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); |
b1e6a015 NP |
13 | int (*d_hash)(const struct dentry *, const struct inode *, |
14 | struct qstr *); | |
621e155a NP |
15 | int (*d_compare)(const struct dentry *, const struct inode *, |
16 | const struct dentry *, const struct inode *, | |
17 | unsigned int, const char *, const struct qstr *); | |
1da177e4 LT |
18 | int (*d_delete)(struct dentry *); |
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); |
cc53ce53 | 23 | int (*d_manage)(struct dentry *, bool); |
1da177e4 LT |
24 | |
25 | locking rules: | |
34286d66 NP |
26 | rename_lock ->d_lock may block rcu-walk |
27 | d_revalidate: no no yes (ref-walk) maybe | |
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 *); | |
50 | int (*readlink) (struct dentry *, char __user *,int); | |
b83be6f2 CH |
51 | void * (*follow_link) (struct dentry *, struct nameidata *); |
52 | void (*put_link) (struct dentry *, struct nameidata *, void *); | |
1da177e4 | 53 | void (*truncate) (struct inode *); |
b74c79e9 | 54 | int (*permission) (struct inode *, int, unsigned int); |
4e34e719 | 55 | int (*get_acl)(struct inode *, int); |
1da177e4 LT |
56 | int (*setattr) (struct dentry *, struct iattr *); |
57 | int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *); | |
58 | int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); | |
59 | ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); | |
60 | ssize_t (*listxattr) (struct dentry *, char *, size_t); | |
61 | int (*removexattr) (struct dentry *, const char *); | |
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, |
47237687 | 66 | umode_t create_mode, int *opened); |
1da177e4 LT |
67 | |
68 | locking rules: | |
b83be6f2 | 69 | all may block |
a7bc02f4 | 70 | i_mutex(inode) |
1da177e4 LT |
71 | lookup: yes |
72 | create: yes | |
73 | link: yes (both) | |
74 | mknod: yes | |
75 | symlink: yes | |
76 | mkdir: yes | |
77 | unlink: yes (both) | |
78 | rmdir: yes (both) (see below) | |
79 | rename: yes (all) (see below) | |
80 | readlink: no | |
81 | follow_link: no | |
b83be6f2 | 82 | put_link: no |
1da177e4 LT |
83 | truncate: yes (see below) |
84 | setattr: yes | |
b74c79e9 | 85 | permission: no (may not block if called in rcu-walk mode) |
4e34e719 | 86 | get_acl: no |
1da177e4 LT |
87 | getattr: no |
88 | setxattr: yes | |
89 | getxattr: no | |
90 | listxattr: no | |
91 | removexattr: yes | |
b83be6f2 | 92 | fiemap: no |
c3b2da31 | 93 | update_time: no |
d18e9008 | 94 | atomic_open: yes |
c3b2da31 | 95 | |
a7bc02f4 | 96 | Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on |
1da177e4 LT |
97 | victim. |
98 | cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. | |
99 | ->truncate() is never called directly - it's a callback, not a | |
b83be6f2 | 100 | method. It's called by vmtruncate() - deprecated library function used by |
1da177e4 LT |
101 | ->setattr(). Locking information above applies to that call (i.e. is |
102 | inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been | |
103 | passed). | |
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 LT |
116 | void (*put_super) (struct super_block *); |
117 | void (*write_super) (struct super_block *); | |
118 | int (*sync_fs)(struct super_block *sb, int wait); | |
c4be0c1d TS |
119 | int (*freeze_fs) (struct super_block *); |
120 | int (*unfreeze_fs) (struct super_block *); | |
726c3342 | 121 | int (*statfs) (struct dentry *, struct kstatfs *); |
1da177e4 | 122 | int (*remount_fs) (struct super_block *, int *, char *); |
1da177e4 | 123 | void (*umount_begin) (struct super_block *); |
34c80b1d | 124 | int (*show_options)(struct seq_file *, struct dentry *); |
1da177e4 LT |
125 | ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); |
126 | ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); | |
b83be6f2 | 127 | int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); |
1da177e4 LT |
128 | |
129 | locking rules: | |
336fb3b9 | 130 | All may block [not true, see below] |
7e325d3a CH |
131 | s_umount |
132 | alloc_inode: | |
133 | destroy_inode: | |
aa385729 | 134 | dirty_inode: |
7e325d3a | 135 | write_inode: |
f283c86a | 136 | drop_inode: !!!inode->i_lock!!! |
336fb3b9 | 137 | evict_inode: |
7e325d3a CH |
138 | put_super: write |
139 | write_super: read | |
140 | sync_fs: read | |
141 | freeze_fs: read | |
142 | unfreeze_fs: read | |
336fb3b9 AV |
143 | statfs: maybe(read) (see below) |
144 | remount_fs: write | |
7e325d3a CH |
145 | umount_begin: no |
146 | show_options: no (namespace_sem) | |
147 | quota_read: no (see below) | |
148 | quota_write: no (see below) | |
b83be6f2 | 149 | bdev_try_to_free_page: no (see below) |
1da177e4 | 150 | |
336fb3b9 AV |
151 | ->statfs() has s_umount (shared) when called by ustat(2) (native or |
152 | compat), but that's an accident of bad API; s_umount is used to pin | |
153 | the superblock down when we only have dev_t given us by userland to | |
154 | identify the superblock. Everything else (statfs(), fstatfs(), etc.) | |
155 | doesn't hold it when calling ->statfs() - superblock is pinned down | |
156 | by resolving the pathname passed to syscall. | |
1da177e4 LT |
157 | ->quota_read() and ->quota_write() functions are both guaranteed to |
158 | be the only ones operating on the quota file by the quota code (via | |
159 | dqio_sem) (unless an admin really wants to screw up something and | |
160 | writes to quota files with quotas on). For other details about locking | |
161 | see also dquot_operations section. | |
b83be6f2 CH |
162 | ->bdev_try_to_free_page is called from the ->releasepage handler of |
163 | the block device inode. See there for more details. | |
1da177e4 LT |
164 | |
165 | --------------------------- file_system_type --------------------------- | |
166 | prototypes: | |
5d8b2ebf JC |
167 | int (*get_sb) (struct file_system_type *, int, |
168 | const char *, void *, struct vfsmount *); | |
b83be6f2 CH |
169 | struct dentry *(*mount) (struct file_system_type *, int, |
170 | const char *, void *); | |
1da177e4 LT |
171 | void (*kill_sb) (struct super_block *); |
172 | locking rules: | |
b83be6f2 | 173 | may block |
b83be6f2 CH |
174 | mount yes |
175 | kill_sb yes | |
1da177e4 | 176 | |
1a102ff9 AV |
177 | ->mount() returns ERR_PTR or the root dentry; its superblock should be locked |
178 | on return. | |
1da177e4 LT |
179 | ->kill_sb() takes a write-locked superblock, does all shutdown work on it, |
180 | unlocks and drops the reference. | |
181 | ||
182 | --------------------------- address_space_operations -------------------------- | |
183 | prototypes: | |
184 | int (*writepage)(struct page *page, struct writeback_control *wbc); | |
185 | int (*readpage)(struct file *, struct page *); | |
186 | int (*sync_page)(struct page *); | |
187 | int (*writepages)(struct address_space *, struct writeback_control *); | |
188 | int (*set_page_dirty)(struct page *page); | |
189 | int (*readpages)(struct file *filp, struct address_space *mapping, | |
190 | struct list_head *pages, unsigned nr_pages); | |
4e02ed4b NP |
191 | int (*write_begin)(struct file *, struct address_space *mapping, |
192 | loff_t pos, unsigned len, unsigned flags, | |
193 | struct page **pagep, void **fsdata); | |
194 | int (*write_end)(struct file *, struct address_space *mapping, | |
195 | loff_t pos, unsigned len, unsigned copied, | |
196 | struct page *page, void *fsdata); | |
1da177e4 LT |
197 | sector_t (*bmap)(struct address_space *, sector_t); |
198 | int (*invalidatepage) (struct page *, unsigned long); | |
199 | int (*releasepage) (struct page *, int); | |
6072d13c | 200 | void (*freepage)(struct page *); |
1da177e4 LT |
201 | int (*direct_IO)(int, struct kiocb *, const struct iovec *iov, |
202 | loff_t offset, unsigned long nr_segs); | |
b83be6f2 CH |
203 | int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, |
204 | unsigned long *); | |
205 | int (*migratepage)(struct address_space *, struct page *, struct page *); | |
206 | int (*launder_page)(struct page *); | |
207 | int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long); | |
208 | int (*error_remove_page)(struct address_space *, struct page *); | |
1da177e4 LT |
209 | |
210 | locking rules: | |
6072d13c | 211 | All except set_page_dirty and freepage may block |
1da177e4 | 212 | |
b83be6f2 CH |
213 | PageLocked(page) i_mutex |
214 | writepage: yes, unlocks (see below) | |
215 | readpage: yes, unlocks | |
216 | sync_page: maybe | |
217 | writepages: | |
218 | set_page_dirty no | |
219 | readpages: | |
220 | write_begin: locks the page yes | |
221 | write_end: yes, unlocks yes | |
222 | bmap: | |
223 | invalidatepage: yes | |
224 | releasepage: yes | |
225 | freepage: yes | |
226 | direct_IO: | |
227 | get_xip_mem: maybe | |
228 | migratepage: yes (both) | |
229 | launder_page: yes | |
230 | is_partially_uptodate: yes | |
231 | error_remove_page: yes | |
1da177e4 | 232 | |
4e02ed4b | 233 | ->write_begin(), ->write_end(), ->sync_page() and ->readpage() |
1da177e4 LT |
234 | may be called from the request handler (/dev/loop). |
235 | ||
236 | ->readpage() unlocks the page, either synchronously or via I/O | |
237 | completion. | |
238 | ||
239 | ->readpages() populates the pagecache with the passed pages and starts | |
240 | I/O against them. They come unlocked upon I/O completion. | |
241 | ||
242 | ->writepage() is used for two purposes: for "memory cleansing" and for | |
243 | "sync". These are quite different operations and the behaviour may differ | |
244 | depending upon the mode. | |
245 | ||
246 | If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then | |
247 | it *must* start I/O against the page, even if that would involve | |
248 | blocking on in-progress I/O. | |
249 | ||
250 | If writepage is called for memory cleansing (sync_mode == | |
251 | WBC_SYNC_NONE) then its role is to get as much writeout underway as | |
252 | possible. So writepage should try to avoid blocking against | |
253 | currently-in-progress I/O. | |
254 | ||
255 | If the filesystem is not called for "sync" and it determines that it | |
256 | would need to block against in-progress I/O to be able to start new I/O | |
257 | against the page the filesystem should redirty the page with | |
258 | redirty_page_for_writepage(), then unlock the page and return zero. | |
259 | This may also be done to avoid internal deadlocks, but rarely. | |
260 | ||
3a4fa0a2 | 261 | If the filesystem is called for sync then it must wait on any |
1da177e4 LT |
262 | in-progress I/O and then start new I/O. |
263 | ||
2054606a ND |
264 | The filesystem should unlock the page synchronously, before returning to the |
265 | caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE | |
266 | value. WRITEPAGE_ACTIVATE means that page cannot really be written out | |
267 | currently, and VM should stop calling ->writepage() on this page for some | |
268 | time. VM does this by moving page to the head of the active list, hence the | |
269 | name. | |
1da177e4 LT |
270 | |
271 | Unless the filesystem is going to redirty_page_for_writepage(), unlock the page | |
272 | and return zero, writepage *must* run set_page_writeback() against the page, | |
273 | followed by unlocking it. Once set_page_writeback() has been run against the | |
274 | page, write I/O can be submitted and the write I/O completion handler must run | |
275 | end_page_writeback() once the I/O is complete. If no I/O is submitted, the | |
276 | filesystem must run end_page_writeback() against the page before returning from | |
277 | writepage. | |
278 | ||
279 | That is: after 2.5.12, pages which are under writeout are *not* locked. Note, | |
280 | if the filesystem needs the page to be locked during writeout, that is ok, too, | |
281 | the page is allowed to be unlocked at any point in time between the calls to | |
282 | set_page_writeback() and end_page_writeback(). | |
283 | ||
284 | Note, failure to run either redirty_page_for_writepage() or the combination of | |
285 | set_page_writeback()/end_page_writeback() on a page submitted to writepage | |
286 | will leave the page itself marked clean but it will be tagged as dirty in the | |
287 | radix tree. This incoherency can lead to all sorts of hard-to-debug problems | |
288 | in the filesystem like having dirty inodes at umount and losing written data. | |
289 | ||
290 | ->sync_page() locking rules are not well-defined - usually it is called | |
291 | with lock on page, but that is not guaranteed. Considering the currently | |
292 | existing instances of this method ->sync_page() itself doesn't look | |
293 | well-defined... | |
294 | ||
295 | ->writepages() is used for periodic writeback and for syscall-initiated | |
296 | sync operations. The address_space should start I/O against at least | |
297 | *nr_to_write pages. *nr_to_write must be decremented for each page which is | |
298 | written. The address_space implementation may write more (or less) pages | |
299 | than *nr_to_write asks for, but it should try to be reasonably close. If | |
300 | nr_to_write is NULL, all dirty pages must be written. | |
301 | ||
302 | writepages should _only_ write pages which are present on | |
303 | mapping->io_pages. | |
304 | ||
305 | ->set_page_dirty() is called from various places in the kernel | |
306 | when the target page is marked as needing writeback. It may be called | |
307 | under spinlock (it cannot block) and is sometimes called with the page | |
308 | not locked. | |
309 | ||
310 | ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some | |
b83be6f2 CH |
311 | filesystems and by the swapper. The latter will eventually go away. Please, |
312 | keep it that way and don't breed new callers. | |
1da177e4 LT |
313 | |
314 | ->invalidatepage() is called when the filesystem must attempt to drop | |
315 | some or all of the buffers from the page when it is being truncated. It | |
316 | returns zero on success. If ->invalidatepage is zero, the kernel uses | |
317 | block_invalidatepage() instead. | |
318 | ||
319 | ->releasepage() is called when the kernel is about to try to drop the | |
320 | buffers from the page in preparation for freeing it. It returns zero to | |
321 | indicate that the buffers are (or may be) freeable. If ->releasepage is zero, | |
322 | the kernel assumes that the fs has no private interest in the buffers. | |
323 | ||
6072d13c LT |
324 | ->freepage() is called when the kernel is done dropping the page |
325 | from the page cache. | |
326 | ||
e3db7691 TM |
327 | ->launder_page() may be called prior to releasing a page if |
328 | it is still found to be dirty. It returns zero if the page was successfully | |
329 | cleaned, or an error value if not. Note that in order to prevent the page | |
330 | getting mapped back in and redirtied, it needs to be kept locked | |
331 | across the entire operation. | |
332 | ||
1da177e4 LT |
333 | ----------------------- file_lock_operations ------------------------------ |
334 | prototypes: | |
1da177e4 LT |
335 | void (*fl_copy_lock)(struct file_lock *, struct file_lock *); |
336 | void (*fl_release_private)(struct file_lock *); | |
337 | ||
338 | ||
339 | locking rules: | |
b83be6f2 CH |
340 | file_lock_lock may block |
341 | fl_copy_lock: yes no | |
342 | fl_release_private: maybe no | |
1da177e4 LT |
343 | |
344 | ----------------------- lock_manager_operations --------------------------- | |
345 | prototypes: | |
8fb47a4f BF |
346 | int (*lm_compare_owner)(struct file_lock *, struct file_lock *); |
347 | void (*lm_notify)(struct file_lock *); /* unblock callback */ | |
348 | int (*lm_grant)(struct file_lock *, struct file_lock *, int); | |
349 | void (*lm_release_private)(struct file_lock *); | |
350 | void (*lm_break)(struct file_lock *); /* break_lease callback */ | |
351 | int (*lm_change)(struct file_lock **, int); | |
1da177e4 LT |
352 | |
353 | locking rules: | |
b83be6f2 | 354 | file_lock_lock may block |
8fb47a4f BF |
355 | lm_compare_owner: yes no |
356 | lm_notify: yes no | |
357 | lm_grant: no no | |
358 | lm_release_private: maybe no | |
359 | lm_break: yes no | |
360 | lm_change yes no | |
b83be6f2 | 361 | |
1da177e4 LT |
362 | --------------------------- buffer_head ----------------------------------- |
363 | prototypes: | |
364 | void (*b_end_io)(struct buffer_head *bh, int uptodate); | |
365 | ||
366 | locking rules: | |
367 | called from interrupts. In other words, extreme care is needed here. | |
368 | bh is locked, but that's all warranties we have here. Currently only RAID1, | |
369 | highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices | |
370 | call this method upon the IO completion. | |
371 | ||
372 | --------------------------- block_device_operations ----------------------- | |
373 | prototypes: | |
e1455d1b CH |
374 | int (*open) (struct block_device *, fmode_t); |
375 | int (*release) (struct gendisk *, fmode_t); | |
376 | int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
377 | int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); | |
378 | int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); | |
1da177e4 | 379 | int (*media_changed) (struct gendisk *); |
e1455d1b | 380 | void (*unlock_native_capacity) (struct gendisk *); |
1da177e4 | 381 | int (*revalidate_disk) (struct gendisk *); |
e1455d1b CH |
382 | int (*getgeo)(struct block_device *, struct hd_geometry *); |
383 | void (*swap_slot_free_notify) (struct block_device *, unsigned long); | |
1da177e4 LT |
384 | |
385 | locking rules: | |
b83be6f2 CH |
386 | bd_mutex |
387 | open: yes | |
388 | release: yes | |
389 | ioctl: no | |
390 | compat_ioctl: no | |
391 | direct_access: no | |
392 | media_changed: no | |
393 | unlock_native_capacity: no | |
394 | revalidate_disk: no | |
395 | getgeo: no | |
396 | swap_slot_free_notify: no (see below) | |
e1455d1b CH |
397 | |
398 | media_changed, unlock_native_capacity and revalidate_disk are called only from | |
399 | check_disk_change(). | |
400 | ||
401 | swap_slot_free_notify is called with swap_lock and sometimes the page lock | |
402 | held. | |
1da177e4 | 403 | |
1da177e4 LT |
404 | |
405 | --------------------------- file_operations ------------------------------- | |
406 | prototypes: | |
407 | loff_t (*llseek) (struct file *, loff_t, int); | |
408 | ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); | |
1da177e4 | 409 | ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); |
027445c3 BP |
410 | ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); |
411 | ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); | |
1da177e4 LT |
412 | int (*readdir) (struct file *, void *, filldir_t); |
413 | unsigned int (*poll) (struct file *, struct poll_table_struct *); | |
1da177e4 LT |
414 | long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); |
415 | long (*compat_ioctl) (struct file *, unsigned int, unsigned long); | |
416 | int (*mmap) (struct file *, struct vm_area_struct *); | |
417 | int (*open) (struct inode *, struct file *); | |
418 | int (*flush) (struct file *); | |
419 | int (*release) (struct inode *, struct file *); | |
02c24a82 | 420 | int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); |
1da177e4 LT |
421 | int (*aio_fsync) (struct kiocb *, int datasync); |
422 | int (*fasync) (int, struct file *, int); | |
423 | int (*lock) (struct file *, int, struct file_lock *); | |
424 | ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, | |
425 | loff_t *); | |
426 | ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, | |
427 | loff_t *); | |
428 | ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, | |
429 | void __user *); | |
430 | ssize_t (*sendpage) (struct file *, struct page *, int, size_t, | |
431 | loff_t *, int); | |
432 | unsigned long (*get_unmapped_area)(struct file *, unsigned long, | |
433 | unsigned long, unsigned long, unsigned long); | |
434 | int (*check_flags)(int); | |
b83be6f2 CH |
435 | int (*flock) (struct file *, int, struct file_lock *); |
436 | ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, | |
437 | size_t, unsigned int); | |
438 | ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, | |
439 | size_t, unsigned int); | |
440 | int (*setlease)(struct file *, long, struct file_lock **); | |
2fe17c10 | 441 | long (*fallocate)(struct file *, int, loff_t, loff_t); |
1da177e4 LT |
442 | }; |
443 | ||
444 | locking rules: | |
b83be6f2 | 445 | All may block except for ->setlease. |
02c24a82 | 446 | No VFS locks held on entry except for ->setlease. |
b83be6f2 CH |
447 | |
448 | ->setlease has the file_list_lock held and must not sleep. | |
1da177e4 LT |
449 | |
450 | ->llseek() locking has moved from llseek to the individual llseek | |
451 | implementations. If your fs is not using generic_file_llseek, you | |
452 | need to acquire and release the appropriate locks in your ->llseek(). | |
453 | For many filesystems, it is probably safe to acquire the inode | |
866707fc JB |
454 | mutex or just to use i_size_read() instead. |
455 | Note: this does not protect the file->f_pos against concurrent modifications | |
456 | since this is something the userspace has to take care about. | |
1da177e4 | 457 | |
b83be6f2 CH |
458 | ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. |
459 | Most instances call fasync_helper(), which does that maintenance, so it's | |
460 | not normally something one needs to worry about. Return values > 0 will be | |
461 | mapped to zero in the VFS layer. | |
1da177e4 LT |
462 | |
463 | ->readdir() and ->ioctl() on directories must be changed. Ideally we would | |
464 | move ->readdir() to inode_operations and use a separate method for directory | |
465 | ->ioctl() or kill the latter completely. One of the problems is that for | |
466 | anything that resembles union-mount we won't have a struct file for all | |
467 | components. And there are other reasons why the current interface is a mess... | |
468 | ||
1da177e4 LT |
469 | ->read on directories probably must go away - we should just enforce -EISDIR |
470 | in sys_read() and friends. | |
471 | ||
1da177e4 LT |
472 | --------------------------- dquot_operations ------------------------------- |
473 | prototypes: | |
1da177e4 LT |
474 | int (*write_dquot) (struct dquot *); |
475 | int (*acquire_dquot) (struct dquot *); | |
476 | int (*release_dquot) (struct dquot *); | |
477 | int (*mark_dirty) (struct dquot *); | |
478 | int (*write_info) (struct super_block *, int); | |
479 | ||
480 | These operations are intended to be more or less wrapping functions that ensure | |
481 | a proper locking wrt the filesystem and call the generic quota operations. | |
482 | ||
483 | What filesystem should expect from the generic quota functions: | |
484 | ||
485 | FS recursion Held locks when called | |
1da177e4 LT |
486 | write_dquot: yes dqonoff_sem or dqptr_sem |
487 | acquire_dquot: yes dqonoff_sem or dqptr_sem | |
488 | release_dquot: yes dqonoff_sem or dqptr_sem | |
489 | mark_dirty: no - | |
490 | write_info: yes dqonoff_sem | |
491 | ||
492 | FS recursion means calling ->quota_read() and ->quota_write() from superblock | |
493 | operations. | |
494 | ||
1da177e4 LT |
495 | More details about quota locking can be found in fs/dquot.c. |
496 | ||
497 | --------------------------- vm_operations_struct ----------------------------- | |
498 | prototypes: | |
499 | void (*open)(struct vm_area_struct*); | |
500 | void (*close)(struct vm_area_struct*); | |
d0217ac0 | 501 | int (*fault)(struct vm_area_struct*, struct vm_fault *); |
c2ec175c | 502 | int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); |
28b2ee20 | 503 | int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); |
1da177e4 LT |
504 | |
505 | locking rules: | |
b83be6f2 CH |
506 | mmap_sem PageLocked(page) |
507 | open: yes | |
508 | close: yes | |
509 | fault: yes can return with page locked | |
510 | page_mkwrite: yes can return with page locked | |
511 | access: yes | |
ed2f2f9b | 512 | |
b827e496 NP |
513 | ->fault() is called when a previously not present pte is about |
514 | to be faulted in. The filesystem must find and return the page associated | |
515 | with the passed in "pgoff" in the vm_fault structure. If it is possible that | |
516 | the page may be truncated and/or invalidated, then the filesystem must lock | |
517 | the page, then ensure it is not already truncated (the page lock will block | |
518 | subsequent truncate), and then return with VM_FAULT_LOCKED, and the page | |
519 | locked. The VM will unlock the page. | |
520 | ||
521 | ->page_mkwrite() is called when a previously read-only pte is | |
522 | about to become writeable. The filesystem again must ensure that there are | |
523 | no truncate/invalidate races, and then return with the page locked. If | |
524 | the page has been truncated, the filesystem should not look up a new page | |
525 | like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which | |
526 | will cause the VM to retry the fault. | |
1da177e4 | 527 | |
28b2ee20 RR |
528 | ->access() is called when get_user_pages() fails in |
529 | acces_process_vm(), typically used to debug a process through | |
530 | /proc/pid/mem or ptrace. This function is needed only for | |
531 | VM_IO | VM_PFNMAP VMAs. | |
532 | ||
1da177e4 LT |
533 | ================================================================================ |
534 | Dubious stuff | |
535 | ||
536 | (if you break something or notice that it is broken and do not fix it yourself | |
537 | - at least put it here) |