diff options
Diffstat (limited to 'Documentation/filesystems/locking.rst')
-rw-r--r-- | Documentation/filesystems/locking.rst | 109 |
1 files changed, 65 insertions, 44 deletions
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 4bb2627026ec..e664061ed55d 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -29,7 +29,7 @@ prototypes:: char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen); struct vfsmount *(*d_automount)(struct path *path); int (*d_manage)(const struct path *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *); + struct dentry *(*d_real)(struct dentry *, enum d_real_type type); locking rules: @@ -56,40 +56,43 @@ inode_operations prototypes:: - int (*create) (struct inode *,struct dentry *,umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); 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 *,umode_t); + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,const char *); + int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t,dev_t); + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); const char *(*get_link) (struct dentry *, struct inode *, struct delayed_call *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int, unsigned int); - struct posix_acl * (*get_acl)(struct inode *, int, bool); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*permission) (struct mnt_idmap *, struct inode *, int, unsigned int); + struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); void (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*fileattr_set)(struct user_namespace *mnt_userns, + int (*tmpfile) (struct mnt_idmap *, struct inode *, + struct file *, umode_t); + int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int); + struct offset_ctx *(*get_offset_ctx)(struct inode *inode); locking rules: all may block -============= ============================================= +============== ================================================== ops i_rwsem(inode) -============= ============================================= +============== ================================================== lookup: shared create: exclusive link: exclusive (both) @@ -98,11 +101,12 @@ symlink: exclusive mkdir: exclusive unlink: exclusive (both) rmdir: exclusive (both)(see below) -rename: exclusive (all) (see below) +rename: exclusive (both parents, some children) (see below) readlink: no get_link: no setattr: exclusive permission: no (may not block if called in rcu-walk mode) +get_inode_acl: no get_acl: no getattr: no listxattr: no @@ -112,12 +116,16 @@ atomic_open: shared (exclusive if O_CREAT is set in open flags) tmpfile: no fileattr_get: no or exclusive fileattr_set: exclusive -============= ============================================= +get_offset_ctx no +============== ================================================== Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem exclusive on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + ->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories + involved. + ->rename() has ->i_rwsem exclusive on any subdirectory that changes parent. See Documentation/filesystems/directory-locking.rst for more detailed discussion of the locking scheme for directory operations. @@ -132,7 +140,7 @@ prototypes:: struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); @@ -256,7 +264,7 @@ prototypes:: struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count); - int (*error_remove_page)(struct address_space *, struct page *); + int (*error_remove_folio)(struct address_space *, struct folio *); int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span) int (*swap_deactivate)(struct file *); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); @@ -282,7 +290,7 @@ direct_IO: migrate_folio: yes (both) launder_folio: yes is_partially_uptodate: yes -error_remove_page: yes +error_remove_folio: yes swap_activate: no swap_deactivate: no swap_rw: yes, unlocks @@ -371,10 +379,17 @@ invalidate_lock before invalidating page cache in truncate / hole punch path (and thus calling into ->invalidate_folio) to block races between page cache invalidation and page cache filling functions (fault, read, ...). -->release_folio() is called when the kernel is about to try to drop the -buffers from the folio in preparation for freeing it. It returns false to -indicate that the buffers are (or may be) freeable. If ->release_folio is -NULL, the kernel assumes that the fs has no private interest in the buffers. +->release_folio() is called when the MM wants to make a change to the +folio that would invalidate the filesystem's private data. For example, +it may be about to be removed from the address_space or split. The folio +is locked and not under writeback. It may be dirty. The gfp parameter +is not usually used for allocation, but rather to indicate what the +filesystem may do to attempt to free the private data. The filesystem may +return false to indicate that the folio's private data cannot be freed. +If it returns true, it should have already removed the private data from +the folio. If a filesystem does not provide a ->release_folio method, +the pagecache will assume that private data is buffer_heads and call +try_to_free_buffers(). ->free_folio() is called when the kernel has dropped the folio from the page cache. @@ -506,7 +521,6 @@ prototypes:: ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll) (struct kiocb *kiocb, bool spin); - int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); @@ -518,8 +532,6 @@ prototypes:: int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - 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); @@ -550,9 +562,8 @@ 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. -->iterate() is called with i_rwsem exclusive. - -->iterate_shared() is called with i_rwsem at least shared. +->iterate_shared() is called with i_rwsem held for reading, and with the +file f_pos_lock held exclusively ->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags. Most instances call fasync_helper(), which does that maintenance, so it's @@ -627,26 +638,29 @@ vm_operations_struct prototypes:: - void (*open)(struct vm_area_struct*); - void (*close)(struct vm_area_struct*); - vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *); + void (*open)(struct vm_area_struct *); + void (*close)(struct vm_area_struct *); + vm_fault_t (*fault)(struct vm_fault *); + vm_fault_t (*huge_fault)(struct vm_fault *, unsigned int order); + vm_fault_t (*map_pages)(struct vm_fault *, pgoff_t start, pgoff_t end); vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *); vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *); int (*access)(struct vm_area_struct *, unsigned long, void*, int, int); locking rules: -============= ========= =========================== +============= ========== =========================== ops mmap_lock PageLocked(page) -============= ========= =========================== -open: yes -close: yes -fault: yes can return with page locked -map_pages: yes -page_mkwrite: yes can return with page locked -pfn_mkwrite: yes -access: yes -============= ========= =========================== +============= ========== =========================== +open: write +close: read/write +fault: read can return with page locked +huge_fault: maybe-read +map_pages: maybe-read +page_mkwrite: read can return with page locked +pfn_mkwrite: read +access: read +============= ========== =========================== ->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 @@ -656,11 +670,18 @@ then ensure the page is not already truncated (invalidate_lock will block subsequent truncate), and then return with VM_FAULT_LOCKED, and the page locked. The VM will unlock the page. +->huge_fault() is called when there is no PUD or PMD entry present. This +gives the filesystem the opportunity to install a PUD or PMD sized page. +Filesystems can also use the ->fault method to return a PMD sized page, +so implementing this function may not be necessary. In particular, +filesystems should not call filemap_fault() from ->huge_fault(). +The mmap_lock may not be held when this method is called. + ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "start_pgoff" -till "end_pgoff". ->map_pages() is called with page table locked and must +till "end_pgoff". ->map_pages() is called with the RCU lock held and must not block. If it's not possible to reach a page without blocking, -filesystem should skip it. Filesystem should use do_set_pte() to setup +filesystem should skip it. Filesystem should use set_pte_range() to setup page table entry. Pointer to entry associated with the page is passed in "pte" field in vm_fault structure. Pointers to entries for other offsets should be calculated relative to "pte". |