1======= 2Locking 3======= 4 5The text below describes the locking rules for VFS-related methods. 6It is (believed to be) up-to-date. *Please*, if you change anything in 7prototypes or locking protocols - update this file. And update the relevant 8instances in the tree, don't leave that to maintainers of filesystems/devices/ 9etc. At the very least, put the list of dubious cases in the end of this file. 10Don't turn it into log - maintainers of out-of-the-tree code are supposed to 11be able to use diff(1). 12 13Thing currently missing here: socket operations. Alexey? 14 15dentry_operations 16================= 17 18prototypes:: 19 20 int (*d_revalidate)(struct dentry *, unsigned int); 21 int (*d_weak_revalidate)(struct dentry *, unsigned int); 22 int (*d_hash)(const struct dentry *, struct qstr *); 23 int (*d_compare)(const struct dentry *, 24 unsigned int, const char *, const struct qstr *); 25 int (*d_delete)(struct dentry *); 26 int (*d_init)(struct dentry *); 27 void (*d_release)(struct dentry *); 28 void (*d_iput)(struct dentry *, struct inode *); 29 char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); 30 struct vfsmount *(*d_automount)(struct path *path); 31 int (*d_manage)(const struct path *, bool); 32 struct dentry *(*d_real)(struct dentry *, const struct inode *); 33 34locking rules: 35 36================== =========== ======== ============== ======== 37ops rename_lock ->d_lock may block rcu-walk 38================== =========== ======== ============== ======== 39d_revalidate: no no yes (ref-walk) maybe 40d_weak_revalidate: no no yes no 41d_hash no no no maybe 42d_compare: yes no no maybe 43d_delete: no yes no no 44d_init: no no yes no 45d_release: no no yes no 46d_prune: no yes no no 47d_iput: no no yes no 48d_dname: no no no no 49d_automount: no no yes no 50d_manage: no no yes (ref-walk) maybe 51d_real no no yes no 52================== =========== ======== ============== ======== 53 54inode_operations 55================ 56 57prototypes:: 58 59 int (*create) (struct inode *,struct dentry *,umode_t, bool); 60 struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); 61 int (*link) (struct dentry *,struct inode *,struct dentry *); 62 int (*unlink) (struct inode *,struct dentry *); 63 int (*symlink) (struct inode *,struct dentry *,const char *); 64 int (*mkdir) (struct inode *,struct dentry *,umode_t); 65 int (*rmdir) (struct inode *,struct dentry *); 66 int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); 67 int (*rename) (struct inode *, struct dentry *, 68 struct inode *, struct dentry *, unsigned int); 69 int (*readlink) (struct dentry *, char __user *,int); 70 const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); 71 void (*truncate) (struct inode *); 72 int (*permission) (struct inode *, int, unsigned int); 73 struct posix_acl * (*get_acl)(struct inode *, int, bool); 74 int (*setattr) (struct dentry *, struct iattr *); 75 int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); 76 ssize_t (*listxattr) (struct dentry *, char *, size_t); 77 int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); 78 void (*update_time)(struct inode *, struct timespec *, int); 79 int (*atomic_open)(struct inode *, struct dentry *, 80 struct file *, unsigned open_flag, 81 umode_t create_mode); 82 int (*tmpfile) (struct inode *, struct dentry *, umode_t); 83 int (*fileattr_set)(struct user_namespace *mnt_userns, 84 struct dentry *dentry, struct fileattr *fa); 85 int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); 86 87locking rules: 88 all may block 89 90============= ============================================= 91ops i_rwsem(inode) 92============= ============================================= 93lookup: shared 94create: exclusive 95link: exclusive (both) 96mknod: exclusive 97symlink: exclusive 98mkdir: exclusive 99unlink: exclusive (both) 100rmdir: exclusive (both)(see below) 101rename: exclusive (all) (see below) 102readlink: no 103get_link: no 104setattr: exclusive 105permission: no (may not block if called in rcu-walk mode) 106get_acl: no 107getattr: no 108listxattr: no 109fiemap: no 110update_time: no 111atomic_open: shared (exclusive if O_CREAT is set in open flags) 112tmpfile: no 113fileattr_get: no or exclusive 114fileattr_set: exclusive 115============= ============================================= 116 117 118 Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem 119 exclusive on victim. 120 cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. 121 122See Documentation/filesystems/directory-locking.rst for more detailed discussion 123of the locking scheme for directory operations. 124 125xattr_handler operations 126======================== 127 128prototypes:: 129 130 bool (*list)(struct dentry *dentry); 131 int (*get)(const struct xattr_handler *handler, struct dentry *dentry, 132 struct inode *inode, const char *name, void *buffer, 133 size_t size); 134 int (*set)(const struct xattr_handler *handler, 135 struct user_namespace *mnt_userns, 136 struct dentry *dentry, struct inode *inode, const char *name, 137 const void *buffer, size_t size, int flags); 138 139locking rules: 140 all may block 141 142===== ============== 143ops i_rwsem(inode) 144===== ============== 145list: no 146get: no 147set: exclusive 148===== ============== 149 150super_operations 151================ 152 153prototypes:: 154 155 struct inode *(*alloc_inode)(struct super_block *sb); 156 void (*free_inode)(struct inode *); 157 void (*destroy_inode)(struct inode *); 158 void (*dirty_inode) (struct inode *, int flags); 159 int (*write_inode) (struct inode *, struct writeback_control *wbc); 160 int (*drop_inode) (struct inode *); 161 void (*evict_inode) (struct inode *); 162 void (*put_super) (struct super_block *); 163 int (*sync_fs)(struct super_block *sb, int wait); 164 int (*freeze_fs) (struct super_block *); 165 int (*unfreeze_fs) (struct super_block *); 166 int (*statfs) (struct dentry *, struct kstatfs *); 167 int (*remount_fs) (struct super_block *, int *, char *); 168 void (*umount_begin) (struct super_block *); 169 int (*show_options)(struct seq_file *, struct dentry *); 170 ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); 171 ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); 172 173locking rules: 174 All may block [not true, see below] 175 176====================== ============ ======================== 177ops s_umount note 178====================== ============ ======================== 179alloc_inode: 180free_inode: called from RCU callback 181destroy_inode: 182dirty_inode: 183write_inode: 184drop_inode: !!!inode->i_lock!!! 185evict_inode: 186put_super: write 187sync_fs: read 188freeze_fs: write 189unfreeze_fs: write 190statfs: maybe(read) (see below) 191remount_fs: write 192umount_begin: no 193show_options: no (namespace_sem) 194quota_read: no (see below) 195quota_write: no (see below) 196====================== ============ ======================== 197 198->statfs() has s_umount (shared) when called by ustat(2) (native or 199compat), but that's an accident of bad API; s_umount is used to pin 200the superblock down when we only have dev_t given us by userland to 201identify the superblock. Everything else (statfs(), fstatfs(), etc.) 202doesn't hold it when calling ->statfs() - superblock is pinned down 203by resolving the pathname passed to syscall. 204 205->quota_read() and ->quota_write() functions are both guaranteed to 206be the only ones operating on the quota file by the quota code (via 207dqio_sem) (unless an admin really wants to screw up something and 208writes to quota files with quotas on). For other details about locking 209see also dquot_operations section. 210 211file_system_type 212================ 213 214prototypes:: 215 216 struct dentry *(*mount) (struct file_system_type *, int, 217 const char *, void *); 218 void (*kill_sb) (struct super_block *); 219 220locking rules: 221 222======= ========= 223ops may block 224======= ========= 225mount yes 226kill_sb yes 227======= ========= 228 229->mount() returns ERR_PTR or the root dentry; its superblock should be locked 230on return. 231 232->kill_sb() takes a write-locked superblock, does all shutdown work on it, 233unlocks and drops the reference. 234 235address_space_operations 236======================== 237prototypes:: 238 239 int (*writepage)(struct page *page, struct writeback_control *wbc); 240 int (*readpage)(struct file *, struct page *); 241 int (*writepages)(struct address_space *, struct writeback_control *); 242 int (*set_page_dirty)(struct page *page); 243 void (*readahead)(struct readahead_control *); 244 int (*readpages)(struct file *filp, struct address_space *mapping, 245 struct list_head *pages, unsigned nr_pages); 246 int (*write_begin)(struct file *, struct address_space *mapping, 247 loff_t pos, unsigned len, unsigned flags, 248 struct page **pagep, void **fsdata); 249 int (*write_end)(struct file *, struct address_space *mapping, 250 loff_t pos, unsigned len, unsigned copied, 251 struct page *page, void *fsdata); 252 sector_t (*bmap)(struct address_space *, sector_t); 253 void (*invalidatepage) (struct page *, unsigned int, unsigned int); 254 int (*releasepage) (struct page *, int); 255 void (*freepage)(struct page *); 256 int (*direct_IO)(struct kiocb *, struct iov_iter *iter); 257 bool (*isolate_page) (struct page *, isolate_mode_t); 258 int (*migratepage)(struct address_space *, struct page *, struct page *); 259 void (*putback_page) (struct page *); 260 int (*launder_page)(struct page *); 261 int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long); 262 int (*error_remove_page)(struct address_space *, struct page *); 263 int (*swap_activate)(struct file *); 264 int (*swap_deactivate)(struct file *); 265 266locking rules: 267 All except set_page_dirty and freepage may block 268 269====================== ======================== ========= =============== 270ops PageLocked(page) i_rwsem invalidate_lock 271====================== ======================== ========= =============== 272writepage: yes, unlocks (see below) 273readpage: yes, unlocks shared 274writepages: 275set_page_dirty no 276readahead: yes, unlocks shared 277readpages: no shared 278write_begin: locks the page exclusive 279write_end: yes, unlocks exclusive 280bmap: 281invalidatepage: yes exclusive 282releasepage: yes 283freepage: yes 284direct_IO: 285isolate_page: yes 286migratepage: yes (both) 287putback_page: yes 288launder_page: yes 289is_partially_uptodate: yes 290error_remove_page: yes 291swap_activate: no 292swap_deactivate: no 293====================== ======================== ========= =============== 294 295->write_begin(), ->write_end() and ->readpage() may be called from 296the request handler (/dev/loop). 297 298->readpage() unlocks the page, either synchronously or via I/O 299completion. 300 301->readahead() unlocks the pages that I/O is attempted on like ->readpage(). 302 303->readpages() populates the pagecache with the passed pages and starts 304I/O against them. They come unlocked upon I/O completion. 305 306->writepage() is used for two purposes: for "memory cleansing" and for 307"sync". These are quite different operations and the behaviour may differ 308depending upon the mode. 309 310If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then 311it *must* start I/O against the page, even if that would involve 312blocking on in-progress I/O. 313 314If writepage is called for memory cleansing (sync_mode == 315WBC_SYNC_NONE) then its role is to get as much writeout underway as 316possible. So writepage should try to avoid blocking against 317currently-in-progress I/O. 318 319If the filesystem is not called for "sync" and it determines that it 320would need to block against in-progress I/O to be able to start new I/O 321against the page the filesystem should redirty the page with 322redirty_page_for_writepage(), then unlock the page and return zero. 323This may also be done to avoid internal deadlocks, but rarely. 324 325If the filesystem is called for sync then it must wait on any 326in-progress I/O and then start new I/O. 327 328The filesystem should unlock the page synchronously, before returning to the 329caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE 330value. WRITEPAGE_ACTIVATE means that page cannot really be written out 331currently, and VM should stop calling ->writepage() on this page for some 332time. VM does this by moving page to the head of the active list, hence the 333name. 334 335Unless the filesystem is going to redirty_page_for_writepage(), unlock the page 336and return zero, writepage *must* run set_page_writeback() against the page, 337followed by unlocking it. Once set_page_writeback() has been run against the 338page, write I/O can be submitted and the write I/O completion handler must run 339end_page_writeback() once the I/O is complete. If no I/O is submitted, the 340filesystem must run end_page_writeback() against the page before returning from 341writepage. 342 343That is: after 2.5.12, pages which are under writeout are *not* locked. Note, 344if the filesystem needs the page to be locked during writeout, that is ok, too, 345the page is allowed to be unlocked at any point in time between the calls to 346set_page_writeback() and end_page_writeback(). 347 348Note, failure to run either redirty_page_for_writepage() or the combination of 349set_page_writeback()/end_page_writeback() on a page submitted to writepage 350will leave the page itself marked clean but it will be tagged as dirty in the 351radix tree. This incoherency can lead to all sorts of hard-to-debug problems 352in the filesystem like having dirty inodes at umount and losing written data. 353 354->writepages() is used for periodic writeback and for syscall-initiated 355sync operations. The address_space should start I/O against at least 356``*nr_to_write`` pages. ``*nr_to_write`` must be decremented for each page 357which is written. The address_space implementation may write more (or less) 358pages than ``*nr_to_write`` asks for, but it should try to be reasonably close. 359If nr_to_write is NULL, all dirty pages must be written. 360 361writepages should _only_ write pages which are present on 362mapping->io_pages. 363 364->set_page_dirty() is called from various places in the kernel 365when the target page is marked as needing writeback. It may be called 366under spinlock (it cannot block) and is sometimes called with the page 367not locked. 368 369->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some 370filesystems and by the swapper. The latter will eventually go away. Please, 371keep it that way and don't breed new callers. 372 373->invalidatepage() is called when the filesystem must attempt to drop 374some or all of the buffers from the page when it is being truncated. It 375returns zero on success. If ->invalidatepage is zero, the kernel uses 376block_invalidatepage() instead. The filesystem must exclusively acquire 377invalidate_lock before invalidating page cache in truncate / hole punch path 378(and thus calling into ->invalidatepage) to block races between page cache 379invalidation and page cache filling functions (fault, read, ...). 380 381->releasepage() is called when the kernel is about to try to drop the 382buffers from the page in preparation for freeing it. It returns zero to 383indicate that the buffers are (or may be) freeable. If ->releasepage is zero, 384the kernel assumes that the fs has no private interest in the buffers. 385 386->freepage() is called when the kernel is done dropping the page 387from the page cache. 388 389->launder_page() may be called prior to releasing a page if 390it is still found to be dirty. It returns zero if the page was successfully 391cleaned, or an error value if not. Note that in order to prevent the page 392getting mapped back in and redirtied, it needs to be kept locked 393across the entire operation. 394 395->swap_activate will be called with a non-zero argument on 396files backing (non block device backed) swapfiles. A return value 397of zero indicates success, in which case this file can be used for 398backing swapspace. The swapspace operations will be proxied to the 399address space operations. 400 401->swap_deactivate() will be called in the sys_swapoff() 402path after ->swap_activate() returned success. 403 404file_lock_operations 405==================== 406 407prototypes:: 408 409 void (*fl_copy_lock)(struct file_lock *, struct file_lock *); 410 void (*fl_release_private)(struct file_lock *); 411 412 413locking rules: 414 415=================== ============= ========= 416ops inode->i_lock may block 417=================== ============= ========= 418fl_copy_lock: yes no 419fl_release_private: maybe maybe[1]_ 420=================== ============= ========= 421 422.. [1]: 423 ->fl_release_private for flock or POSIX locks is currently allowed 424 to block. Leases however can still be freed while the i_lock is held and 425 so fl_release_private called on a lease should not block. 426 427lock_manager_operations 428======================= 429 430prototypes:: 431 432 void (*lm_notify)(struct file_lock *); /* unblock callback */ 433 int (*lm_grant)(struct file_lock *, struct file_lock *, int); 434 void (*lm_break)(struct file_lock *); /* break_lease callback */ 435 int (*lm_change)(struct file_lock **, int); 436 bool (*lm_breaker_owns_lease)(struct file_lock *); 437 438locking rules: 439 440====================== ============= ================= ========= 441ops inode->i_lock blocked_lock_lock may block 442====================== ============= ================= ========= 443lm_notify: yes yes no 444lm_grant: no no no 445lm_break: yes no no 446lm_change yes no no 447lm_breaker_owns_lease: no no no 448====================== ============= ================= ========= 449 450buffer_head 451=========== 452 453prototypes:: 454 455 void (*b_end_io)(struct buffer_head *bh, int uptodate); 456 457locking rules: 458 459called from interrupts. In other words, extreme care is needed here. 460bh is locked, but that's all warranties we have here. Currently only RAID1, 461highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices 462call this method upon the IO completion. 463 464block_device_operations 465======================= 466prototypes:: 467 468 int (*open) (struct block_device *, fmode_t); 469 int (*release) (struct gendisk *, fmode_t); 470 int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); 471 int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); 472 int (*direct_access) (struct block_device *, sector_t, void **, 473 unsigned long *); 474 void (*unlock_native_capacity) (struct gendisk *); 475 int (*getgeo)(struct block_device *, struct hd_geometry *); 476 void (*swap_slot_free_notify) (struct block_device *, unsigned long); 477 478locking rules: 479 480======================= =================== 481ops open_mutex 482======================= =================== 483open: yes 484release: yes 485ioctl: no 486compat_ioctl: no 487direct_access: no 488unlock_native_capacity: no 489getgeo: no 490swap_slot_free_notify: no (see below) 491======================= =================== 492 493swap_slot_free_notify is called with swap_lock and sometimes the page lock 494held. 495 496 497file_operations 498=============== 499 500prototypes:: 501 502 loff_t (*llseek) (struct file *, loff_t, int); 503 ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); 504 ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); 505 ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); 506 ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); 507 int (*iopoll) (struct kiocb *kiocb, bool spin); 508 int (*iterate) (struct file *, struct dir_context *); 509 int (*iterate_shared) (struct file *, struct dir_context *); 510 __poll_t (*poll) (struct file *, struct poll_table_struct *); 511 long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); 512 long (*compat_ioctl) (struct file *, unsigned int, unsigned long); 513 int (*mmap) (struct file *, struct vm_area_struct *); 514 int (*open) (struct inode *, struct file *); 515 int (*flush) (struct file *); 516 int (*release) (struct inode *, struct file *); 517 int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); 518 int (*fasync) (int, struct file *, int); 519 int (*lock) (struct file *, int, struct file_lock *); 520 ssize_t (*sendpage) (struct file *, struct page *, int, size_t, 521 loff_t *, int); 522 unsigned long (*get_unmapped_area)(struct file *, unsigned long, 523 unsigned long, unsigned long, unsigned long); 524 int (*check_flags)(int); 525 int (*flock) (struct file *, int, struct file_lock *); 526 ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, 527 size_t, unsigned int); 528 ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, 529 size_t, unsigned int); 530 int (*setlease)(struct file *, long, struct file_lock **, void **); 531 long (*fallocate)(struct file *, int, loff_t, loff_t); 532 void (*show_fdinfo)(struct seq_file *m, struct file *f); 533 unsigned (*mmap_capabilities)(struct file *); 534 ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, 535 loff_t, size_t, unsigned int); 536 loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, 537 struct file *file_out, loff_t pos_out, 538 loff_t len, unsigned int remap_flags); 539 int (*fadvise)(struct file *, loff_t, loff_t, int); 540 541locking rules: 542 All may block. 543 544->llseek() locking has moved from llseek to the individual llseek 545implementations. If your fs is not using generic_file_llseek, you 546need to acquire and release the appropriate locks in your ->llseek(). 547For many filesystems, it is probably safe to acquire the inode 548mutex or just to use i_size_read() instead. 549Note: this does not protect the file->f_pos against concurrent modifications 550since this is something the userspace has to take care about. 551 552->iterate() is called with i_rwsem exclusive. 553 554->iterate_shared() is called with i_rwsem at least shared. 555 556->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. 557Most instances call fasync_helper(), which does that maintenance, so it's 558not normally something one needs to worry about. Return values > 0 will be 559mapped to zero in the VFS layer. 560 561->readdir() and ->ioctl() on directories must be changed. Ideally we would 562move ->readdir() to inode_operations and use a separate method for directory 563->ioctl() or kill the latter completely. One of the problems is that for 564anything that resembles union-mount we won't have a struct file for all 565components. And there are other reasons why the current interface is a mess... 566 567->read on directories probably must go away - we should just enforce -EISDIR 568in sys_read() and friends. 569 570->setlease operations should call generic_setlease() before or after setting 571the lease within the individual filesystem to record the result of the 572operation 573 574->fallocate implementation must be really careful to maintain page cache 575consistency when punching holes or performing other operations that invalidate 576page cache contents. Usually the filesystem needs to call 577truncate_inode_pages_range() to invalidate relevant range of the page cache. 578However the filesystem usually also needs to update its internal (and on disk) 579view of file offset -> disk block mapping. Until this update is finished, the 580filesystem needs to block page faults and reads from reloading now-stale page 581cache contents from the disk. Since VFS acquires mapping->invalidate_lock in 582shared mode when loading pages from disk (filemap_fault(), filemap_read(), 583readahead paths), the fallocate implementation must take the invalidate_lock to 584prevent reloading. 585 586->copy_file_range and ->remap_file_range implementations need to serialize 587against modifications of file data while the operation is running. For 588blocking changes through write(2) and similar operations inode->i_rwsem can be 589used. To block changes to file contents via a memory mapping during the 590operation, the filesystem must take mapping->invalidate_lock to coordinate 591with ->page_mkwrite. 592 593dquot_operations 594================ 595 596prototypes:: 597 598 int (*write_dquot) (struct dquot *); 599 int (*acquire_dquot) (struct dquot *); 600 int (*release_dquot) (struct dquot *); 601 int (*mark_dirty) (struct dquot *); 602 int (*write_info) (struct super_block *, int); 603 604These operations are intended to be more or less wrapping functions that ensure 605a proper locking wrt the filesystem and call the generic quota operations. 606 607What filesystem should expect from the generic quota functions: 608 609============== ============ ========================= 610ops FS recursion Held locks when called 611============== ============ ========================= 612write_dquot: yes dqonoff_sem or dqptr_sem 613acquire_dquot: yes dqonoff_sem or dqptr_sem 614release_dquot: yes dqonoff_sem or dqptr_sem 615mark_dirty: no - 616write_info: yes dqonoff_sem 617============== ============ ========================= 618 619FS recursion means calling ->quota_read() and ->quota_write() from superblock 620operations. 621 622More details about quota locking can be found in fs/dquot.c. 623 624vm_operations_struct 625==================== 626 627prototypes:: 628 629 void (*open)(struct vm_area_struct*); 630 void (*close)(struct vm_area_struct*); 631 vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *); 632 vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); 633 vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *); 634 int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); 635 636locking rules: 637 638============= ========= =========================== 639ops mmap_lock PageLocked(page) 640============= ========= =========================== 641open: yes 642close: yes 643fault: yes can return with page locked 644map_pages: yes 645page_mkwrite: yes can return with page locked 646pfn_mkwrite: yes 647access: yes 648============= ========= =========================== 649 650->fault() is called when a previously not present pte is about to be faulted 651in. The filesystem must find and return the page associated with the passed in 652"pgoff" in the vm_fault structure. If it is possible that the page may be 653truncated and/or invalidated, then the filesystem must lock invalidate_lock, 654then ensure the page is not already truncated (invalidate_lock will block 655subsequent truncate), and then return with VM_FAULT_LOCKED, and the page 656locked. The VM will unlock the page. 657 658->map_pages() is called when VM asks to map easy accessible pages. 659Filesystem should find and map pages associated with offsets from "start_pgoff" 660till "end_pgoff". ->map_pages() is called with page table locked and must 661not block. If it's not possible to reach a page without blocking, 662filesystem should skip it. Filesystem should use do_set_pte() to setup 663page table entry. Pointer to entry associated with the page is passed in 664"pte" field in vm_fault structure. Pointers to entries for other offsets 665should be calculated relative to "pte". 666 667->page_mkwrite() is called when a previously read-only pte is about to become 668writeable. The filesystem again must ensure that there are no 669truncate/invalidate races or races with operations such as ->remap_file_range 670or ->copy_file_range, and then return with the page locked. Usually 671mapping->invalidate_lock is suitable for proper serialization. If the page has 672been truncated, the filesystem should not look up a new page like the ->fault() 673handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to 674retry the fault. 675 676->pfn_mkwrite() is the same as page_mkwrite but when the pte is 677VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is 678VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior 679after this call is to make the pte read-write, unless pfn_mkwrite returns 680an error. 681 682->access() is called when get_user_pages() fails in 683access_process_vm(), typically used to debug a process through 684/proc/pid/mem or ptrace. This function is needed only for 685VM_IO | VM_PFNMAP VMAs. 686 687-------------------------------------------------------------------------------- 688 689 Dubious stuff 690 691(if you break something or notice that it is broken and do not fix it yourself 692- at least put it here) 693