Locking 23.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11
	The text below describes the locking rules for VFS-related methods.
It is (believed to be) up-to-date. *Please*, if you change anything in
prototypes or locking protocols - update this file. And update the relevant
instances in the tree, don't leave that to maintainers of filesystems/devices/
etc. At the very least, put the list of dubious cases in the end of this file.
Don't turn it into log - maintainers of out-of-the-tree code are supposed to
be able to use diff(1).
	Thing currently missing here: socket operations. Alexey?

--------------------------- dentry_operations --------------------------
prototypes:
12
	int (*d_revalidate)(struct dentry *, unsigned int);
13
	int (*d_weak_revalidate)(struct dentry *, unsigned int);
14 15
	int (*d_hash)(const struct dentry *, struct qstr *);
	int (*d_compare)(const struct dentry *, const struct dentry *,
N
Nick Piggin 已提交
16
			unsigned int, const char *, const struct qstr *);
L
Linus Torvalds 已提交
17 18 19
	int (*d_delete)(struct dentry *);
	void (*d_release)(struct dentry *);
	void (*d_iput)(struct dentry *, struct inode *);
20
	char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
21
	struct vfsmount *(*d_automount)(struct path *path);
22
	int (*d_manage)(struct dentry *, bool);
L
Linus Torvalds 已提交
23 24

locking rules:
25 26
		rename_lock	->d_lock	may block	rcu-walk
d_revalidate:	no		no		yes (ref-walk)	maybe
27
d_weak_revalidate:no		no		yes	 	no
28 29 30 31
d_hash		no		no		no		maybe
d_compare:	yes		no		no		maybe
d_delete:	no		yes		no		no
d_release:	no		no		yes		no
S
Sage Weil 已提交
32
d_prune:        no              yes             no              no
33 34
d_iput:		no		no		yes		no
d_dname:	no		no		no		no
35
d_automount:	no		no		yes		no
36
d_manage:	no		no		yes (ref-walk)	maybe
L
Linus Torvalds 已提交
37 38 39

--------------------------- inode_operations --------------------------- 
prototypes:
A
Al Viro 已提交
40
	int (*create) (struct inode *,struct dentry *,umode_t, bool);
A
Al Viro 已提交
41
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
L
Linus Torvalds 已提交
42 43 44
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
45
	int (*mkdir) (struct inode *,struct dentry *,umode_t);
L
Linus Torvalds 已提交
46
	int (*rmdir) (struct inode *,struct dentry *);
A
Al Viro 已提交
47
	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
L
Linus Torvalds 已提交
48 49
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
M
Miklos Szeredi 已提交
50 51
	int (*rename2) (struct inode *, struct dentry *,
			struct inode *, struct dentry *, unsigned int);
L
Linus Torvalds 已提交
52
	int (*readlink) (struct dentry *, char __user *,int);
53 54
	void * (*follow_link) (struct dentry *, struct nameidata *);
	void (*put_link) (struct dentry *, struct nameidata *, void *);
L
Linus Torvalds 已提交
55
	void (*truncate) (struct inode *);
56
	int (*permission) (struct inode *, int, unsigned int);
57
	int (*get_acl)(struct inode *, int);
L
Linus Torvalds 已提交
58 59 60 61 62 63
	int (*setattr) (struct dentry *, struct iattr *);
	int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*removexattr) (struct dentry *, const char *);
64
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
65
	void (*update_time)(struct inode *, struct timespec *, int);
A
Al Viro 已提交
66
	int (*atomic_open)(struct inode *, struct dentry *,
A
Al Viro 已提交
67
				struct file *, unsigned open_flag,
68
				umode_t create_mode, int *opened);
A
Al Viro 已提交
69
	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
L
Linus Torvalds 已提交
70 71

locking rules:
72
	all may block
A
Artem Bityutskiy 已提交
73
		i_mutex(inode)
L
Linus Torvalds 已提交
74 75 76 77 78 79 80 81 82
lookup:		yes
create:		yes
link:		yes (both)
mknod:		yes
symlink:	yes
mkdir:		yes
unlink:		yes (both)
rmdir:		yes (both)	(see below)
rename:		yes (all)	(see below)
M
Miklos Szeredi 已提交
83
rename2:	yes (all)	(see below)
L
Linus Torvalds 已提交
84 85
readlink:	no
follow_link:	no
86
put_link:	no
L
Linus Torvalds 已提交
87
setattr:	yes
88
permission:	no (may not block if called in rcu-walk mode)
89
get_acl:	no
L
Linus Torvalds 已提交
90 91 92 93 94
getattr:	no
setxattr:	yes
getxattr:	no
listxattr:	no
removexattr:	yes
95
fiemap:		no
96
update_time:	no
M
Miklos Szeredi 已提交
97
atomic_open:	yes
A
Al Viro 已提交
98
tmpfile:	no
99

A
Artem Bityutskiy 已提交
100
	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
L
Linus Torvalds 已提交
101
victim.
M
Miklos Szeredi 已提交
102 103
	cross-directory ->rename() and rename2() has (per-superblock)
->s_vfs_rename_sem.
L
Linus Torvalds 已提交
104 105 106 107 108 109 110 111

See Documentation/filesystems/directory-locking for more detailed discussion
of the locking scheme for directory operations.

--------------------------- super_operations ---------------------------
prototypes:
	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);
112
	void (*dirty_inode) (struct inode *, int flags);
113
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
114 115
	int (*drop_inode) (struct inode *);
	void (*evict_inode) (struct inode *);
L
Linus Torvalds 已提交
116 117
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
118 119
	int (*freeze_fs) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
120
	int (*statfs) (struct dentry *, struct kstatfs *);
L
Linus Torvalds 已提交
121 122
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*umount_begin) (struct super_block *);
123
	int (*show_options)(struct seq_file *, struct dentry *);
L
Linus Torvalds 已提交
124 125
	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
126
	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
L
Linus Torvalds 已提交
127 128

locking rules:
129
	All may block [not true, see below]
130 131 132
			s_umount
alloc_inode:
destroy_inode:
133
dirty_inode:
134
write_inode:
135
drop_inode:				!!!inode->i_lock!!!
136
evict_inode:
137 138
put_super:		write
sync_fs:		read
139 140
freeze_fs:		write
unfreeze_fs:		write
141 142
statfs:			maybe(read)	(see below)
remount_fs:		write
143 144 145 146
umount_begin:		no
show_options:		no		(namespace_sem)
quota_read:		no		(see below)
quota_write:		no		(see below)
147
bdev_try_to_free_page:	no		(see below)
L
Linus Torvalds 已提交
148

149 150 151 152 153 154
->statfs() has s_umount (shared) when called by ustat(2) (native or
compat), but that's an accident of bad API; s_umount is used to pin
the superblock down when we only have dev_t given us by userland to
identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
doesn't hold it when calling ->statfs() - superblock is pinned down
by resolving the pathname passed to syscall.
L
Linus Torvalds 已提交
155 156 157 158 159
->quota_read() and ->quota_write() functions are both guaranteed to
be the only ones operating on the quota file by the quota code (via
dqio_sem) (unless an admin really wants to screw up something and
writes to quota files with quotas on). For other details about locking
see also dquot_operations section.
160 161
->bdev_try_to_free_page is called from the ->releasepage handler of
the block device inode.  See there for more details.
L
Linus Torvalds 已提交
162 163 164

--------------------------- file_system_type ---------------------------
prototypes:
165 166
	int (*get_sb) (struct file_system_type *, int,
		       const char *, void *, struct vfsmount *);
167 168
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
L
Linus Torvalds 已提交
169 170
	void (*kill_sb) (struct super_block *);
locking rules:
171 172 173
		may block
mount		yes
kill_sb		yes
L
Linus Torvalds 已提交
174

A
Al Viro 已提交
175 176
->mount() returns ERR_PTR or the root dentry; its superblock should be locked
on return.
L
Linus Torvalds 已提交
177 178 179 180 181 182 183 184 185 186 187 188
->kill_sb() takes a write-locked superblock, does all shutdown work on it,
unlocks and drops the reference.

--------------------------- address_space_operations --------------------------
prototypes:
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);
	int (*sync_page)(struct page *);
	int (*writepages)(struct address_space *, struct writeback_control *);
	int (*set_page_dirty)(struct page *page);
	int (*readpages)(struct file *filp, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages);
189 190 191 192 193 194
	int (*write_begin)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned flags,
				struct page **pagep, void **fsdata);
	int (*write_end)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);
L
Linus Torvalds 已提交
195
	sector_t (*bmap)(struct address_space *, sector_t);
196
	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
L
Linus Torvalds 已提交
197
	int (*releasepage) (struct page *, int);
198
	void (*freepage)(struct page *);
A
Al Viro 已提交
199
	int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
200 201 202 203
	int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
				unsigned long *);
	int (*migratepage)(struct address_space *, struct page *, struct page *);
	int (*launder_page)(struct page *);
204
	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
205
	int (*error_remove_page)(struct address_space *, struct page *);
206 207
	int (*swap_activate)(struct file *);
	int (*swap_deactivate)(struct file *);
L
Linus Torvalds 已提交
208 209

locking rules:
210
	All except set_page_dirty and freepage may block
L
Linus Torvalds 已提交
211

212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
			PageLocked(page)	i_mutex
writepage:		yes, unlocks (see below)
readpage:		yes, unlocks
sync_page:		maybe
writepages:
set_page_dirty		no
readpages:
write_begin:		locks the page		yes
write_end:		yes, unlocks		yes
bmap:
invalidatepage:		yes
releasepage:		yes
freepage:		yes
direct_IO:
get_xip_mem:					maybe
migratepage:		yes (both)
launder_page:		yes
is_partially_uptodate:	yes
error_remove_page:	yes
231 232
swap_activate:		no
swap_deactivate:	no
L
Linus Torvalds 已提交
233

234
	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261
may be called from the request handler (/dev/loop).

	->readpage() unlocks the page, either synchronously or via I/O
completion.

	->readpages() populates the pagecache with the passed pages and starts
I/O against them.  They come unlocked upon I/O completion.

	->writepage() is used for two purposes: for "memory cleansing" and for
"sync".  These are quite different operations and the behaviour may differ
depending upon the mode.

If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
it *must* start I/O against the page, even if that would involve
blocking on in-progress I/O.

If writepage is called for memory cleansing (sync_mode ==
WBC_SYNC_NONE) then its role is to get as much writeout underway as
possible.  So writepage should try to avoid blocking against
currently-in-progress I/O.

If the filesystem is not called for "sync" and it determines that it
would need to block against in-progress I/O to be able to start new I/O
against the page the filesystem should redirty the page with
redirty_page_for_writepage(), then unlock the page and return zero.
This may also be done to avoid internal deadlocks, but rarely.

262
If the filesystem is called for sync then it must wait on any
L
Linus Torvalds 已提交
263 264
in-progress I/O and then start new I/O.

N
Nikita Danilov 已提交
265 266 267 268 269 270
The filesystem should unlock the page synchronously, before returning to the
caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
value. WRITEPAGE_ACTIVATE means that page cannot really be written out
currently, and VM should stop calling ->writepage() on this page for some
time. VM does this by moving page to the head of the active list, hence the
name.
L
Linus Torvalds 已提交
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311

Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
and return zero, writepage *must* run set_page_writeback() against the page,
followed by unlocking it.  Once set_page_writeback() has been run against the
page, write I/O can be submitted and the write I/O completion handler must run
end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
filesystem must run end_page_writeback() against the page before returning from
writepage.

That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
if the filesystem needs the page to be locked during writeout, that is ok, too,
the page is allowed to be unlocked at any point in time between the calls to
set_page_writeback() and end_page_writeback().

Note, failure to run either redirty_page_for_writepage() or the combination of
set_page_writeback()/end_page_writeback() on a page submitted to writepage
will leave the page itself marked clean but it will be tagged as dirty in the
radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
in the filesystem like having dirty inodes at umount and losing written data.

	->sync_page() locking rules are not well-defined - usually it is called
with lock on page, but that is not guaranteed. Considering the currently
existing instances of this method ->sync_page() itself doesn't look
well-defined...

	->writepages() is used for periodic writeback and for syscall-initiated
sync operations.  The address_space should start I/O against at least
*nr_to_write pages.  *nr_to_write must be decremented for each page which is
written.  The address_space implementation may write more (or less) pages
than *nr_to_write asks for, but it should try to be reasonably close.  If
nr_to_write is NULL, all dirty pages must be written.

writepages should _only_ write pages which are present on
mapping->io_pages.

	->set_page_dirty() is called from various places in the kernel
when the target page is marked as needing writeback.  It may be called
under spinlock (it cannot block) and is sometimes called with the page
not locked.

	->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
312 313
filesystems and by the swapper. The latter will eventually go away.  Please,
keep it that way and don't breed new callers.
L
Linus Torvalds 已提交
314 315

	->invalidatepage() is called when the filesystem must attempt to drop
316 317
some or all of the buffers from the page when it is being truncated. It
returns zero on success. If ->invalidatepage is zero, the kernel uses
L
Linus Torvalds 已提交
318 319 320 321 322 323 324
block_invalidatepage() instead.

	->releasepage() is called when the kernel is about to try to drop the
buffers from the page in preparation for freeing it.  It returns zero to
indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
the kernel assumes that the fs has no private interest in the buffers.

325 326 327
	->freepage() is called when the kernel is done dropping the page
from the page cache.

328 329 330 331 332 333
	->launder_page() may be called prior to releasing a page if
it is still found to be dirty. It returns zero if the page was successfully
cleaned, or an error value if not. Note that in order to prevent the page
getting mapped back in and redirtied, it needs to be kept locked
across the entire operation.

334 335 336 337 338 339 340 341 342
	->swap_activate will be called with a non-zero argument on
files backing (non block device backed) swapfiles. A return value
of zero indicates success, in which case this file can be used for
backing swapspace. The swapspace operations will be proxied to the
address space operations.

	->swap_deactivate() will be called in the sys_swapoff()
path after ->swap_activate() returned success.

L
Linus Torvalds 已提交
343 344 345 346 347 348 349
----------------------- file_lock_operations ------------------------------
prototypes:
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);


locking rules:
350
			inode->i_lock	may block
351 352
fl_copy_lock:		yes		no
fl_release_private:	maybe		no
L
Linus Torvalds 已提交
353 354 355

----------------------- lock_manager_operations ---------------------------
prototypes:
J
J. Bruce Fields 已提交
356
	int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
357
	unsigned long (*lm_owner_key)(struct file_lock *);
J
J. Bruce Fields 已提交
358 359 360 361
	void (*lm_notify)(struct file_lock *);  /* unblock callback */
	int (*lm_grant)(struct file_lock *, struct file_lock *, int);
	void (*lm_break)(struct file_lock *); /* break_lease callback */
	int (*lm_change)(struct file_lock **, int);
L
Linus Torvalds 已提交
362 363

locking rules:
364

365 366 367 368 369 370 371
			inode->i_lock	blocked_lock_lock	may block
lm_compare_owner:	yes[1]		maybe			no
lm_owner_key		yes[1]		yes			no
lm_notify:		yes		yes			no
lm_grant:		no		no			no
lm_break:		yes		no			no
lm_change		yes		no			no
372

373 374 375 376 377
[1]:	->lm_compare_owner and ->lm_owner_key are generally called with
*an* inode->i_lock held. It may not be the i_lock of the inode
associated with either file_lock argument! This is the case with deadlock
detection, since the code has to chase down the owners of locks that may
be entirely unrelated to the one on which the lock is being acquired.
378
For deadlock detection however, the blocked_lock_lock is also held. The
379 380 381
fact that these locks are held ensures that the file_locks do not
disappear out from under you while doing the comparison or generating an
owner key.
382

L
Linus Torvalds 已提交
383 384 385 386 387 388 389 390 391 392 393 394
--------------------------- buffer_head -----------------------------------
prototypes:
	void (*b_end_io)(struct buffer_head *bh, int uptodate);

locking rules:
	called from interrupts. In other words, extreme care is needed here.
bh is locked, but that's all warranties we have here. Currently only RAID1,
highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
call this method upon the IO completion.

--------------------------- block_device_operations -----------------------
prototypes:
395 396 397 398 399
	int (*open) (struct block_device *, fmode_t);
	int (*release) (struct gendisk *, fmode_t);
	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
	int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
L
Linus Torvalds 已提交
400
	int (*media_changed) (struct gendisk *);
401
	void (*unlock_native_capacity) (struct gendisk *);
L
Linus Torvalds 已提交
402
	int (*revalidate_disk) (struct gendisk *);
403 404
	int (*getgeo)(struct block_device *, struct hd_geometry *);
	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
L
Linus Torvalds 已提交
405 406

locking rules:
407 408 409 410 411 412 413 414 415 416 417
			bd_mutex
open:			yes
release:		yes
ioctl:			no
compat_ioctl:		no
direct_access:		no
media_changed:		no
unlock_native_capacity:	no
revalidate_disk:	no
getgeo:			no
swap_slot_free_notify:	no	(see below)
418 419 420 421 422 423

media_changed, unlock_native_capacity and revalidate_disk are called only from
check_disk_change().

swap_slot_free_notify is called with swap_lock and sometimes the page lock
held.
L
Linus Torvalds 已提交
424 425 426 427 428 429 430


--------------------------- file_operations -------------------------------
prototypes:
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
431 432
	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
433 434
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
A
Al Viro 已提交
435
	int (*iterate) (struct file *, struct dir_context *);
L
Linus Torvalds 已提交
436 437 438 439 440 441 442
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
	int (*flush) (struct file *);
	int (*release) (struct inode *, struct file *);
443
	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
L
Linus Torvalds 已提交
444 445 446 447 448 449 450 451 452 453 454 455 456 457
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
			loff_t *);
	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
			loff_t *);
	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
			void __user *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
			loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
			unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
458 459 460 461 462 463
	int (*flock) (struct file *, int, struct file_lock *);
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
			size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
			size_t, unsigned int);
	int (*setlease)(struct file *, long, struct file_lock **);
464
	long (*fallocate)(struct file *, int, loff_t, loff_t);
L
Linus Torvalds 已提交
465 466 467
};

locking rules:
468
	All may block except for ->setlease.
469
	No VFS locks held on entry except for ->setlease.
470 471

->setlease has the file_list_lock held and must not sleep.
L
Linus Torvalds 已提交
472 473 474 475 476

->llseek() locking has moved from llseek to the individual llseek
implementations.  If your fs is not using generic_file_llseek, you
need to acquire and release the appropriate locks in your ->llseek().
For many filesystems, it is probably safe to acquire the inode
477 478 479
mutex or just to use i_size_read() instead.
Note: this does not protect the file->f_pos against concurrent modifications
since this is something the userspace has to take care about.
L
Linus Torvalds 已提交
480

481 482 483 484
->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
Most instances call fasync_helper(), which does that maintenance, so it's
not normally something one needs to worry about.  Return values > 0 will be
mapped to zero in the VFS layer.
L
Linus Torvalds 已提交
485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523

->readdir() and ->ioctl() on directories must be changed. Ideally we would
move ->readdir() to inode_operations and use a separate method for directory
->ioctl() or kill the latter completely. One of the problems is that for
anything that resembles union-mount we won't have a struct file for all
components. And there are other reasons why the current interface is a mess...

->read on directories probably must go away - we should just enforce -EISDIR
in sys_read() and friends.

--------------------------- dquot_operations -------------------------------
prototypes:
	int (*write_dquot) (struct dquot *);
	int (*acquire_dquot) (struct dquot *);
	int (*release_dquot) (struct dquot *);
	int (*mark_dirty) (struct dquot *);
	int (*write_info) (struct super_block *, int);

These operations are intended to be more or less wrapping functions that ensure
a proper locking wrt the filesystem and call the generic quota operations.

What filesystem should expect from the generic quota functions:

		FS recursion	Held locks when called
write_dquot:	yes		dqonoff_sem or dqptr_sem
acquire_dquot:	yes		dqonoff_sem or dqptr_sem
release_dquot:	yes		dqonoff_sem or dqptr_sem
mark_dirty:	no		-
write_info:	yes		dqonoff_sem

FS recursion means calling ->quota_read() and ->quota_write() from superblock
operations.

More details about quota locking can be found in fs/dquot.c.

--------------------------- vm_operations_struct -----------------------------
prototypes:
	void (*open)(struct vm_area_struct*);
	void (*close)(struct vm_area_struct*);
N
Nick Piggin 已提交
524
	int (*fault)(struct vm_area_struct*, struct vm_fault *);
525
	int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
526
	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
L
Linus Torvalds 已提交
527 528

locking rules:
529 530 531 532
		mmap_sem	PageLocked(page)
open:		yes
close:		yes
fault:		yes		can return with page locked
533
map_pages:	yes
534 535
page_mkwrite:	yes		can return with page locked
access:		yes
M
Mark Fasheh 已提交
536

N
Nick Piggin 已提交
537 538 539 540 541 542 543 544
	->fault() is called when a previously not present pte is about
to be faulted in. The filesystem must find and return the page associated
with the passed in "pgoff" in the vm_fault structure. If it is possible that
the page may be truncated and/or invalidated, then the filesystem must lock
the page, then ensure it is not already truncated (the page lock will block
subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
locked. The VM will unlock the page.

545 546 547 548 549 550 551 552 553
	->map_pages() is called when VM asks to map easy accessible pages.
Filesystem should find and map pages associated with offsets from "pgoff"
till "max_pgoff". ->map_pages() is called with page table locked and must
not block.  If it's not possible to reach a page without blocking,
filesystem should skip it. Filesystem should use do_set_pte() to setup
page table entry. Pointer to entry associated with offset "pgoff" is
passed in "pte" field in vm_fault structure. Pointers to entries for other
offsets should be calculated relative to "pte".

N
Nick Piggin 已提交
554 555 556 557 558 559
	->page_mkwrite() is called when a previously read-only pte is
about to become writeable. The filesystem again must ensure that there are
no truncate/invalidate races, and then return with the page locked. If
the page has been truncated, the filesystem should not look up a new page
like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
will cause the VM to retry the fault.
L
Linus Torvalds 已提交
560

561
	->access() is called when get_user_pages() fails in
562
access_process_vm(), typically used to debug a process through
563 564 565
/proc/pid/mem or ptrace.  This function is needed only for
VM_IO | VM_PFNMAP VMAs.

L
Linus Torvalds 已提交
566 567 568 569 570
================================================================================
			Dubious stuff

(if you break something or notice that it is broken and do not fix it yourself
- at least put it here)