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         none have BKL
  22                 dcache_lock     rename_lock     ->d_lock        may block
  23 d_revalidate:   no              no              no              yes
  24 d_hash          no              no              no              yes
  25 d_compare:      no              yes             no              no
  26 d_delete:       yes             no              yes             no
  27 d_release:      no              no              no              yes
  28 d_iput:         no              no              no              yes
  29 d_dname:        no              no              no              no
  30
  31 --------------------------- inode_operations ---------------------------
  32 prototypes:
  33         int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
  34         struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid
  35 ata *);
  36         int (*link) (struct dentry *,struct inode *,struct dentry *);
  37         int (*unlink) (struct inode *,struct dentry *);
  38         int (*symlink) (struct inode *,struct dentry *,const char *);
  39         int (*mkdir) (struct inode *,struct dentry *,int);
  40         int (*rmdir) (struct inode *,struct dentry *);
  41         int (*mknod) (struct inode *,struct dentry *,int,dev_t);
  42         int (*rename) (struct inode *, struct dentry *,
  43                         struct inode *, struct dentry *);
  44         int (*readlink) (struct dentry *, char __user *,int);
  45         int (*follow_link) (struct dentry *, struct nameidata *);
  46         void (*truncate) (struct inode *);
  47         int (*permission) (struct inode *, int, struct nameidata *);
  48         int (*setattr) (struct dentry *, struct iattr *);
  49         int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
  50         int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
  51         ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
  52         ssize_t (*listxattr) (struct dentry *, char *, size_t);
  53         int (*removexattr) (struct dentry *, const char *);
  54
  55 locking rules:
  56         all may block, none have BKL
  57                 i_mutex(inode)
  58 lookup:         yes
  59 create:         yes
  60 link:           yes (both)
  61 mknod:          yes
  62 symlink:        yes
  63 mkdir:          yes
  64 unlink:         yes (both)
  65 rmdir:          yes (both)      (see below)
  66 rename:         yes (all)       (see below)
  67 readlink:       no
  68 follow_link:    no
  69 truncate:       yes             (see below)
  70 setattr:        yes
  71 permission:     no
  72 getattr:        no
  73 setxattr:       yes
  74 getxattr:       no
  75 listxattr:      no
  76 removexattr:    yes
  77         Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
  78 victim.
  79         cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
  80         ->truncate() is never called directly - it's a callback, not a
  81 method. It's called by vmtruncate() - library function normally used by
  82 ->setattr(). Locking information above applies to that call (i.e. is
  83 inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
  84 passed).
  85
  86 See Documentation/filesystems/directory-locking for more detailed discussion
  87 of the locking scheme for directory operations.
  88
  89 --------------------------- super_operations ---------------------------
  90 prototypes:
  91         struct inode *(*alloc_inode)(struct super_block *sb);
  92         void (*destroy_inode)(struct inode *);
  93         void (*dirty_inode) (struct inode *);
  94         int (*write_inode) (struct inode *, int);
  95         int (*drop_inode) (struct inode *);
  96         void (*evict_inode) (struct inode *);
  97         void (*put_super) (struct super_block *);
  98         void (*write_super) (struct super_block *);
  99         int (*sync_fs)(struct super_block *sb, int wait);
 100         int (*freeze_fs) (struct super_block *);
 101         int (*unfreeze_fs) (struct super_block *);
 102         int (*statfs) (struct dentry *, struct kstatfs *);
 103         int (*remount_fs) (struct super_block *, int *, char *);
 104         void (*umount_begin) (struct super_block *);
 105         int (*show_options)(struct seq_file *, struct vfsmount *);
 106         ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
 107         ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 108
 109 locking rules:
 110         All may block [not true, see below]
 111         None have BKL
 112                         s_umount
 113 alloc_inode:
 114 destroy_inode:
 115 dirty_inode:                            (must not sleep)
 116 write_inode:
 117 drop_inode:                             !!!inode_lock!!!
 118 evict_inode:
 119 put_super:              write
 120 write_super:            read
 121 sync_fs:                read
 122 freeze_fs:              read
 123 unfreeze_fs:            read
 124 statfs:                 maybe(read)     (see below)
 125 remount_fs:             write
 126 umount_begin:           no
 127 show_options:           no              (namespace_sem)
 128 quota_read:             no              (see below)
 129 quota_write:            no              (see below)
 130
 131 ->statfs() has s_umount (shared) when called by ustat(2) (native or
 132 compat), but that's an accident of bad API; s_umount is used to pin
 133 the superblock down when we only have dev_t given us by userland to
 134 identify the superblock.  Everything else (statfs(), fstatfs(), etc.)
 135 doesn't hold it when calling ->statfs() - superblock is pinned down
 136 by resolving the pathname passed to syscall.
 137 ->quota_read() and ->quota_write() functions are both guaranteed to
 138 be the only ones operating on the quota file by the quota code (via
 139 dqio_sem) (unless an admin really wants to screw up something and
 140 writes to quota files with quotas on). For other details about locking
 141 see also dquot_operations section.
 142
 143 --------------------------- file_system_type ---------------------------
 144 prototypes:
 145         int (*get_sb) (struct file_system_type *, int,
 146                        const char *, void *, struct vfsmount *);
 147         void (*kill_sb) (struct super_block *);
 148 locking rules:
 149                 may block       BKL
 150 get_sb          yes             no
 151 kill_sb         yes             no
 152
 153 ->get_sb() returns error or 0 with locked superblock attached to the vfsmount
 154 (exclusive on ->s_umount).
 155 ->kill_sb() takes a write-locked superblock, does all shutdown work on it,
 156 unlocks and drops the reference.
 157
 158 --------------------------- address_space_operations --------------------------
 159 prototypes:
 160         int (*writepage)(struct page *page, struct writeback_control *wbc);
 161         int (*readpage)(struct file *, struct page *);
 162         int (*sync_page)(struct page *);
 163         int (*writepages)(struct address_space *, struct writeback_control *);
 164         int (*set_page_dirty)(struct page *page);
 165         int (*readpages)(struct file *filp, struct address_space *mapping,
 166                         struct list_head *pages, unsigned nr_pages);
 167         int (*write_begin)(struct file *, struct address_space *mapping,
 168                                 loff_t pos, unsigned len, unsigned flags,
 169                                 struct page **pagep, void **fsdata);
 170         int (*write_end)(struct file *, struct address_space *mapping,
 171                                 loff_t pos, unsigned len, unsigned copied,
 172                                 struct page *page, void *fsdata);
 173         sector_t (*bmap)(struct address_space *, sector_t);
 174         int (*invalidatepage) (struct page *, unsigned long);
 175         int (*releasepage) (struct page *, int);
 176         void (*freepage)(struct page *);
 177         int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
 178                         loff_t offset, unsigned long nr_segs);
 179         int (*launder_page) (struct page *);
 180
 181 locking rules:
 182         All except set_page_dirty and freepage may block
 183
 184                         BKL     PageLocked(page)        i_mutex
 185 writepage:              no      yes, unlocks (see below)
 186 readpage:               no      yes, unlocks
 187 sync_page:              no      maybe
 188 writepages:             no
 189 set_page_dirty          no      no
 190 readpages:              no
 191 write_begin:            no      locks the page          yes
 192 write_end:              no      yes, unlocks            yes
 193 perform_write:          no      n/a                     yes
 194 bmap:                   no
 195 invalidatepage:         no      yes
 196 releasepage:            no      yes
 197 freepage:               no      yes
 198 direct_IO:              no
 199 launder_page:           no      yes
 200
 201         ->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 202 may be called from the request handler (/dev/loop).
 203
 204         ->readpage() unlocks the page, either synchronously or via I/O
 205 completion.
 206
 207         ->readpages() populates the pagecache with the passed pages and starts
 208 I/O against them.  They come unlocked upon I/O completion.
 209
 210         ->writepage() is used for two purposes: for "memory cleansing" and for
 211 "sync".  These are quite different operations and the behaviour may differ
 212 depending upon the mode.
 213
 214 If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
 215 it *must* start I/O against the page, even if that would involve
 216 blocking on in-progress I/O.
 217
 218 If writepage is called for memory cleansing (sync_mode ==
 219 WBC_SYNC_NONE) then its role is to get as much writeout underway as
 220 possible.  So writepage should try to avoid blocking against
 221 currently-in-progress I/O.
 222
 223 If the filesystem is not called for "sync" and it determines that it
 224 would need to block against in-progress I/O to be able to start new I/O
 225 against the page the filesystem should redirty the page with
 226 redirty_page_for_writepage(), then unlock the page and return zero.
 227 This may also be done to avoid internal deadlocks, but rarely.
 228
 229 If the filesystem is called for sync then it must wait on any
 230 in-progress I/O and then start new I/O.
 231
 232 The filesystem should unlock the page synchronously, before returning to the
 233 caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
 234 value. WRITEPAGE_ACTIVATE means that page cannot really be written out
 235 currently, and VM should stop calling ->writepage() on this page for some
 236 time. VM does this by moving page to the head of the active list, hence the
 237 name.
 238
 239 Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
 240 and return zero, writepage *must* run set_page_writeback() against the page,
 241 followed by unlocking it.  Once set_page_writeback() has been run against the
 242 page, write I/O can be submitted and the write I/O completion handler must run
 243 end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
 244 filesystem must run end_page_writeback() against the page before returning from
 245 writepage.
 246
 247 That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
 248 if the filesystem needs the page to be locked during writeout, that is ok, too,
 249 the page is allowed to be unlocked at any point in time between the calls to
 250 set_page_writeback() and end_page_writeback().
 251
 252 Note, failure to run either redirty_page_for_writepage() or the combination of
 253 set_page_writeback()/end_page_writeback() on a page submitted to writepage
 254 will leave the page itself marked clean but it will be tagged as dirty in the
 255 radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
 256 in the filesystem like having dirty inodes at umount and losing written data.
 257
 258         ->sync_page() locking rules are not well-defined - usually it is called
 259 with lock on page, but that is not guaranteed. Considering the currently
 260 existing instances of this method ->sync_page() itself doesn't look
 261 well-defined...
 262
 263         ->writepages() is used for periodic writeback and for syscall-initiated
 264 sync operations.  The address_space should start I/O against at least
 265 *nr_to_write pages.  *nr_to_write must be decremented for each page which is
 266 written.  The address_space implementation may write more (or less) pages
 267 than *nr_to_write asks for, but it should try to be reasonably close.  If
 268 nr_to_write is NULL, all dirty pages must be written.
 269
 270 writepages should _only_ write pages which are present on
 271 mapping->io_pages.
 272
 273         ->set_page_dirty() is called from various places in the kernel
 274 when the target page is marked as needing writeback.  It may be called
 275 under spinlock (it cannot block) and is sometimes called with the page
 276 not locked.
 277
 278         ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
 279 filesystems and by the swapper. The latter will eventually go away. All
 280 instances do not actually need the BKL. Please, keep it that way and don't
 281 breed new callers.
 282
 283         ->invalidatepage() is called when the filesystem must attempt to drop
 284 some or all of the buffers from the page when it is being truncated.  It
 285 returns zero on success.  If ->invalidatepage is zero, the kernel uses
 286 block_invalidatepage() instead.
 287
 288         ->releasepage() is called when the kernel is about to try to drop the
 289 buffers from the page in preparation for freeing it.  It returns zero to
 290 indicate that the buffers are (or may be) freeable.  If ->releasepage is zero,
 291 the kernel assumes that the fs has no private interest in the buffers.
 292
 293         ->freepage() is called when the kernel is done dropping the page
 294 from the page cache.
 295
 296         ->launder_page() may be called prior to releasing a page if
 297 it is still found to be dirty. It returns zero if the page was successfully
 298 cleaned, or an error value if not. Note that in order to prevent the page
 299 getting mapped back in and redirtied, it needs to be kept locked
 300 across the entire operation.
 301
 302         Note: currently almost all instances of address_space methods are
 303 using BKL for internal serialization and that's one of the worst sources
 304 of contention. Normally they are calling library functions (in fs/buffer.c)
 305 and pass foo_get_block() as a callback (on local block-based filesystems,
 306 indeed). BKL is not needed for library stuff and is usually taken by
 307 foo_get_block(). It's an overkill, since block bitmaps can be protected by
 308 internal fs locking and real critical areas are much smaller than the areas
 309 filesystems protect now.
 310
 311 ----------------------- file_lock_operations ------------------------------
 312 prototypes:
 313         void (*fl_insert)(struct file_lock *);  /* lock insertion callback */
 314         void (*fl_remove)(struct file_lock *);  /* lock removal callback */
 315         void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 316         void (*fl_release_private)(struct file_lock *);
 317
 318
 319 locking rules:
 320                         BKL     may block
 321 fl_insert:              yes     no
 322 fl_remove:              yes     no
 323 fl_copy_lock:           yes     no
 324 fl_release_private:     yes     yes
 325
 326 ----------------------- lock_manager_operations ---------------------------
 327 prototypes:
 328         int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
 329         void (*fl_notify)(struct file_lock *);  /* unblock callback */
 330         void (*fl_release_private)(struct file_lock *);
 331         void (*fl_break)(struct file_lock *); /* break_lease callback */
 332
 333 locking rules:
 334                         BKL     may block
 335 fl_compare_owner:       yes     no
 336 fl_notify:              yes     no
 337 fl_release_private:     yes     yes
 338 fl_break:               yes     no
 339
 340         Currently only NFSD and NLM provide instances of this class. None of the
 341 them block. If you have out-of-tree instances - please, show up. Locking
 342 in that area will change.
 343 --------------------------- buffer_head -----------------------------------
 344 prototypes:
 345         void (*b_end_io)(struct buffer_head *bh, int uptodate);
 346
 347 locking rules:
 348         called from interrupts. In other words, extreme care is needed here.
 349 bh is locked, but that's all warranties we have here. Currently only RAID1,
 350 highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
 351 call this method upon the IO completion.
 352
 353 --------------------------- block_device_operations -----------------------
 354 prototypes:
 355         int (*open) (struct block_device *, fmode_t);
 356         int (*release) (struct gendisk *, fmode_t);
 357         int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 358         int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 359         int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
 360         int (*media_changed) (struct gendisk *);
 361         void (*unlock_native_capacity) (struct gendisk *);
 362         int (*revalidate_disk) (struct gendisk *);
 363         int (*getgeo)(struct block_device *, struct hd_geometry *);
 364         void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 365
 366 locking rules:
 367                         BKL     bd_mutex
 368 open:                   no      yes
 369 release:                no      yes
 370 ioctl:                  no      no
 371 compat_ioctl:           no      no
 372 direct_access:          no      no
 373 media_changed:          no      no
 374 unlock_native_capacity: no      no
 375 revalidate_disk:        no      no
 376 getgeo:                 no      no
 377 swap_slot_free_notify:  no      no      (see below)
 378
 379 media_changed, unlock_native_capacity and revalidate_disk are called only from
 380 check_disk_change().
 381
 382 swap_slot_free_notify is called with swap_lock and sometimes the page lock
 383 held.
 384
 385
 386 --------------------------- file_operations -------------------------------
 387 prototypes:
 388         loff_t (*llseek) (struct file *, loff_t, int);
 389         ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
 390         ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 391         ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 392         ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 393         int (*readdir) (struct file *, void *, filldir_t);
 394         unsigned int (*poll) (struct file *, struct poll_table_struct *);
 395         long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 396         long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 397         int (*mmap) (struct file *, struct vm_area_struct *);
 398         int (*open) (struct inode *, struct file *);
 399         int (*flush) (struct file *);
 400         int (*release) (struct inode *, struct file *);
 401         int (*fsync) (struct file *, int datasync);
 402         int (*aio_fsync) (struct kiocb *, int datasync);
 403         int (*fasync) (int, struct file *, int);
 404         int (*lock) (struct file *, int, struct file_lock *);
 405         ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
 406                         loff_t *);
 407         ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
 408                         loff_t *);
 409         ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
 410                         void __user *);
 411         ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
 412                         loff_t *, int);
 413         unsigned long (*get_unmapped_area)(struct file *, unsigned long,
 414                         unsigned long, unsigned long, unsigned long);
 415         int (*check_flags)(int);
 416 };
 417
 418 locking rules:
 419         All may block.
 420                         BKL
 421 llseek:                 no      (see below)
 422 read:                   no
 423 aio_read:               no
 424 write:                  no
 425 aio_write:              no
 426 readdir:                no
 427 poll:                   no
 428 unlocked_ioctl:         no
 429 compat_ioctl:           no
 430 mmap:                   no
 431 open:                   no
 432 flush:                  no
 433 release:                no
 434 fsync:                  no      (see below)
 435 aio_fsync:              no
 436 fasync:                 no
 437 lock:                   yes
 438 readv:                  no
 439 writev:                 no
 440 sendfile:               no
 441 sendpage:               no
 442 get_unmapped_area:      no
 443 check_flags:            no
 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 Note: ext2_release() was *the* source of contention on fs-intensive
 454 loads and dropping BKL on ->release() helps to get rid of that (we still
 455 grab BKL for cases when we close a file that had been opened r/w, but that
 456 can and should be done using the internal locking with smaller critical areas).
 457 Current worst offender is ext2_get_block()...
 458
 459 ->fasync() is called without BKL protection, and is responsible for
 460 maintaining the FASYNC bit in filp->f_flags.  Most instances call
 461 fasync_helper(), which does that maintenance, so it's not normally
 462 something one needs to worry about.  Return values > 0 will be mapped to
 463 zero in the VFS layer.
 464
 465 ->readdir() and ->ioctl() on directories must be changed. Ideally we would
 466 move ->readdir() to inode_operations and use a separate method for directory
 467 ->ioctl() or kill the latter completely. One of the problems is that for
 468 anything that resembles union-mount we won't have a struct file for all
 469 components. And there are other reasons why the current interface is a mess...
 470
 471 ->read on directories probably must go away - we should just enforce -EISDIR
 472 in sys_read() and friends.
 473
 474 ->fsync() has i_mutex on inode.
 475
 476 --------------------------- dquot_operations -------------------------------
 477 prototypes:
 478         int (*write_dquot) (struct dquot *);
 479         int (*acquire_dquot) (struct dquot *);
 480         int (*release_dquot) (struct dquot *);
 481         int (*mark_dirty) (struct dquot *);
 482         int (*write_info) (struct super_block *, int);
 483
 484 These operations are intended to be more or less wrapping functions that ensure
 485 a proper locking wrt the filesystem and call the generic quota operations.
 486
 487 What filesystem should expect from the generic quota functions:
 488
 489                 FS recursion    Held locks when called
 490 write_dquot:    yes             dqonoff_sem or dqptr_sem
 491 acquire_dquot:  yes             dqonoff_sem or dqptr_sem
 492 release_dquot:  yes             dqonoff_sem or dqptr_sem
 493 mark_dirty:     no              -
 494 write_info:     yes             dqonoff_sem
 495
 496 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 497 operations.
 498
 499 More details about quota locking can be found in fs/dquot.c.
 500
 501 --------------------------- vm_operations_struct -----------------------------
 502 prototypes:
 503         void (*open)(struct vm_area_struct*);
 504         void (*close)(struct vm_area_struct*);
 505         int (*fault)(struct vm_area_struct*, struct vm_fault *);
 506         int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
 507         int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 508
 509 locking rules:
 510                 BKL     mmap_sem        PageLocked(page)
 511 open:           no      yes
 512 close:          no      yes
 513 fault:          no      yes             can return with page locked
 514 page_mkwrite:   no      yes             can return with page locked
 515 access:         no      yes
 516
 517         ->fault() is called when a previously not present pte is about
 518 to be faulted in. The filesystem must find and return the page associated
 519 with the passed in "pgoff" in the vm_fault structure. If it is possible that
 520 the page may be truncated and/or invalidated, then the filesystem must lock
 521 the page, then ensure it is not already truncated (the page lock will block
 522 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 523 locked. The VM will unlock the page.
 524
 525         ->page_mkwrite() is called when a previously read-only pte is
 526 about to become writeable. The filesystem again must ensure that there are
 527 no truncate/invalidate races, and then return with the page locked. If
 528 the page has been truncated, the filesystem should not look up a new page
 529 like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which
 530 will cause the VM to retry the fault.
 531
 532         ->access() is called when get_user_pages() fails in
 533 acces_process_vm(), typically used to debug a process through
 534 /proc/pid/mem or ptrace.  This function is needed only for
 535 VM_IO | VM_PFNMAP VMAs.
 536
 537 ================================================================================
 538                         Dubious stuff
 539
 540 (if you break something or notice that it is broken and do not fix it yourself
 541 - at least put it here)
 542
 543 ipc/shm.c::shm_delete() - may need BKL.
 544 ->read() and ->write() in many drivers are (probably) missing BKL.