diff options
Diffstat (limited to 'fs/namei.c')
| -rw-r--r-- | fs/namei.c | 173 |
1 files changed, 133 insertions, 40 deletions
diff --git a/fs/namei.c b/fs/namei.c index 5e1c2ab2ae70..9e336b408ed1 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -253,6 +253,7 @@ getname_kernel(const char * filename) return result; } +EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { @@ -271,6 +272,7 @@ void putname(struct filename *name) } else __putname(name); } +EXPORT_SYMBOL(putname); /** * check_acl - perform ACL permission checking @@ -1581,8 +1583,9 @@ static struct dentry *lookup_dcache(const struct qstr *name, * when directory is guaranteed to have no in-lookup children * at all. */ -static struct dentry *__lookup_hash(const struct qstr *name, - struct dentry *base, unsigned int flags) +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; @@ -1606,6 +1609,7 @@ static struct dentry *__lookup_hash(const struct qstr *name, } return dentry; } +EXPORT_SYMBOL(lookup_one_qstr_excl); static struct dentry *lookup_fast(struct nameidata *nd) { @@ -2532,16 +2536,17 @@ static int path_parentat(struct nameidata *nd, unsigned flags, } /* Note: this does not consume "name" */ -static int filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) +static int __filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type, + const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); - set_nameidata(&nd, dfd, name, NULL); + set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); @@ -2556,6 +2561,13 @@ static int filename_parentat(int dfd, struct filename *name, return retval; } +static int filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type) +{ + return __filename_parentat(dfd, name, flags, parent, last, type, NULL); +} + /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(struct filename *name, struct path *path) { @@ -2571,7 +2583,7 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - d = __lookup_hash(&last, path->dentry, 0); + d = lookup_one_qstr_excl(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); @@ -2600,6 +2612,24 @@ int kern_path(const char *name, unsigned int flags, struct path *path) EXPORT_SYMBOL(kern_path); /** + * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair + * @filename: filename structure + * @flags: lookup flags + * @parent: pointer to struct path to fill + * @last: last component + * @type: type of the last component + * @root: pointer to struct path of the base directory + */ +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root) +{ + return __filename_parentat(AT_FDCWD, filename, flags, parent, last, + type, root); +} +EXPORT_SYMBOL(vfs_path_parent_lookup); + +/** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory @@ -2980,39 +3010,79 @@ static inline int may_create(struct user_namespace *mnt_userns, return inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC); } +static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) +{ + struct dentry *p; + + p = d_ancestor(p2, p1); + if (p) { + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); + return p; + } + + p = d_ancestor(p1, p2); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + return p; +} + /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { - struct dentry *p; - if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); + return lock_two_directories(p1, p2); +} +EXPORT_SYMBOL(lock_rename); - p = d_ancestor(p2, p1); - if (p) { +/* + * c1 and p2 should be on the same fs. + */ +struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) +{ + if (READ_ONCE(c1->d_parent) == p2) { + /* + * hopefully won't need to touch ->s_vfs_rename_mutex at all. + */ inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); - return p; - } + /* + * now that p2 is locked, nobody can move in or out of it, + * so the test below is safe. + */ + if (likely(c1->d_parent == p2)) + return NULL; - p = d_ancestor(p1, p2); - if (p) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); - return p; + /* + * c1 got moved out of p2 while we'd been taking locks; + * unlock and fall back to slow case. + */ + inode_unlock(p2->d_inode); } - lock_two_inodes(p1->d_inode, p2->d_inode, - I_MUTEX_PARENT, I_MUTEX_PARENT2); + mutex_lock(&c1->d_sb->s_vfs_rename_mutex); + /* + * nobody can move out of any directories on this fs. + */ + if (likely(c1->d_parent != p2)) + return lock_two_directories(c1->d_parent, p2); + + /* + * c1 got moved into p2 while we were taking locks; + * we need p2 locked and ->s_vfs_rename_mutex unlocked, + * for consistency with lock_rename(). + */ + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); return NULL; } -EXPORT_SYMBOL(lock_rename); +EXPORT_SYMBOL(lock_rename_child); void unlock_rename(struct dentry *p1, struct dentry *p2) { @@ -3806,7 +3876,8 @@ static struct dentry *filename_create(int dfd, struct filename *name, if (last.name[last.len] && !want_dir) create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); + dentry = lookup_one_qstr_excl(&last, path->dentry, + reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -4168,7 +4239,7 @@ retry: goto exit2; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; @@ -4302,7 +4373,7 @@ retry: goto exit2; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { struct user_namespace *mnt_userns; @@ -4658,11 +4729,12 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. - * That's where 4.4 screws up. Current fix: serialization on + * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. - * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source. + * c) we may have to lock up to _four_ objects - parents and victim (if it exists), + * and source (if it's a non-directory or a subdirectory that moves to + * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4694,6 +4766,7 @@ int vfs_rename(struct renamedata *rd) bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; + bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; @@ -4747,15 +4820,32 @@ int vfs_rename(struct renamedata *rd) take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* - * Lock all moved children. Moved directories may need to change parent - * pointer so they need the lock to prevent against concurrent - * directory changes moving parent pointer. For regular files we've - * historically always done this. The lockdep locking subclasses are - * somewhat arbitrary but RENAME_EXCHANGE in particular can swap - * regular files and directories so it's difficult to tell which - * subclasses to use. + * Lock children. + * The source subdirectory needs to be locked on cross-directory + * rename or cross-directory exchange since its parent changes. + * The target subdirectory needs to be locked on cross-directory + * exchange due to parent change and on any rename due to becoming + * a victim. + * Non-directories need locking in all cases (for NFS reasons); + * they get locked after any subdirectories (in inode address order). + * + * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. + * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ - lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + lock_old_subdir = new_dir != old_dir; + lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); + if (is_dir) { + if (lock_old_subdir) + inode_lock_nested(source, I_MUTEX_CHILD); + if (target && (!new_is_dir || lock_new_subdir)) + inode_lock(target); + } else if (new_is_dir) { + if (lock_new_subdir) + inode_lock_nested(target, I_MUTEX_CHILD); + inode_lock(source); + } else { + lock_two_nondirectories(source, target); + } error = -EPERM; if (IS_SWAPFILE(source) || (target && IS_SWAPFILE(target))) @@ -4803,8 +4893,9 @@ int vfs_rename(struct renamedata *rd) d_exchange(old_dentry, new_dentry); } out: - inode_unlock(source); - if (target) + if (!is_dir || lock_old_subdir) + inode_unlock(source); + if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { @@ -4876,7 +4967,8 @@ retry: retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); - old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); + old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry, + lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; @@ -4884,7 +4976,8 @@ retry_deleg: error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; - new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); + new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, + lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; |