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