Merge tag 'vfs-6.19-rc1.fs_header' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull fs header updates from Christian Brauner:
"This contains initial work to start splitting up fs.h.

Begin the long-overdue work of splitting up the monolithic fs.h
header. The header has grown to over 3000 lines and includes types and
functions for many different subsystems, making it difficult to
navigate and causing excessive compilation dependencies.

This series introduces new focused headers for superblock-related
code:

- Rename fs_types.h to fs_dirent.h to better reflect its actual
content (directory entry types)

- Add fs/super_types.h containing superblock type definitions

- Add fs/super.h containing superblock function declarations

This is the first step in a longer effort to modularize the VFS
headers.

Cleanups:

- Inode Field Layout Optimization (Mateusz Guzik)

Move inode fields used during fast path lookup closer together to
improve cache locality during path resolution.

- current_umask() Optimization (Mateusz Guzik)

Inline current_umask() and move it to fs_struct.h. This improves
performance by avoiding function call overhead for this
frequently-used function, and places it in a more appropriate
header since it operates on fs_struct"

* tag 'vfs-6.19-rc1.fs_header' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
fs: move inode fields used during fast path lookup closer together
fs: inline current_umask() and move it to fs_struct.h
fs: add fs/super.h header
fs: add fs/super_types.h header
fs: rename fs_types.h to fs_dirent.h

fs/9p/acl.c

···
 
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <linux/slab.h>

fs/Makefile

···
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
-		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
+		fs_dirent.o fs_context.o fs_parser.o fsopen.o init.o \
 		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o \
 		file_attr.o
 

fs/btrfs/inode.c

···
 #include <linux/blk-cgroup.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/time.h>

fs/f2fs/acl.c

···
  *
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <[e-mail]>
  */
+#include <linux/fs_struct.h>
 #include <linux/f2fs_fs.h>
 #include "f2fs.h"
 #include "xattr.h"

fs/fat/inode.c

···
 #include <linux/unaligned.h>
 #include <linux/random.h>
 #include <linux/iversion.h>
+#include <linux/fs_struct.h>
 #include "fat.h"
 
 #ifndef CONFIG_FAT_DEFAULT_IOCHARSET

fs/fs_struct.c

···
 }
 EXPORT_SYMBOL_GPL(unshare_fs_struct);
 
-int current_umask(void)
-{
-	return current->fs->umask;
-}
-EXPORT_SYMBOL(current_umask);
-
 /* to be mentioned only in INIT_TASK */
 struct fs_struct init_fs = {
 	.users		= 1,

fs/fs_types.c fs/fs_dirent.c

···
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/fs.h>
+#include <linux/fs_dirent.h>
 #include <linux/export.h>
 
 /*

fs/hfsplus/options.c

···
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/fs_struct.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/nls.h>

fs/hpfs/super.c

···
 
 #include "hpfs_fn.h"
 #include <linux/module.h>
+#include <linux/fs_struct.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/init.h>

fs/nilfs2/nilfs.h

···
 #include <linux/buffer_head.h>
 #include <linux/spinlock.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 #include <linux/nilfs2_api.h>
 #include <linux/nilfs2_ondisk.h>
 #include "the_nilfs.h"

fs/ntfs3/super.c

···
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include <linux/log2.h>

fs/ocfs2/acl.c

···
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/fs_struct.h>
 
 #include <cluster/masklog.h>
 

fs/omfs/inode.c

···
 #include <linux/writeback.h>
 #include <linux/seq_file.h>
 #include <linux/crc-itu-t.h>
+#include <linux/fs_struct.h>
 #include <linux/fs_context.h>
 #include <linux/fs_parser.h>
 #include "omfs.h"

fs/smb/client/file.c

···
  *
  */
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/filelock.h>
 #include <linux/backing-dev.h>
 #include <linux/stat.h>

fs/smb/client/inode.c

···
  *
  */
 #include <linux/fs.h>
+#include <linux/fs_struct.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>

fs/smb/client/smb1ops.c

···
 
 #include <linux/pagemap.h>
 #include <linux/vfs.h>
+#include <linux/fs_struct.h>
 #include <uapi/linux/magic.h>
 #include "cifsglob.h"
 #include "cifsproto.h"

include/linux/fs.h

···
 #ifndef _LINUX_FS_H
 #define _LINUX_FS_H
 
+#include <linux/fs/super.h>
 #include <linux/vfsdebug.h>
 #include <linux/linkage.h>
 #include <linux/wait_bit.h>
···
 #include <linux/stat.h>
 #include <linux/cache.h>
 #include <linux/list.h>
-#include <linux/list_lru.h>
 #include <linux/llist.h>
 #include <linux/radix-tree.h>
 #include <linux/xarray.h>
···
 #include <linux/uuid.h>
 #include <linux/errseq.h>
 #include <linux/ioprio.h>
-#include <linux/fs_types.h>
 #include <linux/build_bug.h>
 #include <linux/stddef.h>
 #include <linux/mount.h>
···
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
 
-struct backing_dev_info;
 struct bdi_writeback;
 struct bio;
 struct io_comp_batch;
-struct export_operations;
 struct fiemap_extent_info;
 struct hd_geometry;
 struct iovec;
···
 struct cred;
 struct swap_info_struct;
 struct seq_file;
-struct workqueue_struct;
 struct iov_iter;
-struct fscrypt_operations;
-struct fsverity_operations;
 struct fsnotify_mark_connector;
-struct fsnotify_sb_info;
 struct fs_context;
 struct fs_parameter_spec;
 struct file_kattr;
···
 	 */
 	struct file	*ia_file;
 };
-
-/*
- * Includes for diskquotas.
- */
-#include <linux/quota.h>
 
 /*
  * Maximum number of layers of fs stack.  Needs to be limited to
···
 struct inode {
 	umode_t			i_mode;
 	unsigned short		i_opflags;
-	kuid_t			i_uid;
-	kgid_t			i_gid;
 	unsigned int		i_flags;
-
 #ifdef CONFIG_FS_POSIX_ACL
 	struct posix_acl	*i_acl;
 	struct posix_acl	*i_default_acl;
 #endif
+	kuid_t			i_uid;
+	kgid_t			i_gid;
 
 	const struct inode_operations	*i_op;
 	struct super_block	*i_sb;
···
 extern int send_sigurg(struct file *file);
 
 /*
- * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
- * represented in both.
- */
-#define SB_RDONLY       BIT(0)	/* Mount read-only */
-#define SB_NOSUID       BIT(1)	/* Ignore suid and sgid bits */
-#define SB_NODEV        BIT(2)	/* Disallow access to device special files */
-#define SB_NOEXEC       BIT(3)	/* Disallow program execution */
-#define SB_SYNCHRONOUS  BIT(4)	/* Writes are synced at once */
-#define SB_MANDLOCK     BIT(6)	/* Allow mandatory locks on an FS */
-#define SB_DIRSYNC      BIT(7)	/* Directory modifications are synchronous */
-#define SB_NOATIME      BIT(10)	/* Do not update access times. */
-#define SB_NODIRATIME   BIT(11)	/* Do not update directory access times */
-#define SB_SILENT       BIT(15)
-#define SB_POSIXACL     BIT(16)	/* Supports POSIX ACLs */
-#define SB_INLINECRYPT  BIT(17)	/* Use blk-crypto for encrypted files */
-#define SB_KERNMOUNT    BIT(22)	/* this is a kern_mount call */
-#define SB_I_VERSION    BIT(23)	/* Update inode I_version field */
-#define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define SB_DEAD         BIT(21)
-#define SB_DYING        BIT(24)
-#define SB_FORCE        BIT(27)
-#define SB_NOSEC        BIT(28)
-#define SB_BORN         BIT(29)
-#define SB_ACTIVE       BIT(30)
-#define SB_NOUSER       BIT(31)
-
-/* These flags relate to encoding and casefolding */
-#define SB_ENC_STRICT_MODE_FL		(1 << 0)
-#define SB_ENC_NO_COMPAT_FALLBACK_FL	(1 << 1)
-
-#define sb_has_strict_encoding(sb) \
-	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
-
-#if IS_ENABLED(CONFIG_UNICODE)
-#define sb_no_casefold_compat_fallback(sb) \
-	(sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL)
-#else
-#define sb_no_casefold_compat_fallback(sb) (1)
-#endif
-
-/*
  *	Umount options
  */
 
···
 #define MNT_EXPIRE	0x00000004	/* Mark for expiry */
 #define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
 #define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
-
-/* sb->s_iflags */
-#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
-#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
-#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
-#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
-
-/* sb->s_iflags to limit user namespace mounts */
-#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
-#define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
-#define SB_I_UNTRUSTED_MOUNTER		0x00000040
-#define SB_I_EVM_HMAC_UNSUPPORTED	0x00000080
-
-#define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
-#define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
-#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
-#define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */
-#define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
-#define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
-#define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
-
-/* Possible states of 'frozen' field */
-enum {
-	SB_UNFROZEN = 0,		/* FS is unfrozen */
-	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
-	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
-	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
-					 * internal threads if needed) */
-	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
-};
-
-#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
-
-struct sb_writers {
-	unsigned short			frozen;		/* Is sb frozen? */
-	int				freeze_kcount;	/* How many kernel freeze requests? */
-	int				freeze_ucount;	/* How many userspace freeze requests? */
-	const void			*freeze_owner;	/* Owner of the freeze */
-	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
-};
-
-struct mount;
-
-struct super_block {
-	struct list_head	s_list;		/* Keep this first */
-	dev_t			s_dev;		/* search index; _not_ kdev_t */
-	unsigned char		s_blocksize_bits;
-	unsigned long		s_blocksize;
-	loff_t			s_maxbytes;	/* Max file size */
-	struct file_system_type	*s_type;
-	const struct super_operations	*s_op;
-	const struct dquot_operations	*dq_op;
-	const struct quotactl_ops	*s_qcop;
-	const struct export_operations *s_export_op;
-	unsigned long		s_flags;
-	unsigned long		s_iflags;	/* internal SB_I_* flags */
-	unsigned long		s_magic;
-	struct dentry		*s_root;
-	struct rw_semaphore	s_umount;
-	int			s_count;
-	atomic_t		s_active;
-#ifdef CONFIG_SECURITY
-	void                    *s_security;
-#endif
-	const struct xattr_handler * const *s_xattr;
-#ifdef CONFIG_FS_ENCRYPTION
-	const struct fscrypt_operations	*s_cop;
-	struct fscrypt_keyring	*s_master_keys; /* master crypto keys in use */
-#endif
-#ifdef CONFIG_FS_VERITY
-	const struct fsverity_operations *s_vop;
-#endif
-#if IS_ENABLED(CONFIG_UNICODE)
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
-	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
-	struct mount		*s_mounts;	/* list of mounts; _not_ for fs use */
-	struct block_device	*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
-	struct file		*s_bdev_file;
-	struct backing_dev_info *s_bdi;
-	struct mtd_info		*s_mtd;
-	struct hlist_node	s_instances;
-	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
-	struct quota_info	s_dquot;	/* Diskquota specific options */
-
-	struct sb_writers	s_writers;
-
-	/*
-	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
-	 * s_fsnotify_info together for cache efficiency. They are frequently
-	 * accessed and rarely modified.
-	 */
-	void			*s_fs_info;	/* Filesystem private info */
-
-	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
-	u32			s_time_gran;
-	/* Time limits for c/m/atime in seconds */
-	time64_t		   s_time_min;
-	time64_t		   s_time_max;
-#ifdef CONFIG_FSNOTIFY
-	u32			s_fsnotify_mask;
-	struct fsnotify_sb_info	*s_fsnotify_info;
-#endif
-
-	/*
-	 * q: why are s_id and s_sysfs_name not the same? both are human
-	 * readable strings that identify the filesystem
-	 * a: s_id is allowed to change at runtime; it's used in log messages,
-	 * and we want to when a device starts out as single device (s_id is dev
-	 * name) but then a device is hot added and we have to switch to
-	 * identifying it by UUID
-	 * but s_sysfs_name is a handle for programmatic access, and can't
-	 * change at runtime
-	 */
-	char			s_id[32];	/* Informational name */
-	uuid_t			s_uuid;		/* UUID */
-	u8			s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
-
-	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
-	char			s_sysfs_name[UUID_STRING_LEN + 1];
-
-	unsigned int		s_max_links;
-	unsigned int		s_d_flags;	/* default d_flags for dentries */
-
-	/*
-	 * The next field is for VFS *only*. No filesystems have any business
-	 * even looking at it. You had been warned.
-	 */
-	struct mutex s_vfs_rename_mutex;	/* Kludge */
-
-	/*
-	 * Filesystem subtype.  If non-empty the filesystem type field
-	 * in /proc/mounts will be "type.subtype"
-	 */
-	const char *s_subtype;
-
-	const struct dentry_operations *__s_d_op; /* default d_op for dentries */
-
-	struct shrinker *s_shrink;	/* per-sb shrinker handle */
-
-	/* Number of inodes with nlink == 0 but still referenced */
-	atomic_long_t s_remove_count;
-
-	/* Read-only state of the superblock is being changed */
-	int s_readonly_remount;
-
-	/* per-sb errseq_t for reporting writeback errors via syncfs */
-	errseq_t s_wb_err;
-
-	/* AIO completions deferred from interrupt context */
-	struct workqueue_struct *s_dio_done_wq;
-	struct hlist_head s_pins;
-
-	/*
-	 * Owning user namespace and default context in which to
-	 * interpret filesystem uids, gids, quotas, device nodes,
-	 * xattrs and security labels.
-	 */
-	struct user_namespace *s_user_ns;
-
-	/*
-	 * The list_lru structure is essentially just a pointer to a table
-	 * of per-node lru lists, each of which has its own spinlock.
-	 * There is no need to put them into separate cachelines.
-	 */
-	struct list_lru		s_dentry_lru;
-	struct list_lru		s_inode_lru;
-	struct rcu_head		rcu;
-	struct work_struct	destroy_work;
-
-	struct mutex		s_sync_lock;	/* sync serialisation lock */
-
-	/*
-	 * Indicates how deep in a filesystem stack this SB is
-	 */
-	int s_stack_depth;
-
-	/* s_inode_list_lock protects s_inodes */
-	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
-	struct list_head	s_inodes;	/* all inodes */
-
-	spinlock_t		s_inode_wblist_lock;
-	struct list_head	s_inodes_wb;	/* writeback inodes */
-	long			s_min_writeback_pages;
-} __randomize_layout;
 
 static inline struct user_namespace *i_user_ns(const struct inode *inode)
 {
···
  * Snapshotting support.
  */
 
-/*
- * These are internal functions, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-static inline void __sb_end_write(struct super_block *sb, int level)
-{
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-
-static inline void __sb_start_write(struct super_block *sb, int level)
-{
-	percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true);
-}
-
-static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
-{
-	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
-}
-
-#define __sb_writers_acquired(sb, lev)	\
-	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
-#define __sb_writers_release(sb, lev)	\
-	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_)
-
-/**
- * __sb_write_started - check if sb freeze level is held
- * @sb: the super we write to
- * @level: the freeze level
- *
- * * > 0 - sb freeze level is held
- * *   0 - sb freeze level is not held
- * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
- */
-static inline int __sb_write_started(const struct super_block *sb, int level)
-{
-	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
-}
-
-/**
- * sb_write_started - check if SB_FREEZE_WRITE is held
- * @sb: the super we write to
- *
- * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
- */
-static inline bool sb_write_started(const struct super_block *sb)
-{
-	return __sb_write_started(sb, SB_FREEZE_WRITE);
-}
-
-/**
- * sb_write_not_started - check if SB_FREEZE_WRITE is not held
- * @sb: the super we write to
- *
- * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
- */
-static inline bool sb_write_not_started(const struct super_block *sb)
-{
-	return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
-}
-
 /**
  * file_write_started - check if SB_FREEZE_WRITE is held
  * @file: the file we write to
···
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return true;
 	return sb_write_not_started(file_inode(file)->i_sb);
-}
-
-/**
- * sb_end_write - drop write access to a superblock
- * @sb: the super we wrote to
- *
- * Decrement number of writers to the filesystem. Wake up possible waiters
- * wanting to freeze the filesystem.
- */
-static inline void sb_end_write(struct super_block *sb)
-{
-	__sb_end_write(sb, SB_FREEZE_WRITE);
-}
-
-/**
- * sb_end_pagefault - drop write access to a superblock from a page fault
- * @sb: the super we wrote to
- *
- * Decrement number of processes handling write page fault to the filesystem.
- * Wake up possible waiters wanting to freeze the filesystem.
- */
-static inline void sb_end_pagefault(struct super_block *sb)
-{
-	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
-}
-
-/**
- * sb_end_intwrite - drop write access to a superblock for internal fs purposes
- * @sb: the super we wrote to
- *
- * Decrement fs-internal number of writers to the filesystem.  Wake up possible
- * waiters wanting to freeze the filesystem.
- */
-static inline void sb_end_intwrite(struct super_block *sb)
-{
-	__sb_end_write(sb, SB_FREEZE_FS);
-}
-
-/**
- * sb_start_write - get write access to a superblock
- * @sb: the super we write to
- *
- * When a process wants to write data or metadata to a file system (i.e. dirty
- * a page or an inode), it should embed the operation in a sb_start_write() -
- * sb_end_write() pair to get exclusion against file system freezing. This
- * function increments number of writers preventing freezing. If the file
- * system is already frozen, the function waits until the file system is
- * thawed.
- *
- * Since freeze protection behaves as a lock, users have to preserve
- * ordering of freeze protection and other filesystem locks. Generally,
- * freeze protection should be the outermost lock. In particular, we have:
- *
- * sb_start_write
- *   -> i_rwsem			(write path, truncate, directory ops, ...)
- *   -> s_umount		(freeze_super, thaw_super)
- */
-static inline void sb_start_write(struct super_block *sb)
-{
-	__sb_start_write(sb, SB_FREEZE_WRITE);
-}
-
-static inline bool sb_start_write_trylock(struct super_block *sb)
-{
-	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
-}
-
-/**
- * sb_start_pagefault - get write access to a superblock from a page fault
- * @sb: the super we write to
- *
- * When a process starts handling write page fault, it should embed the
- * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
- * exclusion against file system freezing. This is needed since the page fault
- * is going to dirty a page. This function increments number of running page
- * faults preventing freezing. If the file system is already frozen, the
- * function waits until the file system is thawed.
- *
- * Since page fault freeze protection behaves as a lock, users have to preserve
- * ordering of freeze protection and other filesystem locks. It is advised to
- * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
- * handling code implies lock dependency:
- *
- * mmap_lock
- *   -> sb_start_pagefault
- */
-static inline void sb_start_pagefault(struct super_block *sb)
-{
-	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
-}
-
-/**
- * sb_start_intwrite - get write access to a superblock for internal fs purposes
- * @sb: the super we write to
- *
- * This is the third level of protection against filesystem freezing. It is
- * free for use by a filesystem. The only requirement is that it must rank
- * below sb_start_pagefault.
- *
- * For example filesystem can call sb_start_intwrite() when starting a
- * transaction which somewhat eases handling of freezing for internal sources
- * of filesystem changes (internal fs threads, discarding preallocation on file
- * close, etc.).
- */
-static inline void sb_start_intwrite(struct super_block *sb)
-{
-	__sb_start_write(sb, SB_FREEZE_FS);
-}
-
-static inline bool sb_start_intwrite_trylock(struct super_block *sb)
-{
-	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
 }
 
 bool inode_owner_or_capable(struct mnt_idmap *idmap,
···
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
-/**
- * enum freeze_holder - holder of the freeze
- * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
- * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
- * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
- * @FREEZE_EXCL: a freeze that can only be undone by the owner
- *
- * Indicate who the owner of the freeze or thaw request is and whether
- * the freeze needs to be exclusive or can nest.
- * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
- * same holder aren't allowed. It is however allowed to hold a single
- * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
- * the same time. This is relied upon by some filesystems during online
- * repair or similar.
- */
-enum freeze_holder {
-	FREEZE_HOLDER_KERNEL	= (1U << 0),
-	FREEZE_HOLDER_USERSPACE	= (1U << 1),
-	FREEZE_MAY_NEST		= (1U << 2),
-	FREEZE_EXCL		= (1U << 3),
-};
-
-struct super_operations {
-   	struct inode *(*alloc_inode)(struct super_block *sb);
-	void (*destroy_inode)(struct inode *);
-	void (*free_inode)(struct inode *);
-
-   	void (*dirty_inode) (struct inode *, int flags);
-	int (*write_inode) (struct inode *, struct writeback_control *wbc);
-	int (*drop_inode) (struct inode *);
-	void (*evict_inode) (struct inode *);
-	void (*put_super) (struct super_block *);
-	int (*sync_fs)(struct super_block *sb, int wait);
-	int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner);
-	int (*freeze_fs) (struct super_block *);
-	int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner);
-	int (*unfreeze_fs) (struct super_block *);
-	int (*statfs) (struct dentry *, struct kstatfs *);
-	int (*remount_fs) (struct super_block *, int *, char *);
-	void (*umount_begin) (struct super_block *);
-
-	int (*show_options)(struct seq_file *, struct dentry *);
-	int (*show_devname)(struct seq_file *, struct dentry *);
-	int (*show_path)(struct seq_file *, struct dentry *);
-	int (*show_stats)(struct seq_file *, struct dentry *);
-#ifdef CONFIG_QUOTA
-	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
-	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
-	struct dquot __rcu **(*get_dquots)(struct inode *);
-#endif
-	long (*nr_cached_objects)(struct super_block *,
-				  struct shrink_control *);
-	long (*free_cached_objects)(struct super_block *,
-				    struct shrink_control *);
-	/*
-	 * If a filesystem can support graceful removal of a device and
-	 * continue read-write operations, implement this callback.
-	 *
-	 * Return 0 if the filesystem can continue read-write.
-	 * Non-zero return value or no such callback means the fs will be shutdown
-	 * as usual.
-	 */
-	int (*remove_bdev)(struct super_block *sb, struct block_device *bdev);
-	void (*shutdown)(struct super_block *sb);
-};
-
 /*
  * Inode flags - they have no relation to superblock flags now
  */
···
  */
 #define __IS_FLG(inode, flg)	((inode)->i_sb->s_flags & (flg))
 
-static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
 #define IS_RDONLY(inode)	sb_rdonly((inode)->i_sb)
 #define IS_SYNC(inode)		(__IS_FLG(inode, SB_SYNCHRONOUS) || \
 					((inode)->i_flags & S_SYNC))
···
 extern int vfs_statfs(const struct path *, struct kstatfs *);
 extern int user_statfs(const char __user *, struct kstatfs *);
 extern int fd_statfs(int, struct kstatfs *);
-int freeze_super(struct super_block *super, enum freeze_holder who,
-		 const void *freeze_owner);
-int thaw_super(struct super_block *super, enum freeze_holder who,
-	       const void *freeze_owner);
 extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
···
 	vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
 	va_end(args);
 }
-
-extern int current_umask(void);
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
···
 
 #define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
-
-extern struct super_block *blockdev_superblock;
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
-}
 
 void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
···
 extern void inode_sb_list_add(struct inode *inode);
 extern void inode_lru_list_add(struct inode *inode);
 
-int sb_set_blocksize(struct super_block *sb, int size);
-int __must_check sb_min_blocksize(struct super_block *sb, int size);
-
 int generic_file_mmap(struct file *, struct vm_area_struct *);
 int generic_file_mmap_prepare(struct vm_area_desc *desc);
 int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
···
 	return true;
 }
 #endif
-
-static inline struct unicode_map *sb_encoding(const struct super_block *sb)
-{
-#if IS_ENABLED(CONFIG_UNICODE)
-	return sb->s_encoding;
-#else
-	return NULL;
-#endif
-}
-
-static inline bool sb_has_encoding(const struct super_block *sb)
-{
-	return !!sb_encoding(sb);
-}
-
-/*
- * Compare if two super blocks have the same encoding and flags
- */
-static inline bool sb_same_encoding(const struct super_block *sb1,
-				    const struct super_block *sb2)
-{
-#if IS_ENABLED(CONFIG_UNICODE)
-	if (sb1->s_encoding == sb2->s_encoding)
-		return true;
-
-	return (sb1->s_encoding && sb2->s_encoding &&
-	       (sb1->s_encoding->version == sb2->s_encoding->version) &&
-	       (sb1->s_encoding_flags == sb2->s_encoding_flags));
-#else
-	return true;
-#endif
-}
 
 int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid);

include/linux/fs/super.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FS_SUPER_H
+#define _LINUX_FS_SUPER_H
+
+#include <linux/fs/super_types.h>
+#include <linux/unicode.h>
+
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+	percpu_up_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+	percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
+
+#define __sb_writers_acquired(sb, lev) \
+	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev) - 1], 1, _THIS_IP_)
+#define __sb_writers_release(sb, lev) \
+	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev) - 1], _THIS_IP_)
+
+/**
+ * __sb_write_started - check if sb freeze level is held
+ * @sb: the super we write to
+ * @level: the freeze level
+ *
+ * * > 0 - sb freeze level is held
+ * *   0 - sb freeze level is not held
+ * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ */
+static inline int __sb_write_started(const struct super_block *sb, int level)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
+}
+
+/**
+ * sb_write_started - check if SB_FREEZE_WRITE is held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_not_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
+}
+
+/**
+ * sb_end_write - drop write access to a superblock
+ * @sb: the super we wrote to
+ *
+ * Decrement number of writers to the filesystem. Wake up possible waiters
+ * wanting to freeze the filesystem.
+ */
+static inline void sb_end_write(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_end_pagefault - drop write access to a superblock from a page fault
+ * @sb: the super we wrote to
+ *
+ * Decrement number of processes handling write page fault to the filesystem.
+ * Wake up possible waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_pagefault(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_end_intwrite - drop write access to a superblock for internal fs purposes
+ * @sb: the super we wrote to
+ *
+ * Decrement fs-internal number of writers to the filesystem.  Wake up possible
+ * waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_intwrite(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_FS);
+}
+
+/**
+ * sb_start_write - get write access to a superblock
+ * @sb: the super we write to
+ *
+ * When a process wants to write data or metadata to a file system (i.e. dirty
+ * a page or an inode), it should embed the operation in a sb_start_write() -
+ * sb_end_write() pair to get exclusion against file system freezing. This
+ * function increments number of writers preventing freezing. If the file
+ * system is already frozen, the function waits until the file system is
+ * thawed.
+ *
+ * Since freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. Generally,
+ * freeze protection should be the outermost lock. In particular, we have:
+ *
+ * sb_start_write
+ *   -> i_rwsem			(write path, truncate, directory ops, ...)
+ *   -> s_umount		(freeze_super, thaw_super)
+ */
+static inline void sb_start_write(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_WRITE);
+}
+
+static inline bool sb_start_write_trylock(struct super_block *sb)
+{
+	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_start_pagefault - get write access to a superblock from a page fault
+ * @sb: the super we write to
+ *
+ * When a process starts handling write page fault, it should embed the
+ * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
+ * exclusion against file system freezing. This is needed since the page fault
+ * is going to dirty a page. This function increments number of running page
+ * faults preventing freezing. If the file system is already frozen, the
+ * function waits until the file system is thawed.
+ *
+ * Since page fault freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. It is advised to
+ * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
+ * handling code implies lock dependency:
+ *
+ * mmap_lock
+ *   -> sb_start_pagefault
+ */
+static inline void sb_start_pagefault(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_start_intwrite - get write access to a superblock for internal fs purposes
+ * @sb: the super we write to
+ *
+ * This is the third level of protection against filesystem freezing. It is
+ * free for use by a filesystem. The only requirement is that it must rank
+ * below sb_start_pagefault.
+ *
+ * For example filesystem can call sb_start_intwrite() when starting a
+ * transaction which somewhat eases handling of freezing for internal sources
+ * of filesystem changes (internal fs threads, discarding preallocation on file
+ * close, etc.).
+ */
+static inline void sb_start_intwrite(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_FS);
+}
+
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
+{
+	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
+}
+
+static inline bool sb_rdonly(const struct super_block *sb)
+{
+	return sb->s_flags & SB_RDONLY;
+}
+
+static inline bool sb_is_blkdev_sb(struct super_block *sb)
+{
+	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
+}
+
+#if IS_ENABLED(CONFIG_UNICODE)
+static inline struct unicode_map *sb_encoding(const struct super_block *sb)
+{
+	return sb->s_encoding;
+}
+
+/* Compare if two super blocks have the same encoding and flags */
+static inline bool sb_same_encoding(const struct super_block *sb1,
+				    const struct super_block *sb2)
+{
+	if (sb1->s_encoding == sb2->s_encoding)
+		return true;
+
+	return (sb1->s_encoding && sb2->s_encoding &&
+		(sb1->s_encoding->version == sb2->s_encoding->version) &&
+		(sb1->s_encoding_flags == sb2->s_encoding_flags));
+}
+#else
+static inline struct unicode_map *sb_encoding(const struct super_block *sb)
+{
+	return NULL;
+}
+
+static inline bool sb_same_encoding(const struct super_block *sb1,
+				    const struct super_block *sb2)
+{
+	return true;
+}
+#endif
+
+static inline bool sb_has_encoding(const struct super_block *sb)
+{
+	return !!sb_encoding(sb);
+}
+
+int sb_set_blocksize(struct super_block *sb, int size);
+int __must_check sb_min_blocksize(struct super_block *sb, int size);
+
+int freeze_super(struct super_block *super, enum freeze_holder who,
+		 const void *freeze_owner);
+int thaw_super(struct super_block *super, enum freeze_holder who,
+	       const void *freeze_owner);
+
+#endif /* _LINUX_FS_SUPER_H */

include/linux/fs/super_types.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FS_SUPER_TYPES_H
+#define _LINUX_FS_SUPER_TYPES_H
+
+#include <linux/fs_dirent.h>
+#include <linux/errseq.h>
+#include <linux/list_lru.h>
+#include <linux/list.h>
+#include <linux/list_bl.h>
+#include <linux/llist.h>
+#include <linux/uidgid.h>
+#include <linux/uuid.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/workqueue_types.h>
+#include <linux/quota.h>
+
+struct backing_dev_info;
+struct block_device;
+struct dentry;
+struct dentry_operations;
+struct dquot_operations;
+struct export_operations;
+struct file;
+struct file_system_type;
+struct fscrypt_operations;
+struct fsnotify_sb_info;
+struct fsverity_operations;
+struct kstatfs;
+struct mount;
+struct mtd_info;
+struct quotactl_ops;
+struct shrinker;
+struct unicode_map;
+struct user_namespace;
+struct workqueue_struct;
+struct writeback_control;
+struct xattr_handler;
+
+extern struct super_block *blockdev_superblock;
+
+/* Possible states of 'frozen' field */
+enum {
+	SB_UNFROZEN		= 0,	/* FS is unfrozen */
+	SB_FREEZE_WRITE		= 1,	/* Writes, dir ops, ioctls frozen */
+	SB_FREEZE_PAGEFAULT	= 2,	/* Page faults stopped as well */
+	SB_FREEZE_FS		= 3,	/* For internal FS use (e.g. to stop internal threads if needed) */
+	SB_FREEZE_COMPLETE	= 4,	/* ->freeze_fs finished successfully */
+};
+
+#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
+
+struct sb_writers {
+	unsigned short			frozen;		/* Is sb frozen? */
+	int				freeze_kcount;	/* How many kernel freeze requests? */
+	int				freeze_ucount;	/* How many userspace freeze requests? */
+	const void			*freeze_owner;	/* Owner of the freeze */
+	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
+};
+
+/**
+ * enum freeze_holder - holder of the freeze
+ * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
+ * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
+ * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
+ * @FREEZE_EXCL: a freeze that can only be undone by the owner
+ *
+ * Indicate who the owner of the freeze or thaw request is and whether
+ * the freeze needs to be exclusive or can nest.
+ * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
+ * same holder aren't allowed. It is however allowed to hold a single
+ * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
+ * the same time. This is relied upon by some filesystems during online
+ * repair or similar.
+ */
+enum freeze_holder {
+	FREEZE_HOLDER_KERNEL	= (1U << 0),
+	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+	FREEZE_MAY_NEST		= (1U << 2),
+	FREEZE_EXCL		= (1U << 3),
+};
+
+struct super_operations {
+	struct inode *(*alloc_inode)(struct super_block *sb);
+	void (*destroy_inode)(struct inode *inode);
+	void (*free_inode)(struct inode *inode);
+	void (*dirty_inode)(struct inode *inode, int flags);
+	int (*write_inode)(struct inode *inode, struct writeback_control *wbc);
+	int (*drop_inode)(struct inode *inode);
+	void (*evict_inode)(struct inode *inode);
+	void (*put_super)(struct super_block *sb);
+	int (*sync_fs)(struct super_block *sb, int wait);
+	int (*freeze_super)(struct super_block *sb, enum freeze_holder who,
+			    const void *owner);
+	int (*freeze_fs)(struct super_block *sb);
+	int (*thaw_super)(struct super_block *sb, enum freeze_holder who,
+			  const void *owner);
+	int (*unfreeze_fs)(struct super_block *sb);
+	int (*statfs)(struct dentry *dentry, struct kstatfs *kstatfs);
+	int (*remount_fs) (struct super_block *, int *, char *);
+	void (*umount_begin)(struct super_block *sb);
+
+	int (*show_options)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_devname)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_path)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_stats)(struct seq_file *seq, struct dentry *dentry);
+#ifdef CONFIG_QUOTA
+	ssize_t (*quota_read)(struct super_block *sb, int type, char *data,
+			      size_t len, loff_t off);
+	ssize_t (*quota_write)(struct super_block *sb, int type,
+			       const char *data, size_t len, loff_t off);
+	struct dquot __rcu **(*get_dquots)(struct inode *inode);
+#endif
+	long (*nr_cached_objects)(struct super_block *sb,
+				  struct shrink_control *sc);
+	long (*free_cached_objects)(struct super_block *sb,
+				    struct shrink_control *sc);
+	/*
+	 * If a filesystem can support graceful removal of a device and
+	 * continue read-write operations, implement this callback.
+	 *
+	 * Return 0 if the filesystem can continue read-write.
+	 * Non-zero return value or no such callback means the fs will be shutdown
+	 * as usual.
+	 */
+	int (*remove_bdev)(struct super_block *sb, struct block_device *bdev);
+	void (*shutdown)(struct super_block *sb);
+};
+
+struct super_block {
+	struct list_head			s_list;		/* Keep this first */
+	dev_t					s_dev;		/* search index; _not_ kdev_t */
+	unsigned char				s_blocksize_bits;
+	unsigned long				s_blocksize;
+	loff_t					s_maxbytes;	/* Max file size */
+	struct file_system_type			*s_type;
+	const struct super_operations		*s_op;
+	const struct dquot_operations		*dq_op;
+	const struct quotactl_ops		*s_qcop;
+	const struct export_operations		*s_export_op;
+	unsigned long				s_flags;
+	unsigned long				s_iflags;	/* internal SB_I_* flags */
+	unsigned long				s_magic;
+	struct dentry				*s_root;
+	struct rw_semaphore			s_umount;
+	int					s_count;
+	atomic_t				s_active;
+#ifdef CONFIG_SECURITY
+	void					*s_security;
+#endif
+	const struct xattr_handler		*const *s_xattr;
+#ifdef CONFIG_FS_ENCRYPTION
+	const struct fscrypt_operations		*s_cop;
+	struct fscrypt_keyring			*s_master_keys; /* master crypto keys in use */
+#endif
+#ifdef CONFIG_FS_VERITY
+	const struct fsverity_operations	*s_vop;
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+	struct unicode_map			*s_encoding;
+	__u16					s_encoding_flags;
+#endif
+	struct hlist_bl_head			s_roots;	/* alternate root dentries for NFS */
+	struct mount				*s_mounts;	/* list of mounts; _not_ for fs use */
+	struct block_device			*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
+	struct file				*s_bdev_file;
+	struct backing_dev_info 		*s_bdi;
+	struct mtd_info				*s_mtd;
+	struct hlist_node			s_instances;
+	unsigned int				s_quota_types;	/* Bitmask of supported quota types */
+	struct quota_info			s_dquot;	/* Diskquota specific options */
+
+	struct sb_writers			s_writers;
+
+	/*
+	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
+	 * s_fsnotify_info together for cache efficiency. They are frequently
+	 * accessed and rarely modified.
+	 */
+	void					*s_fs_info;	/* Filesystem private info */
+
+	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
+	u32					s_time_gran;
+	/* Time limits for c/m/atime in seconds */
+	time64_t				s_time_min;
+	time64_t		   		s_time_max;
+#ifdef CONFIG_FSNOTIFY
+	u32					s_fsnotify_mask;
+	struct fsnotify_sb_info			*s_fsnotify_info;
+#endif
+
+	/*
+	 * q: why are s_id and s_sysfs_name not the same? both are human
+	 * readable strings that identify the filesystem
+	 * a: s_id is allowed to change at runtime; it's used in log messages,
+	 * and we want to when a device starts out as single device (s_id is dev
+	 * name) but then a device is hot added and we have to switch to
+	 * identifying it by UUID
+	 * but s_sysfs_name is a handle for programmatic access, and can't
+	 * change at runtime
+	 */
+	char					s_id[32];	/* Informational name */
+	uuid_t					s_uuid;		/* UUID */
+	u8					s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
+
+	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+	char					s_sysfs_name[UUID_STRING_LEN + 1];
+
+	unsigned int				s_max_links;
+	unsigned int				s_d_flags;	/* default d_flags for dentries */
+
+	/*
+	 * The next field is for VFS *only*. No filesystems have any business
+	 * even looking at it. You had been warned.
+	 */
+	struct mutex				s_vfs_rename_mutex;	/* Kludge */
+
+	/*
+	 * Filesystem subtype.  If non-empty the filesystem type field
+	 * in /proc/mounts will be "type.subtype"
+	 */
+	const char				*s_subtype;
+
+	const struct dentry_operations		*__s_d_op; /* default d_op for dentries */
+
+	struct shrinker				*s_shrink;	/* per-sb shrinker handle */
+
+	/* Number of inodes with nlink == 0 but still referenced */
+	atomic_long_t				s_remove_count;
+
+	/* Read-only state of the superblock is being changed */
+	int					s_readonly_remount;
+
+	/* per-sb errseq_t for reporting writeback errors via syncfs */
+	errseq_t s_wb_err;
+
+	/* AIO completions deferred from interrupt context */
+	struct workqueue_struct			*s_dio_done_wq;
+	struct hlist_head			s_pins;
+
+	/*
+	 * Owning user namespace and default context in which to
+	 * interpret filesystem uids, gids, quotas, device nodes,
+	 * xattrs and security labels.
+	 */
+	struct user_namespace			*s_user_ns;
+
+	/*
+	 * The list_lru structure is essentially just a pointer to a table
+	 * of per-node lru lists, each of which has its own spinlock.
+	 * There is no need to put them into separate cachelines.
+	 */
+	struct list_lru				s_dentry_lru;
+	struct list_lru				s_inode_lru;
+	struct rcu_head				rcu;
+	struct work_struct			destroy_work;
+
+	struct mutex				s_sync_lock;	/* sync serialisation lock */
+
+	/*
+	 * Indicates how deep in a filesystem stack this SB is
+	 */
+	int s_stack_depth;
+
+	/* s_inode_list_lock protects s_inodes */
+	spinlock_t				s_inode_list_lock ____cacheline_aligned_in_smp;
+	struct list_head			s_inodes;	/* all inodes */
+
+	spinlock_t				s_inode_wblist_lock;
+	struct list_head			s_inodes_wb;	/* writeback inodes */
+	long					s_min_writeback_pages;
+} __randomize_layout;
+
+/*
+ * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
+ * represented in both.
+ */
+#define SB_RDONLY       BIT(0)	/* Mount read-only */
+#define SB_NOSUID       BIT(1)	/* Ignore suid and sgid bits */
+#define SB_NODEV        BIT(2)	/* Disallow access to device special files */
+#define SB_NOEXEC       BIT(3)	/* Disallow program execution */
+#define SB_SYNCHRONOUS  BIT(4)	/* Writes are synced at once */
+#define SB_MANDLOCK     BIT(6)	/* Allow mandatory locks on an FS */
+#define SB_DIRSYNC      BIT(7)	/* Directory modifications are synchronous */
+#define SB_NOATIME      BIT(10)	/* Do not update access times. */
+#define SB_NODIRATIME   BIT(11)	/* Do not update directory access times */
+#define SB_SILENT       BIT(15)
+#define SB_POSIXACL     BIT(16)	/* Supports POSIX ACLs */
+#define SB_INLINECRYPT  BIT(17)	/* Use blk-crypto for encrypted files */
+#define SB_KERNMOUNT    BIT(22)	/* this is a kern_mount call */
+#define SB_I_VERSION    BIT(23)	/* Update inode I_version field */
+#define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define SB_DEAD         BIT(21)
+#define SB_DYING        BIT(24)
+#define SB_FORCE        BIT(27)
+#define SB_NOSEC        BIT(28)
+#define SB_BORN         BIT(29)
+#define SB_ACTIVE       BIT(30)
+#define SB_NOUSER       BIT(31)
+
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL		(1 << 0)
+#define SB_ENC_NO_COMPAT_FALLBACK_FL	(1 << 1)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
+#if IS_ENABLED(CONFIG_UNICODE)
+#define sb_no_casefold_compat_fallback(sb) \
+	(sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL)
+#else
+#define sb_no_casefold_compat_fallback(sb) (1)
+#endif
+
+/* sb->s_iflags */
+#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
+#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
+#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
+#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
+
+/* sb->s_iflags to limit user namespace mounts */
+#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
+#define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
+#define SB_I_UNTRUSTED_MOUNTER		0x00000040
+#define SB_I_EVM_HMAC_UNSUPPORTED	0x00000080
+
+#define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
+#define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
+#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
+#define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */
+#define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
+#define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
+#define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
+
+#endif /* _LINUX_FS_SUPER_TYPES_H */

include/linux/fs_struct.h

···
 #ifndef _LINUX_FS_STRUCT_H
 #define _LINUX_FS_STRUCT_H
 
+#include <linux/sched.h>
 #include <linux/path.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
···
 }
 
 extern bool current_chrooted(void);
+
+static inline int current_umask(void)
+{
+	return current->fs->umask;
+}
 
 #endif /* _LINUX_FS_STRUCT_H */

include/linux/fs_types.h include/linux/fs_dirent.h

···
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FS_TYPES_H
-#define _LINUX_FS_TYPES_H
+#ifndef _LINUX_FS_DIRENT_H
+#define _LINUX_FS_DIRENT_H
+
+#include <linux/stat.h>
+#include <linux/types.h>
 
 /*
  * This is a header for the common implementation of dirent
···
 
 /*
  * declarations for helper functions, accompanying implementation
- * is in fs/fs_types.c
+ * is in fs/fs_dirent.c
  */
 extern unsigned char fs_ftype_to_dtype(unsigned int filetype);
 extern unsigned char fs_umode_to_ftype(umode_t mode);
 extern unsigned char fs_umode_to_dtype(umode_t mode);
 
-#endif
+#endif /* _LINUX_FS_DIRENT_H */

include/linux/namei.h

···
 #include <linux/path.h>
 #include <linux/fcntl.h>
 #include <linux/errno.h>
+#include <linux/fs_struct.h>
 
 enum { MAX_NESTED_LINKS = 8 };