diff options
Diffstat (limited to 'Documentation/filesystems/Locking')
| -rw-r--r-- | Documentation/filesystems/Locking | 534 |
1 files changed, 534 insertions, 0 deletions
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking new file mode 100644 index 00000000..57d827d6 --- /dev/null +++ b/Documentation/filesystems/Locking @@ -0,0 +1,534 @@ + 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 *, struct nameidata *); + int (*d_hash)(const struct dentry *, const struct inode *, + struct qstr *); + int (*d_compare)(const struct dentry *, const struct inode *, + const struct dentry *, const struct inode *, + unsigned int, const char *, const struct qstr *); + int (*d_delete)(struct dentry *); + void (*d_release)(struct dentry *); + void (*d_iput)(struct dentry *, struct inode *); + char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); + struct vfsmount *(*d_automount)(struct path *path); + int (*d_manage)(struct dentry *, bool); + +locking rules: + rename_lock ->d_lock may block rcu-walk +d_revalidate: no no yes (ref-walk) maybe +d_hash no no no maybe +d_compare: yes no no maybe +d_delete: no yes no no +d_release: no no yes no +d_iput: no no yes no +d_dname: no no no no +d_automount: no no yes no +d_manage: no no yes (ref-walk) maybe + +--------------------------- 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); + void * (*follow_link) (struct dentry *, struct nameidata *); + void (*put_link) (struct dentry *, struct nameidata *, void *); + void (*truncate) (struct inode *); + int (*permission) (struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int, unsigned int); + 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 *); + void (*truncate_range)(struct inode *, loff_t, loff_t); + int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); + +locking rules: + all may block + i_mutex(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 +put_link: no +truncate: yes (see below) +setattr: yes +permission: no (may not block if called in rcu-walk mode) +check_acl: no +getattr: no +setxattr: yes +getxattr: no +listxattr: no +removexattr: yes +truncate_range: yes +fiemap: no + Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex 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() - deprecated library function 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 (*dirty_inode) (struct inode *, int flags); + int (*write_inode) (struct inode *, struct writeback_control *wbc); + int (*drop_inode) (struct inode *); + void (*evict_inode) (struct inode *); + void (*put_super) (struct super_block *); + void (*write_super) (struct super_block *); + int (*sync_fs)(struct super_block *sb, int wait); + int (*freeze_fs) (struct super_block *); + int (*unfreeze_fs) (struct super_block *); + int (*statfs) (struct dentry *, struct kstatfs *); + int (*remount_fs) (struct super_block *, int *, char *); + 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); + int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); + +locking rules: + All may block [not true, see below] + s_umount +alloc_inode: +destroy_inode: +dirty_inode: +write_inode: +drop_inode: !!!inode->i_lock!!! +evict_inode: +put_super: write +write_super: read +sync_fs: read +freeze_fs: read +unfreeze_fs: read +statfs: maybe(read) (see below) +remount_fs: write +umount_begin: no +show_options: no (namespace_sem) +quota_read: no (see below) +quota_write: no (see below) +bdev_try_to_free_page: no (see below) + +->statfs() has s_umount (shared) when called by ustat(2) (native or +compat), but that's an accident of bad API; s_umount is used to pin +the superblock down when we only have dev_t given us by userland to +identify the superblock. Everything else (statfs(), fstatfs(), etc.) +doesn't hold it when calling ->statfs() - superblock is pinned down +by resolving the pathname passed to syscall. +->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. +->bdev_try_to_free_page is called from the ->releasepage handler of +the block device inode. See there for more details. + +--------------------------- file_system_type --------------------------- +prototypes: + int (*get_sb) (struct file_system_type *, int, + const char *, void *, struct vfsmount *); + struct dentry *(*mount) (struct file_system_type *, int, + const char *, void *); + void (*kill_sb) (struct super_block *); +locking rules: + may block +mount yes +kill_sb yes + +->mount() returns ERR_PTR or the root dentry; its superblock should be locked +on return. +->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 (*write_begin)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); + int (*write_end)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); + sector_t (*bmap)(struct address_space *, sector_t); + int (*invalidatepage) (struct page *, unsigned long); + int (*releasepage) (struct page *, int); + void (*freepage)(struct page *); + int (*direct_IO)(int, struct kiocb *, const struct iovec *iov, + loff_t offset, unsigned long nr_segs); + int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, + unsigned long *); + int (*migratepage)(struct address_space *, struct page *, struct page *); + int (*launder_page)(struct page *); + int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long); + int (*error_remove_page)(struct address_space *, struct page *); + +locking rules: + All except set_page_dirty and freepage may block + + PageLocked(page) i_mutex +writepage: yes, unlocks (see below) +readpage: yes, unlocks +sync_page: maybe +writepages: +set_page_dirty no +readpages: +write_begin: locks the page yes +write_end: yes, unlocks yes +bmap: +invalidatepage: yes +releasepage: yes +freepage: yes +direct_IO: +get_xip_mem: maybe +migratepage: yes (both) +launder_page: yes +is_partially_uptodate: yes +error_remove_page: yes + + ->write_begin(), ->write_end(), ->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 filesystem 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. 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. + + ->freepage() is called when the kernel is done dropping the page +from the page cache. + + ->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. + +----------------------- file_lock_operations ------------------------------ +prototypes: + void (*fl_copy_lock)(struct file_lock *, struct file_lock *); + void (*fl_release_private)(struct file_lock *); + + +locking rules: + file_lock_lock may block +fl_copy_lock: yes no +fl_release_private: maybe no + +----------------------- lock_manager_operations --------------------------- +prototypes: + int (*fl_compare_owner)(struct file_lock *, struct file_lock *); + void (*fl_notify)(struct file_lock *); /* unblock callback */ + int (*fl_grant)(struct file_lock *, struct file_lock *, int); + void (*fl_release_private)(struct file_lock *); + void (*fl_break)(struct file_lock *); /* break_lease callback */ + int (*fl_change)(struct file_lock **, int); + +locking rules: + file_lock_lock may block +fl_compare_owner: yes no +fl_notify: yes no +fl_grant: no no +fl_release_private: maybe no +fl_break: yes no +fl_change yes no + +--------------------------- 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 block_device *, fmode_t); + int (*release) (struct gendisk *, fmode_t); + int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); + int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); + int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); + int (*media_changed) (struct gendisk *); + void (*unlock_native_capacity) (struct gendisk *); + int (*revalidate_disk) (struct gendisk *); + int (*getgeo)(struct block_device *, struct hd_geometry *); + void (*swap_slot_free_notify) (struct block_device *, unsigned long); + +locking rules: + bd_mutex +open: yes +release: yes +ioctl: no +compat_ioctl: no +direct_access: no +media_changed: no +unlock_native_capacity: no +revalidate_disk: no +getgeo: no +swap_slot_free_notify: no (see below) + +media_changed, unlock_native_capacity and revalidate_disk are called only from +check_disk_change(). + +swap_slot_free_notify is called with swap_lock and sometimes the page lock +held. + + +--------------------------- 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 *); + 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 *, 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 (*flock) (struct file *, int, struct file_lock *); + ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, + size_t, unsigned int); + ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, + size_t, unsigned int); + int (*setlease)(struct file *, long, struct file_lock **); + long (*fallocate)(struct file *, int, loff_t, loff_t); +}; + +locking rules: + All may block except for ->setlease. + No VFS locks held on entry except for ->fsync and ->setlease. + +->fsync() has i_mutex on inode. + +->setlease has the file_list_lock held and must not sleep. + +->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 +mutex or just to use i_size_read() instead. +Note: this does not protect the file->f_pos against concurrent modifications +since this is something the userspace has to take care about. + +->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. +Most instances call fasync_helper(), which does that maintenance, so it's +not normally something one needs to worry about. Return values > 0 will be +mapped to zero in the VFS layer. + +->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... + +->read on directories probably must go away - we should just enforce -EISDIR +in sys_read() and friends. + +--------------------------- dquot_operations ------------------------------- +prototypes: + 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 +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. + +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*); + int (*fault)(struct vm_area_struct*, struct vm_fault *); + int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); + int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); + +locking rules: + mmap_sem PageLocked(page) +open: yes +close: yes +fault: yes can return with page locked +page_mkwrite: yes can return with page locked +access: yes + + ->fault() is called when a previously not present pte is about +to be faulted in. The filesystem must find and return the page associated +with the passed in "pgoff" in the vm_fault structure. If it is possible that +the page may be truncated and/or invalidated, then the filesystem must lock +the page, then ensure it is not already truncated (the page lock will block +subsequent truncate), and then return with VM_FAULT_LOCKED, and the page +locked. The VM will unlock the page. + + ->page_mkwrite() is called when a previously read-only pte is +about to become writeable. The filesystem again must ensure that there are +no truncate/invalidate races, and then return with the page locked. If +the page has been truncated, the filesystem should not look up a new page +like the ->fault() handler, but simply return with VM_FAULT_NOPAGE, which +will cause the VM to retry the fault. + + ->access() is called when get_user_pages() fails in +acces_process_vm(), typically used to debug a process through +/proc/pid/mem or ptrace. This function is needed only for +VM_IO | VM_PFNMAP VMAs. + +================================================================================ + Dubious stuff + +(if you break something or notice that it is broken and do not fix it yourself +- at least put it here) |