@@ -1031,7 +1031,7 @@ static int __init fcntl_init(void)
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(25 - 1 /* for O_RDONLY being 0 */ !=
+ BUILD_BUG_ON(26 - 1 /* for O_RDONLY being 0 */ !=
HWEIGHT32(
(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
__FMODE_EXEC | __FMODE_NONOTIFY));
@@ -1097,7 +1097,7 @@ const char *get_link(struct nameidata *nd)
if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
return ERR_PTR(-ELOOP);
/* Not currently safe. */
- if (unlikely(nd->flags & LOOKUP_BENEATH))
+ if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
return ERR_PTR(-EXDEV);
}
if (IS_ERR_OR_NULL(res))
@@ -1746,7 +1746,7 @@ static inline int handle_dots(struct nameidata *nd, int type)
* cause our parent to have moved outside of the root and us to skip
* over it.
*/
- if (unlikely(nd->flags & LOOKUP_BENEATH))
+ if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
return -EXDEV;
if (!nd->root.mnt)
set_root(nd);
@@ -2297,7 +2297,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->m_seq = read_seqbegin(&mount_lock);
- if (unlikely(nd->flags & LOOKUP_BENEATH)) {
+ if (unlikely(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT))) {
error = dirfd_path_init(nd);
if (unlikely(error))
return ERR_PTR(error);
@@ -960,7 +960,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
* cannot have anything other than the below set of flags
*/
flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH | O_BENEATH |
- O_XDEV | O_NOSYMLINKS | O_NOMAGICLINKS;
+ O_XDEV | O_NOSYMLINKS | O_NOMAGICLINKS | O_THISROOT;
acc_mode = 0;
}
@@ -997,6 +997,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
lookup_flags |= LOOKUP_NO_MAGICLINKS;
if (flags & O_NOSYMLINKS)
lookup_flags |= LOOKUP_NO_SYMLINKS;
+ if (flags & O_THISROOT)
+ lookup_flags |= LOOKUP_IN_ROOT;
op->lookup_flags = lookup_flags;
return 0;
}
@@ -10,7 +10,7 @@
O_APPEND | O_NDELAY | O_NONBLOCK | O_NDELAY | __O_SYNC | O_DSYNC | \
FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE | O_BENEATH | O_XDEV | \
- O_NOMAGICLINKS | O_NOSYMLINKS)
+ O_NOMAGICLINKS | O_NOSYMLINKS | O_THISROOT)
#ifndef force_o_largefile
#define force_o_largefile() (BITS_PER_LONG != 32)
@@ -53,6 +53,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
#define LOOKUP_NO_MAGICLINKS 0x040000 /* No /proc/$pid/fd/ "symlink" crossing. */
#define LOOKUP_NO_SYMLINKS 0x080000 /* No symlink crossing *at all*.
Implies LOOKUP_NO_MAGICLINKS. */
+#define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as %current->fs->root. */
extern int path_pts(struct path *path);
@@ -110,6 +110,9 @@
#ifndef O_NOSYMLINKS
#define O_NOSYMLINKS 01000000000 /* - Block all symlinks (implies AT_NO_MAGICLINKS). */
#endif
+#ifndef O_THISROOT
+#define O_THISROOT 02000000000 /* - Scope ".." resolution to dirfd (like chroot(2)). */
+#endif
#define F_DUPFD 0 /* dup */
#define F_GETFD 1 /* get close_on_exec */
The primary motivation for the need for this flag is container runtimes which have to interact with malicious root filesystems in the host namespaces. One of the first requirements for a container runtime to be secure against a malicious rootfs is that they correctly scope symlinks (that is, they should be scoped as though they are chroot(2)ed into the container's rootfs) and ".."-style paths[*]. The already-existing O_XDEV and O_NOMAGICLINKS[**] help defend against other potential attacks in a malicious rootfs scenario. Currently most container runtimes try to do this resolution in userspace[1], causing many potential race conditions. In addition, the "obvious" alternative (actually performing a {ch,pivot_}root(2)) requires a fork+exec (for some runtimes) which is *very* costly if necessary for every filesystem operation involving a container. [*] At the moment, ".." and "magic link" jumping are disallowed for the same reason it is disabled for O_BENEATH -- currently it is not safe to allow it. Future patches may enable it unconditionally once we have resolved the possible races (for "..") and semantics (for "magic link" jumping). The most significant openat(2) semantic change with O_THISROOT is that absolute pathnames no longer cause dirfd to be ignored completely. The rationale is that O_THISROOT must necessarily chroot-scope symlinks with absolute paths to dirfd, and so doing it for the base path seems to be the most consistent behaviour (and also avoids foot-gunning users who want to scope paths that are absolute). Currently this is only enabled for openat(2), and similar to O_BENEATH and family requires more discussion about extending it to more *at(2) syscalls as well as extending AT_EMPTY_PATH support. [1]: https://github.com/cyphar/filepath-securejoin Cc: Eric Biederman <ebiederm@xmission.com> Cc: Christian Brauner <christian@brauner.io> Cc: Kees Cook <keescook@chromium.org> Signed-off-by: Aleksa Sarai <cyphar@cyphar.com> --- fs/fcntl.c | 2 +- fs/namei.c | 6 +++--- fs/open.c | 4 +++- include/linux/fcntl.h | 2 +- include/linux/namei.h | 1 + include/uapi/asm-generic/fcntl.h | 3 +++ 6 files changed, 12 insertions(+), 6 deletions(-)