Linux Audio

Check our new training course

Loading...
v6.13.7
  1=======
  2Locking
  3=======
  4
  5The text below describes the locking rules for VFS-related methods.
  6It is (believed to be) up-to-date. *Please*, if you change anything in
  7prototypes or locking protocols - update this file. And update the relevant
  8instances in the tree, don't leave that to maintainers of filesystems/devices/
  9etc. At the very least, put the list of dubious cases in the end of this file.
 10Don't turn it into log - maintainers of out-of-the-tree code are supposed to
 11be able to use diff(1).
 12
 13Thing currently missing here: socket operations. Alexey?
 14
 15dentry_operations
 16=================
 17
 18prototypes::
 19
 20	int (*d_revalidate)(struct dentry *, unsigned int);
 21	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 22	int (*d_hash)(const struct dentry *, struct qstr *);
 23	int (*d_compare)(const struct dentry *,
 24			unsigned int, const char *, const struct qstr *);
 25	int (*d_delete)(struct dentry *);
 26	int (*d_init)(struct dentry *);
 27	void (*d_release)(struct dentry *);
 28	void (*d_iput)(struct dentry *, struct inode *);
 29	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 30	struct vfsmount *(*d_automount)(struct path *path);
 31	int (*d_manage)(const struct path *, bool);
 32	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
 33
 34locking rules:
 35
 36================== ===========	========	==============	========
 37ops		   rename_lock	->d_lock	may block	rcu-walk
 38================== ===========	========	==============	========
 39d_revalidate:	   no		no		yes (ref-walk)	maybe
 40d_weak_revalidate: no		no		yes	 	no
 41d_hash		   no		no		no		maybe
 42d_compare:	   yes		no		no		maybe
 43d_delete:	   no		yes		no		no
 44d_init:		   no		no		yes		no
 45d_release:	   no		no		yes		no
 46d_prune:           no		yes		no		no
 47d_iput:		   no		no		yes		no
 48d_dname:	   no		no		no		no
 49d_automount:	   no		no		yes		no
 50d_manage:	   no		no		yes (ref-walk)	maybe
 51d_real		   no		no		yes 		no
 52================== ===========	========	==============	========
 53
 54inode_operations
 55================
 56
 57prototypes::
 58
 59	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool);
 60	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 61	int (*link) (struct dentry *,struct inode *,struct dentry *);
 62	int (*unlink) (struct inode *,struct dentry *);
 63	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *);
 64	int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t);
 65	int (*rmdir) (struct inode *,struct dentry *);
 66	int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t);
 67	int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,
 68			struct inode *, struct dentry *, unsigned int);
 69	int (*readlink) (struct dentry *, char __user *,int);
 70	const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 71	void (*truncate) (struct inode *);
 72	int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int);
 73	struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);
 74	int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
 75	int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int);
 76	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 77	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 78	void (*update_time)(struct inode *, struct timespec *, int);
 79	int (*atomic_open)(struct inode *, struct dentry *,
 80				struct file *, unsigned open_flag,
 81				umode_t create_mode);
 82	int (*tmpfile) (struct mnt_idmap *, struct inode *,
 83			struct file *, umode_t);
 84	int (*fileattr_set)(struct mnt_idmap *idmap,
 85			    struct dentry *dentry, struct fileattr *fa);
 86	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
 87	struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);
 88	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 89
 90locking rules:
 91	all may block
 92
 93==============	==================================================
 94ops		i_rwsem(inode)
 95==============	==================================================
 96lookup:		shared
 97create:		exclusive
 98link:		exclusive (both)
 99mknod:		exclusive
100symlink:	exclusive
101mkdir:		exclusive
102unlink:		exclusive (both)
103rmdir:		exclusive (both)(see below)
104rename:		exclusive (both parents, some children)	(see below)
105readlink:	no
106get_link:	no
107setattr:	exclusive
108permission:	no (may not block if called in rcu-walk mode)
109get_inode_acl:	no
110get_acl:	no
111getattr:	no
112listxattr:	no
113fiemap:		no
114update_time:	no
115atomic_open:	shared (exclusive if O_CREAT is set in open flags)
116tmpfile:	no
117fileattr_get:	no or exclusive
118fileattr_set:	exclusive
119get_offset_ctx  no
120==============	==================================================
121
122
123	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem
124	exclusive on victim.
125	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
126	->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories
127	involved.
128	->rename() has ->i_rwsem exclusive on any subdirectory that changes parent.
129
130See Documentation/filesystems/directory-locking.rst for more detailed discussion
131of the locking scheme for directory operations.
132
133xattr_handler operations
134========================
135
136prototypes::
137
138	bool (*list)(struct dentry *dentry);
139	int (*get)(const struct xattr_handler *handler, struct dentry *dentry,
140		   struct inode *inode, const char *name, void *buffer,
141		   size_t size);
142	int (*set)(const struct xattr_handler *handler,
143                   struct mnt_idmap *idmap,
144                   struct dentry *dentry, struct inode *inode, const char *name,
145                   const void *buffer, size_t size, int flags);
146
147locking rules:
148	all may block
149
150=====		==============
151ops		i_rwsem(inode)
152=====		==============
153list:		no
154get:		no
155set:		exclusive
156=====		==============
157
158super_operations
159================
160
161prototypes::
162
163	struct inode *(*alloc_inode)(struct super_block *sb);
164	void (*free_inode)(struct inode *);
165	void (*destroy_inode)(struct inode *);
166	void (*dirty_inode) (struct inode *, int flags);
167	int (*write_inode) (struct inode *, struct writeback_control *wbc);
168	int (*drop_inode) (struct inode *);
169	void (*evict_inode) (struct inode *);
170	void (*put_super) (struct super_block *);
171	int (*sync_fs)(struct super_block *sb, int wait);
172	int (*freeze_fs) (struct super_block *);
173	int (*unfreeze_fs) (struct super_block *);
174	int (*statfs) (struct dentry *, struct kstatfs *);
175	int (*remount_fs) (struct super_block *, int *, char *);
176	void (*umount_begin) (struct super_block *);
177	int (*show_options)(struct seq_file *, struct dentry *);
178	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
179	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 
180
181locking rules:
182	All may block [not true, see below]
183
184======================	============	========================
185ops			s_umount	note
186======================	============	========================
187alloc_inode:
188free_inode:				called from RCU callback
189destroy_inode:
190dirty_inode:
191write_inode:
192drop_inode:				!!!inode->i_lock!!!
193evict_inode:
194put_super:		write
195sync_fs:		read
196freeze_fs:		write
197unfreeze_fs:		write
198statfs:			maybe(read)	(see below)
199remount_fs:		write
200umount_begin:		no
201show_options:		no		(namespace_sem)
202quota_read:		no		(see below)
203quota_write:		no		(see below)
 
204======================	============	========================
205
206->statfs() has s_umount (shared) when called by ustat(2) (native or
207compat), but that's an accident of bad API; s_umount is used to pin
208the superblock down when we only have dev_t given us by userland to
209identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
210doesn't hold it when calling ->statfs() - superblock is pinned down
211by resolving the pathname passed to syscall.
212
213->quota_read() and ->quota_write() functions are both guaranteed to
214be the only ones operating on the quota file by the quota code (via
215dqio_sem) (unless an admin really wants to screw up something and
216writes to quota files with quotas on). For other details about locking
217see also dquot_operations section.
218
 
 
 
219file_system_type
220================
221
222prototypes::
223
224	struct dentry *(*mount) (struct file_system_type *, int,
225		       const char *, void *);
226	void (*kill_sb) (struct super_block *);
227
228locking rules:
229
230=======		=========
231ops		may block
232=======		=========
233mount		yes
234kill_sb		yes
235=======		=========
236
237->mount() returns ERR_PTR or the root dentry; its superblock should be locked
238on return.
239
240->kill_sb() takes a write-locked superblock, does all shutdown work on it,
241unlocks and drops the reference.
242
243address_space_operations
244========================
245prototypes::
246
247	int (*writepage)(struct page *page, struct writeback_control *wbc);
248	int (*read_folio)(struct file *, struct folio *);
249	int (*writepages)(struct address_space *, struct writeback_control *);
250	bool (*dirty_folio)(struct address_space *, struct folio *folio);
251	void (*readahead)(struct readahead_control *);
 
 
252	int (*write_begin)(struct file *, struct address_space *mapping,
253				loff_t pos, unsigned len,
254				struct folio **foliop, void **fsdata);
255	int (*write_end)(struct file *, struct address_space *mapping,
256				loff_t pos, unsigned len, unsigned copied,
257				struct folio *folio, void *fsdata);
258	sector_t (*bmap)(struct address_space *, sector_t);
259	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
260	bool (*release_folio)(struct folio *, gfp_t);
261	void (*free_folio)(struct folio *);
262	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
263	int (*migrate_folio)(struct address_space *, struct folio *dst,
264			struct folio *src, enum migrate_mode);
265	int (*launder_folio)(struct folio *);
266	bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count);
267	int (*error_remove_folio)(struct address_space *, struct folio *);
268	int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
 
269	int (*swap_deactivate)(struct file *);
270	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
271
272locking rules:
273	All except dirty_folio and free_folio may block
274
275======================	======================== =========	===============
276ops			folio locked		 i_rwsem	invalidate_lock
277======================	======================== =========	===============
278writepage:		yes, unlocks (see below)
279read_folio:		yes, unlocks				shared
280writepages:
281dirty_folio:		maybe
282readahead:		yes, unlocks				shared
283write_begin:		locks the folio		 exclusive
 
284write_end:		yes, unlocks		 exclusive
285bmap:
286invalidate_folio:	yes					exclusive
287release_folio:		yes
288free_folio:		yes
289direct_IO:
290migrate_folio:		yes (both)
291launder_folio:		yes
 
 
292is_partially_uptodate:	yes
293error_remove_folio:	yes
294swap_activate:		no
295swap_deactivate:	no
296swap_rw:		yes, unlocks
297======================	======================== =========	===============
298
299->write_begin(), ->write_end() and ->read_folio() may be called from
300the request handler (/dev/loop).
301
302->read_folio() unlocks the folio, either synchronously or via I/O
303completion.
304
305->readahead() unlocks the folios that I/O is attempted on like ->read_folio().
 
 
 
306
307->writepage() is used for two purposes: for "memory cleansing" and for
308"sync".  These are quite different operations and the behaviour may differ
309depending upon the mode.
310
311If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
312it *must* start I/O against the page, even if that would involve
313blocking on in-progress I/O.
314
315If writepage is called for memory cleansing (sync_mode ==
316WBC_SYNC_NONE) then its role is to get as much writeout underway as
317possible.  So writepage should try to avoid blocking against
318currently-in-progress I/O.
319
320If the filesystem is not called for "sync" and it determines that it
321would need to block against in-progress I/O to be able to start new I/O
322against the page the filesystem should redirty the page with
323redirty_page_for_writepage(), then unlock the page and return zero.
324This may also be done to avoid internal deadlocks, but rarely.
325
326If the filesystem is called for sync then it must wait on any
327in-progress I/O and then start new I/O.
328
329The filesystem should unlock the page synchronously, before returning to the
330caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
331value. WRITEPAGE_ACTIVATE means that page cannot really be written out
332currently, and VM should stop calling ->writepage() on this page for some
333time. VM does this by moving page to the head of the active list, hence the
334name.
335
336Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
337and return zero, writepage *must* run set_page_writeback() against the page,
338followed by unlocking it.  Once set_page_writeback() has been run against the
339page, write I/O can be submitted and the write I/O completion handler must run
340end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
341filesystem must run end_page_writeback() against the page before returning from
342writepage.
343
344That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
345if the filesystem needs the page to be locked during writeout, that is ok, too,
346the page is allowed to be unlocked at any point in time between the calls to
347set_page_writeback() and end_page_writeback().
348
349Note, failure to run either redirty_page_for_writepage() or the combination of
350set_page_writeback()/end_page_writeback() on a page submitted to writepage
351will leave the page itself marked clean but it will be tagged as dirty in the
352radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
353in the filesystem like having dirty inodes at umount and losing written data.
354
355->writepages() is used for periodic writeback and for syscall-initiated
356sync operations.  The address_space should start I/O against at least
357``*nr_to_write`` pages.  ``*nr_to_write`` must be decremented for each page
358which is written.  The address_space implementation may write more (or less)
359pages than ``*nr_to_write`` asks for, but it should try to be reasonably close.
360If nr_to_write is NULL, all dirty pages must be written.
361
362writepages should _only_ write pages which are present on
363mapping->io_pages.
364
365->dirty_folio() is called from various places in the kernel when
366the target folio is marked as needing writeback.  The folio cannot be
367truncated because either the caller holds the folio lock, or the caller
368has found the folio while holding the page table lock which will block
369truncation.
370
371->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
372filesystems and by the swapper. The latter will eventually go away.  Please,
373keep it that way and don't breed new callers.
374
375->invalidate_folio() is called when the filesystem must attempt to drop
376some or all of the buffers from the page when it is being truncated. It
377returns zero on success.  The filesystem must exclusively acquire
378invalidate_lock before invalidating page cache in truncate / hole punch
379path (and thus calling into ->invalidate_folio) to block races between page
380cache invalidation and page cache filling functions (fault, read, ...).
381
382->release_folio() is called when the MM wants to make a change to the
383folio that would invalidate the filesystem's private data.  For example,
384it may be about to be removed from the address_space or split.  The folio
385is locked and not under writeback.  It may be dirty.  The gfp parameter
386is not usually used for allocation, but rather to indicate what the
387filesystem may do to attempt to free the private data.  The filesystem may
388return false to indicate that the folio's private data cannot be freed.
389If it returns true, it should have already removed the private data from
390the folio.  If a filesystem does not provide a ->release_folio method,
391the pagecache will assume that private data is buffer_heads and call
392try_to_free_buffers().
393
394->free_folio() is called when the kernel has dropped the folio
 
 
 
 
 
395from the page cache.
396
397->launder_folio() may be called prior to releasing a folio if
398it is still found to be dirty. It returns zero if the folio was successfully
399cleaned, or an error value if not. Note that in order to prevent the folio
400getting mapped back in and redirtied, it needs to be kept locked
401across the entire operation.
402
403->swap_activate() will be called to prepare the given file for swap.  It
404should perform any validation and preparation necessary to ensure that
405writes can be performed with minimal memory allocation.  It should call
406add_swap_extent(), or the helper iomap_swapfile_activate(), and return
407the number of extents added.  If IO should be submitted through
408->swap_rw(), it should set SWP_FS_OPS, otherwise IO will be submitted
409directly to the block device ``sis->bdev``.
410
411->swap_deactivate() will be called in the sys_swapoff()
412path after ->swap_activate() returned success.
413
414->swap_rw will be called for swap IO if SWP_FS_OPS was set by ->swap_activate().
415
416file_lock_operations
417====================
418
419prototypes::
420
421	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
422	void (*fl_release_private)(struct file_lock *);
423
424
425locking rules:
426
427===================	=============	=========
428ops			inode->i_lock	may block
429===================	=============	=========
430fl_copy_lock:		yes		no
431fl_release_private:	maybe		maybe[1]_
432===================	=============	=========
433
434.. [1]:
435   ->fl_release_private for flock or POSIX locks is currently allowed
436   to block. Leases however can still be freed while the i_lock is held and
437   so fl_release_private called on a lease should not block.
438
439lock_manager_operations
440=======================
441
442prototypes::
443
444	void (*lm_notify)(struct file_lock *);  /* unblock callback */
445	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
446	void (*lm_break)(struct file_lock *); /* break_lease callback */
447	int (*lm_change)(struct file_lock **, int);
448	bool (*lm_breaker_owns_lease)(struct file_lock *);
449        bool (*lm_lock_expirable)(struct file_lock *);
450        void (*lm_expire_lock)(void);
451
452locking rules:
453
454======================	=============	=================	=========
455ops			   flc_lock  	blocked_lock_lock	may block
456======================	=============	=================	=========
457lm_notify:		no      	yes			no
458lm_grant:		no		no			no
459lm_break:		yes		no			no
460lm_change		yes		no			no
461lm_breaker_owns_lease:	yes     	no			no
462lm_lock_expirable	yes		no			no
463lm_expire_lock		no		no			yes
464======================	=============	=================	=========
465
466buffer_head
467===========
468
469prototypes::
470
471	void (*b_end_io)(struct buffer_head *bh, int uptodate);
472
473locking rules:
474
475called from interrupts. In other words, extreme care is needed here.
476bh is locked, but that's all warranties we have here. Currently only RAID1,
477highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
478call this method upon the IO completion.
479
480block_device_operations
481=======================
482prototypes::
483
484	int (*open) (struct block_device *, fmode_t);
485	int (*release) (struct gendisk *, fmode_t);
486	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
487	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
488	int (*direct_access) (struct block_device *, sector_t, void **,
489				unsigned long *);
490	void (*unlock_native_capacity) (struct gendisk *);
 
491	int (*getgeo)(struct block_device *, struct hd_geometry *);
492	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
493
494locking rules:
495
496======================= ===================
497ops			open_mutex
498======================= ===================
499open:			yes
500release:		yes
501ioctl:			no
502compat_ioctl:		no
503direct_access:		no
504unlock_native_capacity:	no
 
505getgeo:			no
506swap_slot_free_notify:	no	(see below)
507======================= ===================
508
 
 
 
509swap_slot_free_notify is called with swap_lock and sometimes the page lock
510held.
511
512
513file_operations
514===============
515
516prototypes::
517
518	loff_t (*llseek) (struct file *, loff_t, int);
519	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
520	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
521	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
522	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
523	int (*iopoll) (struct kiocb *kiocb, bool spin);
524	int (*iterate_shared) (struct file *, struct dir_context *);
525	__poll_t (*poll) (struct file *, struct poll_table_struct *);
526	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
527	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
528	int (*mmap) (struct file *, struct vm_area_struct *);
529	int (*open) (struct inode *, struct file *);
530	int (*flush) (struct file *);
531	int (*release) (struct inode *, struct file *);
532	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
533	int (*fasync) (int, struct file *, int);
534	int (*lock) (struct file *, int, struct file_lock *);
 
 
 
 
 
 
 
 
535	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
536			unsigned long, unsigned long, unsigned long);
537	int (*check_flags)(int);
538	int (*flock) (struct file *, int, struct file_lock *);
539	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
540			size_t, unsigned int);
541	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
542			size_t, unsigned int);
543	int (*setlease)(struct file *, long, struct file_lock **, void **);
544	long (*fallocate)(struct file *, int, loff_t, loff_t);
545	void (*show_fdinfo)(struct seq_file *m, struct file *f);
546	unsigned (*mmap_capabilities)(struct file *);
547	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
548			loff_t, size_t, unsigned int);
549	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
550			struct file *file_out, loff_t pos_out,
551			loff_t len, unsigned int remap_flags);
552	int (*fadvise)(struct file *, loff_t, loff_t, int);
553
554locking rules:
555	All may block.
556
557->llseek() locking has moved from llseek to the individual llseek
558implementations.  If your fs is not using generic_file_llseek, you
559need to acquire and release the appropriate locks in your ->llseek().
560For many filesystems, it is probably safe to acquire the inode
561mutex or just to use i_size_read() instead.
562Note: this does not protect the file->f_pos against concurrent modifications
563since this is something the userspace has to take care about.
564
565->iterate_shared() is called with i_rwsem held for reading, and with the
566file f_pos_lock held exclusively
 
567
568->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
569Most instances call fasync_helper(), which does that maintenance, so it's
570not normally something one needs to worry about.  Return values > 0 will be
571mapped to zero in the VFS layer.
572
573->readdir() and ->ioctl() on directories must be changed. Ideally we would
574move ->readdir() to inode_operations and use a separate method for directory
575->ioctl() or kill the latter completely. One of the problems is that for
576anything that resembles union-mount we won't have a struct file for all
577components. And there are other reasons why the current interface is a mess...
578
579->read on directories probably must go away - we should just enforce -EISDIR
580in sys_read() and friends.
581
582->setlease operations should call generic_setlease() before or after setting
583the lease within the individual filesystem to record the result of the
584operation
585
586->fallocate implementation must be really careful to maintain page cache
587consistency when punching holes or performing other operations that invalidate
588page cache contents. Usually the filesystem needs to call
589truncate_inode_pages_range() to invalidate relevant range of the page cache.
590However the filesystem usually also needs to update its internal (and on disk)
591view of file offset -> disk block mapping. Until this update is finished, the
592filesystem needs to block page faults and reads from reloading now-stale page
593cache contents from the disk. Since VFS acquires mapping->invalidate_lock in
594shared mode when loading pages from disk (filemap_fault(), filemap_read(),
595readahead paths), the fallocate implementation must take the invalidate_lock to
596prevent reloading.
597
598->copy_file_range and ->remap_file_range implementations need to serialize
599against modifications of file data while the operation is running. For
600blocking changes through write(2) and similar operations inode->i_rwsem can be
601used. To block changes to file contents via a memory mapping during the
602operation, the filesystem must take mapping->invalidate_lock to coordinate
603with ->page_mkwrite.
604
605dquot_operations
606================
607
608prototypes::
609
610	int (*write_dquot) (struct dquot *);
611	int (*acquire_dquot) (struct dquot *);
612	int (*release_dquot) (struct dquot *);
613	int (*mark_dirty) (struct dquot *);
614	int (*write_info) (struct super_block *, int);
615
616These operations are intended to be more or less wrapping functions that ensure
617a proper locking wrt the filesystem and call the generic quota operations.
618
619What filesystem should expect from the generic quota functions:
620
621==============	============	=========================
622ops		FS recursion	Held locks when called
623==============	============	=========================
624write_dquot:	yes		dqonoff_sem or dqptr_sem
625acquire_dquot:	yes		dqonoff_sem or dqptr_sem
626release_dquot:	yes		dqonoff_sem or dqptr_sem
627mark_dirty:	no		-
628write_info:	yes		dqonoff_sem
629==============	============	=========================
630
631FS recursion means calling ->quota_read() and ->quota_write() from superblock
632operations.
633
634More details about quota locking can be found in fs/dquot.c.
635
636vm_operations_struct
637====================
638
639prototypes::
640
641	void (*open)(struct vm_area_struct *);
642	void (*close)(struct vm_area_struct *);
643	vm_fault_t (*fault)(struct vm_fault *);
644	vm_fault_t (*huge_fault)(struct vm_fault *, unsigned int order);
645	vm_fault_t (*map_pages)(struct vm_fault *, pgoff_t start, pgoff_t end);
646	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
647	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
648	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
649
650locking rules:
651
652=============	==========	===========================
653ops		mmap_lock	PageLocked(page)
654=============	==========	===========================
655open:		write
656close:		read/write
657fault:		read		can return with page locked
658huge_fault:	maybe-read
659map_pages:	maybe-read
660page_mkwrite:	read		can return with page locked
661pfn_mkwrite:	read
662access:		read
663=============	==========	===========================
664
665->fault() is called when a previously not present pte is about to be faulted
666in. The filesystem must find and return the page associated with the passed in
667"pgoff" in the vm_fault structure. If it is possible that the page may be
668truncated and/or invalidated, then the filesystem must lock invalidate_lock,
669then ensure the page is not already truncated (invalidate_lock will block
670subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
671locked. The VM will unlock the page.
672
673->huge_fault() is called when there is no PUD or PMD entry present.  This
674gives the filesystem the opportunity to install a PUD or PMD sized page.
675Filesystems can also use the ->fault method to return a PMD sized page,
676so implementing this function may not be necessary.  In particular,
677filesystems should not call filemap_fault() from ->huge_fault().
678The mmap_lock may not be held when this method is called.
679
680->map_pages() is called when VM asks to map easy accessible pages.
681Filesystem should find and map pages associated with offsets from "start_pgoff"
682till "end_pgoff". ->map_pages() is called with the RCU lock held and must
683not block.  If it's not possible to reach a page without blocking,
684filesystem should skip it. Filesystem should use set_pte_range() to setup
685page table entry. Pointer to entry associated with the page is passed in
686"pte" field in vm_fault structure. Pointers to entries for other offsets
687should be calculated relative to "pte".
688
689->page_mkwrite() is called when a previously read-only pte is about to become
690writeable. The filesystem again must ensure that there are no
691truncate/invalidate races or races with operations such as ->remap_file_range
692or ->copy_file_range, and then return with the page locked. Usually
693mapping->invalidate_lock is suitable for proper serialization. If the page has
694been truncated, the filesystem should not look up a new page like the ->fault()
695handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to
696retry the fault.
697
698->pfn_mkwrite() is the same as page_mkwrite but when the pte is
699VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
700VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
701after this call is to make the pte read-write, unless pfn_mkwrite returns
702an error.
703
704->access() is called when get_user_pages() fails in
705access_process_vm(), typically used to debug a process through
706/proc/pid/mem or ptrace.  This function is needed only for
707VM_IO | VM_PFNMAP VMAs.
708
709--------------------------------------------------------------------------------
710
711			Dubious stuff
712
713(if you break something or notice that it is broken and do not fix it yourself
714- at least put it here)
v5.9
  1=======
  2Locking
  3=======
  4
  5The text below describes the locking rules for VFS-related methods.
  6It is (believed to be) up-to-date. *Please*, if you change anything in
  7prototypes or locking protocols - update this file. And update the relevant
  8instances in the tree, don't leave that to maintainers of filesystems/devices/
  9etc. At the very least, put the list of dubious cases in the end of this file.
 10Don't turn it into log - maintainers of out-of-the-tree code are supposed to
 11be able to use diff(1).
 12
 13Thing currently missing here: socket operations. Alexey?
 14
 15dentry_operations
 16=================
 17
 18prototypes::
 19
 20	int (*d_revalidate)(struct dentry *, unsigned int);
 21	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 22	int (*d_hash)(const struct dentry *, struct qstr *);
 23	int (*d_compare)(const struct dentry *,
 24			unsigned int, const char *, const struct qstr *);
 25	int (*d_delete)(struct dentry *);
 26	int (*d_init)(struct dentry *);
 27	void (*d_release)(struct dentry *);
 28	void (*d_iput)(struct dentry *, struct inode *);
 29	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
 30	struct vfsmount *(*d_automount)(struct path *path);
 31	int (*d_manage)(const struct path *, bool);
 32	struct dentry *(*d_real)(struct dentry *, const struct inode *);
 33
 34locking rules:
 35
 36================== ===========	========	==============	========
 37ops		   rename_lock	->d_lock	may block	rcu-walk
 38================== ===========	========	==============	========
 39d_revalidate:	   no		no		yes (ref-walk)	maybe
 40d_weak_revalidate: no		no		yes	 	no
 41d_hash		   no		no		no		maybe
 42d_compare:	   yes		no		no		maybe
 43d_delete:	   no		yes		no		no
 44d_init:		   no		no		yes		no
 45d_release:	   no		no		yes		no
 46d_prune:           no		yes		no		no
 47d_iput:		   no		no		yes		no
 48d_dname:	   no		no		no		no
 49d_automount:	   no		no		yes		no
 50d_manage:	   no		no		yes (ref-walk)	maybe
 51d_real		   no		no		yes 		no
 52================== ===========	========	==============	========
 53
 54inode_operations
 55================
 56
 57prototypes::
 58
 59	int (*create) (struct inode *,struct dentry *,umode_t, bool);
 60	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 61	int (*link) (struct dentry *,struct inode *,struct dentry *);
 62	int (*unlink) (struct inode *,struct dentry *);
 63	int (*symlink) (struct inode *,struct dentry *,const char *);
 64	int (*mkdir) (struct inode *,struct dentry *,umode_t);
 65	int (*rmdir) (struct inode *,struct dentry *);
 66	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 67	int (*rename) (struct inode *, struct dentry *,
 68			struct inode *, struct dentry *, unsigned int);
 69	int (*readlink) (struct dentry *, char __user *,int);
 70	const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
 71	void (*truncate) (struct inode *);
 72	int (*permission) (struct inode *, int, unsigned int);
 73	int (*get_acl)(struct inode *, int);
 74	int (*setattr) (struct dentry *, struct iattr *);
 75	int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
 76	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 77	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 78	void (*update_time)(struct inode *, struct timespec *, int);
 79	int (*atomic_open)(struct inode *, struct dentry *,
 80				struct file *, unsigned open_flag,
 81				umode_t create_mode);
 82	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 
 
 
 
 
 83
 84locking rules:
 85	all may block
 86
 87============	=============================================
 88ops		i_rwsem(inode)
 89============	=============================================
 90lookup:		shared
 91create:		exclusive
 92link:		exclusive (both)
 93mknod:		exclusive
 94symlink:	exclusive
 95mkdir:		exclusive
 96unlink:		exclusive (both)
 97rmdir:		exclusive (both)(see below)
 98rename:		exclusive (all)	(see below)
 99readlink:	no
100get_link:	no
101setattr:	exclusive
102permission:	no (may not block if called in rcu-walk mode)
 
103get_acl:	no
104getattr:	no
105listxattr:	no
106fiemap:		no
107update_time:	no
108atomic_open:	shared (exclusive if O_CREAT is set in open flags)
109tmpfile:	no
110============	=============================================
 
 
 
111
112
113	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem
114	exclusive on victim.
115	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
 
 
 
116
117See Documentation/filesystems/directory-locking.rst for more detailed discussion
118of the locking scheme for directory operations.
119
120xattr_handler operations
121========================
122
123prototypes::
124
125	bool (*list)(struct dentry *dentry);
126	int (*get)(const struct xattr_handler *handler, struct dentry *dentry,
127		   struct inode *inode, const char *name, void *buffer,
128		   size_t size);
129	int (*set)(const struct xattr_handler *handler, struct dentry *dentry,
130		   struct inode *inode, const char *name, const void *buffer,
131		   size_t size, int flags);
 
132
133locking rules:
134	all may block
135
136=====		==============
137ops		i_rwsem(inode)
138=====		==============
139list:		no
140get:		no
141set:		exclusive
142=====		==============
143
144super_operations
145================
146
147prototypes::
148
149	struct inode *(*alloc_inode)(struct super_block *sb);
150	void (*free_inode)(struct inode *);
151	void (*destroy_inode)(struct inode *);
152	void (*dirty_inode) (struct inode *, int flags);
153	int (*write_inode) (struct inode *, struct writeback_control *wbc);
154	int (*drop_inode) (struct inode *);
155	void (*evict_inode) (struct inode *);
156	void (*put_super) (struct super_block *);
157	int (*sync_fs)(struct super_block *sb, int wait);
158	int (*freeze_fs) (struct super_block *);
159	int (*unfreeze_fs) (struct super_block *);
160	int (*statfs) (struct dentry *, struct kstatfs *);
161	int (*remount_fs) (struct super_block *, int *, char *);
162	void (*umount_begin) (struct super_block *);
163	int (*show_options)(struct seq_file *, struct dentry *);
164	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
165	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
166	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
167
168locking rules:
169	All may block [not true, see below]
170
171======================	============	========================
172ops			s_umount	note
173======================	============	========================
174alloc_inode:
175free_inode:				called from RCU callback
176destroy_inode:
177dirty_inode:
178write_inode:
179drop_inode:				!!!inode->i_lock!!!
180evict_inode:
181put_super:		write
182sync_fs:		read
183freeze_fs:		write
184unfreeze_fs:		write
185statfs:			maybe(read)	(see below)
186remount_fs:		write
187umount_begin:		no
188show_options:		no		(namespace_sem)
189quota_read:		no		(see below)
190quota_write:		no		(see below)
191bdev_try_to_free_page:	no		(see below)
192======================	============	========================
193
194->statfs() has s_umount (shared) when called by ustat(2) (native or
195compat), but that's an accident of bad API; s_umount is used to pin
196the superblock down when we only have dev_t given us by userland to
197identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
198doesn't hold it when calling ->statfs() - superblock is pinned down
199by resolving the pathname passed to syscall.
200
201->quota_read() and ->quota_write() functions are both guaranteed to
202be the only ones operating on the quota file by the quota code (via
203dqio_sem) (unless an admin really wants to screw up something and
204writes to quota files with quotas on). For other details about locking
205see also dquot_operations section.
206
207->bdev_try_to_free_page is called from the ->releasepage handler of
208the block device inode.  See there for more details.
209
210file_system_type
211================
212
213prototypes::
214
215	struct dentry *(*mount) (struct file_system_type *, int,
216		       const char *, void *);
217	void (*kill_sb) (struct super_block *);
218
219locking rules:
220
221=======		=========
222ops		may block
223=======		=========
224mount		yes
225kill_sb		yes
226=======		=========
227
228->mount() returns ERR_PTR or the root dentry; its superblock should be locked
229on return.
230
231->kill_sb() takes a write-locked superblock, does all shutdown work on it,
232unlocks and drops the reference.
233
234address_space_operations
235========================
236prototypes::
237
238	int (*writepage)(struct page *page, struct writeback_control *wbc);
239	int (*readpage)(struct file *, struct page *);
240	int (*writepages)(struct address_space *, struct writeback_control *);
241	int (*set_page_dirty)(struct page *page);
242	void (*readahead)(struct readahead_control *);
243	int (*readpages)(struct file *filp, struct address_space *mapping,
244			struct list_head *pages, unsigned nr_pages);
245	int (*write_begin)(struct file *, struct address_space *mapping,
246				loff_t pos, unsigned len, unsigned flags,
247				struct page **pagep, void **fsdata);
248	int (*write_end)(struct file *, struct address_space *mapping,
249				loff_t pos, unsigned len, unsigned copied,
250				struct page *page, void *fsdata);
251	sector_t (*bmap)(struct address_space *, sector_t);
252	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
253	int (*releasepage) (struct page *, int);
254	void (*freepage)(struct page *);
255	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
256	bool (*isolate_page) (struct page *, isolate_mode_t);
257	int (*migratepage)(struct address_space *, struct page *, struct page *);
258	void (*putback_page) (struct page *);
259	int (*launder_page)(struct page *);
260	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
261	int (*error_remove_page)(struct address_space *, struct page *);
262	int (*swap_activate)(struct file *);
263	int (*swap_deactivate)(struct file *);
 
264
265locking rules:
266	All except set_page_dirty and freepage may block
267
268======================	======================== =========
269ops			PageLocked(page)	 i_rwsem
270======================	======================== =========
271writepage:		yes, unlocks (see below)
272readpage:		yes, unlocks
273writepages:
274set_page_dirty		no
275readahead:		yes, unlocks
276readpages:		no
277write_begin:		locks the page		 exclusive
278write_end:		yes, unlocks		 exclusive
279bmap:
280invalidatepage:		yes
281releasepage:		yes
282freepage:		yes
283direct_IO:
284isolate_page:		yes
285migratepage:		yes (both)
286putback_page:		yes
287launder_page:		yes
288is_partially_uptodate:	yes
289error_remove_page:	yes
290swap_activate:		no
291swap_deactivate:	no
292======================	======================== =========
 
293
294->write_begin(), ->write_end() and ->readpage() may be called from
295the request handler (/dev/loop).
296
297->readpage() unlocks the page, either synchronously or via I/O
298completion.
299
300->readahead() unlocks the pages that I/O is attempted on like ->readpage().
301
302->readpages() populates the pagecache with the passed pages and starts
303I/O against them.  They come unlocked upon I/O completion.
304
305->writepage() is used for two purposes: for "memory cleansing" and for
306"sync".  These are quite different operations and the behaviour may differ
307depending upon the mode.
308
309If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
310it *must* start I/O against the page, even if that would involve
311blocking on in-progress I/O.
312
313If writepage is called for memory cleansing (sync_mode ==
314WBC_SYNC_NONE) then its role is to get as much writeout underway as
315possible.  So writepage should try to avoid blocking against
316currently-in-progress I/O.
317
318If the filesystem is not called for "sync" and it determines that it
319would need to block against in-progress I/O to be able to start new I/O
320against the page the filesystem should redirty the page with
321redirty_page_for_writepage(), then unlock the page and return zero.
322This may also be done to avoid internal deadlocks, but rarely.
323
324If the filesystem is called for sync then it must wait on any
325in-progress I/O and then start new I/O.
326
327The filesystem should unlock the page synchronously, before returning to the
328caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
329value. WRITEPAGE_ACTIVATE means that page cannot really be written out
330currently, and VM should stop calling ->writepage() on this page for some
331time. VM does this by moving page to the head of the active list, hence the
332name.
333
334Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
335and return zero, writepage *must* run set_page_writeback() against the page,
336followed by unlocking it.  Once set_page_writeback() has been run against the
337page, write I/O can be submitted and the write I/O completion handler must run
338end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
339filesystem must run end_page_writeback() against the page before returning from
340writepage.
341
342That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
343if the filesystem needs the page to be locked during writeout, that is ok, too,
344the page is allowed to be unlocked at any point in time between the calls to
345set_page_writeback() and end_page_writeback().
346
347Note, failure to run either redirty_page_for_writepage() or the combination of
348set_page_writeback()/end_page_writeback() on a page submitted to writepage
349will leave the page itself marked clean but it will be tagged as dirty in the
350radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
351in the filesystem like having dirty inodes at umount and losing written data.
352
353->writepages() is used for periodic writeback and for syscall-initiated
354sync operations.  The address_space should start I/O against at least
355``*nr_to_write`` pages.  ``*nr_to_write`` must be decremented for each page
356which is written.  The address_space implementation may write more (or less)
357pages than ``*nr_to_write`` asks for, but it should try to be reasonably close.
358If nr_to_write is NULL, all dirty pages must be written.
359
360writepages should _only_ write pages which are present on
361mapping->io_pages.
362
363->set_page_dirty() is called from various places in the kernel
364when the target page is marked as needing writeback.  It may be called
365under spinlock (it cannot block) and is sometimes called with the page
366not locked.
 
367
368->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
369filesystems and by the swapper. The latter will eventually go away.  Please,
370keep it that way and don't breed new callers.
371
372->invalidatepage() is called when the filesystem must attempt to drop
373some or all of the buffers from the page when it is being truncated. It
374returns zero on success. If ->invalidatepage is zero, the kernel uses
375block_invalidatepage() instead.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
377->releasepage() is called when the kernel is about to try to drop the
378buffers from the page in preparation for freeing it.  It returns zero to
379indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
380the kernel assumes that the fs has no private interest in the buffers.
381
382->freepage() is called when the kernel is done dropping the page
383from the page cache.
384
385->launder_page() may be called prior to releasing a page if
386it is still found to be dirty. It returns zero if the page was successfully
387cleaned, or an error value if not. Note that in order to prevent the page
388getting mapped back in and redirtied, it needs to be kept locked
389across the entire operation.
390
391->swap_activate will be called with a non-zero argument on
392files backing (non block device backed) swapfiles. A return value
393of zero indicates success, in which case this file can be used for
394backing swapspace. The swapspace operations will be proxied to the
395address space operations.
 
 
396
397->swap_deactivate() will be called in the sys_swapoff()
398path after ->swap_activate() returned success.
399
 
 
400file_lock_operations
401====================
402
403prototypes::
404
405	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
406	void (*fl_release_private)(struct file_lock *);
407
408
409locking rules:
410
411===================	=============	=========
412ops			inode->i_lock	may block
413===================	=============	=========
414fl_copy_lock:		yes		no
415fl_release_private:	maybe		maybe[1]_
416===================	=============	=========
417
418.. [1]:
419   ->fl_release_private for flock or POSIX locks is currently allowed
420   to block. Leases however can still be freed while the i_lock is held and
421   so fl_release_private called on a lease should not block.
422
423lock_manager_operations
424=======================
425
426prototypes::
427
428	void (*lm_notify)(struct file_lock *);  /* unblock callback */
429	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
430	void (*lm_break)(struct file_lock *); /* break_lease callback */
431	int (*lm_change)(struct file_lock **, int);
432	bool (*lm_breaker_owns_lease)(struct file_lock *);
 
 
433
434locking rules:
435
436======================	=============	=================	=========
437ops			inode->i_lock	blocked_lock_lock	may block
438======================	=============	=================	=========
439lm_notify:		yes		yes			no
440lm_grant:		no		no			no
441lm_break:		yes		no			no
442lm_change		yes		no			no
443lm_breaker_owns_lease:	no		no			no
 
 
444======================	=============	=================	=========
445
446buffer_head
447===========
448
449prototypes::
450
451	void (*b_end_io)(struct buffer_head *bh, int uptodate);
452
453locking rules:
454
455called from interrupts. In other words, extreme care is needed here.
456bh is locked, but that's all warranties we have here. Currently only RAID1,
457highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
458call this method upon the IO completion.
459
460block_device_operations
461=======================
462prototypes::
463
464	int (*open) (struct block_device *, fmode_t);
465	int (*release) (struct gendisk *, fmode_t);
466	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
467	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
468	int (*direct_access) (struct block_device *, sector_t, void **,
469				unsigned long *);
470	void (*unlock_native_capacity) (struct gendisk *);
471	int (*revalidate_disk) (struct gendisk *);
472	int (*getgeo)(struct block_device *, struct hd_geometry *);
473	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
474
475locking rules:
476
477======================= ===================
478ops			bd_mutex
479======================= ===================
480open:			yes
481release:		yes
482ioctl:			no
483compat_ioctl:		no
484direct_access:		no
485unlock_native_capacity:	no
486revalidate_disk:	no
487getgeo:			no
488swap_slot_free_notify:	no	(see below)
489======================= ===================
490
491unlock_native_capacity and revalidate_disk are called only from
492check_disk_change().
493
494swap_slot_free_notify is called with swap_lock and sometimes the page lock
495held.
496
497
498file_operations
499===============
500
501prototypes::
502
503	loff_t (*llseek) (struct file *, loff_t, int);
504	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
505	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
506	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
507	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
508	int (*iterate) (struct file *, struct dir_context *);
509	int (*iterate_shared) (struct file *, struct dir_context *);
510	__poll_t (*poll) (struct file *, struct poll_table_struct *);
511	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
512	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
513	int (*mmap) (struct file *, struct vm_area_struct *);
514	int (*open) (struct inode *, struct file *);
515	int (*flush) (struct file *);
516	int (*release) (struct inode *, struct file *);
517	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
518	int (*fasync) (int, struct file *, int);
519	int (*lock) (struct file *, int, struct file_lock *);
520	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
521			loff_t *);
522	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
523			loff_t *);
524	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
525			void __user *);
526	ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
527			loff_t *, int);
528	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
529			unsigned long, unsigned long, unsigned long);
530	int (*check_flags)(int);
531	int (*flock) (struct file *, int, struct file_lock *);
532	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
533			size_t, unsigned int);
534	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
535			size_t, unsigned int);
536	int (*setlease)(struct file *, long, struct file_lock **, void **);
537	long (*fallocate)(struct file *, int, loff_t, loff_t);
 
 
 
 
 
 
 
 
538
539locking rules:
540	All may block.
541
542->llseek() locking has moved from llseek to the individual llseek
543implementations.  If your fs is not using generic_file_llseek, you
544need to acquire and release the appropriate locks in your ->llseek().
545For many filesystems, it is probably safe to acquire the inode
546mutex or just to use i_size_read() instead.
547Note: this does not protect the file->f_pos against concurrent modifications
548since this is something the userspace has to take care about.
549
550->iterate() is called with i_rwsem exclusive.
551
552->iterate_shared() is called with i_rwsem at least shared.
553
554->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
555Most instances call fasync_helper(), which does that maintenance, so it's
556not normally something one needs to worry about.  Return values > 0 will be
557mapped to zero in the VFS layer.
558
559->readdir() and ->ioctl() on directories must be changed. Ideally we would
560move ->readdir() to inode_operations and use a separate method for directory
561->ioctl() or kill the latter completely. One of the problems is that for
562anything that resembles union-mount we won't have a struct file for all
563components. And there are other reasons why the current interface is a mess...
564
565->read on directories probably must go away - we should just enforce -EISDIR
566in sys_read() and friends.
567
568->setlease operations should call generic_setlease() before or after setting
569the lease within the individual filesystem to record the result of the
570operation
571
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
572dquot_operations
573================
574
575prototypes::
576
577	int (*write_dquot) (struct dquot *);
578	int (*acquire_dquot) (struct dquot *);
579	int (*release_dquot) (struct dquot *);
580	int (*mark_dirty) (struct dquot *);
581	int (*write_info) (struct super_block *, int);
582
583These operations are intended to be more or less wrapping functions that ensure
584a proper locking wrt the filesystem and call the generic quota operations.
585
586What filesystem should expect from the generic quota functions:
587
588==============	============	=========================
589ops		FS recursion	Held locks when called
590==============	============	=========================
591write_dquot:	yes		dqonoff_sem or dqptr_sem
592acquire_dquot:	yes		dqonoff_sem or dqptr_sem
593release_dquot:	yes		dqonoff_sem or dqptr_sem
594mark_dirty:	no		-
595write_info:	yes		dqonoff_sem
596==============	============	=========================
597
598FS recursion means calling ->quota_read() and ->quota_write() from superblock
599operations.
600
601More details about quota locking can be found in fs/dquot.c.
602
603vm_operations_struct
604====================
605
606prototypes::
607
608	void (*open)(struct vm_area_struct*);
609	void (*close)(struct vm_area_struct*);
610	vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
 
 
611	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
612	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
613	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
614
615locking rules:
616
617=============	=========	===========================
618ops		mmap_lock	PageLocked(page)
619=============	=========	===========================
620open:		yes
621close:		yes
622fault:		yes		can return with page locked
623map_pages:	yes
624page_mkwrite:	yes		can return with page locked
625pfn_mkwrite:	yes
626access:		yes
627=============	=========	===========================
628
629->fault() is called when a previously not present pte is about
630to be faulted in. The filesystem must find and return the page associated
631with the passed in "pgoff" in the vm_fault structure. If it is possible that
632the page may be truncated and/or invalidated, then the filesystem must lock
633the page, then ensure it is not already truncated (the page lock will block
 
634subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
635locked. The VM will unlock the page.
636
 
 
 
 
 
 
 
637->map_pages() is called when VM asks to map easy accessible pages.
638Filesystem should find and map pages associated with offsets from "start_pgoff"
639till "end_pgoff". ->map_pages() is called with page table locked and must
640not block.  If it's not possible to reach a page without blocking,
641filesystem should skip it. Filesystem should use do_set_pte() to setup
642page table entry. Pointer to entry associated with the page is passed in
643"pte" field in vm_fault structure. Pointers to entries for other offsets
644should be calculated relative to "pte".
645
646->page_mkwrite() is called when a previously read-only pte is
647about to become writeable. The filesystem again must ensure that there are
648no truncate/invalidate races, and then return with the page locked. If
649the page has been truncated, the filesystem should not look up a new page
650like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
651will cause the VM to retry the fault.
 
 
652
653->pfn_mkwrite() is the same as page_mkwrite but when the pte is
654VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
655VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
656after this call is to make the pte read-write, unless pfn_mkwrite returns
657an error.
658
659->access() is called when get_user_pages() fails in
660access_process_vm(), typically used to debug a process through
661/proc/pid/mem or ptrace.  This function is needed only for
662VM_IO | VM_PFNMAP VMAs.
663
664--------------------------------------------------------------------------------
665
666			Dubious stuff
667
668(if you break something or notice that it is broken and do not fix it yourself
669- at least put it here)