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