528 lines
21 KiB
Plaintext
528 lines
21 KiB
Plaintext
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 --------------------------
|
|
prototypes:
|
|
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 ---------------------------
|
|
prototypes:
|
|
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
|
|
victim.
|
|
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
|
|
passed).
|
|
|
|
See Documentation/filesystems/directory-locking for more detailed discussion
|
|
of the locking scheme for directory operations.
|
|
|
|
--------------------------- super_operations ---------------------------
|
|
prototypes:
|
|
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 dentry *, 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: yes 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 ---------------------------
|
|
prototypes:
|
|
int (*get_sb) (struct file_system_type *, int,
|
|
const char *, void *, struct vfsmount *);
|
|
void (*kill_sb) (struct super_block *);
|
|
locking rules:
|
|
may block BKL
|
|
get_sb yes yes
|
|
kill_sb yes yes
|
|
|
|
->get_sb() returns error or 0 with locked superblock attached to the vfsmount
|
|
(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 --------------------------
|
|
prototypes:
|
|
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);
|
|
int (*launder_page) (struct page *);
|
|
|
|
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
|
|
launder_page: no yes
|
|
|
|
->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
|
|
completion.
|
|
|
|
->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 ->writepage() returns special WRITEPAGE_ACTIVATE
|
|
value. WRITEPAGE_ACTIVATE means that page cannot really be written out
|
|
currently, and VM should stop calling ->writepage() on this page for some
|
|
time. VM does this by moving page to the head of the active list, hence the
|
|
name.
|
|
|
|
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
|
|
writepage.
|
|
|
|
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
|
|
well-defined...
|
|
|
|
->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
|
|
mapping->io_pages.
|
|
|
|
->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.
|
|
|
|
->launder_page() may be called prior to releasing a page if
|
|
it is still found to be dirty. It returns zero if the page was successfully
|
|
cleaned, or an error value if not. Note that in order to prevent the page
|
|
getting mapped back in and redirtied, it needs to be kept locked
|
|
across the entire operation.
|
|
|
|
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 ------------------------------
|
|
prototypes:
|
|
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 ---------------------------
|
|
prototypes:
|
|
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 -----------------------------------
|
|
prototypes:
|
|
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 -----------------------
|
|
prototypes:
|
|
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 -------------------------------
|
|
prototypes:
|
|
loff_t (*llseek) (struct file *, loff_t, int);
|
|
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
|
|
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
|
|
ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
|
|
ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, 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.
|
|
BKL
|
|
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 -------------------------------
|
|
prototypes:
|
|
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
|
|
operations.
|
|
|
|
->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 -----------------------------
|
|
prototypes:
|
|
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.
|