| blob | 204dd3ea36bb3a5989eda6e62c4162afed57ae94 |
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?
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 *);
26 locking rules:
27 rename_lock ->d_lock may block rcu-walk
28 d_revalidate: no no yes (ref-walk) maybe
29 d_weak_revalidate:no no yes no
30 d_hash no no no maybe
31 d_compare: yes no no maybe
32 d_delete: no yes no no
33 d_init: no no yes no
34 d_release: no no yes no
35 d_prune: no yes no no
36 d_iput: no no yes no
37 d_dname: no no no no
38 d_automount: no no yes no
39 d_manage: no no yes (ref-walk) maybe
40 d_real no no yes no
42 --------------------------- inode_operations ---------------------------
43 prototypes:
44 int (*create) (struct inode *,struct dentry *,umode_t, bool);
45 struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
46 int (*link) (struct dentry *,struct inode *,struct dentry *);
47 int (*unlink) (struct inode *,struct dentry *);
48 int (*symlink) (struct inode *,struct dentry *,const char *);
49 int (*mkdir) (struct inode *,struct dentry *,umode_t);
50 int (*rmdir) (struct inode *,struct dentry *);
51 int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
52 int (*rename) (struct inode *, struct dentry *,
53 struct inode *, struct dentry *, unsigned int);
54 int (*readlink) (struct dentry *, char __user *,int);
55 const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *);
56 void (*truncate) (struct inode *);
57 int (*permission) (struct inode *, int, unsigned int);
58 int (*get_acl)(struct inode *, int);
59 int (*setattr) (struct dentry *, struct iattr *);
60 int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
61 ssize_t (*listxattr) (struct dentry *, char *, size_t);
62 int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
63 void (*update_time)(struct inode *, struct timespec *, int);
64 int (*atomic_open)(struct inode *, struct dentry *,
65 struct file *, unsigned open_flag,
66 umode_t create_mode);
67 int (*tmpfile) (struct inode *, struct dentry *, umode_t);
69 locking rules:
70 all may block
71 i_rwsem(inode)
72 lookup: shared
73 create: exclusive
74 link: exclusive (both)
75 mknod: exclusive
76 symlink: exclusive
77 mkdir: exclusive
78 unlink: exclusive (both)
79 rmdir: exclusive (both)(see below)
80 rename: exclusive (all) (see below)
81 readlink: no
82 get_link: no
83 setattr: exclusive
84 permission: no (may not block if called in rcu-walk mode)
85 get_acl: no
86 getattr: no
87 listxattr: no
88 fiemap: no
89 update_time: no
90 atomic_open: exclusive
91 tmpfile: no
94 Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem
95 exclusive on victim.
96 cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
98 See Documentation/filesystems/directory-locking for more detailed discussion
99 of the locking scheme for directory operations.
101 ----------------------- xattr_handler operations -----------------------
102 prototypes:
103 bool (*list)(struct dentry *dentry);
104 int (*get)(const struct xattr_handler *handler, struct dentry *dentry,
105 struct inode *inode, const char *name, void *buffer,
106 size_t size);
107 int (*set)(const struct xattr_handler *handler, struct dentry *dentry,
108 struct inode *inode, const char *name, const void *buffer,
109 size_t size, int flags);
111 locking rules:
112 all may block
113 i_rwsem(inode)
114 list: no
115 get: no
116 set: exclusive
118 --------------------------- super_operations ---------------------------
119 prototypes:
120 struct inode *(*alloc_inode)(struct super_block *sb);
121 void (*free_inode)(struct inode *);
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);
139 locking rules:
140 All may block [not true, see below]
141 s_umount
142 alloc_inode:
143 free_inode: called from RCU callback
144 destroy_inode:
145 dirty_inode:
146 write_inode:
147 drop_inode: !!!inode->i_lock!!!
148 evict_inode:
149 put_super: write
150 sync_fs: read
151 freeze_fs: write
152 unfreeze_fs: write
153 statfs: maybe(read) (see below)
154 remount_fs: write
155 umount_begin: no
156 show_options: no (namespace_sem)
157 quota_read: no (see below)
158 quota_write: no (see below)
159 bdev_try_to_free_page: no (see below)
161 ->statfs() has s_umount (shared) when called by ustat(2) (native or
162 compat), but that's an accident of bad API; s_umount is used to pin
163 the superblock down when we only have dev_t given us by userland to
164 identify the superblock. Everything else (statfs(), fstatfs(), etc.)
165 doesn't hold it when calling ->statfs() - superblock is pinned down
166 by resolving the pathname passed to syscall.
167 ->quota_read() and ->quota_write() functions are both guaranteed to
168 be the only ones operating on the quota file by the quota code (via
169 dqio_sem) (unless an admin really wants to screw up something and
170 writes to quota files with quotas on). For other details about locking
171 see also dquot_operations section.
172 ->bdev_try_to_free_page is called from the ->releasepage handler of
173 the block device inode. See there for more details.
175 --------------------------- file_system_type ---------------------------
176 prototypes:
177 struct dentry *(*mount) (struct file_system_type *, int,
178 const char *, void *);
179 void (*kill_sb) (struct super_block *);
180 locking rules:
181 may block
182 mount yes
183 kill_sb yes
185 ->mount() returns ERR_PTR or the root dentry; its superblock should be locked
186 on return.
187 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
188 unlocks and drops the reference.
190 --------------------------- address_space_operations --------------------------
191 prototypes:
192 int (*writepage)(struct page *page, struct writeback_control *wbc);
193 int (*readpage)(struct file *, struct page *);
194 int (*writepages)(struct address_space *, struct writeback_control *);
195 int (*set_page_dirty)(struct page *page);
196 int (*readpages)(struct file *filp, struct address_space *mapping,
197 struct list_head *pages, unsigned nr_pages);
198 int (*write_begin)(struct file *, struct address_space *mapping,
199 loff_t pos, unsigned len, unsigned flags,
200 struct page **pagep, void **fsdata);
201 int (*write_end)(struct file *, struct address_space *mapping,
202 loff_t pos, unsigned len, unsigned copied,
203 struct page *page, void *fsdata);
204 sector_t (*bmap)(struct address_space *, sector_t);
205 void (*invalidatepage) (struct page *, unsigned int, unsigned int);
206 int (*releasepage) (struct page *, int);
207 void (*freepage)(struct page *);
208 int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
209 bool (*isolate_page) (struct page *, isolate_mode_t);
210 int (*migratepage)(struct address_space *, struct page *, struct page *);
211 void (*putback_page) (struct page *);
212 int (*launder_page)(struct page *);
213 int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
214 int (*error_remove_page)(struct address_space *, struct page *);
215 int (*swap_activate)(struct file *);
216 int (*swap_deactivate)(struct file *);
218 locking rules:
219 All except set_page_dirty and freepage may block
221 PageLocked(page) i_rwsem
222 writepage: yes, unlocks (see below)
223 readpage: yes, unlocks
224 writepages:
225 set_page_dirty no
226 readpages:
227 write_begin: locks the page exclusive
228 write_end: yes, unlocks exclusive
229 bmap:
230 invalidatepage: yes
231 releasepage: yes
232 freepage: yes
233 direct_IO:
234 isolate_page: yes
235 migratepage: yes (both)
236 putback_page: yes
237 launder_page: yes
238 is_partially_uptodate: yes
239 error_remove_page: yes
240 swap_activate: no
241 swap_deactivate: no
243 ->write_begin(), ->write_end() and ->readpage() may be called from
244 the request handler (/dev/loop).
246 ->readpage() unlocks the page, either synchronously or via I/O
247 completion.
249 ->readpages() populates the pagecache with the passed pages and starts
250 I/O against them. They come unlocked upon I/O completion.
252 ->writepage() is used for two purposes: for "memory cleansing" and for
253 "sync". These are quite different operations and the behaviour may differ
254 depending upon the mode.
256 If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
257 it *must* start I/O against the page, even if that would involve
258 blocking on in-progress I/O.
260 If writepage is called for memory cleansing (sync_mode ==
261 WBC_SYNC_NONE) then its role is to get as much writeout underway as
262 possible. So writepage should try to avoid blocking against
263 currently-in-progress I/O.
265 If the filesystem is not called for "sync" and it determines that it
266 would need to block against in-progress I/O to be able to start new I/O
267 against the page the filesystem should redirty the page with
268 redirty_page_for_writepage(), then unlock the page and return zero.
269 This may also be done to avoid internal deadlocks, but rarely.
271 If the filesystem is called for sync then it must wait on any
272 in-progress I/O and then start new I/O.
274 The filesystem should unlock the page synchronously, before returning to the
275 caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
276 value. WRITEPAGE_ACTIVATE means that page cannot really be written out
277 currently, and VM should stop calling ->writepage() on this page for some
278 time. VM does this by moving page to the head of the active list, hence the
279 name.
281 Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
282 and return zero, writepage *must* run set_page_writeback() against the page,
283 followed by unlocking it. Once set_page_writeback() has been run against the
284 page, write I/O can be submitted and the write I/O completion handler must run
285 end_page_writeback() once the I/O is complete. If no I/O is submitted, the
286 filesystem must run end_page_writeback() against the page before returning from
287 writepage.
289 That is: after 2.5.12, pages which are under writeout are *not* locked. Note,
290 if the filesystem needs the page to be locked during writeout, that is ok, too,
291 the page is allowed to be unlocked at any point in time between the calls to
292 set_page_writeback() and end_page_writeback().
294 Note, failure to run either redirty_page_for_writepage() or the combination of
295 set_page_writeback()/end_page_writeback() on a page submitted to writepage
296 will leave the page itself marked clean but it will be tagged as dirty in the
297 radix tree. This incoherency can lead to all sorts of hard-to-debug problems
298 in the filesystem like having dirty inodes at umount and losing written data.
300 ->writepages() is used for periodic writeback and for syscall-initiated
301 sync operations. The address_space should start I/O against at least
302 *nr_to_write pages. *nr_to_write must be decremented for each page which is
303 written. The address_space implementation may write more (or less) pages
304 than *nr_to_write asks for, but it should try to be reasonably close. If
305 nr_to_write is NULL, all dirty pages must be written.
307 writepages should _only_ write pages which are present on
308 mapping->io_pages.
310 ->set_page_dirty() is called from various places in the kernel
311 when the target page is marked as needing writeback. It may be called
312 under spinlock (it cannot block) and is sometimes called with the page
313 not locked.
315 ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
316 filesystems and by the swapper. The latter will eventually go away. Please,
317 keep it that way and don't breed new callers.
319 ->invalidatepage() is called when the filesystem must attempt to drop
320 some or all of the buffers from the page when it is being truncated. It
321 returns zero on success. If ->invalidatepage is zero, the kernel uses
322 block_invalidatepage() instead.
324 ->releasepage() is called when the kernel is about to try to drop the
325 buffers from the page in preparation for freeing it. It returns zero to
326 indicate that the buffers are (or may be) freeable. If ->releasepage is zero,
327 the kernel assumes that the fs has no private interest in the buffers.
329 ->freepage() is called when the kernel is done dropping the page
330 from the page cache.
332 ->launder_page() may be called prior to releasing a page if
333 it is still found to be dirty. It returns zero if the page was successfully
334 cleaned, or an error value if not. Note that in order to prevent the page
335 getting mapped back in and redirtied, it needs to be kept locked
336 across the entire operation.
338 ->swap_activate will be called with a non-zero argument on
339 files backing (non block device backed) swapfiles. A return value
340 of zero indicates success, in which case this file can be used for
341 backing swapspace. The swapspace operations will be proxied to the
342 address space operations.
344 ->swap_deactivate() will be called in the sys_swapoff()
345 path after ->swap_activate() returned success.
347 ----------------------- file_lock_operations ------------------------------
348 prototypes:
349 void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
350 void (*fl_release_private)(struct file_lock *);
353 locking rules:
354 inode->i_lock may block
355 fl_copy_lock: yes no
356 fl_release_private: maybe maybe[1]
358 [1]: ->fl_release_private for flock or POSIX locks is currently allowed
359 to block. Leases however can still be freed while the i_lock is held and
360 so fl_release_private called on a lease should not block.
362 ----------------------- lock_manager_operations ---------------------------
363 prototypes:
364 void (*lm_notify)(struct file_lock *); /* unblock callback */
365 int (*lm_grant)(struct file_lock *, struct file_lock *, int);
366 void (*lm_break)(struct file_lock *); /* break_lease callback */
367 int (*lm_change)(struct file_lock **, int);
369 locking rules:
371 inode->i_lock blocked_lock_lock may block
372 lm_notify: yes yes no
373 lm_grant: no no no
374 lm_break: yes no no
375 lm_change yes no no
377 --------------------------- buffer_head -----------------------------------
378 prototypes:
379 void (*b_end_io)(struct buffer_head *bh, int uptodate);
381 locking rules:
382 called from interrupts. In other words, extreme care is needed here.
383 bh is locked, but that's all warranties we have here. Currently only RAID1,
384 highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
385 call this method upon the IO completion.
387 --------------------------- block_device_operations -----------------------
388 prototypes:
389 int (*open) (struct block_device *, fmode_t);
390 int (*release) (struct gendisk *, fmode_t);
391 int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
392 int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
393 int (*direct_access) (struct block_device *, sector_t, void **,
394 unsigned long *);
395 int (*media_changed) (struct gendisk *);
396 void (*unlock_native_capacity) (struct gendisk *);
397 int (*revalidate_disk) (struct gendisk *);
398 int (*getgeo)(struct block_device *, struct hd_geometry *);
399 void (*swap_slot_free_notify) (struct block_device *, unsigned long);
401 locking rules:
402 bd_mutex
403 open: yes
404 release: yes
405 ioctl: no
406 compat_ioctl: no
407 direct_access: no
408 media_changed: no
409 unlock_native_capacity: no
410 revalidate_disk: no
411 getgeo: no
412 swap_slot_free_notify: no (see below)
414 media_changed, unlock_native_capacity and revalidate_disk are called only from
415 check_disk_change().
417 swap_slot_free_notify is called with swap_lock and sometimes the page lock
418 held.
421 --------------------------- file_operations -------------------------------
422 prototypes:
423 loff_t (*llseek) (struct file *, loff_t, int);
424 ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
425 ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
426 ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
427 ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
428 int (*iterate) (struct file *, struct dir_context *);
429 int (*iterate_shared) (struct file *, struct dir_context *);
430 __poll_t (*poll) (struct file *, struct poll_table_struct *);
431 long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
432 long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
433 int (*mmap) (struct file *, struct vm_area_struct *);
434 int (*open) (struct inode *, struct file *);
435 int (*flush) (struct file *);
436 int (*release) (struct inode *, struct file *);
437 int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
438 int (*fasync) (int, struct file *, int);
439 int (*lock) (struct file *, int, struct file_lock *);
440 ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
441 loff_t *);
442 ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
443 loff_t *);
444 ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
445 void __user *);
446 ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
447 loff_t *, int);
448 unsigned long (*get_unmapped_area)(struct file *, unsigned long,
449 unsigned long, unsigned long, unsigned long);
450 int (*check_flags)(int);
451 int (*flock) (struct file *, int, struct file_lock *);
452 ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
453 size_t, unsigned int);
454 ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
455 size_t, unsigned int);
456 int (*setlease)(struct file *, long, struct file_lock **, void **);
457 long (*fallocate)(struct file *, int, loff_t, loff_t);
458 };
460 locking rules:
461 All may block.
463 ->llseek() locking has moved from llseek to the individual llseek
464 implementations. If your fs is not using generic_file_llseek, you
465 need to acquire and release the appropriate locks in your ->llseek().
466 For many filesystems, it is probably safe to acquire the inode
467 mutex or just to use i_size_read() instead.
468 Note: this does not protect the file->f_pos against concurrent modifications
469 since this is something the userspace has to take care about.
471 ->iterate() is called with i_rwsem exclusive.
473 ->iterate_shared() is called with i_rwsem at least shared.
475 ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
476 Most instances call fasync_helper(), which does that maintenance, so it's
477 not normally something one needs to worry about. Return values > 0 will be
478 mapped to zero in the VFS layer.
480 ->readdir() and ->ioctl() on directories must be changed. Ideally we would
481 move ->readdir() to inode_operations and use a separate method for directory
482 ->ioctl() or kill the latter completely. One of the problems is that for
483 anything that resembles union-mount we won't have a struct file for all
484 components. And there are other reasons why the current interface is a mess...
486 ->read on directories probably must go away - we should just enforce -EISDIR
487 in sys_read() and friends.
489 ->setlease operations should call generic_setlease() before or after setting
490 the lease within the individual filesystem to record the result of the
491 operation
493 --------------------------- dquot_operations -------------------------------
494 prototypes:
495 int (*write_dquot) (struct dquot *);
496 int (*acquire_dquot) (struct dquot *);
497 int (*release_dquot) (struct dquot *);
498 int (*mark_dirty) (struct dquot *);
499 int (*write_info) (struct super_block *, int);
501 These operations are intended to be more or less wrapping functions that ensure
502 a proper locking wrt the filesystem and call the generic quota operations.
504 What filesystem should expect from the generic quota functions:
506 FS recursion Held locks when called
507 write_dquot: yes dqonoff_sem or dqptr_sem
508 acquire_dquot: yes dqonoff_sem or dqptr_sem
509 release_dquot: yes dqonoff_sem or dqptr_sem
510 mark_dirty: no -
511 write_info: yes dqonoff_sem
513 FS recursion means calling ->quota_read() and ->quota_write() from superblock
514 operations.
516 More details about quota locking can be found in fs/dquot.c.
518 --------------------------- vm_operations_struct -----------------------------
519 prototypes:
520 void (*open)(struct vm_area_struct*);
521 void (*close)(struct vm_area_struct*);
522 vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
523 vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
524 vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
525 int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
527 locking rules:
528 mmap_sem PageLocked(page)
529 open: yes
530 close: yes
531 fault: yes can return with page locked
532 map_pages: yes
533 page_mkwrite: yes can return with page locked
534 pfn_mkwrite: yes
535 access: yes
537 ->fault() is called when a previously not present pte is about
538 to be faulted in. The filesystem must find and return the page associated
539 with the passed in "pgoff" in the vm_fault structure. If it is possible that
540 the page may be truncated and/or invalidated, then the filesystem must lock
541 the page, then ensure it is not already truncated (the page lock will block
542 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
543 locked. The VM will unlock the page.
545 ->map_pages() is called when VM asks to map easy accessible pages.
546 Filesystem should find and map pages associated with offsets from "start_pgoff"
547 till "end_pgoff". ->map_pages() is called with page table locked and must
548 not block. If it's not possible to reach a page without blocking,
549 filesystem should skip it. Filesystem should use do_set_pte() to setup
550 page table entry. Pointer to entry associated with the page is passed in
551 "pte" field in vm_fault structure. Pointers to entries for other offsets
552 should be calculated relative to "pte".
554 ->page_mkwrite() is called when a previously read-only pte is
555 about to become writeable. The filesystem again must ensure that there are
556 no truncate/invalidate races, and then return with the page locked. If
557 the page has been truncated, the filesystem should not look up a new page
558 like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
559 will cause the VM to retry the fault.
561 ->pfn_mkwrite() is the same as page_mkwrite but when the pte is
562 VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
563 VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
564 after this call is to make the pte read-write, unless pfn_mkwrite returns
565 an error.
567 ->access() is called when get_user_pages() fails in
568 access_process_vm(), typically used to debug a process through
569 /proc/pid/mem or ptrace. This function is needed only for
570 VM_IO | VM_PFNMAP VMAs.
572 ================================================================================
573 Dubious stuff
575 (if you break something or notice that it is broken and do not fix it yourself
576 - at least put it here)