diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 256 |
1 files changed, 195 insertions, 61 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 534e652bd05f..d7ab4f96d705 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> @@ -79,7 +80,7 @@ struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; -struct fileattr; +struct file_kattr; struct iomap_ops; extern void __init inode_init(void); @@ -199,12 +200,12 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* * The two FMODE_NONOTIFY* define which fsnotify events should not be generated - * for a file. These are the possible values of (f->f_mode & - * FMODE_FSNOTIFY_MASK) and their meaning: + * for an open file. These are the possible values of + * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning: * * FMODE_NONOTIFY - suppress all (incl. non-permission) events. * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. - * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM. */ #define FMODE_FSNOTIFY_MASK \ (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) @@ -212,17 +213,16 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_FSNOTIFY_NONE(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS -#define FMODE_FSNOTIFY_PERM(mode) \ +#define FMODE_FSNOTIFY_HSM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) -#define FMODE_FSNOTIFY_HSM(mode) \ +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0) #else -#define FMODE_FSNOTIFY_PERM(mode) 0 +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0 #define FMODE_FSNOTIFY_HSM(mode) 0 #endif - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -399,7 +399,9 @@ struct readahead_control; { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ - { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } + { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }, \ + { IOCB_AIO_RW, "AIO_RW" }, \ + { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } struct kiocb { struct file *ki_filp; @@ -408,6 +410,7 @@ struct kiocb { void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ + u8 ki_write_stream; union { /* * Only used for async buffered reads, where it denotes the @@ -433,7 +436,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) } struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ @@ -444,10 +446,10 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); - int (*write_begin)(struct file *, struct address_space *mapping, + int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); - int (*write_end)(struct file *, struct address_space *mapping, + int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); @@ -524,7 +526,7 @@ struct address_space { /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit - * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. + * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ @@ -791,6 +793,8 @@ struct inode { static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { + VFS_WARN_ON_INODE(strlen(link) != linklen, inode); + VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; @@ -835,7 +839,7 @@ static inline void inode_fake_hash(struct inode *inode) } /* - * inode->i_mutex nesting subclasses for the lock validator: + * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent @@ -865,6 +869,11 @@ static inline void inode_lock(struct inode *inode) down_write(&inode->i_rwsem); } +static inline __must_check int inode_lock_killable(struct inode *inode) +{ + return down_write_killable(&inode->i_rwsem); +} + static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); @@ -875,6 +884,11 @@ static inline void inode_lock_shared(struct inode *inode) down_read(&inode->i_rwsem); } +static inline __must_check int inode_lock_shared_killable(struct inode *inode) +{ + return down_read_killable(&inode->i_rwsem); +} + static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); @@ -977,7 +991,7 @@ static inline loff_t i_size_read(const struct inode *inode) /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it - * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) @@ -1029,6 +1043,7 @@ struct fown_struct { * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. + * @order: Preferred folio order used for most recent readahead. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * @@ -1040,7 +1055,8 @@ struct file_ra_state { unsigned int size; unsigned int async_size; unsigned int ra_pages; - unsigned int mmap_miss; + unsigned short order; + unsigned short mmap_miss; loff_t prev_pos; }; @@ -1055,7 +1071,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations @@ -1065,12 +1080,12 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener + * @f_owner: file owner * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file - * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file @@ -1078,9 +1093,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) + * @f_ref: reference count */ struct file { - file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1090,6 +1105,7 @@ struct file { unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; + struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { @@ -1103,7 +1119,6 @@ struct file { void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ - struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL @@ -1115,6 +1130,7 @@ struct file { struct file_ra_state f_ra; freeptr_t f_freeptr; }; + file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1238,7 +1254,6 @@ extern int send_sigurg(struct file *file); /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) -#define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) @@ -1246,11 +1261,19 @@ extern int send_sigurg(struct file *file); #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ -#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) +#if IS_ENABLED(CONFIG_UNICODE) +#define sb_no_casefold_compat_fallback(sb) \ + (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) +#else +#define sb_no_casefold_compat_fallback(sb) (1) +#endif + /* * Umount options */ @@ -1297,6 +1320,7 @@ struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ + const void *freeze_owner; /* Owner of the freeze */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; @@ -1380,6 +1404,7 @@ struct super_block { char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; + unsigned int s_d_flags; /* default d_flags for dentries */ /* * The next field is for VFS *only*. No filesystems have any business @@ -1393,7 +1418,7 @@ struct super_block { */ const char *s_subtype; - const struct dentry_operations *s_d_op; /* default d_op for dentries */ + const struct dentry_operations *__s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ @@ -1770,7 +1795,7 @@ static inline void __sb_end_write(struct super_block *sb, int level) static inline void __sb_start_write(struct super_block *sb, int level) { - percpu_down_read(sb->s_writers.rw_sem + level - 1); + percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) @@ -1901,7 +1926,7 @@ static inline void sb_end_intwrite(struct super_block *sb) * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write - * -> i_mutex (write path, truncate, directory ops, ...) + * -> i_rwsem (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) @@ -1969,8 +1994,8 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap, */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, @@ -1984,20 +2009,20 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from - * @old_dir: parent of source + * @old_parent: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from - * @new_dir: parent of destination + * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; - struct inode *old_dir; + struct dentry *old_parent; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; - struct inode *new_dir; + struct dentry *new_parent; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; @@ -2027,7 +2052,7 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); -extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, @@ -2061,8 +2086,18 @@ typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, struct dir_context { filldir_t actor; loff_t pos; + /* + * Filesystems MUST NOT MODIFY count, but may use as a hint: + * 0 unknown + * > 0 space in buffer (assume at least one entry) + * INT_MAX unlimited + */ + int count; }; +/* If OR-ed with d_type, pending signals are not checked */ +#define FILLDIR_FLAG_NOINTR 0x1000 + /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -2159,6 +2194,7 @@ struct file_operations { int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); + int (*mmap_prepare)(struct vm_area_desc *); } __randomize_layout; /* Supports async buffered reads */ @@ -2199,8 +2235,8 @@ struct inode_operations { int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); @@ -2223,16 +2259,41 @@ struct inode_operations { int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, - struct dentry *dentry, struct fileattr *fa); - int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + struct dentry *dentry, struct file_kattr *fa); + int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; -static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +/* Did the driver provide valid mmap hook configuration? */ +static inline bool can_mmap_file(struct file *file) +{ + bool has_mmap = file->f_op->mmap; + bool has_mmap_prepare = file->f_op->mmap_prepare; + + /* Hooks are mutually exclusive. */ + if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) + return false; + if (!has_mmap && !has_mmap_prepare) + return false; + + return true; +} + +int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma); + +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { + if (file->f_op->mmap_prepare) + return compat_vma_mmap_prepare(file, vma); + return file->f_op->mmap(file, vma); } +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) +{ + return file->f_op->mmap_prepare(desc); +} + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, @@ -2259,6 +2320,7 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed + * @FREEZE_EXCL: a freeze that can only be undone by the owner * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. @@ -2272,6 +2334,7 @@ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), + FREEZE_EXCL = (1U << 3), }; struct super_operations { @@ -2285,9 +2348,9 @@ struct super_operations { void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_super) (struct super_block *, enum freeze_holder who); + int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*freeze_fs) (struct super_block *); - int (*thaw_super) (struct super_block *, enum freeze_holder who); + int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); @@ -2306,6 +2369,15 @@ struct super_operations { struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); + /* + * If a filesystem can support graceful removal of a device and + * continue read-write operations, implement this callback. + * + * Return 0 if the filesystem can continue read-write. + * Non-zero return value or no such callback means the fs will be shutdown + * as usual. + */ + int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); void (*shutdown)(struct super_block *sb); }; @@ -2334,6 +2406,7 @@ struct super_operations { #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ +#define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2390,6 +2463,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) +#define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) @@ -2604,6 +2678,7 @@ struct file_system_type { #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ +#define FS_LBS 128 /* FS supports LBS */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2641,9 +2716,6 @@ static inline bool is_mgtime(const struct inode *inode) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2697,8 +2769,10 @@ extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -int freeze_super(struct super_block *super, enum freeze_holder who); -int thaw_super(struct super_block *super, enum freeze_holder who); +int freeze_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); +int thaw_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2782,13 +2856,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) return mnt_idmap(mnt) != &nop_mnt_idmap; } -extern long vfs_truncate(const struct path *, loff_t); +int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); +int do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, @@ -2805,7 +2879,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); -struct path *backing_file_user_path(struct file *f); +struct path *backing_file_user_path(const struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file @@ -2817,14 +2891,14 @@ struct path *backing_file_user_path(struct file *f); * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ -static inline const struct path *file_user_path(struct file *f) +static inline const struct path *file_user_path(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ -static inline const struct inode *file_user_inode(struct file *f) +static inline const struct inode *file_user_inode(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); @@ -2839,7 +2913,10 @@ extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); -extern struct filename *getname(const char __user *); +static inline struct filename *getname(const char __user *name) +{ + return getname_flags(name, 0); +} extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) @@ -2852,6 +2929,13 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f return __getname_maybe_null(name); } extern void putname(struct filename *name); +DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) + +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); @@ -2926,6 +3010,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end); static inline int file_write_and_wait(struct file *file) { @@ -2958,6 +3044,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; @@ -3133,6 +3224,12 @@ static inline void exe_file_allow_write_access(struct file *exe_file) allow_write_access(exe_file); } +static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) +{ + file->f_mode &= ~FMODE_FSNOTIFY_MASK; + file->f_mode |= mode; +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3182,6 +3279,22 @@ static inline bool is_dot_dotdot(const char *name, size_t len) (len == 1 || (len == 2 && name[1] == '.')); } +/** + * name_contains_dotdot - check if a file name contains ".." path components + * + * Search for ".." surrounded by either '/' or start/end of string. + */ +static inline bool name_contains_dotdot(const char *name) +{ + size_t name_len; + + name_len = strlen(name); + return strcmp(name, "..") == 0 || + strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); +} + #include <linux/err.h> /* needed for stackable file system support */ @@ -3272,7 +3385,11 @@ static inline void __iget(struct inode *inode) extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode_pseudo(struct super_block *sb); +struct inode *alloc_inode(struct super_block *sb); +static inline struct inode *new_inode_pseudo(struct super_block *sb) +{ + return alloc_inode(sb); +} extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); @@ -3306,8 +3423,10 @@ extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); -extern int generic_file_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap_prepare(struct vm_area_desc *desc); +int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, @@ -3427,6 +3546,8 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); +extern const char *page_get_link_raw(struct dentry *, struct inode *, + struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); @@ -3438,7 +3559,8 @@ void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, - unsigned int unit_max); + unsigned int unit_max, + unsigned int unit_max_opt); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); @@ -3478,9 +3600,11 @@ extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); -extern void iterate_supers(void (*)(struct super_block *, void *), void *); +extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); +void filesystems_freeze(void); +void filesystems_thaw(void); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); @@ -3504,17 +3628,21 @@ extern int simple_rename(struct mnt_idmap *, struct inode *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); +extern void locked_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct folio **foliop, void **fsdata); +extern int simple_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); +struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, + const struct inode *context_inode); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); -extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); @@ -3528,6 +3656,7 @@ extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); +struct dentry *simple_start_creating(struct dentry *, const char *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); @@ -3629,9 +3758,14 @@ void setattr_copy(struct mnt_idmap *, struct inode *inode, extern int file_update_time(struct file *file); +static inline bool file_is_dax(const struct file *file) +{ + return file && IS_DAX(file->f_mapping->host); +} + static inline bool vma_is_dax(const struct vm_area_struct *vma) { - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); + return file_is_dax(vma->vm_file); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) |