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

9 files changed, 3616 insertions, 0 deletions

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 _m