xref: /linux/Documentation/filesystems/locking.rst (revision 4fd18fc38757217c746aa063ba9e4729814dc737)
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
491swap_slot_free_notify is called with swap_lock and sometimes the page lock
492held.
493
494
495file_operations
496===============
497
498prototypes::
499
500	loff_t (*llseek) (struct file *, loff_t, int);
501	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
502	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
503	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
504	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
505	int (*iterate) (struct file *, struct dir_context *);
506	int (*iterate_shared) (struct file *, struct dir_context *);
507	__poll_t (*poll) (struct file *, struct poll_table_struct *);
508	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
509	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
510	int (*mmap) (struct file *, struct vm_area_struct *);
511	int (*open) (struct inode *, struct file *);
512	int (*flush) (struct file *);
513	int (*release) (struct inode *, struct file *);
514	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
515	int (*fasync) (int, struct file *, int);
516	int (*lock) (struct file *, int, struct file_lock *);
517	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
518			loff_t *);
519	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
520			loff_t *);
521	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
522			void __user *);
523	ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
524			loff_t *, int);
525	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
526			unsigned long, unsigned long, unsigned long);
527	int (*check_flags)(int);
528	int (*flock) (struct file *, int, struct file_lock *);
529	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
530			size_t, unsigned int);
531	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
532			size_t, unsigned int);
533	int (*setlease)(struct file *, long, struct file_lock **, void **);
534	long (*fallocate)(struct file *, int, loff_t, loff_t);
535
536locking rules:
537	All may block.
538
539->llseek() locking has moved from llseek to the individual llseek
540implementations.  If your fs is not using generic_file_llseek, you
541need to acquire and release the appropriate locks in your ->llseek().
542For many filesystems, it is probably safe to acquire the inode
543mutex or just to use i_size_read() instead.
544Note: this does not protect the file->f_pos against concurrent modifications
545since this is something the userspace has to take care about.
546
547->iterate() is called with i_rwsem exclusive.
548
549->iterate_shared() is called with i_rwsem at least shared.
550
551->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
552Most instances call fasync_helper(), which does that maintenance, so it's
553not normally something one needs to worry about.  Return values > 0 will be
554mapped to zero in the VFS layer.
555
556->readdir() and ->ioctl() on directories must be changed. Ideally we would
557move ->readdir() to inode_operations and use a separate method for directory
558->ioctl() or kill the latter completely. One of the problems is that for
559anything that resembles union-mount we won't have a struct file for all
560components. And there are other reasons why the current interface is a mess...
561
562->read on directories probably must go away - we should just enforce -EISDIR
563in sys_read() and friends.
564
565->setlease operations should call generic_setlease() before or after setting
566the lease within the individual filesystem to record the result of the
567operation
568
569dquot_operations
570================
571
572prototypes::
573
574	int (*write_dquot) (struct dquot *);
575	int (*acquire_dquot) (struct dquot *);
576	int (*release_dquot) (struct dquot *);
577	int (*mark_dirty) (struct dquot *);
578	int (*write_info) (struct super_block *, int);
579
580These operations are intended to be more or less wrapping functions that ensure
581a proper locking wrt the filesystem and call the generic quota operations.
582
583What filesystem should expect from the generic quota functions:
584
585==============	============	=========================
586ops		FS recursion	Held locks when called
587==============	============	=========================
588write_dquot:	yes		dqonoff_sem or dqptr_sem
589acquire_dquot:	yes		dqonoff_sem or dqptr_sem
590release_dquot:	yes		dqonoff_sem or dqptr_sem
591mark_dirty:	no		-
592write_info:	yes		dqonoff_sem
593==============	============	=========================
594
595FS recursion means calling ->quota_read() and ->quota_write() from superblock
596operations.
597
598More details about quota locking can be found in fs/dquot.c.
599
600vm_operations_struct
601====================
602
603prototypes::
604
605	void (*open)(struct vm_area_struct*);
606	void (*close)(struct vm_area_struct*);
607	vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
608	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
609	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
610	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
611
612locking rules:
613
614=============	=========	===========================
615ops		mmap_lock	PageLocked(page)
616=============	=========	===========================
617open:		yes
618close:		yes
619fault:		yes		can return with page locked
620map_pages:	yes
621page_mkwrite:	yes		can return with page locked
622pfn_mkwrite:	yes
623access:		yes
624=============	=========	===========================
625
626->fault() is called when a previously not present pte is about
627to be faulted in. The filesystem must find and return the page associated
628with the passed in "pgoff" in the vm_fault structure. If it is possible that
629the page may be truncated and/or invalidated, then the filesystem must lock
630the page, then ensure it is not already truncated (the page lock will block
631subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
632locked. The VM will unlock the page.
633
634->map_pages() is called when VM asks to map easy accessible pages.
635Filesystem should find and map pages associated with offsets from "start_pgoff"
636till "end_pgoff". ->map_pages() is called with page table locked and must
637not block.  If it's not possible to reach a page without blocking,
638filesystem should skip it. Filesystem should use do_set_pte() to setup
639page table entry. Pointer to entry associated with the page is passed in
640"pte" field in vm_fault structure. Pointers to entries for other offsets
641should be calculated relative to "pte".
642
643->page_mkwrite() is called when a previously read-only pte is
644about to become writeable. The filesystem again must ensure that there are
645no truncate/invalidate races, and then return with the page locked. If
646the page has been truncated, the filesystem should not look up a new page
647like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
648will cause the VM to retry the fault.
649
650->pfn_mkwrite() is the same as page_mkwrite but when the pte is
651VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
652VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
653after this call is to make the pte read-write, unless pfn_mkwrite returns
654an error.
655
656->access() is called when get_user_pages() fails in
657access_process_vm(), typically used to debug a process through
658/proc/pid/mem or ptrace.  This function is needed only for
659VM_IO | VM_PFNMAP VMAs.
660
661--------------------------------------------------------------------------------
662
663			Dubious stuff
664
665(if you break something or notice that it is broken and do not fix it yourself
666- at least put it here)
667