From b0fd30d3e7e768aad5e398caaea6ae5a5c814eab Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 22 May 2008 09:33:34 -0400 Subject: when creating new inodes, use file_mode/dir_mode exclusively on mount without unix extensions When CIFS creates a new inode on a mount without unix extensions, it temporarily assigns the mode that was passed to it in the create/mkdir call. Eventually, when the inode is revalidated, it changes to have the file_mode or dir_mode for the mount. This is confusing to users who expect that the mode shouldn't change this way. It's also problematic since only the mode is treated this way, not the uid or gid. Suppose you have a CIFS mount that's mounted with: uid=0,gid=0,file_mode=0666,dir_mode=0777 ...if an unprivileged user comes along and does this on the mount: mkdir -m 0700 foo touch foo/bar ...there is a period of time where the touch will fail, since the dir will initially be owned by root and have mode 0700. If the user waits long enough, then "foo" will be revalidated and will get the correct dir_mode permissions. This patch changes cifs_mkdir and cifs_create to not overwrite the mode found by the initial cifs_get_inode_info call after the inode is created on the server. Legacy behavior can be reenabled with the new "dynperm" mount option. Signed-off-by: Jeff Layton Signed-off-by: Steve French --- fs/cifs/dir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/cifs/dir.c') diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f0b5b5f3dd2..fb69c1fa85c 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -260,7 +260,9 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, buf, inode->i_sb, xid, &fileHandle); if (newinode) { - newinode->i_mode = mode; + if (cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_DYNPERM) + newinode->i_mode = mode; if ((oplock & CIFS_CREATE_ACTION) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { -- cgit v1.2.3-70-g09d2