path: root/Documentation/filesystems/Locking
diff options
Diffstat (limited to 'Documentation/filesystems/Locking')
1 files changed, 515 insertions, 0 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
new file mode 100644
index 00000000000..a934baeeb33
--- /dev/null
+++ b/Documentation/filesystems/Locking
@@ -0,0 +1,515 @@
+ The text below describes the locking rules for VFS-related methods.
+It is (believed to be) up-to-date. *Please*, if you change anything in
+prototypes or locking protocols - update this file. And update the relevant
+instances in the tree, don't leave that to maintainers of filesystems/devices/
+etc. At the very least, put the list of dubious cases in the end of this file.
+Don't turn it into log - maintainers of out-of-the-tree code are supposed to
+be able to use diff(1).
+ Thing currently missing here: socket operations. Alexey?
+--------------------------- dentry_operations --------------------------
+ int (*d_revalidate)(struct dentry *, int);
+ int (*d_hash) (struct dentry *, struct qstr *);
+ int (*d_compare) (struct dentry *, struct qstr *, struct qstr *);
+ int (*d_delete)(struct dentry *);
+ void (*d_release)(struct dentry *);
+ void (*d_iput)(struct dentry *, struct inode *);
+locking rules:
+ none have BKL
+ dcache_lock rename_lock ->d_lock may block
+d_revalidate: no no no yes
+d_hash no no no yes
+d_compare: no yes no no
+d_delete: yes no yes no
+d_release: no no no yes
+d_iput: no no no yes
+--------------------------- inode_operations ---------------------------
+ int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
+ struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid
+ata *);
+ int (*link) (struct dentry *,struct inode *,struct dentry *);
+ int (*unlink) (struct inode *,struct dentry *);
+ int (*symlink) (struct inode *,struct dentry *,const char *);
+ int (*mkdir) (struct inode *,struct dentry *,int);
+ int (*rmdir) (struct inode *,struct dentry *);
+ int (*mknod) (struct inode *,struct dentry *,int,dev_t);
+ int (*rename) (struct inode *, struct dentry *,
+ struct inode *, struct dentry *);
+ int (*readlink) (struct dentry *, char __user *,int);
+ int (*follow_link) (struct dentry *, struct nameidata *);
+ void (*truncate) (struct inode *);
+ int (*permission) (struct inode *, int, struct nameidata *);
+ int (*setattr) (struct dentry *, struct iattr *);
+ int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
+ int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
+ ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
+ ssize_t (*listxattr) (struct dentry *, char *, size_t);
+ int (*removexattr) (struct dentry *, const char *);
+locking rules:
+ all may block, none have BKL
+ i_sem(inode)
+lookup: yes
+create: yes
+link: yes (both)
+mknod: yes
+symlink: yes
+mkdir: yes
+unlink: yes (both)
+rmdir: yes (both) (see below)
+rename: yes (all) (see below)
+readlink: no
+follow_link: no
+truncate: yes (see below)
+setattr: yes
+permission: no
+getattr: no
+setxattr: yes
+getxattr: no
+listxattr: no
+removexattr: yes
+ Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_sem on
+ cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+ ->truncate() is never called directly - it's a callback, not a
+method. It's called by vmtruncate() - library function normally used by
+->setattr(). Locking information above applies to that call (i.e. is
+inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
+See Documentation/filesystems/directory-locking for more detailed discussion
+of the locking scheme for directory operations.
+--------------------------- super_operations ---------------------------
+ struct inode *(*alloc_inode)(struct super_block *sb);
+ void (*destroy_inode)(struct inode *);
+ void (*read_inode) (struct inode *);
+ void (*dirty_inode) (struct inode *);
+ int (*write_inode) (struct inode *, int);
+ void (*put_inode) (struct inode *);
+ void (*drop_inode) (struct inode *);
+ void (*delete_inode) (struct inode *);
+ void (*put_super) (struct super_block *);
+ void (*write_super) (struct super_block *);
+ int (*sync_fs)(struct super_block *sb, int wait);
+ void (*write_super_lockfs) (struct super_block *);
+ void (*unlockfs) (struct super_block *);
+ int (*statfs) (struct super_block *, struct kstatfs *);
+ int (*remount_fs) (struct super_block *, int *, char *);
+ void (*clear_inode) (struct inode *);
+ void (*umount_begin) (struct super_block *);
+ int (*show_options)(struct seq_file *, struct vfsmount *);
+ ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
+ ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+locking rules:
+ All may block.
+ BKL s_lock s_umount
+alloc_inode: no no no
+destroy_inode: no
+read_inode: no (see below)
+dirty_inode: no (must not sleep)
+write_inode: no
+put_inode: no
+drop_inode: no !!!inode_lock!!!
+delete_inode: no
+put_super: yes yes no
+write_super: no yes read
+sync_fs: no no read
+write_super_lockfs: ?
+unlockfs: ?
+statfs: no no no
+remount_fs: no yes maybe (see below)
+clear_inode: no
+umount_begin: yes no no
+show_options: no (vfsmount->sem)
+quota_read: no no no (see below)
+quota_write: no no no (see below)
+->read_inode() is not a method - it's a callback used in iget().
+->remount_fs() will have the s_umount lock if it's already mounted.
+When called from get_sb_single, it does NOT have the s_umount lock.
+->quota_read() and ->quota_write() functions are both guaranteed to
+be the only ones operating on the quota file by the quota code (via
+dqio_sem) (unless an admin really wants to screw up something and
+writes to quota files with quotas on). For other details about locking
+see also dquot_operations section.
+--------------------------- file_system_type ---------------------------
+ struct super_block *(*get_sb) (struct file_system_type *, int,
+ const char *, void *);
+ void (*kill_sb) (struct super_block *);
+locking rules:
+ may block BKL
+get_sb yes yes
+kill_sb yes yes
+->get_sb() returns error or a locked superblock (exclusive on ->s_umount).
+->kill_sb() takes a write-locked superblock, does all shutdown work on it,
+unlocks and drops the reference.
+--------------------------- address_space_operations --------------------------
+ int (*writepage)(struct page *page, struct writeback_control *wbc);
+ int (*readpage)(struct file *, struct page *);
+ int (*sync_page)(struct page *);
+ int (*writepages)(struct address_space *, struct writeback_control *);
+ int (*set_page_dirty)(struct page *page);
+ int (*readpages)(struct file *filp, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages);
+ int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
+ int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
+ sector_t (*bmap)(struct address_space *, sector_t);
+ int (*invalidatepage) (struct page *, unsigned long);
+ int (*releasepage) (struct page *, int);
+ int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
+ loff_t offset, unsigned long nr_segs);
+locking rules:
+ All except set_page_dirty may block
+ BKL PageLocked(page)
+writepage: no yes, unlocks (see below)
+readpage: no yes, unlocks
+sync_page: no maybe
+writepages: no
+set_page_dirty no no
+readpages: no
+prepare_write: no yes
+commit_write: no yes
+bmap: yes
+invalidatepage: no yes
+releasepage: no yes
+direct_IO: no
+ ->prepare_write(), ->commit_write(), ->sync_page() and ->readpage()
+may be called from the request handler (/dev/loop).
+ ->readpage() unlocks the page, either synchronously or via I/O
+ ->readpages() populates the pagecache with the passed pages and starts
+I/O against them. They come unlocked upon I/O completion.
+ ->writepage() is used for two purposes: for "memory cleansing" and for
+"sync". These are quite different operations and the behaviour may differ
+depending upon the mode.
+If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then
+it *must* start I/O against the page, even if that would involve
+blocking on in-progress I/O.
+If writepage is called for memory cleansing (sync_mode ==
+WBC_SYNC_NONE) then its role is to get as much writeout underway as
+possible. So writepage should try to avoid blocking against
+currently-in-progress I/O.
+If the filesystem is not called for "sync" and it determines that it
+would need to block against in-progress I/O to be able to start new I/O
+against the page the filesystem should redirty the page with
+redirty_page_for_writepage(), then unlock the page and return zero.
+This may also be done to avoid internal deadlocks, but rarely.
+If the filesytem is called for sync then it must wait on any
+in-progress I/O and then start new I/O.
+The filesystem should unlock the page synchronously, before returning
+to the caller.
+Unless the filesystem is going to redirty_page_for_writepage(), unlock the page
+and return zero, writepage *must* run set_page_writeback() against the page,
+followed by unlocking it. Once set_page_writeback() has been run against the
+page, write I/O can be submitted and the write I/O completion handler must run
+end_page_writeback() once the I/O is complete. If no I/O is submitted, the
+filesystem must run end_page_writeback() against the page before returning from
+That is: after 2.5.12, pages which are under writeout are *not* locked. Note,
+if the filesystem needs the page to be locked during writeout, that is ok, too,
+the page is allowed to be unlocked at any point in time between the calls to
+set_page_writeback() and end_page_writeback().
+Note, failure to run either redirty_page_for_writepage() or the combination of
+set_page_writeback()/end_page_writeback() on a page submitted to writepage
+will leave the page itself marked clean but it will be tagged as dirty in the
+radix tree. This incoherency can lead to all sorts of hard-to-debug problems
+in the filesystem like having dirty inodes at umount and losing written data.
+ ->sync_page() locking rules are not well-defined - usually it is called
+with lock on page, but that is not guaranteed. Considering the currently
+existing instances of this method ->sync_page() itself doesn't look
+ ->writepages() is used for periodic writeback and for syscall-initiated
+sync operations. The address_space should start I/O against at least
+*nr_to_write pages. *nr_to_write must be decremented for each page which is
+written. The address_space implementation may write more (or less) pages
+than *nr_to_write asks for, but it should try to be reasonably close. If
+nr_to_write is NULL, all dirty pages must be written.
+writepages should _only_ write pages which are present on
+ ->set_page_dirty() is called from various places in the kernel
+when the target page is marked as needing writeback. It may be called
+under spinlock (it cannot block) and is sometimes called with the page
+not locked.
+ ->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
+filesystems and by the swapper. The latter will eventually go away. All
+instances do not actually need the BKL. Please, keep it that way and don't
+breed new callers.
+ ->invalidatepage() is called when the filesystem must attempt to drop
+some or all of the buffers from the page when it is being truncated. It
+returns zero on success. If ->invalidatepage is zero, the kernel uses
+block_invalidatepage() instead.
+ ->releasepage() is called when the kernel is about to try to drop the
+buffers from the page in preparation for freeing it. It returns zero to
+indicate that the buffers are (or may be) freeable. If ->releasepage is zero,
+the kernel assumes that the fs has no private interest in the buffers.
+ Note: currently almost all instances of address_space methods are
+using BKL for internal serialization and that's one of the worst sources
+of contention. Normally they are calling library functions (in fs/buffer.c)
+and pass foo_get_block() as a callback (on local block-based filesystems,
+indeed). BKL is not needed for library stuff and is usually taken by
+foo_get_block(). It's an overkill, since block bitmaps can be protected by
+internal fs locking and real critical areas are much smaller than the areas
+filesystems protect now.
+----------------------- file_lock_operations ------------------------------
+ void (*fl_insert)(struct file_lock *); /* lock insertion callback */
+ void (*fl_remove)(struct file_lock *); /* lock removal callback */
+ void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
+ void (*fl_release_private)(struct file_lock *);
+locking rules:
+ BKL may block
+fl_insert: yes no
+fl_remove: yes no
+fl_copy_lock: yes no
+fl_release_private: yes yes
+----------------------- lock_manager_operations ---------------------------
+ int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
+ void (*fl_notify)(struct file_lock *); /* unblock callback */
+ void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
+ void (*fl_release_private)(struct file_lock *);
+ void (*fl_break)(struct file_lock *); /* break_lease callback */
+locking rules:
+ BKL may block
+fl_compare_owner: yes no
+fl_notify: yes no
+fl_copy_lock: yes no
+fl_release_private: yes yes
+fl_break: yes no
+ Currently only NFSD and NLM provide instances of this class. None of the
+them block. If you have out-of-tree instances - please, show up. Locking
+in that area will change.
+--------------------------- buffer_head -----------------------------------
+ void (*b_end_io)(struct buffer_head *bh, int uptodate);
+locking rules:
+ called from interrupts. In other words, extreme care is needed here.
+bh is locked, but that's all warranties we have here. Currently only RAID1,
+highmem, fs/buffer.c, and fs/ntfs/aops.c are providing these. Block devices
+call this method upon the IO completion.
+--------------------------- block_device_operations -----------------------
+ int (*open) (struct inode *, struct file *);
+ int (*release) (struct inode *, struct file *);
+ int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+ int (*media_changed) (struct gendisk *);
+ int (*revalidate_disk) (struct gendisk *);
+locking rules:
+ BKL bd_sem
+open: yes yes
+release: yes yes
+ioctl: yes no
+media_changed: no no
+revalidate_disk: no no
+The last two are called only from check_disk_change().
+--------------------------- file_operations -------------------------------
+ loff_t (*llseek) (struct file *, loff_t, int);
+ ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
+ ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t);
+ ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
+ ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t,
+ loff_t);
+ int (*readdir) (struct file *, void *, filldir_t);
+ unsigned int (*poll) (struct file *, struct poll_table_struct *);
+ int (*ioctl) (struct inode *, struct file *, unsigned int,
+ unsigned long);
+ long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
+ long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
+ int (*mmap) (struct file *, struct vm_area_struct *);
+ int (*open) (struct inode *, struct file *);
+ int (*flush) (struct file *);
+ int (*release) (struct inode *, struct file *);
+ int (*fsync) (struct file *, struct dentry *, int datasync);
+ int (*aio_fsync) (struct kiocb *, int datasync);
+ int (*fasync) (int, struct file *, int);
+ int (*lock) (struct file *, int, struct file_lock *);
+ ssize_t (*readv) (struct file *, const struct iovec *, unsigned long,
+ loff_t *);
+ ssize_t (*writev) (struct file *, const struct iovec *, unsigned long,
+ loff_t *);
+ ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t,
+ void __user *);
+ ssize_t (*sendpage) (struct file *, struct page *, int, size_t,
+ loff_t *, int);
+ unsigned long (*get_unmapped_area)(struct file *, unsigned long,
+ unsigned long, unsigned long, unsigned long);
+ int (*check_flags)(int);
+ int (*dir_notify)(struct file *, unsigned long);
+locking rules:
+ All except ->poll() may block.
+llseek: no (see below)
+read: no
+aio_read: no
+write: no
+aio_write: no
+readdir: no
+poll: no
+ioctl: yes (see below)
+unlocked_ioctl: no (see below)
+compat_ioctl: no
+mmap: no
+open: maybe (see below)
+flush: no
+release: no
+fsync: no (see below)
+aio_fsync: no
+fasync: yes (see below)
+lock: yes
+readv: no
+writev: no
+sendfile: no
+sendpage: no
+get_unmapped_area: no
+check_flags: no
+dir_notify: no
+->llseek() locking has moved from llseek to the individual llseek
+implementations. If your fs is not using generic_file_llseek, you
+need to acquire and release the appropriate locks in your ->llseek().
+For many filesystems, it is probably safe to acquire the inode
+semaphore. Note some filesystems (i.e. remote ones) provide no
+protection for i_size so you will need to use the BKL.
+->open() locking is in-transit: big lock partially moved into the methods.
+The only exception is ->open() in the instances of file_operations that never
+end up in ->i_fop/->proc_fops, i.e. ones that belong to character devices
+(chrdev_open() takes lock before replacing ->f_op and calling the secondary
+method. As soon as we fix the handling of module reference counters all
+instances of ->open() will be called without the BKL.
+Note: ext2_release() was *the* source of contention on fs-intensive
+loads and dropping BKL on ->release() helps to get rid of that (we still
+grab BKL for cases when we close a file that had been opened r/w, but that
+can and should be done using the internal locking with smaller critical areas).
+Current worst offender is ext2_get_block()...
+->fasync() is a mess. This area needs a big cleanup and that will probably
+affect locking.
+->readdir() and ->ioctl() on directories must be changed. Ideally we would
+move ->readdir() to inode_operations and use a separate method for directory
+->ioctl() or kill the latter completely. One of the problems is that for
+anything that resembles union-mount we won't have a struct file for all
+components. And there are other reasons why the current interface is a mess...
+->ioctl() on regular files is superceded by the ->unlocked_ioctl() that
+doesn't take the BKL.
+->read on directories probably must go away - we should just enforce -EISDIR
+in sys_read() and friends.
+->fsync() has i_sem on inode.
+--------------------------- dquot_operations -------------------------------
+ int (*initialize) (struct inode *, int);
+ int (*drop) (struct inode *);
+ int (*alloc_space) (struct inode *, qsize_t, int);
+ int (*alloc_inode) (const struct inode *, unsigned long);
+ int (*free_space) (struct inode *, qsize_t);
+ int (*free_inode) (const struct inode *, unsigned long);
+ int (*transfer) (struct inode *, struct iattr *);
+ int (*write_dquot) (struct dquot *);
+ int (*acquire_dquot) (struct dquot *);
+ int (*release_dquot) (struct dquot *);
+ int (*mark_dirty) (struct dquot *);
+ int (*write_info) (struct super_block *, int);
+These operations are intended to be more or less wrapping functions that ensure
+a proper locking wrt the filesystem and call the generic quota operations.
+What filesystem should expect from the generic quota functions:
+ FS recursion Held locks when called
+initialize: yes maybe dqonoff_sem
+drop: yes -
+alloc_space: ->mark_dirty() -
+alloc_inode: ->mark_dirty() -
+free_space: ->mark_dirty() -
+free_inode: ->mark_dirty() -
+transfer: yes -
+write_dquot: yes dqonoff_sem or dqptr_sem
+acquire_dquot: yes dqonoff_sem or dqptr_sem
+release_dquot: yes dqonoff_sem or dqptr_sem
+mark_dirty: no -
+write_info: yes dqonoff_sem
+FS recursion means calling ->quota_read() and ->quota_write() from superblock
+->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
+only directly by the filesystem and do not call any fs functions only
+the ->mark_dirty() operation.
+More details about quota locking can be found in fs/dquot.c.
+--------------------------- vm_operations_struct -----------------------------
+ void (*open)(struct vm_area_struct*);
+ void (*close)(struct vm_area_struct*);
+ struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
+locking rules:
+ BKL mmap_sem
+open: no yes
+close: no yes
+nopage: no yes
+ Dubious stuff
+(if you break something or notice that it is broken and do not fix it yourself
+- at least put it here)
+ipc/shm.c::shm_delete() - may need BKL.
+->read() and ->write() in many drivers are (probably) missing BKL.
+drivers/sgi/char/graphics.c::sgi_graphics_nopage() - may need BKL.