blob: cbf98b989b11fa8358a9ac1965c58987012f5adf [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001 The text below describes the locking rules for VFS-related methods.
2It is (believed to be) up-to-date. *Please*, if you change anything in
3prototypes or locking protocols - update this file. And update the relevant
4instances in the tree, don't leave that to maintainers of filesystems/devices/
5etc. At the very least, put the list of dubious cases in the end of this file.
6Don't turn it into log - maintainers of out-of-the-tree code are supposed to
7be able to use diff(1).
8 Thing currently missing here: socket operations. Alexey?
9
10--------------------------- dentry_operations --------------------------
11prototypes:
Nick Piggin34286d62011-01-07 17:49:57 +110012 int (*d_revalidate)(struct dentry *, struct nameidata *);
Nick Pigginb1e6a012011-01-07 17:49:28 +110013 int (*d_hash)(const struct dentry *, const struct inode *,
14 struct qstr *);
Nick Piggin621e1552011-01-07 17:49:27 +110015 int (*d_compare)(const struct dentry *, const struct inode *,
16 const struct dentry *, const struct inode *,
17 unsigned int, const char *, const struct qstr *);
Linus Torvalds1da177e2005-04-16 15:20:36 -070018 int (*d_delete)(struct dentry *);
19 void (*d_release)(struct dentry *);
20 void (*d_iput)(struct dentry *, struct inode *);
Eric Dumazetc23fbb62007-05-08 00:26:18 -070021 char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
David Howells9875cf82011-01-14 18:45:21 +000022 struct vfsmount *(*d_automount)(struct path *path);
David Howellscc53ce52011-01-14 18:45:26 +000023 int (*d_manage)(struct dentry *, bool);
Linus Torvalds1da177e2005-04-16 15:20:36 -070024
25locking rules:
Nick Piggin34286d62011-01-07 17:49:57 +110026 rename_lock ->d_lock may block rcu-walk
27d_revalidate: no no yes (ref-walk) maybe
28d_hash no no no maybe
29d_compare: yes no no maybe
30d_delete: no yes no no
31d_release: no no yes no
32d_iput: no no yes no
33d_dname: no no no no
David Howells9875cf82011-01-14 18:45:21 +000034d_automount: no no yes no
David Howellscc53ce52011-01-14 18:45:26 +000035d_manage: no no yes no
Linus Torvalds1da177e2005-04-16 15:20:36 -070036
37--------------------------- inode_operations ---------------------------
38prototypes:
39 int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
40 struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid
41ata *);
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 *);
45 int (*mkdir) (struct inode *,struct dentry *,int);
46 int (*rmdir) (struct inode *,struct dentry *);
47 int (*mknod) (struct inode *,struct dentry *,int,dev_t);
48 int (*rename) (struct inode *, struct dentry *,
49 struct inode *, struct dentry *);
50 int (*readlink) (struct dentry *, char __user *,int);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010051 void * (*follow_link) (struct dentry *, struct nameidata *);
52 void (*put_link) (struct dentry *, struct nameidata *, void *);
Linus Torvalds1da177e2005-04-16 15:20:36 -070053 void (*truncate) (struct inode *);
Nick Pigginb74c79e2011-01-07 17:49:58 +110054 int (*permission) (struct inode *, int, unsigned int);
55 int (*check_acl)(struct inode *, int, unsigned int);
Linus Torvalds1da177e2005-04-16 15:20:36 -070056 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 *);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010062 void (*truncate_range)(struct inode *, loff_t, loff_t);
63 long (*fallocate)(struct inode *inode, int mode, loff_t offset, loff_t len);
64 int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
Linus Torvalds1da177e2005-04-16 15:20:36 -070065
66locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010067 all may block
Artem Bityutskiya7bc02f2007-05-09 07:53:16 +020068 i_mutex(inode)
Linus Torvalds1da177e2005-04-16 15:20:36 -070069lookup: yes
70create: yes
71link: yes (both)
72mknod: yes
73symlink: yes
74mkdir: yes
75unlink: yes (both)
76rmdir: yes (both) (see below)
77rename: yes (all) (see below)
78readlink: no
79follow_link: no
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010080put_link: no
Linus Torvalds1da177e2005-04-16 15:20:36 -070081truncate: yes (see below)
82setattr: yes
Nick Pigginb74c79e2011-01-07 17:49:58 +110083permission: no (may not block if called in rcu-walk mode)
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010084check_acl: no
Linus Torvalds1da177e2005-04-16 15:20:36 -070085getattr: no
86setxattr: yes
87getxattr: no
88listxattr: no
89removexattr: yes
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010090truncate_range: yes
91fallocate: no
92fiemap: no
Artem Bityutskiya7bc02f2007-05-09 07:53:16 +020093 Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
Linus Torvalds1da177e2005-04-16 15:20:36 -070094victim.
95 cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
96 ->truncate() is never called directly - it's a callback, not a
Christoph Hellwigb83be6f2010-12-16 12:04:54 +010097method. It's called by vmtruncate() - deprecated library function used by
Linus Torvalds1da177e2005-04-16 15:20:36 -070098->setattr(). Locking information above applies to that call (i.e. is
99inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
100passed).
101
102See Documentation/filesystems/directory-locking for more detailed discussion
103of the locking scheme for directory operations.
104
105--------------------------- super_operations ---------------------------
106prototypes:
107 struct inode *(*alloc_inode)(struct super_block *sb);
108 void (*destroy_inode)(struct inode *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700109 void (*dirty_inode) (struct inode *);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100110 int (*write_inode) (struct inode *, struct writeback_control *wbc);
Al Viro336fb3b2010-06-08 00:37:12 -0400111 int (*drop_inode) (struct inode *);
112 void (*evict_inode) (struct inode *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700113 void (*put_super) (struct super_block *);
114 void (*write_super) (struct super_block *);
115 int (*sync_fs)(struct super_block *sb, int wait);
Takashi Satoc4be0c12009-01-09 16:40:58 -0800116 int (*freeze_fs) (struct super_block *);
117 int (*unfreeze_fs) (struct super_block *);
David Howells726c3342006-06-23 02:02:58 -0700118 int (*statfs) (struct dentry *, struct kstatfs *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700119 int (*remount_fs) (struct super_block *, int *, char *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700120 void (*umount_begin) (struct super_block *);
121 int (*show_options)(struct seq_file *, struct vfsmount *);
122 ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
123 ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100124 int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700125
126locking rules:
Al Viro336fb3b2010-06-08 00:37:12 -0400127 All may block [not true, see below]
Christoph Hellwig7e325d32009-06-19 20:22:37 +0200128 s_umount
129alloc_inode:
130destroy_inode:
131dirty_inode: (must not sleep)
132write_inode:
133drop_inode: !!!inode_lock!!!
Al Viro336fb3b2010-06-08 00:37:12 -0400134evict_inode:
Christoph Hellwig7e325d32009-06-19 20:22:37 +0200135put_super: write
136write_super: read
137sync_fs: read
138freeze_fs: read
139unfreeze_fs: read
Al Viro336fb3b2010-06-08 00:37:12 -0400140statfs: maybe(read) (see below)
141remount_fs: write
Christoph Hellwig7e325d32009-06-19 20:22:37 +0200142umount_begin: no
143show_options: no (namespace_sem)
144quota_read: no (see below)
145quota_write: no (see below)
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100146bdev_try_to_free_page: no (see below)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700147
Al Viro336fb3b2010-06-08 00:37:12 -0400148->statfs() has s_umount (shared) when called by ustat(2) (native or
149compat), but that's an accident of bad API; s_umount is used to pin
150the superblock down when we only have dev_t given us by userland to
151identify the superblock. Everything else (statfs(), fstatfs(), etc.)
152doesn't hold it when calling ->statfs() - superblock is pinned down
153by resolving the pathname passed to syscall.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700154->quota_read() and ->quota_write() functions are both guaranteed to
155be the only ones operating on the quota file by the quota code (via
156dqio_sem) (unless an admin really wants to screw up something and
157writes to quota files with quotas on). For other details about locking
158see also dquot_operations section.
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100159->bdev_try_to_free_page is called from the ->releasepage handler of
160the block device inode. See there for more details.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700161
162--------------------------- file_system_type ---------------------------
163prototypes:
Jonathan Corbet5d8b2eb2006-07-10 04:44:07 -0700164 int (*get_sb) (struct file_system_type *, int,
165 const char *, void *, struct vfsmount *);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100166 struct dentry *(*mount) (struct file_system_type *, int,
167 const char *, void *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700168 void (*kill_sb) (struct super_block *);
169locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100170 may block
171get_sb yes
172mount yes
173kill_sb yes
Linus Torvalds1da177e2005-04-16 15:20:36 -0700174
David Howells454e2392006-06-23 02:02:57 -0700175->get_sb() returns error or 0 with locked superblock attached to the vfsmount
176(exclusive on ->s_umount).
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100177->mount() returns ERR_PTR or the root dentry.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700178->kill_sb() takes a write-locked superblock, does all shutdown work on it,
179unlocks and drops the reference.
180
181--------------------------- address_space_operations --------------------------
182prototypes:
183 int (*writepage)(struct page *page, struct writeback_control *wbc);
184 int (*readpage)(struct file *, struct page *);
185 int (*sync_page)(struct page *);
186 int (*writepages)(struct address_space *, struct writeback_control *);
187 int (*set_page_dirty)(struct page *page);
188 int (*readpages)(struct file *filp, struct address_space *mapping,
189 struct list_head *pages, unsigned nr_pages);
Nick Piggin4e02ed42008-10-29 14:00:55 -0700190 int (*write_begin)(struct file *, struct address_space *mapping,
191 loff_t pos, unsigned len, unsigned flags,
192 struct page **pagep, void **fsdata);
193 int (*write_end)(struct file *, struct address_space *mapping,
194 loff_t pos, unsigned len, unsigned copied,
195 struct page *page, void *fsdata);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700196 sector_t (*bmap)(struct address_space *, sector_t);
197 int (*invalidatepage) (struct page *, unsigned long);
198 int (*releasepage) (struct page *, int);
Linus Torvalds6072d132010-12-01 13:35:19 -0500199 void (*freepage)(struct page *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700200 int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
201 loff_t offset, unsigned long nr_segs);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100202 int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
203 unsigned long *);
204 int (*migratepage)(struct address_space *, struct page *, struct page *);
205 int (*launder_page)(struct page *);
206 int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
207 int (*error_remove_page)(struct address_space *, struct page *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700208
209locking rules:
Linus Torvalds6072d132010-12-01 13:35:19 -0500210 All except set_page_dirty and freepage may block
Linus Torvalds1da177e2005-04-16 15:20:36 -0700211
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100212 PageLocked(page) i_mutex
213writepage: yes, unlocks (see below)
214readpage: yes, unlocks
215sync_page: maybe
216writepages:
217set_page_dirty no
218readpages:
219write_begin: locks the page yes
220write_end: yes, unlocks yes
221bmap:
222invalidatepage: yes
223releasepage: yes
224freepage: yes
225direct_IO:
226get_xip_mem: maybe
227migratepage: yes (both)
228launder_page: yes
229is_partially_uptodate: yes
230error_remove_page: yes
Linus Torvalds1da177e2005-04-16 15:20:36 -0700231
Nick Piggin4e02ed42008-10-29 14:00:55 -0700232 ->write_begin(), ->write_end(), ->sync_page() and ->readpage()
Linus Torvalds1da177e2005-04-16 15:20:36 -0700233may be called from the request handler (/dev/loop).
234
235 ->readpage() unlocks the page, either synchronously or via I/O
236completion.
237
238 ->readpages() populates the pagecache with the passed pages and starts
239I/O against them. They come unlocked upon I/O completion.
240
241 ->writepage() is used for two purposes: for "memory cleansing" and for
242"sync". These are quite different operations and the behaviour may differ
243depending upon the mode.
244
245If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
246it *must* start I/O against the page, even if that would involve
247blocking on in-progress I/O.
248
249If writepage is called for memory cleansing (sync_mode ==
250WBC_SYNC_NONE) then its role is to get as much writeout underway as
251possible. So writepage should try to avoid blocking against
252currently-in-progress I/O.
253
254If the filesystem is not called for "sync" and it determines that it
255would need to block against in-progress I/O to be able to start new I/O
256against the page the filesystem should redirty the page with
257redirty_page_for_writepage(), then unlock the page and return zero.
258This may also be done to avoid internal deadlocks, but rarely.
259
Robert P. J. Day3a4fa0a2007-10-19 23:10:43 +0200260If the filesystem is called for sync then it must wait on any
Linus Torvalds1da177e2005-04-16 15:20:36 -0700261in-progress I/O and then start new I/O.
262
Nikita Danilov20546062005-05-01 08:58:37 -0700263The filesystem should unlock the page synchronously, before returning to the
264caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
265value. WRITEPAGE_ACTIVATE means that page cannot really be written out
266currently, and VM should stop calling ->writepage() on this page for some
267time. VM does this by moving page to the head of the active list, hence the
268name.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700269
270Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
271and return zero, writepage *must* run set_page_writeback() against the page,
272followed by unlocking it. Once set_page_writeback() has been run against the
273page, write I/O can be submitted and the write I/O completion handler must run
274end_page_writeback() once the I/O is complete. If no I/O is submitted, the
275filesystem must run end_page_writeback() against the page before returning from
276writepage.
277
278That is: after 2.5.12, pages which are under writeout are *not* locked. Note,
279if the filesystem needs the page to be locked during writeout, that is ok, too,
280the page is allowed to be unlocked at any point in time between the calls to
281set_page_writeback() and end_page_writeback().
282
283Note, failure to run either redirty_page_for_writepage() or the combination of
284set_page_writeback()/end_page_writeback() on a page submitted to writepage
285will leave the page itself marked clean but it will be tagged as dirty in the
286radix tree. This incoherency can lead to all sorts of hard-to-debug problems
287in the filesystem like having dirty inodes at umount and losing written data.
288
289 ->sync_page() locking rules are not well-defined - usually it is called
290with lock on page, but that is not guaranteed. Considering the currently
291existing instances of this method ->sync_page() itself doesn't look
292well-defined...
293
294 ->writepages() is used for periodic writeback and for syscall-initiated
295sync operations. The address_space should start I/O against at least
296*nr_to_write pages. *nr_to_write must be decremented for each page which is
297written. The address_space implementation may write more (or less) pages
298than *nr_to_write asks for, but it should try to be reasonably close. If
299nr_to_write is NULL, all dirty pages must be written.
300
301writepages should _only_ write pages which are present on
302mapping->io_pages.
303
304 ->set_page_dirty() is called from various places in the kernel
305when the target page is marked as needing writeback. It may be called
306under spinlock (it cannot block) and is sometimes called with the page
307not locked.
308
309 ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100310filesystems and by the swapper. The latter will eventually go away. Please,
311keep it that way and don't breed new callers.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700312
313 ->invalidatepage() is called when the filesystem must attempt to drop
314some or all of the buffers from the page when it is being truncated. It
315returns zero on success. If ->invalidatepage is zero, the kernel uses
316block_invalidatepage() instead.
317
318 ->releasepage() is called when the kernel is about to try to drop the
319buffers from the page in preparation for freeing it. It returns zero to
320indicate that the buffers are (or may be) freeable. If ->releasepage is zero,
321the kernel assumes that the fs has no private interest in the buffers.
322
Linus Torvalds6072d132010-12-01 13:35:19 -0500323 ->freepage() is called when the kernel is done dropping the page
324from the page cache.
325
Trond Myklebuste3db7692007-01-10 23:15:39 -0800326 ->launder_page() may be called prior to releasing a page if
327it is still found to be dirty. It returns zero if the page was successfully
328cleaned, or an error value if not. Note that in order to prevent the page
329getting mapped back in and redirtied, it needs to be kept locked
330across the entire operation.
331
Linus Torvalds1da177e2005-04-16 15:20:36 -0700332----------------------- file_lock_operations ------------------------------
333prototypes:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700334 void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
335 void (*fl_release_private)(struct file_lock *);
336
337
338locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100339 file_lock_lock may block
340fl_copy_lock: yes no
341fl_release_private: maybe no
Linus Torvalds1da177e2005-04-16 15:20:36 -0700342
343----------------------- lock_manager_operations ---------------------------
344prototypes:
345 int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
346 void (*fl_notify)(struct file_lock *); /* unblock callback */
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100347 int (*fl_grant)(struct file_lock *, struct file_lock *, int);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700348 void (*fl_release_private)(struct file_lock *);
349 void (*fl_break)(struct file_lock *); /* break_lease callback */
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100350 int (*fl_mylease)(struct file_lock *, struct file_lock *);
351 int (*fl_change)(struct file_lock **, int);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700352
353locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100354 file_lock_lock may block
355fl_compare_owner: yes no
356fl_notify: yes no
357fl_grant: no no
358fl_release_private: maybe no
359fl_break: yes no
360fl_mylease: yes no
361fl_change yes no
Linus Torvalds1da177e2005-04-16 15:20:36 -0700362
Linus Torvalds1da177e2005-04-16 15:20:36 -0700363--------------------------- buffer_head -----------------------------------
364prototypes:
365 void (*b_end_io)(struct buffer_head *bh, int uptodate);
366
367locking rules:
368 called from interrupts. In other words, extreme care is needed here.
369bh is locked, but that's all warranties we have here. Currently only RAID1,
370highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
371call this method upon the IO completion.
372
373--------------------------- block_device_operations -----------------------
374prototypes:
Christoph Hellwige1455d12010-10-06 10:46:53 +0200375 int (*open) (struct block_device *, fmode_t);
376 int (*release) (struct gendisk *, fmode_t);
377 int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
378 int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
379 int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700380 int (*media_changed) (struct gendisk *);
Christoph Hellwige1455d12010-10-06 10:46:53 +0200381 void (*unlock_native_capacity) (struct gendisk *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700382 int (*revalidate_disk) (struct gendisk *);
Christoph Hellwige1455d12010-10-06 10:46:53 +0200383 int (*getgeo)(struct block_device *, struct hd_geometry *);
384 void (*swap_slot_free_notify) (struct block_device *, unsigned long);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700385
386locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100387 bd_mutex
388open: yes
389release: yes
390ioctl: no
391compat_ioctl: no
392direct_access: no
393media_changed: no
394unlock_native_capacity: no
395revalidate_disk: no
396getgeo: no
397swap_slot_free_notify: no (see below)
Linus Torvalds1da177e2005-04-16 15:20:36 -0700398
Christoph Hellwige1455d12010-10-06 10:46:53 +0200399media_changed, unlock_native_capacity and revalidate_disk are called only from
400check_disk_change().
401
402swap_slot_free_notify is called with swap_lock and sometimes the page lock
403held.
404
Linus Torvalds1da177e2005-04-16 15:20:36 -0700405
406--------------------------- file_operations -------------------------------
407prototypes:
408 loff_t (*llseek) (struct file *, loff_t, int);
409 ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700410 ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
Badari Pulavarty027445c2006-09-30 23:28:46 -0700411 ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
412 ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700413 int (*readdir) (struct file *, void *, filldir_t);
414 unsigned int (*poll) (struct file *, struct poll_table_struct *);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700415 long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
416 long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
417 int (*mmap) (struct file *, struct vm_area_struct *);
418 int (*open) (struct inode *, struct file *);
419 int (*flush) (struct file *);
420 int (*release) (struct inode *, struct file *);
Christoph Hellwig7ea80852010-05-26 17:53:25 +0200421 int (*fsync) (struct file *, int datasync);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700422 int (*aio_fsync) (struct kiocb *, int datasync);
423 int (*fasync) (int, struct file *, int);
424 int (*lock) (struct file *, int, struct file_lock *);
425 ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
426 loff_t *);
427 ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
428 loff_t *);
429 ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
430 void __user *);
431 ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
432 loff_t *, int);
433 unsigned long (*get_unmapped_area)(struct file *, unsigned long,
434 unsigned long, unsigned long, unsigned long);
435 int (*check_flags)(int);
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100436 int (*flock) (struct file *, int, struct file_lock *);
437 ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
438 size_t, unsigned int);
439 ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
440 size_t, unsigned int);
441 int (*setlease)(struct file *, long, struct file_lock **);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700442};
443
444locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100445 All may block except for ->setlease.
446 No VFS locks held on entry except for ->fsync and ->setlease.
447
448->fsync() has i_mutex on inode.
449
450->setlease has the file_list_lock held and must not sleep.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700451
452->llseek() locking has moved from llseek to the individual llseek
453implementations. If your fs is not using generic_file_llseek, you
454need to acquire and release the appropriate locks in your ->llseek().
455For many filesystems, it is probably safe to acquire the inode
Jan Blunck866707f2010-05-26 14:44:54 -0700456mutex or just to use i_size_read() instead.
457Note: this does not protect the file->f_pos against concurrent modifications
458since this is something the userspace has to take care about.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700459
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100460->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
461Most instances call fasync_helper(), which does that maintenance, so it's
462not normally something one needs to worry about. Return values > 0 will be
463mapped to zero in the VFS layer.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700464
465->readdir() and ->ioctl() on directories must be changed. Ideally we would
466move ->readdir() to inode_operations and use a separate method for directory
467->ioctl() or kill the latter completely. One of the problems is that for
468anything that resembles union-mount we won't have a struct file for all
469components. And there are other reasons why the current interface is a mess...
470
Linus Torvalds1da177e2005-04-16 15:20:36 -0700471->read on directories probably must go away - we should just enforce -EISDIR
472in sys_read() and friends.
473
Linus Torvalds1da177e2005-04-16 15:20:36 -0700474--------------------------- dquot_operations -------------------------------
475prototypes:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700476 int (*write_dquot) (struct dquot *);
477 int (*acquire_dquot) (struct dquot *);
478 int (*release_dquot) (struct dquot *);
479 int (*mark_dirty) (struct dquot *);
480 int (*write_info) (struct super_block *, int);
481
482These operations are intended to be more or less wrapping functions that ensure
483a proper locking wrt the filesystem and call the generic quota operations.
484
485What filesystem should expect from the generic quota functions:
486
487 FS recursion Held locks when called
Linus Torvalds1da177e2005-04-16 15:20:36 -0700488write_dquot: yes dqonoff_sem or dqptr_sem
489acquire_dquot: yes dqonoff_sem or dqptr_sem
490release_dquot: yes dqonoff_sem or dqptr_sem
491mark_dirty: no -
492write_info: yes dqonoff_sem
493
494FS recursion means calling ->quota_read() and ->quota_write() from superblock
495operations.
496
Linus Torvalds1da177e2005-04-16 15:20:36 -0700497More details about quota locking can be found in fs/dquot.c.
498
499--------------------------- vm_operations_struct -----------------------------
500prototypes:
501 void (*open)(struct vm_area_struct*);
502 void (*close)(struct vm_area_struct*);
Nick Piggind0217ac2007-07-19 01:47:03 -0700503 int (*fault)(struct vm_area_struct*, struct vm_fault *);
Nick Pigginc2ec1752009-03-31 15:23:21 -0700504 int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
Rik van Riel28b2ee22008-07-23 21:27:05 -0700505 int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700506
507locking rules:
Christoph Hellwigb83be6f2010-12-16 12:04:54 +0100508 mmap_sem PageLocked(page)
509open: yes
510close: yes
511fault: yes can return with page locked
512page_mkwrite: yes can return with page locked
513access: yes
Mark Fashehed2f2f92007-07-19 01:47:01 -0700514
Nick Pigginb827e492009-04-30 15:08:16 -0700515 ->fault() is called when a previously not present pte is about
516to be faulted in. The filesystem must find and return the page associated
517with the passed in "pgoff" in the vm_fault structure. If it is possible that
518the page may be truncated and/or invalidated, then the filesystem must lock
519the page, then ensure it is not already truncated (the page lock will block
520subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
521locked. The VM will unlock the page.
522
523 ->page_mkwrite() is called when a previously read-only pte is
524about to become writeable. The filesystem again must ensure that there are
525no truncate/invalidate races, and then return with the page locked. If
526the page has been truncated, the filesystem should not look up a new page
527like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
528will cause the VM to retry the fault.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700529
Rik van Riel28b2ee22008-07-23 21:27:05 -0700530 ->access() is called when get_user_pages() fails in
531acces_process_vm(), typically used to debug a process through
532/proc/pid/mem or ptrace. This function is needed only for
533VM_IO | VM_PFNMAP VMAs.
534
Linus Torvalds1da177e2005-04-16 15:20:36 -0700535================================================================================
536 Dubious stuff
537
538(if you break something or notice that it is broken and do not fix it yourself
539- at least put it here)