cachepc-linux

Fork of AMDESE/linux with modifications for CachePC side-channel attack
git clone https://git.sinitax.com/sinitax/cachepc-linux
Log | Files | Refs | README | LICENSE | sfeed.txt

locking.rst (27513B)


      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 (*read_folio)(struct file *, struct folio *);
    241	int (*writepages)(struct address_space *, struct writeback_control *);
    242	bool (*dirty_folio)(struct address_space *, struct folio *folio);
    243	void (*readahead)(struct readahead_control *);
    244	int (*write_begin)(struct file *, struct address_space *mapping,
    245				loff_t pos, unsigned len,
    246				struct page **pagep, void **fsdata);
    247	int (*write_end)(struct file *, struct address_space *mapping,
    248				loff_t pos, unsigned len, unsigned copied,
    249				struct page *page, void *fsdata);
    250	sector_t (*bmap)(struct address_space *, sector_t);
    251	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
    252	bool (*release_folio)(struct folio *, gfp_t);
    253	void (*free_folio)(struct folio *);
    254	int (*direct_IO)(struct kiocb *, struct iov_iter *iter);
    255	bool (*isolate_page) (struct page *, isolate_mode_t);
    256	int (*migratepage)(struct address_space *, struct page *, struct page *);
    257	void (*putback_page) (struct page *);
    258	int (*launder_folio)(struct folio *);
    259	bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count);
    260	int (*error_remove_page)(struct address_space *, struct page *);
    261	int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span)
    262	int (*swap_deactivate)(struct file *);
    263	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
    264
    265locking rules:
    266	All except dirty_folio and free_folio may block
    267
    268======================	======================== =========	===============
    269ops			folio locked		 i_rwsem	invalidate_lock
    270======================	======================== =========	===============
    271writepage:		yes, unlocks (see below)
    272read_folio:		yes, unlocks				shared
    273writepages:
    274dirty_folio:		maybe
    275readahead:		yes, unlocks				shared
    276write_begin:		locks the page		 exclusive
    277write_end:		yes, unlocks		 exclusive
    278bmap:
    279invalidate_folio:	yes					exclusive
    280release_folio:		yes
    281free_folio:		yes
    282direct_IO:
    283isolate_page:		yes
    284migratepage:		yes (both)
    285putback_page:		yes
    286launder_folio:		yes
    287is_partially_uptodate:	yes
    288error_remove_page:	yes
    289swap_activate:		no
    290swap_deactivate:	no
    291swap_rw:		yes, unlocks
    292======================	======================== =========	===============
    293
    294->write_begin(), ->write_end() and ->read_folio() may be called from
    295the request handler (/dev/loop).
    296
    297->read_folio() unlocks the folio, either synchronously or via I/O
    298completion.
    299
    300->readahead() unlocks the folios that I/O is attempted on like ->read_folio().
    301
    302->writepage() is used for two purposes: for "memory cleansing" and for
    303"sync".  These are quite different operations and the behaviour may differ
    304depending upon the mode.
    305
    306If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
    307it *must* start I/O against the page, even if that would involve
    308blocking on in-progress I/O.
    309
    310If writepage is called for memory cleansing (sync_mode ==
    311WBC_SYNC_NONE) then its role is to get as much writeout underway as
    312possible.  So writepage should try to avoid blocking against
    313currently-in-progress I/O.
    314
    315If the filesystem is not called for "sync" and it determines that it
    316would need to block against in-progress I/O to be able to start new I/O
    317against the page the filesystem should redirty the page with
    318redirty_page_for_writepage(), then unlock the page and return zero.
    319This may also be done to avoid internal deadlocks, but rarely.
    320
    321If the filesystem is called for sync then it must wait on any
    322in-progress I/O and then start new I/O.
    323
    324The filesystem should unlock the page synchronously, before returning to the
    325caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE
    326value. WRITEPAGE_ACTIVATE means that page cannot really be written out
    327currently, and VM should stop calling ->writepage() on this page for some
    328time. VM does this by moving page to the head of the active list, hence the
    329name.
    330
    331Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
    332and return zero, writepage *must* run set_page_writeback() against the page,
    333followed by unlocking it.  Once set_page_writeback() has been run against the
    334page, write I/O can be submitted and the write I/O completion handler must run
    335end_page_writeback() once the I/O is complete.  If no I/O is submitted, the
    336filesystem must run end_page_writeback() against the page before returning from
    337writepage.
    338
    339That is: after 2.5.12, pages which are under writeout are *not* locked.  Note,
    340if the filesystem needs the page to be locked during writeout, that is ok, too,
    341the page is allowed to be unlocked at any point in time between the calls to
    342set_page_writeback() and end_page_writeback().
    343
    344Note, failure to run either redirty_page_for_writepage() or the combination of
    345set_page_writeback()/end_page_writeback() on a page submitted to writepage
    346will leave the page itself marked clean but it will be tagged as dirty in the
    347radix tree.  This incoherency can lead to all sorts of hard-to-debug problems
    348in the filesystem like having dirty inodes at umount and losing written data.
    349
    350->writepages() is used for periodic writeback and for syscall-initiated
    351sync operations.  The address_space should start I/O against at least
    352``*nr_to_write`` pages.  ``*nr_to_write`` must be decremented for each page
    353which is written.  The address_space implementation may write more (or less)
    354pages than ``*nr_to_write`` asks for, but it should try to be reasonably close.
    355If nr_to_write is NULL, all dirty pages must be written.
    356
    357writepages should _only_ write pages which are present on
    358mapping->io_pages.
    359
    360->dirty_folio() is called from various places in the kernel when
    361the target folio is marked as needing writeback.  The folio cannot be
    362truncated because either the caller holds the folio lock, or the caller
    363has found the folio while holding the page table lock which will block
    364truncation.
    365
    366->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
    367filesystems and by the swapper. The latter will eventually go away.  Please,
    368keep it that way and don't breed new callers.
    369
    370->invalidate_folio() is called when the filesystem must attempt to drop
    371some or all of the buffers from the page when it is being truncated. It
    372returns zero on success.  The filesystem must exclusively acquire
    373invalidate_lock before invalidating page cache in truncate / hole punch
    374path (and thus calling into ->invalidate_folio) to block races between page
    375cache invalidation and page cache filling functions (fault, read, ...).
    376
    377->release_folio() is called when the kernel is about to try to drop the
    378buffers from the folio in preparation for freeing it.  It returns false to
    379indicate that the buffers are (or may be) freeable.  If ->release_folio is
    380NULL, the kernel assumes that the fs has no private interest in the buffers.
    381
    382->free_folio() is called when the kernel has dropped the folio
    383from the page cache.
    384
    385->launder_folio() may be called prior to releasing a folio if
    386it is still found to be dirty. It returns zero if the folio was successfully
    387cleaned, or an error value if not. Note that in order to prevent the folio
    388getting mapped back in and redirtied, it needs to be kept locked
    389across the entire operation.
    390
    391->swap_activate() will be called to prepare the given file for swap.  It
    392should perform any validation and preparation necessary to ensure that
    393writes can be performed with minimal memory allocation.  It should call
    394add_swap_extent(), or the helper iomap_swapfile_activate(), and return
    395the number of extents added.  If IO should be submitted through
    396->swap_rw(), it should set SWP_FS_OPS, otherwise IO will be submitted
    397directly to the block device ``sis->bdev``.
    398
    399->swap_deactivate() will be called in the sys_swapoff()
    400path after ->swap_activate() returned success.
    401
    402->swap_rw will be called for swap IO if SWP_FS_OPS was set by ->swap_activate().
    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        bool (*lm_lock_expirable)(struct file_lock *);
    438        void (*lm_expire_lock)(void);
    439
    440locking rules:
    441
    442======================	=============	=================	=========
    443ops			   flc_lock  	blocked_lock_lock	may block
    444======================	=============	=================	=========
    445lm_notify:		no      	yes			no
    446lm_grant:		no		no			no
    447lm_break:		yes		no			no
    448lm_change		yes		no			no
    449lm_breaker_owns_lease:	yes     	no			no
    450lm_lock_expirable	yes		no			no
    451lm_expire_lock		no		no			yes
    452======================	=============	=================	=========
    453
    454buffer_head
    455===========
    456
    457prototypes::
    458
    459	void (*b_end_io)(struct buffer_head *bh, int uptodate);
    460
    461locking rules:
    462
    463called from interrupts. In other words, extreme care is needed here.
    464bh is locked, but that's all warranties we have here. Currently only RAID1,
    465highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
    466call this method upon the IO completion.
    467
    468block_device_operations
    469=======================
    470prototypes::
    471
    472	int (*open) (struct block_device *, fmode_t);
    473	int (*release) (struct gendisk *, fmode_t);
    474	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
    475	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
    476	int (*direct_access) (struct block_device *, sector_t, void **,
    477				unsigned long *);
    478	void (*unlock_native_capacity) (struct gendisk *);
    479	int (*getgeo)(struct block_device *, struct hd_geometry *);
    480	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
    481
    482locking rules:
    483
    484======================= ===================
    485ops			open_mutex
    486======================= ===================
    487open:			yes
    488release:		yes
    489ioctl:			no
    490compat_ioctl:		no
    491direct_access:		no
    492unlock_native_capacity:	no
    493getgeo:			no
    494swap_slot_free_notify:	no	(see below)
    495======================= ===================
    496
    497swap_slot_free_notify is called with swap_lock and sometimes the page lock
    498held.
    499
    500
    501file_operations
    502===============
    503
    504prototypes::
    505
    506	loff_t (*llseek) (struct file *, loff_t, int);
    507	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
    508	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
    509	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
    510	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
    511	int (*iopoll) (struct kiocb *kiocb, bool spin);
    512	int (*iterate) (struct file *, struct dir_context *);
    513	int (*iterate_shared) (struct file *, struct dir_context *);
    514	__poll_t (*poll) (struct file *, struct poll_table_struct *);
    515	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
    516	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
    517	int (*mmap) (struct file *, struct vm_area_struct *);
    518	int (*open) (struct inode *, struct file *);
    519	int (*flush) (struct file *);
    520	int (*release) (struct inode *, struct file *);
    521	int (*fsync) (struct file *, loff_t start, loff_t end, int datasync);
    522	int (*fasync) (int, struct file *, int);
    523	int (*lock) (struct file *, int, struct file_lock *);
    524	ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
    525			loff_t *, int);
    526	unsigned long (*get_unmapped_area)(struct file *, unsigned long,
    527			unsigned long, unsigned long, unsigned long);
    528	int (*check_flags)(int);
    529	int (*flock) (struct file *, int, struct file_lock *);
    530	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
    531			size_t, unsigned int);
    532	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
    533			size_t, unsigned int);
    534	int (*setlease)(struct file *, long, struct file_lock **, void **);
    535	long (*fallocate)(struct file *, int, loff_t, loff_t);
    536	void (*show_fdinfo)(struct seq_file *m, struct file *f);
    537	unsigned (*mmap_capabilities)(struct file *);
    538	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
    539			loff_t, size_t, unsigned int);
    540	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
    541			struct file *file_out, loff_t pos_out,
    542			loff_t len, unsigned int remap_flags);
    543	int (*fadvise)(struct file *, loff_t, loff_t, int);
    544
    545locking rules:
    546	All may block.
    547
    548->llseek() locking has moved from llseek to the individual llseek
    549implementations.  If your fs is not using generic_file_llseek, you
    550need to acquire and release the appropriate locks in your ->llseek().
    551For many filesystems, it is probably safe to acquire the inode
    552mutex or just to use i_size_read() instead.
    553Note: this does not protect the file->f_pos against concurrent modifications
    554since this is something the userspace has to take care about.
    555
    556->iterate() is called with i_rwsem exclusive.
    557
    558->iterate_shared() is called with i_rwsem at least shared.
    559
    560->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
    561Most instances call fasync_helper(), which does that maintenance, so it's
    562not normally something one needs to worry about.  Return values > 0 will be
    563mapped to zero in the VFS layer.
    564
    565->readdir() and ->ioctl() on directories must be changed. Ideally we would
    566move ->readdir() to inode_operations and use a separate method for directory
    567->ioctl() or kill the latter completely. One of the problems is that for
    568anything that resembles union-mount we won't have a struct file for all
    569components. And there are other reasons why the current interface is a mess...
    570
    571->read on directories probably must go away - we should just enforce -EISDIR
    572in sys_read() and friends.
    573
    574->setlease operations should call generic_setlease() before or after setting
    575the lease within the individual filesystem to record the result of the
    576operation
    577
    578->fallocate implementation must be really careful to maintain page cache
    579consistency when punching holes or performing other operations that invalidate
    580page cache contents. Usually the filesystem needs to call
    581truncate_inode_pages_range() to invalidate relevant range of the page cache.
    582However the filesystem usually also needs to update its internal (and on disk)
    583view of file offset -> disk block mapping. Until this update is finished, the
    584filesystem needs to block page faults and reads from reloading now-stale page
    585cache contents from the disk. Since VFS acquires mapping->invalidate_lock in
    586shared mode when loading pages from disk (filemap_fault(), filemap_read(),
    587readahead paths), the fallocate implementation must take the invalidate_lock to
    588prevent reloading.
    589
    590->copy_file_range and ->remap_file_range implementations need to serialize
    591against modifications of file data while the operation is running. For
    592blocking changes through write(2) and similar operations inode->i_rwsem can be
    593used. To block changes to file contents via a memory mapping during the
    594operation, the filesystem must take mapping->invalidate_lock to coordinate
    595with ->page_mkwrite.
    596
    597dquot_operations
    598================
    599
    600prototypes::
    601
    602	int (*write_dquot) (struct dquot *);
    603	int (*acquire_dquot) (struct dquot *);
    604	int (*release_dquot) (struct dquot *);
    605	int (*mark_dirty) (struct dquot *);
    606	int (*write_info) (struct super_block *, int);
    607
    608These operations are intended to be more or less wrapping functions that ensure
    609a proper locking wrt the filesystem and call the generic quota operations.
    610
    611What filesystem should expect from the generic quota functions:
    612
    613==============	============	=========================
    614ops		FS recursion	Held locks when called
    615==============	============	=========================
    616write_dquot:	yes		dqonoff_sem or dqptr_sem
    617acquire_dquot:	yes		dqonoff_sem or dqptr_sem
    618release_dquot:	yes		dqonoff_sem or dqptr_sem
    619mark_dirty:	no		-
    620write_info:	yes		dqonoff_sem
    621==============	============	=========================
    622
    623FS recursion means calling ->quota_read() and ->quota_write() from superblock
    624operations.
    625
    626More details about quota locking can be found in fs/dquot.c.
    627
    628vm_operations_struct
    629====================
    630
    631prototypes::
    632
    633	void (*open)(struct vm_area_struct*);
    634	void (*close)(struct vm_area_struct*);
    635	vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
    636	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
    637	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
    638	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
    639
    640locking rules:
    641
    642=============	=========	===========================
    643ops		mmap_lock	PageLocked(page)
    644=============	=========	===========================
    645open:		yes
    646close:		yes
    647fault:		yes		can return with page locked
    648map_pages:	yes
    649page_mkwrite:	yes		can return with page locked
    650pfn_mkwrite:	yes
    651access:		yes
    652=============	=========	===========================
    653
    654->fault() is called when a previously not present pte is about to be faulted
    655in. The filesystem must find and return the page associated with the passed in
    656"pgoff" in the vm_fault structure. If it is possible that the page may be
    657truncated and/or invalidated, then the filesystem must lock invalidate_lock,
    658then ensure the page is not already truncated (invalidate_lock will block
    659subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
    660locked. The VM will unlock the page.
    661
    662->map_pages() is called when VM asks to map easy accessible pages.
    663Filesystem should find and map pages associated with offsets from "start_pgoff"
    664till "end_pgoff". ->map_pages() is called with page table locked and must
    665not block.  If it's not possible to reach a page without blocking,
    666filesystem should skip it. Filesystem should use do_set_pte() to setup
    667page table entry. Pointer to entry associated with the page is passed in
    668"pte" field in vm_fault structure. Pointers to entries for other offsets
    669should be calculated relative to "pte".
    670
    671->page_mkwrite() is called when a previously read-only pte is about to become
    672writeable. The filesystem again must ensure that there are no
    673truncate/invalidate races or races with operations such as ->remap_file_range
    674or ->copy_file_range, and then return with the page locked. Usually
    675mapping->invalidate_lock is suitable for proper serialization. If the page has
    676been truncated, the filesystem should not look up a new page like the ->fault()
    677handler, but simply return with VM_FAULT_NOPAGE, which will cause the VM to
    678retry the fault.
    679
    680->pfn_mkwrite() is the same as page_mkwrite but when the pte is
    681VM_PFNMAP or VM_MIXEDMAP with a page-less entry. Expected return is
    682VM_FAULT_NOPAGE. Or one of the VM_FAULT_ERROR types. The default behavior
    683after this call is to make the pte read-write, unless pfn_mkwrite returns
    684an error.
    685
    686->access() is called when get_user_pages() fails in
    687access_process_vm(), typically used to debug a process through
    688/proc/pid/mem or ptrace.  This function is needed only for
    689VM_IO | VM_PFNMAP VMAs.
    690
    691--------------------------------------------------------------------------------
    692
    693			Dubious stuff
    694
    695(if you break something or notice that it is broken and do not fix it yourself
    696- at least put it here)