pid namespaces: introduce MS_KERNMOUNT flag

This flag tells the .get_sb callback that this is a kern_mount() call so that
it can trust *data pointer to be valid in-kernel one.  If this flag is passed
from the user process, it is cleared since the *data pointer is not a valid
kernel object.

Running a few steps forward - this will be needed for proc to create the
superblock and store a valid pid namespace on it during the namespace
creation.  The reason, why the namespace cannot live without proc mount is
described in the appropriate patch.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 7 insertions, 5 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 07daa7972591..860752998fb3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1411,7 +1411,7 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
                 mnt_flags |= MNT_RELATIME;
 
         flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
-                   MS_NOATIME | MS_NODIRATIME | MS_RELATIME);
+                   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);
 
         /* ... and get the mountpoint */
         retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd);
diff --git a/fs/super.c b/fs/super.c
index feaae7eeaffd..d28fde7e1cfb 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -944,9 +944,9 @@ do_kern_mount(const char *fstype, int flags, const char *name, void *data)
         return mnt;
 }
 
-struct vfsmount *kern_mount(struct file_system_type *type)
+struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
 {
-        return vfs_kern_mount(type, 0, type->name, NULL);
+        return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
 }
 
-EXPORT_SYMBOL(kern_mount);
+EXPORT_SYMBOL_GPL(kern_mount_data);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3efff12049c6..1657e995f72c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -123,6 +123,7 @@ extern int dir_notify_enable;
 #define MS_SLAVE        (1<<19) /* change to slave */
 #define MS_SHARED       (1<<20) /* change to shared */
 #define MS_RELATIME     (1<<21) /* Update atime relative to mtime/ctime. */
+#define MS_KERNMOUNT    (1<<22) /* this is a kern_mount call */
 #define MS_ACTIVE       (1<<30)
 #define MS_NOUSER       (1<<31)
 
@@ -1459,7 +1460,8 @@ void unnamed_dev_init(void);
 
 extern int register_filesystem(struct file_system_type *);
 extern int unregister_filesystem(struct file_system_type *);
-extern struct vfsmount *kern_mount(struct file_system_type *);
+extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
+#define kern_mount(type) kern_mount_data(type, NULL)
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 extern void umount_tree(struct vfsmount *, int, struct list_head *);