summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-05-01 18:50:44 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-05-01 18:50:44 -0700
commit17ae69aba89dbfa2139b7f8024b757ab3cc42f59 (patch)
treed0d13c06cf9bb3024563036a9ba5213b06b454e0
parente6f0bf09f0669b3c2cd77fa906830123279a0a21 (diff)
parent3532b0b4352ce79400b0aa68414f1a0fc422b920 (diff)
Merge tag 'landlock_v34' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security
Pull Landlock LSM from James Morris: "Add Landlock, a new LSM from Mickaël Salaün. Briefly, Landlock provides for unprivileged application sandboxing. From Mickaël's cover letter: "The goal of Landlock is to enable to restrict ambient rights (e.g. global filesystem access) for a set of processes. Because Landlock is a stackable LSM [1], it makes possible to create safe security sandboxes as new security layers in addition to the existing system-wide access-controls. This kind of sandbox is expected to help mitigate the security impact of bugs or unexpected/malicious behaviors in user-space applications. Landlock empowers any process, including unprivileged ones, to securely restrict themselves. Landlock is inspired by seccomp-bpf but instead of filtering syscalls and their raw arguments, a Landlock rule can restrict the use of kernel objects like file hierarchies, according to the kernel semantic. Landlock also takes inspiration from other OS sandbox mechanisms: XNU Sandbox, FreeBSD Capsicum or OpenBSD Pledge/Unveil. In this current form, Landlock misses some access-control features. This enables to minimize this patch series and ease review. This series still addresses multiple use cases, especially with the combined use of seccomp-bpf: applications with built-in sandboxing, init systems, security sandbox tools and security-oriented APIs [2]" The cover letter and v34 posting is here: https://lore.kernel.org/linux-security-module/20210422154123.13086-1-mic@digikod.net/ See also: https://landlock.io/ This code has had extensive design discussion and review over several years" Link: https://lore.kernel.org/lkml/50db058a-7dde-441b-a7f9-f6837fe8b69f@schaufler-ca.com/ [1] Link: https://lore.kernel.org/lkml/f646e1c7-33cf-333f-070c-0a40ad0468cd@digikod.net/ [2] * tag 'landlock_v34' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: landlock: Enable user space to infer supported features landlock: Add user and kernel documentation samples/landlock: Add a sandbox manager example selftests/landlock: Add user space tests landlock: Add syscall implementations arch: Wire up Landlock syscalls fs,security: Add sb_delete hook landlock: Support filesystem access-control LSM: Infrastructure management of the superblock landlock: Add ptrace restrictions landlock: Set up the security framework and manage credentials landlock: Add ruleset and domain management landlock: Add object management
-rw-r--r--Documentation/security/index.rst1
-rw-r--r--Documentation/security/landlock.rst85
-rw-r--r--Documentation/userspace-api/index.rst1
-rw-r--r--Documentation/userspace-api/landlock.rst311
-rw-r--r--MAINTAINERS15
-rw-r--r--arch/Kconfig7
-rw-r--r--arch/alpha/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/arm/tools/syscall.tbl3
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h6
-rw-r--r--arch/ia64/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/m68k/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/microblaze/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/mips/kernel/syscalls/syscall_n32.tbl3
-rw-r--r--arch/mips/kernel/syscalls/syscall_n64.tbl3
-rw-r--r--arch/mips/kernel/syscalls/syscall_o32.tbl3
-rw-r--r--arch/parisc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/sh/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/sparc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/um/Kconfig1
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl3
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl3
-rw-r--r--arch/xtensa/kernel/syscalls/syscall.tbl3
-rw-r--r--fs/super.c1
-rw-r--r--include/linux/lsm_hook_defs.h1
-rw-r--r--include/linux/lsm_hooks.h4
-rw-r--r--include/linux/security.h4
-rw-r--r--include/linux/syscalls.h7
-rw-r--r--include/uapi/asm-generic/unistd.h9
-rw-r--r--include/uapi/linux/landlock.h137
-rw-r--r--kernel/sys_ni.c5
-rw-r--r--samples/Kconfig7
-rw-r--r--samples/Makefile1
-rw-r--r--samples/landlock/.gitignore1
-rw-r--r--samples/landlock/Makefile13
-rw-r--r--samples/landlock/sandboxer.c238
-rw-r--r--security/Kconfig11
-rw-r--r--security/Makefile2
-rw-r--r--security/landlock/Kconfig21
-rw-r--r--security/landlock/Makefile4
-rw-r--r--security/landlock/common.h20
-rw-r--r--security/landlock/cred.c46
-rw-r--r--security/landlock/cred.h58
-rw-r--r--security/landlock/fs.c692
-rw-r--r--security/landlock/fs.h70
-rw-r--r--security/landlock/limits.h21
-rw-r--r--security/landlock/object.c67
-rw-r--r--security/landlock/object.h91
-rw-r--r--security/landlock/ptrace.c120
-rw-r--r--security/landlock/ptrace.h14
-rw-r--r--security/landlock/ruleset.c473
-rw-r--r--security/landlock/ruleset.h165
-rw-r--r--security/landlock/setup.c40
-rw-r--r--security/landlock/setup.h18
-rw-r--r--security/landlock/syscalls.c451
-rw-r--r--security/security.c51
-rw-r--r--security/selinux/hooks.c58
-rw-r--r--security/selinux/include/objsec.h6
-rw-r--r--security/selinux/ss/services.c3
-rw-r--r--security/smack/smack.h6
-rw-r--r--security/smack/smack_lsm.c35
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/landlock/.gitignore2
-rw-r--r--tools/testing/selftests/landlock/Makefile24
-rw-r--r--tools/testing/selftests/landlock/base_test.c266
-rw-r--r--tools/testing/selftests/landlock/common.h183
-rw-r--r--tools/testing/selftests/landlock/config7
-rw-r--r--tools/testing/selftests/landlock/fs_test.c2791
-rw-r--r--tools/testing/selftests/landlock/ptrace_test.c337
-rw-r--r--tools/testing/selftests/landlock/true.c5
72 files changed, 6987 insertions, 77 deletions
diff --git a/Documentation/security/index.rst b/Documentation/security/index.rst
index 8129405eb2cc..16335de04e8c 100644
--- a/Documentation/security/index.rst
+++ b/Documentation/security/index.rst
@@ -16,3 +16,4 @@ Security Documentation
siphash
tpm/index
digsig
+ landlock
diff --git a/Documentation/security/landlock.rst b/Documentation/security/landlock.rst
new file mode 100644
index 000000000000..2e84925ae971
--- /dev/null
+++ b/Documentation/security/landlock.rst
@@ -0,0 +1,85 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+.. Copyright © 2019-2020 ANSSI
+
+==================================
+Landlock LSM: kernel documentation
+==================================
+
+:Author: Mickaël Salaün
+:Date: March 2021
+
+Landlock's goal is to create scoped access-control (i.e. sandboxing). To
+harden a whole system, this feature should be available to any process,
+including unprivileged ones. Because such process may be compromised or
+backdoored (i.e. untrusted), Landlock's features must be safe to use from the
+kernel and other processes point of view. Landlock's interface must therefore
+expose a minimal attack surface.
+
+Landlock is designed to be usable by unprivileged processes while following the
+system security policy enforced by other access control mechanisms (e.g. DAC,
+LSM). Indeed, a Landlock rule shall not interfere with other access-controls
+enforced on the system, only add more restrictions.
+
+Any user can enforce Landlock rulesets on their processes. They are merged and
+evaluated according to the inherited ones in a way that ensures that only more
+constraints can be added.
+
+User space documentation can be found here: :doc:`/userspace-api/landlock`.
+
+Guiding principles for safe access controls
+===========================================
+
+* A Landlock rule shall be focused on access control on kernel objects instead
+ of syscall filtering (i.e. syscall arguments), which is the purpose of
+ seccomp-bpf.
+* To avoid multiple kinds of side-channel attacks (e.g. leak of security
+ policies, CPU-based attacks), Landlock rules shall not be able to
+ programmatically communicate with user space.
+* Kernel access check shall not slow down access request from unsandboxed
+ processes.
+* Computation related to Landlock operations (e.g. enforcing a ruleset) shall
+ only impact the processes requesting them.
+
+Tests
+=====
+
+Userspace tests for backward compatibility, ptrace restrictions and filesystem
+support can be found here: `tools/testing/selftests/landlock/`_.
+
+Kernel structures
+=================
+
+Object
+------
+
+.. kernel-doc:: security/landlock/object.h
+ :identifiers:
+
+Filesystem
+----------
+
+.. kernel-doc:: security/landlock/fs.h
+ :identifiers:
+
+Ruleset and domain
+------------------
+
+A domain is a read-only ruleset tied to a set of subjects (i.e. tasks'
+credentials). Each time a ruleset is enforced on a task, the current domain is
+duplicated and the ruleset is imported as a new layer of rules in the new
+domain. Indeed, once in a domain, each rule is tied to a layer level. To
+grant access to an object, at least one rule of each layer must allow the
+requested action on the object. A task can then only transit to a new domain
+that is the intersection of the constraints from the current domain and those
+of a ruleset provided by the task.
+
+The definition of a subject is implicit for a task sandboxing itself, which
+makes the reasoning much easier and helps avoid pitfalls.
+
+.. kernel-doc:: security/landlock/ruleset.h
+ :identifiers:
+
+.. Links
+.. _tools/testing/selftests/landlock/:
+ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/landlock/
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 1e2438b7afa0..0b5eefed027e 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -18,6 +18,7 @@ place where this information is gathered.
no_new_privs
seccomp_filter
+ landlock
unshare
spec_ctrl
accelerators/ocxl
diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst
new file mode 100644
index 000000000000..62c9361a3c7f
--- /dev/null
+++ b/Documentation/userspace-api/landlock.rst
@@ -0,0 +1,311 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+.. Copyright © 2019-2020 ANSSI
+.. Copyright © 2021 Microsoft Corporation
+
+=====================================
+Landlock: unprivileged access control
+=====================================
+
+:Author: Mickaël Salaün
+:Date: March 2021
+
+The goal of Landlock is to enable to restrict ambient rights (e.g. global
+filesystem access) for a set of processes. Because Landlock is a stackable
+LSM, it makes possible to create safe security sandboxes as new security layers
+in addition to the existing system-wide access-controls. This kind of sandbox
+is expected to help mitigate the security impact of bugs or
+unexpected/malicious behaviors in user space applications. Landlock empowers
+any process, including unprivileged ones, to securely restrict themselves.
+
+Landlock rules
+==============
+
+A Landlock rule describes an action on an object. An object is currently a
+file hierarchy, and the related filesystem actions are defined with `access
+rights`_. A set of rules is aggregated in a ruleset, which can then restrict
+the thread enforcing it, and its future children.
+
+Defining and enforcing a security policy
+----------------------------------------
+
+We first need to create the ruleset that will contain our rules. For this
+example, the ruleset will contain rules that only allow read actions, but write
+actions will be denied. The ruleset then needs to handle both of these kind of
+actions.
+
+.. code-block:: c
+
+ int ruleset_fd;
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs =
+ LANDLOCK_ACCESS_FS_EXECUTE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE |
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR |
+ LANDLOCK_ACCESS_FS_REMOVE_DIR |
+ LANDLOCK_ACCESS_FS_REMOVE_FILE |
+ LANDLOCK_ACCESS_FS_MAKE_CHAR |
+ LANDLOCK_ACCESS_FS_MAKE_DIR |
+ LANDLOCK_ACCESS_FS_MAKE_REG |
+ LANDLOCK_ACCESS_FS_MAKE_SOCK |
+ LANDLOCK_ACCESS_FS_MAKE_FIFO |
+ LANDLOCK_ACCESS_FS_MAKE_BLOCK |
+ LANDLOCK_ACCESS_FS_MAKE_SYM,
+ };
+
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ if (ruleset_fd < 0) {
+ perror("Failed to create a ruleset");
+ return 1;
+ }
+
+We can now add a new rule to this ruleset thanks to the returned file
+descriptor referring to this ruleset. The rule will only allow reading the
+file hierarchy ``/usr``. Without another rule, write actions would then be
+denied by the ruleset. To add ``/usr`` to the ruleset, we open it with the
+``O_PATH`` flag and fill the &struct landlock_path_beneath_attr with this file
+descriptor.
+
+.. code-block:: c
+
+ int err;
+ struct landlock_path_beneath_attr path_beneath = {
+ .allowed_access =
+ LANDLOCK_ACCESS_FS_EXECUTE |
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR,
+ };
+
+ path_beneath.parent_fd = open("/usr", O_PATH | O_CLOEXEC);
+ if (path_beneath.parent_fd < 0) {
+ perror("Failed to open file");
+ close(ruleset_fd);
+ return 1;
+ }
+ err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0);
+ close(path_beneath.parent_fd);
+ if (err) {
+ perror("Failed to update ruleset");
+ close(ruleset_fd);
+ return 1;
+ }
+
+We now have a ruleset with one rule allowing read access to ``/usr`` while
+denying all other handled accesses for the filesystem. The next step is to
+restrict the current thread from gaining more privileges (e.g. thanks to a SUID
+binary).
+
+.. code-block:: c
+
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("Failed to restrict privileges");
+ close(ruleset_fd);
+ return 1;
+ }
+
+The current thread is now ready to sandbox itself with the ruleset.
+
+.. code-block:: c
+
+ if (landlock_restrict_self(ruleset_fd, 0)) {
+ perror("Failed to enforce ruleset");
+ close(ruleset_fd);
+ return 1;
+ }
+ close(ruleset_fd);
+
+If the `landlock_restrict_self` system call succeeds, the current thread is now
+restricted and this policy will be enforced on all its subsequently created
+children as well. Once a thread is landlocked, there is no way to remove its
+security policy; only adding more restrictions is allowed. These threads are
+now in a new Landlock domain, merge of their parent one (if any) with the new
+ruleset.
+
+Full working code can be found in `samples/landlock/sandboxer.c`_.
+
+Layers of file path access rights
+---------------------------------
+
+Each time a thread enforces a ruleset on itself, it updates its Landlock domain
+with a new layer of policy. Indeed, this complementary policy is stacked with
+the potentially other rulesets already restricting this thread. A sandboxed
+thread can then safely add more constraints to itself with a new enforced
+ruleset.
+
+One policy layer grants access to a file path if at least one of its rules
+encountered on the path grants the access. A sandboxed thread can only access
+a file path if all its enforced policy layers grant the access as well as all
+the other system access controls (e.g. filesystem DAC, other LSM policies,
+etc.).
+
+Bind mounts and OverlayFS
+-------------------------
+
+Landlock enables to restrict access to file hierarchies, which means that these
+access rights can be propagated with bind mounts (cf.
+:doc:`/filesystems/sharedsubtree`) but not with :doc:`/filesystems/overlayfs`.
+
+A bind mount mirrors a source file hierarchy to a destination. The destination
+hierarchy is then composed of the exact same files, on which Landlock rules can
+be tied, either via the source or the destination path. These rules restrict
+access when they are encountered on a path, which means that they can restrict
+access to multiple file hierarchies at the same time, whether these hierarchies
+are the result of bind mounts or not.
+
+An OverlayFS mount point consists of upper and lower layers. These layers are
+combined in a merge directory, result of the mount point. This merge hierarchy
+may include files from the upper and lower layers, but modifications performed
+on the merge hierarchy only reflects on the upper layer. From a Landlock
+policy point of view, each OverlayFS layers and merge hierarchies are
+standalone and contains their own set of files and directories, which is
+different from bind mounts. A policy restricting an OverlayFS layer will not
+restrict the resulted merged hierarchy, and vice versa. Landlock users should
+then only think about file hierarchies they want to allow access to, regardless
+of the underlying filesystem.
+
+Inheritance
+-----------
+
+Every new thread resulting from a :manpage:`clone(2)` inherits Landlock domain
+restrictions from its parent. This is similar to the seccomp inheritance (cf.
+:doc:`/userspace-api/seccomp_filter`) or any other LSM dealing with task's
+:manpage:`credentials(7)`. For instance, one process's thread may apply
+Landlock rules to itself, but they will not be automatically applied to other
+sibling threads (unlike POSIX thread credential changes, cf.
+:manpage:`nptl(7)`).
+
+When a thread sandboxes itself, we have the guarantee that the related security
+policy will stay enforced on all this thread's descendants. This allows
+creating standalone and modular security policies per application, which will
+automatically be composed between themselves according to their runtime parent
+policies.
+
+Ptrace restrictions
+-------------------
+
+A sandboxed process has less privileges than a non-sandboxed process and must
+then be subject to additional restrictions when manipulating another process.
+To be allowed to use :manpage:`ptrace(2)` and related syscalls on a target
+process, a sandboxed process should have a subset of the target process rules,
+which means the tracee must be in a sub-domain of the tracer.
+
+Kernel interface
+================
+
+Access rights
+-------------
+
+.. kernel-doc:: include/uapi/linux/landlock.h
+ :identifiers: fs_access
+
+Creating a new ruleset
+----------------------
+
+.. kernel-doc:: security/landlock/syscalls.c
+ :identifiers: sys_landlock_create_ruleset
+
+.. kernel-doc:: include/uapi/linux/landlock.h
+ :identifiers: landlock_ruleset_attr
+
+Extending a ruleset
+-------------------
+
+.. kernel-doc:: security/landlock/syscalls.c
+ :identifiers: sys_landlock_add_rule
+
+.. kernel-doc:: include/uapi/linux/landlock.h
+ :identifiers: landlock_rule_type landlock_path_beneath_attr
+
+Enforcing a ruleset
+-------------------
+
+.. kernel-doc:: security/landlock/syscalls.c
+ :identifiers: sys_landlock_restrict_self
+
+Current limitations
+===================
+
+File renaming and linking
+-------------------------
+
+Because Landlock targets unprivileged access controls, it is needed to properly
+handle composition of rules. Such property also implies rules nesting.
+Properly handling multiple layers of ruleset, each one of them able to restrict
+access to files, also implies to inherit the ruleset restrictions from a parent
+to its hierarchy. Because files are identified and restricted by their
+hierarchy, moving or linking a file from one directory to another implies to
+propagate the hierarchy constraints. To protect against privilege escalations
+through renaming or linking, and for the sake of simplicity, Landlock currently
+limits linking and renaming to the same directory. Future Landlock evolutions
+will enable more flexibility for renaming and linking, with dedicated ruleset
+flags.
+
+Filesystem topology modification
+--------------------------------
+
+As for file renaming and linking, a sandboxed thread cannot modify its
+filesystem topology, whether via :manpage:`mount(2)` or
+:manpage:`pivot_root(2)`. However, :manpage:`chroot(2)` calls are not denied.
+
+Special filesystems
+-------------------
+
+Access to regular files and directories can be restricted by Landlock,
+according to the handled accesses of a ruleset. However, files that do not
+come from a user-visible filesystem (e.g. pipe, socket), but can still be
+accessed through ``/proc/<pid>/fd/*``, cannot currently be explicitly
+restricted. Likewise, some special kernel filesystems such as nsfs, which can
+be accessed through ``/proc/<pid>/ns/*``, cannot currently be explicitly
+restricted. However, thanks to the `ptrace restrictions`_, access to such
+sensitive ``/proc`` files are automatically restricted according to domain
+hierarchies. Future Landlock evolutions could still enable to explicitly
+restrict such paths with dedicated ruleset flags.
+
+Ruleset layers
+--------------
+
+There is a limit of 64 layers of stacked rulesets. This can be an issue for a
+task willing to enforce a new ruleset in complement to its 64 inherited
+rulesets. Once this limit is reached, sys_landlock_restrict_self() returns
+E2BIG. It is then strongly suggested to carefully build rulesets once in the
+life of a thread, especially for applications able to launch other applications
+that may also want to sandbox themselves (e.g. shells, container managers,
+etc.).
+
+Memory usage
+------------
+
+Kernel memory allocated to create rulesets is accounted and can be restricted
+by the :doc:`/admin-guide/cgroup-v1/memory`.
+
+Questions and answers
+=====================
+
+What about user space sandbox managers?
+---------------------------------------
+
+Using user space process to enforce restrictions on kernel resources can lead
+to race conditions or inconsistent evaluations (i.e. `Incorrect mirroring of
+the OS code and state
+<https://www.ndss-symposium.org/ndss2003/traps-and-pitfalls-practical-problems-system-call-interposition-based-security-tools/>`_).
+
+What about namespaces and containers?
+-------------------------------------
+
+Namespaces can help create sandboxes but they are not designed for
+access-control and then miss useful features for such use case (e.g. no
+fine-grained restrictions). Moreover, their complexity can lead to security
+issues, especially when untrusted processes can manipulate them (cf.
+`Controlling access to user namespaces <https://lwn.net/Articles/673597/>`_).
+
+Additional documentation
+========================
+
+* :doc:`/security/landlock`
+* https://landlock.io
+
+.. Links
+.. _samples/landlock/sandboxer.c:
+ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/samples/landlock/sandboxer.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 8c40e7cfba2a..121b1a12384a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10191,6 +10191,21 @@ F: net/core/sock_map.c
F: net/ipv4/tcp_bpf.c
F: net/ipv4/udp_bpf.c
+LANDLOCK SECURITY MODULE
+M: Mickaël Salaün <mic@digikod.net>
+L: linux-security-module@vger.kernel.org
+S: Supported
+W: https://landlock.io
+T: git https://github.com/landlock-lsm/linux.git
+F: Documentation/security/landlock.rst
+F: Documentation/userspace-api/landlock.rst
+F: include/uapi/linux/landlock.h
+F: samples/landlock/
+F: security/landlock/
+F: tools/testing/selftests/landlock/
+K: landlock
+K: LANDLOCK
+
LANTIQ / INTEL Ethernet drivers
M: Hauke Mehrtens <hauke@hauke-m.de>
L: netdev@vger.kernel.org
diff --git a/arch/Kconfig b/arch/Kconfig
index bf27159be4d9..c45b770d3579 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1068,6 +1068,13 @@ config COMPAT_32BIT_TIME
config ARCH_NO_PREEMPT
bool
+config ARCH_EPHEMERAL_INODES
+ def_bool n
+ help
+ An arch should select this symbol if it doesn't keep track of inode
+ instances on its own, but instead relies on something else (e.g. the
+ host kernel for an UML kernel).
+
config ARCH_SUPPORTS_RT
bool
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index c5f7e595adab..5622578742fd 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -483,3 +483,6 @@
551 common epoll_pwait2 sys_epoll_pwait2
552 common mount_setattr sys_mount_setattr
553 common quotactl_path sys_quotactl_path
+554 common landlock_create_ruleset sys_landlock_create_ruleset
+555 common landlock_add_rule sys_landlock_add_rule
+556 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 90cbe207cf3e..c7679d7db98b 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -457,3 +457,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d1f7d35f986e..727bfc3be99b 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 444
+#define __NR_compat_syscalls 447
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 8361c5138e5f..7859749d6628 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -895,6 +895,12 @@ __SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2)
__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
#define __NR_quotactl_path 443
__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+#define __NR_landlock_create_ruleset 444
+__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
+#define __NR_landlock_add_rule 445
+__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
+#define __NR_landlock_restrict_self 446
+__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index c072cd459bb5..1ee8e736a48e 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -364,3 +364,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 5e9f81073ff4..0dd019dc2136 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -443,3 +443,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 8e74d690c64d..2ac716984ca2 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -449,3 +449,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 6f397e56926f..5e0096657251 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -382,3 +382,6 @@
441 n32 epoll_pwait2 compat_sys_epoll_pwait2
442 n32 mount_setattr sys_mount_setattr
443 n32 quotactl_path sys_quotactl_path
+444 n32 landlock_create_ruleset sys_landlock_create_ruleset
+445 n32 landlock_add_rule sys_landlock_add_rule
+446 n32 landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index ab85a357c4fa..9974f5f8e49b 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -358,3 +358,6 @@
441 n64 epoll_pwait2 sys_epoll_pwait2
442 n64 mount_setattr sys_mount_setattr
443 n64 quotactl_path sys_quotactl_path
+444 n64 landlock_create_ruleset sys_landlock_create_ruleset
+445 n64 landlock_add_rule sys_landlock_add_rule
+446 n64 landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9c4cd2b40b38..39d6e71e57b6 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -431,3 +431,6 @@
441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 o32 mount_setattr sys_mount_setattr
443 o32 quotactl_path sys_quotactl_path
+444 o32 landlock_create_ruleset sys_landlock_create_ruleset
+445 o32 landlock_add_rule sys_landlock_add_rule
+446 o32 landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 80fba3f7d47b..5ac80b83d745 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -441,3 +441,6 @@
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index f66f9c9b9d6c..2e68fbb57cc6 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -523,3 +523,6 @@
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index a421905c36e8..7e4a2aba366d 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -446,3 +446,6 @@
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index f68517aaa4f1..f47a0dc55445 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -446,3 +446,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 3ee82321504d..b9e1c0e735b7 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -489,3 +489,6 @@
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index c3030db3325f..57cfd9a1c082 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -5,6 +5,7 @@ menu "UML-specific options"
config UML
bool
default y
+ select ARCH_EPHEMERAL_INODES
select ARCH_HAS_KCOV
select ARCH_NO_PREEMPT
select HAVE_ARCH_AUDITSYSCALL
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f52a443eede0..28a1423ce32e 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -448,3 +448,6 @@
441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
442 i386 mount_setattr sys_mount_setattr
443 i386 quotactl_path sys_quotactl_path
+444 i386 landlock_create_ruleset sys_landlock_create_ruleset
+445 i386 landlock_add_rule sys_landlock_add_rule
+446 i386 landlock_restrict_self sys_landlock_restrict_self
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 7eb007b8cab5..ecd551b08d05 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -365,6 +365,9 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index c71cc45633de..9d76d433d3d6 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -414,3 +414,6 @@
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
+444 common landlock_create_ruleset sys_landlock_create_ruleset
+445 common landlock_add_rule sys_landlock_add_rule
+446 common landlock_restrict_self sys_landlock_restrict_self
diff --git a/fs/super.c b/fs/super.c
index 8c1baca35c16..11b7e7213fd1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -454,6 +454,7 @@ void generic_shutdown_super(struct super_block *sb)
evict_inodes(sb);
/* only nonzero refcount inodes can have marks */
fsnotify_sb_delete(sb);
+ security_sb_delete(sb);
if (sb->s_dio_done_wq) {
destroy_workqueue(sb->s_dio_done_wq);
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 61f04f7dc1a4..04c01794de83 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -59,6 +59,7 @@ LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc,
LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc,
struct fs_parameter *param)
LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb)
+LSM_HOOK(void, LSM_RET_VOID, sb_delete, struct super_block *sb)
LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb)
LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts)
LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index ba2ccd950833..5c4c5c0602cb 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -108,6 +108,9 @@
* allocated.
* @sb contains the super_block structure to be modified.
* Return 0 if operation was successful.
+ * @sb_delete:
+ * Release objects tied to a superblock (e.g. inodes).
+ * @sb contains the super_block structure being released.
* @sb_free_security:
* Deallocate and clear the sb->s_security field.
* @sb contains the super_block structure to be modified.
@@ -1585,6 +1588,7 @@ struct lsm_blob_sizes {
int lbs_cred;
int lbs_file;
int lbs_inode;
+ int lbs_superblock;
int lbs_ipc;
int lbs_msg_msg;
int lbs_task;
diff --git a/include/linux/security.h b/include/linux/security.h
index 9aeda3f9e838..06f7c50ce77f 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -291,6 +291,7 @@ void security_bprm_committed_creds(struct linux_binprm *bprm);
int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc);
int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param);
int security_sb_alloc(struct super_block *sb);
+void security_sb_delete(struct super_block *sb);
void security_sb_free(struct super_block *sb);
void security_free_mnt_opts(void **mnt_opts);
int security_sb_eat_lsm_opts(char *options, void **mnt_opts);
@@ -633,6 +634,9 @@ static inline int security_sb_alloc(struct super_block *sb)
return 0;
}
+static inline void security_sb_delete(struct super_block *sb)
+{ }
+
static inline void security_sb_free(struct super_block *sb)
{ }
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a672bbe28577..050511e8f1f8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -69,6 +69,8 @@ struct io_uring_params;
struct clone_args;
struct open_how;
struct mount_attr;
+struct landlock_ruleset_attr;
+enum landlock_rule_type;
#include <linux/types.h>
#include <linux/aio_abi.h>
@@ -1043,6 +1045,11 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
siginfo_t __user *info,
unsigned int flags);
asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
+asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr __user *attr,
+ size_t size, __u32 flags);
+asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type,
+ const void __user *rule_attr, __u32 flags);
+asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 739c839d28fe..6de5a7fc066b 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -866,8 +866,15 @@ __SYSCALL(__NR_mount_setattr, sys_mount_setattr)
#define __NR_quotactl_path 443
__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
+#define __NR_landlock_create_ruleset 444
+__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
+#define __NR_landlock_add_rule 445
+__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule)
+#define __NR_landlock_restrict_self 446
+__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+
#undef __NR_syscalls
-#define __NR_syscalls 444
+#define __NR_syscalls 447
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
new file mode 100644
index 000000000000..b3d952067f59
--- /dev/null
+++ b/include/uapi/linux/landlock.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Landlock - User space API
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _UAPI_LINUX_LANDLOCK_H
+#define _UAPI_LINUX_LANDLOCK_H
+
+#include <linux/types.h>
+
+/**
+ * struct landlock_ruleset_attr - Ruleset definition
+ *
+ * Argument of sys_landlock_create_ruleset(). This structure can grow in
+ * future versions.
+ */
+struct landlock_ruleset_attr {
+ /**
+ * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_)
+ * that is handled by this ruleset and should then be forbidden if no
+ * rule explicitly allow them. This is needed for backward
+ * compatibility reasons.
+ */
+ __u64 handled_access_fs;
+};
+
+/*
+ * sys_landlock_create_ruleset() flags:
+ *
+ * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI
+ * version.
+ */
+#define LANDLOCK_CREATE_RULESET_VERSION (1U << 0)
+
+/**
+ * enum landlock_rule_type - Landlock rule type
+ *
+ * Argument of sys_landlock_add_rule().
+ */
+enum landlock_rule_type {
+ /**
+ * @LANDLOCK_RULE_PATH_BENEATH: Type of a &struct
+ * landlock_path_beneath_attr .
+ */
+ LANDLOCK_RULE_PATH_BENEATH = 1,
+};
+
+/**
+ * struct landlock_path_beneath_attr - Path hierarchy definition
+ *
+ * Argument of sys_landlock_add_rule().
+ */
+struct landlock_path_beneath_attr {
+ /**
+ * @allowed_access: Bitmask of allowed actions for this file hierarchy
+ * (cf. `Filesystem flags`_).
+ */
+ __u64 allowed_access;
+ /**
+ * @parent_fd: File descriptor, open with ``O_PATH``, which identifies
+ * the parent directory of a file hierarchy, or just a file.
+ */
+ __s32 parent_fd;
+ /*
+ * This struct is packed to avoid trailing reserved members.
+ * Cf. security/landlock/syscalls.c:build_check_abi()
+ */
+} __attribute__((packed));
+
+/**
+ * DOC: fs_access
+ *
+ * A set of actions on kernel objects may be defined by an attribute (e.g.
+ * &struct landlock_path_beneath_attr) including a bitmask of access.
+ *
+ * Filesystem flags
+ * ~~~~~~~~~~~~~~~~
+ *
+ * These flags enable to restrict a sandboxed process to a set of actions on
+ * files and directories. Files or directories opened before the sandboxing
+ * are not subject to these restrictions.
+ *
+ * A file can only receive these access rights:
+ *
+ * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file.
+ * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access.
+ * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access.
+ *
+ * A directory can receive access rights related to files or directories. The
+ * following access right is applied to the directory itself, and the
+ * directories beneath it:
+ *
+ * - %LANDLOCK_ACCESS_FS_READ_DIR: Open a directory or list its content.
+ *
+ * However, the following access rights only apply to the content of a
+ * directory, not the directory itself:
+ *
+ * - %LANDLOCK_ACCESS_FS_REMOVE_DIR: Remove an empty directory or rename one.
+ * - %LANDLOCK_ACCESS_FS_REMOVE_FILE: Unlink (or rename) a file.
+ * - %LANDLOCK_ACCESS_FS_MAKE_CHAR: Create (or rename or link) a character
+ * device.
+ * - %LANDLOCK_ACCESS_FS_MAKE_DIR: Create (or rename) a directory.
+ * - %LANDLOCK_ACCESS_FS_MAKE_REG: Create (or rename or link) a regular file.
+ * - %LANDLOCK_ACCESS_FS_MAKE_SOCK: Create (or rename or link) a UNIX domain
+ * socket.
+ * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe.
+ * - %LANDLOCK_ACCESS_FS_MAKE_BLOCK: Create (or rename or link) a block device.
+ * - %LANDLOCK_ACCESS_FS_MAKE_SYM: Create (or rename or link) a symbolic link.
+ *
+ * .. warning::
+ *
+ * It is currently not possible to restrict some file-related actions
+ * accessible through these syscall families: :manpage:`chdir(2)`,
+ * :manpage:`truncate(2)`, :manpage:`stat(2)`, :manpage:`flock(2)`,
+ * :manpage:`chmod(2)`, :manpage:`chown(2)`, :manpage:`setxattr(2)`,
+ * :manpage:`utime(2)`, :manpage:`ioctl(2)`, :manpage:`fcntl(2)`,
+ * :manpage:`access(2)`.
+ * Future Landlock evolutions will enable to restrict them.
+ */
+#define LANDLOCK_ACCESS_FS_EXECUTE (1ULL << 0)
+#define LANDLOCK_ACCESS_FS_WRITE_FILE (1ULL << 1)
+#define LANDLOCK_ACCESS_FS_READ_FILE (1ULL << 2)
+#define LANDLOCK_ACCESS_FS_READ_DIR (1ULL << 3)
+#define LANDLOCK_ACCESS_FS_REMOVE_DIR (1ULL << 4)
+#define LANDLOCK_ACCESS_FS_REMOVE_FILE (1ULL << 5)
+#define LANDLOCK_ACCESS_FS_MAKE_CHAR (1ULL << 6)
+#define LANDLOCK_ACCESS_FS_MAKE_DIR (1ULL << 7)
+#define LANDLOCK_ACCESS_FS_MAKE_REG (1ULL << 8)
+#define LANDLOCK_ACCESS_FS_MAKE_SOCK (1ULL << 9)
+#define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10)
+#define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11)
+#define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12)
+
+#endif /* _UAPI_LINUX_LANDLOCK_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d24431782414..0ea8128468c3 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -267,6 +267,11 @@ COND_SYSCALL(request_key);
COND_SYSCALL(keyctl);
COND_SYSCALL_COMPAT(keyctl);
+/* security/landlock/syscalls.c */
+COND_SYSCALL(landlock_create_ruleset);
+COND_SYSCALL(landlock_add_rule);
+COND_SYSCALL(landlock_restrict_self);
+
/* arch/example/kernel/sys_example.c */
/* mm/fadvise.c */
diff --git a/samples/Kconfig b/samples/Kconfig
index e76cdfc50e25..b5a1a7aa7e23 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -124,6 +124,13 @@ config SAMPLE_HIDRAW
bool "hidraw sample"
depends on CC_CAN_LINK && HEADERS_INSTALL
+config SAMPLE_LANDLOCK
+ bool "Landlock example"
+ depends on CC_CAN_LINK && HEADERS_INSTALL
+ help
+ Build a simple Landlock sandbox manager able to start a process
+ restricted by a user-defined filesystem access control policy.
+
config SAMPLE_PIDFD
bool "pidfd sample"
depends on CC_CAN_LINK && HEADERS_INSTALL
diff --git a/samples/Makefile b/samples/Makefile
index c3392a595e4b..087e0988ccc5 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_SAMPLE_KDB) += kdb/
obj-$(CONFIG_SAMPLE_KFIFO) += kfifo/
obj-$(CONFIG_SAMPLE_KOBJECT) += kobject/
obj-$(CONFIG_SAMPLE_KPROBES) += kprobes/
+subdir-$(CONFIG_SAMPLE_LANDLOCK) += landlock
obj-$(CONFIG_SAMPLE_LIVEPATCH) += livepatch/
subdir-$(CONFIG_SAMPLE_PIDFD) += pidfd
obj-$(CONFIG_SAMPLE_QMI_CLIENT) += qmi/
diff --git a/samples/landlock/.gitignore b/samples/landlock/.gitignore
new file mode 100644
index 000000000000..f43668b2d318
--- /dev/null
+++ b/samples/landlock/.gitignore
@@ -0,0 +1 @@
+/sandboxer
diff --git a/samples/landlock/Makefile b/samples/landlock/Makefile
new file mode 100644
index 000000000000..5d601e51c2eb
--- /dev/null
+++ b/samples/landlock/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: BSD-3-Clause
+
+userprogs-always-y := sandboxer
+
+userccflags += -I usr/include
+
+.PHONY: all clean
+
+all:
+ $(MAKE) -C ../.. samples/landlock/
+
+clean:
+ $(MAKE) -C ../.. M=samples/landlock/ clean
diff --git a/samples/landlock/sandboxer.c b/samples/landlock/sandboxer.c
new file mode 100644
index 000000000000..7a15910d2171
--- /dev/null
+++ b/samples/landlock/sandboxer.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Simple Landlock sandbox manager able to launch a process restricted by a
+ * user-defined filesystem access control policy.
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2020 ANSSI
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/landlock.h>
+#include <linux/prctl.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#ifndef landlock_create_ruleset
+static inline int landlock_create_ruleset(
+ const struct landlock_ruleset_attr *const attr,
+ const size_t size, const __u32 flags)
+{
+ return syscall(__NR_landlock_create_ruleset, attr, size, flags);
+}
+#endif
+
+#ifndef landlock_add_rule
+static inline int landlock_add_rule(const int ruleset_fd,
+ const enum landlock_rule_type rule_type,
+ const void *const rule_attr, const __u32 flags)
+{
+ return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type,
+ rule_attr, flags);
+}
+#endif
+
+#ifndef landlock_restrict_self
+static inline int landlock_restrict_self(const int ruleset_fd,
+ const __u32 flags)
+{
+ return syscall(__NR_landlock_restrict_self, ruleset_fd, flags);
+}
+#endif
+
+#define ENV_FS_RO_NAME "LL_FS_RO"
+#define ENV_FS_RW_NAME "LL_FS_RW"
+#define ENV_PATH_TOKEN ":"
+
+static int parse_path(char *env_path, const char ***const path_list)
+{
+ int i, num_paths = 0;
+
+ if (env_path) {
+ num_paths++;
+ for (i = 0; env_path[i]; i++) {
+ if (env_path[i] == ENV_PATH_TOKEN[0])
+ num_paths++;
+ }
+ }
+ *path_list = malloc(num_paths * sizeof(**path_list));
+ for (i = 0; i < num_paths; i++)
+ (*path_list)[i] = strsep(&env_path, ENV_PATH_TOKEN);
+
+ return num_paths;
+}
+
+#define ACCESS_FILE ( \
+ LANDLOCK_ACCESS_FS_EXECUTE | \
+ LANDLOCK_ACCESS_FS_WRITE_FILE | \
+ LANDLOCK_ACCESS_FS_READ_FILE)
+
+static int populate_ruleset(
+ const char *const env_var, const int ruleset_fd,
+ const __u64 allowed_access)
+{
+ int num_paths, i, ret = 1;
+ char *env_path_name;
+ const char **path_list = NULL;
+ struct landlock_path_beneath_attr path_beneath = {
+ .parent_fd = -1,
+ };
+
+ env_path_name = getenv(env_var);
+ if (!env_path_name) {
+ /* Prevents users to forget a setting. */
+ fprintf(stderr, "Missing environment variable %s\n", env_var);
+ return 1;
+ }
+ env_path_name = strdup(env_path_name);
+ unsetenv(env_var);
+ num_paths = parse_path(env_path_name, &path_list);
+ if (num_paths == 1 && path_list[0][0] == '\0') {
+ /*
+ * Allows to not use all possible restrictions (e.g. use
+ * LL_FS_RO without LL_FS_RW).
+ */
+ ret = 0;
+ goto out_free_name;
+ }
+
+ for (i = 0; i < num_paths; i++) {
+ struct stat statbuf;
+
+ path_beneath.parent_fd = open(path_list[i], O_PATH |
+ O_CLOEXEC);
+ if (path_beneath.parent_fd < 0) {
+ fprintf(stderr, "Failed to open \"%s\": %s\n",
+ path_list[i],
+ strerror(errno));
+ goto out_free_name;
+ }
+ if (fstat(path_beneath.parent_fd, &statbuf)) {
+ close(path_beneath.parent_fd);
+ goto out_free_name;
+ }
+ path_beneath.allowed_access = allowed_access;
+ if (!S_ISDIR(statbuf.st_mode))
+ path_beneath.allowed_access &= ACCESS_FILE;
+ if (landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0)) {
+ fprintf(stderr, "Failed to update the ruleset with \"%s\": %s\n",
+ path_list[i], strerror(errno));
+ close(path_beneath.parent_fd);
+ goto out_free_name;
+ }
+ close(path_beneath.parent_fd);
+ }
+ ret = 0;
+
+out_free_name:
+ free(env_path_name);
+ return ret;
+}
+
+#define ACCESS_FS_ROUGHLY_READ ( \
+ LANDLOCK_ACCESS_FS_EXECUTE | \
+ LANDLOCK_ACCESS_FS_READ_FILE | \
+ LANDLOCK_ACCESS_FS_READ_DIR)
+
+#define ACCESS_FS_ROUGHLY_WRITE ( \
+ LANDLOCK_ACCESS_FS_WRITE_FILE | \
+ LANDLOCK_ACCESS_FS_REMOVE_DIR | \
+ LANDLOCK_ACCESS_FS_REMOVE_FILE | \
+ LANDLOCK_ACCESS_FS_MAKE_CHAR | \
+ LANDLOCK_ACCESS_FS_MAKE_DIR | \
+ LANDLOCK_ACCESS_FS_MAKE_REG | \
+ LANDLOCK_ACCESS_FS_MAKE_SOCK | \
+ LANDLOCK_ACCESS_FS_MAKE_FIFO | \
+ LANDLOCK_ACCESS_FS_MAKE_BLOCK | \
+ LANDLOCK_ACCESS_FS_MAKE_SYM)
+
+int main(const int argc, char *const argv[], char *const *const envp)
+{
+ const char *cmd_path;
+ char *const *cmd_argv;
+ int ruleset_fd;
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = ACCESS_FS_ROUGHLY_READ |
+ ACCESS_FS_ROUGHLY_WRITE,
+ };
+
+ if (argc < 2) {
+ fprintf(stderr, "usage: %s=\"...\" %s=\"...\" %s <cmd> [args]...\n\n",
+ ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]);
+ fprintf(stderr, "Launch a command in a restricted environment.\n\n");
+ fprintf(stderr, "Environment variables containing paths, "
+ "each separated by a colon:\n");
+ fprintf(stderr, "* %s: list of paths allowed to be used in a read-only way.\n",
+ ENV_FS_RO_NAME);
+ fprintf(stderr, "* %s: list of paths allowed to be used in a read-write way.\n",
+ ENV_FS_RW_NAME);
+ fprintf(stderr, "\nexample:\n"
+ "%s=\"/bin:/lib:/usr:/proc:/etc:/dev/urandom\" "
+ "%s=\"/dev/null:/dev/full:/dev/zero:/dev/pts:/tmp\" "
+ "%s bash -i\n",
+ ENV_FS_RO_NAME, ENV_FS_RW_NAME, argv[0]);
+ return 1;
+ }
+
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ if (ruleset_fd < 0) {
+ const int err = errno;
+
+ perror("Failed to create a ruleset");
+ switch (err) {
+ case ENOSYS:
+ fprintf(stderr, "Hint: Landlock is not supported by the current kernel. "
+ "To support it, build the kernel with "
+ "CONFIG_SECURITY_LANDLOCK=y and prepend "
+ "\"landlock,\" to the content of CONFIG_LSM.\n");
+ break;
+ case EOPNOTSUPP:
+ fprintf(stderr, "Hint: Landlock is currently disabled. "
+ "It can be enabled in the kernel configuration by "
+ "prepending \"landlock,\" to the content of CONFIG_LSM, "
+ "or at boot time by setting the same content to the "
+ "\"lsm\" kernel parameter.\n");
+ break;
+ }
+ return 1;
+ }
+ if (populate_ruleset(ENV_FS_RO_NAME, ruleset_fd,
+ ACCESS_FS_ROUGHLY_READ)) {
+ goto err_close_ruleset;
+ }
+ if (populate_ruleset(ENV_FS_RW_NAME, ruleset_fd,
+ ACCESS_FS_ROUGHLY_READ | ACCESS_FS_ROUGHLY_WRITE)) {
+ goto err_close_ruleset;
+ }
+ if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ perror("Failed to restrict privileges");
+ goto err_close_ruleset;
+ }
+ if (landlock_restrict_self(ruleset_fd, 0)) {
+ perror("Failed to enforce ruleset");
+ goto err_close_ruleset;
+ }
+ close(ruleset_fd);
+
+ cmd_path = argv[1];
+ cmd_argv = argv + 1;
+ execvpe(cmd_path, cmd_argv, envp);
+ fprintf(stderr, "Failed to execute \"%s\": %s\n", cmd_path,
+ strerror(errno));
+ fprintf(stderr, "Hint: access to the binary, the interpreter or "
+ "shared libraries may be denied.\n");
+ return 1;
+
+err_close_ruleset:
+ close(ruleset_fd);
+ return 1;
+}
diff --git a/security/Kconfig b/security/Kconfig
index 7561f6f99f1d..0ced7fd33e4d 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -238,6 +238,7 @@ source "security/loadpin/Kconfig"
source "security/yama/Kconfig"
source "security/safesetid/Kconfig"
source "security/lockdown/Kconfig"
+source "security/landlock/Kconfig"
source "security/integrity/Kconfig"
@@ -277,11 +278,11 @@ endchoice
config LSM
string "Ordered list of enabled LSMs"
- default "lockdown,yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor,bpf" if DEFAULT_SECURITY_SMACK
- default "lockdown,yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo,bpf" if DEFAULT_SECURITY_APPARMOR
- default "lockdown,yama,loadpin,safesetid,integrity,tomoyo,bpf" if DEFAULT_SECURITY_TOMOYO
- default "lockdown,yama,loadpin,safesetid,integrity,bpf" if DEFAULT_SECURITY_DAC
- default "lockdown,yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor,bpf"
+ default "landlock,lockdown,yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor,bpf" if DEFAULT_SECURITY_SMACK
+ default "landlock,lockdown,yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo,bpf" if DEFAULT_SECURITY_APPARMOR
+ default "landlock,lockdown,yama,loadpin,safesetid,integrity,tomoyo,bpf" if DEFAULT_SECURITY_TOMOYO
+ default "landlock,lockdown,yama,loadpin,safesetid,integrity,bpf" if DEFAULT_SECURITY_DAC
+ default "landlock,lockdown,yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor,bpf"
help
A comma-separated list of LSMs, in initialization order.
Any LSMs left off this list will be ignored. This can be
diff --git a/security/Makefile b/security/Makefile
index 3baf435de541..47e432900e24 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -13,6 +13,7 @@ subdir-$(CONFIG_SECURITY_LOADPIN) += loadpin
subdir-$(CONFIG_SECURITY_SAFESETID) += safesetid
subdir-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown
subdir-$(CONFIG_BPF_LSM) += bpf
+subdir-$(CONFIG_SECURITY_LANDLOCK) += landlock
# always enable default capabilities
obj-y += commoncap.o
@@ -32,6 +33,7 @@ obj-$(CONFIG_SECURITY_SAFESETID) += safesetid/
obj-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown/
obj-$(CONFIG_CGROUPS) += device_cgroup.o
obj-$(CONFIG_BPF_LSM) += bpf/
+obj-$(CONFIG_SECURITY_LANDLOCK) += landlock/
# Object integrity file lists
subdir-$(CONFIG_INTEGRITY) += integrity
diff --git a/security/landlock/Kconfig b/security/landlock/Kconfig
new file mode 100644
index 000000000000..8e33c4e8ffb8
--- /dev/null
+++ b/security/landlock/Kconfig
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config SECURITY_LANDLOCK
+ bool "Landlock support"
+ depends on SECURITY && !ARCH_EPHEMERAL_INODES
+ select SECURITY_PATH
+ help
+ Landlock is a sandboxing mechanism that enables processes to restrict
+ themselves (and their future children) by gradually enforcing
+ tailored access control policies. A Landlock security policy is a
+ set of access rights (e.g. open a file in read-only, make a
+ directory, etc.) tied to a file hierarchy. Such policy can be
+ configured and enforced by any processes for themselves using the
+ dedicated system calls: landlock_create_ruleset(),
+ landlock_add_rule(), and landlock_restrict_self().
+
+ See Documentation/userspace-api/landlock.rst for further information.
+
+ If you are unsure how to answer this question, answer N. Otherwise,
+ you should also prepend "landlock," to the content of CONFIG_LSM to
+ enable Landlock at boot time.
diff --git a/security/landlock/Makefile b/security/landlock/Makefile
new file mode 100644
index 000000000000..7bbd2f413b3e
--- /dev/null
+++ b/security/landlock/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_SECURITY_LANDLOCK) := landlock.o
+
+landlock-y := setup.o syscalls.o object.o ruleset.o \
+ cred.o ptrace.o fs.o
diff --git a/security/landlock/common.h b/security/landlock/common.h
new file mode 100644
index 000000000000..5dc0fe15707d
--- /dev/null
+++ b/security/landlock/common.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Common constants and helpers
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_COMMON_H
+#define _SECURITY_LANDLOCK_COMMON_H
+
+#define LANDLOCK_NAME "landlock"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) LANDLOCK_NAME ": " fmt
+
+#endif /* _SECURITY_LANDLOCK_COMMON_H */
diff --git a/security/landlock/cred.c b/security/landlock/cred.c
new file mode 100644
index 000000000000..6725af24c684
--- /dev/null
+++ b/security/landlock/cred.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Credential hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/cred.h>
+#include <linux/lsm_hooks.h>
+
+#include "common.h"
+#include "cred.h"
+#include "ruleset.h"
+#include "setup.h"
+
+static int hook_cred_prepare(struct cred *const new,
+ const struct cred *const old, const gfp_t gfp)
+{
+ struct landlock_ruleset *const old_dom = landlock_cred(old)->domain;
+
+ if (old_dom) {
+ landlock_get_ruleset(old_dom);
+ landlock_cred(new)->domain = old_dom;
+ }
+ return 0;
+}
+
+static void hook_cred_free(struct cred *const cred)
+{
+ struct landlock_ruleset *const dom = landlock_cred(cred)->domain;
+
+ if (dom)
+ landlock_put_ruleset_deferred(dom);
+}
+
+static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = {
+ LSM_HOOK_INIT(cred_prepare, hook_cred_prepare),
+ LSM_HOOK_INIT(cred_free, hook_cred_free),
+};
+
+__init void landlock_add_cred_hooks(void)
+{
+ security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+ LANDLOCK_NAME);
+}
diff --git a/security/landlock/cred.h b/security/landlock/cred.h
new file mode 100644
index 000000000000..5f99d3decade
--- /dev/null
+++ b/security/landlock/cred.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Credential hooks
+ *
+ * Copyright © 2019-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_CRED_H
+#define _SECURITY_LANDLOCK_CRED_H
+
+#include <linux/cred.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+
+#include "ruleset.h"
+#include "setup.h"
+
+struct landlock_cred_security {
+ struct landlock_ruleset *domain;
+};
+
+static inline struct landlock_cred_security *landlock_cred(
+ const struct cred *cred)
+{
+ return cred->security + landlock_blob_sizes.lbs_cred;
+}
+
+static inline const struct landlock_ruleset *landlock_get_current_domain(void)
+{
+ return landlock_cred(current_cred())->domain;
+}
+
+/*
+ * The call needs to come from an RCU read-side critical section.
+ */
+static inline const struct landlock_ruleset *landlock_get_task_domain(
+ const struct task_struct *const task)
+{
+ return landlock_cred(__task_cred(task))->domain;
+}
+
+static inline bool landlocked(const struct task_struct *const task)
+{
+ bool has_dom;
+
+ if (task == current)
+ return !!landlock_get_current_domain();
+
+ rcu_read_lock();
+ has_dom = !!landlock_get_task_domain(task);
+ rcu_read_unlock();
+ return has_dom;
+}
+
+__init void landlock_add_cred_hooks(void);
+
+#endif /* _SECURITY_LANDLOCK_CRED_H */
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
new file mode 100644
index 000000000000..97b8e421f617
--- /dev/null
+++ b/security/landlock/fs.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Filesystem management and hooks
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler_types.h>
+#include <linux/dcache.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/lsm_hooks.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/path.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+#include <linux/wait_bit.h>
+#include <linux/workqueue.h>
+#include <uapi/linux/landlock.h>
+
+#include "common.h"
+#include "cred.h"
+#include "fs.h"
+#include "limits.h"
+#include "object.h"
+#include "ruleset.h"
+#include "setup.h"
+
+/* Underlying object management */
+
+static void release_inode(struct landlock_object *const object)
+ __releases(object->lock)
+{
+ struct inode *const inode = object->underobj;
+ struct super_block *sb;
+
+ if (!inode) {
+ spin_unlock(&object->lock);
+ return;
+ }
+
+ /*
+ * Protects against concurrent use by hook_sb_delete() of the reference
+ * to the underlying inode.
+ */
+ object->underobj = NULL;
+ /*
+ * Makes sure that if the filesystem is concurrently unmounted,
+ * hook_sb_delete() will wait for us to finish iput().
+ */
+ sb = inode->i_sb;
+ atomic_long_inc(&landlock_superblock(sb)->inode_refs);
+ spin_unlock(&object->lock);
+ /*
+ * Because object->underobj was not NULL, hook_sb_delete() and
+ * get_inode_object() guarantee that it is safe to reset
+ * landlock_inode(inode)->object while it is not NULL. It is therefore
+ * not necessary to lock inode->i_lock.
+ */
+ rcu_assign_pointer(landlock_inode(inode)->object, NULL);
+ /*
+ * Now, new rules can safely be tied to @inode with get_inode_object().
+ */
+
+ iput(inode);
+ if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs))
+ wake_up_var(&landlock_superblock(sb)->inode_refs);
+}
+
+static const struct landlock_object_underops landlock_fs_underops = {
+ .release = release_inode
+};
+
+/* Ruleset management */
+
+static struct landlock_object *get_inode_object(struct inode *const inode)
+{
+ struct landlock_object *object, *new_object;
+ struct landlock_inode_security *inode_sec = landlock_inode(inode);
+
+ rcu_read_lock();
+retry:
+ object = rcu_dereference(inode_sec->object);
+ if (object) {
+ if (likely(refcount_inc_not_zero(&object->usage))) {
+ rcu_read_unlock();
+ return object;
+ }
+ /*
+ * We are racing with release_inode(), the object is going
+ * away. Wait for release_inode(), then retry.
+ */
+ spin_lock(&object->lock);
+ spin_unlock(&object->lock);
+ goto retry;
+ }
+ rcu_read_unlock();
+
+ /*
+ * If there is no object tied to @inode, then create a new one (without
+ * holding any locks).
+ */
+ new_object = landlock_create_object(&landlock_fs_underops, inode);
+ if (IS_ERR(new_object))
+ return new_object;
+
+ /*
+ * Protects against concurrent calls to get_inode_object() or
+ * hook_sb_delete().
+ */
+ spin_lock(&inode->i_lock);
+ if (unlikely(rcu_access_pointer(inode_sec->object))) {
+ /* Someone else just created the object, bail out and retry. */
+ spin_unlock(&inode->i_lock);
+ kfree(new_object);
+
+ rcu_read_lock();
+ goto retry;
+ }
+
+ /*
+ * @inode will be released by hook_sb_delete() on its superblock
+ * shutdown, or by release_inode() when no more ruleset references the
+ * related object.
+ */
+ ihold(inode);
+ rcu_assign_pointer(inode_sec->object, new_object);
+ spin_unlock(&inode->i_lock);
+ return new_object;
+}
+
+/* All access rights that can be tied to files. */
+#define ACCESS_FILE ( \
+ LANDLOCK_ACCESS_FS_EXECUTE | \
+ LANDLOCK_ACCESS_FS_WRITE_FILE | \
+ LANDLOCK_ACCESS_FS_READ_FILE)
+
+/*
+ * @path: Should have been checked by get_path_from_fd().
+ */
+int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
+ const struct path *const path, u32 access_rights)
+{
+ int err;
+ struct landlock_object *object;
+
+ /* Files only get access rights that make sense. */
+ if (!d_is_dir(path->dentry) && (access_rights | ACCESS_FILE) !=
+ ACCESS_FILE)
+ return -EINVAL;
+ if (WARN_ON_ONCE(ruleset->num_layers != 1))
+ return -EINVAL;
+
+ /* Transforms relative access rights to absolute ones. */
+ access_rights |= LANDLOCK_MASK_ACCESS_FS & ~ruleset->fs_access_masks[0];
+ object = get_inode_object(d_backing_inode(path->dentry));
+ if (IS_ERR(object))
+ return PTR_ERR(object);
+ mutex_lock(&ruleset->lock);
+ err = landlock_insert_rule(ruleset, object, access_rights);
+ mutex_unlock(&ruleset->lock);
+ /*
+ * No need to check for an error because landlock_insert_rule()
+ * increments the refcount for the new object if needed.
+ */
+ landlock_put_object(object);
+ return err;
+}
+
+/* Access-control management */
+
+static inline u64 unmask_layers(
+ const struct landlock_ruleset *const domain,
+ const struct path *const path, const u32 access_request,
+ u64 layer_mask)
+{
+ const struct landlock_rule *rule;
+ const struct inode *inode;
+ size_t i;
+
+ if (d_is_negative(path->dentry))
+ /* Ignore nonexistent leafs. */
+ return layer_mask;
+ inode = d_backing_inode(path->dentry);
+ rcu_read_lock();
+ rule = landlock_find_rule(domain,
+ rcu_dereference(landlock_inode(inode)->object));
+ rcu_read_unlock();
+ if (!rule)
+ return layer_mask;
+
+ /*
+ * An access is granted if, for each policy layer, at least one rule
+ * encountered on the pathwalk grants the requested accesses,
+ * regardless of their position in the layer stack. We must then check
+ * the remaining layers for each inode, from the first added layer to
+ * the last one.
+ */
+ for (i = 0; i < rule->num_layers; i++) {
+ const struct landlock_layer *const layer = &rule->layers[i];
+ const u64 layer_level = BIT_ULL(layer->level - 1);
+
+ /* Checks that the layer grants access to the full request. */
+ if ((layer->access & access_request) == access_request) {
+ layer_mask &= ~layer_level;
+
+ if (layer_mask == 0)
+ return layer_mask;
+ }
+ }
+ return layer_mask;
+}
+
+static int check_access_path(const struct landlock_ruleset *const domain,
+ const struct path *const path, u32 access_request)
+{
+ bool allowed = false;
+ struct path walker_path;
+ u64 layer_mask;
+ size_t i;
+
+ /* Make sure all layers can be checked. */
+ BUILD_BUG_ON(BITS_PER_TYPE(layer_mask) < LANDLOCK_MAX_NUM_LAYERS);
+
+ if (!access_request)
+ return 0;
+ if (WARN_ON_ONCE(!domain || !path))
+ return 0;
+ /*
+ * Allows access to pseudo filesystems that will never be mountable
+ * (e.g. sockfs, pipefs), but can still be reachable through
+ * /proc/<pid>/fd/<file-descriptor> .
+ */
+ if ((path->dentry->d_sb->s_flags & SB_NOUSER) ||
+ (d_is_positive(path->dentry) &&
+ unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))))
+ return 0;
+ if (WARN_ON_ONCE(domain->num_layers < 1))
+ return -EACCES;
+
+ /* Saves all layers handling a subset of requested accesses. */
+ layer_mask = 0;
+ for (i = 0; i < domain->num_layers; i++) {
+ if (domain->fs_access_masks[i] & access_request)
+ layer_mask |= BIT_ULL(i);
+ }
+ /* An access request not handled by the domain is allowed. */
+ if (layer_mask == 0)
+ return 0;
+
+ walker_path = *path;
+ path_get(&walker_path);
+ /*
+ * We need to walk through all the hierarchy to not miss any relevant
+ * restriction.
+ */
+ while (true) {
+ struct dentry *parent_dentry;
+
+ layer_mask = unmask_layers(domain, &walker_path,
+ access_request, layer_mask);
+ if (layer_mask == 0) {
+ /* Stops when a rule from each layer grants access. */
+ allowed = true;
+ break;
+ }
+
+jump_up:
+ if (walker_path.dentry == walker_path.mnt->mnt_root) {
+ if (follow_up(&walker_path)) {
+ /* Ignores hidden mount points. */
+ goto jump_up;
+ } else {
+ /*
+ * Stops at the real root. Denies access
+ * because not all layers have granted access.
+ */
+ allowed = false;
+ break;
+ }
+ }
+ if (unlikely(IS_ROOT(walker_path.dentry))) {
+ /*
+ * Stops at disconnected root directories. Only allows
+ * access to internal filesystems (e.g. nsfs, which is
+ * reachable through /proc/<pid>/ns/<namespace>).
+ */
+ allowed = !!(walker_path.mnt->mnt_flags & MNT_INTERNAL);
+ break;
+ }
+ parent_dentry = dget_parent(walker_path.dentry);
+ dput(walker_path.dentry);
+ walker_path.dentry = parent_dentry;
+ }
+ path_put(&walker_path);
+ return allowed ? 0 : -EACCES;
+}
+
+static inline int current_check_access_path(const struct path *const path,
+ const u32 access_request)
+{
+ const struct landlock_ruleset *const dom =
+ landlock_get_current_domain();
+
+ if (!dom)
+ return 0;
+ return check_access_path(dom, path, access_request);
+}
+
+/* Inode hooks */
+
+static void hook_inode_free_security(struct inode *const inode)
+{
+ /*
+ * All inodes must already have been untied from their object by
+ * release_inode() or hook_sb_delete().
+ */
+ WARN_ON_ONCE(landlock_inode(inode)->object);
+}
+
+/* Super-block hooks */
+
+/*
+ * Release the inodes used in a security policy.
+ *
+ * Cf. fsnotify_unmount_inodes() and invalidate_inodes()
+ */
+static void hook_sb_delete(struct super_block *const sb)
+{
+ struct inode *inode, *prev_inode = NULL;
+
+ if (!landlock_initialized)
+ return;
+
+ spin_lock(&sb->s_inode_list_lock);
+ list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+ struct landlock_object *object;
+
+ /* Only handles referenced inodes. */
+ if (!atomic_read(&inode->i_count))
+ continue;
+
+ /*
+ * Protects against concurrent modification of inode (e.g.
+ * from get_inode_object()).
+ */
+ spin_lock(&inode->i_lock);
+ /*
+ * Checks I_FREEING and I_WILL_FREE to protect against a race
+ * condition when release_inode() just called iput(), which
+ * could lead to a NULL dereference of inode->security or a
+ * second call to iput() for the same Landlock object. Also
+ * checks I_NEW because such inode cannot be tied to an object.
+ */
+ if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ rcu_read_lock();
+ object = rcu_dereference(landlock_inode(inode)->object);
+ if (!object) {
+ rcu_read_unlock();
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ /* Keeps a reference to this inode until the next loop walk. */
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+
+ /*
+ * If there is no concurrent release_inode() ongoing, then we
+ * are in charge of calling iput() on this inode, otherwise we
+ * will just wait for it to finish.
+ */
+ spin_lock(&object->lock);
+ if (object->underobj == inode) {
+ object->underobj = NULL;
+ spin_unlock(&object->lock);
+ rcu_read_unlock();
+
+ /*
+ * Because object->underobj was not NULL,
+ * release_inode() and get_inode_object() guarantee
+ * that it is safe to reset
+ * landlock_inode(inode)->object while it is not NULL.
+ * It is therefore not necessary to lock inode->i_lock.
+ */
+ rcu_assign_pointer(landlock_inode(inode)->object, NULL);
+ /*
+ * At this point, we own the ihold() reference that was
+ * originally set up by get_inode_object() and the
+ * __iget() reference that we just set in this loop
+ * walk. Therefore the following call to iput() will
+ * not sleep nor drop the inode because there is now at
+ * least two references to it.
+ */
+ iput(inode);
+ } else {
+ spin_unlock(&object->lock);
+ rcu_read_unlock();
+ }
+
+ if (prev_inode) {
+ /*
+ * At this point, we still own the __iget() reference
+ * that we just set in this loop walk. Therefore we
+ * can drop the list lock and know that the inode won't
+ * disappear from under us until the next loop walk.
+ */
+ spin_unlock(&sb->s_inode_list_lock);
+ /*
+ * We can now actually put the inode reference from the
+ * previous loop walk, which is not needed anymore.
+ */
+ iput(prev_inode);
+ cond_resched();
+ spin_lock(&sb->s_inode_list_lock);
+ }
+ prev_inode = inode;
+ }
+ spin_unlock(&sb->s_inode_list_lock);
+
+ /* Puts the inode reference from the last loop walk, if any. */
+ if (prev_inode)
+ iput(prev_inode);
+ /* Waits for pending iput() in release_inode(). */
+ wait_var_event(&landlock_superblock(sb)->inode_refs, !atomic_long_read(
+ &landlock_superblock(sb)->inode_refs));
+}
+
+/*
+ * Because a Landlock security policy is defined according to the filesystem
+ * topology (i.e. the mount namespace), changing it may grant access to files
+ * not previously allowed.
+ *
+ * To make it simple, deny any filesystem topology modification by landlocked
+ * processes. Non-landlocked processes may still change the namespace of a
+ * landlocked process, but this kind of threat must be handled by a system-wide
+ * access-control security policy.
+ *
+ * This could be lifted in the future if Landlock can safely handle mount
+ * namespace updates requested by a landlocked process. Indeed, we could
+ * update the current domain (which is currently read-only) by taking into
+ * account the accesses of the source and the destination of a new mount point.
+ * However, it would also require to make all the child domains dynamically
+ * inherit these new constraints. Anyway, for backward compatibility reasons,
+ * a dedicated user space option would be required (e.g. as a ruleset flag).
+ */
+static int hook_sb_mount(const char *const dev_name,
+ const struct path *const path, const char *const type,
+ const unsigned long flags, void *const data)
+{
+ if (!landlock_get_current_domain())
+ return 0;
+ return -EPERM;
+}
+
+static int hook_move_mount(const struct path *const from_path,
+ const struct path *const to_path)
+{
+ if (!landlock_get_current_domain())
+ return 0;
+ return -EPERM;
+}
+
+/*
+ * Removing a mount point may reveal a previously hidden file hierarchy, which
+ * may then grant access to files, which may have previously been forbidden.
+ */
+static int hook_sb_umount(struct vfsmount *const mnt, const int flags)
+{
+ if (!landlock_get_current_domain())
+ return 0;
+ return -EPERM;
+}
+
+static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts)
+{
+ if (!landlock_get_current_domain())
+ return 0;
+ return -EPERM;
+}
+
+/*
+ * pivot_root(2), like mount(2), changes the current mount namespace. It must
+ * then be forbidden for a landlocked process.
+ *
+ * However, chroot(2) may be allowed because it only changes the relative root
+ * directory of the current process. Moreover, it can be used to restrict the
+ * view of the filesystem.
+ */
+static int hook_sb_pivotroot(const struct path *const old_path,
+ const struct path *const new_path)
+{
+ if (!landlock_get_current_domain())
+ return 0;
+ return -EPERM;
+}
+
+/* Path hooks */
+
+static inline u32 get_mode_access(const umode_t mode)
+{
+ switch (mode & S_IFMT) {
+ case S_IFLNK:
+ return LANDLOCK_ACCESS_FS_MAKE_SYM;
+ case 0:
+ /* A zero mode translates to S_IFREG. */
+ case S_IFREG:
+ return LANDLOCK_ACCESS_FS_MAKE_REG;
+ case S_IFDIR:
+ return LANDLOCK_ACCESS_FS_MAKE_DIR;
+ case S_IFCHR:
+ return LANDLOCK_ACCESS_FS_MAKE_CHAR;
+ case S_IFBLK:
+ return LANDLOCK_ACCESS_FS_MAKE_BLOCK;
+ case S_IFIFO:
+ return LANDLOCK_ACCESS_FS_MAKE_FIFO;
+ case S_IFSOCK:
+ return LANDLOCK_ACCESS_FS_MAKE_SOCK;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+}
+
+/*
+ * Creating multiple links or renaming may lead to privilege escalations if not
+ * handled properly. Indeed, we must be sure that the source doesn't gain more
+ * privileges by being accessible from the destination. This is getting more
+ * complex when dealing with multiple layers. The whole picture can be seen as
+ * a multilayer partial ordering problem. A future version of Landlock will
+ * deal with that.
+ */
+static int hook_path_link(struct dentry *const old_dentry,
+ const struct path *const new_dir,
+ struct dentry *const new_dentry)
+{
+ const struct landlock_ruleset *const dom =
+ landlock_get_current_domain();
+
+ if (!dom)
+ return 0;
+ /* The mount points are the same for old and new paths, cf. EXDEV. */
+ if (old_dentry->d_parent != new_dir->dentry)
+ /* Gracefully forbids reparenting. */
+ return -EXDEV;
+ if (unlikely(d_is_negative(old_dentry)))
+ return -ENOENT;
+ return check_access_path(dom, new_dir,
+ get_mode_access(d_backing_inode(old_dentry)->i_mode));
+}
+
+static inline u32 maybe_remove(const struct dentry *const dentry)
+{
+ if (d_is_negative(dentry))
+ return 0;
+ return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR :
+ LANDLOCK_ACCESS_FS_REMOVE_FILE;
+}
+
+static int hook_path_rename(const struct path *const old_dir,
+ struct dentry *const old_dentry,
+ const struct path *const new_dir,
+ struct dentry *const new_dentry)
+{
+ const struct landlock_ruleset *const dom =
+ landlock_get_current_domain();
+
+ if (!dom)
+ return 0;
+ /* The mount points are the same for old and new paths, cf. EXDEV. */
+ if (old_dir->dentry != new_dir->dentry)
+ /* Gracefully forbids reparenting. */
+ return -EXDEV;
+ if (unlikely(d_is_negative(old_dentry)))
+ return -ENOENT;
+ /* RENAME_EXCHANGE is handled because directories are the same. */
+ return check_access_path(dom, old_dir, maybe_remove(old_dentry) |
+ maybe_remove(new_dentry) |
+ get_mode_access(d_backing_inode(old_dentry)->i_mode));
+}
+
+static int hook_path_mkdir(const struct path *const dir,
+ struct dentry *const dentry, const umode_t mode)
+{
+ return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR);
+}
+
+static int hook_path_mknod(const struct path *const dir,
+ struct dentry *const dentry, const umode_t mode,
+ const unsigned int dev)
+{
+ const struct landlock_ruleset *const dom =
+ landlock_get_current_domain();
+
+ if (!dom)
+ return 0;
+ return check_access_path(dom, dir, get_mode_access(mode));
+}
+
+static int hook_path_symlink(const struct path *const dir,
+ struct dentry *const dentry, const char *const old_name)
+{
+ return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM);
+}
+
+static int hook_path_unlink(const struct path *const dir,
+ struct dentry *const dentry)
+{
+ return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE);
+}
+
+static int hook_path_rmdir(const struct path *const dir,
+ struct dentry *const dentry)
+{
+ return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR);
+}
+
+/* File hooks */
+
+static inline u32 get_file_access(const struct file *const file)
+{
+ u32 access = 0;
+
+ if (file->f_mode & FMODE_READ) {
+ /* A directory can only be opened in read mode. */
+ if (S_ISDIR(file_inode(file)->i_mode))
+ return LANDLOCK_ACCESS_FS_READ_DIR;
+ access = LANDLOCK_ACCESS_FS_READ_FILE;
+ }
+ if (file->f_mode & FMODE_WRITE)
+ access |= LANDLOCK_ACCESS_FS_WRITE_FILE;
+ /* __FMODE_EXEC is indeed part of f_flags, not f_mode. */
+ if (file->f_flags & __FMODE_EXEC)
+ access |= LANDLOCK_ACCESS_FS_EXECUTE;
+ return access;
+}
+
+static int hook_file_open(struct file *const file)
+{
+ const struct landlock_ruleset *const dom =
+ landlock_get_current_domain();
+
+ if (!dom)
+ return 0;
+ /*
+ * Because a file may be opened with O_PATH, get_file_access() may
+ * return 0. This case will be handled with a future Landlock
+ * evolution.
+ */
+ return check_access_path(dom, &file->f_path, get_file_access(file));
+}
+
+static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = {
+ LSM_HOOK_INIT(inode_free_security, hook_inode_free_security),
+
+ LSM_HOOK_INIT(sb_delete, hook_sb_delete),
+ LSM_HOOK_INIT(sb_mount, hook_sb_mount),
+ LSM_HOOK_INIT(move_mount, hook_move_mount),
+ LSM_HOOK_INIT(sb_umount, hook_sb_umount),
+ LSM_HOOK_INIT(sb_remount, hook_sb_remount),
+ LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot),
+
+ LSM_HOOK_INIT(path_link, hook_path_link),
+ LSM_HOOK_INIT(path_rename, hook_path_rename),
+ LSM_HOOK_INIT(path_mkdir, hook_path_mkdir),
+ LSM_HOOK_INIT(path_mknod, hook_path_mknod),
+ LSM_HOOK_INIT(path_symlink, hook_path_symlink),
+ LSM_HOOK_INIT(path_unlink, hook_path_unlink),
+ LSM_HOOK_INIT(path_rmdir, hook_path_rmdir),
+
+ LSM_HOOK_INIT(file_open, hook_file_open),
+};
+
+__init void landlock_add_fs_hooks(void)
+{
+ security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+ LANDLOCK_NAME);
+}
diff --git a/security/landlock/fs.h b/security/landlock/fs.h
new file mode 100644
index 000000000000..187284b421c9
--- /dev/null
+++ b/security/landlock/fs.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Filesystem management and hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_FS_H
+#define _SECURITY_LANDLOCK_FS_H
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+
+#include "ruleset.h"
+#include "setup.h"
+
+/**
+ * struct landlock_inode_security - Inode security blob
+ *
+ * Enable to reference a &struct landlock_object tied to an inode (i.e.
+ * underlying object).
+ */
+struct landlock_inode_security {
+ /**
+ * @object: Weak pointer to an allocated object. All assignments of a
+ * new object are protected by the underlying inode->i_lock. However,
+ * atomically disassociating @object from the inode is only protected
+ * by @object->lock, from the time @object's usage refcount drops to
+ * zero to the time this pointer is nulled out (cf. release_inode() and
+ * hook_sb_delete()). Indeed, such disassociation doesn't require
+ * inode->i_lock thanks to the careful rcu_access_pointer() check
+ * performed by get_inode_object().
+ */
+ struct landlock_object __rcu *object;
+};
+
+/**
+ * struct landlock_superblock_security - Superblock security blob
+ *
+ * Enable hook_sb_delete() to wait for concurrent calls to release_inode().
+ */
+struct landlock_superblock_security {
+ /**
+ * @inode_refs: Number of pending inodes (from this superblock) that
+ * are being released by release_inode().
+ * Cf. struct super_block->s_fsnotify_inode_refs .
+ */
+ atomic_long_t inode_refs;
+};
+
+static inline struct landlock_inode_security *landlock_inode(
+ const struct inode *const inode)
+{
+ return inode->i_security + landlock_blob_sizes.lbs_inode;
+}
+
+static inline struct landlock_superblock_security *landlock_superblock(
+ const struct super_block *const superblock)
+{
+ return superblock->s_security + landlock_blob_sizes.lbs_superblock;
+}
+
+__init void landlock_add_fs_hooks(void);
+
+int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
+ const struct path *const path, u32 access_hierarchy);
+
+#endif /* _SECURITY_LANDLOCK_FS_H */
diff --git a/security/landlock/limits.h b/security/landlock/limits.h
new file mode 100644
index 000000000000..2a0a1095ee27
--- /dev/null
+++ b/security/landlock/limits.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Limits for different components
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_LIMITS_H
+#define _SECURITY_LANDLOCK_LIMITS_H
+
+#include <linux/limits.h>
+#include <uapi/linux/landlock.h>
+
+#define LANDLOCK_MAX_NUM_LAYERS 64
+#define LANDLOCK_MAX_NUM_RULES U32_MAX
+
+#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_MAKE_SYM
+#define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1)
+
+#endif /* _SECURITY_LANDLOCK_LIMITS_H */
diff --git a/security/landlock/object.c b/security/landlock/object.c
new file mode 100644
index 000000000000..d674fdf9ff04
--- /dev/null
+++ b/security/landlock/object.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Object management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/bug.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "object.h"
+
+struct landlock_object *landlock_create_object(
+ const struct landlock_object_underops *const underops,
+ void *const underobj)
+{
+ struct landlock_object *new_object;
+
+ if (WARN_ON_ONCE(!underops || !underobj))
+ return ERR_PTR(-ENOENT);
+ new_object = kzalloc(sizeof(*new_object), GFP_KERNEL_ACCOUNT);
+ if (!new_object)
+ return ERR_PTR(-ENOMEM);
+ refcount_set(&new_object->usage, 1);
+ spin_lock_init(&new_object->lock);
+ new_object->underops = underops;
+ new_object->underobj = underobj;
+ return new_object;
+}
+
+/*
+ * The caller must own the object (i.e. thanks to object->usage) to safely put
+ * it.
+ */
+void landlock_put_object(struct landlock_object *const object)
+{
+ /*
+ * The call to @object->underops->release(object) might sleep, e.g.
+ * because of iput().
+ */
+ might_sleep();
+ if (!object)
+ return;
+
+ /*
+ * If the @object's refcount cannot drop to zero, we can just decrement
+ * the refcount without holding a lock. Otherwise, the decrement must
+ * happen under @object->lock for synchronization with things like
+ * get_inode_object().
+ */
+ if (refcount_dec_and_lock(&object->usage, &object->lock)) {
+ __acquire(&object->lock);
+ /*
+ * With @object->lock initially held, remove the reference from
+ * @object->underobj to @object (if it still exists).
+ */
+ object->underops->release(object);
+ kfree_rcu(object, rcu_free);
+ }
+}
diff --git a/security/landlock/object.h b/security/landlock/object.h
new file mode 100644
index 000000000000..3f80674c6c8d
--- /dev/null
+++ b/security/landlock/object.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Object management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_OBJECT_H
+#define _SECURITY_LANDLOCK_OBJECT_H
+
+#include <linux/compiler_types.h>
+#include <linux/refcount.h>
+#include <linux/spinlock.h>
+
+struct landlock_object;
+
+/**
+ * struct landlock_object_underops - Operations on an underlying object
+ */
+struct landlock_object_underops {
+ /**
+ * @release: Releases the underlying object (e.g. iput() for an inode).
+ */
+ void (*release)(struct landlock_object *const object)
+ __releases(object->lock);
+};
+
+/**
+ * struct landlock_object - Security blob tied to a kernel object
+ *
+ * The goal of this structure is to enable to tie a set of ephemeral access
+ * rights (pertaining to different domains) to a kernel object (e.g an inode)
+ * in a safe way. This implies to handle concurrent use and modification.
+ *
+ * The lifetime of a &struct landlock_object depends on the rules referring to
+ * it.
+ */
+struct landlock_object {
+ /**
+ * @usage: This counter is used to tie an object to the rules matching
+ * it or to keep it alive while adding a new rule. If this counter
+ * reaches zero, this struct must not be modified, but this counter can
+ * still be read from within an RCU read-side critical section. When
+ * adding a new rule to an object with a usage counter of zero, we must
+ * wait until the pointer to this object is set to NULL (or recycled).
+ */
+ refcount_t usage;
+ /**
+ * @lock: Protects against concurrent modifications. This lock must be
+ * held from the time @usage drops to zero until any weak references
+ * from @underobj to this object have been cleaned up.
+ *
+ * Lock ordering: inode->i_lock nests inside this.
+ */
+ spinlock_t lock;
+ /**
+ * @underobj: Used when cleaning up an object and to mark an object as
+ * tied to its underlying kernel structure. This pointer is protected
+ * by @lock. Cf. landlock_release_inodes() and release_inode().
+ */
+ void *underobj;
+ union {
+ /**
+ * @rcu_free: Enables lockless use of @usage, @lock and
+ * @underobj from within an RCU read-side critical section.
+ * @rcu_free and @underops are only used by
+ * landlock_put_object().
+ */
+ struct rcu_head rcu_free;
+ /**
+ * @underops: Enables landlock_put_object() to release the
+ * underlying object (e.g. inode).
+ */
+ const struct landlock_object_underops *underops;
+ };
+};
+
+struct landlock_object *landlock_create_object(
+ const struct landlock_object_underops *const underops,
+ void *const underobj);
+
+void landlock_put_object(struct landlock_object *const object);
+
+static inline void landlock_get_object(struct landlock_object *const object)
+{
+ if (object)
+ refcount_inc(&object->usage);
+}
+
+#endif /* _SECURITY_LANDLOCK_OBJECT_H */
diff --git a/security/landlock/ptrace.c b/security/landlock/ptrace.c
new file mode 100644
index 000000000000..f55b82446de2
--- /dev/null
+++ b/security/landlock/ptrace.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Ptrace hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ */
+
+#include <asm/current.h>
+#include <linux/cred.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/lsm_hooks.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+
+#include "common.h"
+#include "cred.h"
+#include "ptrace.h"
+#include "ruleset.h"
+#include "setup.h"
+
+/**
+ * domain_scope_le - Checks domain ordering for scoped ptrace
+ *
+ * @parent: Parent domain.
+ * @child: Potential child of @parent.
+ *
+ * Checks if the @parent domain is less or equal to (i.e. an ancestor, which
+ * means a subset of) the @child domain.
+ */
+static bool domain_scope_le(const struct landlock_ruleset *const parent,
+ const struct landlock_ruleset *const child)
+{
+ const struct landlock_hierarchy *walker;
+
+ if (!parent)
+ return true;
+ if (!child)
+ return false;
+ for (walker = child->hierarchy; walker; walker = walker->parent) {
+ if (walker == parent->hierarchy)
+ /* @parent is in the scoped hierarchy of @child. */
+ return true;
+ }
+ /* There is no relationship between @parent and @child. */
+ return false;
+}
+
+static bool task_is_scoped(const struct task_struct *const parent,
+ const struct task_struct *const child)
+{
+ bool is_scoped;
+ const struct landlock_ruleset *dom_parent, *dom_child;
+
+ rcu_read_lock();
+ dom_parent = landlock_get_task_domain(parent);
+ dom_child = landlock_get_task_domain(child);
+ is_scoped = domain_scope_le(dom_parent, dom_child);
+ rcu_read_unlock();
+ return is_scoped;
+}
+
+static int task_ptrace(const struct task_struct *const parent,
+ const struct task_struct *const child)
+{
+ /* Quick return for non-landlocked tasks. */
+ if (!landlocked(parent))
+ return 0;
+ if (task_is_scoped(parent, child))
+ return 0;
+ return -EPERM;
+}
+
+/**
+ * hook_ptrace_access_check - Determines whether the current process may access
+ * another
+ *
+ * @child: Process to be accessed.
+ * @mode: Mode of attachment.
+ *
+ * If the current task has Landlock rules, then the child must have at least
+ * the same rules. Else denied.
+ *
+ * Determines whether a process may access another, returning 0 if permission
+ * granted, -errno if denied.
+ */
+static int hook_ptrace_access_check(struct task_struct *const child,
+ const unsigned int mode)
+{
+ return task_ptrace(current, child);
+}
+
+/**
+ * hook_ptrace_traceme - Determines whether another process may trace the
+ * current one
+ *
+ * @parent: Task proposed to be the tracer.
+ *
+ * If the parent has Landlock rules, then the current task must have the same
+ * or more rules. Else denied.
+ *
+ * Determines whether the nominated task is permitted to trace the current
+ * process, returning 0 if permission is granted, -errno if denied.
+ */
+static int hook_ptrace_traceme(struct task_struct *const parent)
+{
+ return task_ptrace(parent, current);
+}
+
+static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = {
+ LSM_HOOK_INIT(ptrace_access_check, hook_ptrace_access_check),
+ LSM_HOOK_INIT(ptrace_traceme, hook_ptrace_traceme),
+};
+
+__init void landlock_add_ptrace_hooks(void)
+{
+ security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+ LANDLOCK_NAME);
+}
diff --git a/security/landlock/ptrace.h b/security/landlock/ptrace.h
new file mode 100644
index 000000000000..265b220ae3bf
--- /dev/null
+++ b/security/landlock/ptrace.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Ptrace hooks
+ *
+ * Copyright © 2017-2019 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_PTRACE_H
+#define _SECURITY_LANDLOCK_PTRACE_H
+
+__init void landlock_add_ptrace_hooks(void);
+
+#endif /* _SECURITY_LANDLOCK_PTRACE_H */
diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
new file mode 100644
index 000000000000..ec72b9262bf3
--- /dev/null
+++ b/security/landlock/ruleset.c
@@ -0,0 +1,473 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Ruleset management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/overflow.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+
+#include "limits.h"
+#include "object.h"
+#include "ruleset.h"
+
+static struct landlock_ruleset *create_ruleset(const u32 num_layers)
+{
+ struct landlock_ruleset *new_ruleset;
+
+ new_ruleset = kzalloc(struct_size(new_ruleset, fs_access_masks,
+ num_layers), GFP_KERNEL_ACCOUNT);
+ if (!new_ruleset)
+ return ERR_PTR(-ENOMEM);
+ refcount_set(&new_ruleset->usage, 1);
+ mutex_init(&new_ruleset->lock);
+ new_ruleset->root = RB_ROOT;
+ new_ruleset->num_layers = num_layers;
+ /*
+ * hierarchy = NULL
+ * num_rules = 0
+ * fs_access_masks[] = 0
+ */
+ return new_ruleset;
+}
+
+struct landlock_ruleset *landlock_create_ruleset(const u32 fs_access_mask)
+{
+ struct landlock_ruleset *new_ruleset;
+
+ /* Informs about useless ruleset. */
+ if (!fs_access_mask)
+ return ERR_PTR(-ENOMSG);
+ new_ruleset = create_ruleset(1);
+ if (!IS_ERR(new_ruleset))
+ new_ruleset->fs_access_masks[0] = fs_access_mask;
+ return new_ruleset;
+}
+
+static void build_check_rule(void)
+{
+ const struct landlock_rule rule = {
+ .num_layers = ~0,
+ };
+
+ BUILD_BUG_ON(rule.num_layers < LANDLOCK_MAX_NUM_LAYERS);
+}
+
+static struct landlock_rule *create_rule(
+ struct landlock_object *const object,
+ const struct landlock_layer (*const layers)[],
+ const u32 num_layers,
+ const struct landlock_layer *const new_layer)
+{
+ struct landlock_rule *new_rule;
+ u32 new_num_layers;
+
+ build_check_rule();
+ if (new_layer) {
+ /* Should already be checked by landlock_merge_ruleset(). */
+ if (WARN_ON_ONCE(num_layers >= LANDLOCK_MAX_NUM_LAYERS))
+ return ERR_PTR(-E2BIG);
+ new_num_layers = num_layers + 1;
+ } else {
+ new_num_layers = num_layers;
+ }
+ new_rule = kzalloc(struct_size(new_rule, layers, new_num_layers),
+ GFP_KERNEL_ACCOUNT);
+ if (!new_rule)
+ return ERR_PTR(-ENOMEM);
+ RB_CLEAR_NODE(&new_rule->node);
+ landlock_get_object(object);
+ new_rule->object = object;
+ new_rule->num_layers = new_num_layers;
+ /* Copies the original layer stack. */
+ memcpy(new_rule->layers, layers,
+ flex_array_size(new_rule, layers, num_layers));
+ if (new_layer)
+ /* Adds a copy of @new_layer on the layer stack. */
+ new_rule->layers[new_rule->num_layers - 1] = *new_layer;
+ return new_rule;
+}
+
+static void free_rule(struct landlock_rule *const rule)
+{
+ might_sleep();
+ if (!rule)
+ return;
+ landlock_put_object(rule->object);
+ kfree(rule);
+}
+
+static void build_check_ruleset(void)
+{
+ const struct landlock_ruleset ruleset = {
+ .num_rules = ~0,
+ .num_layers = ~0,
+ };
+ typeof(ruleset.fs_access_masks[0]) fs_access_mask = ~0;
+
+ BUILD_BUG_ON(ruleset.num_rules < LANDLOCK_MAX_NUM_RULES);
+ BUILD_BUG_ON(ruleset.num_layers < LANDLOCK_MAX_NUM_LAYERS);
+ BUILD_BUG_ON(fs_access_mask < LANDLOCK_MASK_ACCESS_FS);
+}
+
+/**
+ * insert_rule - Create and insert a rule in a ruleset
+ *
+ * @ruleset: The ruleset to be updated.
+ * @object: The object to build the new rule with. The underlying kernel
+ * object must be held by the caller.
+ * @layers: One or multiple layers to be copied into the new rule.
+ * @num_layers: The number of @layers entries.
+ *
+ * When user space requests to add a new rule to a ruleset, @layers only
+ * contains one entry and this entry is not assigned to any level. In this
+ * case, the new rule will extend @ruleset, similarly to a boolean OR between
+ * access rights.
+ *
+ * When merging a ruleset in a domain, or copying a domain, @layers will be
+ * added to @ruleset as new constraints, similarly to a boolean AND between
+ * access rights.
+ */
+static int insert_rule(struct landlock_ruleset *const ruleset,
+ struct landlock_object *const object,
+ const struct landlock_layer (*const layers)[],
+ size_t num_layers)
+{
+ struct rb_node **walker_node;
+ struct rb_node *parent_node = NULL;
+ struct landlock_rule *new_rule;
+
+ might_sleep();
+ lockdep_assert_held(&ruleset->lock);
+ if (WARN_ON_ONCE(!object || !layers))
+ return -ENOENT;
+ walker_node = &(ruleset->root.rb_node);
+ while (*walker_node) {
+ struct landlock_rule *const this = rb_entry(*walker_node,
+ struct landlock_rule, node);
+
+ if (this->object != object) {
+ parent_node = *walker_node;
+ if (this->object < object)
+ walker_node = &((*walker_node)->rb_right);
+ else
+ walker_node = &((*walker_node)->rb_left);
+ continue;
+ }
+
+ /* Only a single-level layer should match an existing rule. */
+ if (WARN_ON_ONCE(num_layers != 1))
+ return -EINVAL;
+
+ /* If there is a matching rule, updates it. */
+ if ((*layers)[0].level == 0) {
+ /*
+ * Extends access rights when the request comes from
+ * landlock_add_rule(2), i.e. @ruleset is not a domain.
+ */
+ if (WARN_ON_ONCE(this->num_layers != 1))
+ return -EINVAL;
+ if (WARN_ON_ONCE(this->layers[0].level != 0))
+ return -EINVAL;
+ this->layers[0].access |= (*layers)[0].access;
+ return 0;
+ }
+
+ if (WARN_ON_ONCE(this->layers[0].level == 0))
+ return -EINVAL;
+
+ /*
+ * Intersects access rights when it is a merge between a
+ * ruleset and a domain.
+ */
+ new_rule = create_rule(object, &this->layers, this->num_layers,
+ &(*layers)[0]);
+ if (IS_ERR(new_rule))
+ return PTR_ERR(new_rule);
+ rb_replace_node(&this->node, &new_rule->node, &ruleset->root);
+ free_rule(this);
+ return 0;
+ }
+
+ /* There is no match for @object. */
+ build_check_ruleset();
+ if (ruleset->num_rules >= LANDLOCK_MAX_NUM_RULES)
+ return -E2BIG;
+ new_rule = create_rule(object, layers, num_layers, NULL);
+ if (IS_ERR(new_rule))
+ return PTR_ERR(new_rule);
+ rb_link_node(&new_rule->node, parent_node, walker_node);
+ rb_insert_color(&new_rule->node, &ruleset->root);
+ ruleset->num_rules++;
+ return 0;
+}
+
+static void build_check_layer(void)
+{
+ const struct landlock_layer layer = {
+ .level = ~0,
+ .access = ~0,
+ };
+
+ BUILD_BUG_ON(layer.level < LANDLOCK_MAX_NUM_LAYERS);
+ BUILD_BUG_ON(layer.access < LANDLOCK_MASK_ACCESS_FS);
+}
+
+/* @ruleset must be locked by the caller. */
+int landlock_insert_rule(struct landlock_ruleset *const ruleset,
+ struct landlock_object *const object, const u32 access)
+{
+ struct landlock_layer layers[] = {{
+ .access = access,
+ /* When @level is zero, insert_rule() extends @ruleset. */
+ .level = 0,
+ }};
+
+ build_check_layer();
+ return insert_rule(ruleset, object, &layers, ARRAY_SIZE(layers));
+}
+
+static inline void get_hierarchy(struct landlock_hierarchy *const hierarchy)
+{
+ if (hierarchy)
+ refcount_inc(&hierarchy->usage);
+}
+
+static void put_hierarchy(struct landlock_hierarchy *hierarchy)
+{
+ while (hierarchy && refcount_dec_and_test(&hierarchy->usage)) {
+ const struct landlock_hierarchy *const freeme = hierarchy;
+
+ hierarchy = hierarchy->parent;
+ kfree(freeme);
+ }
+}
+
+static int merge_ruleset(struct landlock_ruleset *const dst,
+ struct landlock_ruleset *const src)
+{
+ struct landlock_rule *walker_rule, *next_rule;
+ int err = 0;
+
+ might_sleep();
+ /* Should already be checked by landlock_merge_ruleset() */
+ if (WARN_ON_ONCE(!src))
+ return 0;
+ /* Only merge into a domain. */
+ if (WARN_ON_ONCE(!dst || !dst->hierarchy))
+ return -EINVAL;
+
+ /* Locks @dst first because we are its only owner. */
+ mutex_lock(&dst->lock);
+ mutex_lock_nested(&src->lock, SINGLE_DEPTH_NESTING);
+
+ /* Stacks the new layer. */
+ if (WARN_ON_ONCE(src->num_layers != 1 || dst->num_layers < 1)) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+ dst->fs_access_masks[dst->num_layers - 1] = src->fs_access_masks[0];
+
+ /* Merges the @src tree. */
+ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule,
+ &src->root, node) {
+ struct landlock_layer layers[] = {{
+ .level = dst->num_layers,
+ }};
+
+ if (WARN_ON_ONCE(walker_rule->num_layers != 1)) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+ if (WARN_ON_ONCE(walker_rule->layers[0].level != 0)) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+ layers[0].access = walker_rule->layers[0].access;
+ err = insert_rule(dst, walker_rule->object, &layers,
+ ARRAY_SIZE(layers));
+ if (err)
+ goto out_unlock;
+ }
+
+out_unlock:
+ mutex_unlock(&src->lock);
+ mutex_unlock(&dst->lock);
+ return err;
+}
+
+static int inherit_ruleset(struct landlock_ruleset *const parent,
+ struct landlock_ruleset *const child)
+{
+ struct landlock_rule *walker_rule, *next_rule;
+ int err = 0;
+
+ might_sleep();
+ if (!parent)
+ return 0;
+
+ /* Locks @child first because we are its only owner. */
+ mutex_lock(&child->lock);
+ mutex_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING);
+
+ /* Copies the @parent tree. */
+ rbtree_postorder_for_each_entry_safe(walker_rule, next_rule,
+ &parent->root, node) {
+ err = insert_rule(child, walker_rule->object,
+ &walker_rule->layers, walker_rule->num_layers);
+ if (err)
+ goto out_unlock;
+ }
+
+ if (WARN_ON_ONCE(child->num_layers <= parent->num_layers)) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+ /* Copies the parent layer stack and leaves a space for the new layer. */
+ memcpy(child->fs_access_masks, parent->fs_access_masks,
+ flex_array_size(parent, fs_access_masks, parent->num_layers));
+
+ if (WARN_ON_ONCE(!parent->hierarchy)) {
+ err = -EINVAL;
+ goto out_unlock;
+ }
+ get_hierarchy(parent->hierarchy);
+ child->hierarchy->parent = parent->hierarchy;
+
+out_unlock:
+ mutex_unlock(&parent->lock);
+ mutex_unlock(&child->lock);
+ return err;
+}
+
+static void free_ruleset(struct landlock_ruleset *const ruleset)
+{
+ struct landlock_rule *freeme, *next;
+
+ might_sleep();
+ rbtree_postorder_for_each_entry_safe(freeme, next, &ruleset->root,
+ node)
+ free_rule(freeme);
+ put_hierarchy(ruleset->hierarchy);
+ kfree(ruleset);
+}
+
+void landlock_put_ruleset(struct landlock_ruleset *const ruleset)
+{
+ might_sleep();
+ if (ruleset && refcount_dec_and_test(&ruleset->usage))
+ free_ruleset(ruleset);
+}
+
+static void free_ruleset_work(struct work_struct *const work)
+{
+ struct landlock_ruleset *ruleset;
+
+ ruleset = container_of(work, struct landlock_ruleset, work_free);
+ free_ruleset(ruleset);
+}
+
+void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset)
+{
+ if (ruleset && refcount_dec_and_test(&ruleset->usage)) {
+ INIT_WORK(&ruleset->work_free, free_ruleset_work);
+ schedule_work(&ruleset->work_free);
+ }
+}
+
+/**
+ * landlock_merge_ruleset - Merge a ruleset with a domain
+ *
+ * @parent: Parent domain.
+ * @ruleset: New ruleset to be merged.
+ *
+ * Returns the intersection of @parent and @ruleset, or returns @parent if
+ * @ruleset is empty, or returns a duplicate of @ruleset if @parent is empty.
+ */
+struct landlock_ruleset *landlock_merge_ruleset(
+ struct landlock_ruleset *const parent,
+ struct landlock_ruleset *const ruleset)
+{
+ struct landlock_ruleset *new_dom;
+ u32 num_layers;
+ int err;
+
+ might_sleep();
+ if (WARN_ON_ONCE(!ruleset || parent == ruleset))
+ return ERR_PTR(-EINVAL);
+
+ if (parent) {
+ if (parent->num_layers >= LANDLOCK_MAX_NUM_LAYERS)
+ return ERR_PTR(-E2BIG);
+ num_layers = parent->num_layers + 1;
+ } else {
+ num_layers = 1;
+ }
+
+ /* Creates a new domain... */
+ new_dom = create_ruleset(num_layers);
+ if (IS_ERR(new_dom))
+ return new_dom;
+ new_dom->hierarchy = kzalloc(sizeof(*new_dom->hierarchy),
+ GFP_KERNEL_ACCOUNT);
+ if (!new_dom->hierarchy) {
+ err = -ENOMEM;
+ goto out_put_dom;
+ }
+ refcount_set(&new_dom->hierarchy->usage, 1);
+
+ /* ...as a child of @parent... */
+ err = inherit_ruleset(parent, new_dom);
+ if (err)
+ goto out_put_dom;
+
+ /* ...and including @ruleset. */
+ err = merge_ruleset(new_dom, ruleset);
+ if (err)
+ goto out_put_dom;
+
+ return new_dom;
+
+out_put_dom:
+ landlock_put_ruleset(new_dom);
+ return ERR_PTR(err);
+}
+
+/*
+ * The returned access has the same lifetime as @ruleset.
+ */
+const struct landlock_rule *landlock_find_rule(
+ const struct landlock_ruleset *const ruleset,
+ const struct landlock_object *const object)
+{
+ const struct rb_node *node;
+
+ if (!object)
+ return NULL;
+ node = ruleset->root.rb_node;
+ while (node) {
+ struct landlock_rule *this = rb_entry(node,
+ struct landlock_rule, node);
+
+ if (this->object == object)
+ return this;
+ if (this->object < object)
+ node = node->rb_right;
+ else
+ node = node->rb_left;
+ }
+ return NULL;
+}
diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h
new file mode 100644
index 000000000000..2d3ed7ec5a0a
--- /dev/null
+++ b/security/landlock/ruleset.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Ruleset management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_RULESET_H
+#define _SECURITY_LANDLOCK_RULESET_H
+
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/workqueue.h>
+
+#include "object.h"
+
+/**
+ * struct landlock_layer - Access rights for a given layer
+ */
+struct landlock_layer {
+ /**
+ * @level: Position of this layer in the layer stack.
+ */
+ u16 level;
+ /**
+ * @access: Bitfield of allowed actions on the kernel object. They are
+ * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ).
+ */
+ u16 access;
+};
+
+/**
+ * struct landlock_rule - Access rights tied to an object
+ */
+struct landlock_rule {
+ /**
+ * @node: Node in the ruleset's red-black tree.
+ */
+ struct rb_node node;
+ /**
+ * @object: Pointer to identify a kernel object (e.g. an inode). This
+ * is used as a key for this ruleset element. This pointer is set once
+ * and never modified. It always points to an allocated object because
+ * each rule increments the refcount of its object.
+ */
+ struct landlock_object *object;
+ /**
+ * @num_layers: Number of entries in @layers.
+ */
+ u32 num_layers;
+ /**
+ * @layers: Stack of layers, from the latest to the newest, implemented
+ * as a flexible array member (FAM).
+ */
+ struct landlock_layer layers[];
+};
+
+/**
+ * struct landlock_hierarchy - Node in a ruleset hierarchy
+ */
+struct landlock_hierarchy {
+ /**
+ * @parent: Pointer to the parent node, or NULL if it is a root
+ * Landlock domain.
+ */
+ struct landlock_hierarchy *parent;
+ /**
+ * @usage: Number of potential children domains plus their parent
+ * domain.
+ */
+ refcount_t usage;
+};
+
+/**
+ * struct landlock_ruleset - Landlock ruleset
+ *
+ * This data structure must contain unique entries, be updatable, and quick to
+ * match an object.
+ */
+struct landlock_ruleset {
+ /**
+ * @root: Root of a red-black tree containing &struct landlock_rule
+ * nodes. Once a ruleset is tied to a process (i.e. as a domain), this
+ * tree is immutable until @usage reaches zero.
+ */
+ struct rb_root root;
+ /**
+ * @hierarchy: Enables hierarchy identification even when a parent
+ * domain vanishes. This is needed for the ptrace protection.
+ */
+ struct landlock_hierarchy *hierarchy;
+ union {
+ /**
+ * @work_free: Enables to free a ruleset within a lockless
+ * section. This is only used by
+ * landlock_put_ruleset_deferred() when @usage reaches zero.
+ * The fields @lock, @usage, @num_rules, @num_layers and
+ * @fs_access_masks are then unused.
+ */
+ struct work_struct work_free;
+ struct {
+ /**
+ * @lock: Protects against concurrent modifications of
+ * @root, if @usage is greater than zero.
+ */
+ struct mutex lock;
+ /**
+ * @usage: Number of processes (i.e. domains) or file
+ * descriptors referencing this ruleset.
+ */
+ refcount_t usage;
+ /**
+ * @num_rules: Number of non-overlapping (i.e. not for
+ * the same object) rules in this ruleset.
+ */
+ u32 num_rules;
+ /**
+ * @num_layers: Number of layers that are used in this
+ * ruleset. This enables to check that all the layers
+ * allow an access request. A value of 0 identifies a
+ * non-merged ruleset (i.e. not a domain).
+ */
+ u32 num_layers;
+ /**
+ * @fs_access_masks: Contains the subset of filesystem
+ * actions that are restricted by a ruleset. A domain
+ * saves all layers of merged rulesets in a stack
+ * (FAM), starting from the first layer to the last
+ * one. These layers are used when merging rulesets,
+ * for user space backward compatibility (i.e.
+ * future-proof), and to properly handle merged
+ * rulesets without overlapping access rights. These
+ * layers are set once and never changed for the
+ * lifetime of the ruleset.
+ */
+ u16 fs_access_masks[];
+ };
+ };
+};
+
+struct landlock_ruleset *landlock_create_ruleset(const u32 fs_access_mask);
+
+void landlock_put_ruleset(struct landlock_ruleset *const ruleset);
+void landlock_put_ruleset_deferred(struct landlock_ruleset *const ruleset);
+
+int landlock_insert_rule(struct landlock_ruleset *const ruleset,
+ struct landlock_object *const object, const u32 access);
+
+struct landlock_ruleset *landlock_merge_ruleset(
+ struct landlock_ruleset *const parent,
+ struct landlock_ruleset *const ruleset);
+
+const struct landlock_rule *landlock_find_rule(
+ const struct landlock_ruleset *const ruleset,
+ const struct landlock_object *const object);
+
+static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset)
+{
+ if (ruleset)
+ refcount_inc(&ruleset->usage);
+}
+
+#endif /* _SECURITY_LANDLOCK_RULESET_H */
diff --git a/security/landlock/setup.c b/security/landlock/setup.c
new file mode 100644
index 000000000000..f8e8e980454c
--- /dev/null
+++ b/security/landlock/setup.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Security framework setup
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/init.h>
+#include <linux/lsm_hooks.h>
+
+#include "common.h"
+#include "cred.h"
+#include "fs.h"
+#include "ptrace.h"
+#include "setup.h"
+
+bool landlock_initialized __lsm_ro_after_init = false;
+
+struct lsm_blob_sizes landlock_blob_sizes __lsm_ro_after_init = {
+ .lbs_cred = sizeof(struct landlock_cred_security),
+ .lbs_inode = sizeof(struct landlock_inode_security),
+ .lbs_superblock = sizeof(struct landlock_superblock_security),
+};
+
+static int __init landlock_init(void)
+{
+ landlock_add_cred_hooks();
+ landlock_add_ptrace_hooks();
+ landlock_add_fs_hooks();
+ landlock_initialized = true;
+ pr_info("Up and running.\n");
+ return 0;
+}
+
+DEFINE_LSM(LANDLOCK_NAME) = {
+ .name = LANDLOCK_NAME,
+ .init = landlock_init,
+ .blobs = &landlock_blob_sizes,
+};
diff --git a/security/landlock/setup.h b/security/landlock/setup.h
new file mode 100644
index 000000000000..1daffab1ab4b
--- /dev/null
+++ b/security/landlock/setup.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Security framework setup
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_SETUP_H
+#define _SECURITY_LANDLOCK_SETUP_H
+
+#include <linux/lsm_hooks.h>
+
+extern bool landlock_initialized;
+
+extern struct lsm_blob_sizes landlock_blob_sizes;
+
+#endif /* _SECURITY_LANDLOCK_SETUP_H */
diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c
new file mode 100644
index 000000000000..32396962f04d
--- /dev/null
+++ b/security/landlock/syscalls.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - System call implementations and user space interfaces
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <asm/current.h>
+#include <linux/anon_inodes.h>
+#include <linux/build_bug.h>
+#include <linux/capability.h>
+#include <linux/compiler_types.h>
+#include <linux/dcache.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/limits.h>
+#include <linux/mount.h>
+#include <linux/path.h>
+#include <linux/sched.h>
+#include <linux/security.h>
+#include <linux/stddef.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/landlock.h>
+
+#include "cred.h"
+#include "fs.h"
+#include "limits.h"
+#include "ruleset.h"
+#include "setup.h"
+
+/**
+ * copy_min_struct_from_user - Safe future-proof argument copying
+ *
+ * Extend copy_struct_from_user() to check for consistent user buffer.
+ *
+ * @dst: Kernel space pointer or NULL.
+ * @ksize: Actual size of the data pointed to by @dst.
+ * @ksize_min: Minimal required size to be copied.
+ * @src: User space pointer or NULL.
+ * @usize: (Alleged) size of the data pointed to by @src.
+ */
+static __always_inline int copy_min_struct_from_user(void *const dst,
+ const size_t ksize, const size_t ksize_min,
+ const void __user *const src, const size_t usize)
+{
+ /* Checks buffer inconsistencies. */
+ BUILD_BUG_ON(!dst);
+ if (!src)
+ return -EFAULT;
+
+ /* Checks size ranges. */
+ BUILD_BUG_ON(ksize <= 0);
+ BUILD_BUG_ON(ksize < ksize_min);
+ if (usize < ksize_min)
+ return -EINVAL;
+ if (usize > PAGE_SIZE)
+ return -E2BIG;
+
+ /* Copies user buffer and fills with zeros. */
+ return copy_struct_from_user(dst, ksize, src, usize);
+}
+
+/*
+ * This function only contains arithmetic operations with constants, leading to
+ * BUILD_BUG_ON(). The related code is evaluated and checked at build time,
+ * but it is then ignored thanks to compiler optimizations.
+ */
+static void build_check_abi(void)
+{
+ struct landlock_ruleset_attr ruleset_attr;
+ struct landlock_path_beneath_attr path_beneath_attr;
+ size_t ruleset_size, path_beneath_size;
+
+ /*
+ * For each user space ABI structures, first checks that there is no
+ * hole in them, then checks that all architectures have the same
+ * struct size.
+ */
+ ruleset_size = sizeof(ruleset_attr.handled_access_fs);
+ BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size);
+ BUILD_BUG_ON(sizeof(ruleset_attr) != 8);
+
+ path_beneath_size = sizeof(path_beneath_attr.allowed_access);
+ path_beneath_size += sizeof(path_beneath_attr.parent_fd);
+ BUILD_BUG_ON(sizeof(path_beneath_attr) != path_beneath_size);
+ BUILD_BUG_ON(sizeof(path_beneath_attr) != 12);
+}
+
+/* Ruleset handling */
+
+static int fop_ruleset_release(struct inode *const inode,
+ struct file *const filp)
+{
+ struct landlock_ruleset *ruleset = filp->private_data;
+
+ landlock_put_ruleset(ruleset);
+ return 0;
+}
+
+static ssize_t fop_dummy_read(struct file *const filp, char __user *const buf,
+ const size_t size, loff_t *const ppos)
+{
+ /* Dummy handler to enable FMODE_CAN_READ. */
+ return -EINVAL;
+}
+
+static ssize_t fop_dummy_write(struct file *const filp,
+ const char __user *const buf, const size_t size,
+ loff_t *const ppos)
+{
+ /* Dummy handler to enable FMODE_CAN_WRITE. */
+ return -EINVAL;
+}
+
+/*
+ * A ruleset file descriptor enables to build a ruleset by adding (i.e.
+ * writing) rule after rule, without relying on the task's context. This
+ * reentrant design is also used in a read way to enforce the ruleset on the
+ * current task.
+ */
+static const struct file_operations ruleset_fops = {
+ .release = fop_ruleset_release,
+ .read = fop_dummy_read,
+ .write = fop_dummy_write,
+};
+
+#define LANDLOCK_ABI_VERSION 1
+
+/**
+ * sys_landlock_create_ruleset - Create a new ruleset
+ *
+ * @attr: Pointer to a &struct landlock_ruleset_attr identifying the scope of
+ * the new ruleset.
+ * @size: Size of the pointed &struct landlock_ruleset_attr (needed for
+ * backward and forward compatibility).
+ * @flags: Supported value: %LANDLOCK_CREATE_RULESET_VERSION.
+ *
+ * This system call enables to create a new Landlock ruleset, and returns the
+ * related file descriptor on success.
+ *
+ * If @flags is %LANDLOCK_CREATE_RULESET_VERSION and @attr is NULL and @size is
+ * 0, then the returned value is the highest supported Landlock ABI version
+ * (starting at 1).
+ *
+ * Possible returned errors are:
+ *
+ * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - EINVAL: unknown @flags, or unknown access, or too small @size;
+ * - E2BIG or EFAULT: @attr or @size inconsistencies;
+ * - ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ */
+SYSCALL_DEFINE3(landlock_create_ruleset,
+ const struct landlock_ruleset_attr __user *const, attr,
+ const size_t, size, const __u32, flags)
+{
+ struct landlock_ruleset_attr ruleset_attr;
+ struct landlock_ruleset *ruleset;
+ int err, ruleset_fd;
+
+ /* Build-time checks. */
+ build_check_abi();
+
+ if (!landlock_initialized)
+ return -EOPNOTSUPP;
+
+ if (flags) {
+ if ((flags == LANDLOCK_CREATE_RULESET_VERSION)
+ && !attr && !size)
+ return LANDLOCK_ABI_VERSION;
+ return -EINVAL;
+ }
+
+ /* Copies raw user space buffer. */
+ err = copy_min_struct_from_user(&ruleset_attr, sizeof(ruleset_attr),
+ offsetofend(typeof(ruleset_attr), handled_access_fs),
+ attr, size);
+ if (err)
+ return err;
+
+ /* Checks content (and 32-bits cast). */
+ if ((ruleset_attr.handled_access_fs | LANDLOCK_MASK_ACCESS_FS) !=
+ LANDLOCK_MASK_ACCESS_FS)
+ return -EINVAL;
+
+ /* Checks arguments and transforms to kernel struct. */
+ ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs);
+ if (IS_ERR(ruleset))
+ return PTR_ERR(ruleset);
+
+ /* Creates anonymous FD referring to the ruleset. */
+ ruleset_fd = anon_inode_getfd("landlock-ruleset", &ruleset_fops,
+ ruleset, O_RDWR | O_CLOEXEC);
+ if (ruleset_fd < 0)
+ landlock_put_ruleset(ruleset);
+ return ruleset_fd;
+}
+
+/*
+ * Returns an owned ruleset from a FD. It is thus needed to call
+ * landlock_put_ruleset() on the return value.
+ */
+static struct landlock_ruleset *get_ruleset_from_fd(const int fd,
+ const fmode_t mode)
+{
+ struct fd ruleset_f;
+ struct landlock_ruleset *ruleset;
+
+ ruleset_f = fdget(fd);
+ if (!ruleset_f.file)
+ return ERR_PTR(-EBADF);
+
+ /* Checks FD type and access right. */
+ if (ruleset_f.file->f_op != &ruleset_fops) {
+ ruleset = ERR_PTR(-EBADFD);
+ goto out_fdput;
+ }
+ if (!(ruleset_f.file->f_mode & mode)) {
+ ruleset = ERR_PTR(-EPERM);
+ goto out_fdput;
+ }
+ ruleset = ruleset_f.file->private_data;
+ if (WARN_ON_ONCE(ruleset->num_layers != 1)) {
+ ruleset = ERR_PTR(-EINVAL);
+ goto out_fdput;
+ }
+ landlock_get_ruleset(ruleset);
+
+out_fdput:
+ fdput(ruleset_f);
+ return ruleset;
+}
+
+/* Path handling */
+
+/*
+ * @path: Must call put_path(@path) after the call if it succeeded.
+ */
+static int get_path_from_fd(const s32 fd, struct path *const path)
+{
+ struct fd f;
+ int err = 0;
+
+ BUILD_BUG_ON(!__same_type(fd,
+ ((struct landlock_path_beneath_attr *)NULL)->parent_fd));
+
+ /* Handles O_PATH. */
+ f = fdget_raw(fd);
+ if (!f.file)
+ return -EBADF;
+ /*
+ * Forbids ruleset FDs, internal filesystems (e.g. nsfs), including
+ * pseudo filesystems that will never be mountable (e.g. sockfs,
+ * pipefs).
+ */
+ if ((f.file->f_op == &ruleset_fops) ||
+ (f.file->f_path.mnt->mnt_flags & MNT_INTERNAL) ||
+ (f.file->f_path.dentry->d_sb->s_flags & SB_NOUSER) ||
+ d_is_negative(f.file->f_path.dentry) ||
+ IS_PRIVATE(d_backing_inode(f.file->f_path.dentry))) {
+ err = -EBADFD;
+ goto out_fdput;
+ }
+ *path = f.file->f_path;
+ path_get(path);
+
+out_fdput:
+ fdput(f);
+ return err;
+}
+
+/**
+ * sys_landlock_add_rule - Add a new rule to a ruleset
+ *
+ * @ruleset_fd: File descriptor tied to the ruleset that should be extended
+ * with the new rule.
+ * @rule_type: Identify the structure type pointed to by @rule_attr (only
+ * LANDLOCK_RULE_PATH_BENEATH for now).
+ * @rule_attr: Pointer to a rule (only of type &struct
+ * landlock_path_beneath_attr for now).
+ * @flags: Must be 0.
+ *
+ * This system call enables to define a new rule and add it to an existing
+ * ruleset.
+ *
+ * Possible returned errors are:
+ *
+ * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - EINVAL: @flags is not 0, or inconsistent access in the rule (i.e.
+ * &landlock_path_beneath_attr.allowed_access is not a subset of the rule's
+ * accesses);
+ * - ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access);
+ * - EBADF: @ruleset_fd is not a file descriptor for the current thread, or a
+ * member of @rule_attr is not a file descriptor as expected;
+ * - EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of
+ * @rule_attr is not the expected file descriptor type (e.g. file open
+ * without O_PATH);
+ * - EPERM: @ruleset_fd has no write access to the underlying ruleset;
+ * - EFAULT: @rule_attr inconsistency.
+ */
+SYSCALL_DEFINE4(landlock_add_rule,
+ const int, ruleset_fd, const enum landlock_rule_type, rule_type,
+ const void __user *const, rule_attr, const __u32, flags)
+{
+ struct landlock_path_beneath_attr path_beneath_attr;
+ struct path path;
+ struct landlock_ruleset *ruleset;
+ int res, err;
+
+ if (!landlock_initialized)
+ return -EOPNOTSUPP;
+
+ /* No flag for now. */
+ if (flags)
+ return -EINVAL;
+
+ if (rule_type != LANDLOCK_RULE_PATH_BENEATH)
+ return -EINVAL;
+
+ /* Copies raw user space buffer, only one type for now. */
+ res = copy_from_user(&path_beneath_attr, rule_attr,
+ sizeof(path_beneath_attr));
+ if (res)
+ return -EFAULT;
+
+ /* Gets and checks the ruleset. */
+ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_WRITE);
+ if (IS_ERR(ruleset))
+ return PTR_ERR(ruleset);
+
+ /*
+ * Informs about useless rule: empty allowed_access (i.e. deny rules)
+ * are ignored in path walks.
+ */
+ if (!path_beneath_attr.allowed_access) {
+ err = -ENOMSG;
+ goto out_put_ruleset;
+ }
+ /*
+ * Checks that allowed_access matches the @ruleset constraints
+ * (ruleset->fs_access_masks[0] is automatically upgraded to 64-bits).
+ */
+ if ((path_beneath_attr.allowed_access | ruleset->fs_access_masks[0]) !=
+ ruleset->fs_access_masks[0]) {
+ err = -EINVAL;
+ goto out_put_ruleset;
+ }
+
+ /* Gets and checks the new rule. */
+ err = get_path_from_fd(path_beneath_attr.parent_fd, &path);
+ if (err)
+ goto out_put_ruleset;
+
+ /* Imports the new rule. */
+ err = landlock_append_fs_rule(ruleset, &path,
+ path_beneath_attr.allowed_access);
+ path_put(&path);
+
+out_put_ruleset:
+ landlock_put_ruleset(ruleset);
+ return err;
+}
+
+/* Enforcement */
+
+/**
+ * sys_landlock_restrict_self - Enforce a ruleset on the calling thread
+ *
+ * @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
+ * @flags: Must be 0.
+ *
+ * This system call enables to enforce a Landlock ruleset on the current
+ * thread. Enforcing a ruleset requires that the task has CAP_SYS_ADMIN in its
+ * namespace or is running with no_new_privs. This avoids scenarios where
+ * unprivileged tasks can affect the behavior of privileged children.
+ *
+ * Possible returned errors are:
+ *
+ * - EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - EINVAL: @flags is not 0.
+ * - EBADF: @ruleset_fd is not a file descriptor for the current thread;
+ * - EBADFD: @ruleset_fd is not a ruleset file descriptor;
+ * - EPERM: @ruleset_fd has no read access to the underlying ruleset, or the
+ * current thread is not running with no_new_privs, or it doesn't have
+ * CAP_SYS_ADMIN in its namespace.
+ * - E2BIG: The maximum number of stacked rulesets is reached for the current
+ * thread.
+ */
+SYSCALL_DEFINE2(landlock_restrict_self,
+ const int, ruleset_fd, const __u32, flags)
+{
+ struct landlock_ruleset *new_dom, *ruleset;
+ struct cred *new_cred;
+ struct landlock_cred_security *new_llcred;
+ int err;
+
+ if (!landlock_initialized)
+ return -EOPNOTSUPP;
+
+ /* No flag for now. */
+ if (flags)
+ return -EINVAL;
+
+ /*
+ * Similar checks as for seccomp(2), except that an -EPERM may be
+ * returned.
+ */
+ if (!task_no_new_privs(current) &&
+ !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* Gets and checks the ruleset. */
+ ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ);
+ if (IS_ERR(ruleset))
+ return PTR_ERR(ruleset);
+
+ /* Prepares new credentials. */
+ new_cred = prepare_creds();
+ if (!new_cred) {
+ err = -ENOMEM;
+ goto out_put_ruleset;
+ }
+ new_llcred = landlock_cred(new_cred);
+
+ /*
+ * There is no possible race condition while copying and manipulating
+ * the current credentials because they are dedicated per thread.
+ */
+ new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset);
+ if (IS_ERR(new_dom)) {
+ err = PTR_ERR(new_dom);
+ goto out_put_creds;
+ }
+
+ /* Replaces the old (prepared) domain. */
+ landlock_put_ruleset(new_llcred->domain);
+ new_llcred->domain = new_dom;
+
+ landlock_put_ruleset(ruleset);
+ return commit_creds(new_cred);
+
+out_put_creds:
+ abort_creds(new_cred);
+
+out_put_ruleset:
+ landlock_put_ruleset(ruleset);
+ return err;
+}
diff --git a/security/security.c b/security/security.c
index 94383f83ba42..b38155b2de83 100644
--- a/security/security.c
+++ b/security/security.c
@@ -203,6 +203,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode);
lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc);
lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg);
+ lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock);
lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task);
}
@@ -333,12 +334,13 @@ static void __init ordered_lsm_init(void)
for (lsm = ordered_lsms; *lsm; lsm++)
prepare_lsm(*lsm);
- init_debug("cred blob size = %d\n", blob_sizes.lbs_cred);
- init_debug("file blob size = %d\n", blob_sizes.lbs_file);
- init_debug("inode blob size = %d\n", blob_sizes.lbs_inode);
- init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc);
- init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg);
- init_debug("task blob size = %d\n", blob_sizes.lbs_task);
+ init_debug("cred blob size = %d\n", blob_sizes.lbs_cred);
+ init_debug("file blob size = %d\n", blob_sizes.lbs_file);
+ init_debug("inode blob size = %d\n", blob_sizes.lbs_inode);
+ init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc);
+ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg);
+ init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock);
+ init_debug("task blob size = %d\n", blob_sizes.lbs_task);
/*
* Create any kmem_caches needed for blobs
@@ -670,6 +672,27 @@ static void __init lsm_early_task(struct task_struct *task)
panic("%s: Early task alloc failed.\n", __func__);
}
+/**
+ * lsm_superblock_alloc - allocate a composite superblock blob
+ * @sb: the superblock that needs a blob
+ *
+ * Allocate the superblock blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_superblock_alloc(struct super_block *sb)
+{
+ if (blob_sizes.lbs_superblock == 0) {
+ sb->s_security = NULL;
+ return 0;
+ }
+
+ sb->s_security = kzalloc(blob_sizes.lbs_superblock, GFP_KERNEL);
+ if (sb->s_security == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
/*
* The default value of the LSM hook is defined in linux/lsm_hook_defs.h and
* can be accessed with:
@@ -867,12 +890,26 @@ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *
int security_sb_alloc(struct super_block *sb)
{
- return call_int_hook(sb_alloc_security, 0, sb);
+ int rc = lsm_superblock_alloc(sb);
+
+ if (unlikely(rc))
+ return rc;
+ rc = call_int_hook(sb_alloc_security, 0, sb);
+ if (unlikely(rc))
+ security_sb_free(sb);
+ return rc;
+}
+
+void security_sb_delete(struct super_block *sb)
+{
+ call_void_hook(sb_delete, sb);
}
void security_sb_free(struct super_block *sb)
{
call_void_hook(sb_free_security, sb);
+ kfree(sb->s_security);
+ sb->s_security = NULL;
}
void security_free_mnt_opts(void **mnt_opts)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 92f909a2e8f7..eaea837d89d1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -358,7 +358,7 @@ static void inode_free_security(struct inode *inode)
if (!isec)
return;
- sbsec = inode->i_sb->s_security;
+ sbsec = selinux_superblock(inode->i_sb);
/*
* As not all inode security structures are in a list, we check for
* empty list outside of the lock to make sure that we won't waste
@@ -376,13 +376,6 @@ static void inode_free_security(struct inode *inode)
}
}
-static void superblock_free_security(struct super_block *sb)
-{
- struct superblock_security_struct *sbsec = sb->s_security;
- sb->s_security = NULL;
- kfree(sbsec);
-}
-
struct selinux_mnt_opts {
const char *fscontext, *context, *rootcontext, *defcontext;
};
@@ -494,7 +487,7 @@ static int selinux_is_genfs_special_handling(struct super_block *sb)
static int selinux_is_sblabel_mnt(struct super_block *sb)
{
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
/*
* IMPORTANT: Double-check logic in this function when adding a new
@@ -571,7 +564,7 @@ fallback:
static int sb_finish_set_opts(struct super_block *sb)
{
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
struct dentry *root = sb->s_root;
struct inode *root_inode = d_backing_inode(root);
int rc = 0;
@@ -662,7 +655,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
unsigned long *set_kern_flags)
{
const struct cred *cred = current_cred();
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
struct dentry *root = sb->s_root;
struct selinux_mnt_opts *opts = mnt_opts;
struct inode_security_struct *root_isec;
@@ -900,8 +893,8 @@ out_double_mount:
static int selinux_cmp_sb_context(const struct super_block *oldsb,
const struct super_block *newsb)
{
- struct superblock_security_struct *old = oldsb->s_security;
- struct superblock_security_struct *new = newsb->s_security;
+ struct superblock_security_struct *old = selinux_superblock(oldsb);
+ struct superblock_security_struct *new = selinux_superblock(newsb);
char oldflags = old->flags & SE_MNTMASK;
char newflags = new->flags & SE_MNTMASK;
@@ -933,8 +926,9 @@ static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
unsigned long *set_kern_flags)
{
int rc = 0;
- const struct superblock_security_struct *oldsbsec = oldsb->s_security;
- struct superblock_security_struct *newsbsec = newsb->s_security;
+ const struct superblock_security_struct *oldsbsec =
+ selinux_superblock(oldsb);
+ struct superblock_security_struct *newsbsec = selinux_superblock(newsb);
int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT);
int set_context = (oldsbsec->flags & CONTEXT_MNT);
@@ -1113,7 +1107,7 @@ static int show_sid(struct seq_file *m, u32 sid)
static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb)
{
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
int rc;
if (!(sbsec->flags & SE_SBINITIALIZED))
@@ -1464,7 +1458,7 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
if (isec->sclass == SECCLASS_FILE)
isec->sclass = inode_mode_to_security_class(inode->i_mode);
- sbsec = inode->i_sb->s_security;
+ sbsec = selinux_superblock(inode->i_sb);
if (!(sbsec->flags & SE_SBINITIALIZED)) {
/* Defer initialization until selinux_complete_init,
after the initial policy is loaded and the security
@@ -1815,7 +1809,8 @@ selinux_determine_inode_label(const struct task_security_struct *tsec,
const struct qstr *name, u16 tclass,
u32 *_new_isid)
{
- const struct superblock_security_struct *sbsec = dir->i_sb->s_security;
+ const struct superblock_security_struct *sbsec =
+ selinux_superblock(dir->i_sb);
if ((sbsec->flags & SE_SBINITIALIZED) &&
(sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) {
@@ -1846,7 +1841,7 @@ static int may_create(struct inode *dir,
int rc;
dsec = inode_security(dir);
- sbsec = dir->i_sb->s_security;
+ sbsec = selinux_superblock(dir->i_sb);
sid = tsec->sid;
@@ -1995,7 +1990,7 @@ static int superblock_has_perm(const struct cred *cred,
struct superblock_security_struct *sbsec;
u32 sid = cred_sid(cred);
- sbsec = sb->s_security;
+ sbsec = selinux_superblock(sb);
return avc_has_perm(&selinux_state,
sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad);
}
@@ -2617,11 +2612,7 @@ static void selinux_bprm_committed_creds(struct linux_binprm *bprm)
static int selinux_sb_alloc_security(struct super_block *sb)
{
- struct superblock_security_struct *sbsec;
-
- sbsec = kzalloc(sizeof(struct superblock_security_struct), GFP_KERNEL);
- if (!sbsec)
- return -ENOMEM;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
mutex_init(&sbsec->lock);
INIT_LIST_HEAD(&sbsec->isec_head);
@@ -2629,16 +2620,10 @@ static int selinux_sb_alloc_security(struct super_block *sb)
sbsec->sid = SECINITSID_UNLABELED;
sbsec->def_sid = SECINITSID_FILE;
sbsec->mntpoint_sid = SECINITSID_UNLABELED;
- sb->s_security = sbsec;
return 0;
}
-static void selinux_sb_free_security(struct super_block *sb)
-{
- superblock_free_security(sb);
-}
-
static inline int opt_len(const char *s)
{
bool open_quote = false;
@@ -2772,7 +2757,7 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts)
static int selinux_sb_remount(struct super_block *sb, void *mnt_opts)
{
struct selinux_mnt_opts *opts = mnt_opts;
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
u32 sid;
int rc;
@@ -3010,7 +2995,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
int rc;
char *context;
- sbsec = dir->i_sb->s_security;
+ sbsec = selinux_superblock(dir->i_sb);
newsid = tsec->create_sid;
@@ -3312,7 +3297,7 @@ static int selinux_inode_setxattr(struct user_namespace *mnt_userns,
if (!selinux_initialized(&selinux_state))
return (inode_owner_or_capable(mnt_userns, inode) ? 0 : -EPERM);
- sbsec = inode->i_sb->s_security;
+ sbsec = selinux_superblock(inode->i_sb);
if (!(sbsec->flags & SBLABEL_MNT))
return -EOPNOTSUPP;
@@ -3557,13 +3542,14 @@ static int selinux_inode_setsecurity(struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
struct inode_security_struct *isec = inode_security_novalidate(inode);
- struct superblock_security_struct *sbsec = inode->i_sb->s_security;
+ struct superblock_security_struct *sbsec;
u32 newsid;
int rc;
if (strcmp(name, XATTR_SELINUX_SUFFIX))
return -EOPNOTSUPP;
+ sbsec = selinux_superblock(inode->i_sb);
if (!(sbsec->flags & SBLABEL_MNT))
return -EOPNOTSUPP;
@@ -7065,6 +7051,7 @@ struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = {
.lbs_inode = sizeof(struct inode_security_struct),
.lbs_ipc = sizeof(struct ipc_security_struct),
.lbs_msg_msg = sizeof(struct msg_security_struct),
+ .lbs_superblock = sizeof(struct superblock_security_struct),
};
#ifdef CONFIG_PERF_EVENTS
@@ -7165,7 +7152,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds),
LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds),
- LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security),
LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts),
LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat),
LSM_HOOK_INIT(sb_remount, selinux_sb_remount),
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index ca4d7ab6a835..2953132408bf 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -188,4 +188,10 @@ static inline u32 current_sid(void)
return tsec->sid;
}
+static inline struct superblock_security_struct *selinux_superblock(
+ const struct super_block *superblock)
+{
+ return superblock->s_security + selinux_blob_sizes.lbs_superblock;
+}
+
#endif /* _SELINUX_OBJSEC_H_ */
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index f0ba82611343..0a5ce001609b 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -47,6 +47,7 @@
#include <linux/sched.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
+#include <linux/lsm_hooks.h>
#include <net/netlabel.h>
#include "flask.h"
@@ -2955,7 +2956,7 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb)
struct sidtab *sidtab;
int rc;
struct ocontext *c;
- struct superblock_security_struct *sbsec = sb->s_security;
+ struct superblock_security_struct *sbsec = selinux_superblock(sb);
const char *fstype = sb->s_type->name;
if (!selinux_initialized(state)) {
diff --git a/security/smack/smack.h b/security/smack/smack.h
index 08f9cb80655c..c3cfbdf4944a 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -357,6 +357,12 @@ static inline struct smack_known **smack_ipc(const struct kern_ipc_perm *ipc)
return ipc->security + smack_blob_sizes.lbs_ipc;
}
+static inline struct superblock_smack *smack_superblock(
+ const struct super_block *superblock)
+{
+ return superblock->s_security + smack_blob_sizes.lbs_superblock;
+}
+
/*
* Is the directory transmuting?
*/
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index cd14bec4ad80..223a6da0e6dc 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -535,12 +535,7 @@ static int smack_syslog(int typefrom_file)
*/
static int smack_sb_alloc_security(struct super_block *sb)
{
- struct superblock_smack *sbsp;
-
- sbsp = kzalloc(sizeof(struct superblock_smack), GFP_KERNEL);
-
- if (sbsp == NULL)
- return -ENOMEM;
+ struct superblock_smack *sbsp = smack_superblock(sb);
sbsp->smk_root = &smack_known_floor;
sbsp->smk_default = &smack_known_floor;
@@ -549,22 +544,10 @@ static int smack_sb_alloc_security(struct super_block *sb)
/*
* SMK_SB_INITIALIZED will be zero from kzalloc.
*/
- sb->s_security = sbsp;
return 0;
}
-/**
- * smack_sb_free_security - free a superblock blob
- * @sb: the superblock getting the blob
- *
- */
-static void smack_sb_free_security(struct super_block *sb)
-{
- kfree(sb->s_security);
- sb->s_security = NULL;
-}
-
struct smack_mnt_opts {
const char *fsdefault, *fsfloor, *fshat, *fsroot, *fstransmute;
};
@@ -772,7 +755,7 @@ static int smack_set_mnt_opts(struct super_block *sb,
{
struct dentry *root = sb->s_root;
struct inode *inode = d_backing_inode(root);
- struct superblock_smack *sp = sb->s_security;
+ struct superblock_smack *sp = smack_superblock(sb);
struct inode_smack *isp;
struct smack_known *skp;
struct smack_mnt_opts *opts = mnt_opts;
@@ -871,7 +854,7 @@ static int smack_set_mnt_opts(struct super_block *sb,
*/
static int smack_sb_statfs(struct dentry *dentry)
{
- struct superblock_smack *sbp = dentry->d_sb->s_security;
+ struct superblock_smack *sbp = smack_superblock(dentry->d_sb);
int rc;
struct smk_audit_info ad;
@@ -905,7 +888,7 @@ static int smack_bprm_creds_for_exec(struct linux_binprm *bprm)
if (isp->smk_task == NULL || isp->smk_task == bsp->smk_task)
return 0;
- sbsp = inode->i_sb->s_security;
+ sbsp = smack_superblock(inode->i_sb);
if ((sbsp->smk_flags & SMK_SB_UNTRUSTED) &&
isp->smk_task != sbsp->smk_root)
return 0;
@@ -1157,7 +1140,7 @@ static int smack_inode_rename(struct inode *old_inode,
*/
static int smack_inode_permission(struct inode *inode, int mask)
{
- struct superblock_smack *sbsp = inode->i_sb->s_security;
+ struct superblock_smack *sbsp = smack_superblock(inode->i_sb);
struct smk_audit_info ad;
int no_block = mask & MAY_NOT_BLOCK;
int rc;
@@ -1400,7 +1383,7 @@ static int smack_inode_removexattr(struct user_namespace *mnt_userns,
*/
if (strcmp(name, XATTR_NAME_SMACK) == 0) {
struct super_block *sbp = dentry->d_sb;
- struct superblock_smack *sbsp = sbp->s_security;
+ struct superblock_smack *sbsp = smack_superblock(sbp);
isp->smk_inode = sbsp->smk_default;
} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0)
@@ -1670,7 +1653,7 @@ static int smack_mmap_file(struct file *file,
isp = smack_inode(file_inode(file));
if (isp->smk_mmap == NULL)
return 0;
- sbsp = file_inode(file)->i_sb->s_security;
+ sbsp = smack_superblock(file_inode(file)->i_sb);
if (sbsp->smk_flags & SMK_SB_UNTRUSTED &&
isp->smk_mmap != sbsp->smk_root)
return -EACCES;
@@ -3299,7 +3282,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
return;
sbp = inode->i_sb;
- sbsp = sbp->s_security;
+ sbsp = smack_superblock(sbp);
/*
* We're going to use the superblock default label
* if there's no label on the file.
@@ -4714,6 +4697,7 @@ struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = {
.lbs_inode = sizeof(struct inode_smack),
.lbs_ipc = sizeof(struct smack_known *),
.lbs_msg_msg = sizeof(struct smack_known *),
+ .lbs_superblock = sizeof(struct superblock_smack),
};
static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
@@ -4725,7 +4709,6 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(fs_context_parse_param, smack_fs_context_parse_param),
LSM_HOOK_INIT(sb_alloc_security, smack_sb_alloc_security),
- LSM_HOOK_INIT(sb_free_security, smack_sb_free_security),
LSM_HOOK_INIT(sb_free_mnt_opts, smack_free_mnt_opts),
LSM_HOOK_INIT(sb_eat_lsm_opts, smack_sb_eat_lsm_opts),
LSM_HOOK_INIT(sb_statfs, smack_sb_statfs),
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 6c575cf34a71..bc3299a20338 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -25,6 +25,7 @@ TARGETS += ir
TARGETS += kcmp
TARGETS += kexec
TARGETS += kvm
+TARGETS += landlock
TARGETS += lib
TARGETS += livepatch
TARGETS += lkdtm
diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore
new file mode 100644
index 000000000000..470203a7cd73
--- /dev/null
+++ b/tools/testing/selftests/landlock/.gitignore
@@ -0,0 +1,2 @@
+/*_test
+/true
diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
new file mode 100644
index 000000000000..a99596ca9882
--- /dev/null
+++ b/tools/testing/selftests/landlock/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CFLAGS += -Wall -O2
+
+src_test := $(wildcard *_test.c)
+
+TEST_GEN_PROGS := $(src_test:.c=)
+
+TEST_GEN_PROGS_EXTENDED := true
+
+KSFT_KHDR_INSTALL := 1
+OVERRIDE_TARGETS := 1
+include ../lib.mk
+
+khdr_dir = $(top_srcdir)/usr/include
+
+$(khdr_dir)/linux/landlock.h: khdr
+ @:
+
+$(OUTPUT)/true: true.c
+ $(LINK.c) $< $(LDLIBS) -o $@ -static
+
+$(OUTPUT)/%_test: %_test.c $(khdr_dir)/linux/landlock.h ../kselftest_harness.h common.h
+ $(LINK.c) $< $(LDLIBS) -o $@ -lcap -I$(khdr_dir)
diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c
new file mode 100644
index 000000000000..ca40abe9daa8
--- /dev/null
+++ b/tools/testing/selftests/landlock/base_test.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Landlock tests - Common user space base
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/landlock.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include "common.h"
+
+#ifndef O_PATH
+#define O_PATH 010000000
+#endif
+
+TEST(inconsistent_attr) {
+ const long page_size = sysconf(_SC_PAGESIZE);
+ char *const buf = malloc(page_size + 1);
+ struct landlock_ruleset_attr *const ruleset_attr = (void *)buf;
+
+ ASSERT_NE(NULL, buf);
+
+ /* Checks copy_from_user(). */
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 0, 0));
+ /* The size if less than sizeof(struct landlock_attr_enforce). */
+ ASSERT_EQ(EINVAL, errno);
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 1, 0));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, 1, 0));
+ /* The size if less than sizeof(struct landlock_attr_enforce). */
+ ASSERT_EQ(EFAULT, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL,
+ sizeof(struct landlock_ruleset_attr), 0));
+ ASSERT_EQ(EFAULT, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size + 1, 0));
+ ASSERT_EQ(E2BIG, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr,
+ sizeof(struct landlock_ruleset_attr), 0));
+ ASSERT_EQ(ENOMSG, errno);
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size, 0));
+ ASSERT_EQ(ENOMSG, errno);
+
+ /* Checks non-zero value. */
+ buf[page_size - 2] = '.';
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size, 0));
+ ASSERT_EQ(E2BIG, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size + 1, 0));
+ ASSERT_EQ(E2BIG, errno);
+
+ free(buf);
+}
+
+TEST(abi_version) {
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
+ };
+ ASSERT_EQ(1, landlock_create_ruleset(NULL, 0,
+ LANDLOCK_CREATE_RULESET_VERSION));
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0,
+ LANDLOCK_CREATE_RULESET_VERSION));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr),
+ LANDLOCK_CREATE_RULESET_VERSION));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr),
+ LANDLOCK_CREATE_RULESET_VERSION));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0,
+ LANDLOCK_CREATE_RULESET_VERSION | 1 << 31));
+ ASSERT_EQ(EINVAL, errno);
+}
+
+TEST(inval_create_ruleset_flags) {
+ const int last_flag = LANDLOCK_CREATE_RULESET_VERSION;
+ const int invalid_flag = last_flag << 1;
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
+ };
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0, invalid_flag));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, invalid_flag));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr),
+ invalid_flag));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), invalid_flag));
+ ASSERT_EQ(EINVAL, errno);
+}
+
+TEST(empty_path_beneath_attr) {
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE,
+ };
+ const int ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ /* Similar to struct landlock_path_beneath_attr.parent_fd = 0 */
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ NULL, 0));
+ ASSERT_EQ(EFAULT, errno);
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST(inval_fd_enforce) {
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+
+ ASSERT_EQ(-1, landlock_restrict_self(-1, 0));
+ ASSERT_EQ(EBADF, errno);
+}
+
+TEST(unpriv_enforce_without_no_new_privs) {
+ int err;
+
+ drop_caps(_metadata);
+ err = landlock_restrict_self(-1, 0);
+ ASSERT_EQ(EPERM, errno);
+ ASSERT_EQ(err, -1);
+}
+
+TEST(ruleset_fd_io)
+{
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
+ };
+ int ruleset_fd;
+ char buf;
+
+ drop_caps(_metadata);
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(-1, write(ruleset_fd, ".", 1));
+ ASSERT_EQ(EINVAL, errno);
+ ASSERT_EQ(-1, read(ruleset_fd, &buf, 1));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+/* Tests enforcement of a ruleset FD transferred through a UNIX socket. */
+TEST(ruleset_fd_transfer)
+{
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR,
+ };
+ struct landlock_path_beneath_attr path_beneath_attr = {
+ .allowed_access = LANDLOCK_ACCESS_FS_READ_DIR,
+ };
+ int ruleset_fd_tx, dir_fd;
+ union {
+ /* Aligned ancillary data buffer. */
+ char buf[CMSG_SPACE(sizeof(ruleset_fd_tx))];
+ struct cmsghdr _align;
+ } cmsg_tx = {};
+ char data_tx = '.';
+ struct iovec io = {
+ .iov_base = &data_tx,
+ .iov_len = sizeof(data_tx),
+ };
+ struct msghdr msg = {
+ .msg_iov = &io,
+ .msg_iovlen = 1,
+ .msg_control = &cmsg_tx.buf,
+ .msg_controllen = sizeof(cmsg_tx.buf),
+ };
+ struct cmsghdr *cmsg;
+ int socket_fds[2];
+ pid_t child;
+ int status;
+
+ drop_caps(_metadata);
+
+ /* Creates a test ruleset with a simple rule. */
+ ruleset_fd_tx = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd_tx);
+ path_beneath_attr.parent_fd = open("/tmp", O_PATH | O_NOFOLLOW |
+ O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath_attr.parent_fd);
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd_tx, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_attr, 0));
+ ASSERT_EQ(0, close(path_beneath_attr.parent_fd));
+
+ cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(NULL, cmsg);
+ cmsg->cmsg_len = CMSG_LEN(sizeof(ruleset_fd_tx));
+ cmsg->cmsg_level = SOL_SOCKET;
+ cmsg->cmsg_type = SCM_RIGHTS;
+ memcpy(CMSG_DATA(cmsg), &ruleset_fd_tx, sizeof(ruleset_fd_tx));
+
+ /* Sends the ruleset FD over a socketpair and then close it. */
+ ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, socket_fds));
+ ASSERT_EQ(sizeof(data_tx), sendmsg(socket_fds[0], &msg, 0));
+ ASSERT_EQ(0, close(socket_fds[0]));
+ ASSERT_EQ(0, close(ruleset_fd_tx));
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ int ruleset_fd_rx;
+
+ *(char *)msg.msg_iov->iov_base = '\0';
+ ASSERT_EQ(sizeof(data_tx), recvmsg(socket_fds[1], &msg, MSG_CMSG_CLOEXEC));
+ ASSERT_EQ('.', *(char *)msg.msg_iov->iov_base);
+ ASSERT_EQ(0, close(socket_fds[1]));
+ cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(ruleset_fd_tx)));
+ memcpy(&ruleset_fd_rx, CMSG_DATA(cmsg), sizeof(ruleset_fd_tx));
+
+ /* Enforces the received ruleset on the child. */
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd_rx, 0));
+ ASSERT_EQ(0, close(ruleset_fd_rx));
+
+ /* Checks that the ruleset enforcement. */
+ ASSERT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
+ ASSERT_EQ(EACCES, errno);
+ dir_fd = open("/tmp", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, dir_fd);
+ ASSERT_EQ(0, close(dir_fd));
+ _exit(_metadata->passed ? EXIT_SUCCESS : EXIT_FAILURE);
+ return;
+ }
+
+ ASSERT_EQ(0, close(socket_fds[1]));
+
+ /* Checks that the parent is unrestricted. */
+ dir_fd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, dir_fd);
+ ASSERT_EQ(0, close(dir_fd));
+ dir_fd = open("/tmp", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, dir_fd);
+ ASSERT_EQ(0, close(dir_fd));
+
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ ASSERT_EQ(1, WIFEXITED(status));
+ ASSERT_EQ(EXIT_SUCCESS, WEXITSTATUS(status));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
new file mode 100644
index 000000000000..20e2a9286d71
--- /dev/null
+++ b/tools/testing/selftests/landlock/common.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Landlock test helpers
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ * Copyright © 2021 Microsoft Corporation
+ */
+
+#include <errno.h>
+#include <linux/landlock.h>
+#include <sys/capability.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+/*
+ * TEST_F_FORK() is useful when a test drop privileges but the corresponding
+ * FIXTURE_TEARDOWN() requires them (e.g. to remove files from a directory
+ * where write actions are denied). For convenience, FIXTURE_TEARDOWN() is
+ * also called when the test failed, but not when FIXTURE_SETUP() failed. For
+ * this to be possible, we must not call abort() but instead exit smoothly
+ * (hence the step print).
+ */
+#define TEST_F_FORK(fixture_name, test_name) \
+ static void fixture_name##_##test_name##_child( \
+ struct __test_metadata *_metadata, \
+ FIXTURE_DATA(fixture_name) *self, \
+ const FIXTURE_VARIANT(fixture_name) *variant); \
+ TEST_F(fixture_name, test_name) \
+ { \
+ int status; \
+ const pid_t child = fork(); \
+ if (child < 0) \
+ abort(); \
+ if (child == 0) { \
+ _metadata->no_print = 1; \
+ fixture_name##_##test_name##_child(_metadata, self, variant); \
+ if (_metadata->skip) \
+ _exit(255); \
+ if (_metadata->passed) \
+ _exit(0); \
+ _exit(_metadata->step); \
+ } \
+ if (child != waitpid(child, &status, 0)) \
+ abort(); \
+ if (WIFSIGNALED(status) || !WIFEXITED(status)) { \
+ _metadata->passed = 0; \
+ _metadata->step = 1; \
+ return; \
+ } \
+ switch (WEXITSTATUS(status)) { \
+ case 0: \
+ _metadata->passed = 1; \
+ break; \
+ case 255: \
+ _metadata->passed = 1; \
+ _metadata->skip = 1; \
+ break; \
+ default: \
+ _metadata->passed = 0; \
+ _metadata->step = WEXITSTATUS(status); \
+ break; \
+ } \
+ } \
+ static void fixture_name##_##test_name##_child( \
+ struct __test_metadata __attribute__((unused)) *_metadata, \
+ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
+ const FIXTURE_VARIANT(fixture_name) \
+ __attribute__((unused)) *variant)
+
+#ifndef landlock_create_ruleset
+static inline int landlock_create_ruleset(
+ const struct landlock_ruleset_attr *const attr,
+ const size_t size, const __u32 flags)
+{
+ return syscall(__NR_landlock_create_ruleset, attr, size, flags);
+}
+#endif
+
+#ifndef landlock_add_rule
+static inline int landlock_add_rule(const int ruleset_fd,
+ const enum landlock_rule_type rule_type,
+ const void *const rule_attr, const __u32 flags)
+{
+ return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type,
+ rule_attr, flags);
+}
+#endif
+
+#ifndef landlock_restrict_self
+static inline int landlock_restrict_self(const int ruleset_fd,
+ const __u32 flags)
+{
+ return syscall(__NR_landlock_restrict_self, ruleset_fd, flags);
+}
+#endif
+
+static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
+{
+ cap_t cap_p;
+ /* Only these three capabilities are useful for the tests. */
+ const cap_value_t caps[] = {
+ CAP_DAC_OVERRIDE,
+ CAP_MKNOD,
+ CAP_SYS_ADMIN,
+ CAP_SYS_CHROOT,
+ };
+
+ cap_p = cap_get_proc();
+ EXPECT_NE(NULL, cap_p) {
+ TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
+ }
+ EXPECT_NE(-1, cap_clear(cap_p)) {
+ TH_LOG("Failed to cap_clear: %s", strerror(errno));
+ }
+ if (!drop_all) {
+ EXPECT_NE(-1, cap_set_flag(cap_p, CAP_PERMITTED,
+ ARRAY_SIZE(caps), caps, CAP_SET)) {
+ TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
+ }
+ }
+ EXPECT_NE(-1, cap_set_proc(cap_p)) {
+ TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
+ }
+ EXPECT_NE(-1, cap_free(cap_p)) {
+ TH_LOG("Failed to cap_free: %s", strerror(errno));
+ }
+}
+
+/* We cannot put such helpers in a library because of kselftest_harness.h . */
+__attribute__((__unused__))
+static void disable_caps(struct __test_metadata *const _metadata)
+{
+ _init_caps(_metadata, false);
+}
+
+__attribute__((__unused__))
+static void drop_caps(struct __test_metadata *const _metadata)
+{
+ _init_caps(_metadata, true);
+}
+
+static void _effective_cap(struct __test_metadata *const _metadata,
+ const cap_value_t caps, const cap_flag_value_t value)
+{
+ cap_t cap_p;
+
+ cap_p = cap_get_proc();
+ EXPECT_NE(NULL, cap_p) {
+ TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
+ }
+ EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) {
+ TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
+ }
+ EXPECT_NE(-1, cap_set_proc(cap_p)) {
+ TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
+ }
+ EXPECT_NE(-1, cap_free(cap_p)) {
+ TH_LOG("Failed to cap_free: %s", strerror(errno));
+ }
+}
+
+__attribute__((__unused__))
+static void set_cap(struct __test_metadata *const _metadata,
+ const cap_value_t caps)
+{
+ _effective_cap(_metadata, caps, CAP_SET);
+}
+
+__attribute__((__unused__))
+static void clear_cap(struct __test_metadata *const _metadata,
+ const cap_value_t caps)
+{
+ _effective_cap(_metadata, caps, CAP_CLEAR);
+}
diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
new file mode 100644
index 000000000000..0f0a65287bac
--- /dev/null
+++ b/tools/testing/selftests/landlock/config
@@ -0,0 +1,7 @@
+CONFIG_OVERLAY_FS=y
+CONFIG_SECURITY_LANDLOCK=y
+CONFIG_SECURITY_PATH=y
+CONFIG_SECURITY=y
+CONFIG_SHMEM=y
+CONFIG_TMPFS_XATTR=y
+CONFIG_TMPFS=y
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
new file mode 100644
index 000000000000..10c9a1e4ebd9
--- /dev/null
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -0,0 +1,2791 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Landlock tests - Filesystem
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2020 ANSSI
+ * Copyright © 2020-2021 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <linux/landlock.h>
+#include <sched.h>
+#include <string.h>
+#include <sys/capability.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/sendfile.h>
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include <unistd.h>
+
+#include "common.h"
+
+#define TMP_DIR "tmp"
+#define BINARY_PATH "./true"
+
+/* Paths (sibling number and depth) */
+static const char dir_s1d1[] = TMP_DIR "/s1d1";
+static const char file1_s1d1[] = TMP_DIR "/s1d1/f1";
+static const char file2_s1d1[] = TMP_DIR "/s1d1/f2";
+static const char dir_s1d2[] = TMP_DIR "/s1d1/s1d2";
+static const char file1_s1d2[] = TMP_DIR "/s1d1/s1d2/f1";
+static const char file2_s1d2[] = TMP_DIR "/s1d1/s1d2/f2";
+static const char dir_s1d3[] = TMP_DIR "/s1d1/s1d2/s1d3";
+static const char file1_s1d3[] = TMP_DIR "/s1d1/s1d2/s1d3/f1";
+static const char file2_s1d3[] = TMP_DIR "/s1d1/s1d2/s1d3/f2";
+
+static const char dir_s2d1[] = TMP_DIR "/s2d1";
+static const char file1_s2d1[] = TMP_DIR "/s2d1/f1";
+static const char dir_s2d2[] = TMP_DIR "/s2d1/s2d2";
+static const char file1_s2d2[] = TMP_DIR "/s2d1/s2d2/f1";
+static const char dir_s2d3[] = TMP_DIR "/s2d1/s2d2/s2d3";
+static const char file1_s2d3[] = TMP_DIR "/s2d1/s2d2/s2d3/f1";
+static const char file2_s2d3[] = TMP_DIR "/s2d1/s2d2/s2d3/f2";
+
+static const char dir_s3d1[] = TMP_DIR "/s3d1";
+/* dir_s3d2 is a mount point. */
+static const char dir_s3d2[] = TMP_DIR "/s3d1/s3d2";
+static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3";
+
+/*
+ * layout1 hierarchy:
+ *
+ * tmp
+ * ├── s1d1
+ * │   ├── f1
+ * │   ├── f2
+ * │   └── s1d2
+ * │   ├── f1
+ * │   ├── f2
+ * │   └── s1d3
+ * │   ├── f1
+ * │   └── f2
+ * ├── s2d1
+ * │   ├── f1
+ * │   └── s2d2
+ * │   ├── f1
+ * │   └── s2d3
+ * │   ├── f1
+ * │   └── f2
+ * └── s3d1
+ * └── s3d2
+ * └── s3d3
+ */
+
+static void mkdir_parents(struct __test_metadata *const _metadata,
+ const char *const path)
+{
+ char *walker;
+ const char *parent;
+ int i, err;
+
+ ASSERT_NE(path[0], '\0');
+ walker = strdup(path);
+ ASSERT_NE(NULL, walker);
+ parent = walker;
+ for (i = 1; walker[i]; i++) {
+ if (walker[i] != '/')
+ continue;
+ walker[i] = '\0';
+ err = mkdir(parent, 0700);
+ ASSERT_FALSE(err && errno != EEXIST) {
+ TH_LOG("Failed to create directory \"%s\": %s",
+ parent, strerror(errno));
+ }
+ walker[i] = '/';
+ }
+ free(walker);
+}
+
+static void create_directory(struct __test_metadata *const _metadata,
+ const char *const path)
+{
+ mkdir_parents(_metadata, path);
+ ASSERT_EQ(0, mkdir(path, 0700)) {
+ TH_LOG("Failed to create directory \"%s\": %s", path,
+ strerror(errno));
+ }
+}
+
+static void create_file(struct __test_metadata *const _metadata,
+ const char *const path)
+{
+ mkdir_parents(_metadata, path);
+ ASSERT_EQ(0, mknod(path, S_IFREG | 0700, 0)) {
+ TH_LOG("Failed to create file \"%s\": %s", path,
+ strerror(errno));
+ }
+}
+
+static int remove_path(const char *const path)
+{
+ char *walker;
+ int i, ret, err = 0;
+
+ walker = strdup(path);
+ if (!walker) {
+ err = ENOMEM;
+ goto out;
+ }
+ if (unlink(path) && rmdir(path)) {
+ if (errno != ENOENT)
+ err = errno;
+ goto out;
+ }
+ for (i = strlen(walker); i > 0; i--) {
+ if (walker[i] != '/')
+ continue;
+ walker[i] = '\0';
+ ret = rmdir(walker);
+ if (ret) {
+ if (errno != ENOTEMPTY && errno != EBUSY)
+ err = errno;
+ goto out;
+ }
+ if (strcmp(walker, TMP_DIR) == 0)
+ goto out;
+ }
+
+out:
+ free(walker);
+ return err;
+}
+
+static void prepare_layout(struct __test_metadata *const _metadata)
+{
+ disable_caps(_metadata);
+ umask(0077);
+ create_directory(_metadata, TMP_DIR);
+
+ /*
+ * Do not pollute the rest of the system: creates a private mount point
+ * for tests relying on pivot_root(2) and move_mount(2).
+ */
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, unshare(CLONE_NEWNS));
+ ASSERT_EQ(0, mount("tmp", TMP_DIR, "tmpfs", 0, "size=4m,mode=700"));
+ ASSERT_EQ(0, mount(NULL, TMP_DIR, NULL, MS_PRIVATE | MS_REC, NULL));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+}
+
+static void cleanup_layout(struct __test_metadata *const _metadata)
+{
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, umount(TMP_DIR));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, remove_path(TMP_DIR));
+}
+
+static void create_layout1(struct __test_metadata *const _metadata)
+{
+ create_file(_metadata, file1_s1d1);
+ create_file(_metadata, file1_s1d2);
+ create_file(_metadata, file1_s1d3);
+ create_file(_metadata, file2_s1d1);
+ create_file(_metadata, file2_s1d2);
+ create_file(_metadata, file2_s1d3);
+
+ create_file(_metadata, file1_s2d1);
+ create_file(_metadata, file1_s2d2);
+ create_file(_metadata, file1_s2d3);
+ create_file(_metadata, file2_s2d3);
+
+ create_directory(_metadata, dir_s3d2);
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, mount("tmp", dir_s3d2, "tmpfs", 0, "size=4m,mode=700"));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ ASSERT_EQ(0, mkdir(dir_s3d3, 0700));
+}
+
+static void remove_layout1(struct __test_metadata *const _metadata)
+{
+ EXPECT_EQ(0, remove_path(file2_s1d3));
+ EXPECT_EQ(0, remove_path(file2_s1d2));
+ EXPECT_EQ(0, remove_path(file2_s1d1));
+ EXPECT_EQ(0, remove_path(file1_s1d3));
+ EXPECT_EQ(0, remove_path(file1_s1d2));
+ EXPECT_EQ(0, remove_path(file1_s1d1));
+
+ EXPECT_EQ(0, remove_path(file2_s2d3));
+ EXPECT_EQ(0, remove_path(file1_s2d3));
+ EXPECT_EQ(0, remove_path(file1_s2d2));
+ EXPECT_EQ(0, remove_path(file1_s2d1));
+
+ EXPECT_EQ(0, remove_path(dir_s3d3));
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ umount(dir_s3d2);
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, remove_path(dir_s3d2));
+}
+
+FIXTURE(layout1) {
+};
+
+FIXTURE_SETUP(layout1)
+{
+ prepare_layout(_metadata);
+
+ create_layout1(_metadata);
+}
+
+FIXTURE_TEARDOWN(layout1)
+{
+ remove_layout1(_metadata);
+
+ cleanup_layout(_metadata);
+}
+
+/*
+ * This helper enables to use the ASSERT_* macros and print the line number
+ * pointing to the test caller.
+ */
+static int test_open_rel(const int dirfd, const char *const path, const int flags)
+{
+ int fd;
+
+ /* Works with file and directories. */
+ fd = openat(dirfd, path, flags | O_CLOEXEC);
+ if (fd < 0)
+ return errno;
+ /*
+ * Mixing error codes from close(2) and open(2) should not lead to any
+ * (access type) confusion for this test.
+ */
+ if (close(fd) != 0)
+ return errno;
+ return 0;
+}
+
+static int test_open(const char *const path, const int flags)
+{
+ return test_open_rel(AT_FDCWD, path, flags);
+}
+
+TEST_F_FORK(layout1, no_restriction)
+{
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file2_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file2_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(dir_s2d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s2d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(dir_s3d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d3, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, inval)
+{
+ struct landlock_path_beneath_attr path_beneath = {
+ .allowed_access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ .parent_fd = -1,
+ };
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ };
+ int ruleset_fd;
+
+ path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY |
+ O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd);
+
+ ruleset_fd = open(dir_s1d1, O_PATH | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ /* Returns EBADF because ruleset_fd is not a landlock-ruleset FD. */
+ ASSERT_EQ(EBADF, errno);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ruleset_fd = open(dir_s1d1, O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ /* Returns EBADFD because ruleset_fd is not a valid ruleset. */
+ ASSERT_EQ(EBADFD, errno);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Gets a real ruleset. */
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+
+ /* Tests without O_PATH. */
+ path_beneath.parent_fd = open(dir_s1d2, O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd);
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+
+ /* Tests with a ruleset FD. */
+ path_beneath.parent_fd = ruleset_fd;
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(EBADFD, errno);
+
+ /* Checks unhandled allowed_access. */
+ path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY |
+ O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd);
+
+ /* Test with legitimate values. */
+ path_beneath.allowed_access |= LANDLOCK_ACCESS_FS_EXECUTE;
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(EINVAL, errno);
+ path_beneath.allowed_access &= ~LANDLOCK_ACCESS_FS_EXECUTE;
+
+ /* Test with unknown (64-bits) value. */
+ path_beneath.allowed_access |= (1ULL << 60);
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(EINVAL, errno);
+ path_beneath.allowed_access &= ~(1ULL << 60);
+
+ /* Test with no access. */
+ path_beneath.allowed_access = 0;
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(ENOMSG, errno);
+ path_beneath.allowed_access &= ~(1ULL << 60);
+
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+
+ /* Enforces the ruleset. */
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+#define ACCESS_FILE ( \
+ LANDLOCK_ACCESS_FS_EXECUTE | \
+ LANDLOCK_ACCESS_FS_WRITE_FILE | \
+ LANDLOCK_ACCESS_FS_READ_FILE)
+
+#define ACCESS_LAST LANDLOCK_ACCESS_FS_MAKE_SYM
+
+#define ACCESS_ALL ( \
+ ACCESS_FILE | \
+ LANDLOCK_ACCESS_FS_READ_DIR | \
+ LANDLOCK_ACCESS_FS_REMOVE_DIR | \
+ LANDLOCK_ACCESS_FS_REMOVE_FILE | \
+ LANDLOCK_ACCESS_FS_MAKE_CHAR | \
+ LANDLOCK_ACCESS_FS_MAKE_DIR | \
+ LANDLOCK_ACCESS_FS_MAKE_REG | \
+ LANDLOCK_ACCESS_FS_MAKE_SOCK | \
+ LANDLOCK_ACCESS_FS_MAKE_FIFO | \
+ LANDLOCK_ACCESS_FS_MAKE_BLOCK | \
+ ACCESS_LAST)
+
+TEST_F_FORK(layout1, file_access_rights)
+{
+ __u64 access;
+ int err;
+ struct landlock_path_beneath_attr path_beneath = {};
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = ACCESS_ALL,
+ };
+ const int ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ /* Tests access rights for files. */
+ path_beneath.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd);
+ for (access = 1; access <= ACCESS_LAST; access <<= 1) {
+ path_beneath.allowed_access = access;
+ err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0);
+ if ((access | ACCESS_FILE) == ACCESS_FILE) {
+ ASSERT_EQ(0, err);
+ } else {
+ ASSERT_EQ(-1, err);
+ ASSERT_EQ(EINVAL, errno);
+ }
+ }
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+}
+
+static void add_path_beneath(struct __test_metadata *const _metadata,
+ const int ruleset_fd, const __u64 allowed_access,
+ const char *const path)
+{
+ struct landlock_path_beneath_attr path_beneath = {
+ .allowed_access = allowed_access,
+ };
+
+ path_beneath.parent_fd = open(path, O_PATH | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd) {
+ TH_LOG("Failed to open directory \"%s\": %s", path,
+ strerror(errno));
+ }
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0)) {
+ TH_LOG("Failed to update the ruleset with \"%s\": %s", path,
+ strerror(errno));
+ }
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+}
+
+struct rule {
+ const char *path;
+ __u64 access;
+};
+
+#define ACCESS_RO ( \
+ LANDLOCK_ACCESS_FS_READ_FILE | \
+ LANDLOCK_ACCESS_FS_READ_DIR)
+
+#define ACCESS_RW ( \
+ ACCESS_RO | \
+ LANDLOCK_ACCESS_FS_WRITE_FILE)
+
+static int create_ruleset(struct __test_metadata *const _metadata,
+ const __u64 handled_access_fs, const struct rule rules[])
+{
+ int ruleset_fd, i;
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = handled_access_fs,
+ };
+
+ ASSERT_NE(NULL, rules) {
+ TH_LOG("No rule list");
+ }
+ ASSERT_NE(NULL, rules[0].path) {
+ TH_LOG("Empty rule list");
+ }
+
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd) {
+ TH_LOG("Failed to create a ruleset: %s", strerror(errno));
+ }
+
+ for (i = 0; rules[i].path; i++) {
+ add_path_beneath(_metadata, ruleset_fd, rules[i].access,
+ rules[i].path);
+ }
+ return ruleset_fd;
+}
+
+static void enforce_ruleset(struct __test_metadata *const _metadata,
+ const int ruleset_fd)
+{
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)) {
+ TH_LOG("Failed to enforce ruleset: %s", strerror(errno));
+ }
+}
+
+TEST_F_FORK(layout1, proc_nsfs)
+{
+ const struct rule rules[] = {
+ {
+ .path = "/dev/null",
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ struct landlock_path_beneath_attr path_beneath;
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access |
+ LANDLOCK_ACCESS_FS_READ_DIR, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(0, test_open("/proc/self/ns/mnt", O_RDONLY));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open("/dev", O_RDONLY));
+ ASSERT_EQ(0, test_open("/dev/null", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open("/dev/full", O_RDONLY));
+
+ ASSERT_EQ(EACCES, test_open("/proc", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open("/proc/self", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open("/proc/self/ns", O_RDONLY));
+ /*
+ * Because nsfs is an internal filesystem, /proc/self/ns/mnt is a
+ * disconnected path. Such path cannot be identified and must then be
+ * allowed.
+ */
+ ASSERT_EQ(0, test_open("/proc/self/ns/mnt", O_RDONLY));
+
+ /*
+ * Checks that it is not possible to add nsfs-like filesystem
+ * references to a ruleset.
+ */
+ path_beneath.allowed_access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ path_beneath.parent_fd = open("/proc/self/ns/mnt", O_PATH | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath.parent_fd);
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath, 0));
+ ASSERT_EQ(EBADFD, errno);
+ ASSERT_EQ(0, close(path_beneath.parent_fd));
+}
+
+TEST_F_FORK(layout1, unpriv) {
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ int ruleset_fd;
+
+ drop_caps(_metadata);
+
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RO, rules);
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(-1, landlock_restrict_self(ruleset_fd, 0));
+ ASSERT_EQ(EPERM, errno);
+
+ /* enforce_ruleset() calls prctl(no_new_privs). */
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, effective_access)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = ACCESS_RO,
+ },
+ {
+ .path = file1_s2d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+ char buf;
+ int reg_fd;
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Tests on a directory. */
+ ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+
+ /* Tests on a file. */
+ ASSERT_EQ(EACCES, test_open(dir_s2d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d2, O_RDONLY));
+
+ /* Checks effective read and write actions. */
+ reg_fd = open(file1_s2d2, O_RDWR | O_CLOEXEC);
+ ASSERT_LE(0, reg_fd);
+ ASSERT_EQ(1, write(reg_fd, ".", 1));
+ ASSERT_LE(0, lseek(reg_fd, 0, SEEK_SET));
+ ASSERT_EQ(1, read(reg_fd, &buf, 1));
+ ASSERT_EQ('.', buf);
+ ASSERT_EQ(0, close(reg_fd));
+
+ /* Just in case, double-checks effective actions. */
+ reg_fd = open(file1_s2d2, O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, reg_fd);
+ ASSERT_EQ(-1, write(reg_fd, &buf, 1));
+ ASSERT_EQ(EBADF, errno);
+ ASSERT_EQ(0, close(reg_fd));
+}
+
+TEST_F_FORK(layout1, unhandled_access)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ /* Here, we only handle read accesses, not write accesses. */
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RO, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /*
+ * Because the policy does not handle LANDLOCK_ACCESS_FS_WRITE_FILE,
+ * opening for write-only should be allowed, but not read-write.
+ */
+ ASSERT_EQ(0, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+
+ ASSERT_EQ(0, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDWR));
+}
+
+TEST_F_FORK(layout1, ruleset_overlap)
+{
+ const struct rule rules[] = {
+ /* These rules should be ORed among them. */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks s1d1 hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d2 hierarchy. */
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d3 hierarchy. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+}
+
+TEST_F_FORK(layout1, non_overlapping_accesses)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {}
+ };
+ const struct rule layer2[] = {
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {}
+ };
+ int ruleset_fd;
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG,
+ layer1);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, mknod(file1_s1d1, S_IFREG | 0700, 0));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, mknod(file1_s1d2, S_IFREG | 0700, 0));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ layer2);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Unchanged accesses for file creation. */
+ ASSERT_EQ(-1, mknod(file1_s1d1, S_IFREG | 0700, 0));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, mknod(file1_s1d2, S_IFREG | 0700, 0));
+
+ /* Checks file removing. */
+ ASSERT_EQ(-1, unlink(file1_s1d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, unlink(file1_s1d3));
+}
+
+TEST_F_FORK(layout1, interleaved_masked_accesses)
+{
+ /*
+ * Checks overly restrictive rules:
+ * layer 1: allows R s1d1/s1d2/s1d3/file1
+ * layer 2: allows RW s1d1/s1d2/s1d3
+ * allows W s1d1/s1d2
+ * denies R s1d1/s1d2
+ * layer 3: allows R s1d1
+ * layer 4: allows R s1d1/s1d2
+ * denies W s1d1/s1d2
+ * layer 5: allows R s1d1/s1d2
+ * layer 6: allows X ----
+ * layer 7: allows W s1d1/s1d2
+ * denies R s1d1/s1d2
+ */
+ const struct rule layer1_read[] = {
+ /* Allows read access to file1_s1d3 with the first layer. */
+ {
+ .path = file1_s1d3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ /* First rule with write restrictions. */
+ const struct rule layer2_read_write[] = {
+ /* Start by granting read-write access via its parent directory... */
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ /* ...but also denies read access via its grandparent directory. */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ const struct rule layer3_read[] = {
+ /* Allows read access via its great-grandparent directory. */
+ {
+ .path = dir_s1d1,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ const struct rule layer4_read_write[] = {
+ /*
+ * Try to confuse the deny access by denying write (but not
+ * read) access via its grandparent directory.
+ */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ const struct rule layer5_read[] = {
+ /*
+ * Try to override layer2's deny read access by explicitly
+ * allowing read access via file1_s1d3's grandparent.
+ */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ const struct rule layer6_execute[] = {
+ /*
+ * Restricts an unrelated file hierarchy with a new access
+ * (non-overlapping) type.
+ */
+ {
+ .path = dir_s2d1,
+ .access = LANDLOCK_ACCESS_FS_EXECUTE,
+ },
+ {}
+ };
+ const struct rule layer7_read_write[] = {
+ /*
+ * Finally, denies read access to file1_s1d3 via its
+ * grandparent.
+ */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ int ruleset_fd;
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
+ layer1_read);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that read access is granted for file1_s1d3 with layer 1. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE, layer2_read_write);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that previous access rights are unchanged with layer 2. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
+ layer3_read);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that previous access rights are unchanged with layer 3. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
+
+ /* This time, denies write access for the file hierarchy. */
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE, layer4_read_write);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /*
+ * Checks that the only change with layer 4 is that write access is
+ * denied.
+ */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
+ layer5_read);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that previous access rights are unchanged with layer 5. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_EXECUTE,
+ layer6_execute);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that previous access rights are unchanged with layer 6. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+
+ ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE, layer7_read_write);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks read access is now denied with layer 7. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, inherit_subset)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Write access is forbidden. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ /* Readdir access is allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* Write access is forbidden. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ /* Readdir access is allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /*
+ * Tests shared rule extension: the following rules should not grant
+ * any new access, only remove some. Once enforced, these rules are
+ * ANDed with the previous ones.
+ */
+ add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE,
+ dir_s1d2);
+ /*
+ * According to ruleset_fd, dir_s1d2 should now have the
+ * LANDLOCK_ACCESS_FS_READ_FILE and LANDLOCK_ACCESS_FS_WRITE_FILE
+ * access rights (even if this directory is opened a second time).
+ * However, when enforcing this updated ruleset, the ruleset tied to
+ * the current process (i.e. its domain) will still only have the
+ * dir_s1d2 with LANDLOCK_ACCESS_FS_READ_FILE and
+ * LANDLOCK_ACCESS_FS_READ_DIR accesses, but
+ * LANDLOCK_ACCESS_FS_WRITE_FILE must not be allowed because it would
+ * be a privilege escalation.
+ */
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ /* Same tests and results as above. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d2. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ /* Readdir access is still allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ /* Readdir access is still allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /*
+ * Try to get more privileges by adding new access rights to the parent
+ * directory: dir_s1d1.
+ */
+ add_path_beneath(_metadata, ruleset_fd, ACCESS_RW, dir_s1d1);
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ /* Same tests and results as above. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d2. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ /* Readdir access is still allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ /* Readdir access is still allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /*
+ * Now, dir_s1d3 get a new rule tied to it, only allowing
+ * LANDLOCK_ACCESS_FS_WRITE_FILE. The (kernel internal) difference is
+ * that there was no rule tied to it before.
+ */
+ add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE,
+ dir_s1d3);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /*
+ * Same tests and results as above, except for open(dir_s1d3) which is
+ * now denied because the new rule mask the rule previously inherited
+ * from dir_s1d2.
+ */
+
+ /* Same tests and results as above. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d2. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ /* Readdir access is still allowed. */
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* It is still forbidden to write in file1_s1d3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ /*
+ * Readdir of dir_s1d3 is still allowed because of the OR policy inside
+ * the same layer.
+ */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+}
+
+TEST_F_FORK(layout1, inherit_superset)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d3,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ /* Readdir access is denied for dir_s1d2. */
+ ASSERT_EQ(EACCES, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+ /* Readdir access is allowed for dir_s1d3. */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+ /* File access is allowed for file1_s1d3. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+
+ /* Now dir_s1d2, parent of dir_s1d3, gets a new rule tied to it. */
+ add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR, dir_s1d2);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Readdir access is still denied for dir_s1d2. */
+ ASSERT_EQ(EACCES, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+ /* Readdir access is still allowed for dir_s1d3. */
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+ /* File access is still allowed for file1_s1d3. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, max_layers)
+{
+ int i, err;
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ for (i = 0; i < 64; i++)
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ for (i = 0; i < 2; i++) {
+ err = landlock_restrict_self(ruleset_fd, 0);
+ ASSERT_EQ(-1, err);
+ ASSERT_EQ(E2BIG, errno);
+ }
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, empty_or_same_ruleset)
+{
+ struct landlock_ruleset_attr ruleset_attr = {};
+ int ruleset_fd;
+
+ /* Tests empty handled_access_fs. */
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(-1, ruleset_fd);
+ ASSERT_EQ(ENOMSG, errno);
+
+ /* Enforces policy which deny read access to all files. */
+ ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE;
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+
+ /* Nests a policy which deny read access to all directories. */
+ ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR;
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY));
+
+ /* Enforces a second time with the same ruleset. */
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, rule_on_mountpoint)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d1,
+ .access = ACCESS_RO,
+ },
+ {
+ /* dir_s3d2 is a mount point. */
+ .path = dir_s3d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+
+ ASSERT_EQ(EACCES, test_open(dir_s2d1, O_RDONLY));
+
+ ASSERT_EQ(EACCES, test_open(dir_s3d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d3, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, rule_over_mountpoint)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d1,
+ .access = ACCESS_RO,
+ },
+ {
+ /* dir_s3d2 is a mount point. */
+ .path = dir_s3d1,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+
+ ASSERT_EQ(EACCES, test_open(dir_s2d1, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(dir_s3d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s3d3, O_RDONLY));
+}
+
+/*
+ * This test verifies that we can apply a landlock rule on the root directory
+ * (which might require special handling).
+ */
+TEST_F_FORK(layout1, rule_over_root_allow_then_deny)
+{
+ struct rule rules[] = {
+ {
+ .path = "/",
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks allowed access. */
+ ASSERT_EQ(0, test_open("/", O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+
+ rules[0].access = LANDLOCK_ACCESS_FS_READ_FILE;
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks denied access (on a directory). */
+ ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, rule_over_root_deny)
+{
+ const struct rule rules[] = {
+ {
+ .path = "/",
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks denied access (on a directory). */
+ ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY));
+}
+
+TEST_F_FORK(layout1, rule_inside_mount_ns)
+{
+ const struct rule rules[] = {
+ {
+ .path = "s3d3",
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ int ruleset_fd;
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3)) {
+ TH_LOG("Failed to pivot root: %s", strerror(errno));
+ };
+ ASSERT_EQ(0, chdir("/"));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, test_open("s3d3", O_RDONLY));
+ ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+}
+
+TEST_F_FORK(layout1, mount_and_pivot)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s3d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(-1, mount(NULL, dir_s3d2, NULL, MS_RDONLY, NULL));
+ ASSERT_EQ(EPERM, errno);
+ ASSERT_EQ(-1, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3));
+ ASSERT_EQ(EPERM, errno);
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+}
+
+TEST_F_FORK(layout1, move_mount)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s3d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
+ dir_s1d2, 0)) {
+ TH_LOG("Failed to move mount: %s", strerror(errno));
+ }
+
+ ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s1d2, AT_FDCWD,
+ dir_s3d2, 0));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(-1, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
+ dir_s1d2, 0));
+ ASSERT_EQ(EPERM, errno);
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+}
+
+TEST_F_FORK(layout1, release_inodes)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d1,
+ .access = ACCESS_RO,
+ },
+ {
+ .path = dir_s3d2,
+ .access = ACCESS_RO,
+ },
+ {
+ .path = dir_s3d3,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ /* Unmount a file hierarchy while it is being used by a ruleset. */
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, umount(dir_s3d2));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s3d2, O_RDONLY));
+ /* This dir_s3d3 would not be allowed and does not exist anyway. */
+ ASSERT_EQ(ENOENT, test_open(dir_s3d3, O_RDONLY));
+}
+
+enum relative_access {
+ REL_OPEN,
+ REL_CHDIR,
+ REL_CHROOT_ONLY,
+ REL_CHROOT_CHDIR,
+};
+
+static void test_relative_path(struct __test_metadata *const _metadata,
+ const enum relative_access rel)
+{
+ /*
+ * Common layer to check that chroot doesn't ignore it (i.e. a chroot
+ * is not a disconnected root directory).
+ */
+ const struct rule layer1_base[] = {
+ {
+ .path = TMP_DIR,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ const struct rule layer2_subs[] = {
+ {
+ .path = dir_s1d2,
+ .access = ACCESS_RO,
+ },
+ {
+ .path = dir_s2d2,
+ .access = ACCESS_RO,
+ },
+ {}
+ };
+ int dirfd, ruleset_fd;
+
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer2_subs);
+
+ ASSERT_LE(0, ruleset_fd);
+ switch (rel) {
+ case REL_OPEN:
+ case REL_CHDIR:
+ break;
+ case REL_CHROOT_ONLY:
+ ASSERT_EQ(0, chdir(dir_s2d2));
+ break;
+ case REL_CHROOT_CHDIR:
+ ASSERT_EQ(0, chdir(dir_s1d2));
+ break;
+ default:
+ ASSERT_TRUE(false);
+ return;
+ }
+
+ set_cap(_metadata, CAP_SYS_CHROOT);
+ enforce_ruleset(_metadata, ruleset_fd);
+
+ switch (rel) {
+ case REL_OPEN:
+ dirfd = open(dir_s1d2, O_DIRECTORY);
+ ASSERT_LE(0, dirfd);
+ break;
+ case REL_CHDIR:
+ ASSERT_EQ(0, chdir(dir_s1d2));
+ dirfd = AT_FDCWD;
+ break;
+ case REL_CHROOT_ONLY:
+ /* Do chroot into dir_s1d2 (relative to dir_s2d2). */
+ ASSERT_EQ(0, chroot("../../s1d1/s1d2")) {
+ TH_LOG("Failed to chroot: %s", strerror(errno));
+ }
+ dirfd = AT_FDCWD;
+ break;
+ case REL_CHROOT_CHDIR:
+ /* Do chroot into dir_s1d2. */
+ ASSERT_EQ(0, chroot(".")) {
+ TH_LOG("Failed to chroot: %s", strerror(errno));
+ }
+ dirfd = AT_FDCWD;
+ break;
+ }
+
+ ASSERT_EQ((rel == REL_CHROOT_CHDIR) ? 0 : EACCES,
+ test_open_rel(dirfd, "..", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, ".", O_RDONLY));
+
+ if (rel == REL_CHROOT_ONLY) {
+ /* The current directory is dir_s2d2. */
+ ASSERT_EQ(0, test_open_rel(dirfd, "./s2d3", O_RDONLY));
+ } else {
+ /* The current directory is dir_s1d2. */
+ ASSERT_EQ(0, test_open_rel(dirfd, "./s1d3", O_RDONLY));
+ }
+
+ if (rel == REL_CHROOT_ONLY || rel == REL_CHROOT_CHDIR) {
+ /* Checks the root dir_s1d2. */
+ ASSERT_EQ(0, test_open_rel(dirfd, "/..", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "/", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "/f1", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "/s1d3", O_RDONLY));
+ }
+
+ if (rel != REL_CHROOT_CHDIR) {
+ ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s1d1", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2/s1d3", O_RDONLY));
+
+ ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s2d1", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2/s2d3", O_RDONLY));
+ }
+
+ if (rel == REL_OPEN)
+ ASSERT_EQ(0, close(dirfd));
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, relative_open)
+{
+ test_relative_path(_metadata, REL_OPEN);
+}
+
+TEST_F_FORK(layout1, relative_chdir)
+{
+ test_relative_path(_metadata, REL_CHDIR);
+}
+
+TEST_F_FORK(layout1, relative_chroot_only)
+{
+ test_relative_path(_metadata, REL_CHROOT_ONLY);
+}
+
+TEST_F_FORK(layout1, relative_chroot_chdir)
+{
+ test_relative_path(_metadata, REL_CHROOT_CHDIR);
+}
+
+static void copy_binary(struct __test_metadata *const _metadata,
+ const char *const dst_path)
+{
+ int dst_fd, src_fd;
+ struct stat statbuf;
+
+ dst_fd = open(dst_path, O_WRONLY | O_TRUNC | O_CLOEXEC);
+ ASSERT_LE(0, dst_fd) {
+ TH_LOG("Failed to open \"%s\": %s", dst_path,
+ strerror(errno));
+ }
+ src_fd = open(BINARY_PATH, O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, src_fd) {
+ TH_LOG("Failed to open \"" BINARY_PATH "\": %s",
+ strerror(errno));
+ }
+ ASSERT_EQ(0, fstat(src_fd, &statbuf));
+ ASSERT_EQ(statbuf.st_size, sendfile(dst_fd, src_fd, 0,
+ statbuf.st_size));
+ ASSERT_EQ(0, close(src_fd));
+ ASSERT_EQ(0, close(dst_fd));
+}
+
+static void test_execute(struct __test_metadata *const _metadata,
+ const int err, const char *const path)
+{
+ int status;
+ char *const argv[] = {(char *)path, NULL};
+ const pid_t child = fork();
+
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ ASSERT_EQ(err ? -1 : 0, execve(path, argv, NULL)) {
+ TH_LOG("Failed to execute \"%s\": %s", path,
+ strerror(errno));
+ };
+ ASSERT_EQ(err, errno);
+ _exit(_metadata->passed ? 2 : 1);
+ return;
+ }
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ ASSERT_EQ(1, WIFEXITED(status));
+ ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) {
+ TH_LOG("Unexpected return code for \"%s\": %s", path,
+ strerror(errno));
+ };
+}
+
+TEST_F_FORK(layout1, execute)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_EXECUTE,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ copy_binary(_metadata, file1_s1d1);
+ copy_binary(_metadata, file1_s1d2);
+ copy_binary(_metadata, file1_s1d3);
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY));
+ test_execute(_metadata, EACCES, file1_s1d1);
+
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ test_execute(_metadata, 0, file1_s1d2);
+
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ test_execute(_metadata, 0, file1_s1d3);
+}
+
+TEST_F_FORK(layout1, link)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ /* Denies linking because of reparenting. */
+ ASSERT_EQ(-1, link(file1_s2d1, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, link(file2_s1d2, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ ASSERT_EQ(0, link(file2_s1d2, file1_s1d2));
+ ASSERT_EQ(0, link(file2_s1d3, file1_s1d3));
+}
+
+TEST_F_FORK(layout1, rename_file)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /*
+ * Tries to replace a file, from a directory that allows file removal,
+ * but to a different directory (which also allows file removal).
+ */
+ ASSERT_EQ(-1, rename(file1_s2d3, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, file1_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+
+ /*
+ * Tries to replace a file, from a directory that denies file removal,
+ * to a different directory (which allows file removal).
+ */
+ ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file1_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d2, AT_FDCWD, file1_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Exchanges files and directories that partially allow removal. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d2, AT_FDCWD, file1_s2d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, dir_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Renames files with different parents. */
+ ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Exchanges and renames files with same parent. */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, rename(file2_s2d3, file1_s2d3));
+
+ /* Exchanges files and directories with same parent, twice. */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+}
+
+TEST_F_FORK(layout1, rename_dir)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
+ },
+ {
+ .path = dir_s2d1,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ /* Empties dir_s1d3 to allow renaming. */
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Exchanges and renames directory to a different parent. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(dir_s2d3, dir_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+
+ /*
+ * Exchanges directory to the same parent, which doesn't allow
+ * directory removal.
+ */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d1, AT_FDCWD, dir_s2d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s1d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /*
+ * Exchanges and renames directory to the same parent, which allows
+ * directory removal.
+ */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, file1_s1d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, unlink(dir_s1d3));
+ ASSERT_EQ(0, mkdir(dir_s1d3, 0700));
+ ASSERT_EQ(0, rename(file1_s1d2, dir_s1d3));
+ ASSERT_EQ(0, rmdir(dir_s1d3));
+}
+
+TEST_F_FORK(layout1, remove_dir)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, rmdir(dir_s1d3));
+ ASSERT_EQ(0, mkdir(dir_s1d3, 0700));
+ ASSERT_EQ(0, unlinkat(AT_FDCWD, dir_s1d3, AT_REMOVEDIR));
+
+ /* dir_s1d2 itself cannot be removed. */
+ ASSERT_EQ(-1, rmdir(dir_s1d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, unlinkat(AT_FDCWD, dir_s1d2, AT_REMOVEDIR));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rmdir(dir_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, unlinkat(AT_FDCWD, dir_s1d1, AT_REMOVEDIR));
+ ASSERT_EQ(EACCES, errno);
+}
+
+TEST_F_FORK(layout1, remove_file)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, unlink(file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, unlinkat(AT_FDCWD, file1_s1d1, 0));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlinkat(AT_FDCWD, file1_s1d3, 0));
+}
+
+static void test_make_file(struct __test_metadata *const _metadata,
+ const __u64 access, const mode_t mode, const dev_t dev)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = access,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, access, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file2_s1d1));
+ ASSERT_EQ(0, mknod(file2_s1d1, mode | 0400, dev)) {
+ TH_LOG("Failed to make file \"%s\": %s",
+ file2_s1d1, strerror(errno));
+ };
+
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file2_s1d2));
+
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, mknod(file1_s1d1, mode | 0400, dev));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+
+ ASSERT_EQ(0, mknod(file1_s1d2, mode | 0400, dev)) {
+ TH_LOG("Failed to make file \"%s\": %s",
+ file1_s1d2, strerror(errno));
+ };
+ ASSERT_EQ(0, link(file1_s1d2, file2_s1d2));
+ ASSERT_EQ(0, unlink(file2_s1d2));
+ ASSERT_EQ(0, rename(file1_s1d2, file2_s1d2));
+
+ ASSERT_EQ(0, mknod(file1_s1d3, mode | 0400, dev));
+ ASSERT_EQ(0, link(file1_s1d3, file2_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+ ASSERT_EQ(0, rename(file1_s1d3, file2_s1d3));
+}
+
+TEST_F_FORK(layout1, make_char)
+{
+ /* Creates a /dev/null device. */
+ set_cap(_metadata, CAP_MKNOD);
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_CHAR, S_IFCHR,
+ makedev(1, 3));
+}
+
+TEST_F_FORK(layout1, make_block)
+{
+ /* Creates a /dev/loop0 device. */
+ set_cap(_metadata, CAP_MKNOD);
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_BLOCK, S_IFBLK,
+ makedev(7, 0));
+}
+
+TEST_F_FORK(layout1, make_reg_1)
+{
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG, S_IFREG, 0);
+}
+
+TEST_F_FORK(layout1, make_reg_2)
+{
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG, 0, 0);
+}
+
+TEST_F_FORK(layout1, make_sock)
+{
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_SOCK, S_IFSOCK, 0);
+}
+
+TEST_F_FORK(layout1, make_fifo)
+{
+ test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_FIFO, S_IFIFO, 0);
+}
+
+TEST_F_FORK(layout1, make_sym)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_SYM,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file2_s1d1));
+ ASSERT_EQ(0, symlink("none", file2_s1d1));
+
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file2_s1d2));
+
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, symlink("none", file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+
+ ASSERT_EQ(0, symlink("none", file1_s1d2));
+ ASSERT_EQ(0, link(file1_s1d2, file2_s1d2));
+ ASSERT_EQ(0, unlink(file2_s1d2));
+ ASSERT_EQ(0, rename(file1_s1d2, file2_s1d2));
+
+ ASSERT_EQ(0, symlink("none", file1_s1d3));
+ ASSERT_EQ(0, link(file1_s1d3, file2_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+ ASSERT_EQ(0, rename(file1_s1d3, file2_s1d3));
+}
+
+TEST_F_FORK(layout1, make_dir)
+{
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_DIR,
+ },
+ {}
+ };
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Uses file_* as directory names. */
+ ASSERT_EQ(-1, mkdir(file1_s1d1, 0700));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, mkdir(file1_s1d2, 0700));
+ ASSERT_EQ(0, mkdir(file1_s1d3, 0700));
+}
+
+static int open_proc_fd(struct __test_metadata *const _metadata, const int fd,
+ const int open_flags)
+{
+ static const char path_template[] = "/proc/self/fd/%d";
+ char procfd_path[sizeof(path_template) + 10];
+ const int procfd_path_size = snprintf(procfd_path, sizeof(procfd_path),
+ path_template, fd);
+
+ ASSERT_LT(procfd_path_size, sizeof(procfd_path));
+ return open(procfd_path, open_flags);
+}
+
+TEST_F_FORK(layout1, proc_unlinked_file)
+{
+ const struct rule rules[] = {
+ {
+ .path = file1_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ int reg_fd, proc_fd;
+ const int ruleset_fd = create_ruleset(_metadata,
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE, rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ reg_fd = open(file1_s1d2, O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, reg_fd);
+ ASSERT_EQ(0, unlink(file1_s1d2));
+
+ proc_fd = open_proc_fd(_metadata, reg_fd, O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, proc_fd);
+ ASSERT_EQ(0, close(proc_fd));
+
+ proc_fd = open_proc_fd(_metadata, reg_fd, O_RDWR | O_CLOEXEC);
+ ASSERT_EQ(-1, proc_fd) {
+ TH_LOG("Successfully opened /proc/self/fd/%d: %s",
+ reg_fd, strerror(errno));
+ }
+ ASSERT_EQ(EACCES, errno);
+
+ ASSERT_EQ(0, close(reg_fd));
+}
+
+TEST_F_FORK(layout1, proc_pipe)
+{
+ int proc_fd;
+ int pipe_fds[2];
+ char buf = '\0';
+ const struct rule rules[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ /* Limits read and write access to files tied to the filesystem. */
+ const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
+ rules);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks enforcement for normal files. */
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+
+ /* Checks access to pipes through FD. */
+ ASSERT_EQ(0, pipe2(pipe_fds, O_CLOEXEC));
+ ASSERT_EQ(1, write(pipe_fds[1], ".", 1)) {
+ TH_LOG("Failed to write in pipe: %s", strerror(errno));
+ }
+ ASSERT_EQ(1, read(pipe_fds[0], &buf, 1));
+ ASSERT_EQ('.', buf);
+
+ /* Checks write access to pipe through /proc/self/fd . */
+ proc_fd = open_proc_fd(_metadata, pipe_fds[1], O_WRONLY | O_CLOEXEC);
+ ASSERT_LE(0, proc_fd);
+ ASSERT_EQ(1, write(proc_fd, ".", 1)) {
+ TH_LOG("Failed to write through /proc/self/fd/%d: %s",
+ pipe_fds[1], strerror(errno));
+ }
+ ASSERT_EQ(0, close(proc_fd));
+
+ /* Checks read access to pipe through /proc/self/fd . */
+ proc_fd = open_proc_fd(_metadata, pipe_fds[0], O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, proc_fd);
+ buf = '\0';
+ ASSERT_EQ(1, read(proc_fd, &buf, 1)) {
+ TH_LOG("Failed to read through /proc/self/fd/%d: %s",
+ pipe_fds[1], strerror(errno));
+ }
+ ASSERT_EQ(0, close(proc_fd));
+
+ ASSERT_EQ(0, close(pipe_fds[0]));
+ ASSERT_EQ(0, close(pipe_fds[1]));
+}
+
+FIXTURE(layout1_bind) {
+};
+
+FIXTURE_SETUP(layout1_bind)
+{
+ prepare_layout(_metadata);
+
+ create_layout1(_metadata);
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, mount(dir_s1d2, dir_s2d2, NULL, MS_BIND, NULL));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+}
+
+FIXTURE_TEARDOWN(layout1_bind)
+{
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, umount(dir_s2d2));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+
+ remove_layout1(_metadata);
+
+ cleanup_layout(_metadata);
+}
+
+static const char bind_dir_s1d3[] = TMP_DIR "/s2d1/s2d2/s1d3";
+static const char bind_file1_s1d3[] = TMP_DIR "/s2d1/s2d2/s1d3/f1";
+
+/*
+ * layout1_bind hierarchy:
+ *
+ * tmp
+ * ├── s1d1
+ * │   ├── f1
+ * │   ├── f2
+ * │   └── s1d2
+ * │   ├── f1
+ * │   ├── f2
+ * │   └── s1d3
+ * │   ├── f1
+ * │   └── f2
+ * ├── s2d1
+ * │   ├── f1
+ * │   └── s2d2
+ * │   ├── f1
+ * │   ├── f2
+ * │   └── s1d3
+ * │   ├── f1
+ * │   └── f2
+ * └── s3d1
+ * └── s3d2
+ * └── s3d3
+ */
+
+TEST_F_FORK(layout1_bind, no_restriction)
+{
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(dir_s2d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s2d2, O_RDONLY));
+ ASSERT_EQ(ENOENT, test_open(dir_s2d3, O_RDONLY));
+ ASSERT_EQ(ENOENT, test_open(file1_s2d3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(bind_dir_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(bind_file1_s1d3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(dir_s3d1, O_RDONLY));
+}
+
+TEST_F_FORK(layout1_bind, same_content_same_file)
+{
+ /*
+ * Sets access right on parent directories of both source and
+ * destination mount points.
+ */
+ const struct rule layer1_parent[] = {
+ {
+ .path = dir_s1d1,
+ .access = ACCESS_RO,
+ },
+ {
+ .path = dir_s2d1,
+ .access = ACCESS_RW,
+ },
+ {}
+ };
+ /*
+ * Sets access rights on the same bind-mounted directories. The result
+ * should be ACCESS_RW for both directories, but not both hierarchies
+ * because of the first layer.
+ */
+ const struct rule layer2_mount_point[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = dir_s2d2,
+ .access = ACCESS_RW,
+ },
+ {}
+ };
+ /* Only allow read-access to the s1d3 hierarchies. */
+ const struct rule layer3_source[] = {
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {}
+ };
+ /* Removes all access rights. */
+ const struct rule layer4_destination[] = {
+ {
+ .path = bind_file1_s1d3,
+ .access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ int ruleset_fd;
+
+ /* Sets rules for the parent directories. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_parent);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks source hierarchy. */
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* Checks destination hierarchy. */
+ ASSERT_EQ(0, test_open(file1_s2d1, O_RDWR));
+ ASSERT_EQ(0, test_open(dir_s2d1, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(file1_s2d2, O_RDWR));
+ ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY | O_DIRECTORY));
+
+ /* Sets rules for the mount points. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer2_mount_point);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks source hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ /* Checks destination hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s2d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s2d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s2d1, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(file1_s2d2, O_RDWR));
+ ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY | O_DIRECTORY));
+ ASSERT_EQ(0, test_open(bind_dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /* Sets a (shared) rule only on the source. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer3_source);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks source hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d2, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /* Checks destination hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s2d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s2d2, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(dir_s2d2, O_RDONLY | O_DIRECTORY));
+
+ ASSERT_EQ(0, test_open(bind_file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(bind_file1_s1d3, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(bind_dir_s1d3, O_RDONLY | O_DIRECTORY));
+
+ /* Sets a (shared) rule only on the destination. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer4_destination);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks source hierarchy. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_WRONLY));
+
+ /* Checks destination hierarchy. */
+ ASSERT_EQ(EACCES, test_open(bind_file1_s1d3, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(bind_file1_s1d3, O_WRONLY));
+}
+
+#define LOWER_BASE TMP_DIR "/lower"
+#define LOWER_DATA LOWER_BASE "/data"
+static const char lower_fl1[] = LOWER_DATA "/fl1";
+static const char lower_dl1[] = LOWER_DATA "/dl1";
+static const char lower_dl1_fl2[] = LOWER_DATA "/dl1/fl2";
+static const char lower_fo1[] = LOWER_DATA "/fo1";
+static const char lower_do1[] = LOWER_DATA "/do1";
+static const char lower_do1_fo2[] = LOWER_DATA "/do1/fo2";
+static const char lower_do1_fl3[] = LOWER_DATA "/do1/fl3";
+
+static const char (*lower_base_files[])[] = {
+ &lower_fl1,
+ &lower_fo1,
+ NULL
+};
+static const char (*lower_base_directories[])[] = {
+ &lower_dl1,
+ &lower_do1,
+ NULL
+};
+static const char (*lower_sub_files[])[] = {
+ &lower_dl1_fl2,
+ &lower_do1_fo2,
+ &lower_do1_fl3,
+ NULL
+};
+
+#define UPPER_BASE TMP_DIR "/upper"
+#define UPPER_DATA UPPER_BASE "/data"
+#define UPPER_WORK UPPER_BASE "/work"
+static const char upper_fu1[] = UPPER_DATA "/fu1";
+static const char upper_du1[] = UPPER_DATA "/du1";
+static const char upper_du1_fu2[] = UPPER_DATA "/du1/fu2";
+static const char upper_fo1[] = UPPER_DATA "/fo1";
+static const char upper_do1[] = UPPER_DATA "/do1";
+static const char upper_do1_fo2[] = UPPER_DATA "/do1/fo2";
+static const char upper_do1_fu3[] = UPPER_DATA "/do1/fu3";
+
+static const char (*upper_base_files[])[] = {
+ &upper_fu1,
+ &upper_fo1,
+ NULL
+};
+static const char (*upper_base_directories[])[] = {
+ &upper_du1,
+ &upper_do1,
+ NULL
+};
+static const char (*upper_sub_files[])[] = {
+ &upper_du1_fu2,
+ &upper_do1_fo2,
+ &upper_do1_fu3,
+ NULL
+};
+
+#define MERGE_BASE TMP_DIR "/merge"
+#define MERGE_DATA MERGE_BASE "/data"
+static const char merge_fl1[] = MERGE_DATA "/fl1";
+static const char merge_dl1[] = MERGE_DATA "/dl1";
+static const char merge_dl1_fl2[] = MERGE_DATA "/dl1/fl2";
+static const char merge_fu1[] = MERGE_DATA "/fu1";
+static const char merge_du1[] = MERGE_DATA "/du1";
+static const char merge_du1_fu2[] = MERGE_DATA "/du1/fu2";
+static const char merge_fo1[] = MERGE_DATA "/fo1";
+static const char merge_do1[] = MERGE_DATA "/do1";
+static const char merge_do1_fo2[] = MERGE_DATA "/do1/fo2";
+static const char merge_do1_fl3[] = MERGE_DATA "/do1/fl3";
+static const char merge_do1_fu3[] = MERGE_DATA "/do1/fu3";
+
+static const char (*merge_base_files[])[] = {
+ &merge_fl1,
+ &merge_fu1,
+ &merge_fo1,
+ NULL
+};
+static const char (*merge_base_directories[])[] = {
+ &merge_dl1,
+ &merge_du1,
+ &merge_do1,
+ NULL
+};
+static const char (*merge_sub_files[])[] = {
+ &merge_dl1_fl2,
+ &merge_du1_fu2,
+ &merge_do1_fo2,
+ &merge_do1_fl3,
+ &merge_do1_fu3,
+ NULL
+};
+
+/*
+ * layout2_overlay hierarchy:
+ *
+ * tmp
+ * ├── lower
+ * │   └── data
+ * │   ├── dl1
+ * │   │   └── fl2
+ * │   ├── do1
+ * │   │   ├── fl3
+ * │   │   └── fo2
+ * │   ├── fl1
+ * │   └── fo1
+ * ├── merge
+ * │   └── data
+ * │   ├── dl1
+ * │   │   └── fl2
+ * │   ├── do1
+ * │   │   ├── fl3
+ * │   │   ├── fo2
+ * │   │   └── fu3
+ * │   ├── du1
+ * │   │   └── fu2
+ * │   ├── fl1
+ * │   ├── fo1
+ * │   └── fu1
+ * └── upper
+ * ├── data
+ * │   ├── do1
+ * │   │   ├── fo2
+ * │   │   └── fu3
+ * │   ├── du1
+ * │   │   └── fu2
+ * │   ├── fo1
+ * │   └── fu1
+ * └── work
+ * └── work
+ */
+
+FIXTURE(layout2_overlay) {
+};
+
+FIXTURE_SETUP(layout2_overlay)
+{
+ prepare_layout(_metadata);
+
+ create_directory(_metadata, LOWER_BASE);
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ /* Creates tmpfs mount points to get deterministic overlayfs. */
+ ASSERT_EQ(0, mount("tmp", LOWER_BASE, "tmpfs", 0, "size=4m,mode=700"));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ create_file(_metadata, lower_fl1);
+ create_file(_metadata, lower_dl1_fl2);
+ create_file(_metadata, lower_fo1);
+ create_file(_metadata, lower_do1_fo2);
+ create_file(_metadata, lower_do1_fl3);
+
+ create_directory(_metadata, UPPER_BASE);
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ ASSERT_EQ(0, mount("tmp", UPPER_BASE, "tmpfs", 0, "size=4m,mode=700"));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ create_file(_metadata, upper_fu1);
+ create_file(_metadata, upper_du1_fu2);
+ create_file(_metadata, upper_fo1);
+ create_file(_metadata, upper_do1_fo2);
+ create_file(_metadata, upper_do1_fu3);
+ ASSERT_EQ(0, mkdir(UPPER_WORK, 0700));
+
+ create_directory(_metadata, MERGE_DATA);
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ set_cap(_metadata, CAP_DAC_OVERRIDE);
+ ASSERT_EQ(0, mount("overlay", MERGE_DATA, "overlay", 0,
+ "lowerdir=" LOWER_DATA
+ ",upperdir=" UPPER_DATA
+ ",workdir=" UPPER_WORK));
+ clear_cap(_metadata, CAP_DAC_OVERRIDE);
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+}
+
+FIXTURE_TEARDOWN(layout2_overlay)
+{
+ EXPECT_EQ(0, remove_path(lower_do1_fl3));
+ EXPECT_EQ(0, remove_path(lower_dl1_fl2));
+ EXPECT_EQ(0, remove_path(lower_fl1));
+ EXPECT_EQ(0, remove_path(lower_do1_fo2));
+ EXPECT_EQ(0, remove_path(lower_fo1));
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, umount(LOWER_BASE));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, remove_path(LOWER_BASE));
+
+ EXPECT_EQ(0, remove_path(upper_do1_fu3));
+ EXPECT_EQ(0, remove_path(upper_du1_fu2));
+ EXPECT_EQ(0, remove_path(upper_fu1));
+ EXPECT_EQ(0, remove_path(upper_do1_fo2));
+ EXPECT_EQ(0, remove_path(upper_fo1));
+ EXPECT_EQ(0, remove_path(UPPER_WORK "/work"));
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, umount(UPPER_BASE));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, remove_path(UPPER_BASE));
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, umount(MERGE_DATA));
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, remove_path(MERGE_DATA));
+
+ cleanup_layout(_metadata);
+}
+
+TEST_F_FORK(layout2_overlay, no_restriction)
+{
+ ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_dl1_fl2, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_fo1, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_do1, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_do1_fo2, O_RDONLY));
+ ASSERT_EQ(0, test_open(lower_do1_fl3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(upper_fu1, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_du1, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_du1_fu2, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_fo1, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_do1, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_do1_fo2, O_RDONLY));
+ ASSERT_EQ(0, test_open(upper_do1_fu3, O_RDONLY));
+
+ ASSERT_EQ(0, test_open(merge_fl1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_dl1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_dl1_fl2, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_fu1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_du1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_du1_fu2, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_fo1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_do1, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_do1_fo2, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_do1_fl3, O_RDONLY));
+ ASSERT_EQ(0, test_open(merge_do1_fu3, O_RDONLY));
+}
+
+#define for_each_path(path_list, path_entry, i) \
+ for (i = 0, path_entry = *path_list[i]; path_list[i]; \
+ path_entry = *path_list[++i])
+
+TEST_F_FORK(layout2_overlay, same_content_different_file)
+{
+ /* Sets access right on parent directories of both layers. */
+ const struct rule layer1_base[] = {
+ {
+ .path = LOWER_BASE,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = UPPER_BASE,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = MERGE_BASE,
+ .access = ACCESS_RW,
+ },
+ {}
+ };
+ const struct rule layer2_data[] = {
+ {
+ .path = LOWER_DATA,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = UPPER_DATA,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = MERGE_DATA,
+ .access = ACCESS_RW,
+ },
+ {}
+ };
+ /* Sets access right on directories inside both layers. */
+ const struct rule layer3_subdirs[] = {
+ {
+ .path = lower_dl1,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = lower_do1,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = upper_du1,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = upper_do1,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = merge_dl1,
+ .access = ACCESS_RW,
+ },
+ {
+ .path = merge_du1,
+ .access = ACCESS_RW,
+ },
+ {
+ .path = merge_do1,
+ .access = ACCESS_RW,
+ },
+ {}
+ };
+ /* Tighten access rights to the files. */
+ const struct rule layer4_files[] = {
+ {
+ .path = lower_dl1_fl2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = lower_do1_fo2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = lower_do1_fl3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = upper_du1_fu2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = upper_do1_fo2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = upper_do1_fu3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ {
+ .path = merge_dl1_fl2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {
+ .path = merge_du1_fu2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {
+ .path = merge_do1_fo2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {
+ .path = merge_do1_fl3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {
+ .path = merge_do1_fu3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ const struct rule layer5_merge_only[] = {
+ {
+ .path = MERGE_DATA,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {}
+ };
+ int ruleset_fd;
+ size_t i;
+ const char *path_entry;
+
+ /* Sets rules on base directories (i.e. outside overlay scope). */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks lower layer. */
+ for_each_path(lower_base_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ for_each_path(lower_base_directories, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(lower_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ /* Checks upper layer. */
+ for_each_path(upper_base_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ for_each_path(upper_base_directories, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(upper_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ /*
+ * Checks that access rights are independent from the lower and upper
+ * layers: write access to upper files viewed through the merge point
+ * is still allowed, and write access to lower file viewed (and copied)
+ * through the merge point is still allowed.
+ */
+ for_each_path(merge_base_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+ for_each_path(merge_base_directories, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(merge_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+
+ /* Sets rules on data directories (i.e. inside overlay scope). */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer2_data);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks merge. */
+ for_each_path(merge_base_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+ for_each_path(merge_base_directories, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(merge_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+
+ /* Same checks with tighter rules. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer3_subdirs);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks changes for lower layer. */
+ for_each_path(lower_base_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY));
+ }
+ /* Checks changes for upper layer. */
+ for_each_path(upper_base_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY));
+ }
+ /* Checks all merge accesses. */
+ for_each_path(merge_base_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR));
+ }
+ for_each_path(merge_base_directories, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(merge_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+
+ /* Sets rules directly on overlayed files. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer4_files);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks unchanged accesses on lower layer. */
+ for_each_path(lower_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ /* Checks unchanged accesses on upper layer. */
+ for_each_path(upper_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
+ }
+ /* Checks all merge accesses. */
+ for_each_path(merge_base_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR));
+ }
+ for_each_path(merge_base_directories, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(merge_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+
+ /* Only allowes access to the merge hierarchy. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer5_merge_only);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks new accesses on lower layer. */
+ for_each_path(lower_sub_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY));
+ }
+ /* Checks new accesses on upper layer. */
+ for_each_path(upper_sub_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY));
+ }
+ /* Checks all merge accesses. */
+ for_each_path(merge_base_files, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR));
+ }
+ for_each_path(merge_base_directories, path_entry, i) {
+ ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ }
+ for_each_path(merge_sub_files, path_entry, i) {
+ ASSERT_EQ(0, test_open(path_entry, O_RDWR));
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c
new file mode 100644
index 000000000000..15fbef9cc849
--- /dev/null
+++ b/tools/testing/selftests/landlock/ptrace_test.c
@@ -0,0 +1,337 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Landlock tests - Ptrace
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/landlock.h>
+#include <signal.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "common.h"
+
+static void create_domain(struct __test_metadata *const _metadata)
+{
+ int ruleset_fd;
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_MAKE_BLOCK,
+ };
+
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ EXPECT_LE(0, ruleset_fd) {
+ TH_LOG("Failed to create a ruleset: %s", strerror(errno));
+ }
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ EXPECT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+ EXPECT_EQ(0, close(ruleset_fd));
+}
+
+static int test_ptrace_read(const pid_t pid)
+{
+ static const char path_template[] = "/proc/%d/environ";
+ char procenv_path[sizeof(path_template) + 10];
+ int procenv_path_size, fd;
+
+ procenv_path_size = snprintf(procenv_path, sizeof(procenv_path),
+ path_template, pid);
+ if (procenv_path_size >= sizeof(procenv_path))
+ return E2BIG;
+
+ fd = open(procenv_path, O_RDONLY | O_CLOEXEC);
+ if (fd < 0)
+ return errno;
+ /*
+ * Mixing error codes from close(2) and open(2) should not lead to any
+ * (access type) confusion for this test.
+ */
+ if (close(fd) != 0)
+ return errno;
+ return 0;
+}
+
+FIXTURE(hierarchy) { };
+
+FIXTURE_VARIANT(hierarchy) {
+ const bool domain_both;
+ const bool domain_parent;
+ const bool domain_child;
+};
+
+/*
+ * Test multiple tracing combinations between a parent process P1 and a child
+ * process P2.
+ *
+ * Yama's scoped ptrace is presumed disabled. If enabled, this optional
+ * restriction is enforced in addition to any Landlock check, which means that
+ * all P2 requests to trace P1 would be denied.
+ */
+
+/*
+ * No domain
+ *
+ * P1-. P1 -> P2 : allow
+ * \ P2 -> P1 : allow
+ * 'P2
+ */
+FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) {
+ .domain_both = false,
+ .domain_parent = false,
+ .domain_child = false,
+};
+
+/*
+ * Child domain
+ *
+ * P1--. P1 -> P2 : allow
+ * \ P2 -> P1 : deny
+ * .'-----.
+ * | P2 |
+ * '------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) {
+ .domain_both = false,
+ .domain_parent = false,
+ .domain_child = true,
+};
+
+/*
+ * Parent domain
+ * .------.
+ * | P1 --. P1 -> P2 : deny
+ * '------' \ P2 -> P1 : allow
+ * '
+ * P2
+ */
+FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) {
+ .domain_both = false,
+ .domain_parent = true,
+ .domain_child = false,
+};
+
+/*
+ * Parent + child domain (siblings)
+ * .------.
+ * | P1 ---. P1 -> P2 : deny
+ * '------' \ P2 -> P1 : deny
+ * .---'--.
+ * | P2 |
+ * '------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) {
+ .domain_both = false,
+ .domain_parent = true,
+ .domain_child = true,
+};
+
+/*
+ * Same domain (inherited)
+ * .-------------.
+ * | P1----. | P1 -> P2 : allow
+ * | \ | P2 -> P1 : allow
+ * | ' |
+ * | P2 |
+ * '-------------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) {
+ .domain_both = true,
+ .domain_parent = false,
+ .domain_child = false,
+};
+
+/*
+ * Inherited + child domain
+ * .-----------------.
+ * | P1----. | P1 -> P2 : allow
+ * | \ | P2 -> P1 : deny
+ * | .-'----. |
+ * | | P2 | |
+ * | '------' |
+ * '-----------------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) {
+ .domain_both = true,
+ .domain_parent = false,
+ .domain_child = true,
+};
+
+/*
+ * Inherited + parent domain
+ * .-----------------.
+ * |.------. | P1 -> P2 : deny
+ * || P1 ----. | P2 -> P1 : allow
+ * |'------' \ |
+ * | ' |
+ * | P2 |
+ * '-----------------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) {
+ .domain_both = true,
+ .domain_parent = true,
+ .domain_child = false,
+};
+
+/*
+ * Inherited + parent and child domain (siblings)
+ * .-----------------.
+ * | .------. | P1 -> P2 : deny
+ * | | P1 . | P2 -> P1 : deny
+ * | '------'\ |
+ * | \ |
+ * | .--'---. |
+ * | | P2 | |
+ * | '------' |
+ * '-----------------'
+ */
+FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) {
+ .domain_both = true,
+ .domain_parent = true,
+ .domain_child = true,
+};
+
+FIXTURE_SETUP(hierarchy)
+{ }
+
+FIXTURE_TEARDOWN(hierarchy)
+{ }
+
+/* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */
+TEST_F(hierarchy, trace)
+{
+ pid_t child, parent;
+ int status, err_proc_read;
+ int pipe_child[2], pipe_parent[2];
+ char buf_parent;
+ long ret;
+
+ /*
+ * Removes all effective and permitted capabilities to not interfere
+ * with cap_ptrace_access_check() in case of PTRACE_MODE_FSCREDS.
+ */
+ drop_caps(_metadata);
+
+ parent = getpid();
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ if (variant->domain_both) {
+ create_domain(_metadata);
+ if (!_metadata->passed)
+ /* Aborts before forking. */
+ return;
+ }
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ char buf_child;
+
+ ASSERT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, close(pipe_child[0]));
+ if (variant->domain_child)
+ create_domain(_metadata);
+
+ /* Waits for the parent to be in a domain, if any. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf_child, 1));
+
+ /* Tests PTRACE_ATTACH and PTRACE_MODE_READ on the parent. */
+ err_proc_read = test_ptrace_read(parent);
+ ret = ptrace(PTRACE_ATTACH, parent, NULL, 0);
+ if (variant->domain_child) {
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EPERM, errno);
+ EXPECT_EQ(EACCES, err_proc_read);
+ } else {
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, err_proc_read);
+ }
+ if (ret == 0) {
+ ASSERT_EQ(parent, waitpid(parent, &status, 0));
+ ASSERT_EQ(1, WIFSTOPPED(status));
+ ASSERT_EQ(0, ptrace(PTRACE_DETACH, parent, NULL, 0));
+ }
+
+ /* Tests child PTRACE_TRACEME. */
+ ret = ptrace(PTRACE_TRACEME);
+ if (variant->domain_parent) {
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EPERM, errno);
+ } else {
+ EXPECT_EQ(0, ret);
+ }
+
+ /*
+ * Signals that the PTRACE_ATTACH test is done and the
+ * PTRACE_TRACEME test is ongoing.
+ */
+ ASSERT_EQ(1, write(pipe_child[1], ".", 1));
+
+ if (!variant->domain_parent) {
+ ASSERT_EQ(0, raise(SIGSTOP));
+ }
+
+ /* Waits for the parent PTRACE_ATTACH test. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf_child, 1));
+ _exit(_metadata->passed ? EXIT_SUCCESS : EXIT_FAILURE);
+ return;
+ }
+
+ ASSERT_EQ(0, close(pipe_child[1]));
+ ASSERT_EQ(0, close(pipe_parent[0]));
+ if (variant->domain_parent)
+ create_domain(_metadata);
+
+ /* Signals that the parent is in a domain, if any. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+
+ /*
+ * Waits for the child to test PTRACE_ATTACH on the parent and start
+ * testing PTRACE_TRACEME.
+ */
+ ASSERT_EQ(1, read(pipe_child[0], &buf_parent, 1));
+
+ /* Tests child PTRACE_TRACEME. */
+ if (!variant->domain_parent) {
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ ASSERT_EQ(1, WIFSTOPPED(status));
+ ASSERT_EQ(0, ptrace(PTRACE_DETACH, child, NULL, 0));
+ } else {
+ /* The child should not be traced by the parent. */
+ EXPECT_EQ(-1, ptrace(PTRACE_DETACH, child, NULL, 0));
+ EXPECT_EQ(ESRCH, errno);
+ }
+
+ /* Tests PTRACE_ATTACH and PTRACE_MODE_READ on the child. */
+ err_proc_read = test_ptrace_read(child);
+ ret = ptrace(PTRACE_ATTACH, child, NULL, 0);
+ if (variant->domain_parent) {
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EPERM, errno);
+ EXPECT_EQ(EACCES, err_proc_read);
+ } else {
+ EXPECT_EQ(0, ret);
+ EXPECT_EQ(0, err_proc_read);
+ }
+ if (ret == 0) {
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ ASSERT_EQ(1, WIFSTOPPED(status));
+ ASSERT_EQ(0, ptrace(PTRACE_DETACH, child, NULL, 0));
+ }
+
+ /* Signals that the parent PTRACE_ATTACH test is done. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ if (WIFSIGNALED(status) || !WIFEXITED(status) ||
+ WEXITSTATUS(status) != EXIT_SUCCESS)
+ _metadata->passed = 0;
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/true.c b/tools/testing/selftests/landlock/true.c
new file mode 100644
index 000000000000..3f9ccbf52783
--- /dev/null
+++ b/tools/testing/selftests/landlock/true.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+int main(void)
+{
+ return 0;
+}