control *cmd_control_info;
+	struct flush_cmd_control *fcc_info;
 
+	/* for discard command control */
+	struct discard_cmd_control *dcc_info;
 };
 
 /*
···
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	bool submitted;		/* indicate IO submission */
 };
 
 #define is_read_io(rw) (rw == READ)
···
 	struct f2fs_bio_info read_io;			/* for read bios */
 	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
 	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
+	int write_io_size_bits;			/* Write IO size bits */
+	mempool_t *write_io_dummy;		/* Dummy pages */
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
···
 
 	/* for extent tree cache */
 	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
-	struct rw_semaphore extent_tree_lock;	/* locking extent radix tree */
+	struct mutex extent_tree_lock;	/* locking extent radix tree */
 	struct list_head extent_list;		/* lru list for shrinker */
 	spinlock_t extent_lock;			/* locking extent lru list */
 	atomic_t total_ext_tree;		/* extent tree count */
···
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
 	unsigned int cur_victim_sec;		/* current victim section num */
 
+	/* threshold for converting bg victims for fg */
+	u64 fggc_threshold;
+
 	/* maximum # of trials to find a victim segment for SSR and GC */
 	unsigned int max_victim_search;
 
···
 	atomic_t inline_xattr;			/* # of inline_xattr inodes */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
+	atomic_t aw_cnt;			/* # of atomic writes */
+	atomic_t max_aw_cnt;			/* max # of atomic writes */
 	int bg_gc;				/* background gc calls */
 	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
 #endif
···
 };
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
+#define f2fs_show_injection_info(type)				\
+	printk("%sF2FS-fs : inject %s in %s of %pF\n",		\
+		KERN_INFO, fault_name[type],			\
+		__func__, __builtin_return_address(0))
 static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
 {
 	struct f2fs_fault_info *ffi = &sbi->fault_info;
···
 	atomic_inc(&ffi->inject_ops);
 	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
 		atomic_set(&ffi->inject_ops, 0);
-		printk("%sF2FS-fs : inject %s in %pF\n",
-				KERN_INFO,
-				fault_name[type],
-				__builtin_return_address(0));
 		return true;
 	}
 	return false;
···
 	return le64_to_cpu(cp->checkpoint_ver);
 }
 
+static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
+{
+	size_t crc_offset = le32_to_cpu(cp->checksum_offset);
+	return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
+}
+
 static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 {
 	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
···
 	spin_lock(&sbi->cp_lock);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
 	spin_unlock(&sbi->cp_lock);
+}
+
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
+{
+	set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+	if (lock)
+		spin_lock(&sbi->cp_lock);
+	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+	kfree(NM_I(sbi)->nat_bits);
+	NM_I(sbi)->nat_bits = NULL;
+	if (lock)
+		spin_unlock(&sbi->cp_lock);
+}
+
+static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
+					struct cp_control *cpc)
+{
+	bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
+
+	return (cpc) ? (cpc->reason == CP_UMOUNT) && set : set;
 }
 
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
···
 	blkcnt_t diff;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_BLOCK))
+	if (time_to_inject(sbi, FAULT_BLOCK)) {
+		f2fs_show_injection_info(FAULT_BLOCK);
 		return false;
+	}
 #endif
 	/*
 	 * let's increase this in prior to actual block count change in order
···
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	struct page *page = find_lock_page(mapping, index);
+
 	if (page)
 		return page;
 
-	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
+	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
+		f2fs_show_injection_info(FAULT_PAGE_ALLOC);
 		return NULL;
+	}
 #endif
 	if (!for_write)
 		return grab_cache_page(mapping, index);
···
 static inline bool IS_INODE(struct page *page)
 {
 	struct f2fs_node *p = F2FS_NODE(page);
+
 	return RAW_IS_INODE(p);
 }
 
···
 {
 	struct f2fs_node *raw_node;
 	__le32 *addr_array;
+
 	raw_node = F2FS_NODE(node_page);
 	addr_array = blkaddr_in_node(raw_node);
 	return le32_to_cpu(addr_array[offset]);
···
 	FI_UPDATE_WRITE,	/* inode has in-place-update data */
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
+	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
 	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
 	FI_DROP_CACHE,		/* drop dirty page cache */
···
 	FI_INLINE_DOTS,		/* indicate inline dot dentries */
 	FI_DO_DEFRAG,		/* indicate defragment is running */
 	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
+	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
 };
 
 static inline void __mark_inode_dirty_flag(struct inode *inode,
···
 static inline void *inline_xattr_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
+
 	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
 					F2FS_INLINE_XATTR_ADDRS]);
 }
···
 	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
 }
 
+static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
+{
+	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
+}
+
 static inline bool f2fs_is_volatile_file(struct inode *inode)
 {
 	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
···
 static inline void *inline_data_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
+
 	return (void *)&(ri->i_addr[1]);
 }
 
···
 					size_t size, gfp_t flags)
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_KMALLOC))
+	if (time_to_inject(sbi, FAULT_KMALLOC)) {
+		f2fs_show_injection_info(FAULT_KMALLOC);
 		return NULL;
+	}
 #endif
 	return kmalloc(size, flags);
 }
···
 /*
  * file.c
  */
-int f2fs_sync_file(struct file *, loff_t, loff_t, int);
-void truncate_data_blocks(struct dnode_of_data *);
-int truncate_blocks(struct inode *, u64, bool);
-int f2fs_truncate(struct inode *);
-int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
-int f2fs_setattr(struct dentry *, struct iattr *);
-int truncate_hole(struct inode *, pgoff_t, pgoff_t);
-int truncate_data_blocks_range(struct dnode_of_data *, int);
-long f2fs_ioctl(struct file *, unsigned int, unsigned long);
-long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
+void truncate_data_blocks(struct dnode_of_data *dn);
+int truncate_blocks(struct inode *inode, u64 from, bool lock);
+int f2fs_truncate(struct inode *inode);
+int f2fs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			struct kstat *stat);
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
+int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
 /*
  * inode.c
  */
-void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget(struct super_block *, unsigned long);
-struct inode *f2fs_iget_retry(struct super_block *, unsigned long);
-int try_to_free_nats(struct f2fs_sb_info *, int);
-int update_inode(struct inode *, struct page *);
-int update_inode_page(struct inode *);
-int f2fs_write_inode(struct inode *, struct writeback_control *);
-void f2fs_evict_inode(struct inode *);
-void handle_failed_inode(struct inode *);
+void f2fs_set_inode_flags(struct inode *inode);
+struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
+int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
+int update_inode(struct inode *inode, struct page *node_page);
+int update_inode_page(struct inode *inode);
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
+void f2fs_evict_inode(struct inode *inode);
+void handle_failed_inode(struct inode *inode);
 
 /*
  * namei.c
···
 /*
  * dir.c
  */
-void set_de_type(struct f2fs_dir_entry *, umode_t);
-unsigned char get_de_type(struct f2fs_dir_entry *);
-struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
-			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
-int f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
-			unsigned int, struct fscrypt_str *);
-void do_make_empty_dir(struct inode *, struct inode *,
-			struct f2fs_dentry_ptr *);
-struct page *init_inode_metadata(struct inode *, struct inode *,
-		const struct qstr *, const struct qstr *, struct page *);
-void update_parent_metadata(struct inode *, struct inode *, unsigned int);
-int room_for_filename(const void *, int, int);
-void f2fs_drop_nlink(struct inode *, struct inode *);
-struct f2fs_dir_entry *__f2fs_find_entry(struct inode *, struct fscrypt_name *,
-							struct page **);
-struct f2fs_dir_entry *f2fs_find_entry(struct inode *, const struct qstr *,
-							struct page **);
-struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, const struct qstr *, struct page **);
-void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
-				struct page *, struct inode *);
-int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
-void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
-			const struct qstr *, f2fs_hash_t , unsigned int);
-int f2fs_add_regular_entry(struct inode *, const struct qstr *,
-			const struct qstr *, struct inode *, nid_t, umode_t);
-int __f2fs_do_add_link(struct inode *, struct fscrypt_name*, struct inode *,
-			nid_t, umode_t);
-int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
-			umode_t);
-void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
-							struct inode *);
-int f2fs_do_tmpfile(struct inode *, struct inode *);
-bool f2fs_empty_dir(struct inode *);
+void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
+unsigned char get_de_type(struct f2fs_dir_entry *de);
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
+			f2fs_hash_t namehash, int *max_slots,
+			struct f2fs_dentry_ptr *d);
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+			unsigned int start_pos, struct fscrypt_str *fstr);
+void do_make_empty_dir(struct inode *inode, struct inode *parent,
+			struct f2fs_dentry_ptr *d);
+struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+			const struct qstr *new_name,
+			const struct qstr *orig_name, struct page *dpage);
+void update_parent_metadata(struct inode *dir, struct inode *inode,
+			unsigned int current_depth);
+int room_for_filename(const void *bitmap, int slots, int max_slots);
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page);
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
+			const struct qstr *child, struct page **res_page);
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
+ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
+			struct page **page);
+void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
+			struct page *page, struct inode *inode);
+int update_dent_inode(struct inode *inode, struct inode *to,
+			const struct qstr *name);
+void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
+			const struct qstr *name, f2fs_hash_t name_hash,
+			unsigned int bit_pos);
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+			const struct qstr *orig_name,
+			struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+			struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+			struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
+			struct inode *dir, struct inode *inode);
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
+bool f2fs_empty_dir(struct inode *dir);
 
 static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 {
···
 /*
  * super.c
  */
-int f2fs_inode_dirtied(struct inode *, bool);
-void f2fs_inode_synced(struct inode *);
-int f2fs_commit_super(struct f2fs_sb_info *, bool);
-int f2fs_sync_fs(struct super_block *, int);
+int f2fs_inode_dirtied(struct inode *inode, bool sync);
+void f2fs_inode_synced(struct inode *inode);
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
+int f2fs_sync_fs(struct super_block *sb, int sync);
 extern __printf(3, 4)
-void f2fs_msg(struct super_block *, const char *, const char *, ...);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
  */
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info);
 
 /*
  * node.c
···
 struct dnode_of_data;
 struct node_info;
 
-bool available_free_memory(struct f2fs_sb_info *, int);
-int need_dentry_mark(struct f2fs_sb_info *, nid_t);
-bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
-void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
-pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
-int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
-int truncate_inode_blocks(struct inode *, pgoff_t);
-int truncate_xattr_node(struct inode *, struct page *);
-int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t);
-int remove_inode_page(struct inode *);
-struct page *new_inode_page(struct inode *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
-void ra_node_page(struct f2fs_sb_info *, nid_t);
-struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_node_page_ra(struct page *, int);
-void move_node_page(struct page *, int);
-int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
-			struct writeback_control *, bool);
-int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
-void build_free_nids(struct f2fs_sb_info *, bool);
-bool alloc_nid(struct f2fs_sb_info *, nid_t *);
-void alloc_nid_done(struct f2fs_sb_info *, nid_t);
-void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
-int try_to_free_nids(struct f2fs_sb_info *, int);
-void recover_inline_xattr(struct inode *, struct page *);
-void recover_xattr_data(struct inode *, struct page *, block_t);
-int recover_inode_page(struct f2fs_sb_info *, struct page *);
-int restore_node_summary(struct f2fs_sb_info *, unsigned int,
-				struct f2fs_summary_block *);
-void flush_nat_entries(struct f2fs_sb_info *);
-int build_node_manager(struct f2fs_sb_info *);
-void destroy_node_manager(struct f2fs_sb_info *);
+bool available_free_memory(struct f2fs_sb_info *sbi, int type);
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
+void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
+int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
+int truncate_inode_blocks(struct inode *inode, pgoff_t from);
+int truncate_xattr_node(struct inode *inode, struct page *page);
+int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
+int remove_inode_page(struct inode *inode);
+struct page *new_inode_page(struct inode *inode);
+struct page *new_node_page(struct dnode_of_data *dn,
+			unsigned int ofs, struct page *ipage);
+void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
+struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct page *get_node_page_ra(struct page *parent, int start);
+void move_node_page(struct page *node_page, int gc_type);
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+			struct writeback_control *wbc, bool atomic);
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc);
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
+bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
+void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
+void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
+void recover_inline_xattr(struct inode *inode, struct page *page);
+int recover_xattr_data(struct inode *inode, struct page *page,
+			block_t blkaddr);
+int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
+int restore_node_summary(struct f2fs_sb_info *sbi,
+			unsigned int segno, struct f2fs_summary_block *sum);
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_node_manager(struct f2fs_sb_info *sbi);
+void destroy_node_manager(struct f2fs_sb_info *sbi);
 int __init create_node_manager_caches(void);
 void destroy_node_manager_caches(void);
 
 /*
  * segment.c
  */
-void register_inmem_page(struct inode *, struct page *);
-void drop_inmem_pages(struct inode *);
-int commit_inmem_pages(struct inode *);
-void f2fs_balance_fs(struct f2fs_sb_info *, bool);
-void f2fs_balance_fs_bg(struct f2fs_sb_info *);
-int f2fs_issue_flush(struct f2fs_sb_info *);
-int create_flush_cmd_control(struct f2fs_sb_info *);
-void destroy_flush_cmd_control(struct f2fs_sb_info *, bool);
-void invalidate_blocks(struct f2fs_sb_info *, block_t);
-bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
-void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *);
-void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
-void release_discard_addrs(struct f2fs_sb_info *);
-int npages_for_summary_flush(struct f2fs_sb_info *, bool);
-void allocate_new_segments(struct f2fs_sb_info *);
-int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
-struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
-void update_meta_page(struct f2fs_sb_info *, void *, block_t);
-void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(unsigned int, struct f2fs_io_info *);
-void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
-void rewrite_data_page(struct f2fs_io_info *);
-void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
-					block_t, block_t, bool, bool);
-void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
-				block_t, block_t, unsigned char, bool, bool);
-void allocate_data_block(struct f2fs_sb_info *, struct page *,
-		block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
-void write_data_summaries(struct f2fs_sb_info *, block_t);
-void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
-int build_segment_manager(struct f2fs_sb_info *);
-void destroy_segment_manager(struct f2fs_sb_info *);
+void register_inmem_page(struct inode *inode, struct page *page);
+void drop_inmem_pages(struct inode *inode);
+int commit_inmem_pages(struct inode *inode);
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
+int f2fs_issue_flush(struct f2fs_sb_info *sbi);
+int create_flush_cmd_control(struct f2fs_sb_info *sbi);
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
+void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr);
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void release_discard_addrs(struct f2fs_sb_info *sbi);
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page);
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
+void rewrite_data_page(struct f2fs_io_info *fio);
+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_newaddr);
+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,
+			bool recover_newaddr);
+void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+			block_t old_blkaddr, block_t *new_blkaddr,
+			struct f2fs_summary *sum, int type);
+void f2fs_wait_on_page_writeback(struct page *page,
+			enum page_type type, bool ordered);
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+			block_t blkaddr);
+void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+			unsigned int val, int alloc);
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_segment_manager(struct f2fs_sb_info *sbi);
+void destroy_segment_manager(struct f2fs_sb_info *sbi);
 int __init create_segment_manager_caches(void);
 void destroy_segment_manager_caches(void);
 
 /*
  * checkpoint.c
  */
-void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
-struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
-int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
-void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
-long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *, bool);
-bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
-int f2fs_sync_inode_meta(struct f2fs_sb_info *);
-int acquire_orphan_inode(struct f2fs_sb_info *);
-void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct inode *);
-void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
-int recover_orphan_inodes(struct f2fs_sb_info *);
-int get_valid_checkpoint(struct f2fs_sb_info *);
-void update_dirty_page(struct inode *, struct page *);
-void remove_dirty_inode(struct inode *);
-int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
-int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
-void init_ino_entry_info(struct f2fs_sb_info *);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
+bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+			int type, bool sync);
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+			long nr_to_write);
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
+bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
+int acquire_orphan_inode(struct f2fs_sb_info *sbi);
+void release_orphan_inode(struct f2fs_sb_info *sbi);
+void add_orphan_inode(struct inode *inode);
+void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
+int recover_orphan_inodes(struct f2fs_sb_info *sbi);
+int get_valid_checkpoint(struct f2fs_sb_info *sbi);
+void update_dirty_page(struct inode *inode, struct page *page);
+void remove_dirty_inode(struct inode *inode);
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
 
 /*
  * data.c
  */
-void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
-				struct page *, nid_t, enum page_type, int);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *);
-int f2fs_submit_page_bio(struct f2fs_io_info *);
-void f2fs_submit_page_mbio(struct f2fs_io_info *);
-struct block_device *f2fs_target_device(struct f2fs_sb_info *,
-				block_t, struct bio *);
-int f2fs_target_device_index(struct f2fs_sb_info *, block_t);
-void set_data_blkaddr(struct dnode_of_data *);
-void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
-int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
-int reserve_new_block(struct dnode_of_data *);
-int f2fs_get_block(struct dnode_of_data *, pgoff_t);
-int f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
-int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
-struct page *find_data_page(struct inode *, pgoff_t);
-struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
-struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
-int do_write_data_page(struct f2fs_io_info *);
-int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
-int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
-void f2fs_set_page_dirty_nobuffers(struct page *);
-void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
-int f2fs_release_page(struct page *, gfp_t);
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+			int rw);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, int rw);
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
+int f2fs_submit_page_bio(struct f2fs_io_info *fio);
+int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+			block_t blk_addr, struct bio *bio);
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
+void set_data_blkaddr(struct dnode_of_data *dn);
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
+int reserve_new_block(struct dnode_of_data *dn);
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
+int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+			int op_flags, bool for_write);
+struct page *find_data_page(struct inode *inode, pgoff_t index);
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+			bool for_write);
+struct page *get_new_data_page(struct inode *inode,
+			struct page *ipage, pgoff_t index, bool new_i_size);
+int do_write_data_page(struct f2fs_io_info *fio);
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+			int create, int flag);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+			u64 start, u64 len);
+void f2fs_set_page_dirty_nobuffers(struct page *page);
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+			unsigned int length);
+int f2fs_release_page(struct page *page, gfp_t wait);
 #ifdef CONFIG_MIGRATION
-int f2fs_migrate_page(struct address_space *, struct page *, struct page *,
-				enum migrate_mode);
+int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
+			struct page *page, enum migrate_mode mode);
 #endif
 
 /*
  * gc.c
  */
-int start_gc_thread(struct f2fs_sb_info *);
-void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct inode *);
-int f2fs_gc(struct f2fs_sb_info *, bool, bool);
-void build_gc_manager(struct f2fs_sb_info *);
+int start_gc_thread(struct f2fs_sb_info *sbi);
+void stop_gc_thread(struct f2fs_sb_info *sbi);
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background);
+void build_gc_manager(struct f2fs_sb_info *sbi);
 
 /*
  * recovery.c
  */
-int recover_fsync_data(struct f2fs_sb_info *, bool);
-bool space_for_roll_forward(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
+bool space_for_roll_forward(struct f2fs_sb_info *sbi);
 
 /*
  * debug.c
···
 	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
 	int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;
 	int total_count, utilization;
-	int bg_gc, nr_wb_cp_data, nr_wb_data;
-	int inline_xattr, inline_inode, inline_dir, orphans;
+	int bg_gc, nr_wb_cp_data, nr_wb_data, nr_flush, nr_discard;
+	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+	int aw_cnt, max_aw_cnt;
 	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
···
 		((sbi)->block_count[(curseg)->alloc_type]++)
 #define stat_inc_inplace_blocks(sbi)					\
 		(atomic_inc(&(sbi)->inplace_count))
+#define stat_inc_atomic_write(inode)					\
+		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_dec_atomic_write(inode)					\
+		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_update_max_atomic_write(inode)				\
+	do {								\
+		int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt);	\
+		int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);	\
+		if (cur > max)						\
+			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
+	} while (0)
 #define stat_inc_seg_count(sbi, type, gc_type)				\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
···
 		si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0;	\
 	} while (0)
 
-int f2fs_build_stats(struct f2fs_sb_info *);
-void f2fs_destroy_stats(struct f2fs_sb_info *);
+int f2fs_build_stats(struct f2fs_sb_info *sbi);
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
 int __init f2fs_create_root_stats(void);
 void f2fs_destroy_root_stats(void);
 #else
···
 #define stat_dec_inline_inode(inode)
 #define stat_inc_inline_dir(inode)
 #define stat_dec_inline_dir(inode)
+#define stat_inc_atomic_write(inode)
+#define stat_dec_atomic_write(inode)
+#define stat_update_max_atomic_write(inode)
 #define stat_inc_seg_type(sbi, curseg)
 #define stat_inc_block_count(sbi, curseg)
 #define stat_inc_inplace_blocks(sbi)
···
 /*
  * inline.c
  */
-bool f2fs_may_inline_data(struct inode *);
-bool f2fs_may_inline_dentry(struct inode *);
-void read_inline_data(struct page *, struct page *);
-bool truncate_inline_inode(struct page *, u64);
-int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
-int f2fs_convert_inline_inode(struct inode *);
-int f2fs_write_inline_data(struct inode *, struct page *);
-bool recover_inline_data(struct inode *, struct page *);
-struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
-				struct fscrypt_name *, struct page **);
-int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
-int f2fs_add_inline_entry(struct inode *, const struct qstr *,
-		const struct qstr *, struct inode *, nid_t, umode_t);
-void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
-						struct inode *, struct inode *);
-bool f2fs_empty_inline_dir(struct inode *);
-int f2fs_read_inline_dir(struct file *, struct dir_context *,
-						struct fscrypt_str *);
-int f2fs_inline_data_fiemap(struct inode *,
-		struct fiemap_extent_info *, __u64, __u64);
+bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_may_inline_dentry(struct inode *inode);
+void read_inline_data(struct page *page, struct page *ipage);
+bool truncate_inline_inode(struct page *ipage, u64 from);
+int f2fs_read_inline_data(struct inode *inode, struct page *page);
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
+int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_write_inline_data(struct inode *inode, struct page *page);
+bool recover_inline_data(struct inode *inode, struct page *npage);
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page);
+int make_empty_inline_dir(struct inode *inode, struct inode *parent,
+			struct page *ipage);
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+			const struct qstr *orig_name,
+			struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
+			struct inode *dir, struct inode *inode);
+bool f2fs_empty_inline_dir(struct inode *dir);
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+			struct fscrypt_str *fstr);
+int f2fs_inline_data_fiemap(struct inode *inode,
+			struct fiemap_extent_info *fieinfo,
+			__u64 start, __u64 len);
 
 /*
  * shrinker.c
  */
-unsigned long f2fs_shrink_count(struct shrinker *, struct shrink_control *);
-unsigned long f2fs_shrink_scan(struct shrinker *, struct shrink_control *);
-void f2fs_join_shrinker(struct f2fs_sb_info *);
-void f2fs_leave_shrinker(struct f2fs_sb_info *);
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+			struct shrink_control *sc);
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+			struct shrink_control *sc);
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
 
 /*
  * extent_cache.c
  */
-unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
-bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
-void f2fs_drop_extent_tree(struct inode *);
-unsigned int f2fs_destroy_extent_node(struct inode *);
-void f2fs_destroy_extent_tree(struct inode *);
-bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
-void f2fs_update_extent_cache(struct dnode_of_data *);
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_drop_extent_tree(struct inode *inode);
+unsigned int f2fs_destroy_extent_node(struct inode *inode);
+void f2fs_destroy_extent_tree(struct inode *inode);
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+			struct extent_info *ei);
+void f2fs_update_extent_cache(struct dnode_of_data *dn);
 void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
-						pgoff_t, block_t, unsigned int);
-void init_extent_cache_info(struct f2fs_sb_info *);
+			pgoff_t fofs, block_t blkaddr, unsigned int len);
+void init_extent_cache_info(struct f2fs_sb_info *sbi);
 int __init create_extent_cache(void);
 void destroy_extent_cache(void);
 

fs/f2fs/file.c

···
 #include <linux/uaccess.h>
 #include <linux/mount.h>
 #include <linux/pagevec.h>
+#include <linux/uio.h>
 #include <linux/uuid.h>
 #include <linux/file.h>
 
···
 		need_cp = true;
 	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
-	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
-		need_cp = true;
 	else if (test_opt(sbi, FASTBOOT))
 		need_cp = true;
 	else if (sbi->active_logs == 2)
···
 	nid_t pino;
 
 	down_write(&fi->i_sem);
-	fi->xattr_ver = 0;
 	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
 			get_parent_ino(inode, &pino)) {
 		f2fs_i_pino_write(inode, pino);
···
 flush_out:
 	remove_ino_entry(sbi, ino, UPDATE_INO);
 	clear_inode_flag(inode, FI_UPDATE_WRITE);
-	ret = f2fs_issue_flush(sbi);
+	if (!atomic)
+		ret = f2fs_issue_flush(sbi);
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
···
 	}
 
 	if (f2fs_has_inline_data(inode)) {
-		if (truncate_inline_inode(ipage, from))
-			set_page_dirty(ipage);
+		truncate_inline_inode(ipage, from);
+		if (from == 0)
+			clear_inode_flag(inode, FI_DATA_EXIST);
 		f2fs_put_page(ipage, 1);
 		truncate_page = true;
 		goto out;
···
 	if (ret)
 		clear_inode_flag(inode, FI_ATOMIC_FILE);
 out:
+	stat_inc_atomic_write(inode);
+	stat_update_max_atomic_write(inode);
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
···
 		goto err_out;
 
 	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(inode, FI_ATOMIC_FILE);
 		ret = commit_inmem_pages(inode);
-		if (ret) {
-			set_inode_flag(inode, FI_ATOMIC_FILE);
+		if (ret)
 			goto err_out;
-		}
-	}
 
-	ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+		if (!ret) {
+			clear_inode_flag(inode, FI_ATOMIC_FILE);
+			stat_dec_atomic_write(inode);
+		}
+	} else {
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+	}
 err_out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
···
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	pgoff_t pg_start, pg_end;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	unsigned int total = 0, sec_num;
···
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
-		int err = f2fs_preallocate_blocks(iocb, from);
+		int err;
 
+		if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+			set_inode_flag(inode, FI_NO_PREALLOC);
+
+		err = f2fs_preallocate_blocks(iocb, from);
 		if (err) {
 			inode_unlock(inode);
 			return err;
···
 		blk_start_plug(&plug);
 		ret = __generic_file_write_iter(iocb, from);
 		blk_finish_plug(&plug);
+		clear_inode_flag(inode, FI_NO_PREALLOC);
 	}
 	inode_unlock(inode);
 

fs/f2fs/gc.c

···
 		}
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-		if (time_to_inject(sbi, FAULT_CHECKPOINT))
+		if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+			f2fs_show_injection_info(FAULT_CHECKPOINT);
 			f2fs_stop_checkpoint(sbi, false);
+		}
 #endif
 
 		/*
···
 		p->ofs_unit = sbi->segs_per_sec;
 	}
 
-	if (p->max_search > sbi->max_victim_search)
+	/* we need to check every dirty segments in the FG_GC case */
+	if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
 		p->max_search = sbi->max_victim_search;
 
 	p->offset = sbi->last_victim[p->gc_mode];
···
 	for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
 		if (sec_usage_check(sbi, secno))
 			continue;
+
+		if (no_fggc_candidate(sbi, secno))
+			continue;
+
 		clear_bit(secno, dirty_i->victim_secmap);
 		return secno * sbi->segs_per_sec;
 	}
···
 	return UINT_MAX - ((100 * (100 - u) * age) / (100 + u));
 }
 
+static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	unsigned int valid_blocks =
+			get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+
+	return IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+				valid_blocks * 2 : valid_blocks;
+}
+
 static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct victim_sel_policy *p)
 {
···
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
-		return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+		return get_greedy_cost(sbi, segno);
 	else
 		return get_cb_cost(sbi, segno);
 }
···
 			nsearched++;
 		}
 
-
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
 			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
+			goto next;
+		if (gc_type == FG_GC && p.alloc_mode == LFS &&
+					no_fggc_candidate(sbi, secno))
 			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
···
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
 		goto out;
 
+	if (f2fs_is_atomic_file(inode))
+		goto out;
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
 	if (err)
···
 		return;
 
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+		goto out;
+
+	if (f2fs_is_atomic_file(inode))
 		goto out;
 
 	if (gc_type == BG_GC) {
···
 
 	cpc.reason = __get_cp_reason(sbi);
 gc_more:
-	segno = NULL_SEGNO;
-
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
 	if (unlikely(f2fs_cp_error(sbi))) {
···
 		goto stop;
 	}
 
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) {
-		gc_type = FG_GC;
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) {
 		/*
-		 * If there is no victim and no prefree segment but still not
-		 * enough free sections, we should flush dent/node blocks and do
-		 * garbage collections.
+		 * For example, if there are many prefree_segments below given
+		 * threshold, we can make them free by checkpoint. Then, we
+		 * secure free segments which doesn't need fggc any more.
 		 */
-		if (__get_victim(sbi, &segno, gc_type) ||
-						prefree_segments(sbi)) {
-			ret = write_checkpoint(sbi, &cpc);
-			if (ret)
-				goto stop;
-			segno = NULL_SEGNO;
-		} else if (has_not_enough_free_secs(sbi, 0, 0)) {
-			ret = write_checkpoint(sbi, &cpc);
-			if (ret)
-				goto stop;
-		}
-	} else if (gc_type == BG_GC && !background) {
-		/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
-		goto stop;
+		ret = write_checkpoint(sbi, &cpc);
+		if (ret)
+			goto stop;
+		if (has_not_enough_free_secs(sbi, 0, 0))
+			gc_type = FG_GC;
 	}
 
-	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
+	/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+	if (gc_type == BG_GC && !background)
+		goto stop;
+	if (!__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
···
 
 void build_gc_manager(struct f2fs_sb_info *sbi)
 {
+	u64 main_count, resv_count, ovp_count, blocks_per_sec;
+
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
+
+	/* threshold of # of valid blocks in a section for victims of FG_GC */
+	main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
+	resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
+	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
+	blocks_per_sec = sbi->blocks_per_seg * sbi->segs_per_sec;
+
+	sbi->fggc_threshold = div64_u64((main_count - ovp_count) * blocks_per_sec,
+					(main_count - resv_count));
 }

fs/f2fs/inode.c

···
 		goto no_delete;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_EVICT_INODE))
+	if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+		f2fs_show_injection_info(FAULT_EVICT_INODE);
 		goto no_delete;
+	}
 #endif
 
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);

fs/f2fs/namei.c

···
 		if (err)
 			goto err_out;
 	}
-	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
-			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
-			!fscrypt_has_permitted_context(dir, inode)) {
+	if (f2fs_encrypted_inode(dir) &&
+	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+	    !fscrypt_has_permitted_context(dir, inode)) {
 		bool nokey = f2fs_encrypted_inode(inode) &&
 			!fscrypt_has_encryption_key(inode);
 		err = nokey ? -ENOKEY : -EPERM;
···
 	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
+	if ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
 			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
···
 	struct f2fs_dir_entry *old_entry, *new_entry;
 	int old_nlink = 0, new_nlink = 0;
 	int err = -ENOENT;
+
+	if ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
 
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
 			(old_dir != new_dir) &&

fs/f2fs/node.c

···
 	return need_update;
 }
 
-static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
+static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+								bool no_fail)
 {
 	struct nat_entry *new;
 
-	new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
-	f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
+	if (no_fail) {
+		new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+		f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
+	} else {
+		new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+		if (!new)
+			return NULL;
+		if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
+			kmem_cache_free(nat_entry_slab, new);
+			return NULL;
+		}
+	}
+
 	memset(new, 0, sizeof(struct nat_entry));
 	nat_set_nid(new, nid);
 	nat_reset_flag(new);
···
 
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
-		e = grab_nat_entry(nm_i, nid);
-		node_info_from_raw_nat(&e->ni, ne);
+		e = grab_nat_entry(nm_i, nid, false);
+		if (e)
+			node_info_from_raw_nat(&e->ni, ne);
 	} else {
 		f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
 				nat_get_blkaddr(e) !=
···
 	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
-		e = grab_nat_entry(nm_i, ni->nid);
+		e = grab_nat_entry(nm_i, ni->nid, true);
 		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
···
 	if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
 		set_nat_flag(e, IS_CHECKPOINTED, false);
 	__set_nat_cache_dirty(nm_i, e);
+
+	if (enabled_nat_bits(sbi, NULL) && new_blkaddr == NEW_ADDR)
+		clear_bit_le(NAT_BLOCK_OFFSET(ni->nid), nm_i->empty_nat_bits);
 
 	/* update fsync_mark if its inode nat entry is still alive */
 	if (ni->nid != ni->ino)
···
 
 	f2fs_i_xnid_write(inode, 0);
 
-	/* need to do checkpoint during fsync */
-	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
-
 	set_new_dnode(&dn, inode, page, npage, nid);
 
 	if (page)
···
 				unsigned int ofs, struct page *ipage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
-	struct node_info old_ni, new_ni;
+	struct node_info new_ni;
 	struct page *page;
 	int err;
 
···
 		err = -ENOSPC;
 		goto fail;
 	}
-
-	get_node_info(sbi, dn->nid, &old_ni);
-
-	/* Reinitialize old_ni with new node page */
-	f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
-	new_ni = old_ni;
+#ifdef CONFIG_F2FS_CHECK_FS
+	get_node_info(sbi, dn->nid, &new_ni);
+	f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+#endif
+	new_ni.nid = dn->nid;
 	new_ni.ino = dn->inode->i_ino;
+	new_ni.blk_addr = NULL_ADDR;
+	new_ni.flag = 0;
+	new_ni.version = 0;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
 	f2fs_wait_on_page_writeback(page, NODE, true);
···
 	return last_page;
 }
 
+static int __write_node_page(struct page *page, bool atomic, bool *submitted,
+				struct writeback_control *wbc)
+{
+	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	nid_t nid;
+	struct node_info ni;
+	struct f2fs_io_info fio = {
+		.sbi = sbi,
+		.type = NODE,
+		.op = REQ_OP_WRITE,
+		.op_flags = wbc_to_write_flags(wbc),
+		.page = page,
+		.encrypted_page = NULL,
+		.submitted = false,
+	};
+
+	trace_f2fs_writepage(page, NODE);
+
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto redirty_out;
+
+	/* get old block addr of this node page */
+	nid = nid_of_node(page);
+	f2fs_bug_on(sbi, page->index != nid);
+
+	if (wbc->for_reclaim) {
+		if (!down_read_trylock(&sbi->node_write))
+			goto redirty_out;
+	} else {
+		down_read(&sbi->node_write);
+	}
+
+	get_node_info(sbi, nid, &ni);
+
+	/* This page is already truncated */
+	if (unlikely(ni.blk_addr == NULL_ADDR)) {
+		ClearPageUptodate(page);
+		dec_page_count(sbi, F2FS_DIRTY_NODES);
+		up_read(&sbi->node_write);
+		unlock_page(page);
+		return 0;
+	}
+
+	if (atomic && !test_opt(sbi, NOBARRIER))
+		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
+
+	set_page_writeback(page);
+	fio.old_blkaddr = ni.blk_addr;
+	write_node_page(nid, &fio);
+	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
+	dec_page_count(sbi, F2FS_DIRTY_NODES);
+	up_read(&sbi->node_write);
+
+	if (wbc->for_reclaim) {
+		f2fs_submit_merged_bio_cond(sbi, page->mapping->host, 0,
+						page->index, NODE, WRITE);
+		submitted = NULL;
+	}
+
+	unlock_page(page);
+
+	if (unlikely(f2fs_cp_error(sbi))) {
+		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		submitted = NULL;
+	}
+	if (submitted)
+		*submitted = fio.submitted;
+
+	return 0;
+
+redirty_out:
+	redirty_page_for_writepage(wbc, page);
+	return AOP_WRITEPAGE_ACTIVATE;
+}
+
+static int f2fs_write_node_page(struct page *page,
+				struct writeback_control *wbc)
+{
+	return __write_node_page(page, false, NULL, wbc);
+}
+
 int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			struct writeback_control *wbc, bool atomic)
 {
 	pgoff_t index, end;
+	pgoff_t last_idx = ULONG_MAX;
 	struct pagevec pvec;
 	int ret = 0;
 	struct page *last_page = NULL;
 	bool marked = false;
 	nid_t ino = inode->i_ino;
-	int nwritten = 0;
 
 	if (atomic) {
 		last_page = last_fsync_dnode(sbi, ino);
···
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (unlikely(f2fs_cp_error(sbi))) {
 				f2fs_put_page(last_page, 0);
···
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+			ret = __write_node_page(page, atomic &&
+						page == last_page,
+						&submitted, wbc);
 			if (ret) {
 				unlock_page(page);
 				f2fs_put_page(last_page, 0);
 				break;
-			} else {
-				nwritten++;
+			} else if (submitted) {
+				last_idx = page->index;
 			}
 
 			if (page == last_page) {
···
 		goto retry;
 	}
 out:
-	if (nwritten)
-		f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
+	if (last_idx != ULONG_MAX)
+		f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx,
+							NODE, WRITE);
 	return ret ? -EIO: 0;
 }
 
···
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (unlikely(f2fs_cp_error(sbi))) {
 				pagevec_release(&pvec);
···
 			set_fsync_mark(page, 0);
 			set_dentry_mark(page, 0);
 
-			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
+			ret = __write_node_page(page, false, &submitted, wbc);
+			if (ret)
 				unlock_page(page);
-			else
+			else if (submitted)
 				nwritten++;
 
 			if (--wbc->nr_to_write == 0)
···
 	if (!ret)
 		ret = ret2;
 	return ret;
-}
-
-static int f2fs_write_node_page(struct page *page,
-				struct writeback_control *wbc)
-{
-	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
-	nid_t nid;
-	struct node_info ni;
-	struct f2fs_io_info fio = {
-		.sbi = sbi,
-		.type = NODE,
-		.op = REQ_OP_WRITE,
-		.op_flags = wbc_to_write_flags(wbc),
-		.page = page,
-		.encrypted_page = NULL,
-	};
-
-	trace_f2fs_writepage(page, NODE);
-
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto redirty_out;
-	if (unlikely(f2fs_cp_error(sbi)))
-		goto redirty_out;
-
-	/* get old block addr of this node page */
-	nid = nid_of_node(page);
-	f2fs_bug_on(sbi, page->index != nid);
-
-	if (wbc->for_reclaim) {
-		if (!down_read_trylock(&sbi->node_write))
-			goto redirty_out;
-	} else {
-		down_read(&sbi->node_write);
-	}
-
-	get_node_info(sbi, nid, &ni);
-
-	/* This page is already truncated */
-	if (unlikely(ni.blk_addr == NULL_ADDR)) {
-		ClearPageUptodate(page);
-		dec_page_count(sbi, F2FS_DIRTY_NODES);
-		up_read(&sbi->node_write);
-		unlock_page(page);
-		return 0;
-	}
-
-	set_page_writeback(page);
-	fio.old_blkaddr = ni.blk_addr;
-	write_node_page(nid, &fio);
-	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
-	dec_page_count(sbi, F2FS_DIRTY_NODES);
-	up_read(&sbi->node_write);
-
-	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
-
-	unlock_page(page);
-
-	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
-
-	return 0;
-
-redirty_out:
-	redirty_page_for_writepage(wbc, page);
-	return AOP_WRITEPAGE_ACTIVATE;
 }
 
 static int f2fs_write_node_pages(struct address_space *mapping,
···
 		radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
-static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+/* return if the nid is recognized as free */
+static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
···
 
 	/* 0 nid should not be used */
 	if (unlikely(nid == 0))
-		return 0;
+		return false;
 
 	if (build) {
 		/* do not add allocated nids */
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
 				nat_get_blkaddr(ne) != NULL_ADDR))
-			return 0;
+			return false;
 	}
 
 	i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
···
 
 	if (radix_tree_preload(GFP_NOFS)) {
 		kmem_cache_free(free_nid_slab, i);
-		return 0;
+		return true;
 	}
 
 	spin_lock(&nm_i->nid_list_lock);
···
 	radix_tree_preload_end();
 	if (err) {
 		kmem_cache_free(free_nid_slab, i);
-		return 0;
+		return true;
 	}
-	return 1;
+	return true;
 }
 
 static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
···
 		kmem_cache_free(free_nid_slab, i);
 }
 
+void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
+	unsigned int nid_ofs = nid - START_NID(nid);
+
+	if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+		return;
+
+	if (set)
+		set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+	else
+		clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+}
+
 static void scan_nat_page(struct f2fs_sb_info *sbi,
 			struct page *nat_page, nid_t start_nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct f2fs_nat_block *nat_blk = page_address(nat_page);
 	block_t blk_addr;
+	unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
 	int i;
+
+	set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
 
 	i = start_nid % NAT_ENTRY_PER_BLOCK;
 
 	for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {
+		bool freed = false;
 
 		if (unlikely(start_nid >= nm_i->max_nid))
 			break;
···
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
 		if (blk_addr == NULL_ADDR)
-			add_free_nid(sbi, start_nid, true);
+			freed = add_free_nid(sbi, start_nid, true);
+		update_free_nid_bitmap(sbi, start_nid, freed);
 	}
 }
 
-static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
+static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+	struct f2fs_journal *journal = curseg->journal;
+	unsigned int i, idx;
+
+	down_read(&nm_i->nat_tree_lock);
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		if (!test_bit_le(i, nm_i->nat_block_bitmap))
+			continue;
+		for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
+			nid_t nid;
+
+			if (!test_bit_le(idx, nm_i->free_nid_bitmap[i]))
+				continue;
+
+			nid = i * NAT_ENTRY_PER_BLOCK + idx;
+			add_free_nid(sbi, nid, true);
+
+			if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
+				goto out;
+		}
+	}
+out:
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
+		block_t addr;
+		nid_t nid;
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
+		if (addr == NULL_ADDR)
+			add_free_nid(sbi, nid, true);
+		else
+			remove_free_nid(sbi, nid);
+	}
+	up_read(&curseg->journal_rwsem);
+	up_read(&nm_i->nat_tree_lock);
+}
+
+static int scan_nat_bits(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct page *page;
+	unsigned int i = 0;
+	nid_t nid;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return -EAGAIN;
+
+	down_read(&nm_i->nat_tree_lock);
+check_empty:
+	i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+	if (i >= nm_i->nat_blocks) {
+		i = 0;
+		goto check_partial;
+	}
+
+	for (nid = i * NAT_ENTRY_PER_BLOCK; nid < (i + 1) * NAT_ENTRY_PER_BLOCK;
+									nid++) {
+		if (unlikely(nid >= nm_i->max_nid))
+			break;
+		add_free_nid(sbi, nid, true);
+	}
+
+	if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
+		goto out;
+	i++;
+	goto check_empty;
+
+check_partial:
+	i = find_next_zero_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+	if (i >= nm_i->nat_blocks) {
+		disable_nat_bits(sbi, true);
+		up_read(&nm_i->nat_tree_lock);
+		return -EINVAL;
+	}
+
+	nid = i * NAT_ENTRY_PER_BLOCK;
+	page = get_current_nat_page(sbi, nid);
+	scan_nat_page(sbi, page, nid);
+	f2fs_put_page(page, 1);
+
+	if (nm_i->nid_cnt[FREE_NID_LIST] < MAX_FREE_NIDS) {
+		i++;
+		goto check_partial;
+	}
+out:
+	up_read(&nm_i->nat_tree_lock);
+	return 0;
+}
+
+static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
···
 
 	if (!sync && !available_free_memory(sbi, FREE_NIDS))
 		return;
+
+	if (!mount) {
+		/* try to find free nids in free_nid_bitmap */
+		scan_free_nid_bits(sbi);
+
+		if (nm_i->nid_cnt[FREE_NID_LIST])
+			return;
+
+		/* try to find free nids with nat_bits */
+		if (!scan_nat_bits(sbi) && nm_i->nid_cnt[FREE_NID_LIST])
+			return;
+	}
+
+	/* find next valid candidate */
+	if (enabled_nat_bits(sbi, NULL)) {
+		int idx = find_next_zero_bit_le(nm_i->full_nat_bits,
+					nm_i->nat_blocks, 0);
+
+		if (idx >= nm_i->nat_blocks)
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		else
+			nid = idx * NAT_ENTRY_PER_BLOCK;
+	}
 
 	/* readahead nat pages to be scanned */
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
···
 					nm_i->ra_nid_pages, META_NAT, false);
 }
 
-void build_free_nids(struct f2fs_sb_info *sbi, bool sync)
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	mutex_lock(&NM_I(sbi)->build_lock);
-	__build_free_nids(sbi, sync);
+	__build_free_nids(sbi, sync, mount);
 	mutex_unlock(&NM_I(sbi)->build_lock);
 }
 
···
 	struct free_nid *i = NULL;
 retry:
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_ALLOC_NID))
+	if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
+		f2fs_show_injection_info(FAULT_ALLOC_NID);
 		return false;
+	}
 #endif
 	spin_lock(&nm_i->nid_list_lock);
 
···
 		i->state = NID_ALLOC;
 		__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
 		nm_i->available_nids--;
+
+		update_free_nid_bitmap(sbi, *nid, false);
+
 		spin_unlock(&nm_i->nid_list_lock);
 		return true;
 	}
 	spin_unlock(&nm_i->nid_list_lock);
 
 	/* Let's scan nat pages and its caches to get free nids */
-	build_free_nids(sbi, true);
+	build_free_nids(sbi, true, false);
 	goto retry;
 }
 
···
 	}
 
 	nm_i->available_nids++;
+
+	update_free_nid_bitmap(sbi, nid, true);
 
 	spin_unlock(&nm_i->nid_list_lock);
 
···
 	f2fs_put_page(ipage, 1);
 }
 
-void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
+int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
 	nid_t new_xnid = nid_of_node(page);
 	struct node_info ni;
+	struct page *xpage;
 
-	/* 1: invalidate the previous xattr nid */
 	if (!prev_xnid)
 		goto recover_xnid;
 
-	/* Deallocate node address */
+	/* 1: invalidate the previous xattr nid */
 	get_node_info(sbi, prev_xnid, &ni);
 	f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
 	invalidate_blocks(sbi, ni.blk_addr);
···
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
 recover_xnid:
-	/* 2: allocate new xattr nid */
+	/* 2: update xattr nid in inode */
+	remove_free_nid(sbi, new_xnid);
+	f2fs_i_xnid_write(inode, new_xnid);
 	if (unlikely(!inc_valid_node_count(sbi, inode)))
 		f2fs_bug_on(sbi, 1);
+	update_inode_page(inode);
 
-	remove_free_nid(sbi, new_xnid);
+	/* 3: update and set xattr node page dirty */
+	xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid);
+	if (!xpage)
+		return -ENOMEM;
+
+	memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE);
+
 	get_node_info(sbi, new_xnid, &ni);
 	ni.ino = inode->i_ino;
 	set_node_addr(sbi, &ni, NEW_ADDR, false);
-	f2fs_i_xnid_write(inode, new_xnid);
+	set_page_dirty(xpage);
+	f2fs_put_page(xpage, 1);
 
-	/* 3: update xattr blkaddr */
-	refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
-	set_node_addr(sbi, &ni, blkaddr, false);
+	return 0;
 }
 
 int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
···
 
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
-			ne = grab_nat_entry(nm_i, nid);
+			ne = grab_nat_entry(nm_i, nid, true);
 			node_info_from_raw_nat(&ne->ni, &raw_ne);
 		}
 
···
 	list_add_tail(&nes->set_list, head);
 }
 
+void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+						struct page *page)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK;
+	struct f2fs_nat_block *nat_blk = page_address(page);
+	int valid = 0;
+	int i;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return;
+
+	for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) {
+		if (start_nid == 0 && i == 0)
+			valid++;
+		if (nat_blk->entries[i].block_addr)
+			valid++;
+	}
+	if (valid == 0) {
+		set_bit_le(nat_index, nm_i->empty_nat_bits);
+		clear_bit_le(nat_index, nm_i->full_nat_bits);
+		return;
+	}
+
+	clear_bit_le(nat_index, nm_i->empty_nat_bits);
+	if (valid == NAT_ENTRY_PER_BLOCK)
+		set_bit_le(nat_index, nm_i->full_nat_bits);
+	else
+		clear_bit_le(nat_index, nm_i->full_nat_bits);
+}
+
 static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
-					struct nat_entry_set *set)
+		struct nat_entry_set *set, struct cp_control *cpc)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_journal *journal = curseg->journal;
···
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
+	if (enabled_nat_bits(sbi, cpc) ||
+		!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
 	if (to_journal) {
···
 			add_free_nid(sbi, nid, false);
 			spin_lock(&NM_I(sbi)->nid_list_lock);
 			NM_I(sbi)->available_nids++;
+			update_free_nid_bitmap(sbi, nid, true);
+			spin_unlock(&NM_I(sbi)->nid_list_lock);
+		} else {
+			spin_lock(&NM_I(sbi)->nid_list_lock);
+			update_free_nid_bitmap(sbi, nid, false);
 			spin_unlock(&NM_I(sbi)->nid_list_lock);
 		}
 	}
 
-	if (to_journal)
+	if (to_journal) {
 		up_write(&curseg->journal_rwsem);
-	else
+	} else {
+		__update_nat_bits(sbi, start_nid, page);
 		f2fs_put_page(page, 1);
+	}
 
 	f2fs_bug_on(sbi, set->entry_cnt);
 
···
 /*
  * This function is called during the checkpointing process.
  */
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
···
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+	if (enabled_nat_bits(sbi, cpc) ||
+		!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
···
 
 	/* flush dirty nats in nat entry set */
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
-		__flush_nat_entry_set(sbi, set);
+		__flush_nat_entry_set(sbi, set, cpc);
 
 	up_write(&nm_i->nat_tree_lock);
 
 	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
+}
+
+static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE;
+	unsigned int i;
+	__u64 cp_ver = cur_cp_version(ckpt);
+	block_t nat_bits_addr;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return 0;
+
+	nm_i->nat_bits_blocks = F2FS_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 +
+						F2FS_BLKSIZE - 1);
+	nm_i->nat_bits = kzalloc(nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS,
+						GFP_KERNEL);
+	if (!nm_i->nat_bits)
+		return -ENOMEM;
+
+	nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
+						nm_i->nat_bits_blocks;
+	for (i = 0; i < nm_i->nat_bits_blocks; i++) {
+		struct page *page = get_meta_page(sbi, nat_bits_addr++);
+
+		memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+					page_address(page), F2FS_BLKSIZE);
+		f2fs_put_page(page, 1);
+	}
+
+	cp_ver |= (cur_cp_crc(ckpt) << 32);
+	if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
+		disable_nat_bits(sbi, true);
+		return 0;
+	}
+
+	nm_i->full_nat_bits = nm_i->nat_bits + 8;
+	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
+
+	f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint");
+	return 0;
 }
 
 static int init_node_manager(struct f2fs_sb_info *sbi)
···
 	struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned char *version_bitmap;
-	unsigned int nat_segs, nat_blocks;
+	unsigned int nat_segs;
+	int err;
 
 	nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr);
 
 	/* segment_count_nat includes pair segment so divide to 2. */
 	nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
-	nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
-
-	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+	nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
+	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks;
 
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
 	nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
···
 					GFP_KERNEL);
 	if (!nm_i->nat_bitmap)
 		return -ENOMEM;
+
+	err = __get_nat_bitmaps(sbi);
+	if (err)
+		return err;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size,
+					GFP_KERNEL);
+	if (!nm_i->nat_bitmap_mir)
+		return -ENOMEM;
+#endif
+
+	return 0;
+}
+
+int init_free_nid_cache(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	nm_i->free_nid_bitmap = f2fs_kvzalloc(nm_i->nat_blocks *
+					NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL);
+	if (!nm_i->free_nid_bitmap)
+		return -ENOMEM;
+
+	nm_i->nat_block_bitmap = f2fs_kvzalloc(nm_i->nat_blocks / 8,
+								GFP_KERNEL);
+	if (!nm_i->nat_block_bitmap)
+		return -ENOMEM;
 	return 0;
 }
 
···
 	if (err)
 		return err;
 
-	build_free_nids(sbi, true);
+	err = init_free_nid_cache(sbi);
+	if (err)
+		return err;
+
+	build_free_nids(sbi, true, true);
 	return 0;
 }
 
···
 	}
 	up_write(&nm_i->nat_tree_lock);
 
+	kvfree(nm_i->nat_block_bitmap);
+	kvfree(nm_i->free_nid_bitmap);
+
 	kfree(nm_i->nat_bitmap);
+	kfree(nm_i->nat_bits);
+#ifdef CONFIG_F2FS_CHECK_FS
+	kfree(nm_i->nat_bitmap_mir);
+#endif
 	sbi->nm_info = NULL;
 	kfree(nm_i);
 }

fs/f2fs/node.h

···
 		spin_unlock(&nm_i->nid_list_lock);
 		return;
 	}
-	fnid = list_entry(nm_i->nid_list[FREE_NID_LIST].next,
+	fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
 						struct free_nid, list);
 	*nid = fnid->nid;
 	spin_unlock(&nm_i->nid_list_lock);
···
 static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+						nm_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
 }
 
···
 	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
 
 	f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
 }
 
 static inline nid_t ino_of_node(struct page *node_page)
···
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	struct f2fs_node *rn = F2FS_NODE(page);
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
-	__u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
+	__u64 cp_ver = cur_cp_version(ckpt);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
 	rn->footer.cp_ver = cpu_to_le64(cp_ver);
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
···
 static inline bool is_recoverable_dnode(struct page *page)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
 	__u64 cp_ver = cur_cp_version(ckpt);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
 	return cp_ver == cpver_of_node(page);
 }
 
···
 	unsigned int ofs = ofs_of_node(node_page);
 
 	if (f2fs_has_xattr_block(ofs))
-		return false;
+		return true;
 
 	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
 			ofs == 5 + 2 * NIDS_PER_BLOCK)

fs/f2fs/recovery.c

···
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
-		/*
-		 * Deprecated; xattr blocks should be found from cold log.
-		 * But, we should remain this for backward compatibility.
-		 */
-		recover_xattr_data(inode, page, blkaddr);
+		err = recover_xattr_data(inode, page, blkaddr);
+		if (!err)
+			recovered++;
 		goto out;
 	}
 
···
 		}
 
 		if (!file_keep_isize(inode) &&
-				(i_size_read(inode) <= (start << PAGE_SHIFT)))
-			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+			(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
+			f2fs_i_size_write(inode,
+				(loff_t)(start + 1) << PAGE_SHIFT);
 
 		/*
 		 * dest is reserved block, invalidate src block
···
 
 int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
 	struct list_head dir_list;
-	block_t blkaddr;
 	int err;
 	int ret = 0;
 	bool need_writecp = false;
···
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
-
-	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);

fs/f2fs/segment.c

···
 #define __reverse_ffz(x) __reverse_ffs(~(x))
 
 static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *bio_entry_slab;
+static struct kmem_cache *discard_cmd_slab;
 static struct kmem_cache *sit_entry_set_slab;
 static struct kmem_cache *inmem_entry_slab;
 
···
 {
 	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);
+
+	clear_inode_flag(inode, FI_ATOMIC_FILE);
+	stat_dec_atomic_write(inode);
 }
 
 static int __commit_inmem_pages(struct inode *inode,
···
 		.op_flags = REQ_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
-	bool submit_bio = false;
+	pgoff_t last_idx = ULONG_MAX;
 	int err = 0;
 
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
···
 
 			/* record old blkaddr for revoking */
 			cur->old_addr = fio.old_blkaddr;
-
-			submit_bio = true;
+			last_idx = page->index;
 		}
 		unlock_page(page);
 		list_move_tail(&cur->list, revoke_list);
 	}
 
-	if (submit_bio)
-		f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+	if (last_idx != ULONG_MAX)
+		f2fs_submit_merged_bio_cond(sbi, inode, 0, last_idx,
+							DATA, WRITE);
 
 	if (!err)
 		__revoke_inmem_pages(inode, revoke_list, false, false);
···
 	INIT_LIST_HEAD(&revoke_list);
 	f2fs_balance_fs(sbi, true);
 	f2fs_lock_op(sbi);
+
+	set_inode_flag(inode, FI_ATOMIC_COMMIT);
 
 	mutex_lock(&fi->inmem_lock);
 	err = __commit_inmem_pages(inode, &revoke_list);
···
 	}
 	mutex_unlock(&fi->inmem_lock);
 
+	clear_inode_flag(inode, FI_ATOMIC_COMMIT);
+
 	f2fs_unlock_op(sbi);
 	return err;
 }
···
 void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_CHECKPOINT))
+	if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+		f2fs_show_injection_info(FAULT_CHECKPOINT);
 		f2fs_stop_checkpoint(sbi, false);
+	}
 #endif
 
 	if (!need)
···
 	if (!available_free_memory(sbi, FREE_NIDS))
 		try_to_free_nids(sbi, MAX_FREE_NIDS);
 	else
-		build_free_nids(sbi, false);
+		build_free_nids(sbi, false, false);
 
 	if (!is_idle(sbi))
 		return;
···
 
 	if (sbi->s_ndevs && !ret) {
 		for (i = 1; i < sbi->s_ndevs; i++) {
+			trace_f2fs_issue_flush(FDEV(i).bdev,
+					test_opt(sbi, NOBARRIER),
+					test_opt(sbi, FLUSH_MERGE));
 			ret = __submit_flush_wait(FDEV(i).bdev);
 			if (ret)
 				break;
···
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 	wait_queue_head_t *q = &fcc->flush_wait_queue;
 repeat:
 	if (kthread_should_stop())
···
 
 int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 {
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 	struct flush_cmd cmd;
-
-	trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER),
-					test_opt(sbi, FLUSH_MERGE));
 
 	if (test_opt(sbi, NOBARRIER))
 		return 0;
 
-	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
+	if (!test_opt(sbi, FLUSH_MERGE))
+		return submit_flush_wait(sbi);
+
+	if (!atomic_read(&fcc->submit_flush)) {
 		int ret;
 
 		atomic_inc(&fcc->submit_flush);
···
 	struct flush_cmd_control *fcc;
 	int err = 0;
 
-	if (SM_I(sbi)->cmd_control_info) {
-		fcc = SM_I(sbi)->cmd_control_info;
+	if (SM_I(sbi)->fcc_info) {
+		fcc = SM_I(sbi)->fcc_info;
 		goto init_thread;
 	}
 
···
 	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;
+	SM_I(sbi)->fcc_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)) {
 		err = PTR_ERR(fcc->f2fs_issue_flush);
 		kfree(fcc);
-		SM_I(sbi)->cmd_control_info = NULL;
+		SM_I(sbi)->fcc_info = NULL;
 		return err;
 	}
 
···
 
 void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 {
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 
 	if (fcc && fcc->f2fs_issue_flush) {
 		struct task_struct *flush_thread = fcc->f2fs_issue_flush;
···
 	}
 	if (free) {
 		kfree(fcc);
-		SM_I(sbi)->cmd_control_info = NULL;
+		SM_I(sbi)->fcc_info = NULL;
 	}
 }
 
···
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-static struct bio_entry *__add_bio_entry(struct f2fs_sb_info *sbi,
-							struct bio *bio)
+static void __add_discard_cmd(struct f2fs_sb_info *sbi,
+			struct bio *bio, block_t lstart, block_t len)
 {
-	struct list_head *wait_list = &(SM_I(sbi)->wait_list);
-	struct bio_entry *be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *cmd_list = &(dcc->discard_cmd_list);
+	struct discard_cmd *dc;
 
-	INIT_LIST_HEAD(&be->list);
-	be->bio = bio;
-	init_completion(&be->event);
-	list_add_tail(&be->list, wait_list);
+	dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS);
+	INIT_LIST_HEAD(&dc->list);
+	dc->bio = bio;
+	bio->bi_private = dc;
+	dc->lstart = lstart;
+	dc->len = len;
+	dc->state = D_PREP;
+	init_completion(&dc->wait);
 
-	return be;
+	mutex_lock(&dcc->cmd_lock);
+	list_add_tail(&dc->list, cmd_list);
+	mutex_unlock(&dcc->cmd_lock);
 }
 
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *sbi)
+static void __remove_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc)
 {
-	struct list_head *wait_list = &(SM_I(sbi)->wait_list);
-	struct bio_entry *be, *tmp;
+	int err = dc->bio->bi_error;
 
-	list_for_each_entry_safe(be, tmp, wait_list, list) {
-		struct bio *bio = be->bio;
-		int err;
+	if (dc->state == D_DONE)
+		atomic_dec(&(SM_I(sbi)->dcc_info->submit_discard));
 
-		wait_for_completion_io(&be->event);
-		err = be->error;
-		if (err == -EOPNOTSUPP)
-			err = 0;
+	if (err == -EOPNOTSUPP)
+		err = 0;
 
-		if (err)
-			f2fs_msg(sbi->sb, KERN_INFO,
+	if (err)
+		f2fs_msg(sbi->sb, KERN_INFO,
 				"Issue discard failed, ret: %d", err);
-
-		bio_put(bio);
-		list_del(&be->list);
-		kmem_cache_free(bio_entry_slab, be);
-	}
+	bio_put(dc->bio);
+	list_del(&dc->list);
+	kmem_cache_free(discard_cmd_slab, dc);
 }
 
-static void f2fs_submit_bio_wait_endio(struct bio *bio)
+/* This should be covered by global mutex, &sit_i->sentry_lock */
+void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-	struct bio_entry *be = (struct bio_entry *)bio->bi_private;
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *wait_list = &(dcc->discard_cmd_list);
+	struct discard_cmd *dc, *tmp;
+	struct blk_plug plug;
 
-	be->error = bio->bi_error;
-	complete(&be->event);
+	mutex_lock(&dcc->cmd_lock);
+
+	blk_start_plug(&plug);
+
+	list_for_each_entry_safe(dc, tmp, wait_list, list) {
+
+		if (blkaddr == NULL_ADDR) {
+			if (dc->state == D_PREP) {
+				dc->state = D_SUBMIT;
+				submit_bio(dc->bio);
+				atomic_inc(&dcc->submit_discard);
+			}
+			continue;
+		}
+
+		if (dc->lstart <= blkaddr && blkaddr < dc->lstart + dc->len) {
+			if (dc->state == D_SUBMIT)
+				wait_for_completion_io(&dc->wait);
+			else
+				__remove_discard_cmd(sbi, dc);
+		}
+	}
+	blk_finish_plug(&plug);
+
+	/* this comes from f2fs_put_super */
+	if (blkaddr == NULL_ADDR) {
+		list_for_each_entry_safe(dc, tmp, wait_list, list) {
+			wait_for_completion_io(&dc->wait);
+			__remove_discard_cmd(sbi, dc);
+		}
+	}
+	mutex_unlock(&dcc->cmd_lock);
 }
+
+static void f2fs_submit_discard_endio(struct bio *bio)
+{
+	struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
+
+	complete(&dc->wait);
+	dc->state = D_DONE;
+}
+
+static int issue_discard_thread(void *data)
+{
+	struct f2fs_sb_info *sbi = data;
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	wait_queue_head_t *q = &dcc->discard_wait_queue;
+	struct list_head *cmd_list = &dcc->discard_cmd_list;
+	struct discard_cmd *dc, *tmp;
+	struct blk_plug plug;
+	int iter = 0;
+repeat:
+	if (kthread_should_stop())
+		return 0;
+
+	blk_start_plug(&plug);
+
+	mutex_lock(&dcc->cmd_lock);
+	list_for_each_entry_safe(dc, tmp, cmd_list, list) {
+		if (dc->state == D_PREP) {
+			dc->state = D_SUBMIT;
+			submit_bio(dc->bio);
+			atomic_inc(&dcc->submit_discard);
+			if (iter++ > DISCARD_ISSUE_RATE)
+				break;
+		} else if (dc->state == D_DONE) {
+			__remove_discard_cmd(sbi, dc);
+		}
+	}
+	mutex_unlock(&dcc->cmd_lock);
+
+	blk_finish_plug(&plug);
+
+	iter = 0;
+	congestion_wait(BLK_RW_SYNC, HZ/50);
+
+	wait_event_interruptible(*q,
+		kthread_should_stop() || !list_empty(&dcc->discard_cmd_list));
+	goto repeat;
+}
+
 
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
 static int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi,
 		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
 	struct bio *bio = NULL;
+	block_t lblkstart = blkstart;
 	int err;
 
-	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+	trace_f2fs_issue_discard(bdev, blkstart, blklen);
 
 	if (sbi->s_ndevs) {
 		int devi = f2fs_target_device_index(sbi, blkstart);
···
 				SECTOR_FROM_BLOCK(blklen),
 				GFP_NOFS, 0, &bio);
 	if (!err && bio) {
-		struct bio_entry *be = __add_bio_entry(sbi, bio);
-
-		bio->bi_private = be;
-		bio->bi_end_io = f2fs_submit_bio_wait_endio;
+		bio->bi_end_io = f2fs_submit_discard_endio;
 		bio->bi_opf |= REQ_SYNC;
-		submit_bio(bio);
-	}
 
+		__add_discard_cmd(sbi, bio, lblkstart, blklen);
+		wake_up(&SM_I(sbi)->dcc_info->discard_wait_queue);
+	}
 	return err;
 }
 
···
 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;
+	sector_t sector, nr_sects;
 	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_sectors(bdev) - 1) ||
-	    nr_sects != bdev_zone_sectors(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;
 	}
 
 	/*
···
 		return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
 	case BLK_ZONE_TYPE_SEQWRITE_REQ:
 	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		trace_f2fs_issue_reset_zone(sbi->sb, blkstart);
+		sector = SECTOR_FROM_BLOCK(blkstart);
+		nr_sects = SECTOR_FROM_BLOCK(blklen);
+
+		if (sector & (bdev_zone_sectors(bdev) - 1) ||
+				nr_sects != bdev_zone_sectors(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;
+		}
+		trace_f2fs_issue_reset_zone(bdev, blkstart);
 		return blkdev_reset_zones(bdev, sector,
 					  nr_sects, GFP_NOFS);
 	default:
···
 		struct cp_control *cpc, struct seg_entry *se,
 		unsigned int start, unsigned int end)
 {
-	struct list_head *head = &SM_I(sbi)->discard_list;
+	struct list_head *head = &SM_I(sbi)->dcc_info->discard_entry_list;
 	struct discard_entry *new, *last;
 
 	if (!list_empty(head)) {
 		last = list_last_entry(head, struct discard_entry, list);
 		if (START_BLOCK(sbi, cpc->trim_start) + start ==
-						last->blkaddr + last->len) {
+				last->blkaddr + last->len &&
+				last->len < MAX_DISCARD_BLOCKS(sbi)) {
 			last->len += end - start;
 			goto done;
 		}
···
 	new->len = end - start;
 	list_add_tail(&new->list, head);
 done:
-	SM_I(sbi)->nr_discards += end - start;
+	SM_I(sbi)->dcc_info->nr_discards += end - start;
 }
 
-static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
+							bool check_only)
 {
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
 	int max_blocks = sbi->blocks_per_seg;
···
 	int i;
 
 	if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
-		return;
+		return false;
 
 	if (!force) {
 		if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
-		    SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
-			return;
+			SM_I(sbi)->dcc_info->nr_discards >=
+				SM_I(sbi)->dcc_info->max_discards)
+			return false;
 	}
 
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
···
 		dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
 				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
-	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+	while (force || SM_I(sbi)->dcc_info->nr_discards <=
+				SM_I(sbi)->dcc_info->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
 		if (start >= max_blocks)
 			break;
···
 					&& (end - start) < cpc->trim_minlen)
 			continue;
 
+		if (check_only)
+			return true;
+
 		__add_discard_entry(sbi, cpc, se, start, end);
 	}
+	return false;
 }
 
 void release_discard_addrs(struct f2fs_sb_info *sbi)
 {
-	struct list_head *head = &(SM_I(sbi)->discard_list);
+	struct list_head *head = &(SM_I(sbi)->dcc_info->discard_entry_list);
 	struct discard_entry *entry, *this;
 
 	/* drop caches */
···
 
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
-	struct list_head *head = &(SM_I(sbi)->discard_list);
+	struct list_head *head = &(SM_I(sbi)->dcc_info->discard_entry_list);
 	struct discard_entry *entry, *this;
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	struct blk_plug plug;
 	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);
-
-	blk_start_plug(&plug);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
···
 
 		dirty_i->nr_dirty[PRE] -= end - start;
 
-		if (force || !test_opt(sbi, DISCARD))
+		if (!test_opt(sbi, DISCARD))
 			continue;
+
+		if (force && start >= cpc->trim_start &&
+					(end - 1) <= cpc->trim_end)
+				continue;
 
 		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
 			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
···
 		start = start_segno + sbi->segs_per_sec;
 		if (start < end)
 			goto next;
+		else
+			end = start - 1;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
···
 		cpc->trimmed += entry->len;
 skip:
 		list_del(&entry->list);
-		SM_I(sbi)->nr_discards -= entry->len;
+		SM_I(sbi)->dcc_info->nr_discards -= entry->len;
 		kmem_cache_free(discard_entry_slab, entry);
 	}
+}
 
-	blk_finish_plug(&plug);
+static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+	struct discard_cmd_control *dcc;
+	int err = 0;
+
+	if (SM_I(sbi)->dcc_info) {
+		dcc = SM_I(sbi)->dcc_info;
+		goto init_thread;
+	}
+
+	dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL);
+	if (!dcc)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dcc->discard_entry_list);
+	INIT_LIST_HEAD(&dcc->discard_cmd_list);
+	mutex_init(&dcc->cmd_lock);
+	atomic_set(&dcc->submit_discard, 0);
+	dcc->nr_discards = 0;
+	dcc->max_discards = 0;
+
+	init_waitqueue_head(&dcc->discard_wait_queue);
+	SM_I(sbi)->dcc_info = dcc;
+init_thread:
+	dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
+				"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
+	if (IS_ERR(dcc->f2fs_issue_discard)) {
+		err = PTR_ERR(dcc->f2fs_issue_discard);
+		kfree(dcc);
+		SM_I(sbi)->dcc_info = NULL;
+		return err;
+	}
+
+	return err;
+}
+
+static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi, bool free)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	if (dcc && dcc->f2fs_issue_discard) {
+		struct task_struct *discard_thread = dcc->f2fs_issue_discard;
+
+		dcc->f2fs_issue_discard = NULL;
+		kthread_stop(discard_thread);
+	}
+	if (free) {
+		kfree(dcc);
+		SM_I(sbi)->dcc_info = NULL;
+	}
 }
 
 static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
···
 
 	/* Update valid block bitmap */
 	if (del > 0) {
-		if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
+		if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+			if (f2fs_test_and_set_bit(offset,
+						se->cur_valid_map_mir))
+				f2fs_bug_on(sbi, 1);
+			else
+				WARN_ON(1);
+#else
 			f2fs_bug_on(sbi, 1);
+#endif
+		}
 		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))
+		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+			if (!f2fs_test_and_clear_bit(offset,
+						se->cur_valid_map_mir))
+				f2fs_bug_on(sbi, 1);
+			else
+				WARN_ON(1);
+#else
 			f2fs_bug_on(sbi, 1);
+#endif
+		}
 		if (f2fs_discard_en(sbi) &&
 			f2fs_test_and_clear_bit(offset, se->discard_map))
 			sbi->discard_blks++;
···
 
 	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 < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
-		return !test_bit(segno, free_i->free_segmap);
-	return 0;
 }
 
 /*
···
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+	int i, cnt;
+	bool reversed = false;
 
-	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);
+	/* need_SSR() already forces to do this */
+	if (v_ops->get_victim(sbi, &(curseg)->next_segno, BG_GC, type, SSR))
+		return 1;
 
-	/* For data segments, let's do SSR more intensively */
-	for (; type >= CURSEG_HOT_DATA; type--)
+	/* For node segments, let's do SSR more intensively */
+	if (IS_NODESEG(type)) {
+		if (type >= CURSEG_WARM_NODE) {
+			reversed = true;
+			i = CURSEG_COLD_NODE;
+		} else {
+			i = CURSEG_HOT_NODE;
+		}
+		cnt = NR_CURSEG_NODE_TYPE;
+	} else {
+		if (type >= CURSEG_WARM_DATA) {
+			reversed = true;
+			i = CURSEG_COLD_DATA;
+		} else {
+			i = CURSEG_HOT_DATA;
+		}
+		cnt = NR_CURSEG_DATA_TYPE;
+	}
+
+	for (; cnt-- > 0; reversed ? i-- : i++) {
+		if (i == type)
+			continue;
 		if (v_ops->get_victim(sbi, &(curseg)->next_segno,
-						BG_GC, type, SSR))
+						BG_GC, i, SSR))
 			return 1;
+	}
 	return 0;
 }
 
···
 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))
+	else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
+					type == CURSEG_WARM_NODE)
 		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);
+	stat_inc_seg_type(sbi, CURSEG_I(sbi, type));
 }
 
 void allocate_new_segments(struct f2fs_sb_info *sbi)
···
 	struct curseg_info *curseg;
 	unsigned int old_segno;
 	int i;
-
-	if (test_opt(sbi, LFS))
-		return;
 
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		curseg = CURSEG_I(sbi, i);
···
 static const struct segment_allocation default_salloc_ops = {
 	.allocate_segment = allocate_segment_by_default,
 };
+
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
+	__u64 trim_start = cpc->trim_start;
+	bool has_candidate = false;
+
+	mutex_lock(&SIT_I(sbi)->sentry_lock);
+	for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
+		if (add_discard_addrs(sbi, cpc, true)) {
+			has_candidate = true;
+			break;
+		}
+	}
+	mutex_unlock(&SIT_I(sbi)->sentry_lock);
+
+	cpc->trim_start = trim_start;
+	return has_candidate;
+}
 
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
···
 
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
+	f2fs_wait_discard_bio(sbi, *new_blkaddr);
+
 	/*
 	 * __add_sum_entry should be resided under the curseg_mutex
 	 * because, this function updates a summary entry in the
···
 
 	stat_inc_block_count(sbi, curseg);
 
-	if (!__has_curseg_space(sbi, type))
-		sit_i->s_ops->allocate_segment(sbi, type, false);
 	/*
 	 * 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);
 
 	mutex_unlock(&sit_i->sentry_lock);
 
···
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
+	int err;
 
 	if (fio->type == NODE || fio->type == DATA)
 		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
-
+reallocate:
 	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);
+	err = f2fs_submit_page_mbio(fio);
+	if (err == -EAGAIN) {
+		fio->old_blkaddr = fio->new_blkaddr;
+		goto reallocate;
+	}
 
 	if (fio->type == NODE || fio->type == DATA)
 		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
···
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+		f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
+						0, page->index, type, WRITE);
 		if (ordered)
 			wait_on_page_writeback(page);
 		else
···
 			/* add discard candidates */
 			if (cpc->reason != CP_DISCARD) {
 				cpc->trim_start = segno;
-				add_discard_addrs(sbi, cpc);
+				add_discard_addrs(sbi, cpc, false);
 			}
 
 			if (to_journal) {
···
 	f2fs_bug_on(sbi, sit_i->dirty_sentries);
 out:
 	if (cpc->reason == CP_DISCARD) {
+		__u64 trim_start = cpc->trim_start;
+
 		for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
-			add_discard_addrs(sbi, cpc);
+			add_discard_addrs(sbi, cpc, false);
+
+		cpc->trim_start = trim_start;
 	}
 	mutex_unlock(&sit_i->sentry_lock);
 
···
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct sit_info *sit_i;
 	unsigned int sit_segs, start;
-	char *src_bitmap, *dst_bitmap;
+	char *src_bitmap;
 	unsigned int bitmap_size;
 
 	/* allocate memory for SIT information */
···
 				!sit_i->sentries[start].ckpt_valid_map)
 			return -ENOMEM;
 
+#ifdef CONFIG_F2FS_CHECK_FS
+		sit_i->sentries[start].cur_valid_map_mir
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		if (!sit_i->sentries[start].cur_valid_map_mir)
+			return -ENOMEM;
+#endif
+
 		if (f2fs_discard_en(sbi)) {
 			sit_i->sentries[start].discard_map
 				= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
···
 	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)
+	sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+	if (!sit_i->sit_bitmap)
 		return -ENOMEM;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+	if (!sit_i->sit_bitmap_mir)
+		return -ENOMEM;
+#endif
 
 	/* 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 = 0;
-	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;
···
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
 
-	INIT_LIST_HEAD(&sm_info->discard_list);
-	INIT_LIST_HEAD(&sm_info->wait_list);
-	sm_info->nr_discards = 0;
-	sm_info->max_discards = 0;
-
 	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
 
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
···
 		if (err)
 			return err;
 	}
+
+	err = create_discard_cmd_control(sbi);
+	if (err)
+		return err;
 
 	err = build_sit_info(sbi);
 	if (err)
···
 	if (sit_i->sentries) {
 		for (start = 0; start < MAIN_SEGS(sbi); start++) {
 			kfree(sit_i->sentries[start].cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+			kfree(sit_i->sentries[start].cur_valid_map_mir);
+#endif
 			kfree(sit_i->sentries[start].ckpt_valid_map);
 			kfree(sit_i->sentries[start].discard_map);
 		}
···
 
 	SM_I(sbi)->sit_info = NULL;
 	kfree(sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	kfree(sit_i->sit_bitmap_mir);
+#endif
 	kfree(sit_i);
 }
 
···
 	if (!sm_info)
 		return;
 	destroy_flush_cmd_control(sbi, true);
+	destroy_discard_cmd_control(sbi, true);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);
···
 	if (!discard_entry_slab)
 		goto fail;
 
-	bio_entry_slab = f2fs_kmem_cache_create("bio_entry",
-			sizeof(struct bio_entry));
-	if (!bio_entry_slab)
+	discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd",
+			sizeof(struct discard_cmd));
+	if (!discard_cmd_slab)
 		goto destroy_discard_entry;
 
 	sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
 			sizeof(struct sit_entry_set));
 	if (!sit_entry_set_slab)
-		goto destroy_bio_entry;
+		goto destroy_discard_cmd;
 
 	inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
 			sizeof(struct inmem_pages));
···
 
 destroy_sit_entry_set:
 	kmem_cache_destroy(sit_entry_set_slab);
-destroy_bio_entry:
-	kmem_cache_destroy(bio_entry_slab);
+destroy_discard_cmd:
+	kmem_cache_destroy(discard_cmd_slab);
 destroy_discard_entry:
 	kmem_cache_destroy(discard_entry_slab);
 fail:
···
 void destroy_segment_manager_caches(void)
 {
 	kmem_cache_destroy(sit_entry_set_slab);
-	kmem_cache_destroy(bio_entry_slab);
+	kmem_cache_destroy(discard_cmd_slab);
 	kmem_cache_destroy(discard_entry_slab);
 	kmem_cache_destroy(inmem_entry_slab);
 }

fs/f2fs/segment.h

···
 	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
 	unsigned int padding:6;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
+#ifdef CONFIG_F2FS_CHECK_FS
+	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
+#endif
 	/*
 	 * # of valid blocks and the validity bitmap stored in the the last
 	 * checkpoint pack. This information is used by the SSR mode.
···
  * the page is atomically written, and it is in inmem_pages list.
  */
 #define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
 
 struct inmem_pages {
 	struct list_head list;
···
 	block_t sit_blocks;		/* # of blocks used by SIT area */
 	block_t written_valid_blocks;	/* # of valid blocks in main area */
 	char *sit_bitmap;		/* SIT bitmap pointer */
+#ifdef CONFIG_F2FS_CHECK_FS
+	char *sit_bitmap_mir;		/* SIT bitmap mirror */
+#endif
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
 	unsigned long *tmp_map;			/* bitmap for temporal use */
···
 	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
 	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#ifdef CONFIG_F2FS_CHECK_FS
+	memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#endif
 	se->type = GET_SIT_TYPE(rs);
 	se->mtime = le64_to_cpu(rs->mtime);
 }
···
 		void *dst_addr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
+						sit_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
 }
 
···
 
 	check_seg_range(sbi, start);
 
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
+			f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
+		f2fs_bug_on(sbi, 1);
+#endif
+
 	/* calculate sit block address */
 	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
 		blk_addr += sit_i->sit_blocks;
···
 	unsigned int block_off = SIT_BLOCK_OFFSET(start);
 
 	f2fs_change_bit(block_off, sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
+#endif
 }
 
 static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
···
 				- (base + 1) + type;
 }
 
+static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
+						unsigned int secno)
+{
+	if (get_valid_blocks(sbi, secno, sbi->segs_per_sec) >=
+						sbi->fggc_threshold)
+		return true;
+	return false;
+}
+
 static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
 {
 	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
···
  * It is very important to gather dirty pages and write at once, so that we can
  * submit a big bio without interfering other data writes.
  * By default, 512 pages for directory data,
- * 512 pages (2MB) * 3 for three types of nodes, and
- * max_bio_blocks for meta are set.
+ * 512 pages (2MB) * 8 for nodes, and
+ * 256 pages * 8 for meta are set.
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {

fs/f2fs/super.c

···
 	Opt_active_logs,
 	Opt_disable_ext_identify,
 	Opt_inline_xattr,
+	Opt_noinline_xattr,
 	Opt_inline_data,
 	Opt_inline_dentry,
 	Opt_noinline_dentry,
···
 	Opt_noinline_data,
 	Opt_data_flush,
 	Opt_mode,
+	Opt_io_size_bits,
 	Opt_fault_injection,
 	Opt_lazytime,
 	Opt_nolazytime,
···
 	{Opt_active_logs, "active_logs=%u"},
 	{Opt_disable_ext_identify, "disable_ext_identify"},
 	{Opt_inline_xattr, "inline_xattr"},
+	{Opt_noinline_xattr, "noinline_xattr"},
 	{Opt_inline_data, "inline_data"},
 	{Opt_inline_dentry, "inline_dentry"},
 	{Opt_noinline_dentry, "noinline_dentry"},
···
 	{Opt_noinline_data, "noinline_data"},
 	{Opt_data_flush, "data_flush"},
 	{Opt_mode, "mode=%s"},
+	{Opt_io_size_bits, "io_bits=%u"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
···
 enum {
 	GC_THREAD,	/* struct f2fs_gc_thread */
 	SM_INFO,	/* struct f2fs_sm_info */
+	DCC_INFO,	/* struct discard_cmd_control */
 	NM_INFO,	/* struct f2fs_nm_info */
 	F2FS_SBI,	/* struct f2fs_sb_info */
 #ifdef CONFIG_F2FS_FAULT_INJECTION
···
 		return (unsigned char *)sbi->gc_thread;
 	else if (struct_type == SM_INFO)
 		return (unsigned char *)SM_I(sbi);
+	else if (struct_type == DCC_INFO)
+		return (unsigned char *)SM_I(sbi)->dcc_info;
 	else if (struct_type == NM_INFO)
 		return (unsigned char *)NM_I(sbi);
 	else if (struct_type == F2FS_SBI)
···
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
···
 		case Opt_inline_xattr:
 			set_opt(sbi, INLINE_XATTR);
 			break;
+		case Opt_noinline_xattr:
+			clear_opt(sbi, INLINE_XATTR);
+			break;
 #else
 		case Opt_user_xattr:
 			f2fs_msg(sb, KERN_INFO,
···
 		case Opt_inline_xattr:
 			f2fs_msg(sb, KERN_INFO,
 				"inline_xattr options not supported");
+			break;
+		case Opt_noinline_xattr:
+			f2fs_msg(sb, KERN_INFO,
+				"noinline_xattr options not supported");
 			break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
···
 			}
 			kfree(name);
 			break;
+		case Opt_io_size_bits:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			if (arg > __ilog2_u32(BIO_MAX_PAGES)) {
+				f2fs_msg(sb, KERN_WARNING,
+					"Not support %d, larger than %d",
+					1 << arg, BIO_MAX_PAGES);
+				return -EINVAL;
+			}
+			sbi->write_io_size_bits = arg;
+			break;
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 			f2fs_build_fault_attr(sbi, arg);
+			set_opt(sbi, FAULT_INJECTION);
 #else
 			f2fs_msg(sb, KERN_INFO,
 				"FAULT_INJECTION was not selected");
···
 				p);
 			return -EINVAL;
 		}
+	}
+
+	if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
+		f2fs_msg(sb, KERN_ERR,
+				"Should set mode=lfs with %uKB-sized IO",
+				F2FS_IO_SIZE_KB(sbi));
+		return -EINVAL;
 	}
 	return 0;
 }
···
 
 static int f2fs_drop_inode(struct inode *inode)
 {
+	int ret;
 	/*
 	 * This is to avoid a deadlock condition like below.
 	 * writeback_single_inode(inode)
···
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
+		trace_f2fs_drop_inode(inode, 0);
 		return 0;
 	}
-
-	return generic_drop_inode(inode);
+	ret = generic_drop_inode(inode);
+	trace_f2fs_drop_inode(inode, ret);
+	return ret;
 }
 
 int f2fs_inode_dirtied(struct inode *inode, bool sync)
···
 		write_checkpoint(sbi, &cpc);
 	}
 
+	/* be sure to wait for any on-going discard commands */
+	f2fs_wait_discard_bio(sbi, NULL_ADDR);
+
 	/* write_checkpoint can update stat informaion */
 	f2fs_destroy_stats(sbi);
 
···
 	kfree(sbi->raw_super);
 
 	destroy_device_list(sbi);
-
+	mempool_destroy(sbi->write_io_dummy);
 	destroy_percpu_info(sbi);
 	kfree(sbi);
 }
···
 		seq_puts(seq, ",nouser_xattr");
 	if (test_opt(sbi, INLINE_XATTR))
 		seq_puts(seq, ",inline_xattr");
+	else
+		seq_puts(seq, ",noinline_xattr");
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 	if (test_opt(sbi, POSIX_ACL))
···
 	else if (test_opt(sbi, LFS))
 		seq_puts(seq, "lfs");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
+	if (F2FS_IO_SIZE_BITS(sbi))
+		seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (test_opt(sbi, FAULT_INJECTION))
+		seq_puts(seq, ",fault_injection");
+#endif
 
 	return 0;
 }
···
 	sbi->active_logs = NR_CURSEG_TYPE;
 
 	set_opt(sbi, BG_GC);
+	set_opt(sbi, INLINE_XATTR);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
 	set_opt(sbi, EXTENT_CACHE);
···
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	unsigned int max_devices = MAX_DEVICES;
 	int i;
 
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (!RDEV(i).path[0])
+	/* Initialize single device information */
+	if (!RDEV(0).path[0]) {
+		if (!bdev_is_zoned(sbi->sb->s_bdev))
 			return 0;
+		max_devices = 1;
+	}
 
-		if (i == 0) {
-			sbi->devs = kzalloc(sizeof(struct f2fs_dev_info) *
-						MAX_DEVICES, GFP_KERNEL);
-			if (!sbi->devs)
-				return -ENOMEM;
-		}
+	/*
+	 * Initialize multiple devices information, or single
+	 * zoned block device information.
+	 */
+	sbi->devs = kcalloc(max_devices, sizeof(struct f2fs_dev_info),
+				GFP_KERNEL);
+	if (!sbi->devs)
+		return -ENOMEM;
 
-		memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
-		FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments);
-		if (i == 0) {
-			FDEV(i).start_blk = 0;
-			FDEV(i).end_blk = FDEV(i).start_blk +
-				(FDEV(i).total_segments <<
-				sbi->log_blocks_per_seg) - 1 +
-				le32_to_cpu(raw_super->segment0_blkaddr);
-		} else {
-			FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
-			FDEV(i).end_blk = FDEV(i).start_blk +
-				(FDEV(i).total_segments <<
-				sbi->log_blocks_per_seg) - 1;
-		}
+	for (i = 0; i < max_devices; i++) {
 
-		FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+		if (i > 0 && !RDEV(i).path[0])
+			break;
+
+		if (max_devices == 1) {
+			/* Single zoned block device mount */
+			FDEV(0).bdev =
+				blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev,
 					sbi->sb->s_mode, sbi->sb->s_type);
+		} else {
+			/* Multi-device mount */
+			memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+			FDEV(i).total_segments =
+				le32_to_cpu(RDEV(i).total_segments);
+			if (i == 0) {
+				FDEV(i).start_blk = 0;
+				FDEV(i).end_blk = FDEV(i).start_blk +
+				    (FDEV(i).total_segments <<
+				    sbi->log_blocks_per_seg) - 1 +
+				    le32_to_cpu(raw_super->segment0_blkaddr);
+			} else {
+				FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+				FDEV(i).end_blk = FDEV(i).start_blk +
+					(FDEV(i).total_segments <<
+					sbi->log_blocks_per_seg) - 1;
+			}
+			FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+					sbi->sb->s_mode, sbi->sb->s_type);
+		}
 		if (IS_ERR(FDEV(i).bdev))
 			return PTR_ERR(FDEV(i).bdev);
 
···
 					"Failed to initialize F2FS blkzone information");
 				return -EINVAL;
 			}
+			if (max_devices == 1)
+				break;
 			f2fs_msg(sbi->sb, KERN_INFO,
 				"Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
 				i, FDEV(i).path,
···
 				FDEV(i).total_segments,
 				FDEV(i).start_blk, FDEV(i).end_blk);
 	}
+	f2fs_msg(sbi->sb, KERN_INFO,
+			"IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi));
 	return 0;
 }
 
···
 	if (err)
 		goto free_options;
 
+	if (F2FS_IO_SIZE(sbi) > 1) {
+		sbi->write_io_dummy =
+			mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
+		if (!sbi->write_io_dummy)
+			goto free_options;
+	}
+
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_options;
+		goto free_io_dummy;
 	}
 
 	err = get_valid_checkpoint(sbi);
···
 			sbi->valid_super_block ? 1 : 2, err);
 	}
 
+	f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx",
+				cur_cp_version(F2FS_CKPT(sbi)));
 	f2fs_update_time(sbi, CP_TIME);
 	f2fs_update_time(sbi, REQ_TIME);
 	return 0;
···
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
+free_io_dummy:
+	mempool_destroy(sbi->write_io_dummy);
 free_options:
 	destroy_percpu_info(sbi);
 	kfree(options);

fs/f2fs/xattr.c

···
 	return entry;
 }
 
+static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
+					void **last_addr, int index,
+					size_t len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+	unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
+
+	list_for_each_xattr(entry, base_addr) {
+		if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
+			(void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
+			base_addr + inline_size) {
+			*last_addr = entry;
+			return NULL;
+		}
+		if (entry->e_name_index != index)
+			continue;
+		if (entry->e_name_len != len)
+			continue;
+		if (!memcmp(entry->e_name, name, len))
+			break;
+	}
+	return entry;
+}
+
+static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
+				unsigned int index, unsigned int len,
+				const char *name, struct f2fs_xattr_entry **xe,
+				void **base_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	void *cur_addr, *txattr_addr, *last_addr = NULL;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
+	unsigned int inline_size = 0;
+	int err = 0;
+
+	inline_size = inline_xattr_size(inode);
+
+	if (!size && !inline_size)
+		return -ENODATA;
+
+	txattr_addr = kzalloc(inline_size + size + sizeof(__u32),
+							GFP_F2FS_ZERO);
+	if (!txattr_addr)
+		return -ENOMEM;
+
+	/* read from inline xattr */
+	if (inline_size) {
+		struct page *page = NULL;
+		void *inline_addr;
+
+		if (ipage) {
+			inline_addr = inline_xattr_addr(ipage);
+		} else {
+			page = get_node_page(sbi, inode->i_ino);
+			if (IS_ERR(page)) {
+				err = PTR_ERR(page);
+				goto out;
+			}
+			inline_addr = inline_xattr_addr(page);
+		}
+		memcpy(txattr_addr, inline_addr, inline_size);
+		f2fs_put_page(page, 1);
+
+		*xe = __find_inline_xattr(txattr_addr, &last_addr,
+						index, len, name);
+		if (*xe)
+			goto check;
+	}
+
+	/* read from xattr node block */
+	if (xnid) {
+		struct page *xpage;
+		void *xattr_addr;
+
+		/* The inode already has an extended attribute block. */
+		xpage = get_node_page(sbi, xnid);
+		if (IS_ERR(xpage)) {
+			err = PTR_ERR(xpage);
+			goto out;
+		}
+
+		xattr_addr = page_address(xpage);
+		memcpy(txattr_addr + inline_size, xattr_addr, size);
+		f2fs_put_page(xpage, 1);
+	}
+
+	if (last_addr)
+		cur_addr = XATTR_HDR(last_addr) - 1;
+	else
+		cur_addr = txattr_addr;
+
+	*xe = __find_xattr(cur_addr, index, len, name);
+check:
+	if (IS_XATTR_LAST_ENTRY(*xe)) {
+		err = -ENODATA;
+		goto out;
+	}
+
+	*base_addr = txattr_addr;
+	return 0;
+out:
+	kzfree(txattr_addr);
+	return err;
+}
+
 static int read_all_xattrs(struct inode *inode, struct page *ipage,
 							void **base_addr)
 {
···
 	}
 
 	xattr_addr = page_address(xpage);
-	memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
-						sizeof(struct node_footer));
+	memcpy(xattr_addr, txattr_addr + inline_size, MAX_XATTR_BLOCK_SIZE);
 	set_page_dirty(xpage);
 	f2fs_put_page(xpage, 1);
 
-	/* need to checkpoint during fsync */
-	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
 	return 0;
 }
 
 int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		void *buffer, size_t buffer_size, struct page *ipage)
 {
-	struct f2fs_xattr_entry *entry;
-	void *base_addr;
+	struct f2fs_xattr_entry *entry = NULL;
 	int error = 0;
-	size_t size, len;
+	unsigned int size, len;
+	void *base_addr = NULL;
 
 	if (name == NULL)
 		return -EINVAL;
···
 	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
-	error = read_all_xattrs(inode, ipage, &base_addr);
+	error = lookup_all_xattrs(inode, ipage, index, len, name,
+				&entry, &base_addr);
 	if (error)
 		return error;
-
-	entry = __find_xattr(base_addr, index, len, name);
-	if (IS_XATTR_LAST_ENTRY(entry)) {
-		error = -ENODATA;
-		goto cleanup;
-	}
 
 	size = le16_to_cpu(entry->e_value_size);
 
 	if (buffer && size > buffer_size) {
 		error = -ERANGE;
-		goto cleanup;
+		goto out;
 	}
 
 	if (buffer) {
···
 		memcpy(buffer, pval, size);
 	}
 	error = size;
-
-cleanup:
+out:
 	kzfree(base_addr);
 	return error;
 }
···
 	return error;
 }
 
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+					const void *value, size_t size)
+{
+	void *pval = entry->e_name + entry->e_name_len;
+	return (entry->e_value_size == size) && !memcmp(pval, value, size);
+}
+
 static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
···
 
 	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
 
-	if ((flags & XATTR_REPLACE) && !found) {
+	if (found) {
+		if ((flags & XATTR_CREATE)) {
+			error = -EEXIST;
+			goto exit;
+		}
+
+		if (f2fs_xattr_value_same(here, value, size))
+			goto exit;
+	} else if ((flags & XATTR_REPLACE)) {
 		error = -ENODATA;
-		goto exit;
-	} else if ((flags & XATTR_CREATE) && found) {
-		error = -EEXIST;
 		goto exit;
 	}
 

fs/f2fs/xattr.h

···
 		for (entry = XATTR_FIRST_ENTRY(addr);\
 				!IS_XATTR_LAST_ENTRY(entry);\
 				entry = XATTR_NEXT_ENTRY(entry))
-
-#define MIN_OFFSET(i)	XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE -	\
-				sizeof(struct node_footer) - sizeof(__u32))
+#define MAX_XATTR_BLOCK_SIZE	(PAGE_SIZE - sizeof(struct node_footer))
+#define VALID_XATTR_BLOCK_SIZE	(MAX_XATTR_BLOCK_SIZE - sizeof(__u32))
+#define MIN_OFFSET(i)		XATTR_ALIGN(inline_xattr_size(i) +	\
+						VALID_XATTR_BLOCK_SIZE)
 
 #define MAX_VALUE_LEN(i)	(MIN_OFFSET(i) -			\
 				sizeof(struct f2fs_xattr_header) -	\

include/linux/f2fs_fs.h

···
 #define F2FS_NODE_INO(sbi)	(sbi->node_ino_num)
 #define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
 
+#define F2FS_IO_SIZE(sbi)	(1 << (sbi)->write_io_size_bits) /* Blocks */
+#define F2FS_IO_SIZE_KB(sbi)	(1 << ((sbi)->write_io_size_bits + 2)) /* KB */
+#define F2FS_IO_SIZE_BYTES(sbi)	(1 << ((sbi)->write_io_size_bits + 12)) /* B */
+#define F2FS_IO_SIZE_BITS(sbi)	((sbi)->write_io_size_bits) /* power of 2 */
+#define F2FS_IO_SIZE_MASK(sbi)	(F2FS_IO_SIZE(sbi) - 1)
+
 /* This flag is used by node and meta inodes, and by recovery */
 #define GFP_F2FS_ZERO		(GFP_NOFS | __GFP_ZERO)
 #define GFP_F2FS_HIGH_ZERO	(GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
···
 /*
  * For checkpoint
  */
+#define CP_NAT_BITS_FLAG	0x00000080
 #define CP_CRC_RECOVERY_FLAG	0x00000040
 #define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
···
  * For NAT entries
  */
 #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_BITMAP_SIZE	((NAT_ENTRY_PER_BLOCK + 7) / 8)
 
 struct f2fs_nat_entry {
 	__u8 version;		/* latest version of cached nat entry */

include/trace/events/f2fs.h

···
 
 #include <linux/tracepoint.h>
 
-#define show_dev(entry)		MAJOR(entry->dev), MINOR(entry->dev)
-#define show_dev_ino(entry)	show_dev(entry), (unsigned long)entry->ino
+#define show_dev(dev)		MAJOR(dev), MINOR(dev)
+#define show_dev_ino(entry)	show_dev(entry->dev), (unsigned long)entry->ino
 
 TRACE_DEFINE_ENUM(NODE);
 TRACE_DEFINE_ENUM(DATA);
···
 		{ IPU,		"IN-PLACE" },				\
 		{ OPU,		"OUT-OF-PLACE" })
 
-#define F2FS_BIO_FLAG_MASK(t)	(t & (REQ_RAHEAD | REQ_PREFLUSH | REQ_FUA))
-#define F2FS_BIO_EXTRA_MASK(t)	(t & (REQ_META | REQ_PRIO))
+#define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_PREFLUSH | REQ_META |\
+			REQ_PRIO)
+#define F2FS_BIO_FLAG_MASK(t)	(t & F2FS_OP_FLAGS)
 
-#define show_bio_type(op_flags)	show_bio_op_flags(op_flags), 		\
-						show_bio_extra(op_flags)
+#define show_bio_type(op,op_flags)	show_bio_op(op),		\
+						show_bio_op_flags(op_flags)
+
+#define show_bio_op(op)							\
+	__print_symbolic(op,						\
+		{ REQ_OP_READ,			"READ" },		\
+		{ REQ_OP_WRITE,			"WRITE" },		\
+		{ REQ_OP_FLUSH,			"FLUSH" },		\
+		{ REQ_OP_DISCARD,		"DISCARD" },		\
+		{ REQ_OP_ZONE_REPORT,		"ZONE_REPORT" },	\
+		{ REQ_OP_SECURE_ERASE,		"SECURE_ERASE" },	\
+		{ REQ_OP_ZONE_RESET,		"ZONE_RESET" },		\
+		{ REQ_OP_WRITE_SAME,		"WRITE_SAME" },		\
+		{ REQ_OP_WRITE_ZEROES,		"WRITE_ZEROES" })
 
 #define show_bio_op_flags(flags)					\
 	__print_symbolic(F2FS_BIO_FLAG_MASK(flags),			\
-		{ 0,			"WRITE" },			\
-		{ REQ_RAHEAD, 		"READAHEAD" },			\
-		{ REQ_SYNC, 		"REQ_SYNC" },			\
-		{ REQ_PREFLUSH,		"REQ_PREFLUSH" },		\
-		{ REQ_FUA,		"REQ_FUA" })
-
-#define show_bio_extra(type)						\
-	__print_symbolic(F2FS_BIO_EXTRA_MASK(type),			\
+		{ REQ_RAHEAD, 		"(RA)" },			\
+		{ REQ_SYNC, 		"(S)" },			\
+		{ REQ_SYNC | REQ_PRIO,	"(SP)" },			\
 		{ REQ_META, 		"(M)" },			\
-		{ REQ_PRIO, 		"(P)" },			\
 		{ REQ_META | REQ_PRIO,	"(MP)" },			\
+		{ REQ_SYNC | REQ_PREFLUSH , "(SF)" },			\
+		{ REQ_SYNC | REQ_META | REQ_PRIO, "(SMP)" },		\
+		{ REQ_PREFLUSH | REQ_META | REQ_PRIO, "(FMP)" },	\
 		{ 0, " \b" })
 
 #define show_data_type(type)						\
···
 	),
 
 	TP_printk("dev = (%d,%d), superblock is %s, wait = %d",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		__entry->dirty ? "dirty" : "not dirty",
 		__entry->wait)
 );
···
 );
 
 DEFINE_EVENT(f2fs__inode_exit, f2fs_unlink_exit,
+
+	TP_PROTO(struct inode *inode, int ret),
+
+	TP_ARGS(inode, ret)
+);
+
+DEFINE_EVENT(f2fs__inode_exit, f2fs_drop_inode,
 
 	TP_PROTO(struct inode *inode, int ret),
 
···
 	),
 
 	TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		__entry->wait_ms,
 		__entry->prefree,
 		__entry->free)
···
 		__field(int,	alloc_mode)
 		__field(int,	gc_mode)
 		__field(unsigned int,	victim)
+		__field(unsigned int,	cost)
 		__field(unsigned int,	ofs_unit)
 		__field(unsigned int,	pre_victim)
 		__field(unsigned int,	prefree)
···
 		__entry->alloc_mode	= p->alloc_mode;
 		__entry->gc_mode	= p->gc_mode;
 		__entry->victim		= p->min_segno;
+		__entry->cost		= p->min_cost;
 		__entry->ofs_unit	= p->ofs_unit;
 		__entry->pre_victim	= pre_victim;
 		__entry->prefree	= prefree;
 		__entry->free		= free;
 	),
 
-	TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u "
-		"ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u",
-		show_dev(__entry),
+	TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), "
+		"victim = %u, cost = %u, ofs_unit = %u, "
+		"pre_victim_secno = %d, prefree = %u, free = %u",
+		show_dev(__entry->dev),
 		show_data_type(__entry->type),
 		show_gc_type(__entry->gc_type),
 		show_alloc_mode(__entry->alloc_mode),
 		show_victim_policy(__entry->gc_mode),
 		__entry->victim,
+		__entry->cost,
 		__entry->ofs_unit,
 		(int)__entry->pre_victim,
 		__entry->prefree,
···
 	),
 
 	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		(unsigned int)__entry->nid,
 		__entry->ofs_in_node,
 		(unsigned long long)__entry->count)
···
 		(unsigned long)__entry->index,
 		(unsigned long long)__entry->old_blkaddr,
 		(unsigned long long)__entry->new_blkaddr,
-		show_bio_type(__entry->op_flags),
+		show_bio_type(__entry->op, __entry->op_flags),
 		show_block_type(__entry->type))
 );
 
···
 	TP_CONDITION(page->mapping)
 );
 
-DECLARE_EVENT_CLASS(f2fs__submit_bio,
+DECLARE_EVENT_CLASS(f2fs__bio,
 
-	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
-						struct bio *bio),
+	TP_PROTO(struct super_block *sb, int type, struct bio *bio),
 
-	TP_ARGS(sb, fio, bio),
+	TP_ARGS(sb, type, bio),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
+		__field(dev_t,	target)
 		__field(int,	op)
 		__field(int,	op_flags)
 		__field(int,	type)
···
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->op		= fio->op;
-		__entry->op_flags	= fio->op_flags;
-		__entry->type		= fio->type;
+		__entry->target		= bio->bi_bdev->bd_dev;
+		__entry->op		= bio_op(bio);
+		__entry->op_flags	= bio->bi_opf;
+		__entry->type		= type;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->size		= bio->bi_iter.bi_size;
 	),
 
-	TP_printk("dev = (%d,%d), rw = %s%s, %s, sector = %lld, size = %u",
-		show_dev(__entry),
-		show_bio_type(__entry->op_flags),
+	TP_printk("dev = (%d,%d)/(%d,%d), rw = %s%s, %s, sector = %lld, size = %u",
+		show_dev(__entry->target),
+		show_dev(__entry->dev),
+		show_bio_type(__entry->op, __entry->op_flags),
 		show_block_type(__entry->type),
 		(unsigned long long)__entry->sector,
 		__entry->size)
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_write_bio,
 
-	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
-							struct bio *bio),
+	TP_PROTO(struct super_block *sb, int type, struct bio *bio),
 
-	TP_ARGS(sb, fio, bio),
+	TP_ARGS(sb, type, bio),
 
 	TP_CONDITION(bio)
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_read_bio,
 
-	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
-							struct bio *bio),
+	TP_PROTO(struct super_block *sb, int type, struct bio *bio),
 
-	TP_ARGS(sb, fio, bio),
+	TP_ARGS(sb, type, bio),
+
+	TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_read_bio,
+
+	TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+	TP_ARGS(sb, type, bio),
+
+	TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio,
+
+	TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+	TP_ARGS(sb, type, bio),
 
 	TP_CONDITION(bio)
 );
···
 	),
 
 	TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		show_cpreason(__entry->reason),
 		__entry->msg)
 );
 
 TRACE_EVENT(f2fs_issue_discard,
 
-	TP_PROTO(struct super_block *sb, block_t blkstart, block_t blklen),
+	TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
 
-	TP_ARGS(sb, blkstart, blklen),
+	TP_ARGS(dev, blkstart, blklen),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
···
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev	= dev->bd_dev;
 		__entry->blkstart = blkstart;
 		__entry->blklen = blklen;
 	),
 
 	TP_printk("dev = (%d,%d), blkstart = 0x%llx, blklen = 0x%llx",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		(unsigned long long)__entry->blkstart,
 		(unsigned long long)__entry->blklen)
 );
 
 TRACE_EVENT(f2fs_issue_reset_zone,
 
-	TP_PROTO(struct super_block *sb, block_t blkstart),
+	TP_PROTO(struct block_device *dev, block_t blkstart),
 
-	TP_ARGS(sb, blkstart),
+	TP_ARGS(dev, blkstart),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
···
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev	= dev->bd_dev;
 		__entry->blkstart = blkstart;
 	),
 
 	TP_printk("dev = (%d,%d), reset zone at block = 0x%llx",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		(unsigned long long)__entry->blkstart)
 );
 
 TRACE_EVENT(f2fs_issue_flush,
 
-	TP_PROTO(struct super_block *sb, unsigned int nobarrier,
+	TP_PROTO(struct block_device *dev, unsigned int nobarrier,
 					unsigned int flush_merge),
 
-	TP_ARGS(sb, nobarrier, flush_merge),
+	TP_ARGS(dev, nobarrier, flush_merge),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
···
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev	= dev->bd_dev;
 		__entry->nobarrier = nobarrier;
 		__entry->flush_merge = flush_merge;
 	),
 
 	TP_printk("dev = (%d,%d), %s %s",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		__entry->nobarrier ? "skip (nobarrier)" : "issue",
 		__entry->flush_merge ? " with flush_merge" : "")
 );
···
 	),
 
 	TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		__entry->node_cnt,
 		__entry->tree_cnt)
 );
···
 	),
 
 	TP_printk("dev = (%d,%d), %s, dirty count = %lld",
-		show_dev(__entry),
+		show_dev(__entry->dev),
 		show_file_type(__entry->type),
 		__entry->count)
 );