diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index a27c950ece61..6db0e5d1da07 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -159,6 +159,22 @@ overlay filesystem (though an operation on the name of the file such as rename or unlink will of course be noticed and handled). +Multiple lower layers +--------------------- + +Multiple lower layers can now be given using the the colon (":") as a +separator character between the directory names. For example: + + mount -t overlay overlay -olowerdir=/lower1:/lower2:/lower3 /merged + +As the example shows, "upperdir=" and "workdir=" may be omitted. In +that case the overlay will be read-only. + +The specified lower directories will be stacked beginning from the +rightmost one and going left. In the above example lower1 will be the +top, lower2 the middle and lower3 the bottom layer. + + Non-standard behavior --------------------- @@ -196,3 +212,15 @@ Changes to the underlying filesystems while part of a mounted overlay filesystem are not allowed. If the underlying filesystem is changed, the behavior of the overlay is undefined, though it will not result in a crash or deadlock. + +Testsuite +--------- + +There's testsuite developed by David Howells at: + + git://git.infradead.org/users/dhowells/unionmount-testsuite.git + +Run as root: + + # cd unionmount-testsuite + # ./run --ov diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index ea10a8719107..24f640441bd9 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -191,7 +191,6 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) ovl_set_timestamps(upperdentry, stat); return err; - } static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, @@ -385,7 +384,7 @@ int ovl_copy_up(struct dentry *dentry) struct kstat stat; enum ovl_path_type type = ovl_path_type(dentry); - if (type != OVL_PATH_LOWER) + if (OVL_TYPE_UPPER(type)) break; next = dget(dentry); @@ -394,7 +393,7 @@ int ovl_copy_up(struct dentry *dentry) parent = dget_parent(next); type = ovl_path_type(parent); - if (type != OVL_PATH_LOWER) + if (OVL_TYPE_UPPER(type)) break; dput(next); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8ffc4b980f1b..0dc4c33a0a1b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -118,14 +118,14 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry, static int ovl_set_opaque(struct dentry *upperdentry) { - return ovl_do_setxattr(upperdentry, ovl_opaque_xattr, "y", 1, 0); + return ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0); } static void ovl_remove_opaque(struct dentry *upperdentry) { int err; - err = ovl_do_removexattr(upperdentry, ovl_opaque_xattr); + err = ovl_do_removexattr(upperdentry, OVL_XATTR_OPAQUE); if (err) { pr_warn("overlayfs: failed to remove opaque from '%s' (%i)\n", upperdentry->d_name.name, err); @@ -152,7 +152,7 @@ static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, * correct link count. nlink=1 seems to pacify 'find' and * other utilities. */ - if (type == OVL_PATH_MERGE) + if (OVL_TYPE_MERGE(type)) stat->nlink = 1; return 0; @@ -506,7 +506,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) struct dentry *opaquedir = NULL; int err; - if (is_dir) { + if (is_dir && OVL_TYPE_MERGE_OR_LOWER(ovl_path_type(dentry))) { opaquedir = ovl_check_empty_and_clear(dentry); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) @@ -630,7 +630,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) goto out_drop_write; type = ovl_path_type(dentry); - if (type == OVL_PATH_PURE_UPPER) { + if (OVL_TYPE_PURE_UPPER(type)) { err = ovl_remove_upper(dentry, is_dir); } else { const struct cred *old_cred; @@ -712,7 +712,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, /* Don't copy up directory trees */ old_type = ovl_path_type(old); err = -EXDEV; - if ((old_type == OVL_PATH_LOWER || old_type == OVL_PATH_MERGE) && is_dir) + if (OVL_TYPE_MERGE_OR_LOWER(old_type) && is_dir) goto out; if (new->d_inode) { @@ -725,25 +725,25 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, new_type = ovl_path_type(new); err = -EXDEV; - if (!overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) + if (!overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) goto out; err = 0; - if (new_type == OVL_PATH_LOWER && old_type == OVL_PATH_LOWER) { + if (!OVL_TYPE_UPPER(new_type) && !OVL_TYPE_UPPER(old_type)) { if (ovl_dentry_lower(old)->d_inode == ovl_dentry_lower(new)->d_inode) goto out; } - if (new_type != OVL_PATH_LOWER && old_type != OVL_PATH_LOWER) { + if (OVL_TYPE_UPPER(new_type) && OVL_TYPE_UPPER(old_type)) { if (ovl_dentry_upper(old)->d_inode == ovl_dentry_upper(new)->d_inode) goto out; } } else { if (ovl_dentry_is_opaque(new)) - new_type = OVL_PATH_UPPER; + new_type = __OVL_PATH_UPPER; else - new_type = OVL_PATH_PURE_UPPER; + new_type = __OVL_PATH_UPPER | __OVL_PATH_PURE; } err = ovl_want_write(old); @@ -763,8 +763,8 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, goto out_drop_write; } - old_opaque = old_type != OVL_PATH_PURE_UPPER; - new_opaque = new_type != OVL_PATH_PURE_UPPER; + old_opaque = !OVL_TYPE_PURE_UPPER(old_type); + new_opaque = !OVL_TYPE_PURE_UPPER(new_type); if (old_opaque || new_opaque) { err = -ENOMEM; @@ -787,7 +787,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old, old_cred = override_creds(override_cred); } - if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) { + if (overwrite && OVL_TYPE_MERGE_OR_LOWER(new_type) && new_is_dir) { opaquedir = ovl_check_empty_and_clear(new); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) { diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 07d74b24913b..04f124884687 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -205,7 +205,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) static bool ovl_is_private_xattr(const char *name) { - return strncmp(name, "trusted.overlay.", 14) == 0; + return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0; } int ovl_setxattr(struct dentry *dentry, const char *name, @@ -238,7 +238,10 @@ out: static bool ovl_need_xattr_filter(struct dentry *dentry, enum ovl_path_type type) { - return type == OVL_PATH_UPPER && S_ISDIR(dentry->d_inode->i_mode); + if ((type & (__OVL_PATH_PURE | __OVL_PATH_UPPER)) == __OVL_PATH_UPPER) + return S_ISDIR(dentry->d_inode->i_mode); + else + return false; } ssize_t ovl_getxattr(struct dentry *dentry, const char *name, @@ -299,7 +302,7 @@ int ovl_removexattr(struct dentry *dentry, const char *name) if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name)) goto out_drop_write; - if (type == OVL_PATH_LOWER) { + if (!OVL_TYPE_UPPER(type)) { err = vfs_getxattr(realpath.dentry, name, NULL, 0); if (err < 0) goto out_drop_write; @@ -321,7 +324,7 @@ out: static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, struct dentry *realdentry) { - if (type != OVL_PATH_LOWER) + if (OVL_TYPE_UPPER(type)) return false; if (special_file(realdentry->d_inode->i_mode)) @@ -430,5 +433,4 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, } return inode; - } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 814bed33dd07..17ac5afc9ffb 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -12,13 +12,20 @@ struct ovl_entry; enum ovl_path_type { - OVL_PATH_PURE_UPPER, - OVL_PATH_UPPER, - OVL_PATH_MERGE, - OVL_PATH_LOWER, + __OVL_PATH_PURE = (1 << 0), + __OVL_PATH_UPPER = (1 << 1), + __OVL_PATH_MERGE = (1 << 2), }; -extern const char *ovl_opaque_xattr; +#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER) +#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE) +#define OVL_TYPE_PURE_UPPER(type) ((type) & __OVL_PATH_PURE) +#define OVL_TYPE_MERGE_OR_LOWER(type) \ + (OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type)) + +#define OVL_XATTR_PRE_NAME "trusted.overlay." +#define OVL_XATTR_PRE_LEN 16 +#define OVL_XATTR_OPAQUE OVL_XATTR_PRE_NAME"opaque" static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) { @@ -130,6 +137,7 @@ void ovl_dentry_version_inc(struct dentry *dentry); void ovl_path_upper(struct dentry *dentry, struct path *path); void ovl_path_lower(struct dentry *dentry, struct path *path); enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); +int ovl_path_next(int idx, struct dentry *dentry, struct path *path); struct dentry *ovl_dentry_upper(struct dentry *dentry); struct dentry *ovl_dentry_lower(struct dentry *dentry); struct dentry *ovl_dentry_real(struct dentry *dentry); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index c0205990a9f5..907870e81a72 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -24,7 +24,6 @@ struct ovl_cache_entry { struct list_head l_node; struct rb_node node; bool is_whiteout; - bool is_cursor; char name[]; }; @@ -40,6 +39,7 @@ struct ovl_readdir_data { struct rb_root root; struct list_head *list; struct list_head middle; + struct dentry *dir; int count; int err; }; @@ -48,7 +48,7 @@ struct ovl_dir_file { bool is_real; bool is_upper; struct ovl_dir_cache *cache; - struct ovl_cache_entry cursor; + struct list_head *cursor; struct file *realfile; struct file *upperfile; }; @@ -79,23 +79,49 @@ static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, return NULL; } -static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len, +static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir, + const char *name, int len, u64 ino, unsigned int d_type) { struct ovl_cache_entry *p; size_t size = offsetof(struct ovl_cache_entry, name[len + 1]); p = kmalloc(size, GFP_KERNEL); - if (p) { - memcpy(p->name, name, len); - p->name[len] = '\0'; - p->len = len; - p->type = d_type; - p->ino = ino; - p->is_whiteout = false; - p->is_cursor = false; - } + if (!p) + return NULL; + memcpy(p->name, name, len); + p->name[len] = '\0'; + p->len = len; + p->type = d_type; + p->ino = ino; + p->is_whiteout = false; + + if (d_type == DT_CHR) { + struct dentry *dentry; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) { + kfree(p); + return NULL; + } + + /* + * CAP_DAC_OVERRIDE for lookup + */ + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + old_cred = override_creds(override_cred); + + dentry = lookup_one_len(name, dir, len); + if (!IS_ERR(dentry)) { + p->is_whiteout = ovl_is_whiteout(dentry); + dput(dentry); + } + revert_creds(old_cred); + put_cred(override_cred); + } return p; } @@ -122,7 +148,7 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, return 0; } - p = ovl_cache_entry_new(name, len, ino, d_type); + p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type); if (p == NULL) return -ENOMEM; @@ -143,7 +169,7 @@ static int ovl_fill_lower(struct ovl_readdir_data *rdd, if (p) { list_move_tail(&p->l_node, &rdd->middle); } else { - p = ovl_cache_entry_new(name, namelen, ino, d_type); + p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type); if (p == NULL) rdd->err = -ENOMEM; else @@ -168,7 +194,6 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) { struct ovl_dir_cache *cache = od->cache; - list_del_init(&od->cursor.l_node); WARN_ON(cache->refcount <= 0); cache->refcount--; if (!cache->refcount) { @@ -204,6 +229,7 @@ static inline int ovl_dir_read(struct path *realpath, if (IS_ERR(realfile)) return PTR_ERR(realfile); + rdd->dir = realpath->dentry; rdd->ctx.pos = 0; do { rdd->count = 0; @@ -227,108 +253,58 @@ static void ovl_dir_reset(struct file *file) if (cache && ovl_dentry_version_get(dentry) != cache->version) { ovl_cache_put(od, dentry); od->cache = NULL; + od->cursor = NULL; } - WARN_ON(!od->is_real && type != OVL_PATH_MERGE); - if (od->is_real && type == OVL_PATH_MERGE) + WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type)); + if (od->is_real && OVL_TYPE_MERGE(type)) od->is_real = false; } -static int ovl_dir_mark_whiteouts(struct dentry *dir, - struct ovl_readdir_data *rdd) -{ - struct ovl_cache_entry *p; - struct dentry *dentry; - const struct cred *old_cred; - struct cred *override_cred; - - override_cred = prepare_creds(); - if (!override_cred) { - ovl_cache_free(rdd->list); - return -ENOMEM; - } - - /* - * CAP_DAC_OVERRIDE for lookup - */ - cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); - old_cred = override_creds(override_cred); - - mutex_lock(&dir->d_inode->i_mutex); - list_for_each_entry(p, rdd->list, l_node) { - if (p->is_cursor) - continue; - - if (p->type != DT_CHR) - continue; - - dentry = lookup_one_len(p->name, dir, p->len); - if (IS_ERR(dentry)) - continue; - - p->is_whiteout = ovl_is_whiteout(dentry); - dput(dentry); - } - mutex_unlock(&dir->d_inode->i_mutex); - - revert_creds(old_cred); - put_cred(override_cred); - - return 0; -} - static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) { int err; - struct path lowerpath; - struct path upperpath; + struct path realpath; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_merge, .list = list, .root = RB_ROOT, .is_merge = false, }; + int idx, next; - ovl_path_lower(dentry, &lowerpath); - ovl_path_upper(dentry, &upperpath); + for (idx = 0; idx != -1; idx = next) { + next = ovl_path_next(idx, dentry, &realpath); - if (upperpath.dentry) { - err = ovl_dir_read(&upperpath, &rdd); - if (err) - goto out; - - if (lowerpath.dentry) { - err = ovl_dir_mark_whiteouts(upperpath.dentry, &rdd); + if (next != -1) { + err = ovl_dir_read(&realpath, &rdd); if (err) - goto out; + break; + } else { + /* + * Insert lowest layer entries before upper ones, this + * allows offsets to be reasonably constant + */ + list_add(&rdd.middle, rdd.list); + rdd.is_merge = true; + err = ovl_dir_read(&realpath, &rdd); + list_del(&rdd.middle); } } - if (lowerpath.dentry) { - /* - * Insert lowerpath entries before upperpath ones, this allows - * offsets to be reasonably constant - */ - list_add(&rdd.middle, rdd.list); - rdd.is_merge = true; - err = ovl_dir_read(&lowerpath, &rdd); - list_del(&rdd.middle); - } -out: return err; } static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) { - struct ovl_cache_entry *p; + struct list_head *p; loff_t off = 0; - list_for_each_entry(p, &od->cache->entries, l_node) { - if (p->is_cursor) - continue; + list_for_each(p, &od->cache->entries) { if (off >= pos) break; off++; } - list_move_tail(&od->cursor.l_node, &p->l_node); + /* Cursor is safe since the cache is stable */ + od->cursor = p; } static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) @@ -367,6 +343,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) { struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; + struct ovl_cache_entry *p; if (!ctx->pos) ovl_dir_reset(file); @@ -385,19 +362,13 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) ovl_seek_cursor(od, ctx->pos); } - while (od->cursor.l_node.next != &od->cache->entries) { - struct ovl_cache_entry *p; - - p = list_entry(od->cursor.l_node.next, struct ovl_cache_entry, l_node); - /* Skip cursors */ - if (!p->is_cursor) { - if (!p->is_whiteout) { - if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) - break; - } - ctx->pos++; - } - list_move(&od->cursor.l_node, &p->l_node); + while (od->cursor != &od->cache->entries) { + p = list_entry(od->cursor, struct ovl_cache_entry, l_node); + if (!p->is_whiteout) + if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) + break; + od->cursor = p->l_node.next; + ctx->pos++; } return 0; } @@ -452,7 +423,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, /* * Need to check if we started out being a lower dir, but got copied up */ - if (!od->is_upper && ovl_path_type(dentry) != OVL_PATH_LOWER) { + if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) { struct inode *inode = file_inode(file); realfile = lockless_dereference(od->upperfile); @@ -516,11 +487,9 @@ static int ovl_dir_open(struct inode *inode, struct file *file) kfree(od); return PTR_ERR(realfile); } - INIT_LIST_HEAD(&od->cursor.l_node); od->realfile = realfile; - od->is_real = (type != OVL_PATH_MERGE); - od->is_upper = (type != OVL_PATH_LOWER); - od->cursor.is_cursor = true; + od->is_real = !OVL_TYPE_MERGE(type); + od->is_upper = OVL_TYPE_UPPER(type); file->private_data = od; return 0; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index f16d318b71f8..b90952f528b1 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -35,7 +35,8 @@ struct ovl_config { /* private information held for overlayfs's superblock */ struct ovl_fs { struct vfsmount *upper_mnt; - struct vfsmount *lower_mnt; + unsigned numlower; + struct vfsmount **lower_mnt; struct dentry *workdir; long lower_namelen; /* pathnames of lower and upper dirs, for show_options */ @@ -47,7 +48,6 @@ struct ovl_dir_cache; /* private information held for every overlayfs dentry */ struct ovl_entry { struct dentry *__upperdentry; - struct dentry *lowerdentry; struct ovl_dir_cache *cache; union { struct { @@ -56,30 +56,36 @@ struct ovl_entry { }; struct rcu_head rcu; }; + unsigned numlower; + struct path lowerstack[]; }; -const char *ovl_opaque_xattr = "trusted.overlay.opaque"; +#define OVL_MAX_STACK 500 +static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe) +{ + return oe->numlower ? oe->lowerstack[0].dentry : NULL; +} enum ovl_path_type ovl_path_type(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; + enum ovl_path_type type = 0; if (oe->__upperdentry) { - if (oe->lowerdentry) { + type = __OVL_PATH_UPPER; + + if (oe->numlower) { if (S_ISDIR(dentry->d_inode->i_mode)) - return OVL_PATH_MERGE; - else - return OVL_PATH_UPPER; - } else { - if (oe->opaque) - return OVL_PATH_UPPER; - else - return OVL_PATH_PURE_UPPER; + type |= __OVL_PATH_MERGE; + } else if (!oe->opaque) { + type |= __OVL_PATH_PURE; } } else { - return OVL_PATH_LOWER; + if (oe->numlower > 1) + type |= __OVL_PATH_MERGE; } + return type; } static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) @@ -98,10 +104,9 @@ void ovl_path_upper(struct dentry *dentry, struct path *path) enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) { - enum ovl_path_type type = ovl_path_type(dentry); - if (type == OVL_PATH_LOWER) + if (!OVL_TYPE_UPPER(type)) ovl_path_lower(dentry, path); else ovl_path_upper(dentry, path); @@ -120,7 +125,7 @@ struct dentry *ovl_dentry_lower(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; - return oe->lowerdentry; + return __ovl_dentry_lower(oe); } struct dentry *ovl_dentry_real(struct dentry *dentry) @@ -130,7 +135,7 @@ struct dentry *ovl_dentry_real(struct dentry *dentry) realdentry = ovl_upperdentry_dereference(oe); if (!realdentry) - realdentry = oe->lowerdentry; + realdentry = __ovl_dentry_lower(oe); return realdentry; } @@ -143,7 +148,7 @@ struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper) if (realdentry) { *is_upper = true; } else { - realdentry = oe->lowerdentry; + realdentry = __ovl_dentry_lower(oe); *is_upper = false; } return realdentry; @@ -165,11 +170,9 @@ void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache) void ovl_path_lower(struct dentry *dentry, struct path *path) { - struct ovl_fs *ofs = dentry->d_sb->s_fs_info; struct ovl_entry *oe = dentry->d_fsdata; - path->mnt = ofs->lower_mnt; - path->dentry = oe->lowerdentry; + *path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL }; } int ovl_want_write(struct dentry *dentry) @@ -249,7 +252,7 @@ static bool ovl_is_opaquedir(struct dentry *dentry) if (!S_ISDIR(inode->i_mode) || !inode->i_op->getxattr) return false; - res = inode->i_op->getxattr(dentry, ovl_opaque_xattr, &val, 1); + res = inode->i_op->getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1); if (res == 1 && val == 'y') return true; @@ -261,8 +264,11 @@ static void ovl_dentry_release(struct dentry *dentry) struct ovl_entry *oe = dentry->d_fsdata; if (oe) { + unsigned int i; + dput(oe->__upperdentry); - dput(oe->lowerdentry); + for (i = 0; i < oe->numlower; i++) + dput(oe->lowerstack[i].dentry); kfree_rcu(oe, rcu); } } @@ -271,9 +277,15 @@ static const struct dentry_operations ovl_dentry_operations = { .d_release = ovl_dentry_release, }; -static struct ovl_entry *ovl_alloc_entry(void) +static struct ovl_entry *ovl_alloc_entry(unsigned int numlower) { - return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL); + size_t size = offsetof(struct ovl_entry, lowerstack[numlower]); + struct ovl_entry *oe = kzalloc(size, GFP_KERNEL); + + if (oe) + oe->numlower = numlower; + + return oe; } static inline struct dentry *ovl_lookup_real(struct dentry *dir, @@ -295,82 +307,154 @@ static inline struct dentry *ovl_lookup_real(struct dentry *dir, return dentry; } +/* + * Returns next layer in stack starting from top. + * Returns -1 if this is the last layer. + */ +int ovl_path_next(int idx, struct dentry *dentry, struct path *path) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + BUG_ON(idx < 0); + if (idx == 0) { + ovl_path_upper(dentry, path); + if (path->dentry) + return oe->numlower ? 1 : -1; + idx++; + } + BUG_ON(idx > oe->numlower); + *path = oe->lowerstack[idx - 1]; + + return (idx < oe->numlower) ? idx + 1 : -1; +} + struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct ovl_entry *oe; - struct dentry *upperdir; - struct dentry *lowerdir; - struct dentry *upperdentry = NULL; - struct dentry *lowerdentry = NULL; + struct ovl_entry *poe = dentry->d_parent->d_fsdata; + struct path *stack = NULL; + struct dentry *upperdir, *upperdentry = NULL; + unsigned int ctr = 0; struct inode *inode = NULL; + bool upperopaque = false; + struct dentry *this, *prev = NULL; + unsigned int i; int err; - err = -ENOMEM; - oe = ovl_alloc_entry(); - if (!oe) - goto out; - - upperdir = ovl_dentry_upper(dentry->d_parent); - lowerdir = ovl_dentry_lower(dentry->d_parent); - + upperdir = ovl_upperdentry_dereference(poe); if (upperdir) { - upperdentry = ovl_lookup_real(upperdir, &dentry->d_name); - err = PTR_ERR(upperdentry); - if (IS_ERR(upperdentry)) - goto out_put_dir; + this = ovl_lookup_real(upperdir, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) + goto out; - if (lowerdir && upperdentry) { - if (ovl_is_whiteout(upperdentry)) { - dput(upperdentry); - upperdentry = NULL; - oe->opaque = true; - } else if (ovl_is_opaquedir(upperdentry)) { - oe->opaque = true; + if (this) { + if (ovl_is_whiteout(this)) { + dput(this); + this = NULL; + upperopaque = true; + } else if (poe->numlower && ovl_is_opaquedir(this)) { + upperopaque = true; } } - } - if (lowerdir && !oe->opaque) { - lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name); - err = PTR_ERR(lowerdentry); - if (IS_ERR(lowerdentry)) - goto out_dput_upper; + upperdentry = prev = this; } - if (lowerdentry && upperdentry && - (!S_ISDIR(upperdentry->d_inode->i_mode) || - !S_ISDIR(lowerdentry->d_inode->i_mode))) { - dput(lowerdentry); - lowerdentry = NULL; - oe->opaque = true; + if (!upperopaque && poe->numlower) { + err = -ENOMEM; + stack = kcalloc(poe->numlower, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_put_upper; } - if (lowerdentry || upperdentry) { + for (i = 0; !upperopaque && i < poe->numlower; i++) { + bool opaque = false; + struct path lowerpath = poe->lowerstack[i]; + + this = ovl_lookup_real(lowerpath.dentry, &dentry->d_name); + err = PTR_ERR(this); + if (IS_ERR(this)) { + /* + * If it's positive, then treat ENAMETOOLONG as ENOENT. + */ + if (err == -ENAMETOOLONG && (upperdentry || ctr)) + continue; + goto out_put; + } + if (!this) + continue; + if (ovl_is_whiteout(this)) { + dput(this); + break; + } + /* + * Only makes sense to check opaque dir if this is not the + * lowermost layer. + */ + if (i < poe->numlower - 1 && ovl_is_opaquedir(this)) + opaque = true; + + if (prev && (!S_ISDIR(prev->d_inode->i_mode) || + !S_ISDIR(this->d_inode->i_mode))) { + /* + * FIXME: check for upper-opaqueness maybe better done + * in remove code. + */ + if (prev == upperdentry) + upperopaque = true; + dput(this); + break; + } + /* + * If this is a non-directory then stop here. + */ + if (!S_ISDIR(this->d_inode->i_mode)) + opaque = true; + + stack[ctr].dentry = this; + stack[ctr].mnt = lowerpath.mnt; + ctr++; + prev = this; + if (opaque) + break; + } + + oe = ovl_alloc_entry(ctr); + err = -ENOMEM; + if (!oe) + goto out_put; + + if (upperdentry || ctr) { struct dentry *realdentry; - realdentry = upperdentry ? upperdentry : lowerdentry; + realdentry = upperdentry ? upperdentry : stack[0].dentry; + err = -ENOMEM; inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode, oe); if (!inode) - goto out_dput; + goto out_free_oe; ovl_copyattr(realdentry->d_inode, inode); } + oe->opaque = upperopaque; oe->__upperdentry = upperdentry; - oe->lowerdentry = lowerdentry; - + memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); + kfree(stack); dentry->d_fsdata = oe; d_add(dentry, inode); return NULL; -out_dput: - dput(lowerdentry); -out_dput_upper: - dput(upperdentry); -out_put_dir: +out_free_oe: kfree(oe); +out_put: + for (i = 0; i < ctr; i++) + dput(stack[i].dentry); + kfree(stack); +out_put_upper: + dput(upperdentry); out: return ERR_PTR(err); } @@ -383,10 +467,12 @@ struct file *ovl_path_open(struct path *path, int flags) static void ovl_put_super(struct super_block *sb) { struct ovl_fs *ufs = sb->s_fs_info; + unsigned i; dput(ufs->workdir); mntput(ufs->upper_mnt); - mntput(ufs->lower_mnt); + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir); @@ -400,7 +486,7 @@ static void ovl_put_super(struct super_block *sb) * @buf: The struct kstatfs to fill in with stats * * Get the filesystem statistics. As writes always target the upper layer - * filesystem pass the statfs to the same filesystem. + * filesystem pass the statfs to the upper filesystem (if it exists) */ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) { @@ -409,7 +495,7 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) struct path path; int err; - ovl_path_upper(root_dentry, &path); + ovl_path_real(root_dentry, &path); err = vfs_statfs(&path, buf); if (!err) { @@ -432,8 +518,21 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) struct ovl_fs *ufs = sb->s_fs_info; seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir); - seq_printf(m, ",upperdir=%s", ufs->config.upperdir); - seq_printf(m, ",workdir=%s", ufs->config.workdir); + if (ufs->config.upperdir) { + seq_printf(m, ",upperdir=%s", ufs->config.upperdir); + seq_printf(m, ",workdir=%s", ufs->config.workdir); + } + return 0; +} + +static int ovl_remount(struct super_block *sb, int *flags, char *data) +{ + struct ovl_fs *ufs = sb->s_fs_info; + + if (!(*flags & MS_RDONLY) && + (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY))) + return -EROFS; + return 0; } @@ -441,6 +540,7 @@ static const struct super_operations ovl_super_operations = { .put_super = ovl_put_super, .statfs = ovl_statfs, .show_options = ovl_show_options, + .remount_fs = ovl_remount, }; enum { @@ -585,24 +685,6 @@ static void ovl_unescape(char *s) } } -static int ovl_mount_dir(const char *name, struct path *path) -{ - int err; - char *tmp = kstrdup(name, GFP_KERNEL); - - if (!tmp) - return -ENOMEM; - - ovl_unescape(tmp); - err = kern_path(tmp, LOOKUP_FOLLOW, path); - if (err) { - pr_err("overlayfs: failed to resolve '%s': %i\n", tmp, err); - err = -EINVAL; - } - kfree(tmp); - return err; -} - static bool ovl_is_allowed_fs_type(struct dentry *root) { const struct dentry_operations *dop = root->d_op; @@ -622,6 +704,75 @@ static bool ovl_is_allowed_fs_type(struct dentry *root) return true; } +static int ovl_mount_dir_noesc(const char *name, struct path *path) +{ + int err = -EINVAL; + + if (!*name) { + pr_err("overlayfs: empty lowerdir\n"); + goto out; + } + err = kern_path(name, LOOKUP_FOLLOW, path); + if (err) { + pr_err("overlayfs: failed to resolve '%s': %i\n", name, err); + goto out; + } + err = -EINVAL; + if (!ovl_is_allowed_fs_type(path->dentry)) { + pr_err("overlayfs: filesystem on '%s' not supported\n", name); + goto out_put; + } + if (!S_ISDIR(path->dentry->d_inode->i_mode)) { + pr_err("overlayfs: '%s' not a directory\n", name); + goto out_put; + } + return 0; + +out_put: + path_put(path); +out: + return err; +} + +static int ovl_mount_dir(const char *name, struct path *path) +{ + int err = -ENOMEM; + char *tmp = kstrdup(name, GFP_KERNEL); + + if (tmp) { + ovl_unescape(tmp); + err = ovl_mount_dir_noesc(tmp, path); + kfree(tmp); + } + return err; +} + +static int ovl_lower_dir(const char *name, struct path *path, long *namelen, + int *stack_depth) +{ + int err; + struct kstatfs statfs; + + err = ovl_mount_dir_noesc(name, path); + if (err) + goto out; + + err = vfs_statfs(path, &statfs); + if (err) { + pr_err("overlayfs: statfs failed on '%s'\n", name); + goto out_put; + } + *namelen = max(*namelen, statfs.f_namelen); + *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth); + + return 0; + +out_put: + path_put(path); +out: + return err; +} + /* Workdir should not be subdir of upperdir and vice versa */ static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) { @@ -634,16 +785,39 @@ static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir) return ok; } +static unsigned int ovl_split_lowerdirs(char *str) +{ + unsigned int ctr = 1; + char *s, *d; + + for (s = d = str;; s++, d++) { + if (*s == '\\') { + s++; + } else if (*s == ':') { + *d = '\0'; + ctr++; + continue; + } + *d = *s; + if (!*s) + break; + } + return ctr; +} + static int ovl_fill_super(struct super_block *sb, void *data, int silent) { - struct path lowerpath; - struct path upperpath; - struct path workpath; - struct inode *root_inode; + struct path upperpath = { NULL, NULL }; + struct path workpath = { NULL, NULL }; struct dentry *root_dentry; struct ovl_entry *oe; struct ovl_fs *ufs; - struct kstatfs statfs; + struct path *stack = NULL; + char *lowertmp; + char *lower; + unsigned int numlower; + unsigned int stacklen = 0; + unsigned int i; int err; err = -ENOMEM; @@ -655,123 +829,135 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_free_config; - /* FIXME: workdir is not needed for a R/O mount */ err = -EINVAL; - if (!ufs->config.upperdir || !ufs->config.lowerdir || - !ufs->config.workdir) { - pr_err("overlayfs: missing upperdir or lowerdir or workdir\n"); + if (!ufs->config.lowerdir) { + pr_err("overlayfs: missing 'lowerdir'\n"); goto out_free_config; } + sb->s_stack_depth = 0; + if (ufs->config.upperdir) { + /* FIXME: workdir is not needed for a R/O mount */ + if (!ufs->config.workdir) { + pr_err("overlayfs: missing 'workdir'\n"); + goto out_free_config; + } + + err = ovl_mount_dir(ufs->config.upperdir, &upperpath); + if (err) + goto out_free_config; + + err = ovl_mount_dir(ufs->config.workdir, &workpath); + if (err) + goto out_put_upperpath; + + err = -EINVAL; + if (upperpath.mnt != workpath.mnt) { + pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); + goto out_put_workpath; + } + if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) { + pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); + goto out_put_workpath; + } + sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth; + } + err = -ENOMEM; + lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL); + if (!lowertmp) + goto out_put_workpath; + + err = -EINVAL; + stacklen = ovl_split_lowerdirs(lowertmp); + if (stacklen > OVL_MAX_STACK) + goto out_free_lowertmp; + + stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL); + if (!stack) + goto out_free_lowertmp; + + lower = lowertmp; + for (numlower = 0; numlower < stacklen; numlower++) { + err = ovl_lower_dir(lower, &stack[numlower], + &ufs->lower_namelen, &sb->s_stack_depth); + if (err) + goto out_put_lowerpath; + + lower = strchr(lower, '\0') + 1; + } + + err = -EINVAL; + sb->s_stack_depth++; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("overlayfs: maximum fs stacking depth exceeded\n"); + goto out_put_lowerpath; + } + + if (ufs->config.upperdir) { + ufs->upper_mnt = clone_private_mount(&upperpath); + err = PTR_ERR(ufs->upper_mnt); + if (IS_ERR(ufs->upper_mnt)) { + pr_err("overlayfs: failed to clone upperpath\n"); + goto out_put_lowerpath; + } + + ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); + err = PTR_ERR(ufs->workdir); + if (IS_ERR(ufs->workdir)) { + pr_err("overlayfs: failed to create directory %s/%s\n", + ufs->config.workdir, OVL_WORKDIR_NAME); + goto out_put_upper_mnt; + } + } + err = -ENOMEM; - oe = ovl_alloc_entry(); - if (oe == NULL) - goto out_free_config; + ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL); + if (ufs->lower_mnt == NULL) + goto out_put_workdir; + for (i = 0; i < numlower; i++) { + struct vfsmount *mnt = clone_private_mount(&stack[i]); - err = ovl_mount_dir(ufs->config.upperdir, &upperpath); - if (err) - goto out_free_oe; + err = PTR_ERR(mnt); + if (IS_ERR(mnt)) { + pr_err("overlayfs: failed to clone lowerpath\n"); + goto out_put_lower_mnt; + } + /* + * Make lower_mnt R/O. That way fchmod/fchown on lower file + * will fail instead of modifying lower fs. + */ + mnt->mnt_flags |= MNT_READONLY; - err = ovl_mount_dir(ufs->config.lowerdir, &lowerpath); - if (err) - goto out_put_upperpath; - - err = ovl_mount_dir(ufs->config.workdir, &workpath); - if (err) - goto out_put_lowerpath; - - err = -EINVAL; - if (!S_ISDIR(upperpath.dentry->d_inode->i_mode) || - !S_ISDIR(lowerpath.dentry->d_inode->i_mode) || - !S_ISDIR(workpath.dentry->d_inode->i_mode)) { - pr_err("overlayfs: upperdir or lowerdir or workdir not a directory\n"); - goto out_put_workpath; + ufs->lower_mnt[ufs->numlower] = mnt; + ufs->numlower++; } - if (upperpath.mnt != workpath.mnt) { - pr_err("overlayfs: workdir and upperdir must reside under the same mount\n"); - goto out_put_workpath; - } - if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) { - pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); - goto out_put_workpath; - } - - if (!ovl_is_allowed_fs_type(upperpath.dentry)) { - pr_err("overlayfs: filesystem of upperdir is not supported\n"); - goto out_put_workpath; - } - - if (!ovl_is_allowed_fs_type(lowerpath.dentry)) { - pr_err("overlayfs: filesystem of lowerdir is not supported\n"); - goto out_put_workpath; - } - - err = vfs_statfs(&lowerpath, &statfs); - if (err) { - pr_err("overlayfs: statfs failed on lowerpath\n"); - goto out_put_workpath; - } - ufs->lower_namelen = statfs.f_namelen; - - sb->s_stack_depth = max(upperpath.mnt->mnt_sb->s_stack_depth, - lowerpath.mnt->mnt_sb->s_stack_depth) + 1; - - err = -EINVAL; - if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { - pr_err("overlayfs: maximum fs stacking depth exceeded\n"); - goto out_put_workpath; - } - - ufs->upper_mnt = clone_private_mount(&upperpath); - err = PTR_ERR(ufs->upper_mnt); - if (IS_ERR(ufs->upper_mnt)) { - pr_err("overlayfs: failed to clone upperpath\n"); - goto out_put_workpath; - } - - ufs->lower_mnt = clone_private_mount(&lowerpath); - err = PTR_ERR(ufs->lower_mnt); - if (IS_ERR(ufs->lower_mnt)) { - pr_err("overlayfs: failed to clone lowerpath\n"); - goto out_put_upper_mnt; - } - - ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); - err = PTR_ERR(ufs->workdir); - if (IS_ERR(ufs->workdir)) { - pr_err("overlayfs: failed to create directory %s/%s\n", - ufs->config.workdir, OVL_WORKDIR_NAME); - goto out_put_lower_mnt; - } - - /* - * Make lower_mnt R/O. That way fchmod/fchown on lower file - * will fail instead of modifying lower fs. - */ - ufs->lower_mnt->mnt_flags |= MNT_READONLY; - - /* If the upper fs is r/o, we mark overlayfs r/o too */ - if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY) + /* If the upper fs is r/o or nonexistent, we mark overlayfs r/o too */ + if (!ufs->upper_mnt || (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY)) sb->s_flags |= MS_RDONLY; sb->s_d_op = &ovl_dentry_operations; err = -ENOMEM; - root_inode = ovl_new_inode(sb, S_IFDIR, oe); - if (!root_inode) - goto out_put_workdir; + oe = ovl_alloc_entry(numlower); + if (!oe) + goto out_put_lower_mnt; - root_dentry = d_make_root(root_inode); + root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, oe)); if (!root_dentry) - goto out_put_workdir; + goto out_free_oe; mntput(upperpath.mnt); - mntput(lowerpath.mnt); + for (i = 0; i < numlower; i++) + mntput(stack[i].mnt); path_put(&workpath); + kfree(lowertmp); oe->__upperdentry = upperpath.dentry; - oe->lowerdentry = lowerpath.dentry; + for (i = 0; i < numlower; i++) { + oe->lowerstack[i].dentry = stack[i].dentry; + oe->lowerstack[i].mnt = ufs->lower_mnt[i]; + } root_dentry->d_fsdata = oe; @@ -782,20 +968,26 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) return 0; -out_put_workdir: - dput(ufs->workdir); -out_put_lower_mnt: - mntput(ufs->lower_mnt); -out_put_upper_mnt: - mntput(ufs->upper_mnt); -out_put_workpath: - path_put(&workpath); -out_put_lowerpath: - path_put(&lowerpath); -out_put_upperpath: - path_put(&upperpath); out_free_oe: kfree(oe); +out_put_lower_mnt: + for (i = 0; i < ufs->numlower; i++) + mntput(ufs->lower_mnt[i]); + kfree(ufs->lower_mnt); +out_put_workdir: + dput(ufs->workdir); +out_put_upper_mnt: + mntput(ufs->upper_mnt); +out_put_lowerpath: + for (i = 0; i < numlower; i++) + path_put(&stack[i]); + kfree(stack); +out_free_lowertmp: + kfree(lowertmp); +out_put_workpath: + path_put(&workpath); +out_put_upperpath: + path_put(&upperpath); out_free_config: kfree(ufs->config.lowerdir); kfree(ufs->config.upperdir);