Merge branch 'vfs-7.4.lookup' into vfs.all

Signed-off-by: Christian Brauner <brauner@kernel.org>

16 files changed, 455 insertions, 80 deletions

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 3829554ca369..b1e0823c87b5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -776,6 +776,9 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int p9_omode;
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (d_in_lookup(dentry)) {
 		struct dentry *res = v9fs_vfs_lookup(dir, dentry, 0);
 		if (res || d_really_is_positive(dentry))
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 116b29e95f21..64e0aba08da1 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -238,6 +238,9 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	struct v9fs_session_info *v9ses;
 	struct posix_acl *pacl = NULL, *dacl = NULL;
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (d_in_lookup(dentry)) {
 		struct dentry *res = v9fs_vfs_lookup(dir, dentry, 0);
 		if (res || d_really_is_positive(dentry))
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index bd3e3f5c269e..78a0b2540f10 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -812,6 +812,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	      dir, ceph_vinop(dir), dentry, dentry,
 	      d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (dentry->d_name.len > NAME_MAX)
 		return -ENAMETOOLONG;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index e49b4e874b15..17217d97b9e7 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -944,6 +944,9 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	struct fuse_conn *fc = get_fuse_conn(dir);
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (fuse_is_bad(dir))
 		return -EIO;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index f361876c5583..3ee1360f1bc2 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1386,6 +1386,9 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 {
 	bool excl = !!(flags & O_EXCL);
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (d_in_lookup(dentry)) {
 		struct dentry *d = __gfs2_lookup(dir, dentry, file);
 		if (file->f_mode & FMODE_OPENED) {
diff --git a/fs/internal.h b/fs/internal.h
index c658c8a5ebd5..9632239036ac 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -205,6 +205,7 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 int chown_common(const struct path *path, uid_t user, gid_t group);
 extern int vfs_open(const struct path *, struct file *);
+int vfs_open_consume(struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 20a6534ea3ef..9da900f6c113 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1382,13 +1382,13 @@ int may_linkat(struct mnt_idmap *idmap, const struct path *link)
 
 /**
  * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
- *			  should be allowed, or not, on files that already
- *			  exist.
+ *			  should be allowed, or not, on files/directories that
+ *			  already exist.
  * @idmap: idmap of the mount the inode was found from
  * @nd: nameidata pathwalk data
  * @inode: the inode of the file to open
  *
- * Block an O_CREAT open of a FIFO (or a regular file) when:
+ * Block an O_CREAT open of a FIFO (or a regular file/directory) when:
  *   - sysctl_protected_fifos (or sysctl_protected_regular) is enabled
  *   - the file already exists
  *   - we are in a sticky directory
@@ -1416,6 +1416,14 @@ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd,
 	if (likely(!(dir_mode & S_ISVTX)))
 		return 0;
 
+	/*
+	 * There is no separate sysctl for directory creation in sticky
+	 * folders. Therefore, for the S_ISDIR case, disabling
+	 * sysctl_protected_regular is not enough to allow creating a
+	 * directory in a sticky folder, because that may surprise users
+	 * not expecting that O_CREAT|O_DIRECTORY is possible on newer
+	 * kernels.
+	 */
 	if (S_ISREG(inode->i_mode) && !sysctl_protected_regular)
 		return 0;
 
@@ -1447,6 +1455,12 @@ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd,
 					      "sticky_create_regular");
 			return -EACCES;
 		}
+
+		if (S_ISDIR(inode->i_mode)) {
+			audit_log_path_denied(AUDIT_ANOM_CREAT,
+					      "sticky_create_dir");
+			return -EACCES;
+		}
 	}
 
 	return 0;
@@ -2781,9 +2795,16 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	return s;
 }
 
+static inline bool trailing_slashes(const struct qstr *last)
+{
+	/* last->len is set by hash_name() to the length of the current
+	 * component ->name, terminating with '/' or a NUL character. */
+	return (bool)last->name[last->len];
+}
+
 static inline const char *lookup_last(struct nameidata *nd)
 {
-	if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
+	if (nd->last_type == LAST_NORM && trailing_slashes(&nd->last))
 		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 
 	return walk_component(nd, WALK_TRAILING);
@@ -4159,6 +4180,24 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
 	return mode;
 }
 
+static inline
+int vfs_create_no_perm(struct mnt_idmap *idmap, struct dentry *dentry,
+		       umode_t mode, struct delegated_inode *di)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	int error;
+
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
+	if (error)
+		return error;
+
+	error = dir->i_op->create(idmap, dir, dentry, mode);
+	if (!error)
+		fsnotify_create(dir, dentry);
+
+	return error;
+}
+
 /**
  * vfs_create - create new file
  * @idmap:	idmap of the mount the inode was found from
@@ -4191,13 +4230,8 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode,
 	error = security_inode_create(dir, dentry, mode);
 	if (error)
 		return error;
-	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
-	if (error)
-		return error;
-	error = dir->i_op->create(idmap, dir, dentry, mode);
-	if (!error)
-		fsnotify_create(dir, dentry);
-	return error;
+
+	return vfs_create_no_perm(idmap, dentry, mode, di);
 }
 EXPORT_SYMBOL(vfs_create);
 
@@ -4314,21 +4348,41 @@ static inline int open_to_namei_flags(int flag)
 
 static int may_o_create(struct mnt_idmap *idmap,
 			const struct path *dir, struct dentry *dentry,
-			umode_t mode)
+			int open_flag, umode_t mode)
 {
-	int error = security_path_mknod(dir, dentry, mode, 0);
+	struct inode *dir_inode = dir->dentry->d_inode;
+	bool create_dir = O_IS_MKDIR(open_flag);
+	int error;
+
+	if (create_dir)
+		error = security_path_mkdir(dir, dentry, mode);
+	else
+		error = security_path_mknod(dir, dentry, mode, 0);
 	if (error)
 		return error;
 
 	if (!fsuidgid_has_mapping(dir->dentry->d_sb, idmap))
 		return -EOVERFLOW;
 
-	error = inode_permission(idmap, dir->dentry->d_inode,
-				 MAY_WRITE | MAY_EXEC);
+	error = inode_permission(idmap, dir_inode, MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
 
-	return security_inode_create(dir->dentry->d_inode, dentry, mode);
+	if (create_dir)
+		error = security_inode_mkdir(dir_inode, dentry, mode);
+	else
+		error = security_inode_create(dir_inode, dentry, mode);
+
+	return error;
+}
+
+static inline umode_t o_create_mode(struct mnt_idmap *idmap,
+		const struct inode *dir, int open_flag, umode_t mode)
+{
+	if (O_IS_MKDIR(open_flag))
+		return vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, S_IFDIR);
+	else
+		return vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG);
 }
 
 /**
@@ -4364,8 +4418,9 @@ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry
 
 	file->__f_path.dentry = DENTRY_NOT_SET;
 	file->__f_path.mnt = path->mnt;
+
 	error = dir_inode->i_op->atomic_open(dir_inode, dentry, file,
-				       open_to_namei_flags(open_flag), mode);
+					     open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
 
 	if (!error) {
@@ -4410,10 +4465,21 @@ static struct dentry *atomic_open(const struct path *path, struct dentry *dentry
 		}
 		dput(dentry);
 		dentry = ERR_PTR(error);
+	} else {
+		if (file->f_mode & FMODE_CREATED)
+			fsnotify_create(dir_inode, dentry);
+		if (file->f_mode & FMODE_OPENED)
+			fsnotify_open(file);
 	}
+
+
 	return dentry;
 }
 
+static inline
+struct dentry *vfs_mkdir_no_perm(struct mnt_idmap *, struct inode *,
+				 struct dentry *, umode_t,
+				 struct delegated_inode *);
 /*
  * Look up and maybe create and open the last component.
  *
@@ -4435,6 +4501,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 	struct mnt_idmap *idmap;
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
+	bool create_dir = O_IS_MKDIR(op->mode);
 	int open_flag;
 	struct dentry *dentry;
 	int error, create_error;
@@ -4455,7 +4522,7 @@ retry:
 		 */
 	}
 	if (open_flag & O_CREAT)
-		inode_lock(dir_inode);
+		inode_lock_nested(dir_inode, I_MUTEX_PARENT);
 	else
 		inode_lock_shared(dir_inode);
 
@@ -4507,12 +4574,17 @@ retry:
 	if (open_flag & O_CREAT) {
 		if (open_flag & O_EXCL)
 			open_flag &= ~O_TRUNC;
-		mode = vfs_prepare_mode(idmap, dir_inode, mode, mode, mode);
+		mode = o_create_mode(idmap, dir_inode, open_flag, mode);
 		if (likely(got_write))
 			create_error = may_o_create(idmap, &nd->path,
-						    dentry, mode);
+						    dentry, open_flag, mode);
 		else
 			create_error = -EROFS;
+		/* Refuse to create a directory through a dangling (trailing)
+		 * symlink. For regular files this has been allowed historically
+		 * on O_CREAT without O_EXCL. */
+		if (unlikely(nd->depth) && create_dir && !create_error)
+			create_error = -EEXIST;
 	}
 	if (create_error)
 		open_flag &= ~O_CREAT;
@@ -4537,6 +4609,7 @@ retry:
 			dentry = res;
 		}
 	}
+
 	if (dentry->d_inode || !(op->open_flag & O_CREAT)) {
 		/*
 		 * No need to create a file.  If lookup returned a positive
@@ -4554,26 +4627,26 @@ retry:
 		goto out_dput;
 	}
 
-	error = try_break_deleg(dir_inode, LEASE_BREAK_DIR_CREATE, &delegated_inode);
-	if (error)
-		goto out_dput;
-
-	file->f_mode |= FMODE_CREATED;
-	if (!dir_inode->i_op->create) {
+	if ((create_dir && !dir_inode->i_op->mkdir)
+		|| (!create_dir && !dir_inode->i_op->create)) {
 		error = -EACCES;
 		goto out_dput;
 	}
 
-	error = dir_inode->i_op->create(idmap, dir_inode, dentry, mode);
+	if (create_dir) {
+		struct dentry *res = vfs_mkdir_no_perm(idmap, dir_inode, dentry,
+						       mode, &delegated_inode);
+			error = PTR_ERR_OR_ZERO(res);
+			if (!error)
+				dentry = res;
+	} else {
+		error = vfs_create_no_perm(idmap, dentry, mode, &delegated_inode);
+	}
 	if (error)
 		goto out_dput;
+
+	file->f_mode |= FMODE_CREATED;
 out:
-	if (!IS_ERR(dentry)) {
-		if (file->f_mode & FMODE_CREATED)
-			fsnotify_create(dir_inode, dentry);
-		if (file->f_mode & FMODE_OPENED)
-			fsnotify_open(file);
-	}
 	if ((open_flag & O_CREAT) || create_error)
 		inode_unlock(dir_inode);
 	else
@@ -4695,17 +4768,12 @@ struct file *vfs_lookup_open(struct path *parent, struct qstr *last,
 }
 EXPORT_SYMBOL_FOR_MODULES(vfs_lookup_open, "nfsd");
 
-static inline bool trailing_slashes(struct nameidata *nd)
-{
-	return (bool)nd->last.name[nd->last.len];
-}
-
 static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
 {
 	struct dentry *dentry;
 
 	if (open_flag & O_CREAT) {
-		if (trailing_slashes(nd))
+		if (trailing_slashes(&nd->last) && !(open_flag & O_DIRECTORY))
 			return ERR_PTR(-EISDIR);
 
 		/* Don't bother on an O_EXCL create */
@@ -4713,7 +4781,7 @@ static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
 			return NULL;
 	}
 
-	if (trailing_slashes(nd))
+	if (trailing_slashes(&nd->last))
 		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
 
 	dentry = lookup_fast(nd);
@@ -4789,6 +4857,7 @@ finish_lookup:
 static int do_open(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
+	struct vfsmount *mnt;
 	struct mnt_idmap *idmap;
 	int open_flag = op->open_flag;
 	bool do_truncate;
@@ -4806,8 +4875,9 @@ static int do_open(struct nameidata *nd,
 	if (open_flag & O_CREAT) {
 		if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED))
 			return -EEXIST;
-		if (d_is_dir(nd->path.dentry))
+		if (!(open_flag & O_DIRECTORY) && d_is_dir(nd->path.dentry))
 			return -EISDIR;
+
 		error = may_create_in_sticky(idmap, nd,
 					     d_backing_inode(nd->path.dentry));
 		if (unlikely(error))
@@ -4830,11 +4900,17 @@ static int do_open(struct nameidata *nd,
 		error = mnt_want_write(nd->path.mnt);
 		if (error)
 			return error;
+		/*
+		 * A dedicated reference is needed because after the call to
+		 * vfs_open_consume() we no longer own the reference in nd->path.mnt
+		 * while we need to undo write acess below.
+		 */
+		mnt = mntget(nd->path.mnt);
 		do_truncate = true;
 	}
 	error = may_open(idmap, &nd->path, acc_mode, open_flag);
 	if (!error && !(file->f_mode & FMODE_OPENED))
-		error = vfs_open(&nd->path, file);
+		error = vfs_open_consume(&nd->path, file);
 	if (!error)
 		error = security_file_post_open(file, op->acc_mode);
 	if (!error && do_truncate)
@@ -4843,8 +4919,10 @@ static int do_open(struct nameidata *nd,
 		WARN_ON(1);
 		error = -EINVAL;
 	}
-	if (do_truncate)
-		mnt_drop_write(nd->path.mnt);
+	if (do_truncate) {
+		mnt_drop_write(mnt);
+		mntput(mnt);
+	}
 	return error;
 }
 
@@ -5087,7 +5165,7 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 * Do the final lookup.  Suppress 'create' if there is a trailing
 	 * '/', and a directory wasn't requested.
 	 */
-	if (last.name[last.len] && !want_dir)
+	if (trailing_slashes(&last) && !want_dir)
 		create_flags &= ~LOOKUP_CREATE;
 	dentry = start_dirop(path->dentry, &last, reval_flag | create_flags);
 	if (IS_ERR(dentry))
@@ -5182,7 +5260,7 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 		path->dentry = dir;
 		mode = vfs_prepare_mode(idmap, dir_inode, mode, S_IALLUGO, S_IFREG);
 
-		create_error = may_o_create(idmap, path, dentry, mode);
+		create_error = may_o_create(idmap, path, dentry, flags, mode);
 		if (create_error)
 			flags &= ~O_CREAT;
 
@@ -5356,6 +5434,34 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
 	return filename_mknodat(AT_FDCWD, name, mode, dev);
 }
 
+/* Returns the dentry to use (not NULL) or -E on error */
+static inline
+struct dentry *vfs_mkdir_no_perm(struct mnt_idmap *idmap, struct inode *dir,
+				 struct dentry *dentry, umode_t mode,
+				 struct delegated_inode *di)
+{
+	int error;
+	struct dentry *de;
+	unsigned max_links = dir->i_sb->s_max_links;
+
+	if (max_links && dir->i_nlink >= max_links)
+		return ERR_PTR(-EMLINK);
+
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
+	if (error)
+		return ERR_PTR(error);
+
+	de = dir->i_op->mkdir(idmap, dir, dentry, mode);
+	if (IS_ERR(de))
+		return de;
+	if (de) {
+		dput(dentry);
+		dentry = de;
+	}
+	fsnotify_mkdir(dir, dentry);
+	return dentry;
+}
+
 /**
  * vfs_mkdir - create directory returning correct dentry if possible
  * @idmap:		idmap of the mount the inode was found from
@@ -5383,7 +5489,6 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 			 struct delegated_inode *delegated_inode)
 {
 	int error;
-	unsigned max_links = dir->i_sb->s_max_links;
 	struct dentry *de;
 
 	error = may_create_dentry(idmap, dir, dentry);
@@ -5399,24 +5504,12 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		goto err;
 
-	error = -EMLINK;
-	if (max_links && dir->i_nlink >= max_links)
+	de = vfs_mkdir_no_perm(idmap, dir, dentry, mode, delegated_inode);
+	if (IS_ERR(de)) {
+		error = PTR_ERR(de);
 		goto err;
-
-	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
-	if (error)
-		goto err;
-
-	de = dir->i_op->mkdir(idmap, dir, dentry, mode);
-	error = PTR_ERR(de);
-	if (IS_ERR(de))
-		goto err;
-	if (de) {
-		dput(dentry);
-		dentry = de;
 	}
-	fsnotify_mkdir(dir, dentry);
-	return dentry;
+	return de;
 
 err:
 	end_creating(dentry);
@@ -5703,7 +5796,7 @@ retry_deleg:
 		goto exit_drop_write;
 
 	/* Why not before? Because we want correct error value */
-	if (unlikely(last.name[last.len])) {
+	if (unlikely(trailing_slashes(&last))) {
 		if (d_is_dir(dentry))
 			error = -EISDIR;
 		else
@@ -6305,16 +6398,16 @@ retry_deleg:
 	if (flags & RENAME_EXCHANGE) {
 		if (!d_is_dir(rd.new_dentry)) {
 			error = -ENOTDIR;
-			if (new_last.name[new_last.len])
+			if (trailing_slashes(&new_last))
 				goto exit_unlock;
 		}
 	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
 	if (!d_is_dir(rd.old_dentry)) {
 		error = -ENOTDIR;
-		if (old_last.name[old_last.len])
+		if (trailing_slashes(&old_last))
 			goto exit_unlock;
-		if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
+		if (!(flags & RENAME_EXCHANGE) && trailing_slashes(&new_last))
 			goto exit_unlock;
 	}
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 49394123bd09..f01f9013202d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2121,6 +2121,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	dfprintk(VFS, "NFS: atomic_open(%s/%llu), %pd\n",
 			dir->i_sb->s_id, dir->i_ino, dentry);
 
+	if (O_IS_MKDIR(open_flags))
+		open_flags &= ~O_CREAT;
+
 	err = nfs_check_flags(open_flags);
 	if (err)
 		return err;
@@ -2317,6 +2320,9 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
 	 */
 	int error = 0;
 
+	if (O_IS_MKDIR(open_flags))
+		open_flags &= ~O_CREAT;
+
 	if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
 		return -ENAMETOOLONG;
 
diff --git a/fs/open.c b/fs/open.c
index 6b1c14e684a9..a84b55301719 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -931,6 +931,11 @@ cleanup_inode:
 	return error;
 }
 
+/*
+ * Populate struct file
+ *
+ * NOTE: it assumes f_path is populated and consumes the caller's reference.
+ */
 static int do_dentry_open(struct file *f,
 			  int (*open)(struct inode *, struct file *))
 {
@@ -938,7 +943,6 @@ static int do_dentry_open(struct file *f,
 	struct inode *inode = f->f_path.dentry->d_inode;
 	int error;
 
-	path_get(&f->f_path);
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
@@ -1055,6 +1059,7 @@ int finish_open(struct file *file, struct dentry *dentry,
 	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
 	file->__f_path.dentry = dentry;
+	path_get(&file->f_path);
 	return do_dentry_open(file, open);
 }
 EXPORT_SYMBOL(finish_open);
@@ -1098,6 +1103,7 @@ int vfs_open(const struct path *path, struct file *file)
 	int ret;
 
 	file->__f_path = *path;
+	path_get(&file->f_path);
 	ret = do_dentry_open(file, NULL);
 	if (!ret) {
 		/*
@@ -1110,6 +1116,25 @@ int vfs_open(const struct path *path, struct file *file)
 	return ret;
 }
 
+/**
+ * vfs_open_consume - open the file at the given path and consume the reference
+ * @path: path to open
+ * @file: newly allocated file with f_flag initialized
+ */
+int vfs_open_consume(struct path *path, struct file *file)
+{
+	int ret;
+
+	file->__f_path = *path;
+	path->mnt = NULL;
+	path->dentry = NULL;
+	ret = do_dentry_open(file, NULL);
+	if (!ret) {
+		fsnotify_open(file);
+	}
+	return ret;
+}
+
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
 {
@@ -1239,29 +1264,30 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 	if (WILL_CREATE(flags)) {
 		if (how->mode & ~S_IALLUGO)
 			return -EINVAL;
-		op->mode = how->mode | S_IFREG;
+		if (O_IS_MKDIR(flags))
+			op->mode = how->mode | S_IFDIR;
+		else
+			op->mode = how->mode | S_IFREG;
 	} else {
 		if (how->mode != 0)
 			return -EINVAL;
 		op->mode = 0;
 	}
 
-	/*
-	 * Block bugs where O_DIRECTORY | O_CREAT created regular files.
-	 * Note, that blocking O_DIRECTORY | O_CREAT here also protects
-	 * O_TMPFILE below which requires O_DIRECTORY being raised.
-	 */
-	if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT))
-		return -EINVAL;
-
 	/* Now handle the creative implementation of O_TMPFILE. */
 	if (flags & __O_TMPFILE) {
 		/*
 		 * In order to ensure programs get explicit errors when trying
 		 * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY
-		 * is raised alongside __O_TMPFILE.
+		 * is raised alongside __O_TMPFILE, but without O_CREAT. The
+		 * reason for disallowing O_CREAT|O_TMPFILE is that
+		 * O_DIRECTORY|O_CREAT used to work and created a regular file
+		 * if nothing existed at the open path. Hence, allowing the
+		 * combination would have caused O_CREAT|O_TMPFILE to create a
+		 * regular (non-temporary) file on old kernels, while the caller
+		 * would believe they created an actual O_TMPFILE.
 		 */
-		if (!(flags & O_DIRECTORY))
+		if (!(flags & O_DIRECTORY) || (flags & O_CREAT))
 			return -EINVAL;
 		if (!(acc_mode & MAY_WRITE))
 			return -EINVAL;
@@ -1318,6 +1344,15 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 
 	op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
 
+	/*
+	 * Requesting write access on a directory can never succeed. Rather
+	 * than performing a path-walk to determine whether the target is
+	 * actually a directory (-EISDIR) or not (-ENOTDIR), we short-circuit
+	 * to -ENOTDIR.
+	 */
+	if ((flags & O_DIRECTORY) && !(flags & __O_TMPFILE) && (acc_mode & MAY_WRITE))
+		return -ENOTDIR;
+
 	if (flags & O_CREAT) {
 		op->intent |= LOOKUP_CREATE;
 		if (flags & O_EXCL) {
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 6fa6d48fdfd3..f44defb64354 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -534,6 +534,9 @@ int cifs_atomic_open(struct inode *dir, struct dentry *direntry,
 	if (unlikely(cifs_forced_shutdown(cifs_sb)))
 		return smb_EIO(smb_eio_trace_forced_shutdown);
 
+	if (O_IS_MKDIR(oflags))
+		oflags &= ~O_CREAT;
+
 	/*
 	 * Posix open is only called (at lookup time) for file create now. For
 	 * opens (rather than creates), because we do not know if it is a file
diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c
index 0b9eab157432..6e306ddd722b 100644
--- a/fs/vboxsf/dir.c
+++ b/fs/vboxsf/dir.c
@@ -318,6 +318,9 @@ static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry,
 	u64 handle;
 	int err;
 
+	if (O_IS_MKDIR(flags))
+		flags &= ~O_CREAT;
+
 	if (d_in_lookup(dentry)) {
 		struct dentry *res = vboxsf_dir_lookup(parent, dentry, 0);
 		if (res || d_really_is_positive(dentry))
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 6ad6b9e7a226..204e16bbe263 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -30,6 +30,12 @@
  */
 #define __O_REGULAR		(1 << 30)
 
+#define O_MKDIR_MASK	(O_CREAT | O_DIRECTORY)
+static inline bool O_IS_MKDIR(unsigned int flags)
+{
+	return (flags & O_MKDIR_MASK) == O_MKDIR_MASK;
+}
+
 /* List of all valid flags for the how->resolve argument: */
 #define VALID_RESOLVE_FLAGS \
 	(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore
index 9eb185fb2f9d..01c588d4c84f 100644
--- a/tools/testing/selftests/filesystems/.gitignore
+++ b/tools/testing/selftests/filesystems/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
+open_o_creat_o_dir
 dnotify_test
 devpts_pts
 fclog
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 03be337c1f35..0959bd26875a 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 CFLAGS += $(KHDR_INCLUDES)
-TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test
+TEST_GEN_PROGS := open_o_creat_o_dir devpts_pts file_stressor anon_inode_test kernfs_test fclog ustat_test
 TEST_GEN_PROGS += idmapped_tmpfile
 TEST_GEN_PROGS_EXTENDED := dnotify_test
 
diff --git a/tools/testing/selftests/filesystems/open_o_creat_o_dir.c b/tools/testing/selftests/filesystems/open_o_creat_o_dir.c
new file mode 100644
index 000000000000..be0ab34267e1
--- /dev/null
+++ b/tools/testing/selftests/filesystems/open_o_creat_o_dir.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/stat.h>
+#include <errno.h>
+#include <limits.h>
+#include <fcntl.h>
+
+#include "kselftest_harness.h"
+#include "wrappers.h"
+
+#define openat_o_mkdir_checked_flags(dfd, pathname, flags) ({	\
+	struct stat __st;						\
+	int __fd = openat_o_mkdir(dfd, pathname, flags, S_IRWXU);	\
+	ASSERT_GE(__fd, 0);						\
+	ASSERT_EQ(fstat(__fd, &__st), 0);				\
+	EXPECT_TRUE(S_ISDIR(__st.st_mode));				\
+	__fd;								\
+})
+
+#define openat_o_mkdir_checked(dfd, pathname) \
+	openat_o_mkdir_checked_flags(dfd, pathname, O_RDONLY)
+
+FIXTURE(open_o_creat_o_dir) {
+	char dirpath[PATH_MAX];
+	int dfd;
+};
+
+FIXTURE_SETUP(open_o_creat_o_dir)
+{
+	strcpy(self->dirpath, "/tmp/open_o_creat_o_dir_test.XXXXXX");
+	ASSERT_NE(mkdtemp(self->dirpath), NULL);
+	self->dfd = open(self->dirpath, O_DIRECTORY);
+	ASSERT_GE(self->dfd, 0);
+}
+
+FIXTURE_TEARDOWN(open_o_creat_o_dir)
+{
+	close(self->dfd);
+	rmdir(self->dirpath);
+}
+
+/* Does open_o_creat_o_dir return a fd at all? */
+TEST_F(open_o_creat_o_dir, returns_fd)
+{
+	int fd = openat_o_mkdir_checked(self->dfd, "newdir");
+	EXPECT_EQ(close(fd), 0);
+	EXPECT_EQ(unlinkat(self->dfd, "newdir", AT_REMOVEDIR), 0);
+}
+
+/* The fd must refer to the directory that was just created. */
+TEST_F(open_o_creat_o_dir, fd_is_created_dir)
+{
+	int fd;
+	struct stat st_via_fd, st_via_path;
+	char path[PATH_MAX];
+
+	fd = openat_o_mkdir_checked(self->dfd, "checkdir");
+
+	ASSERT_EQ(fstat(fd, &st_via_fd), 0);
+
+	snprintf(path, sizeof(path), "%s/checkdir", self->dirpath);
+	ASSERT_EQ(stat(path, &st_via_path), 0);
+
+	EXPECT_EQ(st_via_fd.st_ino, st_via_path.st_ino);
+	EXPECT_EQ(st_via_fd.st_dev, st_via_path.st_dev);
+
+	EXPECT_EQ(close(fd), 0);
+	EXPECT_EQ(rmdir(path), 0);
+}
+
+/* Missing parent component must fail with ENOENT. */
+TEST_F(open_o_creat_o_dir, enoent_missing_parent)
+{
+	EXPECT_EQ(openat_o_mkdir(self->dfd, "nonexistent/child", O_RDONLY, S_IRWXU), -1);
+	EXPECT_EQ(errno, ENOENT);
+}
+
+/* An invalid dfd must fail with EBADF. */
+TEST_F(open_o_creat_o_dir, ebadf)
+{
+	EXPECT_EQ(openat_o_mkdir(FD_INVALID, "badfdir", O_RDONLY, S_IRWXU), -1);
+	EXPECT_EQ(errno, EBADF);
+}
+
+/* A dfd that points to a file (not a directory) must fail with ENOTDIR. */
+TEST_F(open_o_creat_o_dir, enotdir_dfd)
+{
+	int file_fd;
+
+	file_fd = openat(self->dfd, "file",
+			 O_CREAT | O_RDONLY, S_IRWXU);
+	ASSERT_GE(file_fd, 0);
+
+	EXPECT_EQ(openat_o_mkdir(file_fd, "subdir", O_RDONLY, S_IRWXU), -1);
+	EXPECT_EQ(errno, ENOTDIR);
+
+	EXPECT_EQ(close(file_fd), 0);
+	EXPECT_EQ(unlinkat(self->dfd, "file", 0), 0);
+}
+
+/*
+ * O_EXCL together with O_CREAT|O_DIRECTORY should succeed if the target
+ * directory does not yet exist. After directory creation, repeating this
+ * call must fail with EEXIST.
+ */
+TEST_F(open_o_creat_o_dir, o_excl_eexist)
+{
+	int excldir_fd;
+
+	excldir_fd = openat_o_mkdir_checked_flags(self->dfd, "excldir", O_EXCL);
+
+	EXPECT_EQ(openat_o_mkdir(excldir_fd, ".", O_EXCL, S_IRWXU), -1);
+	EXPECT_EQ(errno, EEXIST);
+
+	EXPECT_EQ(close(excldir_fd), 0);
+	EXPECT_EQ(unlinkat(self->dfd, "excldir", AT_REMOVEDIR), 0);
+}
+
+/*
+ * O_CREAT|O_DIRECTORY on a path that already exists as a regular file
+ * must fail with ENOTDIR.
+ */
+TEST_F(open_o_creat_o_dir, existing_file_enotdir)
+{
+	int file_fd;
+
+	file_fd = openat(self->dfd, "regfile",
+			 O_CREAT | O_RDONLY, S_IRWXU);
+	ASSERT_GE(file_fd, 0);
+	EXPECT_EQ(close(file_fd), 0);
+
+	EXPECT_EQ(openat_o_mkdir(self->dfd, "regfile", O_RDONLY, S_IRWXU), -1);
+	EXPECT_EQ(errno, ENOTDIR);
+
+	EXPECT_EQ(unlinkat(self->dfd, "regfile", 0), 0);
+}
+
+/*
+ * O_CREAT|O_DIRECTORY combined with a writable access mode must be
+ * rejected: a directory cannot be opened for writing.
+ */
+TEST_F(open_o_creat_o_dir, rejects_writable_acc_mode)
+{
+	EXPECT_EQ(openat_o_mkdir(self->dfd, "rdwrdir", O_RDWR, S_IRWXU), -1);
+	EXPECT_EQ(errno, ENOTDIR);
+	/* Clean up if the kernel created the directory anyway. */
+	unlinkat(self->dfd, "rdwrdir", AT_REMOVEDIR);
+}
+
+/*
+ * openat(O_CREAT|O_DIRECTORY) with a trailing slash should work.
+ */
+TEST_F(open_o_creat_o_dir, trailing_slash)
+{
+	int fd = openat_o_mkdir_checked(self->dfd, "newdir/");
+	EXPECT_EQ(close(fd), 0);
+	EXPECT_EQ(unlinkat(self->dfd, "newdir", AT_REMOVEDIR), 0);
+}
+
+/*
+ * openat(O_CREAT) with a trailing slash but without O_DIRECTORY
+ * must fail with EISDIR and must not create anything at the path.
+ */
+TEST_F(open_o_creat_o_dir, trailing_slash_no_o_dir)
+{
+	int fd;
+	struct stat st;
+
+	fd = openat(self->dfd, "trailing/", O_CREAT | O_RDONLY, S_IRWXU);
+	EXPECT_EQ(fd, -1);
+	EXPECT_EQ(errno, EISDIR);
+
+	EXPECT_EQ(fstatat(self->dfd, "trailing", &st, 0), -1);
+	EXPECT_EQ(errno, ENOENT);
+
+	/* Best-effort cleanup in case the kernel left a file behind. */
+	if (fd >= 0)
+		close(fd);
+	unlinkat(self->dfd, "trailing", 0);
+}
+
+/*
+ * The returned fd must be usable as a dfd for further *at() calls.
+ */
+TEST_F(open_o_creat_o_dir, fd_usable_as_dfd)
+{
+	int parent_fd, child_fd;
+	char path[PATH_MAX];
+
+	parent_fd = openat_o_mkdir_checked(self->dfd, "parent");
+	child_fd = openat_o_mkdir_checked(parent_fd, "child");
+
+	EXPECT_EQ(close(child_fd), 0);
+	EXPECT_EQ(close(parent_fd), 0);
+
+	snprintf(path, sizeof(path), "%s/parent/child", self->dirpath);
+	EXPECT_EQ(rmdir(path), 0);
+	snprintf(path, sizeof(path), "%s/parent", self->dirpath);
+	EXPECT_EQ(rmdir(path), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/filesystems/wrappers.h b/tools/testing/selftests/filesystems/wrappers.h
index 420ae4f908cf..abe5b85cebdc 100644
--- a/tools/testing/selftests/filesystems/wrappers.h
+++ b/tools/testing/selftests/filesystems/wrappers.h
@@ -13,6 +13,10 @@
 #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
 #endif
 
+#ifndef FD_INVALID
+#define FD_INVALID -10009
+#endif
+
 static inline int sys_fsopen(const char *fsname, unsigned int flags)
 {
 	return syscall(__NR_fsopen, fsname, flags);
@@ -105,4 +109,11 @@ static inline int sys_open_tree(int dfd, const char *filename, unsigned int flag
 	return syscall(__NR_open_tree, dfd, filename, flags);
 }
 
+static inline int openat_o_mkdir(int dfd, const char *pathname,
+				 unsigned int flags, mode_t mode)
+{
+	return syscall(__NR_openat, dfd, pathname,
+		       flags | O_DIRECTORY | O_CREAT, mode);
+}
+
 #endif