Merge tag 'f2fs-for-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
"In this round, there are three major updates: (1) folio conversion,
(2) refactoring for mount API conversion, (3) some performance
improvement such as direct IO, checkpoint speed, and IO priority
hints.

For stability, there are patches which add more sanity checks and
fixes some major issues like i_size in atomic write operations and
write pointer recovery in zoned devices.

Enhancements:
- huge folio converion work by Matthew Wilcox
- clean up for mount API conversion by Eric Sandeen
- improve direct IO speed in the overwrite case
- add some sanity check on node consistency
- set highest IO priority for checkpoint thread
- keep POSIX_FADV_NOREUSE ranges and add sysfs entry to reclaim pages
- add ioctl to get IO priority hint
- add carve_out sysfs node for fsstat

Bug fixes:
- disable nat_bits during umount to avoid potential nat entry corruption
- fix missing i_size update on atomic writes
- fix missing discard for active segments
- fix running out of free segments
- fix out-of-bounds access in f2fs_truncate_inode_blocks()
- call f2fs_recover_quota_end() correctly
- fix potential deadloop in prepare_compress_overwrite()
- fix the missing write pointer correction for zoned device
- fix to avoid panic once fallocation fails for pinfile
- don't retry IO for corrupted data scenario

There are many other clean up patches and minor bug fixes as usual"

* tag 'f2fs-for-6.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (68 commits)
f2fs: fix missing discard for active segments
f2fs: optimize f2fs DIO overwrites
f2fs: fix to avoid atomicity corruption of atomic file
f2fs: pass sbi rather than sb to parse_options()
f2fs: pass sbi rather than sb to quota qf_name helpers
f2fs: defer readonly check vs norecovery
f2fs: Pass sbi rather than sb to f2fs_set_test_dummy_encryption
f2fs: make LAZYTIME a mount option flag
f2fs: make INLINECRYPT a mount option flag
f2fs: factor out an f2fs_default_check function
f2fs: consolidate unsupported option handling errors
f2fs: use f2fs_sb_has_device_alias during option parsing
f2fs: add carve_out sysfs node
f2fs: fix to avoid running out of free segments
f2fs: Remove f2fs_write_node_page()
f2fs: Remove f2fs_write_meta_page()
f2fs: Remove f2fs_write_data_page()
f2fs: Remove check for ->writepage
Revert "f2fs: rebuild nat_bits during umount"
f2fs: fix to avoid accessing uninitialized curseg
...

Documentation/ABI/testing/sysfs-fs-f2fs

···
 		FAULT_BLKADDR_VALIDITY           0x000040000
 		FAULT_BLKADDR_CONSISTENCE        0x000080000
 		FAULT_NO_SEGMENT                 0x000100000
+		FAULT_INCONSISTENT_FOOTER        0x000200000
 		===========================      ===========
 
 What:		/sys/fs/f2fs/<disk>/discard_io_aware_gran
···
 Contact:	"Chao Yu" <[e-mail]>
 Description:	It controls max read extent count for per-inode, the value of threshold
 		is 10240 by default.
+
+What:		/sys/fs/f2fs/tuning/reclaim_caches_kb
+Date:		February 2025
+Contact:	"Jaegeuk Kim" <[e-mail]>
+Description:	It reclaims the given KBs of file-backed pages registered by
+		ioctl(F2FS_IOC_DONATE_RANGE).
+		For example, writing N tries to drop N KBs spaces in LRU.
+
+What:		/sys/fs/f2fs/<disk>/carve_out
+Date:		March 2025
+Contact:	"Daeho Jeong" <[e-mail]>
+Description:	For several zoned storage devices, vendors will provide extra space which
+		was used for device level GC than specs and F2FS can use this space for
+		filesystem level GC. To do that, we can reserve the space using
+		reserved_blocks. However, it is not enough, since this extra space should
+		not be shown to users. So, with this new sysfs node, we can hide the space
+		by substracting reserved_blocks from total bytes.

Documentation/filesystems/f2fs.rst

···
 			 FAULT_BLKADDR_VALIDITY           0x000040000
 			 FAULT_BLKADDR_CONSISTENCE        0x000080000
 			 FAULT_NO_SEGMENT                 0x000100000
+			 FAULT_INCONSISTENT_FOOTER        0x000200000
 			 ===========================      ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random
···
 			 pending node write	drop		keep		N/A
 			 pending meta write	keep		keep		N/A
 			 ====================== =============== =============== ========
+nat_bits		 Enable nat_bits feature to enhance full/empty nat blocks access,
+			 by default it's disabled.
 ======================== ============================================================
 
 Debugfs Entries

fs/f2fs/checkpoint.c

···
 #include "iostat.h"
 #include <trace/events/f2fs.h>
 
-#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 3))
 
 static struct kmem_cache *ino_entry_slab;
 struct kmem_cache *f2fs_inode_entry_slab;
···
 							bool is_meta)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	struct page *page;
+	struct folio *folio;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = META,
···
 	if (unlikely(!is_meta))
 		fio.op_flags &= ~REQ_META;
 repeat:
-	page = f2fs_grab_cache_page(mapping, index, false);
-	if (!page) {
+	folio = f2fs_grab_cache_folio(mapping, index, false);
+	if (IS_ERR(folio)) {
 		cond_resched();
 		goto repeat;
 	}
-	if (PageUptodate(page))
+	if (folio_test_uptodate(folio))
 		goto out;
 
-	fio.page = page;
+	fio.page = &folio->page;
 
 	err = f2fs_submit_page_bio(&fio);
 	if (err) {
-		f2fs_put_page(page, 1);
+		f2fs_folio_put(folio, true);
 		return ERR_PTR(err);
 	}
 
 	f2fs_update_iostat(sbi, NULL, FS_META_READ_IO, F2FS_BLKSIZE);
 
-	lock_page(page);
-	if (unlikely(page->mapping != mapping)) {
-		f2fs_put_page(page, 1);
+	folio_lock(folio);
+	if (unlikely(folio->mapping != mapping)) {
+		f2fs_folio_put(folio, true);
 		goto repeat;
 	}
 
-	if (unlikely(!PageUptodate(page))) {
-		f2fs_handle_page_eio(sbi, page_folio(page), META);
-		f2fs_put_page(page, 1);
+	if (unlikely(!folio_test_uptodate(folio))) {
+		f2fs_handle_page_eio(sbi, folio, META);
+		f2fs_folio_put(folio, true);
 		return ERR_PTR(-EIO);
 	}
 out:
-	return page;
+	return &folio->page;
 }
 
 struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
···
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
-static int f2fs_write_meta_page(struct page *page,
-				struct writeback_control *wbc)
-{
-	return __f2fs_write_meta_page(page, wbc, FS_META_IO);
-}
-
 static int f2fs_write_meta_pages(struct address_space *mapping,
 				struct writeback_control *wbc)
 {
···
 }
 
 const struct address_space_operations f2fs_meta_aops = {
-	.writepage	= f2fs_write_meta_page,
 	.writepages	= f2fs_write_meta_pages,
 	.dirty_folio	= f2fs_dirty_meta_folio,
 	.invalidate_folio = f2fs_invalidate_folio,
···
 retry_flush_quotas:
 	f2fs_lock_all(sbi);
 	if (__need_flush_quota(sbi)) {
-		int locked;
+		bool need_lock = sbi->umount_lock_holder != current;
 
 		if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
 			set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
···
 		}
 		f2fs_unlock_all(sbi);
 
-		/* only failed during mount/umount/freeze/quotactl */
-		locked = down_read_trylock(&sbi->sb->s_umount);
-		f2fs_quota_sync(sbi->sb, -1);
-		if (locked)
+		/* don't grab s_umount lock during mount/umount/remount/freeze/quotactl */
+		if (!need_lock) {
+			f2fs_do_quota_sync(sbi->sb, -1);
+		} else if (down_read_trylock(&sbi->sb->s_umount)) {
+			f2fs_do_quota_sync(sbi->sb, -1);
 			up_read(&sbi->sb->s_umount);
+		}
 		cond_resched();
 		goto retry_flush_quotas;
 	}
···
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long flags;
 
-	if (cpc->reason & CP_UMOUNT) {
-		if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
-			NM_I(sbi)->nat_bits_blocks > BLKS_PER_SEG(sbi)) {
-			clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
-			f2fs_notice(sbi, "Disable nat_bits due to no space");
-		} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&
-						f2fs_nat_bitmap_enabled(sbi)) {
-			f2fs_enable_nat_bits(sbi);
-			set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
-			f2fs_notice(sbi, "Rebuild and enable nat_bits");
-		}
-	}
-
 	spin_lock_irqsave(&sbi->cp_lock, flags);
+
+	if ((cpc->reason & CP_UMOUNT) &&
+			le32_to_cpu(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_TRIMMED)
 		__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
···
 	start_blk = __start_cp_next_addr(sbi);
 
 	/* write nat bits */
-	if ((cpc->reason & CP_UMOUNT) &&
-			is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG)) {
+	if (enabled_nat_bits(sbi, cpc)) {
 		__u64 cp_ver = cur_cp_version(ckpt);
 		block_t blk;
 
···
 	struct cp_control cpc;
 
 	cpc.reason = __get_cp_reason(sbi);
-	if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC) {
+	if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC ||
+		sbi->umount_lock_holder == current) {
 		int ret;
 
 		f2fs_down_write(&sbi->gc_lock);

fs/f2fs/compress.c

···
 		f2fs_compress_ctx_add_page(cc, page_folio(page));
 
 		if (!PageUptodate(page)) {
+			f2fs_handle_page_eio(sbi, page_folio(page), DATA);
 release_and_retry:
 			f2fs_put_rpages(cc);
 			f2fs_unlock_rpages(cc, i + 1);

fs/f2fs/data.c

···
 static void f2fs_write_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi;
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
 	iostat_update_and_unbind_ctx(bio);
 	sbi = bio->bi_private;
···
 	if (time_to_inject(sbi, FAULT_WRITE_IO))
 		bio->bi_status = BLK_STS_IOERR;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		struct page *page = bvec->bv_page;
-		enum count_type type = WB_DATA_TYPE(page, false);
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
+		enum count_type type;
 
-		fscrypt_finalize_bounce_page(&page);
+		if (fscrypt_is_bounce_folio(folio)) {
+			struct folio *io_folio = folio;
+
+			folio = fscrypt_pagecache_folio(io_folio);
+			fscrypt_free_bounce_page(&io_folio->page);
+		}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-		if (f2fs_is_compressed_page(page)) {
-			f2fs_compress_write_end_io(bio, page);
+		if (f2fs_is_compressed_page(&folio->page)) {
+			f2fs_compress_write_end_io(bio, &folio->page);
 			continue;
 		}
 #endif
 
+		type = WB_DATA_TYPE(&folio->page, false);
+
 		if (unlikely(bio->bi_status)) {
-			mapping_set_error(page->mapping, -EIO);
+			mapping_set_error(folio->mapping, -EIO);
 			if (type == F2FS_WB_CP_DATA)
 				f2fs_stop_checkpoint(sbi, true,
 						STOP_CP_REASON_WRITE_FAIL);
 		}
 
-		f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
-				page_folio(page)->index != nid_of_node(page));
+		f2fs_bug_on(sbi, folio->mapping == NODE_MAPPING(sbi) &&
+				folio->index != nid_of_node(&folio->page));
 
 		dec_page_count(sbi, type);
-		if (f2fs_in_warm_node_list(sbi, page))
-			f2fs_del_fsync_node_entry(sbi, page);
-		clear_page_private_gcing(page);
-		end_page_writeback(page);
+		if (f2fs_in_warm_node_list(sbi, folio))
+			f2fs_del_fsync_node_entry(sbi, &folio->page);
+		clear_page_private_gcing(&folio->page);
+		folio_end_writeback(folio);
 	}
 	if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
 				wq_has_sleeper(&sbi->cp_wait))
···
 static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
 {
 	unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0);
+	struct folio *fio_folio = page_folio(fio->page);
 	unsigned int fua_flag, meta_flag, io_flag;
 	blk_opf_t op_flags = 0;
 
···
 		op_flags |= REQ_META;
 	if (BIT(fio->temp) & fua_flag)
 		op_flags |= REQ_FUA;
+
+	if (fio->type == DATA &&
+	    F2FS_I(fio_folio->mapping->host)->ioprio_hint == F2FS_IOPRIO_WRITE)
+		op_flags |= REQ_PRIO;
+
 	return op_flags;
 }
 
···
 	struct bio *bio = *fio->bio;
 	struct page *page = fio->encrypted_page ?
 			fio->encrypted_page : fio->page;
+	struct folio *folio = page_folio(fio->page);
 
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
 			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
···
 alloc_new:
 	if (!bio) {
 		bio = __bio_alloc(fio, BIO_MAX_VECS);
-		f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
-				page_folio(fio->page)->index, fio, GFP_NOIO);
+		f2fs_set_bio_crypt_ctx(bio, folio->mapping->host,
+				folio->index, fio, GFP_NOIO);
 
 		add_bio_entry(fio->sbi, bio, page, fio->temp);
 	} else {
···
 	}
 
 	if (fio->io_wbc)
-		wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
-					 PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, folio, folio_size(folio));
 
 	inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
 
···
 	bio = bio_alloc_bioset(bdev, bio_max_segs(nr_pages),
 			       REQ_OP_READ | op_flag,
 			       for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset);
-	if (!bio)
-		return ERR_PTR(-ENOMEM);
 	bio->bi_iter.bi_sector = sector;
 	f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS);
 	bio->bi_end_io = f2fs_read_end_io;
···
 	return err;
 }
 
-struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
-				     blk_opf_t op_flags, bool for_write,
-				     pgoff_t *next_pgofs)
+struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
+		blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
-	struct page *page;
+	struct folio *folio;
 	int err;
 
-	page = f2fs_grab_cache_page(mapping, index, for_write);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	folio = f2fs_grab_cache_folio(mapping, index, for_write);
+	if (IS_ERR(folio))
+		return folio;
 
 	if (f2fs_lookup_read_extent_cache_block(inode, index,
 						&dn.data_blkaddr)) {
···
 		goto put_err;
 	}
 got_it:
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		return page;
+	if (folio_test_uptodate(folio)) {
+		folio_unlock(folio);
+		return folio;
 	}
 
 	/*
···
 	 * f2fs_init_inode_metadata.
 	 */
 	if (dn.data_blkaddr == NEW_ADDR) {
-		zero_user_segment(page, 0, PAGE_SIZE);
-		if (!PageUptodate(page))
-			SetPageUptodate(page);
-		unlock_page(page);
-		return page;
+		folio_zero_segment(folio, 0, folio_size(folio));
+		if (!folio_test_uptodate(folio))
+			folio_mark_uptodate(folio);
+		folio_unlock(folio);
+		return folio;
 	}
 
-	err = f2fs_submit_page_read(inode, page_folio(page), dn.data_blkaddr,
+	err = f2fs_submit_page_read(inode, folio, dn.data_blkaddr,
 						op_flags, for_write);
 	if (err)
 		goto put_err;
-	return page;
+	return folio;
 
 put_err:
-	f2fs_put_page(page, 1);
+	f2fs_folio_put(folio, true);
 	return ERR_PTR(err);
 }
 
-struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
 					pgoff_t *next_pgofs)
 {
 	struct address_space *mapping = inode->i_mapping;
-	struct page *page;
+	struct folio *folio;
 
-	page = find_get_page_flags(mapping, index, FGP_ACCESSED);
-	if (page && PageUptodate(page))
-		return page;
-	f2fs_put_page(page, 0);
+	folio = __filemap_get_folio(mapping, index, FGP_ACCESSED, 0);
+	if (IS_ERR(folio))
+		goto read;
+	if (folio_test_uptodate(folio))
+		return folio;
+	f2fs_folio_put(folio, false);
 
-	page = f2fs_get_read_data_page(inode, index, 0, false, next_pgofs);
-	if (IS_ERR(page))
-		return page;
+read:
+	folio = f2fs_get_read_data_folio(inode, index, 0, false, next_pgofs);
+	if (IS_ERR(folio))
+		return folio;
 
-	if (PageUptodate(page))
-		return page;
+	if (folio_test_uptodate(folio))
+		return folio;
 
-	wait_on_page_locked(page);
-	if (unlikely(!PageUptodate(page))) {
-		f2fs_put_page(page, 0);
+	folio_wait_locked(folio);
+	if (unlikely(!folio_test_uptodate(folio))) {
+		f2fs_folio_put(folio, false);
 		return ERR_PTR(-EIO);
 	}
-	return page;
+	return folio;
 }
 
 /*
···
  * Because, the callers, functions in dir.c and GC, should be able to know
  * whether this page exists or not.
  */
-struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
 							bool for_write)
 {
 	struct address_space *mapping = inode->i_mapping;
-	struct page *page;
+	struct folio *folio;
 
-	page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
-	if (IS_ERR(page))
-		return page;
+	folio = f2fs_get_read_data_folio(inode, index, 0, for_write, NULL);
+	if (IS_ERR(folio))
+		return folio;
 
 	/* wait for read completion */
-	lock_page(page);
-	if (unlikely(page->mapping != mapping || !PageUptodate(page))) {
-		f2fs_put_page(page, 1);
+	folio_lock(folio);
+	if (unlikely(folio->mapping != mapping || !folio_test_uptodate(folio))) {
+		f2fs_folio_put(folio, true);
 		return ERR_PTR(-EIO);
 	}
-	return page;
+	return folio;
 }
 
 /*
···
 	int i;
 	int ret = 0;
 
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
+		from_dnode = false;
+		goto out_put_dnode;
+	}
+
 	f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
 
 	last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
···
 	if (ret)
 		goto out;
 
-	if (unlikely(f2fs_cp_error(sbi))) {
-		ret = -EIO;
-		goto out_put_dnode;
-	}
 	f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
 
 skip_reading_dnode:
···
 	return err;
 }
 
-static int f2fs_write_data_page(struct page *page,
-					struct writeback_control *wbc)
-{
-	struct folio *folio = page_folio(page);
-#ifdef CONFIG_F2FS_FS_COMPRESSION
-	struct inode *inode = folio->mapping->host;
-
-	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
-		goto out;
-
-	if (f2fs_compressed_file(inode)) {
-		if (f2fs_is_compressed_cluster(inode, folio->index)) {
-			folio_redirty_for_writepage(wbc, folio);
-			return AOP_WRITEPAGE_ACTIVATE;
-		}
-	}
-out:
-#endif
-
-	return f2fs_write_single_data_page(folio, NULL, NULL, NULL,
-						wbc, FS_DATA_IO, 0, true);
-}
-
 /*
  * This function was copied from write_cache_pages from mm/page-writeback.c.
  * The major change is making write step of cold data page separately from
···
 	int ret;
 	bool locked = false;
 
-	/* deal with chardevs and other special file */
-	if (!mapping->a_ops->writepage)
-		return 0;
-
 	/* skip writing if there is no dirty page in this inode */
 	if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
 		return 0;
···
 
 restart:
 	/* check inline_data */
-	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto unlock_out;
···
 	struct page *ipage;
 	int err = 0;
 
-	ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
···
 
 	f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
 
-	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto unlock_out;
···
 const struct address_space_operations f2fs_dblock_aops = {
 	.read_folio	= f2fs_read_data_folio,
 	.readahead	= f2fs_readahead,
-	.writepage	= f2fs_write_data_page,
 	.writepages	= f2fs_write_data_pages,
 	.write_begin	= f2fs_write_begin,
 	.write_end	= f2fs_write_end,
···
 	map.m_next_pgofs = &next_pgofs;
 	map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
 						inode->i_write_hint);
-	if (flags & IOMAP_WRITE)
+
+	/*
+	 * If the blocks being overwritten are already allocated,
+	 * f2fs_map_lock and f2fs_balance_fs are not necessary.
+	 */
+	if ((flags & IOMAP_WRITE) &&
+		!f2fs_overwrite_io(inode, offset, length))
 		map.m_may_create = true;
 
 	err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DIO);

fs/f2fs/debug.c

···
 	si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
 	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+	si->ndonate_files = sbi->donate_files;
 	si->nquota_files = sbi->nquota_files;
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->aw_cnt = atomic_read(&sbi->atomic_files);
···
 			   si->compr_inode, si->compr_blocks);
 		seq_printf(s, "  - Swapfile Inode: %u\n",
 			   si->swapfile_inode);
+		seq_printf(s, "  - Donate Inode: %u\n",
+			   si->ndonate_files);
 		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",

fs/f2fs/dir.c

···
 				goto put_error;
 		}
 	} else {
-		page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino);
+		page = f2fs_get_inode_page(F2FS_I_SB(dir), inode->i_ino);
 		if (IS_ERR(page))
 			return page;
 	}

fs/f2fs/f2fs.h

···
 	FAULT_BLKADDR_VALIDITY,
 	FAULT_BLKADDR_CONSISTENCE,
 	FAULT_NO_SEGMENT,
+	FAULT_INCONSISTENT_FOOTER,
 	FAULT_MAX,
 };
 
···
 #define	F2FS_MOUNT_GC_MERGE		0x02000000
 #define F2FS_MOUNT_COMPRESS_CACHE	0x04000000
 #define F2FS_MOUNT_AGE_EXTENT_CACHE	0x08000000
+#define F2FS_MOUNT_NAT_BITS		0x10000000
+#define F2FS_MOUNT_INLINECRYPT		0x20000000
+/*
+ * Some f2fs environments expect to be able to pass the "lazytime" option
+ * string rather than using the MS_LAZYTIME flag, so this must remain.
+ */
+#define F2FS_MOUNT_LAZYTIME		0x40000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
···
 
 	/* Use below internally in f2fs*/
 	unsigned long flags[BITS_TO_LONGS(FI_MAX)];	/* use to pass per-file flags */
+	unsigned int ioprio_hint;	/* hint for IO priority */
 	struct f2fs_rwsem i_sem;	/* protect fi info */
 	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
···
 #endif
 	struct list_head dirty_list;	/* dirty list for dirs and files */
 	struct list_head gdirty_list;	/* linked in global dirty list */
+
+	/* linked in global inode list for cache donation */
+	struct list_head gdonate_list;
+	pgoff_t donate_start, donate_end; /* inclusive */
+
 	struct task_struct *atomic_write_task;	/* store atomic write task */
 	struct extent_tree *extent_tree[NR_EXTENT_CACHES];
 					/* cached extent_tree entry */
···
 	DIR_INODE,			/* for dirty dir inode */
 	FILE_INODE,			/* for dirty regular/symlink inode */
 	DIRTY_META,			/* for all dirtied inode metadata */
+	DONATE_INODE,			/* for all inode to donate pages */
 	NR_INODE_TYPE,
 };
 
···
 	unsigned int warm_data_age_threshold;
 	unsigned int last_age_weight;
 
+	/* control donate caches */
+	unsigned int donate_files;
+
 	/* basic filesystem units */
 	unsigned int log_sectors_per_block;	/* log2 sectors per block */
 	unsigned int log_blocksize;		/* log2 block size */
···
 
 	unsigned int nquota_files;		/* # of quota sysfile */
 	struct f2fs_rwsem quota_sem;		/* blocking cp for flags */
+	struct task_struct *umount_lock_holder;	/* s_umount lock holder */
 
 	/* # of pages, see count_type */
 	atomic_t nr_pages[NR_COUNT_TYPE];
···
 	s64 peak_atomic_write;
 	u64 committed_atomic_block;
 	u64 revoked_atomic_block;
+
+	/* carve out reserved_blocks from total blocks */
+	bool carve_out;
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	struct kmem_cache *page_array_slab;	/* page array entry */
···
 	return (struct f2fs_checkpoint *)(sbi->ckpt);
 }
 
-static inline struct f2fs_node *F2FS_NODE(struct page *page)
+static inline struct f2fs_node *F2FS_NODE(const struct page *page)
 {
 	return (struct f2fs_node *)page_address(page);
 }
···
 #ifdef CONFIG_F2FS_UNFAIR_RWSEM
 	wake_up_all(&sem->read_waiters);
 #endif
+}
+
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
+{
+	unsigned long flags;
+	unsigned char *nat_bits;
+
+	/*
+	 * In order to re-enable nat_bits we need to call fsck.f2fs by
+	 * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
+	 * so let's rely on regular fsck or unclean shutdown.
+	 */
+
+	if (lock)
+		spin_lock_irqsave(&sbi->cp_lock, flags);
+	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+	nat_bits = NM_I(sbi)->nat_bits;
+	NM_I(sbi)->nat_bits = NULL;
+	if (lock)
+		spin_unlock_irqrestore(&sbi->cp_lock, flags);
+
+	kvfree(nat_bits);
+}
+
+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)
···
 	return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
 }
 
-static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
-						pgoff_t index, bool for_write)
+static inline struct folio *f2fs_grab_cache_folio(struct address_space *mapping,
+		pgoff_t index, bool for_write)
 {
-	struct page *page;
+	struct folio *folio;
 	unsigned int flags;
 
 	if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
+		fgf_t fgf_flags;
+
 		if (!for_write)
-			page = find_get_page_flags(mapping, index,
-							FGP_LOCK | FGP_ACCESSED);
+			fgf_flags = FGP_LOCK | FGP_ACCESSED;
 		else
-			page = find_lock_page(mapping, index);
-		if (page)
-			return page;
+			fgf_flags = FGP_LOCK;
+		folio = __filemap_get_folio(mapping, index, fgf_flags, 0);
+		if (!IS_ERR(folio))
+			return folio;
 
 		if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 	}
 
 	if (!for_write)
-		return grab_cache_page(mapping, index);
+		return filemap_grab_folio(mapping, index);
 
 	flags = memalloc_nofs_save();
-	page = grab_cache_page_write_begin(mapping, index);
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
 	memalloc_nofs_restore(flags);
 
-	return page;
+	return folio;
+}
+
+static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
+						pgoff_t index, bool for_write)
+{
+	struct folio *folio = f2fs_grab_cache_folio(mapping, index, for_write);
+
+	if (IS_ERR(folio))
+		return NULL;
+	return &folio->page;
 }
 
 static inline struct page *f2fs_pagecache_get_page(
···
 	return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
 }
 
+static inline void f2fs_folio_put(struct folio *folio, bool unlock)
+{
+	if (!folio)
+		return;
+
+	if (unlock) {
+		f2fs_bug_on(F2FS_F_SB(folio), !folio_test_locked(folio));
+		folio_unlock(folio);
+	}
+	folio_put(folio);
+}
+
 static inline void f2fs_put_page(struct page *page, int unlock)
 {
 	if (!page)
 		return;
-
-	if (unlock) {
-		f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
-		unlock_page(page);
-	}
-	put_page(page);
+	f2fs_folio_put(page_folio(page), unlock);
 }
 
 static inline void f2fs_put_dnode(struct dnode_of_data *dn)
···
 void f2fs_inode_synced(struct inode *inode);
 int f2fs_dquot_initialize(struct inode *inode);
 int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
-int f2fs_quota_sync(struct super_block *sb, int type);
+int f2fs_do_quota_sync(struct super_block *sb, int type);
 loff_t max_file_blocks(struct inode *inode);
 void f2fs_quota_off_umount(struct super_block *sb);
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag);
···
 
 int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
 bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
-bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi,
+		const struct folio *folio);
 void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
 void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
 void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
···
 int f2fs_truncate_xattr_node(struct inode *inode);
 int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
 					unsigned int seq_id);
-bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi);
 int f2fs_remove_inode_page(struct inode *inode);
 struct page *f2fs_new_inode_page(struct inode *inode);
 struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
 void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
 struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct folio *f2fs_get_inode_folio(struct f2fs_sb_info *sbi, pgoff_t ino);
+struct page *f2fs_get_inode_page(struct f2fs_sb_info *sbi, pgoff_t ino);
+struct page *f2fs_get_xnode_page(struct f2fs_sb_info *sbi, pgoff_t xnid);
 struct page *f2fs_get_node_page_ra(struct page *parent, int start);
 int f2fs_move_node_page(struct page *node_page, int gc_type);
 void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
···
 int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
 int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct f2fs_summary_block *sum);
-void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi);
 int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
 int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
 void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
···
 			struct f2fs_io_info *fio);
 void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
 					block_t blkaddr, unsigned int blkcnt);
-void f2fs_wait_on_page_writeback(struct page *page,
-			enum page_type type, bool ordered, bool locked);
+void f2fs_folio_wait_writeback(struct folio *folio, enum page_type type,
+		bool ordered, bool locked);
+#define f2fs_wait_on_page_writeback(page, type, ordered, locked)	\
+		f2fs_folio_wait_writeback(page_folio(page), type, ordered, locked)
 void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
 void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
 								block_t len);
···
 int f2fs_reserve_new_block(struct dnode_of_data *dn);
 int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index);
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
-			blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs);
-struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
-							pgoff_t *next_pgofs);
-struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
+		blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs);
+struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
+		pgoff_t *next_pgofs);
+struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
 			bool for_write);
 struct page *f2fs_get_new_data_page(struct inode *inode,
 			struct page *ipage, pgoff_t index, bool new_i_size);
···
 int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
 void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
 extern const struct iomap_ops f2fs_iomap_ops;
+
+static inline struct page *f2fs_find_data_page(struct inode *inode,
+		pgoff_t index, pgoff_t *next_pgofs)
+{
+	struct folio *folio = f2fs_find_data_folio(inode, index, next_pgofs);
+
+	return &folio->page;
+}
+
+static inline struct page *f2fs_get_lock_data_page(struct inode *inode,
+		pgoff_t index, bool for_write)
+{
+	struct folio *folio = f2fs_get_lock_data_folio(inode, index, for_write);
+
+	return &folio->page;
+}
 
 /*
  * gc.c
···
 	unsigned long long allocated_data_blocks;
 	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
 	int ndirty_data, ndirty_qdata;
-	unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
+	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
+	unsigned int nquota_files, ndonate_files;
 	int nats, dirty_nats, sits, dirty_sits;
 	int free_nids, avail_nids, alloc_nids;
 	int total_count, utilization;
···
 			struct shrink_control *sc);
 unsigned long f2fs_shrink_scan(struct shrinker *shrink,
 			struct shrink_control *sc);
+unsigned int f2fs_donate_files(void);
+void f2fs_reclaim_caches(unsigned int reclaim_caches_kb);
 void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
 void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
 

fs/f2fs/file.c

···
 	loff_t offset = from & (PAGE_SIZE - 1);
 	pgoff_t index = from >> PAGE_SHIFT;
 	struct address_space *mapping = inode->i_mapping;
-	struct page *page;
+	struct folio *folio;
 
 	if (!offset && !cache_only)
 		return 0;
 
 	if (cache_only) {
-		page = find_lock_page(mapping, index);
-		if (page && PageUptodate(page))
+		folio = filemap_lock_folio(mapping, index);
+		if (IS_ERR(folio))
+		       return 0;
+		if (folio_test_uptodate(folio))
 			goto truncate_out;
-		f2fs_put_page(page, 1);
+		f2fs_folio_put(folio, true);
 		return 0;
 	}
 
-	page = f2fs_get_lock_data_page(inode, index, true);
-	if (IS_ERR(page))
-		return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
+	folio = f2fs_get_lock_data_folio(inode, index, true);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio) == -ENOENT ? 0 : PTR_ERR(folio);
 truncate_out:
-	f2fs_wait_on_page_writeback(page, DATA, true, true);
-	zero_user(page, offset, PAGE_SIZE - offset);
+	f2fs_folio_wait_writeback(folio, DATA, true, true);
+	folio_zero_segment(folio, offset, folio_size(folio));
 
 	/* An encrypted inode should have a key and truncate the last page. */
 	f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode));
 	if (!cache_only)
-		set_page_dirty(page);
-	f2fs_put_page(page, 1);
+		folio_mark_dirty(folio);
+	f2fs_folio_put(folio, true);
 	return 0;
 }
 
···
 	if (lock)
 		f2fs_lock_op(sbi);
 
-	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto out;
···
 
 		map.m_len = sec_blks;
 next_alloc:
+		f2fs_down_write(&sbi->pin_sem);
+
+		if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+			if (has_not_enough_free_secs(sbi, 0, 0)) {
+				f2fs_up_write(&sbi->pin_sem);
+				err = -ENOSPC;
+				f2fs_warn_ratelimited(sbi,
+					"ino:%lu, start:%lu, end:%lu, need to trigger GC to "
+					"reclaim enough free segment when checkpoint is enabled",
+					inode->i_ino, pg_start, pg_end);
+				goto out_err;
+			}
+		}
+
 		if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ?
 			ZONED_PIN_SEC_REQUIRED_COUNT :
 			GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
 			f2fs_down_write(&sbi->gc_lock);
 			stat_inc_gc_call_count(sbi, FOREGROUND);
 			err = f2fs_gc(sbi, &gc_control);
-			if (err && err != -ENODATA)
+			if (err && err != -ENODATA) {
+				f2fs_up_write(&sbi->pin_sem);
 				goto out_err;
+			}
 		}
-
-		f2fs_down_write(&sbi->pin_sem);
 
 		err = f2fs_allocate_pinning_section(sbi);
 		if (err) {
···
 		mnt_drop_write_file(filp);
 
 	return ret;
+}
+
+static void f2fs_keep_noreuse_range(struct inode *inode,
+				loff_t offset, loff_t len)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	u64 max_bytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
+	u64 start, end;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	if (offset >= max_bytes || len > max_bytes ||
+	    (offset + len) > max_bytes)
+		return;
+
+	start = offset >> PAGE_SHIFT;
+	end = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+
+	inode_lock(inode);
+	if (f2fs_is_atomic_file(inode)) {
+		inode_unlock(inode);
+		return;
+	}
+
+	spin_lock(&sbi->inode_lock[DONATE_INODE]);
+	/* let's remove the range, if len = 0 */
+	if (!len) {
+		if (!list_empty(&F2FS_I(inode)->gdonate_list)) {
+			list_del_init(&F2FS_I(inode)->gdonate_list);
+			sbi->donate_files--;
+		}
+	} else {
+		if (list_empty(&F2FS_I(inode)->gdonate_list)) {
+			list_add_tail(&F2FS_I(inode)->gdonate_list,
+					&sbi->inode_list[DONATE_INODE]);
+			sbi->donate_files++;
+		} else {
+			list_move_tail(&F2FS_I(inode)->gdonate_list,
+					&sbi->inode_list[DONATE_INODE]);
+		}
+		F2FS_I(inode)->donate_start = start;
+		F2FS_I(inode)->donate_end = end - 1;
+	}
+	spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+	inode_unlock(inode);
 }
 
 static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
···
 {
 	return put_user(IS_DEVICE_ALIASING(file_inode(filp)) ? 1 : 0,
 			(u32 __user *)arg);
+}
+
+static int f2fs_ioc_io_prio(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	__u32 level;
+
+	if (get_user(level, (__u32 __user *)arg))
+		return -EFAULT;
+
+	if (!S_ISREG(inode->i_mode) || level >= F2FS_IOPRIO_MAX)
+		return -EINVAL;
+
+	inode_lock(inode);
+	F2FS_I(inode)->ioprio_hint = level;
+	inode_unlock(inode);
+	return 0;
 }
 
 int f2fs_precache_extents(struct inode *inode)
···
 		return f2fs_ioc_compress_file(filp);
 	case F2FS_IOC_GET_DEV_ALIAS_FILE:
 		return f2fs_ioc_get_dev_alias_file(filp, arg);
+	case F2FS_IOC_IO_PRIO:
+		return f2fs_ioc_io_prio(filp, arg);
 	default:
 		return -ENOTTY;
 	}
···
 	}
 
 	err = generic_fadvise(filp, offset, len, advice);
-	if (!err && advice == POSIX_FADV_DONTNEED &&
-		test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) &&
-		f2fs_compressed_file(inode))
-		f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino);
+	if (err)
+		return err;
 
-	return err;
+	if (advice == POSIX_FADV_DONTNEED &&
+	    (test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) &&
+	     f2fs_compressed_file(inode)))
+		f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino);
+	else if (advice == POSIX_FADV_NOREUSE)
+		f2fs_keep_noreuse_range(inode, offset, len);
+	return 0;
 }
 
 #ifdef CONFIG_COMPAT
···
 	case F2FS_IOC_DECOMPRESS_FILE:
 	case F2FS_IOC_COMPRESS_FILE:
 	case F2FS_IOC_GET_DEV_ALIAS_FILE:
+	case F2FS_IOC_IO_PRIO:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/f2fs/gc.c

···
 }
 
 static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
-							unsigned int segno, int off)
+						unsigned int segno, int off)
 {
-	struct page *page;
+	struct folio *folio;
 	int err = 0;
 
-	page = f2fs_get_lock_data_page(inode, bidx, true);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
+	folio = f2fs_get_lock_data_folio(inode, bidx, true);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off)) {
 		err = -ENOENT;
···
 		goto out;
 
 	if (gc_type == BG_GC) {
-		if (folio_test_writeback(page_folio(page))) {
+		if (folio_test_writeback(folio)) {
 			err = -EAGAIN;
 			goto out;
 		}
-		set_page_dirty(page);
-		set_page_private_gcing(page);
+		folio_mark_dirty(folio);
+		set_page_private_gcing(&folio->page);
 	} else {
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
···
 			.op = REQ_OP_WRITE,
 			.op_flags = REQ_SYNC,
 			.old_blkaddr = NULL_ADDR,
-			.page = page,
+			.page = &folio->page,
 			.encrypted_page = NULL,
 			.need_lock = LOCK_REQ,
 			.io_type = FS_GC_DATA_IO,
 		};
-		bool is_dirty = PageDirty(page);
+		bool is_dirty = folio_test_dirty(folio);
 
 retry:
-		f2fs_wait_on_page_writeback(page, DATA, true, true);
+		f2fs_folio_wait_writeback(folio, DATA, true, true);
 
-		set_page_dirty(page);
-		if (clear_page_dirty_for_io(page)) {
+		folio_mark_dirty(folio);
+		if (folio_clear_dirty_for_io(folio)) {
 			inode_dec_dirty_pages(inode);
 			f2fs_remove_dirty_inode(inode);
 		}
 
-		set_page_private_gcing(page);
+		set_page_private_gcing(&folio->page);
 
 		err = f2fs_do_write_data_page(&fio);
 		if (err) {
-			clear_page_private_gcing(page);
+			clear_page_private_gcing(&folio->page);
 			if (err == -ENOMEM) {
 				memalloc_retry_wait(GFP_NOFS);
 				goto retry;
 			}
 			if (is_dirty)
-				set_page_dirty(page);
+				folio_mark_dirty(folio);
 		}
 	}
 out:
-	f2fs_put_page(page, 1);
+	f2fs_folio_put(folio, true);
 	return err;
 }
 
···
 	entry = sum;
 
 	for (off = 0; off < usable_blks_in_seg; off++, entry++) {
-		struct page *data_page;
 		struct inode *inode;
 		struct node_info dni; /* dnode info for the data */
 		unsigned int ofs_in_node, nofs;
···
 		ofs_in_node = le16_to_cpu(entry->ofs_in_node);
 
 		if (phase == 3) {
+			struct folio *data_folio;
 			int err;
 
 			inode = f2fs_iget(sb, dni.ino);
···
 				continue;
 			}
 
-			data_page = f2fs_get_read_data_page(inode, start_bidx,
+			data_folio = f2fs_get_read_data_folio(inode, start_bidx,
 							REQ_RAHEAD, true, NULL);
 			f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
-			if (IS_ERR(data_page)) {
+			if (IS_ERR(data_folio)) {
 				iput(inode);
 				continue;
 			}
 
-			f2fs_put_page(data_page, 0);
+			f2fs_folio_put(data_folio, false);
 			add_gc_inode(gc_list, inode);
 			continue;
 		}

fs/f2fs/inline.c

···
 {
 	struct page *ipage;
 
-	ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage)) {
 		folio_unlock(folio);
 		return PTR_ERR(ipage);
···
 
 	f2fs_lock_op(sbi);
 
-	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto out;
···
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *ipage;
 
-	ipage = f2fs_get_node_page(sbi, inode->i_ino);
+	ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
···
 	if (f2fs_has_inline_data(inode) &&
 			ri && (ri->i_inline & F2FS_INLINE_DATA)) {
 process_inline:
-		ipage = f2fs_get_node_page(sbi, inode->i_ino);
+		ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 		if (IS_ERR(ipage))
 			return PTR_ERR(ipage);
 
···
 	}
 
 	if (f2fs_has_inline_data(inode)) {
-		ipage = f2fs_get_node_page(sbi, inode->i_ino);
+		ipage = f2fs_get_inode_page(sbi, inode->i_ino);
 		if (IS_ERR(ipage))
 			return PTR_ERR(ipage);
 		f2fs_truncate_inline_inode(inode, ipage, 0);
···
 	struct page *ipage;
 	void *inline_dentry;
 
-	ipage = f2fs_get_node_page(sbi, dir->i_ino);
+	ipage = f2fs_get_inode_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage)) {
 		*res_page = ipage;
 		return NULL;
···
 	if (err)
 		goto out;
 
-	ipage = f2fs_get_node_page(sbi, dir->i_ino);
+	ipage = f2fs_get_inode_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto out_fname;
···
 	struct page *page = NULL;
 	int err = 0;
 
-	ipage = f2fs_get_node_page(sbi, dir->i_ino);
+	ipage = f2fs_get_inode_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
···
 	void *inline_dentry;
 	struct f2fs_dentry_ptr d;
 
-	ipage = f2fs_get_node_page(sbi, dir->i_ino);
+	ipage = f2fs_get_inode_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage))
 		return false;
 
···
 	if (ctx->pos == d.max)
 		return 0;
 
-	ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
···
 	struct page *ipage;
 	int err = 0;
 
-	ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 

fs/f2fs/inode.c

···
 	if (f2fs_inode_dirtied(inode, sync))
 		return;
 
-	if (f2fs_is_atomic_file(inode)) {
-		set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+	if (f2fs_is_atomic_file(inode))
 		return;
-	}
 
 	mark_inode_dirty_sync(inode);
 }
···
 	if (f2fs_check_nid_range(sbi, inode->i_ino))
 		return -EINVAL;
 
-	node_page = f2fs_get_node_page(sbi, inode->i_ino);
+	node_page = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page))
 		return PTR_ERR(node_page);
 
···
 	struct page *node_page;
 	int count = 0;
 retry:
-	node_page = f2fs_get_node_page(sbi, inode->i_ino);
+	node_page = f2fs_get_inode_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
 		int err = PTR_ERR(node_page);
 
···
 		if (err == -ENOENT)
 			return;
 
+		if (err == -EFSCORRUPTED)
+			goto stop_checkpoint;
+
 		if (err == -ENOMEM || ++count <= DEFAULT_RETRY_IO_COUNT)
 			goto retry;
+stop_checkpoint:
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_UPDATE_INODE);
 		return;
 	}
···
 		!is_inode_flag_set(inode, FI_DIRTY_INODE))
 		return 0;
 
+	/*
+	 * no need to update inode page, ultimately f2fs_evict_inode() will
+	 * clear dirty status of inode.
+	 */
+	if (f2fs_cp_error(sbi))
+		return -EIO;
+
 	if (!f2fs_is_checkpoint_ready(sbi)) {
 		f2fs_mark_inode_dirty_sync(inode, true);
 		return -ENOSPC;
···
 	if (wbc && wbc->nr_to_write)
 		f2fs_balance_fs(sbi, true);
 	return 0;
+}
+
+static void f2fs_remove_donate_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	if (list_empty(&F2FS_I(inode)->gdonate_list))
+		return;
+
+	spin_lock(&sbi->inode_lock[DONATE_INODE]);
+	list_del_init(&F2FS_I(inode)->gdonate_list);
+	sbi->donate_files--;
+	spin_unlock(&sbi->inode_lock[DONATE_INODE]);
 }
 
 /*
···
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
 	f2fs_remove_dirty_inode(inode);
+	f2fs_remove_donate_inode(inode);
 
 	if (!IS_DEVICE_ALIASING(inode))
 		f2fs_destroy_extent_tree(inode);

fs/f2fs/namei.c

···
 		goto out;
 	}
 
+	if (inode->i_nlink == 0) {
+		f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink",
+			  __func__, inode->i_ino);
+		err = -EFSCORRUPTED;
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+		goto out_iput;
+	}
+
 	if (IS_ENCRYPTED(dir) &&
 	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 	    !fscrypt_has_permitted_context(dir, inode)) {

fs/f2fs/node.c

···
 							start, nr);
 }
 
-bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page)
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, const struct folio *folio)
 {
-	return NODE_MAPPING(sbi) == page->mapping &&
-			IS_DNODE(page) && is_cold_node(page);
+	return NODE_MAPPING(sbi) == folio->mapping &&
+			IS_DNODE(&folio->page) && is_cold_node(&folio->page);
 }
 
 void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi)
···
 	npage[0] = dn->inode_page;
 
 	if (!npage[0]) {
-		npage[0] = f2fs_get_node_page(sbi, nids[0]);
+		npage[0] = f2fs_get_inode_page(sbi, nids[0]);
 		if (IS_ERR(npage[0]))
 			return PTR_ERR(npage[0]);
 	}
···
 	unsigned int nofs = 0;
 	struct f2fs_inode *ri;
 	struct dnode_of_data dn;
-	struct page *page;
+	struct folio *folio;
 
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
 	level = get_node_path(inode, from, offset, noffset);
-	if (level < 0) {
+	if (level <= 0) {
+		if (!level) {
+			level = -EFSCORRUPTED;
+			f2fs_err(sbi, "%s: inode ino=%lx has corrupted node block, from:%lu addrs:%u",
+					__func__, inode->i_ino,
+					from, ADDRS_PER_INODE(inode));
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		}
 		trace_f2fs_truncate_inode_blocks_exit(inode, level);
 		return level;
 	}
 
-	page = f2fs_get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(page)) {
-		trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
-		return PTR_ERR(page);
+	folio = f2fs_get_inode_folio(sbi, inode->i_ino);
+	if (IS_ERR(folio)) {
+		trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(folio));
+		return PTR_ERR(folio);
 	}
 
-	set_new_dnode(&dn, inode, page, NULL, 0);
-	unlock_page(page);
+	set_new_dnode(&dn, inode, &folio->page, NULL, 0);
+	folio_unlock(folio);
 
-	ri = F2FS_INODE(page);
+	ri = F2FS_INODE(&folio->page);
 	switch (level) {
 	case 0:
 	case 1:
···
 
 skip_partial:
 	while (cont) {
-		dn.nid = get_nid(page, offset[0], true);
+		dn.nid = get_nid(&folio->page, offset[0], true);
 		switch (offset[0]) {
 		case NODE_DIR1_BLOCK:
 		case NODE_DIR2_BLOCK:
···
 			BUG();
 		}
 		if (err == -ENOENT) {
-			set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+			set_sbi_flag(F2FS_F_SB(folio), SBI_NEED_FSCK);
 			f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
 			f2fs_err_ratelimited(sbi,
 				"truncate node fail, ino:%lu, nid:%u, "
···
 		}
 		if (err < 0)
 			goto fail;
-		if (offset[1] == 0 && get_nid(page, offset[0], true)) {
-			lock_page(page);
-			BUG_ON(page->mapping != NODE_MAPPING(sbi));
-			set_nid(page, offset[0], 0, true);
-			unlock_page(page);
+		if (offset[1] == 0 && get_nid(&folio->page, offset[0], true)) {
+			folio_lock(folio);
+			BUG_ON(folio->mapping != NODE_MAPPING(sbi));
+			set_nid(&folio->page, offset[0], 0, true);
+			folio_unlock(folio);
 		}
 		offset[1] = 0;
 		offset[0]++;
 		nofs += err;
 	}
 fail:
-	f2fs_put_page(page, 0);
+	f2fs_folio_put(folio, false);
 	trace_f2fs_truncate_inode_blocks_exit(inode, err);
 	return err > 0 ? 0 : err;
 }
···
 	if (!nid)
 		return 0;
 
-	npage = f2fs_get_node_page(sbi, nid);
+	npage = f2fs_get_xnode_page(sbi, nid);
 	if (IS_ERR(npage))
 		return PTR_ERR(npage);
 
···
 	f2fs_put_page(apage, err ? 1 : 0);
 }
 
-static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
-					struct page *parent, int start)
+static int sanity_check_node_footer(struct f2fs_sb_info *sbi,
+					struct page *page, pgoff_t nid,
+					enum node_type ntype)
 {
-	struct page *page;
+	if (unlikely(nid != nid_of_node(page) ||
+		(ntype == NODE_TYPE_INODE && !IS_INODE(page)) ||
+		(ntype == NODE_TYPE_XATTR &&
+		!f2fs_has_xattr_block(ofs_of_node(page))) ||
+		time_to_inject(sbi, FAULT_INCONSISTENT_FOOTER))) {
+		f2fs_warn(sbi, "inconsistent node block, node_type:%d, nid:%lu, "
+			  "node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+			  ntype, nid, nid_of_node(page), ino_of_node(page),
+			  ofs_of_node(page), cpver_of_node(page),
+			  next_blkaddr_of_node(page));
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
+		return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+static struct folio *__get_node_folio(struct f2fs_sb_info *sbi, pgoff_t nid,
+					struct page *parent, int start,
+					enum node_type ntype)
+{
+	struct folio *folio;
 	int err;
 
 	if (!nid)
···
 	if (f2fs_check_nid_range(sbi, nid))
 		return ERR_PTR(-EINVAL);
 repeat:
-	page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
-	if (!page)
-		return ERR_PTR(-ENOMEM);
+	folio = f2fs_grab_cache_folio(NODE_MAPPING(sbi), nid, false);
+	if (IS_ERR(folio))
+		return folio;
 
-	err = read_node_page(page, 0);
+	err = read_node_page(&folio->page, 0);
 	if (err < 0) {
 		goto out_put_err;
 	} else if (err == LOCKED_PAGE) {
···
 	if (parent)
 		f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE);
 
-	lock_page(page);
+	folio_lock(folio);
 
-	if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
-		f2fs_put_page(page, 1);
+	if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
+		f2fs_folio_put(folio, true);
 		goto repeat;
 	}
 
-	if (unlikely(!PageUptodate(page))) {
+	if (unlikely(!folio_test_uptodate(folio))) {
 		err = -EIO;
 		goto out_err;
 	}
 
-	if (!f2fs_inode_chksum_verify(sbi, page)) {
+	if (!f2fs_inode_chksum_verify(sbi, &folio->page)) {
 		err = -EFSBADCRC;
 		goto out_err;
 	}
 page_hit:
-	if (likely(nid == nid_of_node(page)))
-		return page;
-
-	f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
-			  nid, nid_of_node(page), ino_of_node(page),
-			  ofs_of_node(page), cpver_of_node(page),
-			  next_blkaddr_of_node(page));
-	set_sbi_flag(sbi, SBI_NEED_FSCK);
-	f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
-	err = -EFSCORRUPTED;
+	err = sanity_check_node_footer(sbi, &folio->page, nid, ntype);
+	if (!err)
+		return folio;
 out_err:
-	ClearPageUptodate(page);
+	folio_clear_uptodate(folio);
 out_put_err:
 	/* ENOENT comes from read_node_page which is not an error. */
 	if (err != -ENOENT)
-		f2fs_handle_page_eio(sbi, page_folio(page), NODE);
-	f2fs_put_page(page, 1);
+		f2fs_handle_page_eio(sbi, folio, NODE);
+	f2fs_folio_put(folio, true);
 	return ERR_PTR(err);
 }
 
 struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 {
-	return __get_node_page(sbi, nid, NULL, 0);
+	struct folio *folio = __get_node_folio(sbi, nid, NULL, 0,
+						NODE_TYPE_REGULAR);
+
+	return &folio->page;
+}
+
+struct folio *f2fs_get_inode_folio(struct f2fs_sb_info *sbi, pgoff_t ino)
+{
+	return __get_node_folio(sbi, ino, NULL, 0, NODE_TYPE_INODE);
+}
+
+struct page *f2fs_get_inode_page(struct f2fs_sb_info *sbi, pgoff_t ino)
+{
+	struct folio *folio = f2fs_get_inode_folio(sbi, ino);
+
+	return &folio->page;
+}
+
+struct page *f2fs_get_xnode_page(struct f2fs_sb_info *sbi, pgoff_t xnid)
+{
+	struct folio *folio = __get_node_folio(sbi, xnid, NULL, 0,
+						NODE_TYPE_XATTR);
+
+	return &folio->page;
 }
 
 struct page *f2fs_get_node_page_ra(struct page *parent, int start)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
 	nid_t nid = get_nid(parent, start, false);
+	struct folio *folio = __get_node_folio(sbi, nid, parent, start,
+							NODE_TYPE_REGULAR);
 
-	return __get_node_page(sbi, nid, parent, start);
+	return &folio->page;
 }
 
 static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
···
 	iput(inode);
 }
 
-static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
+static struct folio *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	pgoff_t index;
 	struct folio_batch fbatch;
-	struct page *last_page = NULL;
+	struct folio *last_folio = NULL;
 	int nr_folios;
 
 	folio_batch_init(&fbatch);
···
 		int i;
 
 		for (i = 0; i < nr_folios; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
 
 			if (unlikely(f2fs_cp_error(sbi))) {
-				f2fs_put_page(last_page, 0);
+				f2fs_folio_put(last_folio, false);
 				folio_batch_release(&fbatch);
 				return ERR_PTR(-EIO);
 			}
 
-			if (!IS_DNODE(page) || !is_cold_node(page))
+			if (!IS_DNODE(&folio->page) || !is_cold_node(&folio->page))
 				continue;
-			if (ino_of_node(page) != ino)
+			if (ino_of_node(&folio->page) != ino)
 				continue;
 
-			lock_page(page);
+			folio_lock(folio);
 
-			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+			if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
 continue_unlock:
-				unlock_page(page);
+				folio_unlock(folio);
 				continue;
 			}
-			if (ino_of_node(page) != ino)
+			if (ino_of_node(&folio->page) != ino)
 				goto continue_unlock;
 
-			if (!PageDirty(page)) {
+			if (!folio_test_dirty(folio)) {
 				/* someone wrote it for us */
 				goto continue_unlock;
 			}
 
-			if (last_page)
-				f2fs_put_page(last_page, 0);
+			if (last_folio)
+				f2fs_folio_put(last_folio, false);
 
-			get_page(page);
-			last_page = page;
-			unlock_page(page);
+			folio_get(folio);
+			last_folio = folio;
+			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
 	}
-	return last_page;
+	return last_folio;
 }
 
 static int __write_node_page(struct page *page, bool atomic, bool *submitted,
···
 		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 
 	/* should add to global list before clearing PAGECACHE status */
-	if (f2fs_in_warm_node_list(sbi, page)) {
+	if (f2fs_in_warm_node_list(sbi, folio)) {
 		seq = f2fs_add_fsync_node_entry(sbi, page);
 		if (seq_id)
 			*seq_id = seq;
···
 	return err;
 }
 
-static int f2fs_write_node_page(struct page *page,
-				struct writeback_control *wbc)
-{
-	return __write_node_page(page, false, NULL, wbc, false,
-						FS_NODE_IO, NULL);
-}
-
 int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			struct writeback_control *wbc, bool atomic,
 			unsigned int *seq_id)
···
 	pgoff_t index;
 	struct folio_batch fbatch;
 	int ret = 0;
-	struct page *last_page = NULL;
+	struct folio *last_folio = NULL;
 	bool marked = false;
 	nid_t ino = inode->i_ino;
 	int nr_folios;
 	int nwritten = 0;
 
 	if (atomic) {
-		last_page = last_fsync_dnode(sbi, ino);
-		if (IS_ERR_OR_NULL(last_page))
-			return PTR_ERR_OR_ZERO(last_page);
+		last_folio = last_fsync_dnode(sbi, ino);
+		if (IS_ERR_OR_NULL(last_folio))
+			return PTR_ERR_OR_ZERO(last_folio);
 	}
 retry:
 	folio_batch_init(&fbatch);
···
 		int i;
 
 		for (i = 0; i < nr_folios; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
 			bool submitted = false;
 
 			if (unlikely(f2fs_cp_error(sbi))) {
-				f2fs_put_page(last_page, 0);
+				f2fs_folio_put(last_folio, false);
 				folio_batch_release(&fbatch);
 				ret = -EIO;
 				goto out;
 			}
 
-			if (!IS_DNODE(page) || !is_cold_node(page))
+			if (!IS_DNODE(&folio->page) || !is_cold_node(&folio->page))
 				continue;
-			if (ino_of_node(page) != ino)
+			if (ino_of_node(&folio->page) != ino)
 				continue;
 
-			lock_page(page);
+			folio_lock(folio);
 
-			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+			if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
 continue_unlock:
-				unlock_page(page);
+				folio_unlock(folio);
 				continue;
 			}
-			if (ino_of_node(page) != ino)
+			if (ino_of_node(&folio->page) != ino)
 				goto continue_unlock;
 
-			if (!PageDirty(page) && page != last_page) {
+			if (!folio_test_dirty(folio) && folio != last_folio) {
 				/* someone wrote it for us */
 				goto continue_unlock;
 			}
 
-			f2fs_wait_on_page_writeback(page, NODE, true, true);
+			f2fs_folio_wait_writeback(folio, NODE, true, true);
 
-			set_fsync_mark(page, 0);
-			set_dentry_mark(page, 0);
+			set_fsync_mark(&folio->page, 0);
+			set_dentry_mark(&folio->page, 0);
 
-			if (!atomic || page == last_page) {
-				set_fsync_mark(page, 1);
+			if (!atomic || folio == last_folio) {
+				set_fsync_mark(&folio->page, 1);
 				percpu_counter_inc(&sbi->rf_node_block_count);
-				if (IS_INODE(page)) {
+				if (IS_INODE(&folio->page)) {
 					if (is_inode_flag_set(inode,
 								FI_DIRTY_INODE))
-						f2fs_update_inode(inode, page);
-					set_dentry_mark(page,
+						f2fs_update_inode(inode, &folio->page);
+					set_dentry_mark(&folio->page,
 						f2fs_need_dentry_mark(sbi, ino));
 				}
 				/* may be written by other thread */
-				if (!PageDirty(page))
-					set_page_dirty(page);
+				if (!folio_test_dirty(folio))
+					folio_mark_dirty(folio);
 			}
 
-			if (!clear_page_dirty_for_io(page))
+			if (!folio_clear_dirty_for_io(folio))
 				goto continue_unlock;
 
-			ret = __write_node_page(page, atomic &&
-						page == last_page,
+			ret = __write_node_page(&folio->page, atomic &&
+						folio == last_folio,
 						&submitted, wbc, true,
 						FS_NODE_IO, seq_id);
 			if (ret) {
-				unlock_page(page);
-				f2fs_put_page(last_page, 0);
+				folio_unlock(folio);
+				f2fs_folio_put(last_folio, false);
 				break;
 			} else if (submitted) {
 				nwritten++;
 			}
 
-			if (page == last_page) {
-				f2fs_put_page(page, 0);
+			if (folio == last_folio) {
+				f2fs_folio_put(folio, false);
 				marked = true;
 				break;
 			}
···
 	}
 	if (!ret && atomic && !marked) {
 		f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx",
-			   ino, page_folio(last_page)->index);
-		lock_page(last_page);
-		f2fs_wait_on_page_writeback(last_page, NODE, true, true);
-		set_page_dirty(last_page);
-		unlock_page(last_page);
+			   ino, last_folio->index);
+		folio_lock(last_folio);
+		f2fs_folio_wait_writeback(last_folio, NODE, true, true);
+		folio_mark_dirty(last_folio);
+		folio_unlock(last_folio);
 		goto retry;
 	}
 out:
···
 	return 1;
 }
 
-static bool flush_dirty_inode(struct page *page)
+static bool flush_dirty_inode(struct folio *folio)
 {
-	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	struct f2fs_sb_info *sbi = F2FS_F_SB(folio);
 	struct inode *inode;
-	nid_t ino = ino_of_node(page);
+	nid_t ino = ino_of_node(&folio->page);
 
 	inode = find_inode_nowait(sbi->sb, ino, f2fs_match_ino, NULL);
 	if (!inode)
 		return false;
 
-	f2fs_update_inode(inode, page);
-	unlock_page(page);
+	f2fs_update_inode(inode, &folio->page);
+	folio_unlock(folio);
 
 	iput(inode);
 	return true;
···
 		int i;
 
 		for (i = 0; i < nr_folios; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
 
-			if (!IS_INODE(page))
+			if (!IS_INODE(&folio->page))
 				continue;
 
-			lock_page(page);
+			folio_lock(folio);
 
-			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
-continue_unlock:
-				unlock_page(page);
-				continue;
-			}
-
-			if (!PageDirty(page)) {
-				/* someone wrote it for us */
-				goto continue_unlock;
-			}
+			if (unlikely(folio->mapping != NODE_MAPPING(sbi)))
+				goto unlock;
+			if (!folio_test_dirty(folio))
+				goto unlock;
 
 			/* flush inline_data, if it's async context. */
-			if (page_private_inline(page)) {
-				clear_page_private_inline(page);
-				unlock_page(page);
-				flush_inline_data(sbi, ino_of_node(page));
+			if (page_private_inline(&folio->page)) {
+				clear_page_private_inline(&folio->page);
+				folio_unlock(folio);
+				flush_inline_data(sbi, ino_of_node(&folio->page));
 				continue;
 			}
-			unlock_page(page);
+unlock:
+			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
···
 		int i;
 
 		for (i = 0; i < nr_folios; i++) {
-			struct page *page = &fbatch.folios[i]->page;
+			struct folio *folio = fbatch.folios[i];
 			bool submitted = false;
 
 			/* give a priority to WB_SYNC threads */
···
 			 * 1. dentry dnodes
 			 * 2. file dnodes
 			 */
-			if (step == 0 && IS_DNODE(page))
+			if (step == 0 && IS_DNODE(&folio->page))
 				continue;
-			if (step == 1 && (!IS_DNODE(page) ||
-						is_cold_node(page)))
+			if (step == 1 && (!IS_DNODE(&folio->page) ||
+						is_cold_node(&folio->page)))
 				continue;
-			if (step == 2 && (!IS_DNODE(page) ||
-						!is_cold_node(page)))
+			if (step == 2 && (!IS_DNODE(&folio->page) ||
+						!is_cold_node(&folio->page)))
 				continue;
 lock_node:
 			if (wbc->sync_mode == WB_SYNC_ALL)
-				lock_page(page);
-			else if (!trylock_page(page))
+				folio_lock(folio);
+			else if (!folio_trylock(folio))
 				continue;
 
-			if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+			if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
 continue_unlock:
-				unlock_page(page);
+				folio_unlock(folio);
 				continue;
 			}
 
-			if (!PageDirty(page)) {
+			if (!folio_test_dirty(folio)) {
 				/* someone wrote it for us */
 				goto continue_unlock;
 			}
···
 				goto write_node;
 
 			/* flush inline_data */
-			if (page_private_inline(page)) {
-				clear_page_private_inline(page);
-				unlock_page(page);
-				flush_inline_data(sbi, ino_of_node(page));
+			if (page_private_inline(&folio->page)) {
+				clear_page_private_inline(&folio->page);
+				folio_unlock(folio);
+				flush_inline_data(sbi, ino_of_node(&folio->page));
 				goto lock_node;
 			}
 
 			/* flush dirty inode */
-			if (IS_INODE(page) && flush_dirty_inode(page))
+			if (IS_INODE(&folio->page) && flush_dirty_inode(folio))
 				goto lock_node;
 write_node:
-			f2fs_wait_on_page_writeback(page, NODE, true, true);
+			f2fs_folio_wait_writeback(folio, NODE, true, true);
 
-			if (!clear_page_dirty_for_io(page))
+			if (!folio_clear_dirty_for_io(folio))
 				goto continue_unlock;
 
-			set_fsync_mark(page, 0);
-			set_dentry_mark(page, 0);
+			set_fsync_mark(&folio->page, 0);
+			set_dentry_mark(&folio->page, 0);
 
-			ret = __write_node_page(page, false, &submitted,
+			ret = __write_node_page(&folio->page, false, &submitted,
 						wbc, do_balance, io_type, NULL);
 			if (ret)
-				unlock_page(page);
+				folio_unlock(folio);
 			else if (submitted)
 				nwritten++;
 
···
  * Structure of the f2fs node operations
  */
 const struct address_space_operations f2fs_node_aops = {
-	.writepage	= f2fs_write_node_page,
 	.writepages	= f2fs_write_node_pages,
 	.dirty_folio	= f2fs_dirty_node_folio,
 	.invalidate_folio = f2fs_invalidate_folio,
···
 	default:
 		BUG_ON(1);
 	}
-}
-
-bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned int i;
-	bool ret = true;
-
-	f2fs_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)) {
-			ret = false;
-			break;
-		}
-	}
-	f2fs_up_read(&nm_i->nat_tree_lock);
-
-	return ret;
 }
 
 static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
···
 	struct page *ipage;
 	struct f2fs_inode *ri;
 
-	ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
···
 	list_add_tail(&nes->set_list, head);
 }
 
-static void __update_nat_bits(struct f2fs_nm_info *nm_i, unsigned int nat_ofs,
-							unsigned int valid)
-{
-	if (valid == 0) {
-		__set_bit_le(nat_ofs, nm_i->empty_nat_bits);
-		__clear_bit_le(nat_ofs, nm_i->full_nat_bits);
-		return;
-	}
-
-	__clear_bit_le(nat_ofs, nm_i->empty_nat_bits);
-	if (valid == NAT_ENTRY_PER_BLOCK)
-		__set_bit_le(nat_ofs, nm_i->full_nat_bits);
-	else
-		__clear_bit_le(nat_ofs, nm_i->full_nat_bits);
-}
-
-static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+static 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);
···
 	int valid = 0;
 	int i = 0;
 
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+	if (!enabled_nat_bits(sbi, NULL))
 		return;
 
 	if (nat_index == 0) {
···
 		if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR)
 			valid++;
 	}
-
-	__update_nat_bits(nm_i, nat_index, valid);
-}
-
-void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned int nat_ofs;
-
-	f2fs_down_read(&nm_i->nat_tree_lock);
-
-	for (nat_ofs = 0; nat_ofs < nm_i->nat_blocks; nat_ofs++) {
-		unsigned int valid = 0, nid_ofs = 0;
-
-		/* handle nid zero due to it should never be used */
-		if (unlikely(nat_ofs == 0)) {
-			valid = 1;
-			nid_ofs = 1;
-		}
-
-		for (; nid_ofs < NAT_ENTRY_PER_BLOCK; nid_ofs++) {
-			if (!test_bit_le(nid_ofs,
-					nm_i->free_nid_bitmap[nat_ofs]))
-				valid++;
-		}
-
-		__update_nat_bits(nm_i, nat_ofs, 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;
 	}
 
-	f2fs_up_read(&nm_i->nat_tree_lock);
+	__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 int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
···
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if ((cpc->reason & CP_UMOUNT) ||
+	if (enabled_nat_bits(sbi, cpc) ||
 		!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
···
 	if (to_journal) {
 		up_write(&curseg->journal_rwsem);
 	} else {
-		update_nat_bits(sbi, start_nid, page);
+		__update_nat_bits(sbi, start_nid, page);
 		f2fs_put_page(page, 1);
 	}
 
···
 	 * during unmount, let's flush nat_bits before checking
 	 * nat_cnt[DIRTY_NAT].
 	 */
-	if (cpc->reason & CP_UMOUNT) {
+	if (enabled_nat_bits(sbi, cpc)) {
 		f2fs_down_write(&nm_i->nat_tree_lock);
 		remove_nats_in_journal(sbi);
 		f2fs_up_write(&nm_i->nat_tree_lock);
···
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (cpc->reason & CP_UMOUNT ||
+	if (enabled_nat_bits(sbi, cpc) ||
 		!__has_cursum_space(journal,
 			nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
···
 	__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_BLK_ALIGN((nat_bits_bytes << 1) + 8);
 	nm_i->nat_bits = f2fs_kvzalloc(sbi,
 			F2FS_BLK_TO_BYTES(nm_i->nat_bits_blocks), GFP_KERNEL);
 	if (!nm_i->nat_bits)
 		return -ENOMEM;
-
-	nm_i->full_nat_bits = nm_i->nat_bits + 8;
-	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
-
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
-		return 0;
 
 	nat_bits_addr = __start_cp_addr(sbi) + BLKS_PER_SEG(sbi) -
 						nm_i->nat_bits_blocks;
···
 
 	cp_ver |= (cur_cp_crc(ckpt) << 32);
 	if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
-		clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
-		f2fs_notice(sbi, "Disable nat_bits due to incorrect cp_ver (%llu, %llu)",
-			cp_ver, le64_to_cpu(*(__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_notice(sbi, "Found nat_bits in checkpoint");
 	return 0;
···
 	unsigned int i = 0;
 	nid_t nid, last_nid;
 
-	if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+	if (!enabled_nat_bits(sbi, NULL))
 		return;
 
 	for (i = 0; i < nm_i->nat_blocks; i++) {
···
 					GFP_KERNEL);
 	if (!nm_i->nat_bitmap)
 		return -ENOMEM;
+
+	if (!test_opt(sbi, NAT_BITS))
+		disable_nat_bits(sbi, true);
 
 	err = __get_nat_bitmaps(sbi);
 	if (err)

fs/f2fs/node.h

···
 	IS_PREALLOC,		/* nat entry is preallocated */
 };
 
+/* For node type in __get_node_folio() */
+enum node_type {
+	NODE_TYPE_REGULAR,
+	NODE_TYPE_INODE,
+	NODE_TYPE_XATTR,
+};
+
 /*
  * For node information
  */
···
 	return le32_to_cpu(rn->footer.nid);
 }
 
-static inline unsigned int ofs_of_node(struct page *node_page)
+static inline unsigned int ofs_of_node(const struct page *node_page)
 {
 	struct f2fs_node *rn = F2FS_NODE(node_page);
 	unsigned flag = le32_to_cpu(rn->footer.flag);
···
  *                 `- indirect node ((6 + 2N) + (N - 1)(N + 1))
  *                       `- direct node
  */
-static inline bool IS_DNODE(struct page *node_page)
+static inline bool IS_DNODE(const struct page *node_page)
 {
 	unsigned int ofs = ofs_of_node(node_page);
 
···
  *  - Mark cold data pages in page cache
  */
 
-static inline int is_node(struct page *page, int type)
+static inline int is_node(const struct page *page, int type)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
 	return le32_to_cpu(rn->footer.flag) & BIT(type);

fs/f2fs/segment.c

···
 		return false;
 
 	if (!force) {
-		if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
+		if (!f2fs_realtime_discard_enable(sbi) ||
+			(!se->valid_blocks &&
+				!IS_CURSEG(sbi, cpc->trim_start)) ||
 			SM_I(sbi)->dcc_info->nr_discards >=
 				SM_I(sbi)->dcc_info->max_discards)
 			return false;
···
 	dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
 	dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY;
 	dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE;
-	if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT)
+	if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT ||
+		F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
 		dcc->discard_granularity = BLKS_PER_SEG(sbi);
-	else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
-		dcc->discard_granularity = BLKS_PER_SEC(sbi);
 
 	INIT_LIST_HEAD(&dcc->entry_list);
 	for (i = 0; i < MAX_PLIST_NUM; i++)
···
 							MAIN_SECS(sbi));
 		if (secno >= MAIN_SECS(sbi)) {
 			ret = -ENOSPC;
-			f2fs_bug_on(sbi, 1);
+			f2fs_bug_on(sbi, !pinning);
 			goto out_unlock;
 		}
 	}
···
 out_unlock:
 	spin_unlock(&free_i->segmap_lock);
 
-	if (ret == -ENOSPC)
+	if (ret == -ENOSPC && !pinning)
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
 	return ret;
 }
···
 	return curseg->segno;
 }
 
+static void reset_curseg_fields(struct curseg_info *curseg)
+{
+	curseg->inited = false;
+	curseg->segno = NULL_SEGNO;
+	curseg->next_segno = 0;
+}
+
 /*
  * Allocate a current working segment.
  * This function always allocates a free segment in LFS manner.
···
 	ret = get_new_segment(sbi, &segno, new_sec, pinning);
 	if (ret) {
 		if (ret == -ENOSPC)
-			curseg->segno = NULL_SEGNO;
+			reset_curseg_fields(curseg);
 		return ret;
 	}
 
···
 		get_random_u32_inclusive(1, sbi->max_fragment_hole);
 }
 
-static void reset_curseg_fields(struct curseg_info *curseg)
-{
-	curseg->inited = false;
-	curseg->segno = NULL_SEGNO;
-	curseg->next_segno = 0;
-}
-
 int f2fs_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,
···
 
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
+	struct folio *folio = page_folio(fio->page);
 	enum log_type type = __get_segment_type(fio);
 	int seg_type = log_type_to_seg_type(type);
 	bool keep_order = (f2fs_lfs_mode(fio->sbi) &&
···
 
 	if (f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 			&fio->new_blkaddr, sum, type, fio)) {
-		if (fscrypt_inode_uses_fs_layer_crypto(fio->page->mapping->host))
+		if (fscrypt_inode_uses_fs_layer_crypto(folio->mapping->host))
 			fscrypt_finalize_bounce_page(&fio->encrypted_page);
-		end_page_writeback(fio->page);
-		if (f2fs_in_warm_node_list(fio->sbi, fio->page))
+		folio_end_writeback(folio);
+		if (f2fs_in_warm_node_list(fio->sbi, folio))
 			f2fs_del_fsync_node_entry(fio->sbi, fio->page);
 		goto out;
 	}
···
 	f2fs_update_data_blkaddr(dn, new_addr);
 }
 
-void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type, bool ordered, bool locked)
+void f2fs_folio_wait_writeback(struct folio *folio, enum page_type type,
+		bool ordered, bool locked)
 {
-	if (folio_test_writeback(page_folio(page))) {
-		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	if (folio_test_writeback(folio)) {
+		struct f2fs_sb_info *sbi = F2FS_F_SB(folio);
 
 		/* submit cached LFS IO */
-		f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+		f2fs_submit_merged_write_cond(sbi, NULL, &folio->page, 0, type);
 		/* submit cached IPU IO */
-		f2fs_submit_merged_ipu_write(sbi, NULL, page);
+		f2fs_submit_merged_ipu_write(sbi, NULL, &folio->page);
 		if (ordered) {
-			wait_on_page_writeback(page);
-			f2fs_bug_on(sbi, locked &&
-				folio_test_writeback(page_folio(page)));
+			folio_wait_writeback(folio);
+			f2fs_bug_on(sbi, locked && folio_test_writeback(folio));
 		} else {
-			wait_for_stable_page(page);
+			folio_wait_stable(folio);
 		}
 	}
 }

fs/f2fs/segment.h

···
 			unsigned int node_blocks, unsigned int data_blocks,
 			unsigned int dent_blocks)
 {
-
 	unsigned int segno, left_blocks, blocks;
 	int i;
 
 	/* check current data/node sections in the worst case. */
 	for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) {
 		segno = CURSEG_I(sbi, i)->segno;
+
+		if (unlikely(segno == NULL_SEGNO))
+			return false;
+
 		left_blocks = CAP_BLKS_PER_SEC(sbi) -
 				get_ckpt_valid_blocks(sbi, segno, true);
 
···
 
 	/* check current data section for dentry blocks. */
 	segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
+
+	if (unlikely(segno == NULL_SEGNO))
+		return false;
+
 	left_blocks = CAP_BLKS_PER_SEC(sbi) -
 			get_ckpt_valid_blocks(sbi, segno, true);
 	if (dent_blocks > left_blocks)

fs/f2fs/shrinker.c

···
 		mutex_unlock(&sbi->umount_mutex);
 	}
 	spin_unlock(&f2fs_list_lock);
-	return count;
+	return count ?: SHRINK_EMPTY;
 }
 
 unsigned long f2fs_shrink_scan(struct shrinker *shrink,
···
 	}
 	spin_unlock(&f2fs_list_lock);
 	return freed;
+}
+
+unsigned int f2fs_donate_files(void)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned int donate_files = 0;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		donate_files += sbi->donate_files;
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
+
+	return donate_files;
+}
+
+static unsigned int do_reclaim_caches(struct f2fs_sb_info *sbi,
+				unsigned int reclaim_caches_kb)
+{
+	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	unsigned int nfiles = sbi->donate_files;
+	pgoff_t npages = reclaim_caches_kb >> (PAGE_SHIFT - 10);
+
+	while (npages && nfiles--) {
+		pgoff_t len;
+
+		spin_lock(&sbi->inode_lock[DONATE_INODE]);
+		if (list_empty(&sbi->inode_list[DONATE_INODE])) {
+			spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+			break;
+		}
+		fi = list_first_entry(&sbi->inode_list[DONATE_INODE],
+					struct f2fs_inode_info, gdonate_list);
+		list_move_tail(&fi->gdonate_list, &sbi->inode_list[DONATE_INODE]);
+		inode = igrab(&fi->vfs_inode);
+		spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+
+		if (!inode)
+			continue;
+
+		len = fi->donate_end - fi->donate_start + 1;
+		npages = npages < len ? 0 : npages - len;
+		invalidate_inode_pages2_range(inode->i_mapping,
+					fi->donate_start, fi->donate_end);
+		iput(inode);
+		cond_resched();
+	}
+	return npages << (PAGE_SHIFT - 10);
+}
+
+void f2fs_reclaim_caches(unsigned int reclaim_caches_kb)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list && reclaim_caches_kb) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		reclaim_caches_kb = do_reclaim_caches(sbi, reclaim_caches_kb);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
 }
 
 void f2fs_join_shrinker(struct f2fs_sb_info *sbi)

fs/f2fs/super.c

···
 	[FAULT_BLKADDR_VALIDITY]	= "invalid blkaddr",
 	[FAULT_BLKADDR_CONSISTENCE]	= "inconsistent blkaddr",
 	[FAULT_NO_SEGMENT]		= "no free segment",
+	[FAULT_INCONSISTENT_FOOTER]	= "inconsistent footer",
 };
 
 int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
···
 	Opt_memory_mode,
 	Opt_age_extent_cache,
 	Opt_errors,
+	Opt_nat_bits,
 	Opt_err,
 };
 
···
 	{Opt_memory_mode, "memory=%s"},
 	{Opt_age_extent_cache, "age_extent_cache"},
 	{Opt_errors, "errors=%s"},
+	{Opt_nat_bits, "nat_bits"},
 	{Opt_err, NULL},
 };
 
···
 #ifdef CONFIG_QUOTA
 static const char * const quotatypes[] = INITQFNAMES;
 #define QTYPE2NAME(t) (quotatypes[t])
-static int f2fs_set_qf_name(struct super_block *sb, int qtype,
+static int f2fs_set_qf_name(struct f2fs_sb_info *sbi, int qtype,
 							substring_t *args)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct super_block *sb = sbi->sb;
 	char *qname;
 	int ret = -EINVAL;
 
···
 	return ret;
 }
 
-static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
+static int f2fs_clear_qf_name(struct f2fs_sb_info *sbi, int qtype)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	struct super_block *sb = sbi->sb;
 
 	if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) {
 		f2fs_err(sbi, "Cannot change journaled quota options when quota turned on");
···
 }
 #endif
 
-static int f2fs_set_test_dummy_encryption(struct super_block *sb,
+static int f2fs_set_test_dummy_encryption(struct f2fs_sb_info *sbi,
 					  const char *opt,
 					  const substring_t *arg,
 					  bool is_remount)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct fs_parameter param = {
 		.type = fs_value_is_string,
 		.string = arg->from ? arg->from : "",
···
 #endif
 #endif
 
-static int parse_options(struct super_block *sb, char *options, bool is_remount)
+static int parse_options(struct f2fs_sb_info *sbi, char *options, bool is_remount)
 {
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	unsigned char (*ext)[F2FS_EXTENSION_LEN];
···
 	int ret;
 
 	if (!options)
-		goto default_check;
+		return 0;
 
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
···
 			set_opt(sbi, DISABLE_ROLL_FORWARD);
 			break;
 		case Opt_norecovery:
-			/* this option mounts f2fs with ro */
+			/* requires ro mount, checked in f2fs_default_check */
 			set_opt(sbi, NORECOVERY);
-			if (!f2fs_readonly(sb))
-				return -EINVAL;
 			break;
 		case Opt_discard:
 			if (!f2fs_hw_support_discard(sbi)) {
···
 			break;
 #else
 		case Opt_user_xattr:
-			f2fs_info(sbi, "user_xattr options not supported");
-			break;
 		case Opt_nouser_xattr:
-			f2fs_info(sbi, "nouser_xattr options not supported");
-			break;
 		case Opt_inline_xattr:
-			f2fs_info(sbi, "inline_xattr options not supported");
-			break;
 		case Opt_noinline_xattr:
-			f2fs_info(sbi, "noinline_xattr options not supported");
+		case Opt_inline_xattr_size:
+			f2fs_info(sbi, "xattr options not supported");
 			break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
···
 			break;
 #else
 		case Opt_acl:
-			f2fs_info(sbi, "acl options not supported");
-			break;
 		case Opt_noacl:
-			f2fs_info(sbi, "noacl options not supported");
+			f2fs_info(sbi, "acl options not supported");
 			break;
 #endif
 		case Opt_active_logs:
···
 			set_opt(sbi, READ_EXTENT_CACHE);
 			break;
 		case Opt_noextent_cache:
-			if (F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_DEVICE_ALIAS)) {
+			if (f2fs_sb_has_device_alias(sbi)) {
 				f2fs_err(sbi, "device aliasing requires extent cache");
 				return -EINVAL;
 			}
···
 			break;
 #else
 		case Opt_fault_injection:
-			f2fs_info(sbi, "fault_injection options not supported");
-			break;
-
 		case Opt_fault_type:
-			f2fs_info(sbi, "fault_type options not supported");
+			f2fs_info(sbi, "fault injection options not supported");
 			break;
 #endif
 		case Opt_lazytime:
-			sb->s_flags |= SB_LAZYTIME;
+			set_opt(sbi, LAZYTIME);
 			break;
 		case Opt_nolazytime:
-			sb->s_flags &= ~SB_LAZYTIME;
+			clear_opt(sbi, LAZYTIME);
 			break;
 #ifdef CONFIG_QUOTA
 		case Opt_quota:
···
 			set_opt(sbi, PRJQUOTA);
 			break;
 		case Opt_usrjquota:
-			ret = f2fs_set_qf_name(sb, USRQUOTA, &args[0]);
+			ret = f2fs_set_qf_name(sbi, USRQUOTA, &args[0]);
 			if (ret)
 				return ret;
 			break;
 		case Opt_grpjquota:
-			ret = f2fs_set_qf_name(sb, GRPQUOTA, &args[0]);
+			ret = f2fs_set_qf_name(sbi, GRPQUOTA, &args[0]);
 			if (ret)
 				return ret;
 			break;
 		case Opt_prjjquota:
-			ret = f2fs_set_qf_name(sb, PRJQUOTA, &args[0]);
+			ret = f2fs_set_qf_name(sbi, PRJQUOTA, &args[0]);
 			if (ret)
 				return ret;
 			break;
 		case Opt_offusrjquota:
-			ret = f2fs_clear_qf_name(sb, USRQUOTA);
+			ret = f2fs_clear_qf_name(sbi, USRQUOTA);
 			if (ret)
 				return ret;
 			break;
 		case Opt_offgrpjquota:
-			ret = f2fs_clear_qf_name(sb, GRPQUOTA);
+			ret = f2fs_clear_qf_name(sbi, GRPQUOTA);
 			if (ret)
 				return ret;
 			break;
 		case Opt_offprjjquota:
-			ret = f2fs_clear_qf_name(sb, PRJQUOTA);
+			ret = f2fs_clear_qf_name(sbi, PRJQUOTA);
 			if (ret)
 				return ret;
 			break;
···
 			kfree(name);
 			break;
 		case Opt_test_dummy_encryption:
-			ret = f2fs_set_test_dummy_encryption(sb, p, &args[0],
+			ret = f2fs_set_test_dummy_encryption(sbi, p, &args[0],
 							     is_remount);
 			if (ret)
 				return ret;
 			break;
 		case Opt_inlinecrypt:
 #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
-			sb->s_flags |= SB_INLINECRYPT;
+			set_opt(sbi, INLINECRYPT);
 #else
 			f2fs_info(sbi, "inline encryption not supported");
 #endif
···
 			}
 			kfree(name);
 			break;
+		case Opt_nat_bits:
+			set_opt(sbi, NAT_BITS);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
 			return -EINVAL;
 		}
 	}
-default_check:
+	return 0;
+}
+
+static int f2fs_default_check(struct f2fs_sb_info *sbi)
+{
 #ifdef CONFIG_QUOTA
 	if (f2fs_check_quota_options(sbi))
 		return -EINVAL;
···
 		f2fs_err(sbi, "Allow to mount readonly mode only");
 		return -EROFS;
 	}
+
+	if (test_opt(sbi, NORECOVERY) && !f2fs_readonly(sbi->sb)) {
+		f2fs_err(sbi, "norecovery requires readonly mount");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
···
 	spin_lock_init(&fi->i_size_lock);
 	INIT_LIST_HEAD(&fi->dirty_list);
 	INIT_LIST_HEAD(&fi->gdirty_list);
+	INIT_LIST_HEAD(&fi->gdonate_list);
 	init_f2fs_rwsem(&fi->i_gc_rwsem[READ]);
 	init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]);
 	init_f2fs_rwsem(&fi->i_xattr_sem);
···
 		inc_page_count(sbi, F2FS_DIRTY_IMETA);
 	}
 	spin_unlock(&sbi->inode_lock[DIRTY_META]);
+
+	if (!ret && f2fs_is_atomic_file(inode))
+		set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+
 	return ret;
 }
 
···
 
 static int f2fs_freeze(struct super_block *sb)
 {
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
 	if (f2fs_readonly(sb))
 		return 0;
 
 	/* IO error happened before */
-	if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
 	/* must be clean, since sync_filesystem() was already called */
-	if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+	if (is_sbi_flag_set(sbi, SBI_IS_DIRTY))
 		return -EINVAL;
 
+	sbi->umount_lock_holder = current;
+
 	/* Let's flush checkpoints and stop the thread. */
-	f2fs_flush_ckpt_thread(F2FS_SB(sb));
+	f2fs_flush_ckpt_thread(sbi);
+
+	sbi->umount_lock_holder = NULL;
 
 	/* to avoid deadlock on f2fs_evict_inode->SB_FREEZE_FS */
-	set_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
+	set_sbi_flag(sbi, SBI_IS_FREEZING);
 	return 0;
 }
 
···
 	buf->f_blocks = total_count - start_count;
 
 	spin_lock(&sbi->stat_lock);
-
+	if (sbi->carve_out)
+		buf->f_blocks -= sbi->current_reserved_blocks;
 	user_block_count = sbi->user_block_count;
 	total_valid_node_count = valid_node_count(sbi);
 	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
···
 	else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC)
 		seq_printf(seq, ",errors=%s", "panic");
 
+	if (test_opt(sbi, NAT_BITS))
+		seq_puts(seq, ",nat_bits");
+
 	return 0;
 }
 
···
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
 	set_opt(sbi, MERGE_CHECKPOINT);
+	set_opt(sbi, LAZYTIME);
 	F2FS_OPTION(sbi).unusable_cap = 0;
-	sbi->sb->s_flags |= SB_LAZYTIME;
 	if (!f2fs_is_readonly(sbi))
 		set_opt(sbi, FLUSH_MERGE);
 	if (f2fs_sb_has_blkzoned(sbi))
···
 	bool no_discard = !test_opt(sbi, DISCARD);
 	bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
 	bool block_unit_discard = f2fs_block_unit_discard(sbi);
+	bool no_nat_bits = !test_opt(sbi, NAT_BITS);
 #ifdef CONFIG_QUOTA
 	int i, j;
 #endif
···
 	 */
 	org_mount_opt = sbi->mount_opt;
 	old_sb_flags = sb->s_flags;
+
+	sbi->umount_lock_holder = current;
 
 #ifdef CONFIG_QUOTA
 	org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt;
···
 	default_options(sbi, true);
 
 	/* parse mount options */
-	err = parse_options(sb, data, true);
+	err = parse_options(sbi, data, true);
 	if (err)
 		goto restore_opts;
 
···
 		goto restore_opts;
 	}
 #endif
+
+	err = f2fs_default_check(sbi);
+	if (err)
+		goto restore_opts;
 
 	/* flush outstanding errors before changing fs state */
 	flush_work(&sbi->s_error_work);
···
 	if (block_unit_discard != f2fs_block_unit_discard(sbi)) {
 		err = -EINVAL;
 		f2fs_warn(sbi, "switch discard_unit option is not allowed");
+		goto restore_opts;
+	}
+
+	if (no_nat_bits == !!test_opt(sbi, NAT_BITS)) {
+		err = -EINVAL;
+		f2fs_warn(sbi, "switch nat_bits option is not allowed");
 		goto restore_opts;
 	}
 
···
 
 	limit_reserve_root(sbi);
 	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
+
+	sbi->umount_lock_holder = NULL;
 	return 0;
 restore_checkpoint:
 	if (need_enable_checkpoint) {
···
 #endif
 	sbi->mount_opt = org_mount_opt;
 	sb->s_flags = old_sb_flags;
+
+	sbi->umount_lock_holder = NULL;
 	return err;
 }
 
···
 	return ret;
 }
 
-int f2fs_quota_sync(struct super_block *sb, int type)
+int f2fs_do_quota_sync(struct super_block *sb, int type)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct quota_info *dqopt = sb_dqopt(sb);
···
 	return ret;
 }
 
+static int f2fs_quota_sync(struct super_block *sb, int type)
+{
+	int ret;
+
+	F2FS_SB(sb)->umount_lock_holder = current;
+	ret = f2fs_do_quota_sync(sb, type);
+	F2FS_SB(sb)->umount_lock_holder = NULL;
+	return ret;
+}
+
 static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
 							const struct path *path)
 {
 	struct inode *inode;
-	int err;
+	int err = 0;
 
 	/* if quota sysfile exists, deny enabling quota with specific file */
 	if (f2fs_sb_has_quota_ino(F2FS_SB(sb))) {
···
 	if (path->dentry->d_sb != sb)
 		return -EXDEV;
 
-	err = f2fs_quota_sync(sb, type);
+	F2FS_SB(sb)->umount_lock_holder = current;
+
+	err = f2fs_do_quota_sync(sb, type);
 	if (err)
-		return err;
+		goto out;
 
 	inode = d_inode(path->dentry);
 
 	err = filemap_fdatawrite(inode->i_mapping);
 	if (err)
-		return err;
+		goto out;
 
 	err = filemap_fdatawait(inode->i_mapping);
 	if (err)
-		return err;
+		goto out;
 
 	err = dquot_quota_on(sb, type, format_id, path);
 	if (err)
-		return err;
+		goto out;
 
 	inode_lock(inode);
 	F2FS_I(inode)->i_flags |= F2FS_QUOTA_DEFAULT_FL;
 	f2fs_set_inode_flags(inode);
 	inode_unlock(inode);
 	f2fs_mark_inode_dirty_sync(inode, false);
-
-	return 0;
+out:
+	F2FS_SB(sb)->umount_lock_holder = NULL;
+	return err;
 }
 
 static int __f2fs_quota_off(struct super_block *sb, int type)
···
 	if (!inode || !igrab(inode))
 		return dquot_quota_off(sb, type);
 
-	err = f2fs_quota_sync(sb, type);
+	err = f2fs_do_quota_sync(sb, type);
 	if (err)
 		goto out_put;
 
···
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	int err;
 
+	F2FS_SB(sb)->umount_lock_holder = current;
+
 	err = __f2fs_quota_off(sb, type);
 
 	/*
···
 	 */
 	if (is_journalled_quota(sbi))
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+
+	F2FS_SB(sb)->umount_lock_holder = NULL;
+
 	return err;
 }
 
···
 	return 0;
 }
 
-int f2fs_quota_sync(struct super_block *sb, int type)
+int f2fs_do_quota_sync(struct super_block *sb, int type)
 {
 	return 0;
 }
···
 
 	if (shutdown)
 		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+	else
+		dump_stack();
 
 	/*
 	 * Continue filesystem operators if errors=continue. Should not set
···
 		goto free_sb_buf;
 	}
 
-	err = parse_options(sb, options, false);
+	err = parse_options(sbi, options, false);
+	if (err)
+		goto free_options;
+
+	err = f2fs_default_check(sbi);
 	if (err)
 		goto free_options;
 
···
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
+	if (test_opt(sbi, INLINECRYPT))
+		sb->s_flags |= SB_INLINECRYPT;
+
+	if (test_opt(sbi, LAZYTIME))
+		sb->s_flags |= SB_LAZYTIME;
+	else
+		sb->s_flags &= ~SB_LAZYTIME;
+
 	super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
 	super_set_sysfs_name_bdev(sb);
 	sb->s_iflags |= SB_I_CGROUPWB;
···
 	if (err)
 		goto free_compress_inode;
 
+	sbi->umount_lock_holder = current;
 #ifdef CONFIG_QUOTA
 	/* Enable quota usage during mount */
 	if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) {
···
 	if (err)
 		goto free_meta;
 
-	if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)))
+	if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) {
+		skip_recovery = true;
 		goto reset_checkpoint;
+	}
 
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD) &&
···
 		}
 	}
 
+reset_checkpoint:
 #ifdef CONFIG_QUOTA
 	f2fs_recover_quota_end(sbi, quota_enabled);
 #endif
-reset_checkpoint:
 	/*
 	 * If the f2fs is not readonly and fsync data recovery succeeds,
 	 * write pointer consistency of cursegs and other zones are already
···
 	f2fs_update_time(sbi, CP_TIME);
 	f2fs_update_time(sbi, REQ_TIME);
 	clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
+
+	sbi->umount_lock_holder = NULL;
 	return 0;
 
 sync_free_meta:
···
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (sb->s_root) {
+		sbi->umount_lock_holder = current;
+
 		set_sbi_flag(sbi, SBI_IS_CLOSE);
 		f2fs_stop_gc_thread(sbi);
 		f2fs_stop_discard_thread(sbi);

fs/f2fs/sysfs.c

···
 	int id;
 };
 
+struct f2fs_base_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct f2fs_base_attr *a, char *buf);
+	ssize_t (*store)(struct f2fs_base_attr *a, const char *buf, size_t len);
+};
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			     struct f2fs_sb_info *sbi, char *buf);
 
···
 	complete(&sbi->s_kobj_unregister);
 }
 
+static ssize_t f2fs_base_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct f2fs_base_attr *a = container_of(attr,
+				struct f2fs_base_attr, attr);
+
+	return a->show ? a->show(a, buf) : 0;
+}
+
+static ssize_t f2fs_base_attr_store(struct kobject *kobj,
+				struct attribute *attr,
+				const char *buf, size_t len)
+{
+	struct f2fs_base_attr *a = container_of(attr,
+				struct f2fs_base_attr, attr);
+
+	return a->store ? a->store(a, buf, len) : 0;
+}
+
 /*
  * Note that there are three feature list entries:
  * 1) /sys/fs/f2fs/features
···
  *     please add new on-disk feature in this list only.
  *     - ref. F2FS_SB_FEATURE_RO_ATTR()
  */
-static ssize_t f2fs_feature_show(struct f2fs_attr *a,
-		struct f2fs_sb_info *sbi, char *buf)
+static ssize_t f2fs_feature_show(struct f2fs_base_attr *a, char *buf)
 {
 	return sysfs_emit(buf, "supported\n");
 }
 
 #define F2FS_FEATURE_RO_ATTR(_name)				\
-static struct f2fs_attr f2fs_attr_##_name = {			\
+static struct f2fs_base_attr f2fs_base_attr_##_name = {		\
 	.attr = {.name = __stringify(_name), .mode = 0444 },	\
 	.show	= f2fs_feature_show,				\
+}
+
+static ssize_t f2fs_tune_show(struct f2fs_base_attr *a, char *buf)
+{
+	unsigned int res = 0;
+
+	if (!strcmp(a->attr.name, "reclaim_caches_kb"))
+		res = f2fs_donate_files();
+
+	return sysfs_emit(buf, "%u\n", res);
+}
+
+static ssize_t f2fs_tune_store(struct f2fs_base_attr *a,
+			const char *buf, size_t count)
+{
+	unsigned long t;
+	int ret;
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret)
+		return ret;
+
+	if (!strcmp(a->attr.name, "reclaim_caches_kb"))
+		f2fs_reclaim_caches(t);
+
+	return count;
+}
+
+#define F2FS_TUNE_RW_ATTR(_name)				\
+static struct f2fs_base_attr f2fs_base_attr_##_name = {		\
+	.attr = {.name = __stringify(_name), .mode = 0644 },	\
+	.show	= f2fs_tune_show,				\
+	.store	= f2fs_tune_store,				\
 }
 
 static ssize_t f2fs_sb_feature_show(struct f2fs_attr *a,
···
 F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
 F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
 #endif
+F2FS_SBI_GENERAL_RW_ATTR(carve_out);
 
 /* STAT_INFO ATTR */
 #ifdef CONFIG_F2FS_STAT_FS
···
 	ATTR_LIST(warm_data_age_threshold),
 	ATTR_LIST(last_age_weight),
 	ATTR_LIST(max_read_extent_count),
+	ATTR_LIST(carve_out),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);
 
+#define BASE_ATTR_LIST(name) (&f2fs_base_attr_##name.attr)
 static struct attribute *f2fs_feat_attrs[] = {
 #ifdef CONFIG_FS_ENCRYPTION
-	ATTR_LIST(encryption),
-	ATTR_LIST(test_dummy_encryption_v2),
+	BASE_ATTR_LIST(encryption),
+	BASE_ATTR_LIST(test_dummy_encryption_v2),
 #if IS_ENABLED(CONFIG_UNICODE)
-	ATTR_LIST(encrypted_casefold),
+	BASE_ATTR_LIST(encrypted_casefold),
 #endif
 #endif /* CONFIG_FS_ENCRYPTION */
 #ifdef CONFIG_BLK_DEV_ZONED
-	ATTR_LIST(block_zoned),
+	BASE_ATTR_LIST(block_zoned),
 #endif
-	ATTR_LIST(atomic_write),
-	ATTR_LIST(extra_attr),
-	ATTR_LIST(project_quota),
-	ATTR_LIST(inode_checksum),
-	ATTR_LIST(flexible_inline_xattr),
-	ATTR_LIST(quota_ino),
-	ATTR_LIST(inode_crtime),
-	ATTR_LIST(lost_found),
+	BASE_ATTR_LIST(atomic_write),
+	BASE_ATTR_LIST(extra_attr),
+	BASE_ATTR_LIST(project_quota),
+	BASE_ATTR_LIST(inode_checksum),
+	BASE_ATTR_LIST(flexible_inline_xattr),
+	BASE_ATTR_LIST(quota_ino),
+	BASE_ATTR_LIST(inode_crtime),
+	BASE_ATTR_LIST(lost_found),
 #ifdef CONFIG_FS_VERITY
-	ATTR_LIST(verity),
+	BASE_ATTR_LIST(verity),
 #endif
-	ATTR_LIST(sb_checksum),
+	BASE_ATTR_LIST(sb_checksum),
 #if IS_ENABLED(CONFIG_UNICODE)
-	ATTR_LIST(casefold),
+	BASE_ATTR_LIST(casefold),
 #endif
-	ATTR_LIST(readonly),
+	BASE_ATTR_LIST(readonly),
 #ifdef CONFIG_F2FS_FS_COMPRESSION
-	ATTR_LIST(compression),
+	BASE_ATTR_LIST(compression),
 #endif
-	ATTR_LIST(pin_file),
+	BASE_ATTR_LIST(pin_file),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs_feat);
···
 };
 ATTRIBUTE_GROUPS(f2fs_sb_feat);
 
+F2FS_TUNE_RW_ATTR(reclaim_caches_kb);
+
+static struct attribute *f2fs_tune_attrs[] = {
+	BASE_ATTR_LIST(reclaim_caches_kb),
+	NULL,
+};
+ATTRIBUTE_GROUPS(f2fs_tune);
+
 static const struct sysfs_ops f2fs_attr_ops = {
 	.show	= f2fs_attr_show,
 	.store	= f2fs_attr_store,
···
 	.kobj	= {.ktype = &f2fs_ktype},
 };
 
+static const struct sysfs_ops f2fs_feat_attr_ops = {
+	.show	= f2fs_base_attr_show,
+	.store	= f2fs_base_attr_store,
+};
+
 static const struct kobj_type f2fs_feat_ktype = {
 	.default_groups = f2fs_feat_groups,
-	.sysfs_ops	= &f2fs_attr_ops,
+	.sysfs_ops	= &f2fs_feat_attr_ops,
 };
 
 static struct kobject f2fs_feat = {
+	.kset	= &f2fs_kset,
+};
+
+static const struct sysfs_ops f2fs_tune_attr_ops = {
+	.show	= f2fs_base_attr_show,
+	.store	= f2fs_base_attr_store,
+};
+
+static const struct kobj_type f2fs_tune_ktype = {
+	.default_groups = f2fs_tune_groups,
+	.sysfs_ops	= &f2fs_tune_attr_ops,
+};
+
+static struct kobject f2fs_tune = {
 	.kset	= &f2fs_kset,
 };
 
···
 	if (ret)
 		goto put_kobject;
 
+	ret = kobject_init_and_add(&f2fs_tune, &f2fs_tune_ktype,
+				   NULL, "tuning");
+	if (ret)
+		goto put_kobject;
+
 	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
 	if (!f2fs_proc_root) {
 		ret = -ENOMEM;
···
 	}
 
 	return 0;
+
 put_kobject:
+	kobject_put(&f2fs_tune);
 	kobject_put(&f2fs_feat);
 	kset_unregister(&f2fs_kset);
 	return ret;
···
 
 void f2fs_exit_sysfs(void)
 {
+	kobject_put(&f2fs_tune);
 	kobject_put(&f2fs_feat);
 	kset_unregister(&f2fs_kset);
 	remove_proc_entry("fs/f2fs", NULL);

fs/f2fs/xattr.c

···
 	if (ipage) {
 		inline_addr = inline_xattr_addr(inode, ipage);
 	} else {
-		page = f2fs_get_node_page(sbi, inode->i_ino);
+		page = f2fs_get_inode_page(sbi, inode->i_ino);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
···
 	void *xattr_addr;
 
 	/* The inode already has an extended attribute block. */
-	xpage = f2fs_get_node_page(sbi, xnid);
+	xpage = f2fs_get_xnode_page(sbi, xnid);
 	if (IS_ERR(xpage))
 		return PTR_ERR(xpage);
 
···
 		if (ipage) {
 			inline_addr = inline_xattr_addr(inode, ipage);
 		} else {
-			in_page = f2fs_get_node_page(sbi, inode->i_ino);
+			in_page = f2fs_get_inode_page(sbi, inode->i_ino);
 			if (IS_ERR(in_page)) {
 				f2fs_alloc_nid_failed(sbi, new_nid);
 				return PTR_ERR(in_page);
···
 
 	/* write to xattr node block */
 	if (F2FS_I(inode)->i_xattr_nid) {
-		xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+		xpage = f2fs_get_xnode_page(sbi, F2FS_I(inode)->i_xattr_nid);
 		if (IS_ERR(xpage)) {
 			err = PTR_ERR(xpage);
 			f2fs_alloc_nid_failed(sbi, new_nid);

include/linux/pagemap.h

···
 unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch);
 
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
-			pgoff_t index);
-
 /*
  * Returns locked page at given index in given cache, creating it if needed.
  */
···
 	return folio_wait_bit_killable(folio, PG_locked);
 }
 
-static inline void wait_on_page_locked(struct page *page)
-{
-	folio_wait_locked(page_folio(page));
-}
-
 void folio_end_read(struct folio *folio, bool success);
 void wait_on_page_writeback(struct page *page);
 void folio_wait_writeback(struct folio *folio);
 int folio_wait_writeback_killable(struct folio *folio);
 void end_page_writeback(struct page *page);
 void folio_end_writeback(struct folio *folio);
-void wait_for_stable_page(struct page *page);
 void folio_wait_stable(struct folio *folio);
 void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
 void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb);

include/uapi/linux/f2fs.h

···
 #define F2FS_IOC_COMPRESS_FILE		_IO(F2FS_IOCTL_MAGIC, 24)
 #define F2FS_IOC_START_ATOMIC_REPLACE	_IO(F2FS_IOCTL_MAGIC, 25)
 #define F2FS_IOC_GET_DEV_ALIAS_FILE	_IOR(F2FS_IOCTL_MAGIC, 26, __u32)
+#define F2FS_IOC_IO_PRIO		_IOW(F2FS_IOCTL_MAGIC, 27, __u32)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.
···
 #define F2FS_TRIM_FILE_DISCARD		0x1	/* send discard command */
 #define F2FS_TRIM_FILE_ZEROOUT		0x2	/* zero out */
 #define F2FS_TRIM_FILE_MASK		0x3
+
+/* for F2FS_IOC_IO_PRIO */
+enum {
+	F2FS_IOPRIO_WRITE = 1,	/* high write priority */
+	F2FS_IOPRIO_MAX,
+};
 
 struct f2fs_gc_range {
 	__u32 sync;

mm/filemap.c

···
  * @ptl: already locked ptl. This function will drop the lock.
  *
  * Wait for a migration entry referencing the given page to be removed. This is
- * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
+ * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except
  * this can be called without taking a reference on the page. Instead this
  * should be called while holding the ptl for the migration entry referencing
  * the page.

mm/folio-compat.c

···
 }
 EXPORT_SYMBOL_GPL(wait_on_page_writeback);
 
-void wait_for_stable_page(struct page *page)
-{
-	return folio_wait_stable(page_folio(page));
-}
-EXPORT_SYMBOL_GPL(wait_for_stable_page);
-
 void mark_page_accessed(struct page *page)
 {
 	folio_mark_accessed(page_folio(page));
···
 	return folio_file_page(folio, index);
 }
 EXPORT_SYMBOL(pagecache_get_page);
-
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
-					pgoff_t index)
-{
-	return pagecache_get_page(mapping, index, FGP_WRITEBEGIN,
-			mapping_gfp_mask(mapping));
-}
-EXPORT_SYMBOL(grab_cache_page_write_begin);