On 7/22/22 1:07 AM, Martin KaFai Lau wrote:
On Thu, Jul 21, 2022 at 12:28:07PM -0500, Frederick Lawler wrote:
The LSM hook userns_create was introduced to provide LSM's an
opportunity to block or allow unprivileged user namespace creation. This
test serves two purposes: it provides a test eBPF implementation, and
tests the hook successfully blocks or allows user namespace creation.
This tests 4 cases:
1. Unattached bpf program does not block unpriv user namespace
creation.
2. Attached bpf program allows user namespace creation given
CAP_SYS_ADMIN privileges.
3. Attached bpf program denies user namespace creation for a
user without CAP_SYS_ADMIN.
4. The sleepable implementation loads
Signed-off-by: Frederick Lawler <fred@xxxxxxxxxxxxxx>
---
The generic deny_namespace file name is used for future namespace
expansion. I didn't want to limit these files to just the create_user_ns
hook.
Changes since v2:
- Rename create_user_ns hook to userns_create
Changes since v1:
- Introduce this patch
---
.../selftests/bpf/prog_tests/deny_namespace.c | 88 +++++++++++++++++++
.../selftests/bpf/progs/test_deny_namespace.c | 39 ++++++++
2 files changed, 127 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/deny_namespace.c
create mode 100644 tools/testing/selftests/bpf/progs/test_deny_namespace.c
diff --git a/tools/testing/selftests/bpf/prog_tests/deny_namespace.c b/tools/testing/selftests/bpf/prog_tests/deny_namespace.c
new file mode 100644
index 000000000000..9e4714295008
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/deny_namespace.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include "test_deny_namespace.skel.h"
+#include <sched.h>
+#include "cap_helpers.h"
+
+#define STACK_SIZE (1024 * 1024)
Does the child need 1M stack space ?
No, I can reduce that.
+static char child_stack[STACK_SIZE];
+
+int clone_callback(void *arg)
static
+{
+ return 0;
+}
+
+static int create_new_user_ns(void)
+{
+ int status;
+ pid_t cpid;
+
+ cpid = clone(clone_callback, child_stack + STACK_SIZE,
+ CLONE_NEWUSER | SIGCHLD, NULL);
+
+ if (cpid == -1)
+ return errno;
+
+ if (cpid == 0)
Not an expert in clone() call and it is not clear what 0
return value mean from the man page. Could you explain ?
Good catch. This is using the libc clone().
+ return 0;
+
+ waitpid(cpid, &status, 0);
+ if (WIFEXITED(status))
+ return WEXITSTATUS(status);
+
+ return -1;
+}
+
+static void test_userns_create_bpf(void)
+{
+ __u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+ __u64 old_caps = 0;
+
+ ASSERT_OK(create_new_user_ns(), "priv new user ns");
Does it need to enable CAP_SYS_ADMIN first ?
You're right, this should be more explicitly set. I ran tests with the
vmtest.sh script supplied with sefltests/bpf which run under root. I
should always set CAP_SYS_ADMIN here to be consistent.
+
+ cap_disable_effective(cap_mask, &old_caps);
+
+ ASSERT_EQ(create_new_user_ns(), EPERM, "unpriv new user ns");
+
+ if (cap_mask & old_caps)
+ cap_enable_effective(cap_mask, NULL);
+}
+
+static void test_unpriv_userns_create_no_bpf(void)
+{
+ __u32 cap_mask = 1ULL << CAP_SYS_ADMIN;
+ __u64 old_caps = 0;
+
+ cap_disable_effective(cap_mask, &old_caps);
+
+ ASSERT_OK(create_new_user_ns(), "no-bpf unpriv new user ns");
+
+ if (cap_mask & old_caps)
+ cap_enable_effective(cap_mask, NULL);
+}
+
+void test_deny_namespace(void)
+{
+ struct test_deny_namespace *skel = NULL;
+ int err;
+
+ if (test__start_subtest("unpriv_userns_create_no_bpf"))
+ test_unpriv_userns_create_no_bpf();
+
+ skel = test_deny_namespace__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel load"))
+ goto close_prog;
+
+ err = test_deny_namespace__attach(skel);
+ if (!ASSERT_OK(err, "attach"))
+ goto close_prog;
+
+ if (test__start_subtest("userns_create_bpf"))
+ test_userns_create_bpf();
+
+ test_deny_namespace__detach(skel);
+
+close_prog:
+ test_deny_namespace__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
new file mode 100644
index 000000000000..9ec9dabc8372
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+#include <linux/capability.h>
+
+struct kernel_cap_struct {
+ __u32 cap[_LINUX_CAPABILITY_U32S_3];
+} __attribute__((preserve_access_index));
+
+struct cred {
+ struct kernel_cap_struct cap_effective;
+} __attribute__((preserve_access_index));
+
+char _license[] SEC("license") = "GPL";
+
+SEC("lsm/userns_create")
+int BPF_PROG(test_userns_create, const struct cred *cred, int ret)
+{
+ struct kernel_cap_struct caps = cred->cap_effective;
+ int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN);
+ __u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN);
+
+ if (ret)
+ return 0;
+
+ ret = -EPERM;
+ if (caps.cap[cap_index] & cap_mask)
+ return 0;
+
+ return -EPERM;
+}
+
+SEC("lsm.s/userns_create")
+int BPF_PROG(test_sleepable_userns_create, const struct cred *cred, int ret)
+{
An empty program is weird. If the intention is
to ensure a sleepable program can attach to userns_create,
move the test logic here and remove the non-sleepable
program above.
Sure, I can do that.
+ return 0;
+}
--
2.30.2
