dentry_operations¶

prototypes:

int (*d_revalidate)(struct inode *, const struct qstr *,                    struct dentry *, unsigned int);int (*d_weak_revalidate)(struct dentry *, unsigned int);int (*d_hash)(const struct dentry *, struct qstr *);int (*d_compare)(const struct dentry *,                unsigned int, const char *, const struct qstr *);int (*d_delete)(struct dentry *);int (*d_init)(struct dentry *);void (*d_release)(struct dentry *);void (*d_iput)(struct dentry *, struct inode *);char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);struct vfsmount *(*d_automount)(struct path *path);int (*d_manage)(const struct path *, bool);struct dentry *(*d_real)(struct dentry *, enum d_real_type type);bool (*d_unalias_trylock)(const struct dentry *);void (*d_unalias_unlock)(const struct dentry *);

locking rules:

inode_operations¶

prototypes:

int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool);struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);int (*link) (struct dentry *,struct inode *,struct dentry *);int (*unlink) (struct inode *,struct dentry *);int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *);struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);int (*rmdir) (struct inode *,struct dentry *);int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,                struct inode *, struct dentry *, unsigned int);int (*readlink) (struct dentry *, char __user *,int);const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);void (*truncate) (struct inode *);int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int);struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);int (*getattr) (struct mnt_idmap *, 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);void (*update_time)(struct inode *, struct timespec *, int);int (*atomic_open)(struct inode *, struct dentry *,                        struct file *, unsigned open_flag,                        umode_t create_mode);int (*tmpfile) (struct mnt_idmap *, struct inode *,                struct file *, umode_t);int (*fileattr_set)(struct mnt_idmap *idmap,                    struct dentry *dentry, struct file_kattr *fa);int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);struct offset_ctx *(*get_offset_ctx)(struct inode *inode);

locking rules:

all may block

Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsemexclusive on victim.cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.->unlink() and ->rename() have ->i_rwsem exclusive on all non-directoriesinvolved.->rename() has ->i_rwsem exclusive on any subdirectory that changes parent.

SeeDirectory Locking for more detailed discussionof the locking scheme for directory operations.

xattr_handler operations¶

prototypes:

bool (*list)(struct dentry *dentry);int (*get)(const struct xattr_handler *handler, struct dentry *dentry,           struct inode *inode, const char *name, void *buffer,           size_t size);int (*set)(const struct xattr_handler *handler,           struct mnt_idmap *idmap,           struct dentry *dentry, struct inode *inode, const char *name,           const void *buffer, size_t size, int flags);

locking rules:

all may block

super_operations¶

prototypes:

struct inode *(*alloc_inode)(struct super_block *sb);void (*free_inode)(struct inode *);void (*destroy_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_fs) (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 *);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);

locking rules:

All may block [not true, see below]

->statfs() has s_umount (shared) when called by ustat(2) (native orcompat), but that’s an accident of bad API; s_umount is used to pinthe superblock down when we only have dev_t given us by userland toidentify the superblock. Everything else (statfs(),fstatfs(), etc.)doesn’t hold it when calling ->statfs() - superblock is pinned downby resolving the pathname passed to syscall.

->quota_read() and ->quota_write() functions are both guaranteed tobe the only ones operating on the quota file by the quota code (viadqio_sem) (unless an admin really wants to screw up something andwrites to quota files with quotas on). For other details about lockingsee also dquot_operations section.

file_system_type¶

prototypes:

struct dentry *(*mount) (struct file_system_type *, int,               const char *, void *);void (*kill_sb) (struct super_block *);

locking rules:

->mount() returns ERR_PTR or the root dentry; its superblock should be lockedon return.

->kill_sb() takes a write-locked superblock, does all shutdown work on it,unlocks and drops the reference.

address_space_operations¶

prototypes:

int (*read_folio)(struct file *, struct folio *);int (*writepages)(struct address_space *, struct writeback_control *);bool (*dirty_folio)(struct address_space *, struct folio *folio);void (*readahead)(struct readahead_control *);int (*write_begin)(const struct kiocb *, struct address_space *mapping,                        loff_t pos, unsigned len,                        struct folio **foliop, void **fsdata);int (*write_end)(const struct kiocb *, struct address_space *mapping,                        loff_t pos, unsigned len, unsigned copied,                        struct folio *folio, void *fsdata);sector_t (*bmap)(struct address_space *, sector_t);void (*invalidate_folio) (struct folio *, size_t start, size_t len);bool (*release_folio)(struct folio *, gfp_t);void (*free_folio)(struct folio *);int (*direct_IO)(struct kiocb *, struct iov_iter *iter);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);int (*error_remove_folio)(struct address_space *, struct folio *);int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)int (*swap_deactivate)(struct file *);int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);

locking rules:

All except dirty_folio and free_folio may block

->write_begin(), ->write_end() and ->read_folio() may be called fromthe request handler (/dev/loop).

->read_folio() unlocks the folio, either synchronously or via I/Ocompletion.

->readahead() unlocks the folios that I/O is attempted on like ->read_folio().

->writepages() is used for periodic writeback and for syscall-initiatedsync operations. The address_space should start I/O against at least*nr_to_write pages.*nr_to_write must be decremented for each pagewhich is written. The address_space implementation may write more (or less)pages than*nr_to_write asks for, but it should try to be reasonably close.If nr_to_write is NULL, all dirty pages must be written.

writepages should _only_ write pages which are present inmapping->i_pages.

->dirty_folio() is called from various places in the kernel whenthe target folio is marked as needing writeback. The folio cannot betruncated because either the caller holds the folio lock, or the callerhas found the folio while holding the page table lock which will blocktruncation.

->bmap() is currently used by legacy ioctl() (FIBMAP) provided by somefilesystems and by the swapper. The latter will eventually go away. Please,keep it that way and don’t breed new callers.

->invalidate_folio() is called when the filesystem must attempt to dropsome or all of the buffers from the page when it is being truncated. Itreturns zero on success. The filesystem must exclusively acquireinvalidate_lock before invalidating page cache in truncate / hole punchpath (and thus calling into ->invalidate_folio) to block races between pagecache invalidation and page cache filling functions (fault, read, ...).

->release_folio() is called when the MM wants to make a change to thefolio that would invalidate the filesystem’s private data. For example,it may be about to be removed from the address_space or split. The foliois locked and not under writeback. It may be dirty. The gfp parameteris not usually used for allocation, but rather to indicate what thefilesystem may do to attempt to free the private data. The filesystem mayreturn false to indicate that the folio’s private data cannot be freed.If it returns true, it should have already removed the private data fromthe folio. If a filesystem does not provide a ->release_folio method,the pagecache will assume that private data is buffer_heads and calltry_to_free_buffers().

->free_folio() is called when the kernel has dropped the foliofrom the page cache.

->launder_folio() may be called prior to releasing a folio ifit is still found to be dirty. It returns zero if the folio was successfullycleaned, or an error value if not. Note that in order to prevent the foliogetting mapped back in and redirtied, it needs to be kept lockedacross the entire operation.

->swap_activate() will be called to prepare the given file for swap. Itshould perform any validation and preparation necessary to ensure thatwrites can be performed with minimal memory allocation. It should calladd_swap_extent(), or the helperiomap_swapfile_activate(), and returnthe number of extents added. If IO should be submitted through->swap_rw(), it should set SWP_FS_OPS, otherwise IO will be submitteddirectly to the block devicesis->bdev.

->swap_deactivate() will be called in thesys_swapoff()path after ->swap_activate() returned success.

->swap_rw will be called for swap IO if SWP_FS_OPS was set by ->swap_activate().

file_lock_operations¶

prototypes:

void (*fl_copy_lock)(struct file_lock *, struct file_lock *);void (*fl_release_private)(struct file_lock *);

locking rules:

lock_manager_operations¶

prototypes:

void (*lm_notify)(struct file_lock *);  /* unblock callback */int (*lm_grant)(struct file_lock *, struct file_lock *, int);void (*lm_break)(struct file_lock *); /* break_lease callback */int (*lm_change)(struct file_lock **, int);bool (*lm_breaker_owns_lease)(struct file_lock *);bool (*lm_lock_expirable)(struct file_lock *);void (*lm_expire_lock)(void);

locking rules:

buffer_head¶

prototypes:

void (*b_end_io)(struct buffer_head *bh, int uptodate);

locking rules:

called from interrupts. In other words, extreme care is needed here.bh is locked, but that’s all warranties we have here. Currently only RAID1,highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devicescall this method upon the IO completion.

block_device_operations¶

prototypes:

int (*open) (struct block_device *, fmode_t);int (*release) (struct gendisk *, fmode_t);int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);int (*direct_access) (struct block_device *, sector_t, void **,                        unsigned long *);void (*unlock_native_capacity) (struct gendisk *);int (*getgeo)(struct gendisk *, struct hd_geometry *);void (*swap_slot_free_notify) (struct block_device *, unsigned long);

locking rules:

swap_slot_free_notify is called with swap_lock and sometimes the page lockheld.

file_operations¶

prototypes:

loff_t (*llseek) (struct file *, loff_t, int);ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);int (*iopoll) (struct kiocb *kiocb, bool spin);int (*iterate_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 *);int (*open) (struct inode *, struct file *);int (*flush) (struct file *);int (*release) (struct inode *, struct file *);int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);int (*fasync) (int, struct file *, int);int (*lock) (struct file *, int, struct file_lock *);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 *, int, loff_t, loff_t);void (*show_fdinfo)(struct seq_file *m, struct file *f);unsigned (*mmap_capabilities)(struct file *);ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,                loff_t, size_t, unsigned int);loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,                struct file *file_out, loff_t pos_out,                loff_t len, unsigned int remap_flags);int (*fadvise)(struct file *, loff_t, loff_t, int);

locking rules:

All may block.

->llseek() locking has moved from llseek to the individual llseekimplementations. If your fs is not using generic_file_llseek, youneed to acquire and release the appropriate locks in your ->llseek().For many filesystems, it is probably safe to acquire the inodemutex or just to usei_size_read() instead.Note: this does not protect the file->f_pos against concurrent modificationssince this is something the userspace has to take care about.

->iterate_shared() is called with i_rwsem held for reading, and with thefile f_pos_lock held exclusively

->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.Most instances callfasync_helper(), which does that maintenance, so it’snot normally something one needs to worry about. Return values > 0 will bemapped to zero in the VFS layer.

->readdir() and ->ioctl() on directories must be changed. Ideally we wouldmove ->readdir() to inode_operations and use a separate method for directory->ioctl() or kill the latter completely. One of the problems is that foranything that resembles union-mount we won’t have astructfile for allcomponents. And there are other reasons why the current interface is a mess...

->read on directories probably must go away - we should just enforce -EISDIRinsys_read() and friends.

->setlease operations should callgeneric_setlease() before or after settingthe lease within the individual filesystem to record the result of theoperation

->fallocate implementation must be really careful to maintain page cacheconsistency when punching holes or performing other operations that invalidatepage cache contents. Usually the filesystem needs to calltruncate_inode_pages_range() to invalidate relevant range of the page cache.However the filesystem usually also needs to update its internal (and on disk)view of file offset -> disk block mapping. Until this update is finished, thefilesystem needs to block page faults and reads from reloading now-stale pagecache contents from the disk. Since VFS acquires mapping->invalidate_lock inshared mode when loading pages from disk (filemap_fault(),filemap_read(),readahead paths), the fallocate implementation must take the invalidate_lock toprevent reloading.

->copy_file_range and ->remap_file_range implementations need to serializeagainst modifications of file data while the operation is running. Forblocking changes through write(2) and similar operations inode->i_rwsem can beused. To block changes to file contents via a memory mapping during theoperation, the filesystem must take mapping->invalidate_lock to coordinatewith ->page_mkwrite.

dquot_operations¶

prototypes:

int (*write_dquot) (struct dquot *);int (*acquire_dquot) (struct dquot *);int (*release_dquot) (struct dquot *);int (*mark_dirty) (struct dquot *);int (*write_info) (struct super_block *, int);

These operations are intended to be more or less wrapping functions that ensurea proper locking wrt the filesystem and call the generic quota operations.

What filesystem should expect from the generic quota functions:

FS recursion means calling ->quota_read() and ->quota_write() from superblockoperations.

More details about quota locking can be found in fs/dquot.c.

vm_operations_struct¶

prototypes:

void (*open)(struct vm_area_struct *);void (*close)(struct vm_area_struct *);vm_fault_t (*fault)(struct vm_fault *);vm_fault_t (*huge_fault)(struct vm_fault *, unsigned int order);vm_fault_t (*map_pages)(struct vm_fault *, pgoff_t start, pgoff_t end);vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);

locking rules:

->fault() is called when a previously not present pte is about to be faultedin. The filesystem must find and return the page associated with the passed in“pgoff” in the vm_fault structure. If it is possible that the page may betruncated and/or invalidated, then the filesystem must lock invalidate_lock,then ensure the page is not already truncated (invalidate_lock will blocksubsequent truncate), and then return with VM_FAULT_LOCKED, and the pagelocked. The VM will unlock the page.

->huge_fault() is called when there is no PUD or PMD entry present. Thisgives the filesystem the opportunity to install a PUD or PMD sized page.Filesystems can also use the ->fault method to return a PMD sized page,so implementing this function may not be necessary. In particular,filesystems should not callfilemap_fault() from ->huge_fault().The mmap_lock may not be held when this method is called.

->map_pages() is called when VM asks to map easy accessible pages.Filesystem should find and map pages associated with offsets from “start_pgoff”till “end_pgoff”. ->map_pages() is called with the RCU lock held and mustnot block. If it’s not possible to reach a page without blocking,filesystem should skip it. Filesystem should useset_pte_range() to setuppage table entry. Pointer to entry associated with the page is passed in“pte” field in vm_fault structure. Pointers to entries for other offsetsshould be calculated relative to “pte”.

->page_mkwrite() is called when a previously read-only pte is about to becomewriteable. The filesystem again must ensure that there are notruncate/invalidate races or races with operations such as ->remap_file_rangeor ->copy_file_range, and then return with the page locked. Usuallymapping->invalidate_lock is suitable for proper serialization. If the page hasbeen truncated, the filesystem should not look up a new page like the ->fault()handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM toretry the fault.

->pfn_mkwrite() is the same as page_mkwrite but when the pte isVM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return isVM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behaviorafter this call is to make the pte read-write, unless pfn_mkwrite returnsan error.

->access() is called whenget_user_pages() fails inaccess_process_vm(), typically used to debug a process through/proc/pid/mem or ptrace. This function is needed only forVM_IO | VM_PFNMAP VMAs.

Dubious stuff

(if you break something or notice that it is broken and do not fix it yourself- at least put it here)