blob: b3b3d95eac2fba457b5c51991c2ac1f17bc9a15d [file] [log] [blame]
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_FS_H
#define _LINUX_FS_H
#include <linux/linkage.h>
#include <linux/wait_bit.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.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/rbtree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fcntl.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
#include <linux/delayed_call.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/android_kabi.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
#include <linux/android_vendor.h>
struct backing_dev_info;
struct bdi_writeback;
struct bio;
struct export_operations;
struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
struct fscrypt_info;
struct fscrypt_operations;
struct fsverity_info;
struct fsverity_operations;
struct fs_context;
struct fs_parameter_spec;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);
extern struct files_stat_struct files_stat;
extern unsigned long get_max_files(void);
extern unsigned int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
extern int sysctl_protected_fifos;
extern int sysctl_protected_regular;
typedef __kernel_rwf_t rwf_t;
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
#define MAY_READ 0x00000004
#define MAY_APPEND 0x00000008
#define MAY_ACCESS 0x00000010
#define MAY_OPEN 0x00000020
#define MAY_CHDIR 0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK 0x00000080
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
* to O_WRONLY and O_RDWR via the strange trick in do_dentry_open()
/* file is open for reading */
#define FMODE_READ ((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE ((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK ((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD ((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE ((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC ((__force fmode_t)0x20)
/* File is opened with O_NDELAY (only set for block devices) */
#define FMODE_NDELAY ((__force fmode_t)0x40)
/* File is opened with O_EXCL (only set for block devices) */
#define FMODE_EXCL ((__force fmode_t)0x80)
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
(specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH ((__force fmode_t)0x400)
* Don't update ctime and mtime.
* Currently a special hack for the XFS open_by_handle ioctl, but we'll
* hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
#define FMODE_NOCMTIME ((__force fmode_t)0x800)
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)0x1000)
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH ((__force fmode_t)0x4000)
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000)
/* Write access to underlying fs */
#define FMODE_WRITER ((__force fmode_t)0x10000)
/* Has read method(s) */
#define FMODE_CAN_READ ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE ((__force fmode_t)0x40000)
#define FMODE_OPENED ((__force fmode_t)0x80000)
#define FMODE_CREATED ((__force fmode_t)0x100000)
/* File is stream-like */
#define FMODE_STREAM ((__force fmode_t)0x200000)
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
/* File is capable of returning -EAGAIN if I/O will block */
#define FMODE_NOWAIT ((__force fmode_t)0x8000000)
/* File represents mount that needs unmounting */
#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000)
/* File does not contribute to nr_files count */
#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000)
/* File supports async buffered reads */
#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
#define ATTR_MODE (1 << 0)
#define ATTR_UID (1 << 1)
#define ATTR_GID (1 << 2)
#define ATTR_SIZE (1 << 3)
#define ATTR_ATIME (1 << 4)
#define ATTR_MTIME (1 << 5)
#define ATTR_CTIME (1 << 6)
#define ATTR_ATIME_SET (1 << 7)
#define ATTR_MTIME_SET (1 << 8)
#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
#define ATTR_KILL_SUID (1 << 11)
#define ATTR_KILL_SGID (1 << 12)
#define ATTR_FILE (1 << 13)
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
#define ATTR_TOUCH (1 << 17)
* Whiteout is represented by a char device. The following constants define the
* mode and device number to use.
#define WHITEOUT_DEV 0
* This is the Inode Attributes structure, used for notify_change(). It
* uses the above definitions as flags, to know which values have changed.
* Also, in this manner, a Filesystem can look at only the values it cares
* about. Basically, these are the attributes that the VFS layer can
* request to change from the FS layer.
* Derek Atkins <warlord@MIT.EDU> 94-10-20
struct iattr {
unsigned int ia_valid;
umode_t ia_mode;
kuid_t ia_uid;
kgid_t ia_gid;
loff_t ia_size;
struct timespec64 ia_atime;
struct timespec64 ia_mtime;
struct timespec64 ia_ctime;
* Not an attribute, but an auxiliary info for filesystems wanting to
* implement an ftruncate() like method. NOTE: filesystem should
* check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
struct file *ia_file;
* Includes for diskquotas.
#include <linux/quota.h>
* Maximum number of layers of fs stack. Needs to be limited to
* prevent kernel stack overflow
* enum positive_aop_returns - aop return codes with specific semantics
* @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
* completed, that the page is still locked, and
* should be considered active. The VM uses this hint
* to return the page to the active list -- it won't
* be a candidate for writeback again in the near
* future. Other callers must be careful to unlock
* the page if they get this return. Returned by
* writepage();
* @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
* unlocked it and the page might have been truncated.
* The caller should back up to acquiring a new page and
* trying again. The aop will be taking reasonable
* precautions not to livelock. If the caller held a page
* reference, it should drop it before retrying. Returned
* by readpage().
* address_space_operation functions return these large constants to indicate
* special semantics to the caller. These are much larger than the bytes in a
* page to allow for functions that return the number of bytes operated on in a
* given page.
enum positive_aop_returns {
#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */
#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct
* helper code (eg buffer layer)
* to clear GFP_FS from alloc */
* oh the beauties of C type declarations.
struct page;
struct address_space;
struct writeback_control;
struct readahead_control;
* Write life time hint values.
* Stored in struct inode as u8.
enum rw_hint {
/* Match RWF_* bits to IOCB bits */
#define IOCB_HIPRI (__force int) RWF_HIPRI
#define IOCB_DSYNC (__force int) RWF_DSYNC
#define IOCB_SYNC (__force int) RWF_SYNC
#define IOCB_NOWAIT (__force int) RWF_NOWAIT
#define IOCB_APPEND (__force int) RWF_APPEND
/* non-RWF related bits - start at 16 */
#define IOCB_EVENTFD (1 << 16)
#define IOCB_DIRECT (1 << 17)
#define IOCB_WRITE (1 << 18)
/* iocb->ki_waitq is valid */
#define IOCB_WAITQ (1 << 19)
#define IOCB_NOIO (1 << 20)
struct kiocb {
struct file *ki_filp;
/* The 'ki_filp' pointer is shared in a union for aio */
loff_t ki_pos;
void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
void *private;
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
union {
unsigned int ki_cookie; /* for ->iopoll */
struct wait_page_queue *ki_waitq; /* for async buffered IO */
static inline bool is_sync_kiocb(struct kiocb *kiocb)
return kiocb->ki_complete == NULL;
* "descriptor" for what we're up to with a read.
* This allows us to use the same read code yet
* have multiple different users of the data that
* we read from a file.
* The simplest case just copies the data to user
* mode.
typedef struct {
size_t written;
size_t count;
union {
char __user *buf;
void *data;
} arg;
int error;
} read_descriptor_t;
typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
unsigned long, unsigned long);
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
/* Set a page dirty. Return true if this dirtied it */
int (*set_page_dirty)(struct page *page);
* Reads in the requested pages. Unlike ->readpage(), this is
* PURELY used for read-ahead!.
int (*readpages)(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
void (*readahead)(struct readahead_control *);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
int (*write_end)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
sector_t (*bmap)(struct address_space *, sector_t);
void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
* migrate the contents of a page to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
int (*migratepage) (struct address_space *,
struct page *, struct page *, enum migrate_mode);
bool (*isolate_page)(struct page *, isolate_mode_t);
void (*putback_page)(struct page *);
int (*launder_page) (struct page *);
int (*is_partially_uptodate) (struct page *, unsigned long,
unsigned long);
void (*is_dirty_writeback) (struct page *, bool *, bool *);
int (*error_remove_page)(struct address_space *, struct page *);
/* swapfile support */
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
sector_t *span);
void (*swap_deactivate)(struct file *file);
extern const struct address_space_operations empty_aops;
* pagecache_write_begin/pagecache_write_end must be used by general code
* to write into the pagecache.
int pagecache_write_begin(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
int pagecache_write_end(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
* struct address_space - Contents of a cacheable, mappable object.
* @host: Owner, either the inode or the block_device.
* @i_pages: Cached pages.
* @gfp_mask: Memory allocation flags to use for allocating pages.
* @i_mmap_writable: Number of VM_SHARED mappings.
* @nr_thps: Number of THPs in the pagecache (non-shmem only).
* @i_mmap: Tree of private and shared mappings.
* @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
* @nrpages: Number of page entries, protected by the i_pages lock.
* @nrexceptional: Shadow or DAX entries, protected by the i_pages lock.
* @writeback_index: Writeback starts here.
* @a_ops: Methods.
* @flags: Error bits and flags (AS_*).
* @wb_err: The most recent error which has occurred.
* @private_lock: For use by the owner of the address_space.
* @private_list: For use by the owner of the address_space.
* @private_data: For use by the owner of the address_space.
struct address_space {
struct inode *host;
struct xarray i_pages;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
/* number of thp, only for non-shmem files */
atomic_t nr_thps;
struct rb_root_cached i_mmap;
struct rw_semaphore i_mmap_rwsem;
unsigned long nrpages;
unsigned long nrexceptional;
pgoff_t writeback_index;
const struct address_space_operations *a_ops;
unsigned long flags;
errseq_t wb_err;
spinlock_t private_lock;
struct list_head private_list;
void *private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
* On most architectures that alignment is already the case; but
* must be enforced here for CRIS, to let the least significant bit
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
/* XArray tags, for tagging dirty and writeback pages in the pagecache. */
* Returns true if any of the pages in the mapping are marked with the tag.
static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
return xa_marked(&mapping->i_pages, tag);
static inline void i_mmap_lock_write(struct address_space *mapping)
static inline int i_mmap_trylock_write(struct address_space *mapping)
return down_write_trylock(&mapping->i_mmap_rwsem);
static inline void i_mmap_unlock_write(struct address_space *mapping)
static inline void i_mmap_lock_read(struct address_space *mapping)
static inline void i_mmap_unlock_read(struct address_space *mapping)
static inline void i_mmap_assert_locked(struct address_space *mapping)
static inline void i_mmap_assert_write_locked(struct address_space *mapping)
* Might pages of this file be mapped into userspace?
static inline int mapping_mapped(struct address_space *mapping)
return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
* Might pages of this file have been modified in userspace?
* Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap
* marks vma as VM_SHARED if it is shared, and the file was opened for
* writing i.e. vma may be mprotected writable even if now readonly.
* If i_mmap_writable is negative, no new writable mappings are allowed. You
* can only deny writable mappings, if none exists right now.
static inline int mapping_writably_mapped(struct address_space *mapping)
return atomic_read(&mapping->i_mmap_writable) > 0;
static inline int mapping_map_writable(struct address_space *mapping)
return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
0 : -EPERM;
static inline void mapping_unmap_writable(struct address_space *mapping)
static inline int mapping_deny_writable(struct address_space *mapping)
return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
0 : -EBUSY;
static inline void mapping_allow_writable(struct address_space *mapping)
* Use sequence counter to get consistent i_size on 32-bit processors.
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#define i_size_ordered_init(inode) do { } while (0)
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
#define ACL_DONT_CACHE ((void *)(-3))
static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
return (void *)task + 1;
static inline bool
is_uncached_acl(struct posix_acl *acl)
return (long)acl & 1;
#define IOP_FASTPERM 0x0001
#define IOP_LOOKUP 0x0002
#define IOP_NOFOLLOW 0x0004
#define IOP_XATTR 0x0008
struct fsnotify_mark_connector;
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
struct inode {
umode_t i_mode;
unsigned short i_opflags;
kuid_t i_uid;
kgid_t i_gid;
unsigned int i_flags;
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
void *i_security;
/* Stat data, not accessed from path walking */
unsigned long i_ino;
* Filesystems may only read i_nlink directly. They shall use the
* following functions for modification:
* (set|clear|inc|drop)_nlink
* inode_(inc|dec)_link_count
union {
const unsigned int i_nlink;
unsigned int __i_nlink;
dev_t i_rdev;
loff_t i_size;
struct timespec64 i_atime;
struct timespec64 i_mtime;
struct timespec64 i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
u8 i_write_hint;
blkcnt_t i_blocks;
seqcount_t i_size_seqcount;
/* Misc */
unsigned long i_state;
struct rw_semaphore i_rwsem;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_io_list; /* backing dev IO list */
struct bdi_writeback *i_wb; /* the associated cgroup wb */
/* foreign inode detection, see wbc_detach_inode() */
int i_wb_frn_winner;
u16 i_wb_frn_avg_time;
u16 i_wb_frn_history;
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
struct list_head i_wb_list; /* backing dev writeback list */
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
atomic64_t i_version;
atomic64_t i_sequence; /* see futex */
atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
atomic_t i_readcount; /* struct files open RO */
union {
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
void (*free_inode)(struct inode *);
struct file_lock_context *i_flctx;
struct address_space i_data;
struct list_head i_devices;
union {
struct pipe_inode_info *i_pipe;
struct block_device *i_bdev;
struct cdev *i_cdev;
char *i_link;
unsigned i_dir_seq;
__u32 i_generation;
__u32 i_fsnotify_mask; /* all events this inode cares about */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
struct fscrypt_info *i_crypt_info;
struct fsverity_info *i_verity_info;
void *i_private; /* fs or device private pointer */
} __randomize_layout;
struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode);
static inline unsigned int i_blocksize(const struct inode *node)
return (1 << node->i_blkbits);
static inline int inode_unhashed(struct inode *inode)
return hlist_unhashed(&inode->i_hash);
* __mark_inode_dirty expects inodes to be hashed. Since we don't
* want special inodes in the fileset inode space, we make them
* appear hashed, but do not put on any lists. hlist_del()
* will work fine and require no locking.
static inline void inode_fake_hash(struct inode *inode)
* inode->i_mutex nesting subclasses for the lock validator:
* 0: the object of the current VFS operation
* 1: parent
* 2: child/target
* 3: xattr
* 4: second non-directory
* 5: second parent (when locking independent directories in rename)
* I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
* non-directories at once.
* The locking order between these classes is
* parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
enum inode_i_mutex_lock_class
static inline void inode_lock(struct inode *inode)
static inline void inode_unlock(struct inode *inode)
static inline void inode_lock_shared(struct inode *inode)
static inline void inode_unlock_shared(struct inode *inode)
static inline int inode_trylock(struct inode *inode)
return down_write_trylock(&inode->i_rwsem);
static inline int inode_trylock_shared(struct inode *inode)
return down_read_trylock(&inode->i_rwsem);
static inline int inode_is_locked(struct inode *inode)
return rwsem_is_locked(&inode->i_rwsem);
static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
down_write_nested(&inode->i_rwsem, subclass);
static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass)
down_read_nested(&inode->i_rwsem, subclass);
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
* with respect to the local cpu (unlike with preempt disabled),
* but they don't need to be atomic with respect to other cpus like in
* true SMP (so they need either to either locally disable irq around
* the read or for example on x86 they can be still implemented as a
* cmpxchg8b without the need of the lock prefix). For SMP compiles
* and 64bit archs it makes no difference if preempt is enabled or not.
static inline loff_t i_size_read(const struct inode *inode)
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
loff_t i_size;
unsigned int seq;
do {
seq = read_seqcount_begin(&inode->i_size_seqcount);
i_size = inode->i_size;
} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
return i_size;
loff_t i_size;
i_size = inode->i_size;
return i_size;
return inode->i_size;
* NOTE: unlike i_size_read(), i_size_write() does need locking around it
* (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
* can be lost, resulting in subsequent i_size_read() calls spinning forever.
static inline void i_size_write(struct inode *inode, loff_t i_size)
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
inode->i_size = i_size;
inode->i_size = i_size;
inode->i_size = i_size;
static inline unsigned iminor(const struct inode *inode)
return MINOR(inode->i_rdev);
static inline unsigned imajor(const struct inode *inode)
return MAJOR(inode->i_rdev);
struct fown_struct {
rwlock_t lock; /* protects pid, uid, euid fields */
struct pid *pid; /* pid or -pgrp where SIGIO should be sent */
enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */
kuid_t uid, euid; /* uid/euid of process setting the owner */
int signum; /* posix.1b rt signal to be delivered on IO */
* Track a single file's readahead state
struct file_ra_state {
pgoff_t start; /* where readahead started */
unsigned int size; /* # of readahead pages */
unsigned int async_size; /* do asynchronous readahead when
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
* Check if @index falls in the readahead windows.
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
return (index >= ra->start &&
index < ra->start + ra->size);
struct file {
union {
struct llist_node fu_llist;
struct rcu_head fu_rcuhead;
} f_u;
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
* Protects f_ep_links, f_flags.
* Must not be taken from IRQ context.
spinlock_t f_lock;
enum rw_hint f_write_hint;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
struct mutex f_pos_lock;
loff_t f_pos;
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
u64 f_version;
void *f_security;
/* needed for tty driver, and maybe others */
void *private_data;
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
errseq_t f_sb_err; /* for syncfs */
} __randomize_layout
__attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
__u32 handle_bytes;
int handle_type;
/* file identifier */
unsigned char f_handle[];
static inline struct file *get_file(struct file *f)
return f;
#define get_file_rcu_many(x, cnt) \
atomic_long_add_unless(&(x)->f_count, (cnt), 0)
#define get_file_rcu(x) get_file_rcu_many((x), 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
#define MAX_NON_LFS ((1UL<<31) - 1)
/* Page cache limit. The filesystems should put that into their s_maxbytes
limits, otherwise bad things can happen in VM. */
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX)
#define FL_POSIX 1
#define FL_FLOCK 2
#define FL_DELEG 4 /* NFSv4 delegation */
#define FL_ACCESS 8 /* not trying to lock, just looking */
#define FL_EXISTS 16 /* when unlocking, test for existence */
#define FL_LEASE 32 /* lease held on this file */
#define FL_CLOSE 64 /* unlock on close */
#define FL_SLEEP 128 /* A blocking lock */
#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING 512 /* Lease is being broken */
#define FL_OFDLCK 1024 /* lock is "owned" by struct file */
#define FL_LAYOUT 2048 /* outstanding pNFS layout */
* Special return value from posix_lock_file() and vfs_lock_file() for
* asynchronous locking.
/* legacy typedef, should eventually be removed */
typedef void *fl_owner_t;
struct file_lock;
struct file_lock_operations {
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
struct lock_manager_operations {
fl_owner_t (*lm_get_owner)(fl_owner_t);
void (*lm_put_owner)(fl_owner_t);
void (*lm_notify)(struct file_lock *); /* unblock callback */
int (*lm_grant)(struct file_lock *, int);
bool (*lm_break)(struct file_lock *);
int (*lm_change)(struct file_lock *, int, struct list_head *);
void (*lm_setup)(struct file_lock *, void **);
bool (*lm_breaker_owns_lease)(struct file_lock *);
struct lock_manager {
struct list_head list;
* NFSv4 and up also want opens blocked during the grace period;
* NLM doesn't care:
bool block_opens;
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
void locks_end_grace(struct lock_manager *);
bool locks_in_grace(struct net *);
bool opens_in_grace(struct net *);
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>
* struct file_lock represents a generic "file lock". It's used to represent
* POSIX byte range locks, BSD (flock) locks, and leases. It's important to
* note that the same struct is used to represent both a request for a lock and
* the lock itself, but the same object is never used for both.
* FIXME: should we create a separate "struct lock_request" to help distinguish
* these two uses?
* The varous i_flctx lists are ordered by:
* 1) lock owner
* 2) lock range start
* 3) lock range end
* Obviously, the last two criteria only matter for POSIX locks.
struct file_lock {
struct file_lock *fl_blocker; /* The lock, that is blocking us */
struct list_head fl_list; /* link into file_lock_context */
struct hlist_node fl_link; /* node in global lists */
struct list_head fl_blocked_requests; /* list of requests with
* ->fl_blocker pointing here
struct list_head fl_blocked_member; /* node in
* ->fl_blocker->fl_blocked_requests
fl_owner_t fl_owner;
unsigned int fl_flags;
unsigned char fl_type;
unsigned int fl_pid;
int fl_link_cpu; /* what cpu's list is this on? */
wait_queue_head_t fl_wait;
struct file *fl_file;
loff_t fl_start;
loff_t fl_end;
struct fasync_struct * fl_fasync; /* for lease break notifications */
/* for lease breaks: */
unsigned long fl_break_time;
unsigned long fl_downgrade_time;
const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
union {
struct nfs_lock_info nfs_fl;
struct nfs4_lock_info nfs4_fl;
struct {
struct list_head link; /* link in AFS vnode's pending_locks list */
int state; /* state of grant or error if -ve */
unsigned int debug_id;
} afs;
} fl_u;
struct list_head android_reserved1; /* not a macro as we might just need it as-is */
} __randomize_layout;
struct file_lock_context {
spinlock_t flc_lock;
struct list_head flc_flock;
struct list_head flc_posix;
struct list_head flc_lease;
/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX INT_LIMIT(loff_t)
extern void send_sigio(struct fown_struct *fown, int fd, int band);
#define locks_inode(f) file_inode(f)
extern int fcntl_getlk(struct file *, unsigned int, struct flock *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
struct flock *);
#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *);
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
struct flock64 *);
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);
/* fs/locks.c */
void locks_free_lock_context(struct inode *inode);
void locks_free_lock(struct file_lock *fl);
extern void locks_init_lock(struct file_lock *);
extern struct file_lock * locks_alloc_lock(void);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_file(struct file *);
extern void locks_release_private(struct file_lock *);
extern void posix_test_lock(struct file *, struct file_lock *);
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
extern int locks_delete_block(struct file_lock *);
extern int vfs_test_lock(struct file *, struct file_lock *);
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
extern void lease_get_mtime(struct inode *, struct timespec64 *time);
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
extern int lease_modify(struct file_lock *, int, struct list_head *);
struct notifier_block;
extern int lease_register_notifier(struct notifier_block *);
extern void lease_unregister_notifier(struct notifier_block *);
struct files_struct;
extern void show_fd_locks(struct seq_file *f,
struct file *filp, struct files_struct *files);
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
struct flock __user *user)
return -EINVAL;
static inline int fcntl_setlk(unsigned int fd, struct file *file,
unsigned int cmd, struct flock __user *user)
return -EACCES;
#if BITS_PER_LONG == 32
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
struct flock64 __user *user)
return -EINVAL;
static inline int fcntl_setlk64(unsigned int fd, struct file *file,
unsigned int cmd, struct flock64 __user *user)
return -EACCES;
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
return -EINVAL;
static inline int fcntl_getlease(struct file *filp)
return F_UNLCK;
static inline void
locks_free_lock_context(struct inode *inode)
static inline void locks_init_lock(struct file_lock *fl)
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
static inline void locks_remove_file(struct file *filp)
static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
struct file_lock *conflock)
return -ENOLCK;
static inline int locks_delete_block(struct file_lock *waiter)
return -ENOENT;
static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
return 0;
static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
struct file_lock *fl, struct file_lock *conf)
return -ENOLCK;
static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
return 0;
static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl)
return -ENOLCK;
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
return 0;
static inline void lease_get_mtime(struct inode *inode,
struct timespec64 *time)
static inline int generic_setlease(struct file *filp, long arg,
struct file_lock **flp, void **priv)
return -EINVAL;
static inline int vfs_setlease(struct file *filp, long arg,
struct file_lock **lease, void **priv)
return -EINVAL;
static inline int lease_modify(struct file_lock *fl, int arg,
struct list_head *dispose)
return -EINVAL;
struct files_struct;
static inline void show_fd_locks(struct seq_file *f,
struct file *filp, struct files_struct *files) {}
static inline struct inode *file_inode(const struct file *f)
return f->f_inode;
static inline struct dentry *file_dentry(const struct file *file)
return d_real(file->f_path.dentry, file_inode(file));
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
return locks_lock_inode_wait(locks_inode(filp), fl);
struct fasync_struct {
rwlock_t fa_lock;
int magic;
int fa_fd;
struct fasync_struct *fa_next; /* singly linked list */
struct file *fa_file;
struct rcu_head fa_rcu;
#define FASYNC_MAGIC 0x4601
/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);
* sb->s_flags. Note that these mirror the equivalent MS_* flags where
* represented in both.
#define SB_RDONLY 1 /* Mount read-only */
#define SB_NOSUID 2 /* Ignore suid and sgid bits */
#define SB_NODEV 4 /* Disallow access to device special files */
#define SB_NOEXEC 8 /* Disallow program execution */
#define SB_SYNCHRONOUS 16 /* Writes are synced at once */
#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */
#define SB_DIRSYNC 128 /* Directory modifications are synchronous */
#define SB_NOATIME 1024 /* Do not update access times. */
#define SB_NODIRATIME 2048 /* Do not update directory access times */
#define SB_SILENT 32768
#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */
#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */
#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define SB_I_VERSION (1<<23) /* Update inode I_version field */
#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */
/* These sb flags are internal to the kernel */
#define SB_SUBMOUNT (1<<26)
#define SB_FORCE (1<<27)
#define SB_NOSEC (1<<28)
#define SB_BORN (1<<29)
#define SB_ACTIVE (1<<30)
#define SB_NOUSER (1<<31)
/* These flags relate to encoding and casefolding */
#define SB_ENC_STRICT_MODE_FL (1 << 0)
#define sb_has_strict_encoding(sb) \
(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
* Umount options
#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */
#define MNT_DETACH 0x00000002 /* Just detach from the tree */
#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_UNTRUSTED_MOUNTER 0x00000040
#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */
/* 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 */
struct sb_writers {
int frozen; /* Is sb frozen? */
wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
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;
void *s_security;
const struct xattr_handler **s_xattr;
const struct fscrypt_operations *s_cop;
struct key *s_master_keys; /* master crypto keys in use */
const struct fsverity_operations *s_vop;
struct unicode_map *s_encoding;
__u16 s_encoding_flags;
struct hlist_bl_head s_roots; /* alternate root dentries for NFS */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev;
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_marks 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;
__u32 s_fsnotify_mask;
struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
char s_id[32]; /* Informational name */
uuid_t s_uuid; /* UUID */
unsigned int s_max_links;
fmode_t s_mode;
* 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 */
* Saved pool identifier for cleancache (-1 means none)
int cleancache_poolid;
struct shrinker s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
/* Pending fsnotify inode refs */
atomic_long_t s_fsnotify_inode_refs;
/* Being remounted read-only */
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 */
} __randomize_layout;
/* Helper functions so that in most cases filesystems will
* not need to deal directly with kuid_t and kgid_t and can
* instead deal with the raw numeric values that are stored
* in the filesystem.
static inline uid_t i_uid_read(const struct inode *inode)
return from_kuid(inode->i_sb->s_user_ns, inode->i_uid);
static inline gid_t i_gid_read(const struct inode *inode)
return from_kgid(inode->i_sb->s_user_ns, inode->i_gid);
static inline void i_uid_write(struct inode *inode, uid_t uid)
inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid);
static inline void i_gid_write(struct inode *inode, gid_t gid)
inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
extern struct timespec64 current_time(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(sb->s_writers.rw_sem + level - 1);
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], 1, _THIS_IP_)
* 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_mutex (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);
extern bool inode_owner_or_capable(const struct inode *inode);
* VFS helper functions..
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry)
return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
int open_flag);
int vfs_mkobj(struct dentry *, umode_t,
int (*f)(struct dentry *, umode_t, void *),
void *);
int vfs_fchown(struct file *file, uid_t user, gid_t group);
int vfs_fchmod(struct file *file, umode_t mode);
int vfs_utimes(const struct path *path, struct timespec64 *times);
extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
#define compat_ptr_ioctl NULL
* VFS file helper functions.
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
umode_t mode);
extern bool may_open_dev(const struct path *path);
* This is the "filldir" function type, used by readdir() to let
* the kernel specify what kind of dirent layout it wants to have.
* This allows the kernel to read directories into kernel space or
* to have different dirent layouts depending on the binary type.
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
struct dir_context {
filldir_t actor;
loff_t pos;
* These flags let !MMU mmap() govern direct device mapping vs immediate
* copying more easily for MAP_PRIVATE, especially for ROM filesystems.
* NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE)
* NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED)
* NOMMU_MAP_READ: Can be mapped for reading
* NOMMU_MAP_WRITE: Can be mapped for writing
* NOMMU_MAP_EXEC: Can be mapped for execution
#define NOMMU_MAP_COPY 0x00000001
#define NOMMU_MAP_DIRECT 0x00000008
* These flags control the behavior of the remap_file_range function pointer.
* If it is called with len == 0 that means "remap to end of source file".
* See Documentation/filesystems/vfs.rst for more details about this call.
* REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
* REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request
#define REMAP_FILE_DEDUP (1 << 0)
#define REMAP_FILE_CAN_SHORTEN (1 << 1)
* These flags signal that the caller is ok with altering various aspects of
* the behavior of the remap operation. The changes must be made by the
* implementation; the vfs remap helper functions can take advantage of them.
* Flags in this category exist to preserve the quirky behavior of the hoisted
* btrfs clone/dedupe ioctls.
struct iov_iter;
struct file_operations {
struct module *owner;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iopoll)(struct kiocb *kiocb, bool spin);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
unsigned long mmap_supported_flags;
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
int (*flock) (struct file *, int, struct file_lock *);
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
int (*setlease)(struct file *, long, struct file_lock **, void **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
void (*show_fdinfo)(struct seq_file *m, struct file *f);
#ifndef CONFIG_MMU
unsigned (*mmap_capabilities)(struct file *);
ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
loff_t, size_t, unsigned int);
loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
int (*fadvise)(struct file *, loff_t, loff_t, int);
} __randomize_layout;
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
int (*permission) (struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
int (*create) (struct inode *,struct dentry *, umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
int (*mkdir) (struct inode *,struct dentry *,umode_t);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, struct timespec64 *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
umode_t create_mode);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
int (*set_acl)(struct inode *, struct posix_acl *, int);
} ____cacheline_aligned;
static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
struct iov_iter *iter)
return file->f_op->read_iter(kio, iter);
static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
struct iov_iter *iter)
return file->f_op->write_iter(kio, iter);
static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
return file->f_op->mmap(file, vma);
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t len, unsigned int flags);
extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *count,
unsigned int remap_flags);
extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t len, unsigned int remap_flags);
extern int vfs_dedupe_file_range(struct file *file,
struct file_dedupe_range *same);
extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
struct file *dst_file, loff_t dst_pos,
loff_t len, unsigned int remap_flags);
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 *);
int (*freeze_fs) (struct super_block *);
int (*thaw_super) (struct super_block *);
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 *);
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 **(*get_dquots)(struct inode *);
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
long (*nr_cached_objects)(struct super_block *,
struct shrink_control *);
long (*free_cached_objects)(struct super_block *,
struct shrink_control *);
* Inode flags - they have no relation to superblock flags now
#define S_SYNC (1 << 0) /* Writes are synced at once */
#define S_NOATIME (1 << 1) /* Do not update access times */
#define S_APPEND (1 << 2) /* Append-only file */
#define S_IMMUTABLE (1 << 3) /* Immutable file */
#define S_DEAD (1 << 4) /* removed, but still open directory */
#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */
#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */
#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */
#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE (1 << 9) /* Inode is fs-internal */
#define S_IMA (1 << 10) /* Inode has an associated IMA struct */
#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */
#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */
#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */
#define S_DAX 0 /* Make all the DAX code disappear */
#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */
#define S_CASEFOLD (1 << 15) /* Casefolded file */
#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */
* Note that nosuid etc flags are inode-specific: setting some file-system
* flags just means all the inodes inherit those flags by default. It might be
* possible to override it selectively if you really wanted to with some
* ioctl() that is not currently implemented.
* Exception: SB_RDONLY is always applied to the entire file system.
* Unfortunately, it is possible to change a filesystems flags with it mounted
* with files in use. This means that all of the inodes will not have their
* i_flags updated. Hence, i_flags no longer inherit the superblock mount
* flags, so these have to be checked separately. --
#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))
#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK)
#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME)
#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE)
#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL)
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
#define IS_DAX(inode) ((inode)->i_flags & S_DAX)
#define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED)
#define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD)
#define IS_VERITY(inode) ((inode)->i_flags & S_VERITY)
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
static inline bool HAS_UNMAPPED_ID(struct inode *inode)
return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid);
static inline enum rw_hint file_write_hint(struct file *file)
if (file->f_write_hint != WRITE_LIFE_NOT_SET)
return file->f_write_hint;
return file_inode(file)->i_write_hint;
static inline int iocb_flags(struct file *file);
static inline u16 ki_hint_validate(enum rw_hint hint)
typeof(((struct kiocb *)0)->ki_hint) max_hint = -1;
if (hint <= max_hint)
return hint;
return 0;
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
*kiocb = (struct kiocb) {
.ki_filp = filp,
.ki_flags = iocb_flags(filp),
.ki_hint = ki_hint_validate(file_write_hint(filp)),
.ki_ioprio = get_current_ioprio(),
static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
struct file *filp)
*kiocb = (struct kiocb) {
.ki_filp = filp,
.ki_flags = kiocb_src->ki_flags,
.ki_hint = kiocb_src->ki_hint,
.ki_ioprio = kiocb_src->ki_ioprio,
.ki_pos = kiocb_src->ki_pos,
* Inode state bits. Protected by inode->i_lock
* Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
* Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
* until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
* various stages of removing an inode.
* Two bits are used for locking and completion notification, I_NEW and I_SYNC.
* I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
* fdatasync(). i_atime is the usual cause.
* I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
* these changes separately from I_DIRTY_SYNC so that we
* don't have to write inode on fdatasync() when only
* mtime has changed in it.
* I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
* I_NEW Serves as both a mutex and completion notification.
* New inodes set I_NEW. If two processes both create
* the same inode, one of them will release its inode and
* wait for I_NEW to be released before returning.
* Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
* also cause waiting on I_NEW, without I_NEW actually
* being set. find_inode() uses this to prevent returning
* nearly-dead inodes.
* I_WILL_FREE Must be set when calling write_inode_now() if i_count
* is zero. I_FREEING must be set when I_WILL_FREE is
* cleared.
* I_FREEING Set when inode is about to be freed but still has dirty
* pages or buffers attached or the inode itself is still
* dirty.
* I_CLEAR Added by clear_inode(). In this state the inode is
* clean and can be destroyed. Inode keeps I_FREEING.
* Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
* prohibited for many purposes. iget() must wait for
* the inode to be completely released, then create it
* anew. Other functions will just ignore such inodes,
* if appropriate. I_NEW is used for waiting.
* I_SYNC Writeback of inode is running. The bit is set during
* data writeback, and cleared with a wakeup on the bit
* address once it is done. The bit is also used to pin
* the inode in memory for flusher thread.
* I_REFERENCED Marks the inode as recently references on the LRU list.
* I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit().
* I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
* synchronize competing switching instances and to tell
* wb stat updates to grab the i_pages lock. See
* inode_switch_wbs_work_fn() for details.
* I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
* and work dirs among overlayfs mounts.
* I_CREATING New object's inode in the middle of setting up.
* I_DONTCACHE Evict inode as soon as it is not used anymore.
* I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists.
* Used to detect that mark_inode_dirty() should not move
* inode between dirty lists.
* Q: What is the difference between I_WILL_FREE and I_FREEING?
#define I_DIRTY_SYNC (1 << 0)
#define I_DIRTY_DATASYNC (1 << 1)
#define I_DIRTY_PAGES (1 << 2)
#define __I_NEW 3
#define I_NEW (1 << __I_NEW)
#define I_WILL_FREE (1 << 4)
#define I_FREEING (1 << 5)
#define I_CLEAR (1 << 6)
#define __I_SYNC 7
#define I_SYNC (1 << __I_SYNC)
#define I_REFERENCED (1 << 8)
#define __I_DIO_WAKEUP 9
#define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP)
#define I_LINKABLE (1 << 10)
#define I_DIRTY_TIME (1 << 11)
#define I_WB_SWITCH (1 << 13)
#define I_OVL_INUSE (1 << 14)
#define I_CREATING (1 << 15)
#define I_DONTCACHE (1 << 16)
#define I_SYNC_QUEUED (1 << 17)
extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
__mark_inode_dirty(inode, I_DIRTY);
static inline void mark_inode_dirty_sync(struct inode *inode)
__mark_inode_dirty(inode, I_DIRTY_SYNC);
extern void inc_nlink(struct inode *inode);
extern void drop_nlink(struct inode *inode);
extern void clear_nlink(struct inode *inode);
extern void set_nlink(struct inode *inode, unsigned int nlink);
static inline void inode_inc_link_count(struct inode *inode)
static inline void inode_dec_link_count(struct inode *inode)
enum file_time_flags {
S_ATIME = 1,
S_MTIME = 2,
S_CTIME = 4,
extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
if (!(file->f_flags & O_NOATIME))
extern int file_modified(struct file *file);
int sync_inode(struct inode *inode, struct writeback_control *wbc);
int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
const char *name;
int fs_flags;
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_spec *parameters;
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
struct hlist_head fs_supers;
struct lock_class_key s_lock_key;
struct lock_class_key s_umount_key;
struct lock_class_key s_vfs_rename_key;
struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
struct lock_class_key i_mutex_dir_key;
extern struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
int set_anon_super_fc(struct super_block *s, struct fs_context *fc);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
struct super_block *sget_fc(struct fs_context *fc,
int (*test)(struct super_block *, struct fs_context *),
int (*set)(struct super_block *, struct fs_context *));
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags, void *data);
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
#define fops_put(fops) \
do { if (fops) module_put((fops)->owner); } while(0)
* This one is to be used *ONLY* from ->open() instances.
* fops must be non-NULL, pinned down *and* module dependencies
* should be sufficient to pin the caller down as well.
#define replace_fops(f, fops) \
do { \
struct file *__file = (f); \
fops_put(__file->f_op); \
BUG_ON(!(__file->f_op = (fops))); \
} while(0)
extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount(struct file_system_type *);
extern void kern_unmount(struct vfsmount *mnt);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern long do_mount(const char *, const char __user *,
const char *, unsigned long, void *);
extern struct vfsmount *collect_mounts(const struct path *);
extern void drop_collected_mounts(struct vfsmount *);
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
struct vfsmount *);
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 *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern bool our_mnt(struct vfsmount *mnt);
extern __printf(2, 3)
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
extern int super_setup_bdi(struct super_block *sb);
extern int current_umask(void);
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
extern int generic_update_time(struct inode *, struct timespec64 *, int);
/* /sys/fs */
extern struct kobject *fs_kobj;
extern int locks_mandatory_locked(struct file *);
extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char);
* Candidates for mandatory locking have the setgid bit set
* but no group execute bit - an otherwise meaningless combination.
static inline int __mandatory_lock(struct inode *ino)
return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
* ... and these candidates should be on SB_MANDLOCK mounted fs,
* otherwise these will be advisory locks
static inline int mandatory_lock(struct inode *ino)
return IS_MANDLOCK(ino) && __mandatory_lock(ino);
static inline int locks_verify_locked(struct file *file)
if (mandatory_lock(locks_inode(file)))
return locks_mandatory_locked(file);
return 0;
static inline int locks_verify_truncate(struct inode *inode,
struct file *f,
loff_t size)
if (!inode->i_flctx || !mandatory_lock(inode))
return 0;
if (size < inode->i_size) {
return locks_mandatory_area(inode, f, size, inode->i_size - 1,
} else {
return locks_mandatory_area(inode, f, inode->i_size, size - 1,
static inline int locks_mandatory_locked(struct file *file)
return 0;
static inline int locks_mandatory_area(struct inode *inode, struct file *filp,
loff_t start, loff_t end, unsigned char type)
return 0;
static inline int __mandatory_lock(struct inode *inode)
return 0;
static inline int mandatory_lock(struct inode *inode)
return 0;
static inline int locks_verify_locked(struct file *file)
return 0;
static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
size_t size)
return 0;
static inline int break_lease(struct inode *inode, unsigned int mode)
* Since this check is lockless, we must ensure that any refcounts
* taken are done before checking i_flctx->flc_lease. Otherwise, we
* could end up racing with tasks trying to set a new lease on this
* file.
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode, mode, FL_LEASE);
return 0;
static inline int break_deleg(struct inode *inode, unsigned int mode)
* Since this check is lockless, we must ensure that any refcounts
* taken are done before checking i_flctx->flc_lease. Otherwise, we
* could end up racing with tasks trying to set a new lease on this
* file.
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode, mode, FL_DELEG);
return 0;
static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
int ret;
ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
if (ret == -EWOULDBLOCK && delegated_inode) {
*delegated_inode = inode;
return ret;
static inline int break_deleg_wait(struct inode **delegated_inode)
int ret;
ret = break_deleg(*delegated_inode, O_WRONLY);
*delegated_inode = NULL;
return ret;
static inline int break_layout(struct inode *inode, bool wait)
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode,
return 0;
static inline int break_lease(struct inode *inode, unsigned int mode)
return 0;
static inline int break_deleg(struct inode *inode, unsigned int mode)
return 0;
static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
return 0;
static inline int break_deleg_wait(struct inode **delegated_inode)
return 0;
static inline int break_layout(struct inode *inode, bool wait)
return 0;
/* fs/open.c */
struct audit_names;
struct filename {
const char *name; /* pointer to actual string */
const __user char *uptr; /* original userland pointer */
int refcnt;
struct audit_names *aname;
const char iname[];
static_assert(offsetof(struct filename, iname) % sizeof(long) == 0);
extern long vfs_truncate(const struct path *, loff_t);
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
umode_t mode);
extern struct file *file_open_name(struct filename *, int, umode_t);
extern struct file *filp_open(const char *, int, umode_t);
extern struct file *filp_open_block(const char *, int, umode_t);
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
const char *, int, umode_t);
extern struct file * dentry_open(const struct path *, int, const struct cred *);
extern struct file * open_with_fake_path(const struct path *, int,
struct inode*, const struct cred *);
static inline struct file *file_clone_open(struct file *file)
return dentry_open(&file->f_path, file->f_flags, file->f_cred);
extern int filp_close(struct file *, fl_owner_t id);
extern struct filename *getname_flags(const char __user *, int, int *);
extern struct filename *getname(const char __user *);
extern struct filename *getname_kernel(const char *);
extern void putname(struct filename *name);
extern int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *));
extern int finish_no_open(struct file *file, struct dentry *dentry);
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(void);
extern struct kmem_cache *names_cachep;
#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 const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;
/* fs/char_dev.c */
#define CHRDEV_MAJOR_MAX 512
/* Marks the bottom of the first segment of free char majors */
/* Marks the top and bottom of the second segment of free char majors */
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name,
const struct file_operations *fops);
extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name);
extern void unregister_chrdev_region(dev_t, unsigned);
extern void chrdev_show(struct seq_file *,off_t);
static inline int register_chrdev(unsigned int major, const char *name,
const struct file_operations *fops)
return __register_chrdev(major, 0, 256, name, fops);
static inline void unregister_chrdev(unsigned int major, const char *name)
__unregister_chrdev(major, 0, 256, name);
extern void init_special_inode(struct inode *, umode_t, dev_t);
/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern bool is_bad_inode(struct inode *);
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end);
void invalidate_mapping_pagevec(struct address_space *mapping,
pgoff_t start, pgoff_t end,
unsigned long *nr_pagevec);
static inline void invalidate_remote_inode(struct inode *inode)
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
invalidate_mapping_pages(inode->i_mapping, 0, -1);
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
loff_t lend);
extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
loff_t start_byte, loff_t end_byte);
static inline int filemap_fdatawait(struct address_space *mapping)
return filemap_fdatawait_range(mapping, 0, LLONG_MAX);
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
loff_t lend);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
extern int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
extern int filemap_check_errors(struct address_space *mapping);
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
static inline int filemap_write_and_wait(struct address_space *mapping)
return filemap_write_and_wait_range(mapping, 0, LLONG_MAX);
extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
loff_t lend);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
loff_t start, loff_t end);
static inline int file_write_and_wait(struct file *file)
return file_write_and_wait_range(file, 0, LLONG_MAX);
* filemap_set_wb_err - set a writeback error on an address_space
* @mapping: mapping in which to set writeback error
* @err: error to be set in mapping
* When writeback fails in some way, we must record that error so that
* userspace can be informed when fsync and the like are called. We endeavor
* to report errors on any file that was open at the time of the error. Some
* internal callers also need to know when writeback errors have occurred.
* When a writeback error occurs, most filesystems will want to call
* filemap_set_wb_err to record the error in the mapping so that it will be
* automatically reported whenever fsync is called on the file.
static inline void filemap_set_wb_err(struct address_space *mapping, int err)
/* Fastpath for common case of no error */
if (unlikely(err))
__filemap_set_wb_err(mapping, err);
* filemap_check_wb_err - has an error occurred since the mark was sampled?
* @mapping: mapping to check for writeback errors
* @since: previously-sampled errseq_t
* Grab the errseq_t value from the mapping, and see if it has changed "since"
* the given value was sampled.
* If it has then report the latest error set, otherwise return 0.
static inline int filemap_check_wb_err(struct address_space *mapping,
errseq_t since)
return errseq_check(&mapping->wb_err, since);
* filemap_sample_wb_err - sample the current errseq_t to test for later errors
* @mapping: mapping to be sampled
* Writeback errors are always reported relative to a particular sample point
* in the past. This function provides those sample points.
static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
return errseq_sample(&mapping->wb_err);
* file_sample_sb_err - sample the current errseq_t to test for later errors
* @file: file pointer to be sampled
* Grab the most current superblock-level errseq_t value for the given
* struct file.
static inline errseq_t file_sample_sb_err(struct file *file)
return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
unsigned int flags);
* Sync the bytes written if this was a synchronous write. Expect ki_pos
* to already be updated for the write, and will return either the amount
* of bytes passed in, or an error if syncing the file failed.
static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
if (iocb->ki_flags & IOCB_DSYNC) {
int ret = vfs_fsync_range(iocb->ki_filp,
iocb->ki_pos - count, iocb->ki_pos - 1,
(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
if (ret)
return ret;
return count;
extern void emergency_sync(void);
extern void emergency_remount(void);
extern int bmap(struct inode *inode, sector_t *block);
static inline int bmap(struct inode *inode, sector_t *block)
return -EINVAL;
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
extern int inode_permission(struct inode *, int);
extern int generic_permission(struct inode *, int);
extern int __check_sticky(struct inode *dir, struct inode *inode);
static inline bool execute_ok(struct inode *inode)
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
static inline bool inode_wrong_type(const struct inode *inode, umode_t mode)
return (inode->i_mode ^ mode) & S_IFMT;
static inline void file_start_write(struct file *file)
if (!S_ISREG(file_inode(file)->i_mode))
static inline bool file_start_write_trylock(struct file *file)
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return sb_start_write_trylock(file_inode(file)->i_sb);
static inline void file_end_write(struct file *file)
if (!S_ISREG(file_inode(file)->i_mode))
__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
* This is used for regular files.
* We cannot support write (and maybe mmap read-write shared) accesses and
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
* can have the following values:
* 0: no writers, no VM_DENYWRITE mappings
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
* > 0: (i_writecount) users are writing to the file.
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
* except for the cases where we don't hold i_writecount yet. Then we need to
* use {get,deny}_write_access() - these functions check the sign and refuse
* to do the change if sign is wrong.
static inline int get_write_access(struct inode *inode)
return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
static inline int deny_write_access(struct file *file)
struct inode *inode = file_inode(file);
return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
static inline void put_write_access(struct inode * inode)
static inline void allow_write_access(struct file *file)
if (file)
static inline bool inode_is_open_for_write(const struct inode *inode)
return atomic_read(&inode->i_writecount) > 0;
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
static inline void i_readcount_dec(struct inode *inode)
static inline void i_readcount_inc(struct inode *inode)
static inline void i_readcount_dec(struct inode *inode)
static inline void i_readcount_inc(struct inode *inode)
extern int do_pipe_flags(int *, int);
extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
extern struct file * open_exec(const char *);
/* fs/dcache.c -- generic fs support functions */
extern bool is_subdir(struct dentry *, struct dentry *);
extern bool path_is_under(const struct path *, const struct path *);
extern char *file_path(struct file *, char *, int);
#include <linux/err.h>
/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
extern void address_space_init_once(struct address_space *mapping);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern int generic_delete_inode(struct inode *inode);
static inline int generic_drop_inode(struct inode *inode)
return !inode->i_nlink || inode_unhashed(inode);
extern void d_mark_dontcache(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
void *data);
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *),
void *data);
extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern struct inode *find_inode_nowait(struct super_block *,
unsigned long,
int (*match)(struct inode *,
unsigned long, void *),
void *data);
extern struct inode *find_inode_rcu(struct super_block *, unsigned long,
int (*)(struct inode *, void *), void *);
extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
extern void unlock_new_inode(struct inode *);
extern void discard_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern void evict_inodes(struct super_block *sb);
* Userspace may rely on the the inode number being non-zero. For example, glibc
* simply ignores files with zero i_ino in unlink() and other places.
* As an additional complication, if userspace was compiled with
* _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the
* lower 32 bits, so we need to check that those aren't zero explicitly. With
* _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but
* better safe than sorry.
static inline bool is_zero_ino(ino_t ino)
return (u32)ino == 0;
extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void clear_inode(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
extern void free_inode_nonrcu(struct inode *inode);
extern int should_remove_suid(struct dentry *);
extern int file_remove_privs(struct file *);
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
static inline void insert_inode_hash(struct inode *inode)
__insert_inode_hash(inode, inode->i_ino);
extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
extern void inode_sb_list_add(struct inode *inode);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);