Skip to content
Permalink
master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Go to file
 
 
Cannot retrieve contributors at this time
/* 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/mount.h>
#include <linux/cred.h>
#include <linux/mnt_idmapping.h>
#include <linux/slab.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 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;
struct fileattr;
struct iomap_ops;
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 unsigned long get_max_files(void);
extern unsigned int sysctl_nr_open;
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/mem): 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 supports DIRECT IO */
#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000)
/* 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)
/* File supports async nowait buffered writes */
#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000)
/*
* 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_MODE 0
#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;
/*
* The two anonymous unions wrap structures with the same member.
*
* Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which
* are a dedicated type requiring the filesystem to use the dedicated
* helpers. Other filesystem can continue to use ia_{g,u}id until they
* have been ported.
*
* They always contain the same value. In other words FS_ALLOW_IDMAP
* pass down the same value on idmapped mounts as they would on regular
* mounts.
*/
union {
kuid_t ia_uid;
vfsuid_t ia_vfsuid;
};
union {
kgid_t ia_gid;
vfsgid_t ia_vfsgid;
};
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
*/
#define FILESYSTEM_MAX_STACK_DEPTH 2
/**
* 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 read_folio().
*
* 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 {
AOP_WRITEPAGE_ACTIVATE = 0x80000,
AOP_TRUNCATED_PAGE = 0x80001,
};
/*
* 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 {
WRITE_LIFE_NOT_SET = 0,
WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE,
WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT,
WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM,
WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG,
WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME,
};
/* 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)
/* can use bio alloc cache */
#define IOCB_ALLOC_CACHE (1 << 21)
struct kiocb {
struct file *ki_filp;
loff_t ki_pos;
void (*ki_complete)(struct kiocb *iocb, long ret);
void *private;
int ki_flags;
u16 ki_ioprio; /* See linux/ioprio.h */
struct wait_page_queue *ki_waitq; /* for async buffered IO */
};
static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
return kiocb->ki_complete == NULL;
}
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*read_folio)(struct file *, struct folio *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
/* Mark a folio dirty. Return true if this dirtied it */
bool (*dirty_folio)(struct address_space *, struct folio *);
void (*readahead)(struct readahead_control *);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len,
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 (*invalidate_folio) (struct folio *, size_t offset, size_t len);
bool (*release_folio)(struct folio *, gfp_t);
void (*free_folio)(struct folio *folio);
ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
/*
* migrate the contents of a folio to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
*/
int (*migrate_folio)(struct address_space *, struct folio *dst,
struct folio *src, enum migrate_mode);
int (*launder_folio)(struct folio *);
bool (*is_partially_uptodate) (struct folio *, size_t from,
size_t count);
void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
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);
int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
};
extern const struct address_space_operations empty_aops;
/**
* struct address_space - Contents of a cacheable, mappable object.
* @host: Owner, either the inode or the block_device.
* @i_pages: Cached pages.
* @invalidate_lock: Guards coherency between page cache contents and
* file offset->disk block mappings in the filesystem during invalidates.
* It is also used to block modification of page cache contents through
* memory mappings.
* @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.
* @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;
struct rw_semaphore invalidate_lock;
gfp_t gfp_mask;
atomic_t i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
/* number of thp, only for non-shmem files */
atomic_t nr_thps;
#endif
struct rb_root_cached i_mmap;
struct rw_semaphore i_mmap_rwsem;
unsigned long nrpages;
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. */
#define PAGECACHE_TAG_DIRTY XA_MARK_0
#define PAGECACHE_TAG_WRITEBACK XA_MARK_1
#define PAGECACHE_TAG_TOWRITE XA_MARK_2
/*
* 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)
{
down_write(&mapping->i_mmap_rwsem);
}
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)
{
up_write(&mapping->i_mmap_rwsem);
}
static inline int i_mmap_trylock_read(struct address_space *mapping)
{
return down_read_trylock(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_lock_read(struct address_space *mapping)
{
down_read(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_unlock_read(struct address_space *mapping)
{
up_read(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_assert_locked(struct address_space *mapping)
{
lockdep_assert_held(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_assert_write_locked(struct address_space *mapping)
{
lockdep_assert_held_write(&mapping->i_mmap_rwsem);
}
/*
* 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)
{
atomic_dec(&mapping->i_mmap_writable);
}
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)
{
atomic_inc(&mapping->i_mmap_writable);
}
/*
* 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 __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
/*
* ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
* cache the ACL. This also means that ->get_inode_acl() can be called in RCU
* mode with the LOOKUP_RCU flag.
*/
#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
#define IOP_DEFAULT_READLINK 0x0010
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;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
/* 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;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
/* 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 */
#ifdef CONFIG_CGROUP_WRITEBACK
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;
#endif
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 */
#endif
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 cdev *i_cdev;
char *i_link;
unsigned i_dir_seq;
};
__u32 i_generation;
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_info *i_crypt_info;
#endif
#ifdef CONFIG_FS_VERITY
struct fsverity_info *i_verity_info;
#endif
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)
{
hlist_add_fake(&inode->i_hash);
}
/*
* 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
{
I_MUTEX_NORMAL,
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
I_MUTEX_NONDIR2,
I_MUTEX_PARENT2,
};
static inline void inode_lock(struct inode *inode)
{
down_write(&inode->i_rwsem);
}
static inline void inode_unlock(struct inode *inode)
{
up_write(&inode->i_rwsem);
}
static inline void inode_lock_shared(struct inode *inode)
{
down_read(&inode->i_rwsem);
}
static inline void inode_unlock_shared(struct inode *inode)
{
up_read(&inode->i_rwsem);
}
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);
}
static inline void filemap_invalidate_lock(struct address_space *mapping)
{
down_write(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_unlock(struct address_space *mapping)
{
up_write(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
{
down_read(&mapping->invalidate_lock);
}
static inline int filemap_invalidate_trylock_shared(
struct address_space *mapping)
{
return down_read_trylock(&mapping->invalidate_lock);
}
static inline void filemap_invalidate_unlock_shared(
struct address_space *mapping)
{
up_read(&mapping->invalidate_lock);
}
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
void filemap_invalidate_lock_two(struct address_space *mapping1,
struct address_space *mapping2);
void filemap_invalidate_unlock_two(struct address_space *mapping1,
struct address_space *mapping2);
/*
* 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;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
loff_t i_size;
preempt_disable();
i_size = inode->i_size;
preempt_enable();
return i_size;
#else
return inode->i_size;
#endif
}
/*
* 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)
preempt_disable();
write_seqcount_begin(&inode->i_size_seqcount);
inode->i_size = i_size;
write_seqcount_end(&inode->i_size_seqcount);
preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
preempt_disable();
inode->i_size = i_size;
preempt_enable();
#else
inode->i_size = i_size;
#endif
}
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 */
};
/**
* struct file_ra_state - Track a file's readahead state.
* @start: Where the most recent readahead started.
* @size: Number of pages read in the most recent readahead.
* @async_size: Numer of pages that were/are not needed immediately
* and so were/are genuinely "ahead". Start next readahead when
* the first of these pages is accessed.
* @ra_pages: Maximum size of a readahead request, copied from the bdi.
* @mmap_miss: How many mmap accesses missed in the page cache.
* @prev_pos: The last byte in the most recent read request.
*
* When this structure is passed to ->readahead(), the "most recent"
* readahead means the current readahead.
*/
struct file_ra_state {
pgoff_t start;
unsigned int size;
unsigned int async_size;
unsigned int ra_pages;
unsigned int mmap_miss;
loff_t prev_pos;
};
/*
* 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 f_llist;
struct rcu_head f_rcuhead;
unsigned int f_iocb_flags;
};
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
/*
* Protects f_ep, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
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;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* needed for tty driver, and maybe others */
void *private_data;
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct hlist_head *f_ep;
#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)
{
atomic_long_inc(&f->f_count);
return f;
}
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
#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. */
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT)
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX)
#endif
#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 */
#define FL_RECLAIM 4096 /* reclaiming from a reboot server */
#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
/*
* Special return value from posix_lock_file() and vfs_lock_file() for
* asynchronous locking.
*/
#define FILE_LOCK_DEFERRED 1
/* 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 {
void *lm_mod_owner;
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 *);
bool (*lm_lock_expirable)(struct file_lock *cfl);
void (*lm_expire_lock)(void);
};
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;
struct {
struct inode *inode;
} ceph;
} fl_u;
} __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 OFFSET_MAX type_max(loff_t)
#define OFFT_OFFSET_MAX type_max(off_t)
#endif
extern void send_sigio(struct fown_struct *fown, int fd, int band);
#define locks_inode(f) file_inode(f)
#ifdef CONFIG_FILE_LOCKING
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 *);
#endif
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);
bool vfs_inode_has_locks(struct inode *inode);
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);
extern bool locks_owner_has_blockers(struct file_lock_context *flctx,
fl_owner_t owner);
static inline struct file_lock_context *
locks_inode_context(const struct inode *inode)
{
return smp_load_acquire(&inode->i_flctx);
}
#else /* !CONFIG_FILE_LOCKING */
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)
{
return -EINVAL;
}
static inline int fcntl_setlk64(unsigned int fd, struct file *file,
unsigned int cmd, struct flock64 *user)
{
return -EACCES;
}
#endif
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)
{
return;
}
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
return;
}
static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
return;
}
static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
return;
}
static inline void locks_remove_file(struct file *filp)
{
return;
}
static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
{
return;
}
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 bool vfs_inode_has_locks(struct inode *inode)
{
return false;
}
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)
{
return;
}
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 bool locks_owner_has_blockers(struct file_lock_context *flctx,
fl_owner_t owner)
{
return false;
}
static inline struct file_lock_context *
locks_inode_context(const struct inode *inode)
{
return NULL;
}
#endif /* !CONFIG_FILE_LOCKING */
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_IMA_UNVERIFIABLE_SIGNATURE 0x00000020
#define SB_I_UNTRUSTED_MOUNTER 0x00000040
#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 */
/* 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 {
int frozen; /* Is sb frozen? */
wait_queue_head_t wait_unfrozen; /* wait for thaw */
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;
#ifdef CONFIG_SECURITY
void *s_security;
#endif
const struct xattr_handler **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 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;
#ifdef CONFIG_FSNOTIFY
__u32 s_fsnotify_mask;
struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
#endif
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 */
struct shrinker s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
/*
* Number of inode/mount/sb objects that are being watched, note that
* inodes objects are currently double-accounted.
*/
atomic_long_t s_fsnotify_connectors;
/* 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;
static inline struct user_namespace *i_user_ns(const struct inode *inode)
{
return inode->i_sb->s_user_ns;
}
/* 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(i_user_ns(inode), inode->i_uid);
}
static inline gid_t i_gid_read(const struct inode *inode)
{
return from_kgid(i_user_ns(inode), inode->i_gid);
}
static inline void i_uid_write(struct inode *inode, uid_t uid)
{
inode->i_uid = make_kuid(i_user_ns(inode), uid);
}
static inline void i_gid_write(struct inode *inode, gid_t gid)
{
inode->i_gid = make_kgid(i_user_ns(inode), gid);
}
/**
* i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
* Return: whe inode's i_uid mapped down according to @mnt_userns.
* If the inode's i_uid has no mapping INVALID_VFSUID is returned.
*/
static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns,
const struct inode *inode)
{
return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid);
}
/**
* i_uid_needs_update - check whether inode's i_uid needs to be updated
* @mnt_userns: user namespace of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Check whether the $inode's i_uid field needs to be updated taking idmapped
* mounts into account if the filesystem supports it.
*
* Return: true if @inode's i_uid field needs to be updated, false if not.
*/
static inline bool i_uid_needs_update(struct user_namespace *mnt_userns,
const struct iattr *attr,
const struct inode *inode)
{
return ((attr->ia_valid & ATTR_UID) &&
!vfsuid_eq(attr->ia_vfsuid,
i_uid_into_vfsuid(mnt_userns, inode)));
}
/**
* i_uid_update - update @inode's i_uid field
* @mnt_userns: user namespace of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Safely update @inode's i_uid field translating the vfsuid of any idmapped
* mount into the filesystem kuid.
*/
static inline void i_uid_update(struct user_namespace *mnt_userns,
const struct iattr *attr,
struct inode *inode)
{
if (attr->ia_valid & ATTR_UID)
inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode),
attr->ia_vfsuid);
}
/**
* i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to map
*
* Return: the inode's i_gid mapped down according to @mnt_userns.
* If the inode's i_gid has no mapping INVALID_VFSGID is returned.
*/
static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns,
const struct inode *inode)
{
return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid);
}
/**
* i_gid_needs_update - check whether inode's i_gid needs to be updated
* @mnt_userns: user namespace of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Check whether the $inode's i_gid field needs to be updated taking idmapped
* mounts into account if the filesystem supports it.
*
* Return: true if @inode's i_gid field needs to be updated, false if not.
*/
static inline bool i_gid_needs_update(struct user_namespace *mnt_userns,
const struct iattr *attr,
const struct inode *inode)
{
return ((attr->ia_valid & ATTR_GID) &&
!vfsgid_eq(attr->ia_vfsgid,
i_gid_into_vfsgid(mnt_userns, inode)));
}
/**
* i_gid_update - update @inode's i_gid field
* @mnt_userns: user namespace of the mount the inode was found from
* @attr: the new attributes of @inode
* @inode: the inode to update
*
* Safely update @inode's i_gid field translating the vfsgid of any idmapped
* mount into the filesystem kgid.
*/
static inline void i_gid_update(struct user_namespace *mnt_userns,
const struct iattr *attr,
struct inode *inode)
{
if (attr->ia_valid & ATTR_GID)
inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode),
attr->ia_vfsgid);
}
/**
* inode_fsuid_set - initialize inode's i_uid field with callers fsuid
* @inode: inode to initialize
* @mnt_userns: user namespace of the mount the inode was found from
*
* Initialize the i_uid field of @inode. If the inode was found/created via
* an idmapped mount map the caller's fsuid according to @mnt_users.
*/
static inline void inode_fsuid_set(struct inode *inode,
struct user_namespace *mnt_userns)
{
inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode));
}
/**
* inode_fsgid_set - initialize inode's i_gid field with callers fsgid
* @inode: inode to initialize
* @mnt_userns: user namespace of the mount the inode was found from
*
* Initialize the i_gid field of @inode. If the inode was found/created via
* an idmapped mount map the caller's fsgid according to @mnt_users.
*/
static inline void inode_fsgid_set(struct inode *inode,
struct user_namespace *mnt_userns)
{
inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode));
}
/**
* fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped
* @sb: the superblock we want a mapping in
* @mnt_userns: user namespace of the relevant mount
*
* Check whether the caller's fsuid and fsgid have a valid mapping in the
* s_user_ns of the superblock @sb. If the caller is on an idmapped mount map
* the caller's fsuid and fsgid according to the @mnt_userns first.
*
* Return: true if fsuid and fsgid is mapped, false if not.
*/
static inline bool fsuidgid_has_mapping(struct super_block *sb,
struct user_namespace *mnt_userns)
{
struct user_namespace *fs_userns = sb->s_user_ns;
kuid_t kuid;
kgid_t kgid;
kuid = mapped_fsuid(mnt_userns, fs_userns);
if (!uid_valid(kuid))
return false;
kgid = mapped_fsgid(mnt_userns, fs_userns);
if (!gid_valid(kgid))
return false;
return kuid_has_mapping(fs_userns, kuid) &&
kgid_has_mapping(fs_userns, kgid);
}
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_)
static inline bool sb_write_started(const struct super_block *sb)
{
return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
}
/**
* 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);
}
bool inode_owner_or_capable(struct user_namespace *mnt_userns,
const struct inode *inode);
/*
* VFS helper functions..
*/
int vfs_create(struct user_namespace *, struct inode *,
struct dentry *, umode_t, bool);
int vfs_mkdir(struct user_namespace *, struct inode *,
struct dentry *, umode_t);
int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *,
umode_t, dev_t);
int vfs_symlink(struct user_namespace *, struct inode *,
struct dentry *, const char *);
int vfs_link(struct dentry *, struct user_namespace *, struct inode *,
struct dentry *, struct inode **);
int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *);
int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *,
struct inode **);
/**
* struct renamedata - contains all information required for renaming
* @old_mnt_userns: old user namespace of the mount the inode was found from
* @old_dir: parent of source
* @old_dentry: source
* @new_mnt_userns: new user namespace of the mount the inode was found from
* @new_dir: parent of destination
* @new_dentry: destination
* @delegated_inode: returns an inode needing a delegation break
* @flags: rename flags
*/
struct renamedata {
struct user_namespace *old_mnt_userns;
struct inode *old_dir;
struct dentry *old_dentry;
struct user_namespace *new_mnt_userns;
struct inode *new_dir;
struct dentry *new_dentry;
struct inode **delegated_inode;
unsigned int flags;
} __randomize_layout;
int vfs_rename(struct renamedata *);
static inline int vfs_whiteout(struct user_namespace *mnt_userns,
struct inode *dir, struct dentry *dentry)
{
return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE,
WHITEOUT_DEV);
}
struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns,
const struct path *parentpath,
umode_t mode, int open_flag, const struct cred *cred);
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);
#ifdef CONFIG_COMPAT
extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg);
#else
#define compat_ptr_ioctl NULL
#endif
/*
* VFS file helper functions.
*/
void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
const struct inode *dir, umode_t mode);
extern bool may_open_dev(const struct path *path);
umode_t mode_strip_sgid(struct user_namespace *mnt_userns,
const struct inode *dir, umode_t mode);
/*
* 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.
* Return 'true' to keep going and 'false' if there are no more entries.
*/
struct dir_context;
typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
unsigned);
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
#define NOMMU_MAP_READ VM_MAYREAD
#define NOMMU_MAP_WRITE VM_MAYWRITE
#define NOMMU_MAP_EXEC VM_MAYEXEC
#define NOMMU_VMFLAGS \
(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
/*
* 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.
*/
#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN)
/*
* These flags control the behavior of vfs_copy_file_range().
* They are not available to the user via syscall.
*
* COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops
*/
#define COPY_FILE_SPLICE (1 << 0)
struct iov_iter;
struct io_uring_cmd;
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, struct io_comp_batch *,
unsigned int flags);
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 *);
#endif
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);
int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *,
unsigned int poll_flags);
} __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 user_namespace *, struct inode *, int);
struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
int (*readlink) (struct dentry *, char __user *,int);
int (*create) (struct user_namespace *, struct inode *,struct dentry *,
umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct user_namespace *, struct inode *,struct dentry *,
const char *);
int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *,
umode_t);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct user_namespace *, struct inode *,struct dentry *,
umode_t,dev_t);
int (*rename) (struct user_namespace *, struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct user_namespace *, struct dentry *,
struct iattr *);
int (*getattr) (struct user_namespace *, 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 user_namespace *, struct inode *,
struct file *, umode_t);
struct posix_acl *(*get_acl)(struct user_namespace *, struct dentry *,
int);
int (*set_acl)(struct user_namespace *, struct dentry *,
struct posix_acl *, int);
int (*fileattr_set)(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa);
int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
} ____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);
int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
const struct iomap_ops *dax_read_ops);
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 *);
#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 **(*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 *);
};
/*
* 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 */
#ifdef CONFIG_FS_DAX
#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */
#else
#define S_DAX 0 /* Make all the DAX code disappear */
#endif
#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/) */
#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */
/*
* 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. -- rmk@arm.uk.linux.org
*/
#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 user_namespace *mnt_userns,
struct inode *inode)
{
return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) ||
!vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode));
}
static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
*kiocb = (struct kiocb) {
.ki_filp = filp,
.ki_flags = filp->f_iocb_flags,
.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_ioprio = kiocb_src->ki_ioprio,
.ki_pos = kiocb_src->ki_pos,
};
}
/*
* Inode state bits. Protected by inode->i_lock
*
* Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
* I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
*
* 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() (unless I_DIRTY_DATASYNC is also set).
* Timestamp updates are 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
* e.g. the timestamps have changed.
* I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
* I_DIRTY_TIME The inode itself has dirty timestamps, and the
* lazytime mount option is enabled. We keep track of this
* separately from I_DIRTY_SYNC in order to implement
* lazytime. This gets cleared if I_DIRTY_INODE
* (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
* I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
* in place because writeback might already be in progress
* and we don't want to lose the time update
* 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.
*
* I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
*
* 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)
#define I_PINNING_FSCACHE_WB (1 << 18)
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
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);
}
/*
* Returns true if the given inode itself only has dirty timestamps (its pages
* may still be dirty) and isn't currently being allocated or freed.
* Filesystems should call this if when writing an inode when lazytime is
* enabled, they want to opportunistically write the timestamps of other inodes
* located very nearby on-disk, e.g. in the same inode block. This returns true
* if the given inode is in need of such an opportunistic update. Requires
* i_lock, or at least later re-checking under i_lock.
*/
static inline bool inode_is_dirtytime_only(struct inode *inode)
{
return (inode->i_state & (I_DIRTY_TIME | I_NEW |
I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
}
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)
{
inc_nlink(inode);
mark_inode_dirty(inode);
}
static inline void inode_dec_link_count(struct inode *inode)
{
drop_nlink(inode);
mark_inode_dirty(inode);
}
enum file_time_flags {
S_ATIME = 1,
S_MTIME = 2,
S_CTIME = 4,
S_VERSION = 8,
};
extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
int inode_update_time(struct inode *inode, struct timespec64 *time, int flags);
static inline void file_accessed(struct file *file)
{
if (!(file->f_flags & O_NOATIME))
touch_atime(&file->f_path);
}
extern int file_modified(struct file *file);
int kiocb_modified(struct kiocb *iocb);
int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
const char *name;
int fs_flags;
#define FS_REQUIRES_DEV 1
#define FS_BINARY_MOUNTDATA 2
#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_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */
#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 invalidate_lock_key;
struct lock_class_key i_mutex_dir_key;
};
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
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 retire_super(struct super_block *sb);
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 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 __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;
#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)
#ifdef CONFIG_FILE_LOCKING
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.
*/
smp_mb();
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.
*/
smp_mb();
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;
ihold(inode);
}
return ret;
}
static inline int break_deleg_wait(struct inode **delegated_inode)
{
int ret;
ret = break_deleg(*delegated_inode, O_WRONLY);
iput(*delegated_inode);
*delegated_inode = NULL;
return ret;
}
static inline int break_layout(struct inode *inode, bool wait)
{
smp_mb();
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode,
wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
FL_LAYOUT);
return 0;
}
#else /* !CONFIG_FILE_LOCKING */
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)
{
BUG();
return 0;
}
static inline int break_layout(struct inode *inode, bool wait)
{
return 0;
}
#endif /* CONFIG_FILE_LOCKING */
/* 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);
static inline struct user_namespace *file_mnt_user_ns(struct file *file)
{
return mnt_user_ns(file->f_path.mnt);
}
static inline struct mnt_idmap *file_mnt_idmap(struct file *file)
{
return mnt_idmap(file->f_path.mnt);
}
/**
* is_idmapped_mnt - check whether a mount is mapped
* @mnt: the mount to check
*
* If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped.
*
* Return: true if mount is mapped, false if not.
*/
static inline bool is_idmapped_mnt(const struct vfsmount *mnt)
{
return mnt_idmap(mnt) != &nop_mnt_idmap;
}
extern long vfs_truncate(const struct path *, loff_t);
int do_truncate(struct user_namespace *, 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 *file_open_root(const struct path *,
const char *, int, umode_t);
static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
const char *name, int flags, umode_t mode)
{
return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
name, flags, mode);
}
extern struct file * dentry_open(const struct path *, int, const struct cred *);
extern struct file *dentry_create(const struct path *path, int flags,
umode_t mode, const struct cred *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_uflags(const char __user *, 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);
/* Helper for the simple case when original dentry is used */
static inline int finish_open_simple(struct file *file, int error)
{
if (error)
return error;
return finish_open(file, file->f_path.dentry, NULL);
}
/* 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 */
#define CHRDEV_MAJOR_DYN_END 234
/* Marks the top and bottom of the second segment of free char majors */
#define CHRDEV_MAJOR_DYN_EXT_START 511
#define CHRDEV_MAJOR_DYN_EXT_END 384
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 *);
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);
}
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);
static inline bool iocb_is_dsync(const struct kiocb *iocb)
{
return (iocb->ki_flags & IOCB_DSYNC) ||
IS_SYNC(iocb->ki_filp->f_mapping->host);
}
/*
* 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_is_dsync(iocb)) {
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);
#ifdef CONFIG_BLOCK
extern int bmap(struct inode *inode, sector_t *block);
#else
static inline int bmap(struct inode *inode, sector_t *block)
{
return -EINVAL;
}
#endif
int notify_change(struct user_namespace *, struct dentry *,
struct iattr *, struct inode **);
int inode_permission(struct user_namespace *, struct inode *, int);
int generic_permission(struct user_namespace *, struct inode *, int);
static inline int file_permission(struct file *file, int mask)
{
return inode_permission(file_mnt_user_ns(file),
file_inode(file), mask);
}
static inline int path_permission(const struct path *path, int mask)
{
return inode_permission(mnt_user_ns(path->mnt),
d_inode(path->dentry), mask);
}
int __check_sticky(struct user_namespace *mnt_userns, 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))
return;
sb_start_write(file_inode(file)->i_sb);
}
static inline bool file_start_write_trylock(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return sb_start_writ