Documentation/filesystems/Locking

   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:
  12         int (*d_revalidate)(struct dentry *, unsigned int);
  13         int (*d_weak_revalidate)(struct dentry *, unsigned int);
  14         int (*d_hash)(const struct dentry *, struct qstr *);
  15         int (*d_compare)(const struct dentry *,
  16                         unsigned int, const char *, const struct qstr *);
  17         int (*d_delete)(struct dentry *);
  18         int (*d_init)(struct dentry *);
  19         void (*d_release)(struct dentry *);
  20         void (*d_iput)(struct dentry *, struct inode *);
  21         char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
  22         struct vfsmount *(*d_automount)(struct path *path);
  23         int (*d_manage)(const struct path *, bool);
  24         struct dentry *(*d_real)(struct dentry *, const struct inode *,
  25                                  unsigned int);
  26
  27 locking rules:
  28                 rename_lock     ->d_lock        may block       rcu-walk
  29 d_revalidate:   no              no              yes (ref-walk)  maybe
  30 d_weak_revalidate:no            no              yes             no
  31 d_hash          no              no              no              maybe
  32 d_compare:      yes             no              no              maybe
  33 d_delete:       no              yes             no              no
  34 d_init: no              no              yes             no
  35 d_release:      no              no              yes             no
  36 d_prune:        no              yes             no              no
  37 d_iput:         no              no              yes             no
  38 d_dname:        no              no              no              no
  39 d_automount:    no              no              yes             no
  40 d_manage:       no              no              yes (ref-walk)  maybe
  41 d_real          no              no              yes             no
  42
  43 --------------------------- inode_operations ---------------------------
  44 prototypes:
  45         int (*create) (struct inode *,struct dentry *,umode_t, bool);
  46         struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
  47         int (*link) (struct dentry *,struct inode *,struct dentry *);
  48         int (*unlink) (struct inode *,struct dentry *);
  49         int (*symlink) (struct inode *,struct dentry *,const char *);
  50         int (*mkdir) (struct inode *,struct dentry *,umode_t);
  51         int (*rmdir) (struct inode *,struct dentry *);
  52         int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
  53         int (*rename) (struct inode *, struct dentry *,
  54                         struct inode *, struct dentry *, unsigned int);
  55         int (*readlink) (struct dentry *, char __user *,int);
  56         const char *(*get_link) (struct dentry *, struct inode *, void **);
  57         void (*truncate) (struct inode *);
  58         int (*permission) (struct inode *, int, unsigned int);
  59         int (*get_acl)(struct inode *, int);
  60         int (*setattr) (struct dentry *, struct iattr *);
  61         int (*getattr) (const struct path *, struct dentry *, struct kstat *,
  62                         u32, unsigned int);
  63         ssize_t (*listxattr) (struct dentry *, char *, size_t);
  64         int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
  65         void (*update_time)(struct inode *, struct timespec *, int);
  66         int (*atomic_open)(struct inode *, struct dentry *,
  67                                 struct file *, unsigned open_flag,
  68                                 umode_t create_mode, int *opened);
  69         int (*tmpfile) (struct inode *, struct dentry *, umode_t);
  70
  71 locking rules:
  72         all may block
  73                 i_mutex(inode)
  74 lookup:         yes
  75 create:         yes
  76 link:           yes (both)
  77 mknod:          yes
  78 symlink:        yes
  79 mkdir:          yes
  80 unlink:         yes (both)
  81 rmdir:          yes (both)      (see below)
  82 rename: yes (all)       (see below)
  83 readlink:       no
  84 get_link:       no
  85 setattr:        yes
  86 permission:     no (may not block if called in rcu-walk mode)
  87 get_acl:        no
  88 getattr:        no
  89 listxattr:      no
  90 fiemap:         no
  91 update_time:    no
  92 atomic_open:    yes
  93 tmpfile:        no
  94
  95
  96         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
  97 victim.
  98         cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
  99
 100 See Documentation/filesystems/directory-locking for more detailed discussion
 101 of the locking scheme for directory operations.
 102
 103 ----------------------- xattr_handler operations -----------------------
 104 prototypes:
 105         bool (*list)(struct dentry *dentry);
 106         int (*get)(const struct xattr_handler *handler, struct dentry *dentry,
 107                    struct inode *inode, const char *name, void *buffer,
 108                    size_t size);
 109         int (*set)(const struct xattr_handler *handler, struct dentry *dentry,
 110                    struct inode *inode, const char *name, const void *buffer,
 111                    size_t size, int flags);
 112
 113 locking rules:
 114         all may block
 115                 i_mutex(inode)
 116 list:           no
 117 get:            no
 118 set:            yes
 119
 120 --------------------------- super_operations ---------------------------
 121 prototypes:
 122         struct inode *(*alloc_inode)(struct super_block *sb);
 123         void (*destroy_inode)(struct inode *);
 124         void (*dirty_inode) (struct inode *, int flags);
 125         int (*write_inode) (struct inode *, struct writeback_control *wbc);
 126         int (*drop_inode) (struct inode *);
 127         void (*evict_inode) (struct inode *);
 128         void (*put_super) (struct super_block *);
 129         int (*sync_fs)(struct super_block *sb, int wait);
 130         int (*freeze_fs) (struct super_block *);
 131         int (*unfreeze_fs) (struct super_block *);
 132         int (*statfs) (struct dentry *, struct kstatfs *);
 133         int (*remount_fs) (struct super_block *, int *, char *);
 134         void (*umount_begin) (struct super_block *);
 135         int (*show_options)(struct seq_file *, struct dentry *);
 136         ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 137         ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 138         int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
 139
 140 locking rules:
 141         All may block [not true, see below]
 142                         s_umount
 143 alloc_inode:
 144 destroy_inode:
 145 dirty_inode:
 146 write_inode:
 147 drop_inode:                             !!!inode->i_lock!!!
 148 evict_inode:
 149 put_super:              write
 150 sync_fs:                read
 151 freeze_fs:              write
 152 unfreeze_fs:            write
 153 statfs:                 maybe(read)     (see below)
 154 remount_fs:             write
 155 umount_begin:           no
 156 show_options:           no              (namespace_sem)
 157 quota_read:             no              (see below)
 158 quota_write:            no              (see below)
 159 bdev_try_to_free_page:  no              (see below)
 160
 161 ->statfs() has s_umount (shared) when called by ustat(2) (native or
 162 compat), but that's an accident of bad API; s_umount is used to pin
 163 the superblock down when we only have dev_t given us by userland to
 164 identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
 165 doesn't hold it when calling ->statfs() - superblock is pinned down
 166 by resolving the pathname passed to syscall.
 167 ->quota_read() and ->quota_write() functions are both guaranteed to
 168 be the only ones operating on the quota file by the quota code (via
 169 dqio_sem) (unless an admin really wants to screw up something and
 170 writes to quota files with quotas on). For other details about locking
 171 see also dquot_operations section.
 172 ->bdev_try_to_free_page is called from the ->releasepage handler of
 173 the block device inode.  See there for more details.
 174
 175 --------------------------- file_system_type ---------------------------
 176 prototypes:
 177         struct dentry *(*mount) (struct file_system_type *, int,
 178                        const char *, void *);
 179         void (*kill_sb) (struct super_block *);
 180 locking rules:
 181                 may block
 182 mount           yes
 183 kill_sb         yes
 184
 185 ->mount() returns ERR_PTR or the root dentry; its superblock should be locked
 186 on return.
 187 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 188 unlocks and drops the reference.
 189
 190 --------------------------- address_space_operations --------------------------
 191 prototypes:
 192         int (*writepage)(struct page *page, struct writeback_control *wbc);
 193         int (*readpage)(struct file *, struct page *);
 194         int (*writepages)(struct address_space *, struct writeback_control *);
 195         int (*set_page_dirty)(struct page *page);
 196         int (*readpages)(struct file *filp, struct address_space *mapping,
 197                         struct list_head *pages, unsigned nr_pages);
 198         int (*write_begin)(struct file *, struct address_space *mapping,
 199                                 loff_t pos, unsigned len, unsigned flags,
 200                                 struct page **pagep, void **fsdata);
 201         int (*write_end)(struct file *, struct address_space *mapping,
 202                                 loff_t pos, unsigned len, unsigned copied,
 203                                 struct page *page, void *fsdata);
 204         sector_t (*bmap)(struct address_space *, sector_t);
 205         void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 206         int (*releasepage) (struct page *, int);
 207         void (*freepage)(struct page *);
 208         int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
 209         bool (*isolate_page) (struct page *, isolate_mode_t);
 210         int (*migratepage)(struct address_space *, struct page *, struct page *);
 211         void (*putback_page) (struct page *);
 212         int (*launder_page)(struct page *);
 213         int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
 214         int (*error_remove_page)(struct address_space *, struct page *);
 215         int (*swap_activate)(struct file *);
 216         int (*swap_deactivate)(struct file *);
 217
 218 locking rules:
 219         All except set_page_dirty and freepage may block
 220
 221                         PageLocked(page)        i_mutex
 222 writepage:              yes, unlocks (see below)
 223 readpage:               yes, unlocks
 224 writepages:
 225 set_page_dirty          no
 226 readpages:
 227 write_begin:            locks the page          yes
 228 write_end:              yes, unlocks            yes
 229 bmap:
 230 invalidatepage:         yes
 231 releasepage:            yes
 232 freepage:               yes
 233 direct_IO:
 234 isolate_page:           yes
 235 migratepage:            yes (both)
 236 putback_page:           yes
 237 launder_page:           yes
 238 is_partially_uptodate:  yes
 239 error_remove_page:      yes
 240 swap_activate:          no
 241 swap_deactivate:        no
 242
 243         ->write_begin(), ->write_end() and ->readpage() may be called from
 244 the request handler (/dev/loop).
 245
 246         ->readpage() unlocks the page, either synchronously or via I/O
 247 completion.
 248
 249         ->readpages() populates the pagecache with the passed pages and starts
 250 I/O against them.  They come unlocked upon I/O completion.
 251
 252         ->writepage() is used for two purposes: for "memory cleansing" and for
 253 "sync".  These are quite different operations and the behaviour may differ
 254 depending upon the mode.
 255
 256 If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
 257 it *must* start I/O against the page, even if that would involve
 258 blocking on in-progress I/O.
 259
 260 If writepage is called for memory cleansing (sync_mode ==
 261 WBC_SYNC_NONE) then its role is to get as much writeout underway as
 262 possible.  So writepage should try to avoid blocking against
 263 currently-in-progress I/O.
 264
 265 If the filesystem is not called for "sync" and it determines that it
 266 would need to block against in-progress I/O to be able to start new I/O
 267 against the page the filesystem should redirty the page with
 268 redirty_page_for_writepage(), then unlock the page and return zero.
 269 This may also be done to avoid internal deadlocks, but rarely.
 270
 271 If the filesystem is called for sync then it must wait on any
 272 in-progress I/O and then start new I/O.
 273
 274 The filesystem should unlock the page synchronously, before returning to the
 275 caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
 276 value. WRITEPAGE_ACTIVATE means that page cannot really be written out
 277 currently, and VM should stop calling ->writepage() on this page for some
 278 time. VM does this by moving page to the head of the active list, hence the
 279 name.
 280
 281 Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
 282 and return zero, writepage *must* run set_page_writeback() against the page,
 283 followed by unlocking it.  Once set_page_writeback() has been run against the
 284 page, write I/O can be submitted and the write I/O completion handler must run
 285 end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
 286 filesystem must run end_page_writeback() against the page before returning from
 287 writepage.
 288
 289 That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
 290 if the filesystem needs the page to be locked during writeout, that is ok, too,
 291 the page is allowed to be unlocked at any point in time between the calls to
 292 set_page_writeback() and end_page_writeback().
 293
 294 Note, failure to run either redirty_page_for_writepage() or the combination of
 295 set_page_writeback()/end_page_writeback() on a page submitted to writepage
 296 will leave the page itself marked clean but it will be tagged as dirty in the
 297 radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
 298 in the filesystem like having dirty inodes at umount and losing written data.
 299
 300         ->writepages() is used for periodic writeback and for syscall-initiated
 301 sync operations.  The address_space should start I/O against at least
 302 *nr_to_write pages.  *nr_to_write must be decremented for each page which is
 303 written.  The address_space implementation may write more (or less) pages
 304 than *nr_to_write asks for, but it should try to be reasonably close.  If
 305 nr_to_write is NULL, all dirty pages must be written.
 306
 307 writepages should _only_ write pages which are present on
 308 mapping->io_pages.
 309
 310         ->set_page_dirty() is called from various places in the kernel
 311 when the target page is marked as needing writeback.  It may be called
 312 under spinlock (it cannot block) and is sometimes called with the page
 313 not locked.
 314
 315         ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
 316 filesystems and by the swapper. The latter will eventually go away.  Please,
 317 keep it that way and don't breed new callers.
 318
 319         ->invalidatepage() is called when the filesystem must attempt to drop
 320 some or all of the buffers from the page when it is being truncated. It
 321 returns zero on success. If ->invalidatepage is zero, the kernel uses
 322 block_invalidatepage() instead.
 323
 324         ->releasepage() is called when the kernel is about to try to drop the
 325 buffers from the page in preparation for freeing it.  It returns zero to
 326 indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
 327 the kernel assumes that the fs has no private interest in the buffers.
 328
 329         ->freepage() is called when the kernel is done dropping the page
 330 from the page cache.
 331
 332         ->launder_page() may be called prior to releasing a page if
 333 it is still found to be dirty. It returns zero if the page was successfully
 334 cleaned, or an error value if not. Note that in order to prevent the page
 335 getting mapped back in and redirtied, it needs to be kept locked
 336 across the entire operation.
 337
 338         ->swap_activate will be called with a non-zero argument on
 339 files backing (non block device backed) swapfiles. A return value
 340 of zero indicates success, in which case this file can be used for
 341 backing swapspace. The swapspace operations will be proxied to the
 342 address space operations.
 343
 344         ->swap_deactivate() will be called in the sys_swapoff()
 345 path after ->swap_activate() returned success.
 346
 347 ----------------------- file_lock_operations ------------------------------
 348 prototypes:
 349         void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 350         void (*fl_release_private)(struct file_lock *);
 351
 352
 353 locking rules:
 354                         inode->i_lock   may block
 355 fl_copy_lock:           yes             no
 356 fl_release_private:     maybe           maybe[1]
 357
 358 [1]:    ->fl_release_private for flock or POSIX locks is currently allowed
 359 to block. Leases however can still be freed while the i_lock is held and
 360 so fl_release_private called on a lease should not block.
 361
 362 ----------------------- lock_manager_operations ---------------------------
 363 prototypes:
 364         int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
 365         unsigned long (*lm_owner_key)(struct file_lock *);
 366         void (*lm_notify)(struct file_lock *);  /* unblock callback */
 367         int (*lm_grant)(struct file_lock *, struct file_lock *, int);
 368         void (*lm_break)(struct file_lock *); /* break_lease callback */
 369         int (*lm_change)(struct file_lock **, int);
 370
 371 locking rules:
 372
 373                         inode->i_lock   blocked_lock_lock       may block
 374 lm_compare_owner:       yes[1]          maybe                   no
 375 lm_owner_key            yes[1]          yes                     no
 376 lm_notify:              yes             yes                     no
 377 lm_grant:               no              no                      no
 378 lm_break:               yes             no                      no
 379 lm_change               yes             no                      no
 380
 381 [1]:    ->lm_compare_owner and ->lm_owner_key are generally called with
 382 *an* inode->i_lock held. It may not be the i_lock of the inode
 383 associated with either file_lock argument! This is the case with deadlock
 384 detection, since the code has to chase down the owners of locks that may
 385 be entirely unrelated to the one on which the lock is being acquired.
 386 For deadlock detection however, the blocked_lock_lock is also held. The
 387 fact that these locks are held ensures that the file_locks do not
 388 disappear out from under you while doing the comparison or generating an
 389 owner key.
 390
 391 --------------------------- buffer_head -----------------------------------
 392 prototypes:
 393         void (*b_end_io)(struct buffer_head *bh, int uptodate);
 394
 395 locking rules:
 396         called from interrupts. In other words, extreme care is needed here.
 397 bh is locked, but that's all warranties we have here. Currently only RAID1,
 398 highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
 399 call this method upon the IO completion.
 400
 401 --------------------------- block_device_operations -----------------------
 402 prototypes:
 403         int (*open) (struct block_device *, fmode_t);
 404         int (*release) (struct gendisk *, fmode_t);
 405         int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 406         int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 407         int (*direct_access) (struct block_device *, sector_t, void **,
 408                                 unsigned long *);
 409         int (*media_changed) (struct gendisk *);
 410         void (*unlock_native_capacity) (struct gendisk *);
 411         int (*revalidate_disk) (struct gendisk *);
 412         int (*getgeo)(struct block_device *, struct hd_geometry *);
 413         void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 414
 415 locking rules:
 416                         bd_mutex
 417 open:                   yes
 418 release:                yes
 419 ioctl:                  no
 420 compat_ioctl:           no
 421 direct_access:          no
 422 media_changed:          no
 423 unlock_native_capacity: no
 424 revalidate_disk:        no
 425 getgeo:                 no
 426 swap_slot_free_notify:  no      (see below)
 427
 428 media_changed, unlock_native_capacity and revalidate_disk are called only from
 429 check_disk_change().
 430
 431 swap_slot_free_notify is called with swap_lock and sometimes the page lock
 432 held.
 433
 434
 435 --------------------------- file_operations -------------------------------
 436 prototypes:
 437         loff_t (*llseek) (struct file *, loff_t, int);
 438         ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
 439         ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 440         ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
 441         ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 442         int (*iterate) (struct file *, struct dir_context *);
 443         unsigned int (*poll) (struct file *, struct poll_table_struct *);
 444         long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 445         long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 446         int (*mmap) (struct file *, struct vm_area_struct *);
 447         int (*open) (struct inode *, struct file *);
 448         int (*flush) (struct file *);
 449         int (*release) (struct inode *, struct file *);
 450         int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
 451         int (*fasync) (int, struct file *, int);
 452         int (*lock) (struct file *, int, struct file_lock *);
 453         ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
 454                         loff_t *);
 455         ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
 456                         loff_t *);
 457         ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
 458                         void __user *);
 459         ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
 460                         loff_t *, int);
 461         unsigned long (*get_unmapped_area)(struct file *, unsigned long,
 462                         unsigned long, unsigned long, unsigned long);
 463         int (*check_flags)(int);
 464         int (*flock) (struct file *, int, struct file_lock *);
 465         ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
 466                         size_t, unsigned int);
 467         ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
 468                         size_t, unsigned int);
 469         int (*setlease)(struct file *, long, struct file_lock **, void **);
 470         long (*fallocate)(struct file *, int, loff_t, loff_t);
 471 };
 472
 473 locking rules:
 474         All may block.
 475
 476 ->llseek() locking has moved from llseek to the individual llseek
 477 implementations.  If your fs is not using generic_file_llseek, you
 478 need to acquire and release the appropriate locks in your ->llseek().
 479 For many filesystems, it is probably safe to acquire the inode
 480 mutex or just to use i_size_read() instead.
 481 Note: this does not protect the file->f_pos against concurrent modifications
 482 since this is something the userspace has to take care about.
 483
 484 ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
 485 Most instances call fasync_helper(), which does that maintenance, so it's
 486 not normally something one needs to worry about.  Return values > 0 will be
 487 mapped to zero in the VFS layer.
 488
 489 ->readdir() and ->ioctl() on directories must be changed. Ideally we would
 490 move ->readdir() to inode_operations and use a separate method for directory
 491 ->ioctl() or kill the latter completely. One of the problems is that for
 492 anything that resembles union-mount we won't have a struct file for all
 493 components. And there are other reasons why the current interface is a mess...
 494
 495 ->read on directories probably must go away - we should just enforce -EISDIR
 496 in sys_read() and friends.
 497
 498 ->setlease operations should call generic_setlease() before or after setting
 499 the lease within the individual filesystem to record the result of the
 500 operation
 501
 502 --------------------------- dquot_operations -------------------------------
 503 prototypes:
 504         int (*write_dquot) (struct dquot *);
 505         int (*acquire_dquot) (struct dquot *);
 506         int (*release_dquot) (struct dquot *);
 507         int (*mark_dirty) (struct dquot *);
 508         int (*write_info) (struct super_block *, int);
 509
 510 These operations are intended to be more or less wrapping functions that ensure
 511 a proper locking wrt the filesystem and call the generic quota operations.
 512
 513 What filesystem should expect from the generic quota functions:
 514
 515                 FS recursion    Held locks when called
 516 write_dquot:    yes             dqonoff_sem or dqptr_sem
 517 acquire_dquot:  yes             dqonoff_sem or dqptr_sem
 518 release_dquot:  yes             dqonoff_sem or dqptr_sem
 519 mark_dirty:     no              -
 520 write_info:     yes             dqonoff_sem
 521
 522 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 523 operations.
 524
 525 More details about quota locking can be found in fs/dquot.c.
 526
 527 --------------------------- vm_operations_struct -----------------------------
 528 prototypes:
 529         void (*open)(struct vm_area_struct*);
 530         void (*close)(struct vm_area_struct*);
 531         int (*fault)(struct vm_area_struct*, struct vm_fault *);
 532         int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
 533         int (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
 534         int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 535
 536 locking rules:
 537                 mmap_sem        PageLocked(page)
 538 open:           yes
 539 close:          yes
 540 fault:          yes             can return with page locked
 541 map_pages:      yes
 542 page_mkwrite:   yes             can return with page locked
 543 pfn_mkwrite:    yes
 544 access:         yes
 545
 546         ->fault() is called when a previously not present pte is about
 547 to be faulted in. The filesystem must find and return the page associated
 548 with the passed in "pgoff" in the vm_fault structure. If it is possible that
 549 the page may be truncated and/or invalidated, then the filesystem must lock
 550 the page, then ensure it is not already truncated (the page lock will block
 551 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 552 locked. The VM will unlock the page.
 553
 554         ->map_pages() is called when VM asks to map easy accessible pages.
 555 Filesystem should find and map pages associated with offsets from "start_pgoff"
 556 till "end_pgoff". ->map_pages() is called with page table locked and must
 557 not block.  If it's not possible to reach a page without blocking,
 558 filesystem should skip it. Filesystem should use do_set_pte() to setup
 559 page table entry. Pointer to entry associated with the page is passed in
 560 "pte" field in vm_fault structure. Pointers to entries for other offsets
 561 should be calculated relative to "pte".
 562
 563         ->page_mkwrite() is called when a previously read-only pte is
 564 about to become writeable. The filesystem again must ensure that there are
 565 no truncate/invalidate races, and then return with the page locked. If
 566 the page has been truncated, the filesystem should not look up a new page
 567 like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
 568 will cause the VM to retry the fault.
 569
 570         ->pfn_mkwrite() is the same as page_mkwrite but when the pte is
 571 VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
 572 VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
 573 after this call is to make the pte read-write, unless pfn_mkwrite returns
 574 an error.
 575
 576         ->access() is called when get_user_pages() fails in
 577 access_process_vm(), typically used to debug a process through
 578 /proc/pid/mem or ptrace.  This function is needed only for
 579 VM_IO | VM_PFNMAP VMAs.
 580
 581 ================================================================================
 582                         Dubious stuff
 583
 584 (if you break something or notice that it is broken and do not fix it yourself
 585 - at least put it here)