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
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -734,6 +734,7 @@ Description:	Support configuring fault injection type, should be
 		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
@@ -828,3 +829,20 @@ Date:		November 2024
 Contact:	"Chao Yu" <[email protected]>
 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" <[email protected]>
+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" <[email protected]>
+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

@@ -206,6 +206,7 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 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
@@ -365,6 +366,8 @@ errors=%s		 Specify f2fs behavior on critical errors. This supports modes:
 			 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

@@ -21,7 +21,7 @@
 #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;
@@ -58,7 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 							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,
@@ -74,37 +74,37 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 	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)
@@ -381,12 +381,6 @@ static int __f2fs_write_meta_page(struct page *page,
 	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)
 {
@@ -507,7 +501,6 @@ static bool f2fs_dirty_meta_folio(struct address_space *mapping,
 }
 
 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,
@@ -1237,7 +1230,7 @@ static int block_operations(struct f2fs_sb_info *sbi)
 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);
@@ -1246,11 +1239,13 @@ static int block_operations(struct f2fs_sb_info *sbi)
 		}
 		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;
 	}
@@ -1344,21 +1339,13 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	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);
 	else
@@ -1541,8 +1528,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	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;
 
@@ -1867,7 +1853,8 @@ int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi)
 	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

@@ -1150,6 +1150,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
 		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);