Merge tag 'f2fs-for-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we've mainly investigated the zoned block device
  support along with patches such as correcting write pointers between
  f2fs and storage, adding asynchronous zone reset flow, and managing
  the number of open zones.

  Other than them, f2fs adds another mount option, "errors=x" to specify
  how to handle when it detects an unexpected behavior at runtime.

  Enhancements:
   - support 'errors=remount-ro|continue|panic' mount option
   - enforce some inode flag policies
   - allow .tmp compression given extensions
   - add some ioctls to manage the f2fs compression
   - improve looped node chain flow
   - avoid issuing small-sized discard commands during checkpoint
   - implement an asynchronous zone reset

  Bug fixes:
   - fix deadlock in xattr and inode page lock
   - fix and add sanity check in some error paths
   - fix to avoid NULL pointer dereference f2fs_write_end_io() along
     with put_super
   - set proper flags to quota files
   - fix potential deadlock due to unpaired node_write lock use
   - fix over-estimating free section during FG GC
   - fix the wrong condition to determine atomic context

  As usual, also there are a number of patches with code refactoring and
  minor clean-ups"

* tag 'f2fs-for-6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (46 commits)
  f2fs: fix to do sanity check on direct node in truncate_dnode()
  f2fs: only set release for file that has compressed data
  f2fs: fix compile warning in f2fs_destroy_node_manager()
  f2fs: fix error path handling in truncate_dnode()
  f2fs: fix deadlock in i_xattr_sem and inode page lock
  f2fs: remove unneeded page uptodate check/set
  f2fs: update mtime and ctime in move file range method
  f2fs: compress tmp files given extension
  f2fs: refactor struct f2fs_attr macro
  f2fs: convert to use sbi directly
  f2fs: remove redundant assignment to variable err
  f2fs: do not issue small discard commands during checkpoint
  f2fs: check zone write pointer points to the end of zone
  f2fs: add f2fs_ioc_get_compress_blocks
  f2fs: cleanup MIN_INLINE_XATTR_SIZE
  f2fs: add helper to check compression level
  f2fs: set FMODE_CAN_ODIRECT instead of a dummy direct_IO method
  f2fs: do more sanity check on inode
  f2fs: compress: fix to check validity of i_compress_flag field
  f2fs: add sanity compress level check for compressed file
  ...

21 files changed, 1069 insertions, 407 deletions

diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index c57745375edb..9359978a5af2 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -351,6 +351,22 @@ age_extent_cache	 Enable an age extent cache based on rb-tree. It records
 			 data block update frequency of the extent per inode, in
 			 order to provide better temperature hints for data block
 			 allocation.
+errors=%s		 Specify f2fs behavior on critical errors. This supports modes:
+			 "panic", "continue" and "remount-ro", respectively, trigger
+			 panic immediately, continue without doing anything, and remount
+			 the partition in read-only mode. By default it uses "continue"
+			 mode.
+			 ====================== =============== =============== ========
+			 mode			continue	remount-ro	panic
+			 ====================== =============== =============== ========
+			 access ops		normal		noraml		N/A
+			 syscall errors		-EIO		-EROFS		N/A
+			 mount option		rw		ro		N/A
+			 pending dir write	keep		keep		N/A
+			 pending non-dir write	drop		keep		N/A
+			 pending node write	drop		keep		N/A
+			 pending meta write	keep		keep		N/A
+			 ====================== =============== =============== ========
 ======================== ============================================================
 
 Debugfs Entries
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 64b3860f50ee..8fd3b7f9fb88 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -30,12 +30,9 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
 						unsigned char reason)
 {
 	f2fs_build_fault_attr(sbi, 0, 0);
-	set_ckpt_flags(sbi, CP_ERROR_FLAG);
-	if (!end_io) {
+	if (!end_io)
 		f2fs_flush_merged_writes(sbi);
-
-		f2fs_handle_stop(sbi, reason);
-	}
+	f2fs_handle_critical_error(sbi, reason, end_io);
 }
 
 /*
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 11653fa79289..236d890f560b 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -55,6 +55,7 @@ struct f2fs_compress_ops {
 	int (*init_decompress_ctx)(struct decompress_io_ctx *dic);
 	void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic);
 	int (*decompress_pages)(struct decompress_io_ctx *dic);
+	bool (*is_level_valid)(int level);
 };
 
 static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index)
@@ -308,17 +309,25 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic)
 	return 0;
 }
 
+static bool lz4_is_level_valid(int lvl)
+{
+#ifdef CONFIG_F2FS_FS_LZ4HC
+	return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL);
+#else
+	return lvl == 0;
+#endif
+}
+
 static const struct f2fs_compress_ops f2fs_lz4_ops = {
 	.init_compress_ctx	= lz4_init_compress_ctx,
 	.destroy_compress_ctx	= lz4_destroy_compress_ctx,
 	.compress_pages		= lz4_compress_pages,
 	.decompress_pages	= lz4_decompress_pages,
+	.is_level_valid		= lz4_is_level_valid,
 };
 #endif
 
 #ifdef CONFIG_F2FS_FS_ZSTD
-#define F2FS_ZSTD_DEFAULT_CLEVEL	1
-
 static int zstd_init_compress_ctx(struct compress_ctx *cc)
 {
 	zstd_parameters params;
@@ -327,6 +336,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
 	unsigned int workspace_size;
 	unsigned char level = F2FS_I(cc->inode)->i_compress_level;
 
+	/* Need to remain this for backward compatibility */
 	if (!level)
 		level = F2FS_ZSTD_DEFAULT_CLEVEL;
 
@@ -477,6 +487,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic)
 	return 0;
 }
 
+static bool zstd_is_level_valid(int lvl)
+{
+	return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel();
+}
+
 static const struct f2fs_compress_ops f2fs_zstd_ops = {
 	.init_compress_ctx	= zstd_init_compress_ctx,
 	.destroy_compress_ctx	= zstd_destroy_compress_ctx,
@@ -484,6 +499,7 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = {
 	.init_decompress_ctx	= zstd_init_decompress_ctx,
 	.destroy_decompress_ctx	= zstd_destroy_decompress_ctx,
 	.decompress_pages	= zstd_decompress_pages,
+	.is_level_valid		= zstd_is_level_valid,
 };
 #endif
 
@@ -542,6 +558,16 @@ bool f2fs_is_compress_backend_ready(struct inode *inode)
 	return f2fs_cops[F2FS_I(inode)->i_compress_algorithm];
 }
 
+bool f2fs_is_compress_level_valid(int alg, int lvl)
+{
+	const struct f2fs_compress_ops *cops = f2fs_cops[alg];
+
+	if (cops->is_level_valid)
+		return cops->is_level_valid(lvl);
+
+	return lvl == 0;
+}
+
 static mempool_t *compress_page_pool;
 static int num_compress_pages = 512;
 module_param(num_compress_pages, uint, 0444);
@@ -743,8 +769,8 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task)
 		ret = -EFSCORRUPTED;
 
 		/* Avoid f2fs_commit_super in irq context */
-		if (in_task)
-			f2fs_save_errors(sbi, ERROR_FAIL_DECOMPRESSION);
+		if (!in_task)
+			f2fs_handle_error_async(sbi, ERROR_FAIL_DECOMPRESSION);
 		else
 			f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
 		goto out_release;
@@ -1215,6 +1241,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 	unsigned int last_index = cc->cluster_size - 1;
 	loff_t psize;
 	int i, err;
+	bool quota_inode = IS_NOQUOTA(inode);
 
 	/* we should bypass data pages to proceed the kworker jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -1222,7 +1249,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		goto out_free;
 	}
 
-	if (IS_NOQUOTA(inode)) {
+	if (quota_inode) {
 		/*
 		 * We need to wait for node_write to avoid block allocation during
 		 * checkpoint. This can only happen to quota writes which can cause
@@ -1344,7 +1371,7 @@ unlock_continue:
 		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
 
 	f2fs_put_dnode(&dn);
-	if (IS_NOQUOTA(inode))
+	if (quota_inode)
 		f2fs_up_read(&sbi->node_write);
 	else
 		f2fs_unlock_op(sbi);
@@ -1370,7 +1397,7 @@ out_put_cic:
 out_put_dnode:
 	f2fs_put_dnode(&dn);
 out_unlock_op:
-	if (IS_NOQUOTA(inode))
+	if (quota_inode)
 		f2fs_up_read(&sbi->node_write);
 	else
 		f2fs_unlock_op(sbi);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7165b1202f53..5882afe71d82 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -383,6 +383,17 @@ static void f2fs_write_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static void f2fs_zone_write_end_io(struct bio *bio)
+{
+	struct f2fs_bio_info *io = (struct f2fs_bio_info *)bio->bi_private;
+
+	bio->bi_private = io->bi_private;
+	complete(&io->zone_wait);
+	f2fs_write_end_io(bio);
+}
+#endif
+
 struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
 		block_t blk_addr, sector_t *sector)
 {
@@ -639,6 +650,11 @@ int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
 			INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
 			INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
 			init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
+#ifdef CONFIG_BLK_DEV_ZONED
+			init_completion(&sbi->write_io[i][j].zone_wait);
+			sbi->write_io[i][j].zone_pending_bio = NULL;
+			sbi->write_io[i][j].bi_private = NULL;
+#endif
 		}
 	}
 
@@ -965,6 +981,26 @@ alloc_new:
 	return 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	int devi = 0;
+
+	if (f2fs_is_multi_device(sbi)) {
+		devi = f2fs_target_device_index(sbi, blkaddr);
+		if (blkaddr < FDEV(devi).start_blk ||
+		    blkaddr > FDEV(devi).end_blk) {
+			f2fs_err(sbi, "Invalid block %x", blkaddr);
+			return false;
+		}
+		blkaddr -= FDEV(devi).start_blk;
+	}
+	return bdev_zoned_model(FDEV(devi).bdev) == BLK_ZONED_HM &&
+		f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
+		(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
+}
+#endif
+
 void f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
@@ -975,6 +1011,16 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
 	f2fs_bug_on(sbi, is_read_io(fio->op));
 
 	f2fs_down_write(&io->io_rwsem);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) {
+		wait_for_completion_io(&io->zone_wait);
+		bio_put(io->zone_pending_bio);
+		io->zone_pending_bio = NULL;
+		io->bi_private = NULL;
+	}
+#endif
+
 next:
 	if (fio->in_list) {
 		spin_lock(&io->io_lock);
@@ -1038,6 +1084,18 @@ skip:
 	if (fio->in_list)
 		goto next;
 out:
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
+			is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
+		bio_get(io->bio);
+		reinit_completion(&io->zone_wait);
+		io->bi_private = io->bio->bi_private;
+		io->bio->bi_private = io;
+		io->bio->bi_end_io = f2fs_zone_write_end_io;
+		io->zone_pending_bio = io->bio;
+		__submit_merged_bio(io);
+	}
+#endif
 	if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
 				!f2fs_is_checkpoint_ready(sbi))
 		__submit_merged_bio(io);
@@ -2173,7 +2231,6 @@ submit_and_realloc:
 	f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
 							F2FS_BLKSIZE);
 	*last_block_in_bio = block_nr;
-	goto out;
 out:
 	*bio_ret = bio;
 	return ret;
@@ -2775,6 +2832,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 	loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
 	unsigned offset = 0;
 	bool need_balance_fs = false;
+	bool quota_inode = IS_NOQUOTA(inode);
 	int err = 0;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
@@ -2807,6 +2865,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 		if (S_ISDIR(inode->i_mode) &&
 				!is_sbi_flag_set(sbi, SBI_IS_CLOSE))
 			goto redirty_out;
+
+		/* keep data pages in remount-ro mode */
+		if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
+			goto redirty_out;
 		goto out;
 	}
 
@@ -2832,19 +2894,19 @@ write:
 		goto out;
 
 	/* Dentry/quota blocks are controlled by checkpoint */
-	if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) {
+	if (S_ISDIR(inode->i_mode) || quota_inode) {
 		/*
 		 * We need to wait for node_write to avoid block allocation during
 		 * checkpoint. This can only happen to quota writes which can cause
 		 * the below discard race condition.
 		 */
-		if (IS_NOQUOTA(inode))
+		if (quota_inode)
 			f2fs_down_read(&sbi->node_write);
 
 		fio.need_lock = LOCK_DONE;
 		err = f2fs_do_write_data_page(&fio);
 
-		if (IS_NOQUOTA(inode))
+		if (quota_inode)
 			f2fs_up_read(&sbi->node_write);
 
 		goto done;
@@ -4067,7 +4129,6 @@ const struct address_space_operations f2fs_dblock_aops = {
 	.migrate_folio	= filemap_migrate_folio,
 	.invalidate_folio = f2fs_invalidate_folio,
 	.release_folio	= f2fs_release_folio,
-	.direct_IO	= noop_direct_IO,
 	.bmap		= f2fs_bmap,
 	.swap_activate  = f2fs_swap_activate,
 	.swap_deactivate = f2fs_swap_deactivate,
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 887e55988450..d635c58cf5a3 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -775,8 +775,15 @@ int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
 {
 	int err = -EAGAIN;
 
-	if (f2fs_has_inline_dentry(dir))
+	if (f2fs_has_inline_dentry(dir)) {
+		/*
+		 * Should get i_xattr_sem to keep the lock order:
+		 * i_xattr_sem -> inode_page lock used by f2fs_setxattr.
+		 */
+		f2fs_down_read(&F2FS_I(dir)->i_xattr_sem);
 		err = f2fs_add_inline_entry(dir, fname, inode, ino, mode);
+		f2fs_up_read(&F2FS_I(dir)->i_xattr_sem);
+	}
 	if (err == -EAGAIN)
 		err = f2fs_add_regular_entry(dir, fname, inode, ino, mode);
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d211ee89c158..c7cb2177b252 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -80,34 +80,34 @@ extern const char *f2fs_fault_name[FAULT_MAX];
 /*
  * For mount options
  */
-#define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000002
-#define F2FS_MOUNT_DISCARD		0x00000004
-#define F2FS_MOUNT_NOHEAP		0x00000008
-#define F2FS_MOUNT_XATTR_USER		0x00000010
-#define F2FS_MOUNT_POSIX_ACL		0x00000020
-#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000040
-#define F2FS_MOUNT_INLINE_XATTR		0x00000080
-#define F2FS_MOUNT_INLINE_DATA		0x00000100
-#define F2FS_MOUNT_INLINE_DENTRY	0x00000200
-#define F2FS_MOUNT_FLUSH_MERGE		0x00000400
-#define F2FS_MOUNT_NOBARRIER		0x00000800
-#define F2FS_MOUNT_FASTBOOT		0x00001000
-#define F2FS_MOUNT_READ_EXTENT_CACHE	0x00002000
-#define F2FS_MOUNT_DATA_FLUSH		0x00008000
-#define F2FS_MOUNT_FAULT_INJECTION	0x00010000
-#define F2FS_MOUNT_USRQUOTA		0x00080000
-#define F2FS_MOUNT_GRPQUOTA		0x00100000
-#define F2FS_MOUNT_PRJQUOTA		0x00200000
-#define F2FS_MOUNT_QUOTA		0x00400000
-#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00800000
-#define F2FS_MOUNT_RESERVE_ROOT		0x01000000
-#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x02000000
-#define F2FS_MOUNT_NORECOVERY		0x04000000
-#define F2FS_MOUNT_ATGC			0x08000000
-#define F2FS_MOUNT_MERGE_CHECKPOINT	0x10000000
-#define	F2FS_MOUNT_GC_MERGE		0x20000000
-#define F2FS_MOUNT_COMPRESS_CACHE	0x40000000
-#define F2FS_MOUNT_AGE_EXTENT_CACHE	0x80000000
+#define F2FS_MOUNT_DISABLE_ROLL_FORWARD	0x00000001
+#define F2FS_MOUNT_DISCARD		0x00000002
+#define F2FS_MOUNT_NOHEAP		0x00000004
+#define F2FS_MOUNT_XATTR_USER		0x00000008
+#define F2FS_MOUNT_POSIX_ACL		0x00000010
+#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY	0x00000020
+#define F2FS_MOUNT_INLINE_XATTR		0x00000040
+#define F2FS_MOUNT_INLINE_DATA		0x00000080
+#define F2FS_MOUNT_INLINE_DENTRY	0x00000100
+#define F2FS_MOUNT_FLUSH_MERGE		0x00000200
+#define F2FS_MOUNT_NOBARRIER		0x00000400
+#define F2FS_MOUNT_FASTBOOT		0x00000800
+#define F2FS_MOUNT_READ_EXTENT_CACHE	0x00001000
+#define F2FS_MOUNT_DATA_FLUSH		0x00002000
+#define F2FS_MOUNT_FAULT_INJECTION	0x00004000
+#define F2FS_MOUNT_USRQUOTA		0x00008000
+#define F2FS_MOUNT_GRPQUOTA		0x00010000
+#define F2FS_MOUNT_PRJQUOTA		0x00020000
+#define F2FS_MOUNT_QUOTA		0x00040000
+#define F2FS_MOUNT_INLINE_XATTR_SIZE	0x00080000
+#define F2FS_MOUNT_RESERVE_ROOT		0x00100000
+#define F2FS_MOUNT_DISABLE_CHECKPOINT	0x00200000
+#define F2FS_MOUNT_NORECOVERY		0x00400000
+#define F2FS_MOUNT_ATGC			0x00800000
+#define F2FS_MOUNT_MERGE_CHECKPOINT	0x01000000
+#define	F2FS_MOUNT_GC_MERGE		0x02000000
+#define F2FS_MOUNT_COMPRESS_CACHE	0x04000000
+#define F2FS_MOUNT_AGE_EXTENT_CACHE	0x08000000
 
 #define F2FS_OPTION(sbi)	((sbi)->mount_opt)
 #define clear_opt(sbi, option)	(F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -162,6 +162,7 @@ struct f2fs_mount_info {
 	int fs_mode;			/* fs mode: LFS or ADAPTIVE */
 	int bggc_mode;			/* bggc mode: off, on or sync */
 	int memory_mode;		/* memory mode */
+	int errors;			/* errors parameter */
 	int discard_unit;		/*
 					 * discard command's offset/size should
 					 * be aligned to this unit: block,
@@ -185,21 +186,21 @@ struct f2fs_mount_info {
 	unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */
 };
 
-#define F2FS_FEATURE_ENCRYPT		0x0001
-#define F2FS_FEATURE_BLKZONED		0x0002
-#define F2FS_FEATURE_ATOMIC_WRITE	0x0004
-#define F2FS_FEATURE_EXTRA_ATTR		0x0008
-#define F2FS_FEATURE_PRJQUOTA		0x0010
-#define F2FS_FEATURE_INODE_CHKSUM	0x0020
-#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x0040
-#define F2FS_FEATURE_QUOTA_INO		0x0080
-#define F2FS_FEATURE_INODE_CRTIME	0x0100
-#define F2FS_FEATURE_LOST_FOUND		0x0200
-#define F2FS_FEATURE_VERITY		0x0400
-#define F2FS_FEATURE_SB_CHKSUM		0x0800
-#define F2FS_FEATURE_CASEFOLD		0x1000
-#define F2FS_FEATURE_COMPRESSION	0x2000
-#define F2FS_FEATURE_RO			0x4000
+#define F2FS_FEATURE_ENCRYPT			0x00000001
+#define F2FS_FEATURE_BLKZONED			0x00000002
+#define F2FS_FEATURE_ATOMIC_WRITE		0x00000004
+#define F2FS_FEATURE_EXTRA_ATTR			0x00000008
+#define F2FS_FEATURE_PRJQUOTA			0x00000010
+#define F2FS_FEATURE_INODE_CHKSUM		0x00000020
+#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR	0x00000040
+#define F2FS_FEATURE_QUOTA_INO			0x00000080
+#define F2FS_FEATURE_INODE_CRTIME		0x00000100
+#define F2FS_FEATURE_LOST_FOUND			0x00000200
+#define F2FS_FEATURE_VERITY			0x00000400
+#define F2FS_FEATURE_SB_CHKSUM			0x00000800
+#define F2FS_FEATURE_CASEFOLD			0x00001000
+#define F2FS_FEATURE_COMPRESSION		0x00002000
+#define F2FS_FEATURE_RO				0x00004000
 
 #define __F2FS_HAS_FEATURE(raw_super, mask)				\
 	((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -1175,6 +1176,7 @@ enum iostat_type {
 	/* other */
 	FS_DISCARD_IO,			/* discard */
 	FS_FLUSH_IO,			/* flush */
+	FS_ZONE_RESET_IO,		/* zone reset */
 	NR_IO_TYPE,
 };
 
@@ -1217,6 +1219,11 @@ struct f2fs_bio_info {
 	struct bio *bio;		/* bios to merge */
 	sector_t last_block_in_bio;	/* last block number */
 	struct f2fs_io_info fio;	/* store buffered io info. */
+#ifdef CONFIG_BLK_DEV_ZONED
+	struct completion zone_wait;	/* condition value for the previous open zone to close */
+	struct bio *zone_pending_bio;	/* pending bio for the previous zone */
+	void *bi_private;		/* previous bi_private for pending bio */
+#endif
 	struct f2fs_rwsem io_rwsem;	/* blocking op for bio */
 	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
 	struct list_head io_list;	/* track fios */
@@ -1370,6 +1377,12 @@ enum {
 	MEMORY_MODE_LOW,	/* memory mode for low memry devices */
 };
 
+enum errors_option {
+	MOUNT_ERRORS_READONLY,	/* remount fs ro on errors */
+	MOUNT_ERRORS_CONTINUE,	/* continue on errors */
+	MOUNT_ERRORS_PANIC,	/* panic on errors */
+};
+
 static inline int f2fs_test_bit(unsigned int nr, char *addr);
 static inline void f2fs_set_bit(unsigned int nr, char *addr);
 static inline void f2fs_clear_bit(unsigned int nr, char *addr);
@@ -1427,6 +1440,8 @@ struct compress_data {
 
 #define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000
 
+#define F2FS_ZSTD_DEFAULT_CLEVEL	1
+
 #define	COMPRESS_LEVEL_OFFSET	8
 
 /* compress context */
@@ -1721,8 +1736,14 @@ struct f2fs_sb_info {
 
 	struct workqueue_struct *post_read_wq;	/* post read workqueue */
 
-	unsigned char errors[MAX_F2FS_ERRORS];	/* error flags */
-	spinlock_t error_lock;			/* protect errors array */
+	/*
+	 * If we are in irq context, let's update error information into
+	 * on-disk superblock in the work.
+	 */
+	struct work_struct s_error_work;
+	unsigned char errors[MAX_F2FS_ERRORS];		/* error flags */
+	unsigned char stop_reason[MAX_STOP_REASON];	/* stop reason */
+	spinlock_t error_lock;			/* protect errors/stop_reason array */
 	bool error_dirty;			/* errors of sb is dirty */
 
 	struct kmem_cache *inline_xattr_slab;	/* inline xattr entry */
@@ -2941,6 +2962,8 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 #define F2FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
 #define F2FS_CASEFOLD_FL		0x40000000 /* Casefolded file */
 
+#define F2FS_QUOTA_DEFAULT_FL		(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL)
+
 /* Flags that should be inherited by new inodes from their parent. */
 #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
 			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
@@ -3394,6 +3417,8 @@ static inline int get_inline_xattr_addrs(struct inode *inode)
 	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
+#define F2FS_MIN_EXTRA_ATTR_SIZE		(sizeof(__le32))
+
 #define F2FS_TOTAL_EXTRA_ATTR_SIZE			\
 	(offsetof(struct f2fs_inode, i_extra_end) -	\
 	offsetof(struct f2fs_inode, i_extra_isize))	\
@@ -3432,7 +3457,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr)
  * file.c
  */
 int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
-void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
 int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
 int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
 int f2fs_truncate(struct inode *inode);
@@ -3541,9 +3565,11 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
 int f2fs_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_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason);
 void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag);
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
+							bool irq_context);
 void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error);
+void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error);
 int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
 int f2fs_sync_fs(struct super_block *sb, int sync);
 int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
@@ -3815,7 +3841,7 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
 block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
 int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control);
 void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
-int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count);
+int f2fs_resize_fs(struct file *filp, __u64 block_count);
 int __init f2fs_create_garbage_collection_cache(void);
 void f2fs_destroy_garbage_collection_cache(void);
 /* victim selection function for cleaning and SSR */
@@ -4213,6 +4239,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
 int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
 void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
 bool f2fs_is_compress_backend_ready(struct inode *inode);
+bool f2fs_is_compress_level_valid(int alg, int lvl);
 int __init f2fs_init_compress_mempool(void);
 void f2fs_destroy_compress_mempool(void);
 void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task);
@@ -4277,6 +4304,7 @@ static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
 	/* not support compression */
 	return false;
 }
+static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; }
 static inline struct page *f2fs_compress_control_page(struct page *page)
 {
 	WARN_ON_ONCE(1);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 2435111a8532..093039dee992 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -149,8 +149,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		zero_user_segment(page, offset, PAGE_SIZE);
 	}
 	set_page_dirty(page);
-	if (!PageUptodate(page))
-		SetPageUptodate(page);
 
 	f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
 	f2fs_update_time(sbi, REQ_TIME);
@@ -546,7 +544,8 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 	if (err)
 		return err;
 
-	filp->f_mode |= FMODE_NOWAIT;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+	filp->f_mode |= FMODE_CAN_ODIRECT;
 
 	return dquot_file_open(inode, filp);
 }
@@ -627,11 +626,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 					 dn->ofs_in_node, nr_free);
 }
 
-void f2fs_truncate_data_blocks(struct dnode_of_data *dn)
-{
-	f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode));
-}
-
 static int truncate_partial_data_page(struct inode *inode, u64 from,
 								bool cache_only)
 {
@@ -2225,7 +2219,6 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 				ret = 0;
 				f2fs_stop_checkpoint(sbi, false,
 						STOP_CP_REASON_SHUTDOWN);
-				set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 				trace_f2fs_shutdown(sbi, in, ret);
 			}
 			return ret;
@@ -2238,7 +2231,6 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 		if (ret)
 			goto out;
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 		thaw_bdev(sb->s_bdev);
 		break;
 	case F2FS_GOING_DOWN_METASYNC:
@@ -2247,16 +2239,13 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 		if (ret)
 			goto out;
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 		break;
 	case F2FS_GOING_DOWN_NOSYNC:
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 		break;
 	case F2FS_GOING_DOWN_METAFLUSH:
 		f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
-		set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
 		break;
 	case F2FS_GOING_DOWN_NEED_FSCK:
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -2593,6 +2582,11 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 
 	inode_lock(inode);
 
+	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+		err = -EINVAL;
+		goto unlock_out;
+	}
+
 	/* if in-place-update policy is enabled, don't waste time here */
 	set_inode_flag(inode, FI_OPU_WRITE);
 	if (f2fs_should_update_inplace(inode, NULL)) {
@@ -2717,6 +2711,7 @@ clear_out:
 	clear_inode_flag(inode, FI_SKIP_WRITES);
 out:
 	clear_inode_flag(inode, FI_OPU_WRITE);
+unlock_out:
 	inode_unlock(inode);
 	if (!err)
 		range->len = (u64)total << PAGE_SHIFT;
@@ -2876,6 +2871,17 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 		f2fs_up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]);
 out_src:
 	f2fs_up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
+	if (ret)
+		goto out_unlock;
+
+	src->i_mtime = src->i_ctime = current_time(src);
+	f2fs_mark_inode_dirty_sync(src, false);
+	if (src != dst) {
+		dst->i_mtime = dst->i_ctime = current_time(dst);
+		f2fs_mark_inode_dirty_sync(dst, false);
+	}
+	f2fs_update_time(sbi, REQ_TIME);
+
 out_unlock:
 	if (src != dst)
 		inode_unlock(dst);
@@ -3278,7 +3284,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
 			   sizeof(block_count)))
 		return -EFAULT;
 
-	return f2fs_resize_fs(sbi, block_count);
+	return f2fs_resize_fs(filp, block_count);
 }
 
 static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg)
@@ -3375,18 +3381,29 @@ out:
 	return err;
 }
 
-static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
+static int f2fs_get_compress_blocks(struct inode *inode, __u64 *blocks)
 {
-	struct inode *inode = file_inode(filp);
-	__u64 blocks;
-
 	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
 		return -EOPNOTSUPP;
 
 	if (!f2fs_compressed_file(inode))
 		return -EINVAL;
 
-	blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks);
+	*blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks);
+
+	return 0;
+}
+
+static int f2fs_ioc_get_compress_blocks(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	__u64 blocks;
+	int ret;
+
+	ret = f2fs_get_compress_blocks(inode, &blocks);
+	if (ret < 0)
+		return ret;
+
 	return put_user(blocks, (u64 __user *)arg);
 }
 
@@ -3455,7 +3472,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	int ret;
 	int writecount;
 
-	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+	if (!f2fs_sb_has_compression(sbi))
 		return -EOPNOTSUPP;
 
 	if (!f2fs_compressed_file(inode))
@@ -3468,7 +3485,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret)
 		return ret;
 
-	f2fs_balance_fs(F2FS_I_SB(inode), true);
+	f2fs_balance_fs(sbi, true);
 
 	inode_lock(inode);
 
@@ -3488,13 +3505,15 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 	if (ret)
 		goto out;
 
+	if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+		ret = -EPERM;
+		goto out;
+	}
+
 	set_inode_flag(inode, FI_COMPRESS_RELEASED);
 	inode->i_ctime = current_time(inode);
 	f2fs_mark_inode_dirty_sync(inode, true);
 
-	if (!atomic_read(&F2FS_I(inode)->i_compr_blocks))
-		goto out;
-
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
@@ -3625,7 +3644,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	unsigned int reserved_blocks = 0;
 	int ret;
 
-	if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+	if (!f2fs_sb_has_compression(sbi))
 		return -EOPNOTSUPP;
 
 	if (!f2fs_compressed_file(inode))
@@ -3641,7 +3660,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 	if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
 		goto out;
 
-	f2fs_balance_fs(F2FS_I_SB(inode), true);
+	f2fs_balance_fs(sbi, true);
 
 	inode_lock(inode);
 
@@ -4035,7 +4054,7 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 	if (!f2fs_compressed_file(inode))
 		return -EINVAL;
 
-	f2fs_balance_fs(F2FS_I_SB(inode), true);
+	f2fs_balance_fs(sbi, true);
 
 	file_start_write(filp);
 	inode_lock(inode);
@@ -4110,7 +4129,7 @@ static int f2fs_ioc_compress_file(struct file *filp)
 	if (!f2fs_compressed_file(inode))
 		return -EINVAL;
 
-	f2fs_balance_fs(F2FS_I_SB(inode), true);
+	f2fs_balance_fs(sbi, true);