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 | 14 | int (*d_hash)(const struct dentry *, struct qstr *); |
6fa67e70 | 15 | int (*d_compare)(const struct dentry *, |
621e155a | 16 | unsigned int, const char *, const struct qstr *); |
1da177e4 | 17 | int (*d_delete)(struct dentry *); |
285b102d | 18 | int (*d_init)(struct dentry *); |
1da177e4 LT |
19 | void (*d_release)(struct dentry *); |
20 | void (*d_iput)(struct dentry *, struct inode *); | |
c23fbb6b | 21 | char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); |
9875cf80 | 22 | struct vfsmount *(*d_automount)(struct path *path); |
fb5f51c7 | 23 | int (*d_manage)(const struct path *, bool); |
fb16043b | 24 | struct dentry *(*d_real)(struct dentry *, const struct inode *); |
1da177e4 LT |
25 | |
26 | locking rules: | |
34286d66 NP |
27 | rename_lock ->d_lock may block rcu-walk |
28 | d_revalidate: no no yes (ref-walk) maybe | |
ecf3d1f1 | 29 | d_weak_revalidate:no no yes no |
34286d66 NP |
30 | d_hash no no no maybe |
31 | d_compare: yes no no maybe | |
32 | d_delete: no yes no no | |
285b102d | 33 | d_init: no no yes no |
34286d66 | 34 | d_release: no no yes no |
f0023bc6 | 35 | d_prune: no yes no no |
34286d66 NP |
36 | d_iput: no no yes no |
37 | d_dname: no no no no | |
9875cf80 | 38 | d_automount: no no yes no |
ab90911f | 39 | d_manage: no no yes (ref-walk) maybe |
e698b8a4 | 40 | d_real no no yes no |
1da177e4 LT |
41 | |
42 | --------------------------- inode_operations --------------------------- | |
43 | prototypes: | |
ebfc3b49 | 44 | int (*create) (struct inode *,struct dentry *,umode_t, bool); |
00cd8dd3 | 45 | struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); |
1da177e4 LT |
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 *); | |
18bb1db3 | 49 | int (*mkdir) (struct inode *,struct dentry *,umode_t); |
1da177e4 | 50 | int (*rmdir) (struct inode *,struct dentry *); |
1a67aafb | 51 | int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); |
1da177e4 | 52 | int (*rename) (struct inode *, struct dentry *, |
520c8b16 | 53 | struct inode *, struct dentry *, unsigned int); |
1da177e4 | 54 | int (*readlink) (struct dentry *, char __user *,int); |
6b255391 | 55 | const char *(*get_link) (struct dentry *, struct inode *, void **); |
1da177e4 | 56 | void (*truncate) (struct inode *); |
b74c79e9 | 57 | int (*permission) (struct inode *, int, unsigned int); |
4e34e719 | 58 | int (*get_acl)(struct inode *, int); |
1da177e4 | 59 | int (*setattr) (struct dentry *, struct iattr *); |
75dd7e4b | 60 | int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); |
1da177e4 | 61 | ssize_t (*listxattr) (struct dentry *, char *, size_t); |
b83be6f2 | 62 | int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); |
c3b2da31 | 63 | void (*update_time)(struct inode *, struct timespec *, int); |
d9585277 | 64 | int (*atomic_open)(struct inode *, struct dentry *, |
30d90494 | 65 | struct file *, unsigned open_flag, |
6c9b1de1 | 66 | umode_t create_mode); |
48bde8d3 | 67 | int (*tmpfile) (struct inode *, struct dentry *, umode_t); |
1da177e4 LT |
68 | |
69 | locking rules: | |
b83be6f2 | 70 | all may block |
965de0ec SA |
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) | |
1da177e4 | 81 | readlink: no |
6b255391 | 82 | get_link: no |
965de0ec | 83 | setattr: exclusive |
b74c79e9 | 84 | permission: no (may not block if called in rcu-walk mode) |
4e34e719 | 85 | get_acl: no |
1da177e4 | 86 | getattr: no |
1da177e4 | 87 | listxattr: no |
b83be6f2 | 88 | fiemap: no |
c3b2da31 | 89 | update_time: no |
965de0ec | 90 | atomic_open: exclusive |
48bde8d3 | 91 | tmpfile: no |
c3b2da31 | 92 | |
6c6ef9f2 | 93 | |
965de0ec SA |
94 | Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem |
95 | exclusive on victim. | |
2773bf00 | 96 | cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. |
1da177e4 LT |
97 | |
98 | See Documentation/filesystems/directory-locking for more detailed discussion | |
99 | of the locking scheme for directory operations. | |
100 | ||
6c6ef9f2 AG |
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); | |
110 | ||
111 | locking rules: | |
112 | all may block | |
965de0ec | 113 | i_rwsem(inode) |
6c6ef9f2 AG |
114 | list: no |
115 | get: no | |
965de0ec | 116 | set: exclusive |
6c6ef9f2 | 117 | |
1da177e4 LT |
118 | --------------------------- super_operations --------------------------- |
119 | prototypes: | |
120 | struct inode *(*alloc_inode)(struct super_block *sb); | |
121 | void (*destroy_inode)(struct inode *); | |
aa385729 | 122 | void (*dirty_inode) (struct inode *, int flags); |
b83be6f2 | 123 | int (*write_inode) (struct inode *, struct writeback_control *wbc); |
336fb3b9 AV |
124 | int (*drop_inode) (struct inode *); |
125 | void (*evict_inode) (struct inode *); | |
1da177e4 | 126 | void (*put_super) (struct super_block *); |
1da177e4 | 127 | int (*sync_fs)(struct super_block *sb, int wait); |
c4be0c1d TS |
128 | int (*freeze_fs) (struct super_block *); |
129 | int (*unfreeze_fs) (struct super_block *); | |
726c3342 | 130 | int (*statfs) (struct dentry *, struct kstatfs *); |
1da177e4 | 131 | int (*remount_fs) (struct super_block *, int *, char *); |
1da177e4 | 132 | void (*umount_begin) (struct super_block *); |
34c80b1d | 133 | int (*show_options)(struct seq_file *, struct dentry *); |
1da177e4 LT |
134 | ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); |
135 | ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); | |
b83be6f2 | 136 | int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); |
1da177e4 LT |
137 | |
138 | locking rules: | |
336fb3b9 | 139 | All may block [not true, see below] |
7e325d3a CH |
140 | s_umount |
141 | alloc_inode: | |
142 | destroy_inode: | |
aa385729 | 143 | dirty_inode: |
7e325d3a | 144 | write_inode: |
f283c86a | 145 | drop_inode: !!!inode->i_lock!!! |
336fb3b9 | 146 | evict_inode: |
7e325d3a | 147 | put_super: write |
7e325d3a | 148 | sync_fs: read |
06fd516c VA |
149 | freeze_fs: write |
150 | unfreeze_fs: write | |
336fb3b9 AV |
151 | statfs: maybe(read) (see below) |
152 | remount_fs: write | |
7e325d3a CH |
153 | umount_begin: no |
154 | show_options: no (namespace_sem) | |
155 | quota_read: no (see below) | |
156 | quota_write: no (see below) | |
b83be6f2 | 157 | bdev_try_to_free_page: no (see below) |
1da177e4 | 158 | |
336fb3b9 AV |
159 | ->statfs() has s_umount (shared) when called by ustat(2) (native or |
160 | compat), but that's an accident of bad API; s_umount is used to pin | |
161 | the superblock down when we only have dev_t given us by userland to | |
162 | identify the superblock. Everything else (statfs(), fstatfs(), etc.) | |
163 | doesn't hold it when calling ->statfs() - superblock is pinned down | |
164 | by resolving the pathname passed to syscall. | |
1da177e4 LT |
165 | ->quota_read() and ->quota_write() functions are both guaranteed to |
166 | be the only ones operating on the quota file by the quota code (via | |
167 | dqio_sem) (unless an admin really wants to screw up something and | |
168 | writes to quota files with quotas on). For other details about locking | |
169 | see also dquot_operations section. | |
b83be6f2 CH |
170 | ->bdev_try_to_free_page is called from the ->releasepage handler of |
171 | the block device inode. See there for more details. | |
1da177e4 LT |
172 | |
173 | --------------------------- file_system_type --------------------------- | |
174 | prototypes: | |
b83be6f2 CH |
175 | struct dentry *(*mount) (struct file_system_type *, int, |
176 | const char *, void *); | |
1da177e4 LT |
177 | void (*kill_sb) (struct super_block *); |
178 | locking rules: | |
b83be6f2 | 179 | may block |
b83be6f2 CH |
180 | mount yes |
181 | kill_sb yes | |
1da177e4 | 182 | |
1a102ff9 AV |
183 | ->mount() returns ERR_PTR or the root dentry; its superblock should be locked |
184 | on return. | |
1da177e4 LT |
185 | ->kill_sb() takes a write-locked superblock, does all shutdown work on it, |
186 | unlocks and drops the reference. | |
187 | ||
188 | --------------------------- address_space_operations -------------------------- | |
189 | prototypes: | |
190 | int (*writepage)(struct page *page, struct writeback_control *wbc); | |
191 | int (*readpage)(struct file *, struct page *); | |
1da177e4 LT |
192 | int (*writepages)(struct address_space *, struct writeback_control *); |
193 | int (*set_page_dirty)(struct page *page); | |
194 | int (*readpages)(struct file *filp, struct address_space *mapping, | |
195 | struct list_head *pages, unsigned nr_pages); | |
4e02ed4b NP |
196 | int (*write_begin)(struct file *, struct address_space *mapping, |
197 | loff_t pos, unsigned len, unsigned flags, | |
198 | struct page **pagep, void **fsdata); | |
199 | int (*write_end)(struct file *, struct address_space *mapping, | |
200 | loff_t pos, unsigned len, unsigned copied, | |
201 | struct page *page, void *fsdata); | |
1da177e4 | 202 | sector_t (*bmap)(struct address_space *, sector_t); |
d47992f8 | 203 | void (*invalidatepage) (struct page *, unsigned int, unsigned int); |
1da177e4 | 204 | int (*releasepage) (struct page *, int); |
6072d13c | 205 | void (*freepage)(struct page *); |
c8b8e32d | 206 | int (*direct_IO)(struct kiocb *, struct iov_iter *iter); |
bda807d4 | 207 | bool (*isolate_page) (struct page *, isolate_mode_t); |
b83be6f2 | 208 | int (*migratepage)(struct address_space *, struct page *, struct page *); |
bda807d4 | 209 | void (*putback_page) (struct page *); |
b83be6f2 | 210 | int (*launder_page)(struct page *); |
c186afb4 | 211 | int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long); |
b83be6f2 | 212 | int (*error_remove_page)(struct address_space *, struct page *); |
62c230bc MG |
213 | int (*swap_activate)(struct file *); |
214 | int (*swap_deactivate)(struct file *); | |
1da177e4 LT |
215 | |
216 | locking rules: | |
6072d13c | 217 | All except set_page_dirty and freepage may block |
1da177e4 | 218 | |
965de0ec | 219 | PageLocked(page) i_rwsem |
b83be6f2 CH |
220 | writepage: yes, unlocks (see below) |
221 | readpage: yes, unlocks | |
b83be6f2 CH |
222 | writepages: |
223 | set_page_dirty no | |
224 | readpages: | |
965de0ec SA |
225 | write_begin: locks the page exclusive |
226 | write_end: yes, unlocks exclusive | |
b83be6f2 CH |
227 | bmap: |
228 | invalidatepage: yes | |
229 | releasepage: yes | |
230 | freepage: yes | |
231 | direct_IO: | |
bda807d4 | 232 | isolate_page: yes |
b83be6f2 | 233 | migratepage: yes (both) |
bda807d4 | 234 | putback_page: yes |
b83be6f2 CH |
235 | launder_page: yes |
236 | is_partially_uptodate: yes | |
237 | error_remove_page: yes | |
62c230bc MG |
238 | swap_activate: no |
239 | swap_deactivate: no | |
1da177e4 | 240 | |
f4e6d844 MW |
241 | ->write_begin(), ->write_end() and ->readpage() may be called from |
242 | the request handler (/dev/loop). | |
1da177e4 LT |
243 | |
244 | ->readpage() unlocks the page, either synchronously or via I/O | |
245 | completion. | |
246 | ||
247 | ->readpages() populates the pagecache with the passed pages and starts | |
248 | I/O against them. They come unlocked upon I/O completion. | |
249 | ||
250 | ->writepage() is used for two purposes: for "memory cleansing" and for | |
251 | "sync". These are quite different operations and the behaviour may differ | |
252 | depending upon the mode. | |
253 | ||
254 | If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then | |
255 | it *must* start I/O against the page, even if that would involve | |
256 | blocking on in-progress I/O. | |
257 | ||
258 | If writepage is called for memory cleansing (sync_mode == | |
259 | WBC_SYNC_NONE) then its role is to get as much writeout underway as | |
260 | possible. So writepage should try to avoid blocking against | |
261 | currently-in-progress I/O. | |
262 | ||
263 | If the filesystem is not called for "sync" and it determines that it | |
264 | would need to block against in-progress I/O to be able to start new I/O | |
265 | against the page the filesystem should redirty the page with | |
266 | redirty_page_for_writepage(), then unlock the page and return zero. | |
267 | This may also be done to avoid internal deadlocks, but rarely. | |
268 | ||
3a4fa0a2 | 269 | If the filesystem is called for sync then it must wait on any |
1da177e4 LT |
270 | in-progress I/O and then start new I/O. |
271 | ||
2054606a ND |
272 | The filesystem should unlock the page synchronously, before returning to the |
273 | caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE | |
274 | value. WRITEPAGE_ACTIVATE means that page cannot really be written out | |
275 | currently, and VM should stop calling ->writepage() on this page for some | |
276 | time. VM does this by moving page to the head of the active list, hence the | |
277 | name. | |
1da177e4 LT |
278 | |
279 | Unless the filesystem is going to redirty_page_for_writepage(), unlock the page | |
280 | and return zero, writepage *must* run set_page_writeback() against the page, | |
281 | followed by unlocking it. Once set_page_writeback() has been run against the | |
282 | page, write I/O can be submitted and the write I/O completion handler must run | |
283 | end_page_writeback() once the I/O is complete. If no I/O is submitted, the | |
284 | filesystem must run end_page_writeback() against the page before returning from | |
285 | writepage. | |
286 | ||
287 | That is: after 2.5.12, pages which are under writeout are *not* locked. Note, | |
288 | if the filesystem needs the page to be locked during writeout, that is ok, too, | |
289 | the page is allowed to be unlocked at any point in time between the calls to | |
290 | set_page_writeback() and end_page_writeback(). | |
291 | ||
292 | Note, failure to run either redirty_page_for_writepage() or the combination of | |
293 | set_page_writeback()/end_page_writeback() on a page submitted to writepage | |
294 | will leave the page itself marked clean but it will be tagged as dirty in the | |
295 | radix tree. This incoherency can lead to all sorts of hard-to-debug problems | |
296 | in the filesystem like having dirty inodes at umount and losing written data. | |
297 | ||
1da177e4 LT |
298 | ->writepages() is used for periodic writeback and for syscall-initiated |
299 | sync operations. The address_space should start I/O against at least | |
300 | *nr_to_write pages. *nr_to_write must be decremented for each page which is | |
301 | written. The address_space implementation may write more (or less) pages | |
302 | than *nr_to_write asks for, but it should try to be reasonably close. If | |
303 | nr_to_write is NULL, all dirty pages must be written. | |
304 | ||
305 | writepages should _only_ write pages which are present on | |
306 | mapping->io_pages. | |
307 | ||
308 | ->set_page_dirty() is called from various places in the kernel | |
309 | when the target page is marked as needing writeback. It may be called | |
310 | under spinlock (it cannot block) and is sometimes called with the page | |
311 | not locked. | |
312 | ||
313 | ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some | |
b83be6f2 CH |
314 | filesystems and by the swapper. The latter will eventually go away. Please, |
315 | keep it that way and don't breed new callers. | |
1da177e4 LT |
316 | |
317 | ->invalidatepage() is called when the filesystem must attempt to drop | |
d47992f8 LC |
318 | some or all of the buffers from the page when it is being truncated. It |
319 | returns zero on success. If ->invalidatepage is zero, the kernel uses | |
1da177e4 LT |
320 | block_invalidatepage() instead. |
321 | ||
322 | ->releasepage() is called when the kernel is about to try to drop the | |
323 | buffers from the page in preparation for freeing it. It returns zero to | |
324 | indicate that the buffers are (or may be) freeable. If ->releasepage is zero, | |
325 | the kernel assumes that the fs has no private interest in the buffers. | |
326 | ||
6072d13c LT |
327 | ->freepage() is called when the kernel is done dropping the page |
328 | from the page cache. | |
329 | ||
e3db7691 TM |
330 | ->launder_page() may be called prior to releasing a page if |
331 | it is still found to be dirty. It returns zero if the page was successfully | |
332 | cleaned, or an error value if not. Note that in order to prevent the page | |
333 | getting mapped back in and redirtied, it needs to be kept locked | |
334 | across the entire operation. | |
335 | ||
62c230bc MG |
336 | ->swap_activate will be called with a non-zero argument on |
337 | files backing (non block device backed) swapfiles. A return value | |
338 | of zero indicates success, in which case this file can be used for | |
339 | backing swapspace. The swapspace operations will be proxied to the | |
340 | address space operations. | |
341 | ||
342 | ->swap_deactivate() will be called in the sys_swapoff() | |
343 | path after ->swap_activate() returned success. | |
344 | ||
1da177e4 LT |
345 | ----------------------- file_lock_operations ------------------------------ |
346 | prototypes: | |
1da177e4 LT |
347 | void (*fl_copy_lock)(struct file_lock *, struct file_lock *); |
348 | void (*fl_release_private)(struct file_lock *); | |
349 | ||
350 | ||
351 | locking rules: | |
1c8c601a | 352 | inode->i_lock may block |
b83be6f2 | 353 | fl_copy_lock: yes no |
2ece173e JL |
354 | fl_release_private: maybe maybe[1] |
355 | ||
356 | [1]: ->fl_release_private for flock or POSIX locks is currently allowed | |
357 | to block. Leases however can still be freed while the i_lock is held and | |
358 | so fl_release_private called on a lease should not block. | |
1da177e4 LT |
359 | |
360 | ----------------------- lock_manager_operations --------------------------- | |
361 | prototypes: | |
8fb47a4f | 362 | int (*lm_compare_owner)(struct file_lock *, struct file_lock *); |
3999e493 | 363 | unsigned long (*lm_owner_key)(struct file_lock *); |
8fb47a4f BF |
364 | void (*lm_notify)(struct file_lock *); /* unblock callback */ |
365 | int (*lm_grant)(struct file_lock *, struct file_lock *, int); | |
8fb47a4f BF |
366 | void (*lm_break)(struct file_lock *); /* break_lease callback */ |
367 | int (*lm_change)(struct file_lock **, int); | |
1da177e4 LT |
368 | |
369 | locking rules: | |
1c8c601a | 370 | |
7b2296af JL |
371 | inode->i_lock blocked_lock_lock may block |
372 | lm_compare_owner: yes[1] maybe no | |
373 | lm_owner_key yes[1] yes no | |
374 | lm_notify: yes yes no | |
375 | lm_grant: no no no | |
376 | lm_break: yes no no | |
377 | lm_change yes no no | |
1c8c601a | 378 | |
3999e493 JL |
379 | [1]: ->lm_compare_owner and ->lm_owner_key are generally called with |
380 | *an* inode->i_lock held. It may not be the i_lock of the inode | |
381 | associated with either file_lock argument! This is the case with deadlock | |
382 | detection, since the code has to chase down the owners of locks that may | |
383 | be entirely unrelated to the one on which the lock is being acquired. | |
7b2296af | 384 | For deadlock detection however, the blocked_lock_lock is also held. The |
3999e493 JL |
385 | fact that these locks are held ensures that the file_locks do not |
386 | disappear out from under you while doing the comparison or generating an | |
387 | owner key. | |
b83be6f2 | 388 | |
1da177e4 LT |
389 | --------------------------- buffer_head ----------------------------------- |
390 | prototypes: | |
391 | void (*b_end_io)(struct buffer_head *bh, int uptodate); | |
392 | ||
393 | locking rules: | |
394 | called from interrupts. In other words, extreme care is needed here. | |
395 | bh is locked, but that's all warranties we have here. Currently only RAID1, | |
396 | highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices | |
397 | call this method upon the IO completion. | |
398 | ||
399 | --------------------------- block_device_operations ----------------------- | |
400 | prototypes: | |
e1455d1b CH |
401 | int (*open) (struct block_device *, fmode_t); |
402 | int (*release) (struct gendisk *, fmode_t); | |
403 | int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
404 | int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
7a9eb206 | 405 | int (*direct_access) (struct block_device *, sector_t, void **, |
e2e05394 | 406 | unsigned long *); |
1da177e4 | 407 | int (*media_changed) (struct gendisk *); |
e1455d1b | 408 | void (*unlock_native_capacity) (struct gendisk *); |
1da177e4 | 409 | int (*revalidate_disk) (struct gendisk *); |
e1455d1b CH |
410 | int (*getgeo)(struct block_device *, struct hd_geometry *); |
411 | void (*swap_slot_free_notify) (struct block_device *, unsigned long); | |
1da177e4 LT |
412 | |
413 | locking rules: | |
b83be6f2 CH |
414 | bd_mutex |
415 | open: yes | |
416 | release: yes | |
417 | ioctl: no | |
418 | compat_ioctl: no | |
419 | direct_access: no | |
420 | media_changed: no | |
421 | unlock_native_capacity: no | |
422 | revalidate_disk: no | |
423 | getgeo: no | |
424 | swap_slot_free_notify: no (see below) | |
e1455d1b CH |
425 | |
426 | media_changed, unlock_native_capacity and revalidate_disk are called only from | |
427 | check_disk_change(). | |
428 | ||
429 | swap_slot_free_notify is called with swap_lock and sometimes the page lock | |
430 | held. | |
1da177e4 | 431 | |
1da177e4 LT |
432 | |
433 | --------------------------- file_operations ------------------------------- | |
434 | prototypes: | |
435 | loff_t (*llseek) (struct file *, loff_t, int); | |
436 | ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); | |
1da177e4 | 437 | ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); |
293bc982 AV |
438 | ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); |
439 | ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); | |
2233f31a | 440 | int (*iterate) (struct file *, struct dir_context *); |
965de0ec | 441 | int (*iterate_shared) (struct file *, struct dir_context *); |
6e8b704d | 442 | __poll_t (*poll) (struct file *, struct poll_table_struct *); |
1da177e4 LT |
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 *); | |
02c24a82 | 449 | int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); |
1da177e4 LT |
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); | |
b83be6f2 CH |
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); | |
e6f5c789 | 468 | int (*setlease)(struct file *, long, struct file_lock **, void **); |
2fe17c10 | 469 | long (*fallocate)(struct file *, int, loff_t, loff_t); |
1da177e4 LT |
470 | }; |
471 | ||
472 | locking rules: | |
a11e1d43 | 473 | All may block. |
b83be6f2 | 474 | |
1da177e4 LT |
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 | |
866707fc JB |
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. | |
1da177e4 | 482 | |
965de0ec SA |
483 | ->iterate() is called with i_rwsem exclusive. |
484 | ||
485 | ->iterate_shared() is called with i_rwsem at least shared. | |
486 | ||
b83be6f2 CH |
487 | ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. |
488 | Most instances call fasync_helper(), which does that maintenance, so it's | |
489 | not normally something one needs to worry about. Return values > 0 will be | |
490 | mapped to zero in the VFS layer. | |
1da177e4 LT |
491 | |
492 | ->readdir() and ->ioctl() on directories must be changed. Ideally we would | |
493 | move ->readdir() to inode_operations and use a separate method for directory | |
494 | ->ioctl() or kill the latter completely. One of the problems is that for | |
495 | anything that resembles union-mount we won't have a struct file for all | |
496 | components. And there are other reasons why the current interface is a mess... | |
497 | ||
1da177e4 LT |
498 | ->read on directories probably must go away - we should just enforce -EISDIR |
499 | in sys_read() and friends. | |
500 | ||
f82b4b67 JL |
501 | ->setlease operations should call generic_setlease() before or after setting |
502 | the lease within the individual filesystem to record the result of the | |
503 | operation | |
504 | ||
1da177e4 LT |
505 | --------------------------- dquot_operations ------------------------------- |
506 | prototypes: | |
1da177e4 LT |
507 | int (*write_dquot) (struct dquot *); |
508 | int (*acquire_dquot) (struct dquot *); | |
509 | int (*release_dquot) (struct dquot *); | |
510 | int (*mark_dirty) (struct dquot *); | |
511 | int (*write_info) (struct super_block *, int); | |
512 | ||
513 | These operations are intended to be more or less wrapping functions that ensure | |
514 | a proper locking wrt the filesystem and call the generic quota operations. | |
515 | ||
516 | What filesystem should expect from the generic quota functions: | |
517 | ||
518 | FS recursion Held locks when called | |
1da177e4 LT |
519 | write_dquot: yes dqonoff_sem or dqptr_sem |
520 | acquire_dquot: yes dqonoff_sem or dqptr_sem | |
521 | release_dquot: yes dqonoff_sem or dqptr_sem | |
522 | mark_dirty: no - | |
523 | write_info: yes dqonoff_sem | |
524 | ||
525 | FS recursion means calling ->quota_read() and ->quota_write() from superblock | |
526 | operations. | |
527 | ||
1da177e4 LT |
528 | More details about quota locking can be found in fs/dquot.c. |
529 | ||
530 | --------------------------- vm_operations_struct ----------------------------- | |
531 | prototypes: | |
532 | void (*open)(struct vm_area_struct*); | |
533 | void (*close)(struct vm_area_struct*); | |
fe3136f4 SJ |
534 | vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *); |
535 | vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); | |
536 | vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *); | |
28b2ee20 | 537 | int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); |
1da177e4 LT |
538 | |
539 | locking rules: | |
b83be6f2 CH |
540 | mmap_sem PageLocked(page) |
541 | open: yes | |
542 | close: yes | |
543 | fault: yes can return with page locked | |
8c6e50b0 | 544 | map_pages: yes |
b83be6f2 | 545 | page_mkwrite: yes can return with page locked |
dd906184 | 546 | pfn_mkwrite: yes |
b83be6f2 | 547 | access: yes |
ed2f2f9b | 548 | |
b827e496 NP |
549 | ->fault() is called when a previously not present pte is about |
550 | to be faulted in. The filesystem must find and return the page associated | |
551 | with the passed in "pgoff" in the vm_fault structure. If it is possible that | |
552 | the page may be truncated and/or invalidated, then the filesystem must lock | |
553 | the page, then ensure it is not already truncated (the page lock will block | |
554 | subsequent truncate), and then return with VM_FAULT_LOCKED, and the page | |
555 | locked. The VM will unlock the page. | |
556 | ||
8c6e50b0 | 557 | ->map_pages() is called when VM asks to map easy accessible pages. |
bae473a4 KS |
558 | Filesystem should find and map pages associated with offsets from "start_pgoff" |
559 | till "end_pgoff". ->map_pages() is called with page table locked and must | |
8c6e50b0 KS |
560 | not block. If it's not possible to reach a page without blocking, |
561 | filesystem should skip it. Filesystem should use do_set_pte() to setup | |
bae473a4 | 562 | page table entry. Pointer to entry associated with the page is passed in |
82b0f8c3 | 563 | "pte" field in vm_fault structure. Pointers to entries for other offsets |
bae473a4 | 564 | should be calculated relative to "pte". |
8c6e50b0 | 565 | |
b827e496 NP |
566 | ->page_mkwrite() is called when a previously read-only pte is |
567 | about to become writeable. The filesystem again must ensure that there are | |
568 | no truncate/invalidate races, and then return with the page locked. If | |
569 | the page has been truncated, the filesystem should not look up a new page | |
570 | like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which | |
571 | will cause the VM to retry the fault. | |
1da177e4 | 572 | |
dd906184 BH |
573 | ->pfn_mkwrite() is the same as page_mkwrite but when the pte is |
574 | VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is | |
575 | VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior | |
576 | after this call is to make the pte read-write, unless pfn_mkwrite returns | |
577 | an error. | |
578 | ||
28b2ee20 | 579 | ->access() is called when get_user_pages() fails in |
507da6a1 | 580 | access_process_vm(), typically used to debug a process through |
28b2ee20 RR |
581 | /proc/pid/mem or ptrace. This function is needed only for |
582 | VM_IO | VM_PFNMAP VMAs. | |
583 | ||
1da177e4 LT |
584 | ================================================================================ |
585 | Dubious stuff | |
586 | ||
587 | (if you break something or notice that it is broken and do not fix it yourself | |
588 | - at least put it here) |