diff options
54 files changed, 316 insertions, 174 deletions
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 08d01bc62c31..c274c5eef733 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -61,7 +61,7 @@ inode_operations prototypes:: - int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,umode_t); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index d13f0a23c882..02522fbfd968 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1401,3 +1401,11 @@ as with d_dispose_if_unused() these are not trivial; with this variant of API it's more explicit, since grabbing ->d_lock is caller-side, but d_dispose_if_unused() had all the same issues. It's a low-level primitive; use only if you have no alternative. + +--- + +**mandatory** + +The .create inode_operation no longer receives the 'excl' arg. It must +always assume the file does not already exist. If the filesystem needs +to be involved in non-exclusive create, it should provide atomic_open. diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 7c753148af88..651b83b00440 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -415,7 +415,7 @@ As of kernel 2.6.22, the following members are defined: .. code-block:: c struct inode_operations { - int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t); struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 5783d0336f96..e47b90e70837 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -645,7 +645,6 @@ error: * @dir: The parent directory * @dentry: The name of file to be created * @mode: The UNIX file mode to set - * @excl: True if the file must not yet exist * * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called * for mknod(2). @@ -654,7 +653,7 @@ error: static int v9fs_vfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); u32 perm = unixmode2p9mode(v9ses, mode); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index f7396d20cb6c..d17c3b6eebb2 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -213,12 +213,11 @@ int v9fs_open_to_dotl_flags(int flags) * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @omode: create permissions - * @excl: True if the file must not yet exist * */ static int v9fs_vfs_create_dotl(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t omode, bool excl) + struct dentry *dentry, umode_t omode) { return v9fs_vfs_mknod_dotl(idmap, dir, dentry, omode, 0); } diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 44a3f69d275f..d6b3393633f2 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -169,7 +169,7 @@ extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int l extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int); extern int affs_unlink(struct inode *dir, struct dentry *dentry); extern int affs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool); + struct dentry *dentry, umode_t mode); extern struct dentry *affs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); extern int affs_rmdir(struct inode *dir, struct dentry *dentry); diff --git a/fs/affs/namei.c b/fs/affs/namei.c index c3c6532da4b0..b0001084727a 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -243,7 +243,7 @@ affs_unlink(struct inode *dir, struct dentry *dentry) int affs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 6df56fe9163f..6401fbdd10aa 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -34,7 +34,7 @@ static bool afs_lookup_filldir(struct dir_context *ctx, const char *name, int nl u64 ino, u32 uniquifier); #define AFS_LOOKUP ((filldir_t)0x137UL) static int afs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl); + struct dentry *dentry, umode_t mode); static struct dentry *afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode); static int afs_rmdir(struct inode *dir, struct dentry *dentry); @@ -1633,7 +1633,7 @@ static const struct afs_operation_ops afs_create_operation = { * create a regular file on an AFS filesystem */ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct afs_operation *op; struct afs_vnode *dvnode = AFS_FS_I(dir); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index acf8613f5e36..486c40f73e51 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -29,7 +29,7 @@ static const struct file_operations bad_file_ops = static int bad_inode_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) + umode_t mode) { return -EIO; } diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 5b40ab09a796..4c3b4db08cde 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -83,7 +83,7 @@ const struct file_operations bfs_dir_operations = { }; static int bfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { int err; struct inode *inode; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2534cd9284d5..910c06297119 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7007,7 +7007,7 @@ static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir, } static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct inode *inode; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index ef9e92e362d3..cee70570bd0b 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -983,7 +983,7 @@ out: } static int ceph_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { return ceph_mknod(idmap, dir, dentry, mode, 0); } diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 835eb7fdfdad..ea710a5dbbb7 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -134,7 +134,7 @@ static inline void coda_dir_drop_nlink(struct inode *dir) /* creation routines: create, mknod, mkdir, link, symlink */ static int coda_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *de, umode_t mode, bool excl) + struct dentry *de, umode_t mode) { int error; const char *name=de->d_name.name; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 7aaf1913f9c6..525297c7ebd8 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -268,7 +268,7 @@ out: static int ecryptfs_create(struct mnt_idmap *idmap, struct inode *directory_inode, struct dentry *ecryptfs_dentry, - umode_t mode, bool excl) + umode_t mode) { struct inode *ecryptfs_inode; int rc; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 95dcad83da11..f0d009555fc6 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -75,7 +75,7 @@ static bool efivarfs_valid_name(const char *str, int len) } static int efivarfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct inode *inode = NULL; struct efivar_entry *var; diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index b7d5e44ad38e..cd9c9eca58f8 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -538,7 +538,7 @@ out: } static int exfat_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 0d09d22fe708..742a78e165d4 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -99,7 +99,7 @@ struct dentry *ext2_get_parent(struct dentry *child) */ static int ext2_create (struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, - umode_t mode, bool excl) + umode_t mode) { struct inode *inode; int err; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index cc49ae04a6f6..c3de64d2a2df 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2811,7 +2811,7 @@ static int ext4_add_nondir(handle_t *handle, * with d_instantiate(). */ static int ext4_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { handle_t *handle; struct inode *inode; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index cac03b8e91a1..648681c5ba50 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -366,7 +366,7 @@ fail_drop: } static int f2fs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct f2fs_lock_context lc; diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index c93e05d35ef8..ee6824c5d136 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -265,7 +265,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, /***** Create a file */ static int msdos_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode = NULL; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index e909447873e3..139d3ef4bfae 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -755,7 +755,7 @@ error: } static int vfat_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0e2a1039fa43..0efb3141f7f7 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1084,7 +1084,7 @@ static int fuse_mknod(struct mnt_idmap *idmap, struct inode *dir, } static int fuse_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *entry, umode_t mode, bool excl) + struct dentry *entry, umode_t mode) { return fuse_mknod(idmap, dir, entry, mode, 0); } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 8a77794bbd4a..17bfa283b320 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -963,15 +963,14 @@ fail: * @dir: The directory in which to create the file * @dentry: The dentry of the new file * @mode: The mode of the new file - * @excl: Force fail if inode exists * * Returns: errno */ static int gfs2_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { - return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl); + return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, 1); } /** diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index e13450bb933e..93edc5a80c81 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -184,7 +184,7 @@ static int hfs_dir_release(struct inode *inode, struct file *file) * the directory and the name (and its length) of the new file. */ static int hfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct inode *inode; int res; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 8bf6c7cdd9a8..f0aae2cd6fcf 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -562,7 +562,7 @@ out: } static int hfsplus_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { return hfsplus_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index abe86d72d9ef..7add056d47d8 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -593,7 +593,7 @@ static struct inode *hostfs_iget(struct super_block *sb, char *name) } static int hostfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct inode *inode; char *name; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 353e13a615f5..809113d8248d 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -129,7 +129,7 @@ bail: } static int hpfs_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; unsigned len = dentry->d_name.len; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 216e1a0dd0b2..16d8437aed51 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -979,7 +979,7 @@ static struct dentry *hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, - umode_t mode, bool excl) + umode_t mode) { return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index c4088c3b4ac0..3d4695b838ed 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -26,7 +26,7 @@ static int jffs2_readdir (struct file *, struct dir_context *); static int jffs2_create (struct mnt_idmap *, struct inode *, - struct dentry *, umode_t, bool); + struct dentry *, umode_t); static struct dentry *jffs2_lookup (struct inode *,struct dentry *, unsigned int); static int jffs2_link (struct dentry *,struct inode *,struct dentry *); @@ -163,7 +163,7 @@ static int jffs2_readdir(struct file *file, struct dir_context *ctx) static int jffs2_create(struct mnt_idmap *idmap, struct inode *dir_i, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { struct jffs2_raw_inode *ri; struct jffs2_inode_info *f, *dir_f; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 442d62679262..2cf4e280ee18 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -61,7 +61,7 @@ static inline void free_ea_wmap(struct inode *inode) * */ static int jfs_create(struct mnt_idmap *idmap, struct inode *dip, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { int rc = 0; tid_t tid; /* transaction id */ diff --git a/fs/minix/namei.c b/fs/minix/namei.c index 263e4ba8b1c8..79e591bdfdc1 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -64,7 +64,7 @@ static int minix_tmpfile(struct mnt_idmap *idmap, struct inode *dir, } static int minix_create(struct mnt_idmap *idmap, struct inode *dir, - struct dentry *dentry, umode_t mode, bool excl) + struct dentry *dentry, umode_t mode) { return minix_mknod(&nop_mnt_idmap, dir, dentry, mode, 0); } diff --git a/fs/namei.c b/fs/namei.c index 19ce43c9a6e6..9c34304d6671 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4199,7 +4199,7 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode, error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di); if (error) return error; - error = dir->i_op->create(idmap, dir, dentry, mode, true); + error = dir->i_op->create(idmap, dir, dentry, mode); if (!error) fsnotify_create(dir, dentry); return error; @@ -4336,50 +4336,83 @@ static int may_o_create(struct mnt_idmap *idmap, return security_inode_create(dir->dentry->d_inode, dentry, mode); } -/* - * Attempt to atomically look up, create and open a file from a negative - * dentry. - * - * Returns 0 if successful. The file will have been created and attached to - * @file by the filesystem calling finish_open(). - * - * If the file was looked up only or didn't need creating, FMODE_OPENED won't - * be set. The caller will need to perform the open themselves. @path will - * have been updated to point to the new dentry. This may be negative. - * - * Returns an error code otherwise. +/** + * atomic_open() - atomically look up, create and open a file + * @path: parent directory path + * @dentry: child to ->atomic_open() + * @file: file to attach child to + * @open_flag: open flags + * @mode: create mode + * @create_error: return value from may_o_create() + * + * Attempt to look up, create and open @dentry, which must be negative, in a + * single call into the filesystem. + * + * If a non-error dentry is returned then: when FMODE_OPENED is set, + * the file will have been attached to @file by the filesystem calling + * finish_open(). If FMODE_OPENED isn't set, the filesystem instead called + * finish_no_open() and the caller will need to perform the open themselves. + * + * FMODE_CREATED is set when the call to ->atomic_open() actually created + * the file. + * + * Returns: the opened or looked-up dentry, or ERR_PTR() on failure. The + * reference to @dentry is consumed in either case. */ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry, struct file *file, - int open_flag, umode_t mode) + int open_flag, umode_t mode, int create_error) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; - struct inode *dir = path->dentry->d_inode; + struct inode *dir_inode = path->dentry->d_inode; int error; file->__f_path.dentry = DENTRY_NOT_SET; file->__f_path.mnt = path->mnt; - error = dir->i_op->atomic_open(dir, dentry, file, + error = dir_inode->i_op->atomic_open(dir_inode, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); + if (!error) { if (file->f_mode & FMODE_OPENED) { - if (unlikely(dentry != file->f_path.dentry)) { + /* finish_open() called */ + struct dentry *opened = file->f_path.dentry; + + if (unlikely(opened != dentry)) { dput(dentry); - dentry = dget(file->f_path.dentry); + dentry = dget(opened); } - } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { - error = -EIO; - } else { - if (file->f_path.dentry) { + } else if (likely(file->f_path.dentry != DENTRY_NOT_SET)) { + /* finish_no_open() called */ + struct dentry *replaced = file->f_path.dentry; + + if (replaced) { dput(dentry); - dentry = file->f_path.dentry; + dentry = replaced; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; + } else { + const char *fsname = dentry->d_sb->s_type->name; + + WARN(1, "%s: ->atomic_open() left file->f_path.dentry unset!\n", + fsname); + error = -EIO; } } + if (error) { + if (unlikely(create_error) && error == -ENOENT) { + /* + * Should have done a create, but errored before. + * Some filesystems return -ENOENT directly instead of + * calling finish_no_open() with a negative dentry; + * either way it should only mean the child doesn't exist, + * so a refused create is safe to record here. + */ + audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); + error = create_error; + } dput(dentry); dentry = ERR_PTR(error); } @@ -4389,32 +4422,52 @@ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry /* * Look up and maybe create and open the last component. * - * Must be called with parent locked (exclusive in O_CREAT case). + * Takes the parent inode lock itself, exclusive if O_CREAT was requested and + * shared otherwise, and drops it again before returning. The caller must not + * hold it. * - * Returns 0 on success, that is, if - * the file was successfully atomically created (if necessary) and opened, or - * the file was not completely opened at this time, though lookups and - * creations were performed. - * These case are distinguished by presence of FMODE_OPENED on file->f_mode. - * In the latter case dentry returned in @path might be negative if O_CREAT - * hadn't been specified. + * On success returns the dentry of the last component. If FMODE_OPENED is set + * on file->f_mode the file was also opened and attached to @file; otherwise + * only lookup and creat |