1 files changed, 106 insertions, 38 deletions

diff --git a/fs/namei.c b/fs/namei.c
index e1cf56d0ba08..e99e6d9c947c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -52,8 +52,8 @@
  * The new code replaces the old recursive symlink resolution with
  * an iterative one (in case of non-nested symlink chains).  It does
  * this with calls to <fs>_follow_link().
- * As a side effect, dir_namei(), _namei() and follow_link() are now 
- * replaced with a single function lookup_dentry() that can handle all 
+ * As a side effect, dir_namei(), _namei() and follow_link() are now
+ * replaced with a single function lookup_dentry() that can handle all
  * the special cases of the former code.
  *
  * With the new dcache, the pathname is stored at each inode, at least as
@@ -2879,20 +2879,14 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	p = d_ancestor(p2, p1);
 	if (p) {
 		inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
-		inode_lock_nested(p1->d_inode, I_MUTEX_CHILD);
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2);
 		return p;
 	}
 
 	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;
-	}
-
-	lock_two_inodes(p1->d_inode, p2->d_inode,
-			I_MUTEX_PARENT, I_MUTEX_PARENT2);
-	return NULL;
+	inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+	inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
+	return p;
 }
 EXPORT_SYMBOL(lock_rename);
 
@@ -2906,6 +2900,63 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
 }
 EXPORT_SYMBOL(unlock_rename);
 
+/**
+ * mode_strip_umask - handle vfs umask stripping
+ * @dir:	parent directory of the new inode
+ * @mode:	mode of the new inode to be created in @dir
+ *
+ * Umask stripping depends on whether or not the filesystem supports POSIX
+ * ACLs. If the filesystem doesn't support it umask stripping is done directly
+ * in here. If the filesystem does support POSIX ACLs umask stripping is
+ * deferred until the filesystem calls posix_acl_create().
+ *
+ * Returns: mode
+ */
+static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode)
+{
+	if (!IS_POSIXACL(dir))
+		mode &= ~current_umask();
+	return mode;
+}
+
+/**
+ * vfs_prepare_mode - prepare the mode to be used for a new inode
+ * @dir:	parent directory of the new inode
+ * @mode:	mode of the new inode
+ * @mask_perms:	allowed permission by the vfs
+ * @type:	type of file to be created
+ *
+ * This helper consolidates and enforces vfs restrictions on the @mode of a new
+ * object to be created.
+ *
+ * Umask stripping depends on whether the filesystem supports POSIX ACLs (see
+ * the kernel documentation for mode_strip_umask()). Moving umask stripping
+ * after setgid stripping allows the same ordering for both non-POSIX ACL and
+ * POSIX ACL supporting filesystems.
+ *
+ * Note that it's currently valid for @type to be 0 if a directory is created.
+ * Filesystems raise that flag individually and we need to check whether each
+ * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a
+ * non-zero type.
+ *
+ * Returns: mode to be passed to the filesystem
+ */
+static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode,
+				       umode_t mask_perms, umode_t type)
+{
+	mode = mode_strip_sgid(dir, mode);
+	mode = mode_strip_umask(dir, mode);
+
+	/*
+	 * Apply the vfs mandated allowed permission mask and set the type of
+	 * file to be created before we call into the filesystem.
+	 */
+	mode &= (mask_perms & ~S_IFMT);
+	mode |= (type & S_IFMT);
+
+	return mode;
+}
+
 int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		bool want_excl)
 {
@@ -2915,8 +2966,8 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	if (!dir->i_op->create)
 		return -EACCES;	/* shouldn't it be ENOSYS? */
-	mode &= S_IALLUGO;
-	mode |= S_IFREG;
+
+	mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG);
 	error = security_inode_create(dir, dentry, mode);
 	if (error)
 		return error;
@@ -3186,8 +3237,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	 * O_EXCL open we want to return EEXIST not EROFS).
 	 */
 	if (open_flag & O_CREAT) {
-		if (!IS_POSIXACL(dir->d_inode))
-			mode &= ~current_umask();
+		mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode);
 		if (unlikely(!got_write)) {
 			create_error = -EROFS;
 			open_flag &= ~O_CREAT;
@@ -3463,8 +3513,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
 	child = d_alloc(dentry, &slash_name);
 	if (unlikely(!child))
 		goto out_err;
-	if (!IS_POSIXACL(dir))
-		mode &= ~current_umask();
+	mode = vfs_prepare_mode(dir, mode, mode, mode);
 	error = dir->i_op->tmpfile(dir, child, mode);
 	if (error)
 		goto out_err;
@@ -3723,6 +3772,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
 	if (!dir->i_op->mknod)
 		return -EPERM;
 
+	mode = vfs_prepare_mode(dir, mode, mode, mode);
 	error = devcgroup_inode_mknod(mode, dev);
 	if (error)
 		return error;
@@ -3771,9 +3821,8 @@ retry:
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (!IS_POSIXACL(path.dentry->d_inode))
-		mode &= ~current_umask();
-	error = security_path_mknod(&path, dentry, mode, dev);
+	error = security_path_mknod(&path, dentry,
+			mode_strip_umask(path.dentry->d_inode, mode), dev);
 	if (error)
 		goto out;
 	switch (mode & S_IFMT) {
@@ -3821,7 +3870,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (!dir->i_op->mkdir)
 		return -EPERM;
 
-	mode &= (S_IRWXUGO|S_ISVTX);
+	mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0);
 	error = security_inode_mkdir(dir, dentry, mode);
 	if (error)
 		return error;
@@ -3848,9 +3897,8 @@ retry:
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (!IS_POSIXACL(path.dentry->d_inode))
-		mode &= ~current_umask();
-	error = security_path_mkdir(&path, dentry, mode);
+	error = security_path_mkdir(&path, dentry,
+			mode_strip_umask(path.dentry->d_inode, mode));
 	if (!error)
 		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
 	done_path_create(&path, dentry);
@@ -4383,11 +4431,12 @@ 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
@@ -4416,6 +4465,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	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;
@@ -4465,15 +4515,32 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	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 = -EBUSY;
 	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
@@ -4517,8 +4584,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			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) {