diff options
author | Jeff Layton <jlayton@redhat.com> | 2010-07-20 00:00:17 +0200 |
---|---|---|
committer | Steve French <sfrench@us.ibm.com> | 2010-08-02 14:40:39 +0200 |
commit | 3e4b3e1f68c10510ec8d3076cffc5729b88f8de6 (patch) | |
tree | bee962570f8a54547cfb67550f76874d82981fea /fs/cifs/cifsglob.h | |
parent | fs: cifs: check kmalloc() result (diff) | |
download | linux-3e4b3e1f68c10510ec8d3076cffc5729b88f8de6.tar.xz linux-3e4b3e1f68c10510ec8d3076cffc5729b88f8de6.zip |
cifs: add separate cred_uid field to sesInfo
Right now, there's no clear separation between the uid that owns the
credentials used to do the mount and the overriding owner of the files
on that mount.
Add a separate cred_uid field that is set to the real uid
of the mount user. Unlike the linux_uid, the uid= option does not
override this parameter. The parm is sent to cifs.upcall, which can then
preferentially use the creduid= parm instead of the uid= parm for
finding credentials.
This is not the only way to solve this. We could try to do all of this
in kernel instead by having a module parameter that affects what gets
passed in the uid= field of the upcall. That said, we have a lot more
flexibility to change things in userspace so I think it probably makes
sense to do it this way.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
Diffstat (limited to 'fs/cifs/cifsglob.h')
-rw-r--r-- | fs/cifs/cifsglob.h | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 9b7cf9aa3a00..59906146ad36 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -214,7 +214,8 @@ struct cifsSesInfo { char *serverNOS; /* name of network operating system of server */ char *serverDomain; /* security realm of server */ int Suid; /* remote smb uid */ - uid_t linux_uid; /* local Linux uid */ + uid_t linux_uid; /* overriding owner of files on the mount */ + uid_t cred_uid; /* owner of credentials */ int capabilities; char serverName[SERVER_NAME_LEN_WITH_NULL * 2]; /* BB make bigger for TCP names - will ipv6 and sctp addresses fit? */ |