1 files changed, 69 insertions, 15 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 74f7c66c3e5c..a4cba6991a4d 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
@@ -2900,6 +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)
 {
@@ -2909,8 +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;
@@ -3180,8 +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;
@@ -3457,8 +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;
@@ -3717,6 +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;
@@ -3765,9 +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) {
@@ -3815,7 +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;
@@ -3842,9 +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);