From: Jeff Xu <[email protected]>
Since Linux introduced the memfd feature, memfd have always had their
execute bit set, and the memfd_create() syscall doesn't allow setting
it differently.
However, in a secure by default system, such as ChromeOS, (where all
executables should come from the rootfs, which is protected by Verified
boot), this executable nature of memfd opens a door for NoExec bypass
and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
process created a memfd to share the content with an external process,
however the memfd is overwritten and used for executing arbitrary code
and root escalation. [2] lists more VRP in this kind.
On the other hand, executable memfd has its legit use, runc uses memfd’s
seal and executable feature to copy the contents of the binary then
execute them, for such system, we need a solution to differentiate runc's
use of executable memfds and an attacker's [3].
To address those above, this set of patches add following:
1> Let memfd_create() set X bit at creation time.
2> Let memfd to be sealed for modifying X bit.
3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of
X bit.For example, if a container has vm.memfd_noexec=2, then
memfd_create() without MFD_NOEXEC_SEAL will be rejected.
4> A new security hook in memfd_create(). This make it possible to a new
LSM, which rejects or allows executable memfd based on its security policy.
Change history:
v7:
- patch 2/6: remove #ifdef and MAX_PATH (memfd_test.c).
- patch 3/6: check capability (CAP_SYS_ADMIN) from userns instead of
global ns (pid_sysctl.h). Add a tab (pid_namespace.h).
- patch 5/6: remove #ifdef (memfd_test.c)
- patch 6/6: remove unneeded security_move_mount(security.c).
v6:https://lore.kernel.org/lkml/[email protected]/
- Address comment and move "#ifdef CONFIG_" from .c file to pid_sysctl.h
v5:https://lore.kernel.org/lkml/[email protected]/
- Pass vm.memfd_noexec from current ns to child ns.
- Fix build issue detected by kernel test robot.
- Add missing security.c
v3:https://lore.kernel.org/lkml/[email protected]/
- Address API design comments in v2.
- Let memfd_create() to set X bit at creation time.
- A new pid namespace sysctl: vm.memfd_noexec to control behavior of X bit.
- A new security hook in memfd_create().
v2:https://lore.kernel.org/lkml/[email protected]/
- address comments in V1.
- add sysctl (vm.mfd_noexec) to set the default file permissions of
memfd_create to be non-executable.
v1:https://lwn.net/Articles/890096/
[1] https://crbug.com/1305411
[2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20memfd%20escalation&can=1
[3] https://lwn.net/Articles/781013/
Daniel Verkamp (2):
mm/memfd: add F_SEAL_EXEC
selftests/memfd: add tests for F_SEAL_EXEC
Jeff Xu (4):
mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC
mm/memfd: Add write seals when apply SEAL_EXEC to executable memfd
selftests/memfd: add tests for MFD_NOEXEC_SEAL MFD_EXEC
mm/memfd: security hook for memfd_create
include/linux/lsm_hook_defs.h | 1 +
include/linux/lsm_hooks.h | 4 +
include/linux/pid_namespace.h | 19 ++
include/linux/security.h | 6 +
include/uapi/linux/fcntl.h | 1 +
include/uapi/linux/memfd.h | 4 +
kernel/pid_namespace.c | 5 +
kernel/pid_sysctl.h | 59 ++++
mm/memfd.c | 61 +++-
mm/shmem.c | 6 +
security/security.c | 5 +
tools/testing/selftests/memfd/fuse_test.c | 1 +
tools/testing/selftests/memfd/memfd_test.c | 341 ++++++++++++++++++++-
13 files changed, 510 insertions(+), 3 deletions(-)
create mode 100644 kernel/pid_sysctl.h
base-commit: eb7081409f94a9a8608593d0fb63a1aa3d6f95d8
--
2.39.0.rc1.256.g54fd8350bd-goog
On Fri, Dec 9, 2022 at 11:05 AM <[email protected]> wrote:
> From: Jeff Xu <[email protected]>
>
> Since Linux introduced the memfd feature, memfd have always had their
> execute bit set, and the memfd_create() syscall doesn't allow setting
> it differently.
>
> However, in a secure by default system, such as ChromeOS, (where all
> executables should come from the rootfs, which is protected by Verified
> boot), this executable nature of memfd opens a door for NoExec bypass
> and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
> process created a memfd to share the content with an external process,
> however the memfd is overwritten and used for executing arbitrary code
> and root escalation. [2] lists more VRP in this kind.
...
> [1] https://crbug.com/1305411
Can you make this accessible so those of us on the public lists can
view this bug? If not, please remove it from future postings and
adjust your description accordingly.
--
paul-moore.com
On Fri, Dec 09, 2022 at 04:04:47PM +0000, [email protected] wrote:
> From: Jeff Xu <[email protected]>
>
> Since Linux introduced the memfd feature, memfd have always had their
> execute bit set, and the memfd_create() syscall doesn't allow setting
> it differently.
>
> However, in a secure by default system, such as ChromeOS, (where all
> executables should come from the rootfs, which is protected by Verified
> boot), this executable nature of memfd opens a door for NoExec bypass
> and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
> process created a memfd to share the content with an external process,
> however the memfd is overwritten and used for executing arbitrary code
> and root escalation. [2] lists more VRP in this kind.
>
> On the other hand, executable memfd has its legit use, runc uses memfd’s
> seal and executable feature to copy the contents of the binary then
> execute them, for such system, we need a solution to differentiate runc's
> use of executable memfds and an attacker's [3].
>
> To address those above, this set of patches add following:
> 1> Let memfd_create() set X bit at creation time.
> 2> Let memfd to be sealed for modifying X bit.
> 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of
> X bit.For example, if a container has vm.memfd_noexec=2, then
> memfd_create() without MFD_NOEXEC_SEAL will be rejected.
> 4> A new security hook in memfd_create(). This make it possible to a new
> LSM, which rejects or allows executable memfd based on its security policy.
I think patch 1-5 look good to land. The LSM hook seems separable, and
could continue on its own. Thoughts?
(Which tree should memfd change go through?)
-Kees
--
Kees Cook
On Wed, Dec 14, 2022 at 10:54 AM Kees Cook <[email protected]> wrote:
>
> On Fri, Dec 09, 2022 at 04:04:47PM +0000, [email protected] wrote:
> > From: Jeff Xu <[email protected]>
> >
> > Since Linux introduced the memfd feature, memfd have always had their
> > execute bit set, and the memfd_create() syscall doesn't allow setting
> > it differently.
> >
> > However, in a secure by default system, such as ChromeOS, (where all
> > executables should come from the rootfs, which is protected by Verified
> > boot), this executable nature of memfd opens a door for NoExec bypass
> > and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
> > process created a memfd to share the content with an external process,
> > however the memfd is overwritten and used for executing arbitrary code
> > and root escalation. [2] lists more VRP in this kind.
> >
> > On the other hand, executable memfd has its legit use, runc uses memfd’s
> > seal and executable feature to copy the contents of the binary then
> > execute them, for such system, we need a solution to differentiate runc's
> > use of executable memfds and an attacker's [3].
> >
> > To address those above, this set of patches add following:
> > 1> Let memfd_create() set X bit at creation time.
> > 2> Let memfd to be sealed for modifying X bit.
> > 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of
> > X bit.For example, if a container has vm.memfd_noexec=2, then
> > memfd_create() without MFD_NOEXEC_SEAL will be rejected.
> > 4> A new security hook in memfd_create(). This make it possible to a new
> > LSM, which rejects or allows executable memfd based on its security policy.
>
> I think patch 1-5 look good to land. The LSM hook seems separable, and
> could continue on its own. Thoughts?
>
Agreed.
> (Which tree should memfd change go through?)
>
I'm not sure, is there a recommendation ?
Thanks.
Jeff
> -Kees
>
> --
> Kees Cook
On Wed, Dec 14, 2022 at 03:32:16PM -0800, Jeff Xu wrote:
> On Wed, Dec 14, 2022 at 10:54 AM Kees Cook <[email protected]> wrote:
> >
> > On Fri, Dec 09, 2022 at 04:04:47PM +0000, [email protected] wrote:
> > > From: Jeff Xu <[email protected]>
> > >
> > > Since Linux introduced the memfd feature, memfd have always had their
> > > execute bit set, and the memfd_create() syscall doesn't allow setting
> > > it differently.
> > >
> > > However, in a secure by default system, such as ChromeOS, (where all
> > > executables should come from the rootfs, which is protected by Verified
> > > boot), this executable nature of memfd opens a door for NoExec bypass
> > > and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
> > > process created a memfd to share the content with an external process,
> > > however the memfd is overwritten and used for executing arbitrary code
> > > and root escalation. [2] lists more VRP in this kind.
> > >
> > > On the other hand, executable memfd has its legit use, runc uses memfd’s
> > > seal and executable feature to copy the contents of the binary then
> > > execute them, for such system, we need a solution to differentiate runc's
> > > use of executable memfds and an attacker's [3].
> > >
> > > To address those above, this set of patches add following:
> > > 1> Let memfd_create() set X bit at creation time.
> > > 2> Let memfd to be sealed for modifying X bit.
> > > 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of
> > > X bit.For example, if a container has vm.memfd_noexec=2, then
> > > memfd_create() without MFD_NOEXEC_SEAL will be rejected.
> > > 4> A new security hook in memfd_create(). This make it possible to a new
> > > LSM, which rejects or allows executable memfd based on its security policy.
> >
> > I think patch 1-5 look good to land. The LSM hook seems separable, and
> > could continue on its own. Thoughts?
> >
> Agreed.
>
> > (Which tree should memfd change go through?)
> >
> I'm not sure, is there a recommendation ?
It looks like it's traditionally through akpm's tree. Andrew, will you
carry patches 1-5?
Thanks!
--
Kees Cook
On Wed, Dec 14, 2022 at 4:08 PM Kees Cook <[email protected]> wrote:
>
> On Wed, Dec 14, 2022 at 03:32:16PM -0800, Jeff Xu wrote:
> > On Wed, Dec 14, 2022 at 10:54 AM Kees Cook <[email protected]> wrote:
> > >
> > > On Fri, Dec 09, 2022 at 04:04:47PM +0000, [email protected] wrote:
> > > > From: Jeff Xu <[email protected]>
> > > >
> > > > Since Linux introduced the memfd feature, memfd have always had their
> > > > execute bit set, and the memfd_create() syscall doesn't allow setting
> > > > it differently.
> > > >
> > > > However, in a secure by default system, such as ChromeOS, (where all
> > > > executables should come from the rootfs, which is protected by Verified
> > > > boot), this executable nature of memfd opens a door for NoExec bypass
> > > > and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm
> > > > process created a memfd to share the content with an external process,
> > > > however the memfd is overwritten and used for executing arbitrary code
> > > > and root escalation. [2] lists more VRP in this kind.
> > > >
> > > > On the other hand, executable memfd has its legit use, runc uses memfd’s
> > > > seal and executable feature to copy the contents of the binary then
> > > > execute them, for such system, we need a solution to differentiate runc's
> > > > use of executable memfds and an attacker's [3].
> > > >
> > > > To address those above, this set of patches add following:
> > > > 1> Let memfd_create() set X bit at creation time.
> > > > 2> Let memfd to be sealed for modifying X bit.
> > > > 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of
> > > > X bit.For example, if a container has vm.memfd_noexec=2, then
> > > > memfd_create() without MFD_NOEXEC_SEAL will be rejected.
> > > > 4> A new security hook in memfd_create(). This make it possible to a new
> > > > LSM, which rejects or allows executable memfd based on its security policy.
> > >
> > > I think patch 1-5 look good to land. The LSM hook seems separable, and
> > > could continue on its own. Thoughts?
> > >
> > Agreed.
> >
> > > (Which tree should memfd change go through?)
> > >
> > I'm not sure, is there a recommendation ?
>
> It looks like it's traditionally through akpm's tree. Andrew, will you
> carry patches 1-5?
>
Hi Andrew, if you are taking this, V8 is the latest that contains patch 1-5.
Thanks
Jeff
> Thanks!
>
> --
> Kees Cook