About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / filesystems / Locking


Based on kernel version 4.16.1. Page generated on 2018-04-09 11:53 EST.

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


About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog