]>
Commit | Line | Data |
---|---|---|
1da177e4 LT |
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: | |
0b728e19 | 12 | int (*d_revalidate)(struct dentry *, unsigned int); |
ecf3d1f1 | 13 | int (*d_weak_revalidate)(struct dentry *, unsigned int); |
da53be12 LT |
14 | int (*d_hash)(const struct dentry *, struct qstr *); |
15 | int (*d_compare)(const struct dentry *, const struct dentry *, | |
621e155a | 16 | unsigned int, const char *, const struct qstr *); |
1da177e4 LT |
17 | int (*d_delete)(struct dentry *); |
18 | void (*d_release)(struct dentry *); | |
19 | void (*d_iput)(struct dentry *, struct inode *); | |
c23fbb6b | 20 | char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); |
9875cf80 | 21 | struct vfsmount *(*d_automount)(struct path *path); |
cc53ce53 | 22 | int (*d_manage)(struct dentry *, bool); |
1da177e4 LT |
23 | |
24 | locking rules: | |
34286d66 NP |
25 | rename_lock ->d_lock may block rcu-walk |
26 | d_revalidate: no no yes (ref-walk) maybe | |
ecf3d1f1 | 27 | d_weak_revalidate:no no yes no |
34286d66 NP |
28 | d_hash no no no maybe |
29 | d_compare: yes no no maybe | |
30 | d_delete: no yes no no | |
31 | d_release: no no yes no | |
f0023bc6 | 32 | d_prune: no yes no no |
34286d66 NP |
33 | d_iput: no no yes no |
34 | d_dname: no no no no | |
9875cf80 | 35 | d_automount: no no yes no |
ab90911f | 36 | d_manage: no no yes (ref-walk) maybe |
1da177e4 LT |
37 | |
38 | --------------------------- inode_operations --------------------------- | |
39 | prototypes: | |
ebfc3b49 | 40 | int (*create) (struct inode *,struct dentry *,umode_t, bool); |
00cd8dd3 | 41 | struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); |
1da177e4 LT |
42 | int (*link) (struct dentry *,struct inode *,struct dentry *); |
43 | int (*unlink) (struct inode *,struct dentry *); | |
44 | int (*symlink) (struct inode *,struct dentry *,const char *); | |
18bb1db3 | 45 | int (*mkdir) (struct inode *,struct dentry *,umode_t); |
1da177e4 | 46 | int (*rmdir) (struct inode *,struct dentry *); |
1a67aafb | 47 | int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); |
1da177e4 LT |
48 | int (*rename) (struct inode *, struct dentry *, |
49 | struct inode *, struct dentry *); | |
520c8b16 MS |
50 | int (*rename2) (struct inode *, struct dentry *, |
51 | struct inode *, struct dentry *, unsigned int); | |
1da177e4 | 52 | int (*readlink) (struct dentry *, char __user *,int); |
6b255391 | 53 | const char *(*get_link) (struct dentry *, struct inode *, void **); |
1da177e4 | 54 | void (*truncate) (struct inode *); |
b74c79e9 | 55 | int (*permission) (struct inode *, int, unsigned int); |
4e34e719 | 56 | int (*get_acl)(struct inode *, int); |
1da177e4 LT |
57 | int (*setattr) (struct dentry *, struct iattr *); |
58 | int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *); | |
59 | int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); | |
60 | ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); | |
61 | ssize_t (*listxattr) (struct dentry *, char *, size_t); | |
62 | int (*removexattr) (struct dentry *, const char *); | |
b83be6f2 | 63 | int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); |
c3b2da31 | 64 | void (*update_time)(struct inode *, struct timespec *, int); |
d9585277 | 65 | int (*atomic_open)(struct inode *, struct dentry *, |
30d90494 | 66 | struct file *, unsigned open_flag, |
47237687 | 67 | umode_t create_mode, int *opened); |
48bde8d3 | 68 | int (*tmpfile) (struct inode *, struct dentry *, umode_t); |
4aa7c634 | 69 | int (*dentry_open)(struct dentry *, struct file *, const struct cred *); |
1da177e4 LT |
70 | |
71 | locking rules: | |
b83be6f2 | 72 | all may block |
a7bc02f4 | 73 | i_mutex(inode) |
1da177e4 LT |
74 | lookup: yes |
75 | create: yes | |
76 | link: yes (both) | |
77 | mknod: yes | |
78 | symlink: yes | |
79 | mkdir: yes | |
80 | unlink: yes (both) | |
81 | rmdir: yes (both) (see below) | |
82 | rename: yes (all) (see below) | |
520c8b16 | 83 | rename2: yes (all) (see below) |
1da177e4 | 84 | readlink: no |
6b255391 | 85 | get_link: no |
1da177e4 | 86 | setattr: yes |
b74c79e9 | 87 | permission: no (may not block if called in rcu-walk mode) |
4e34e719 | 88 | get_acl: no |
1da177e4 LT |
89 | getattr: no |
90 | setxattr: yes | |
91 | getxattr: no | |
92 | listxattr: no | |
93 | removexattr: yes | |
b83be6f2 | 94 | fiemap: no |
c3b2da31 | 95 | update_time: no |
d18e9008 | 96 | atomic_open: yes |
48bde8d3 | 97 | tmpfile: no |
4aa7c634 | 98 | dentry_open: no |
c3b2da31 | 99 | |
a7bc02f4 | 100 | Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on |
1da177e4 | 101 | victim. |
520c8b16 MS |
102 | cross-directory ->rename() and rename2() has (per-superblock) |
103 | ->s_vfs_rename_sem. | |
1da177e4 LT |
104 | |
105 | See Documentation/filesystems/directory-locking for more detailed discussion | |
106 | of the locking scheme for directory operations. | |
107 | ||
108 | --------------------------- super_operations --------------------------- | |
109 | prototypes: | |
110 | struct inode *(*alloc_inode)(struct super_block *sb); | |
111 | void (*destroy_inode)(struct inode *); | |
aa385729 | 112 | void (*dirty_inode) (struct inode *, int flags); |
b83be6f2 | 113 | int (*write_inode) (struct inode *, struct writeback_control *wbc); |
336fb3b9 AV |
114 | int (*drop_inode) (struct inode *); |
115 | void (*evict_inode) (struct inode *); | |
1da177e4 | 116 | void (*put_super) (struct super_block *); |
1da177e4 | 117 | int (*sync_fs)(struct super_block *sb, int wait); |
c4be0c1d TS |
118 | int (*freeze_fs) (struct super_block *); |
119 | int (*unfreeze_fs) (struct super_block *); | |
726c3342 | 120 | int (*statfs) (struct dentry *, struct kstatfs *); |
1da177e4 | 121 | int (*remount_fs) (struct super_block *, int *, char *); |
1da177e4 | 122 | void (*umount_begin) (struct super_block *); |
34c80b1d | 123 | int (*show_options)(struct seq_file *, struct dentry *); |
1da177e4 LT |
124 | ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); |
125 | ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); | |
b83be6f2 | 126 | int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); |
1da177e4 LT |
127 | |
128 | locking rules: | |
336fb3b9 | 129 | All may block [not true, see below] |
7e325d3a CH |
130 | s_umount |
131 | alloc_inode: | |
132 | destroy_inode: | |
aa385729 | 133 | dirty_inode: |
7e325d3a | 134 | write_inode: |
f283c86a | 135 | drop_inode: !!!inode->i_lock!!! |
336fb3b9 | 136 | evict_inode: |
7e325d3a | 137 | put_super: write |
7e325d3a | 138 | sync_fs: read |
06fd516c VA |
139 | freeze_fs: write |
140 | unfreeze_fs: write | |
336fb3b9 AV |
141 | statfs: maybe(read) (see below) |
142 | remount_fs: write | |
7e325d3a CH |
143 | umount_begin: no |
144 | show_options: no (namespace_sem) | |
145 | quota_read: no (see below) | |
146 | quota_write: no (see below) | |
b83be6f2 | 147 | bdev_try_to_free_page: no (see below) |
1da177e4 | 148 | |
336fb3b9 AV |
149 | ->statfs() has s_umount (shared) when called by ustat(2) (native or |
150 | compat), but that's an accident of bad API; s_umount is used to pin | |
151 | the superblock down when we only have dev_t given us by userland to | |
152 | identify the superblock. Everything else (statfs(), fstatfs(), etc.) | |
153 | doesn't hold it when calling ->statfs() - superblock is pinned down | |
154 | by resolving the pathname passed to syscall. | |
1da177e4 LT |
155 | ->quota_read() and ->quota_write() functions are both guaranteed to |
156 | be the only ones operating on the quota file by the quota code (via | |
157 | dqio_sem) (unless an admin really wants to screw up something and | |
158 | writes to quota files with quotas on). For other details about locking | |
159 | see also dquot_operations section. | |
b83be6f2 CH |
160 | ->bdev_try_to_free_page is called from the ->releasepage handler of |
161 | the block device inode. See there for more details. | |
1da177e4 LT |
162 | |
163 | --------------------------- file_system_type --------------------------- | |
164 | prototypes: | |
b83be6f2 CH |
165 | struct dentry *(*mount) (struct file_system_type *, int, |
166 | const char *, void *); | |
1da177e4 LT |
167 | void (*kill_sb) (struct super_block *); |
168 | locking rules: | |
b83be6f2 | 169 | may block |
b83be6f2 CH |
170 | mount yes |
171 | kill_sb yes | |
1da177e4 | 172 | |
1a102ff9 AV |
173 | ->mount() returns ERR_PTR or the root dentry; its superblock should be locked |
174 | on return. | |
1da177e4 LT |
175 | ->kill_sb() takes a write-locked superblock, does all shutdown work on it, |
176 | unlocks and drops the reference. | |
177 | ||
178 | --------------------------- address_space_operations -------------------------- | |
179 | prototypes: | |
180 | int (*writepage)(struct page *page, struct writeback_control *wbc); | |
181 | int (*readpage)(struct file *, struct page *); | |
182 | int (*sync_page)(struct page *); | |
183 | int (*writepages)(struct address_space *, struct writeback_control *); | |
184 | int (*set_page_dirty)(struct page *page); | |
185 | int (*readpages)(struct file *filp, struct address_space *mapping, | |
186 | struct list_head *pages, unsigned nr_pages); | |
4e02ed4b NP |
187 | int (*write_begin)(struct file *, struct address_space *mapping, |
188 | loff_t pos, unsigned len, unsigned flags, | |
189 | struct page **pagep, void **fsdata); | |
190 | int (*write_end)(struct file *, struct address_space *mapping, | |
191 | loff_t pos, unsigned len, unsigned copied, | |
192 | struct page *page, void *fsdata); | |
1da177e4 | 193 | sector_t (*bmap)(struct address_space *, sector_t); |
d47992f8 | 194 | void (*invalidatepage) (struct page *, unsigned int, unsigned int); |
1da177e4 | 195 | int (*releasepage) (struct page *, int); |
6072d13c | 196 | void (*freepage)(struct page *); |
c8b8e32d | 197 | int (*direct_IO)(struct kiocb *, struct iov_iter *iter); |
b83be6f2 CH |
198 | int (*migratepage)(struct address_space *, struct page *, struct page *); |
199 | int (*launder_page)(struct page *); | |
c186afb4 | 200 | int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long); |
b83be6f2 | 201 | int (*error_remove_page)(struct address_space *, struct page *); |
62c230bc MG |
202 | int (*swap_activate)(struct file *); |
203 | int (*swap_deactivate)(struct file *); | |
1da177e4 LT |
204 | |
205 | locking rules: | |
6072d13c | 206 | All except set_page_dirty and freepage may block |
1da177e4 | 207 | |
b83be6f2 CH |
208 | PageLocked(page) i_mutex |
209 | writepage: yes, unlocks (see below) | |
210 | readpage: yes, unlocks | |
211 | sync_page: maybe | |
212 | writepages: | |
213 | set_page_dirty no | |
214 | readpages: | |
215 | write_begin: locks the page yes | |
216 | write_end: yes, unlocks yes | |
217 | bmap: | |
218 | invalidatepage: yes | |
219 | releasepage: yes | |
220 | freepage: yes | |
221 | direct_IO: | |
b83be6f2 CH |
222 | migratepage: yes (both) |
223 | launder_page: yes | |
224 | is_partially_uptodate: yes | |
225 | error_remove_page: yes | |
62c230bc MG |
226 | swap_activate: no |
227 | swap_deactivate: no | |
1da177e4 | 228 | |
4e02ed4b | 229 | ->write_begin(), ->write_end(), ->sync_page() and ->readpage() |
1da177e4 LT |
230 | may be called from the request handler (/dev/loop). |
231 | ||
232 | ->readpage() unlocks the page, either synchronously or via I/O | |
233 | completion. | |
234 | ||
235 | ->readpages() populates the pagecache with the passed pages and starts | |
236 | I/O against them. They come unlocked upon I/O completion. | |
237 | ||
238 | ->writepage() is used for two purposes: for "memory cleansing" and for | |
239 | "sync". These are quite different operations and the behaviour may differ | |
240 | depending upon the mode. | |
241 | ||
242 | If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then | |
243 | it *must* start I/O against the page, even if that would involve | |
244 | blocking on in-progress I/O. | |
245 | ||
246 | If writepage is called for memory cleansing (sync_mode == | |
247 | WBC_SYNC_NONE) then its role is to get as much writeout underway as | |
248 | possible. So writepage should try to avoid blocking against | |
249 | currently-in-progress I/O. | |
250 | ||
251 | If the filesystem is not called for "sync" and it determines that it | |
252 | would need to block against in-progress I/O to be able to start new I/O | |
253 | against the page the filesystem should redirty the page with | |
254 | redirty_page_for_writepage(), then unlock the page and return zero. | |
255 | This may also be done to avoid internal deadlocks, but rarely. | |
256 | ||
3a4fa0a2 | 257 | If the filesystem is called for sync then it must wait on any |
1da177e4 LT |
258 | in-progress I/O and then start new I/O. |
259 | ||
2054606a ND |
260 | The filesystem should unlock the page synchronously, before returning to the |
261 | caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE | |
262 | value. WRITEPAGE_ACTIVATE means that page cannot really be written out | |
263 | currently, and VM should stop calling ->writepage() on this page for some | |
264 | time. VM does this by moving page to the head of the active list, hence the | |
265 | name. | |
1da177e4 LT |
266 | |
267 | Unless the filesystem is going to redirty_page_for_writepage(), unlock the page | |
268 | and return zero, writepage *must* run set_page_writeback() against the page, | |
269 | followed by unlocking it. Once set_page_writeback() has been run against the | |
270 | page, write I/O can be submitted and the write I/O completion handler must run | |
271 | end_page_writeback() once the I/O is complete. If no I/O is submitted, the | |
272 | filesystem must run end_page_writeback() against the page before returning from | |
273 | writepage. | |
274 | ||
275 | That is: after 2.5.12, pages which are under writeout are *not* locked. Note, | |
276 | if the filesystem needs the page to be locked during writeout, that is ok, too, | |
277 | the page is allowed to be unlocked at any point in time between the calls to | |
278 | set_page_writeback() and end_page_writeback(). | |
279 | ||
280 | Note, failure to run either redirty_page_for_writepage() or the combination of | |
281 | set_page_writeback()/end_page_writeback() on a page submitted to writepage | |
282 | will leave the page itself marked clean but it will be tagged as dirty in the | |
283 | radix tree. This incoherency can lead to all sorts of hard-to-debug problems | |
284 | in the filesystem like having dirty inodes at umount and losing written data. | |
285 | ||
286 | ->sync_page() locking rules are not well-defined - usually it is called | |
287 | with lock on page, but that is not guaranteed. Considering the currently | |
288 | existing instances of this method ->sync_page() itself doesn't look | |
289 | well-defined... | |
290 | ||
291 | ->writepages() is used for periodic writeback and for syscall-initiated | |
292 | sync operations. The address_space should start I/O against at least | |
293 | *nr_to_write pages. *nr_to_write must be decremented for each page which is | |
294 | written. The address_space implementation may write more (or less) pages | |
295 | than *nr_to_write asks for, but it should try to be reasonably close. If | |
296 | nr_to_write is NULL, all dirty pages must be written. | |
297 | ||
298 | writepages should _only_ write pages which are present on | |
299 | mapping->io_pages. | |
300 | ||
301 | ->set_page_dirty() is called from various places in the kernel | |
302 | when the target page is marked as needing writeback. It may be called | |
303 | under spinlock (it cannot block) and is sometimes called with the page | |
304 | not locked. | |
305 | ||
306 | ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some | |
b83be6f2 CH |
307 | filesystems and by the swapper. The latter will eventually go away. Please, |
308 | keep it that way and don't breed new callers. | |
1da177e4 LT |
309 | |
310 | ->invalidatepage() is called when the filesystem must attempt to drop | |
d47992f8 LC |
311 | some or all of the buffers from the page when it is being truncated. It |
312 | returns zero on success. If ->invalidatepage is zero, the kernel uses | |
1da177e4 LT |
313 | block_invalidatepage() instead. |
314 | ||
315 | ->releasepage() is called when the kernel is about to try to drop the | |
316 | buffers from the page in preparation for freeing it. It returns zero to | |
317 | indicate that the buffers are (or may be) freeable. If ->releasepage is zero, | |
318 | the kernel assumes that the fs has no private interest in the buffers. | |
319 | ||
6072d13c LT |
320 | ->freepage() is called when the kernel is done dropping the page |
321 | from the page cache. | |
322 | ||
e3db7691 TM |
323 | ->launder_page() may be called prior to releasing a page if |
324 | it is still found to be dirty. It returns zero if the page was successfully | |
325 | cleaned, or an error value if not. Note that in order to prevent the page | |
326 | getting mapped back in and redirtied, it needs to be kept locked | |
327 | across the entire operation. | |
328 | ||
62c230bc MG |
329 | ->swap_activate will be called with a non-zero argument on |
330 | files backing (non block device backed) swapfiles. A return value | |
331 | of zero indicates success, in which case this file can be used for | |
332 | backing swapspace. The swapspace operations will be proxied to the | |
333 | address space operations. | |
334 | ||
335 | ->swap_deactivate() will be called in the sys_swapoff() | |
336 | path after ->swap_activate() returned success. | |
337 | ||
1da177e4 LT |
338 | ----------------------- file_lock_operations ------------------------------ |
339 | prototypes: | |
1da177e4 LT |
340 | void (*fl_copy_lock)(struct file_lock *, struct file_lock *); |
341 | void (*fl_release_private)(struct file_lock *); | |
342 | ||
343 | ||
344 | locking rules: | |
1c8c601a | 345 | inode->i_lock may block |
b83be6f2 | 346 | fl_copy_lock: yes no |
2ece173e JL |
347 | fl_release_private: maybe maybe[1] |
348 | ||
349 | [1]: ->fl_release_private for flock or POSIX locks is currently allowed | |
350 | to block. Leases however can still be freed while the i_lock is held and | |
351 | so fl_release_private called on a lease should not block. | |
1da177e4 LT |
352 | |
353 | ----------------------- lock_manager_operations --------------------------- | |
354 | prototypes: | |
8fb47a4f | 355 | int (*lm_compare_owner)(struct file_lock *, struct file_lock *); |
3999e493 | 356 | unsigned long (*lm_owner_key)(struct file_lock *); |
8fb47a4f BF |
357 | void (*lm_notify)(struct file_lock *); /* unblock callback */ |
358 | int (*lm_grant)(struct file_lock *, struct file_lock *, int); | |
8fb47a4f BF |
359 | void (*lm_break)(struct file_lock *); /* break_lease callback */ |
360 | int (*lm_change)(struct file_lock **, int); | |
1da177e4 LT |
361 | |
362 | locking rules: | |
1c8c601a | 363 | |
7b2296af JL |
364 | inode->i_lock blocked_lock_lock may block |
365 | lm_compare_owner: yes[1] maybe no | |
366 | lm_owner_key yes[1] yes no | |
367 | lm_notify: yes yes no | |
368 | lm_grant: no no no | |
369 | lm_break: yes no no | |
370 | lm_change yes no no | |
1c8c601a | 371 | |
3999e493 JL |
372 | [1]: ->lm_compare_owner and ->lm_owner_key are generally called with |
373 | *an* inode->i_lock held. It may not be the i_lock of the inode | |
374 | associated with either file_lock argument! This is the case with deadlock | |
375 | detection, since the code has to chase down the owners of locks that may | |
376 | be entirely unrelated to the one on which the lock is being acquired. | |
7b2296af | 377 | For deadlock detection however, the blocked_lock_lock is also held. The |
3999e493 JL |
378 | fact that these locks are held ensures that the file_locks do not |
379 | disappear out from under you while doing the comparison or generating an | |
380 | owner key. | |
b83be6f2 | 381 | |
1da177e4 LT |
382 | --------------------------- buffer_head ----------------------------------- |
383 | prototypes: | |
384 | void (*b_end_io)(struct buffer_head *bh, int uptodate); | |
385 | ||
386 | locking rules: | |
387 | called from interrupts. In other words, extreme care is needed here. | |
388 | bh is locked, but that's all warranties we have here. Currently only RAID1, | |
389 | highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices | |
390 | call this method upon the IO completion. | |
391 | ||
392 | --------------------------- block_device_operations ----------------------- | |
393 | prototypes: | |
e1455d1b CH |
394 | int (*open) (struct block_device *, fmode_t); |
395 | int (*release) (struct gendisk *, fmode_t); | |
396 | int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
397 | int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
e2e05394 RZ |
398 | int (*direct_access) (struct block_device *, sector_t, void __pmem **, |
399 | unsigned long *); | |
1da177e4 | 400 | int (*media_changed) (struct gendisk *); |
e1455d1b | 401 | void (*unlock_native_capacity) (struct gendisk *); |
1da177e4 | 402 | int (*revalidate_disk) (struct gendisk *); |
e1455d1b CH |
403 | int (*getgeo)(struct block_device *, struct hd_geometry *); |
404 | void (*swap_slot_free_notify) (struct block_device *, unsigned long); | |
1da177e4 LT |
405 | |
406 | locking rules: | |
b83be6f2 CH |
407 | bd_mutex |
408 | open: yes | |
409 | release: yes | |
410 | ioctl: no | |
411 | compat_ioctl: no | |
412 | direct_access: no | |
413 | media_changed: no | |
414 | unlock_native_capacity: no | |
415 | revalidate_disk: no | |
416 | getgeo: no | |
417 | swap_slot_free_notify: no (see below) | |
e1455d1b CH |
418 | |
419 | media_changed, unlock_native_capacity and revalidate_disk are called only from | |
420 | check_disk_change(). | |
421 | ||
422 | swap_slot_free_notify is called with swap_lock and sometimes the page lock | |
423 | held. | |
1da177e4 | 424 | |
1da177e4 LT |
425 | |
426 | --------------------------- file_operations ------------------------------- | |
427 | prototypes: | |
428 | loff_t (*llseek) (struct file *, loff_t, int); | |
429 | ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); | |
1da177e4 | 430 | ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); |
293bc982 AV |
431 | ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); |
432 | ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); | |
2233f31a | 433 | int (*iterate) (struct file *, struct dir_context *); |
1da177e4 | 434 | unsigned int (*poll) (struct file *, struct poll_table_struct *); |
1da177e4 LT |
435 | long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); |
436 | long (*compat_ioctl) (struct file *, unsigned int, unsigned long); | |
437 | int (*mmap) (struct file *, struct vm_area_struct *); | |
438 | int (*open) (struct inode *, struct file *); | |
439 | int (*flush) (struct file *); | |
440 | int (*release) (struct inode *, struct file *); | |
02c24a82 | 441 | int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); |
1da177e4 LT |
442 | int (*aio_fsync) (struct kiocb *, int datasync); |
443 | int (*fasync) (int, struct file *, int); | |
444 | int (*lock) (struct file *, int, struct file_lock *); | |
445 | ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, | |
446 | loff_t *); | |
447 | ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, | |
448 | loff_t *); | |
449 | ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, | |
450 | void __user *); | |
451 | ssize_t (*sendpage) (struct file *, struct page *, int, size_t, | |
452 | loff_t *, int); | |
453 | unsigned long (*get_unmapped_area)(struct file *, unsigned long, | |
454 | unsigned long, unsigned long, unsigned long); | |
455 | int (*check_flags)(int); | |
b83be6f2 CH |
456 | int (*flock) (struct file *, int, struct file_lock *); |
457 | ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, | |
458 | size_t, unsigned int); | |
459 | ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, | |
460 | size_t, unsigned int); | |
e6f5c789 | 461 | int (*setlease)(struct file *, long, struct file_lock **, void **); |
2fe17c10 | 462 | long (*fallocate)(struct file *, int, loff_t, loff_t); |
1da177e4 LT |
463 | }; |
464 | ||
465 | locking rules: | |
c45198ed | 466 | All may block. |
b83be6f2 | 467 | |
1da177e4 LT |
468 | ->llseek() locking has moved from llseek to the individual llseek |
469 | implementations. If your fs is not using generic_file_llseek, you | |
470 | need to acquire and release the appropriate locks in your ->llseek(). | |
471 | For many filesystems, it is probably safe to acquire the inode | |
866707fc JB |
472 | mutex or just to use i_size_read() instead. |
473 | Note: this does not protect the file->f_pos against concurrent modifications | |
474 | since this is something the userspace has to take care about. | |
1da177e4 | 475 | |
b83be6f2 CH |
476 | ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. |
477 | Most instances call fasync_helper(), which does that maintenance, so it's | |
478 | not normally something one needs to worry about. Return values > 0 will be | |
479 | mapped to zero in the VFS layer. | |
1da177e4 LT |
480 | |
481 | ->readdir() and ->ioctl() on directories must be changed. Ideally we would | |
482 | move ->readdir() to inode_operations and use a separate method for directory | |
483 | ->ioctl() or kill the latter completely. One of the problems is that for | |
484 | anything that resembles union-mount we won't have a struct file for all | |
485 | components. And there are other reasons why the current interface is a mess... | |
486 | ||
1da177e4 LT |
487 | ->read on directories probably must go away - we should just enforce -EISDIR |
488 | in sys_read() and friends. | |
489 | ||
f82b4b67 JL |
490 | ->setlease operations should call generic_setlease() before or after setting |
491 | the lease within the individual filesystem to record the result of the | |
492 | operation | |
493 | ||
1da177e4 LT |
494 | --------------------------- dquot_operations ------------------------------- |
495 | prototypes: | |
1da177e4 LT |
496 | int (*write_dquot) (struct dquot *); |
497 | int (*acquire_dquot) (struct dquot *); | |
498 | int (*release_dquot) (struct dquot *); | |
499 | int (*mark_dirty) (struct dquot *); | |
500 | int (*write_info) (struct super_block *, int); | |
501 | ||
502 | These operations are intended to be more or less wrapping functions that ensure | |
503 | a proper locking wrt the filesystem and call the generic quota operations. | |
504 | ||
505 | What filesystem should expect from the generic quota functions: | |
506 | ||
507 | FS recursion Held locks when called | |
1da177e4 LT |
508 | write_dquot: yes dqonoff_sem or dqptr_sem |
509 | acquire_dquot: yes dqonoff_sem or dqptr_sem | |
510 | release_dquot: yes dqonoff_sem or dqptr_sem | |
511 | mark_dirty: no - | |
512 | write_info: yes dqonoff_sem | |
513 | ||
514 | FS recursion means calling ->quota_read() and ->quota_write() from superblock | |
515 | operations. | |
516 | ||
1da177e4 LT |
517 | More details about quota locking can be found in fs/dquot.c. |
518 | ||
519 | --------------------------- vm_operations_struct ----------------------------- | |
520 | prototypes: | |
521 | void (*open)(struct vm_area_struct*); | |
522 | void (*close)(struct vm_area_struct*); | |
d0217ac0 | 523 | int (*fault)(struct vm_area_struct*, struct vm_fault *); |
c2ec175c | 524 | int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); |
dd906184 | 525 | int (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *); |
28b2ee20 | 526 | int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); |
1da177e4 LT |
527 | |
528 | locking rules: | |
b83be6f2 CH |
529 | mmap_sem PageLocked(page) |
530 | open: yes | |
531 | close: yes | |
532 | fault: yes can return with page locked | |
8c6e50b0 | 533 | map_pages: yes |
b83be6f2 | 534 | page_mkwrite: yes can return with page locked |
dd906184 | 535 | pfn_mkwrite: yes |
b83be6f2 | 536 | access: yes |
ed2f2f9b | 537 | |
b827e496 NP |
538 | ->fault() is called when a previously not present pte is about |
539 | to be faulted in. The filesystem must find and return the page associated | |
540 | with the passed in "pgoff" in the vm_fault structure. If it is possible that | |
541 | the page may be truncated and/or invalidated, then the filesystem must lock | |
542 | the page, then ensure it is not already truncated (the page lock will block | |
543 | subsequent truncate), and then return with VM_FAULT_LOCKED, and the page | |
544 | locked. The VM will unlock the page. | |
545 | ||
8c6e50b0 KS |
546 | ->map_pages() is called when VM asks to map easy accessible pages. |
547 | Filesystem should find and map pages associated with offsets from "pgoff" | |
548 | till "max_pgoff". ->map_pages() is called with page table locked and must | |
549 | not block. If it's not possible to reach a page without blocking, | |
550 | filesystem should skip it. Filesystem should use do_set_pte() to setup | |
551 | page table entry. Pointer to entry associated with offset "pgoff" is | |
552 | passed in "pte" field in vm_fault structure. Pointers to entries for other | |
553 | offsets should be calculated relative to "pte". | |
554 | ||
b827e496 NP |
555 | ->page_mkwrite() is called when a previously read-only pte is |
556 | about to become writeable. The filesystem again must ensure that there are | |
557 | no truncate/invalidate races, and then return with the page locked. If | |
558 | the page has been truncated, the filesystem should not look up a new page | |
559 | like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which | |
560 | will cause the VM to retry the fault. | |
1da177e4 | 561 | |
dd906184 BH |
562 | ->pfn_mkwrite() is the same as page_mkwrite but when the pte is |
563 | VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is | |
564 | VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior | |
565 | after this call is to make the pte read-write, unless pfn_mkwrite returns | |
566 | an error. | |
567 | ||
28b2ee20 | 568 | ->access() is called when get_user_pages() fails in |
507da6a1 | 569 | access_process_vm(), typically used to debug a process through |
28b2ee20 RR |
570 | /proc/pid/mem or ptrace. This function is needed only for |
571 | VM_IO | VM_PFNMAP VMAs. | |
572 | ||
1da177e4 LT |
573 | ================================================================================ |
574 | Dubious stuff | |
575 | ||
576 | (if you break something or notice that it is broken and do not fix it yourself | |
577 | - at least put it here) |