Merge tag 'f2fs-for-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs update from Jaegeuk Kim:
 "In this round, we've mainly modified to support non-power-of-two zone
  size, which is not required for f2fs by design. In order to avoid arch
  dependency, we refactored the messy rb_entry structure shared across
  different extent_cache. In addition to the improvement, we've also
  fixed several subtle bugs and error cases.

  Enhancements:
   - support non-power-of-two zone size for zoned device
   - remove sharing the rb_entry structure in extent cache
   - refactor f2fs_gc to call checkpoint in urgent condition
   - support iopoll

  Bug fixes:
   - fix potential corruption when moving a directory
   - fix to avoid use-after-free for cached IPU bio
   - fix the folio private usage
   - avoid kernel warnings or panics in the cp_error case
   - fix to recover quota data correctly
   - fix some bugs in atomic operations
   - fix system crash due to lack of free space in LFS
   - fix null pointer panic in tracepoint in __replace_atomic_write_block
   - fix iostat lock protection
   - fix scheduling while atomic in decompression path
   - preserve direct write semantics when buffering is forced
   - fix to call f2fs_wait_on_page_writeback() in f2fs_write_raw_pages()"

* tag 'f2fs-for-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (52 commits)
  f2fs: remove unnessary comment in __may_age_extent_tree
  f2fs: allocate node blocks for atomic write block replacement
  f2fs: use cow inode data when updating atomic write
  f2fs: remove power-of-two limitation of zoned device
  f2fs: allocate trace path buffer from names_cache
  f2fs: add has_enough_free_secs()
  f2fs: relax sanity check if checkpoint is corrupted
  f2fs: refactor f2fs_gc to call checkpoint in urgent condition
  f2fs: remove folio_detach_private() in .invalidate_folio and .release_folio
  f2fs: remove bulk remove_proc_entry() and unnecessary kobject_del()
  f2fs: support iopoll method
  f2fs: remove batched_trim_sections node description
  f2fs: fix to check return value of inc_valid_block_count()
  f2fs: fix to check return value of f2fs_do_truncate_blocks()
  f2fs: fix passing relative address when discard zones
  f2fs: fix potential corruption when moving a directory
  f2fs: add radix_tree_preload_end in error case
  f2fs: fix to recover quota data correctly
  f2fs: fix to check readonly condition correctly
  docs: f2fs: Correct instruction to disable checkpoint
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -190,12 +190,6 @@ Description:	Controls the memory footprint used by free nids and cached
 		nat entries. By default, 1 is set, which indicates
 		10 MB / 1 GB RAM.
 
-What:		/sys/fs/f2fs/<disk>/batched_trim_sections
-Date:		February 2015
-Contact:	"Jaegeuk Kim" <[email protected]>
-Description:	Controls the trimming rate in batch mode.
-		<deprecated>
-
 What:		/sys/fs/f2fs/<disk>/cp_interval
 Date:		October 2015
 Contact:	"Jaegeuk Kim" <[email protected]>
@@ -729,3 +723,20 @@ What:		/sys/fs/f2fs/<disk>/last_age_weight
 Date:		January 2023
 Contact:	"Ping Xiong" <[email protected]>
 Description:	When DATA SEPARATION is on, it controls the weight of last data block age.
+
+What:		/sys/fs/f2fs/<disk>/compress_watermark
+Date:		February 2023
+Contact:	"Yangtao Li" <[email protected]>
+Description:	When compress cache is on, it controls free memory watermark
+		in order to limit caching compress page. If free memory is lower
+		than watermark, then deny caching compress page. The value should be in
+		range of (0, 100], by default it was initialized as 20(%).
+
+What:		/sys/fs/f2fs/<disk>/compress_percent
+Date:		February 2023
+Contact:	"Yangtao Li" <[email protected]>
+Description:	When compress cache is on, it controls cached page
+		percent(compress pages / free_ram) in order to limit caching compress page.
+		If cached page percent exceed threshold, then deny caching compress page.
+		The value should be in range of (0, 100], by default it was initialized
+		as 20(%).

Documentation/filesystems/f2fs.rst

@@ -264,7 +264,7 @@ checkpoint=%s[:%u[%]]	 Set to "disable" to turn off checkpointing. Set to "enabl
 			 disabled, any unmounting or unexpected shutdowns will cause
 			 the filesystem contents to appear as they did when the
 			 filesystem was mounted with that option.
-			 While mounting with checkpoint=disabled, the filesystem must
+			 While mounting with checkpoint=disable, the filesystem must
 			 run garbage collection to ensure that all available space can
 			 be used. If this takes too much time, the mount may return
 			 EAGAIN. You may optionally add a value to indicate how much

fs/f2fs/checkpoint.c

@@ -152,6 +152,11 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 	se = get_seg_entry(sbi, segno);
 
 	exist = f2fs_test_bit(offset, se->cur_valid_map);
+
+	/* skip data, if we already have an error in checkpoint. */
+	if (unlikely(f2fs_cp_error(sbi)))
+		return exist;
+
 	if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) {
 		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
 			 blkaddr, exist);
@@ -202,6 +207,11 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 	case DATA_GENERIC_ENHANCE_UPDATE:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
 				blkaddr < MAIN_BLKADDR(sbi))) {
+
+			/* Skip to emit an error message. */
+			if (unlikely(f2fs_cp_error(sbi)))
+				return false;
+
 			f2fs_warn(sbi, "access invalid blkaddr:%u",
 				  blkaddr);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -325,8 +335,15 @@ static int __f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
+			ClearPageUptodate(page);
+			dec_page_count(sbi, F2FS_DIRTY_META);
+			unlock_page(page);
+			return 0;
+		}
 		goto redirty_out;
+	}
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
@@ -508,6 +525,7 @@ static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
 	if (!e) {
 		if (!new) {
 			spin_unlock(&im->ino_lock);
+			radix_tree_preload_end();
 			goto retry;
 		}
 		e = new;
@@ -706,32 +724,18 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 {
 	block_t start_blk, orphan_blocks, i, j;
-	unsigned int s_flags = sbi->sb->s_flags;
 	int err = 0;
-#ifdef CONFIG_QUOTA
-	int quota_enabled;
-#endif
 
 	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
 
-	if (bdev_read_only(sbi->sb->s_bdev)) {
+	if (f2fs_hw_is_readonly(sbi)) {
 		f2fs_info(sbi, "write access unavailable, skipping orphan cleanup");
 		return 0;
 	}
 
-	if (s_flags & SB_RDONLY) {
+	if (is_sbi_flag_set(sbi, SBI_IS_WRITABLE))
 		f2fs_info(sbi, "orphan cleanup on readonly fs");
-		sbi->sb->s_flags &= ~SB_RDONLY;
-	}
-
-#ifdef CONFIG_QUOTA
-	/*
-	 * Turn on quotas which were not enabled for read-only mounts if
-	 * filesystem has quota feature, so that they are updated correctly.
-	 */
-	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
-#endif
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
 	orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
@@ -765,13 +769,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 out:
 	set_sbi_flag(sbi, SBI_IS_RECOVERED);
 
-#ifdef CONFIG_QUOTA
-	/* Turn quotas off */
-	if (quota_enabled)
-		f2fs_quota_off_umount(sbi->sb);
-#endif
-	sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
-
 	return err;
 }
 
@@ -982,7 +979,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 
 	cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
 	if (cur_page == cp2)
-		cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+		cp_blk_no += BIT(le32_to_cpu(fsb->log_blocks_per_seg));
 
 	for (i = 1; i < cp_blks; i++) {
 		void *sit_bitmap_ptr;
@@ -1133,7 +1130,7 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
 	goto retry;
 }
 
-int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
+static int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head = &sbi->inode_list[DIRTY_META];
 	struct inode *inode;
@@ -1306,7 +1303,8 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
 		if (!get_pages(sbi, type))
 			break;
 
-		if (unlikely(f2fs_cp_error(sbi)))
+		if (unlikely(f2fs_cp_error(sbi) &&
+			!is_sbi_flag_set(sbi, SBI_IS_CLOSE)))
 			break;
 
 		if (type == F2FS_DIRTY_META)

fs/f2fs/compress.c

@@ -264,35 +264,21 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
 	cc->private = NULL;
 }
 
-#ifdef CONFIG_F2FS_FS_LZ4HC
-static int lz4hc_compress_pages(struct compress_ctx *cc)
+static int lz4_compress_pages(struct compress_ctx *cc)
 {
+	int len = -EINVAL;
 	unsigned char level = F2FS_I(cc->inode)->i_compress_level;
-	int len;
 
-	if (level)
-		len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen,
-					cc->clen, level, cc->private);
-	else
+	if (!level)
 		len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
 						cc->clen, cc->private);
-	if (!len)
-		return -EAGAIN;
-
-	cc->clen = len;
-	return 0;
-}
-#endif
-
-static int lz4_compress_pages(struct compress_ctx *cc)
-{
-	int len;
-
 #ifdef CONFIG_F2FS_FS_LZ4HC
-	return lz4hc_compress_pages(cc);
+	else
+		len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+					cc->clen, level, cc->private);
 #endif
-	len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
-						cc->clen, cc->private);
+	if (len < 0)
+		return len;
 	if (!len)
 		return -EAGAIN;
 
@@ -670,7 +656,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
 
-	if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)
+	if (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))
 		chksum = f2fs_crc32(F2FS_I_SB(cc->inode),
 					cc->cbuf->cdata, cc->clen);
 	cc->cbuf->chksum = cpu_to_le32(chksum);
@@ -755,13 +741,18 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task)
 
 	if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) {
 		ret = -EFSCORRUPTED;
-		f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
+
+		/* Avoid f2fs_commit_super in irq context */
+		if (in_task)
+			f2fs_save_errors(sbi, ERROR_FAIL_DECOMPRESSION);
+		else
+			f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
 		goto out_release;
 	}
 
 	ret = cops->decompress_pages(dic);
 
-	if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) {
+	if (!ret && (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))) {
 		u32 provided = le32_to_cpu(dic->cbuf->chksum);
 		u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen);
 
@@ -1456,6 +1447,12 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 		if (!PageDirty(cc->rpages[i]))
 			goto continue_unlock;
 
+		if (PageWriteback(cc->rpages[i])) {
+			if (wbc->sync_mode == WB_SYNC_NONE)
+				goto continue_unlock;
+			f2fs_wait_on_page_writeback(cc->rpages[i], DATA, true, true);
+		}
+
 		if (!clear_page_dirty_for_io(cc->rpages[i]))
 			goto continue_unlock;