This adds a selftest for `bpf_cgroup_write_interface` kfunc. The test works by forking a child then:
1. Child: - Migrate to a new cgroup - Loads bpf programs - Trigger the 'lsm_freeze_cgroup' bpf program so it freeze itself.
<- wait for parent to unthaw
- On unthaw it continues, forks another process and triggers the 'tp_newchild' bpf program to set some monitored pids of the new process, that assert that the user space resumed correctly.
2. Parent: - Keeps reading the 'cgroup.freeze' file of the child cgroup until it prints 1 which means the child cgroup is frozen. - Attaches the sample 'lsm_task_free' so it triggers the bpf program to unthaw the child task cgroup. - Then waits for a clean exit of the child process.
The scenario allows to test multiple sides of: freeze and unthaw a cgroup.
Signed-off-by: Djalal Harouni tixxdz@gmail.com --- .../bpf/prog_tests/task_freeze_cgroup.c | 172 ++++++++++++++++++ .../bpf/progs/test_task_freeze_cgroup.c | 155 ++++++++++++++++ 2 files changed, 327 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c create mode 100644 tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c
diff --git a/tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c new file mode 100644 index 000000000000..d4e9c0f32196 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_freeze_cgroup.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <sys/syscall.h> +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <unistd.h> +#include "test_task_freeze_cgroup.skel.h" + +#define CGROUP_PATH "/test-task-freeze-cgroup" + +static int bpf_sleepable(struct test_task_freeze_cgroup *skel) +{ + int err, cgroup_fd; + pid_t new_pid2; + + cgroup_fd = cgroup_setup_and_join(CGROUP_PATH); + if (!ASSERT_OK(cgroup_fd < 0, "cgroup_setup_and_join")) + return -errno; + + skel = test_task_freeze_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_freeze_cgroup__open")) { + err = -errno; + goto cleanup_cgroup; + } + + skel->rodata->parent_pid = getppid(); + skel->rodata->monitor_pid = getpid(); + skel->rodata->cgid = get_cgroup_id(CGROUP_PATH); + skel->bss->new_pid = getpid(); + skel->bss->freeze = 1; + + err = test_task_freeze_cgroup__load(skel); + if (!ASSERT_OK(err, "test_task_freeze_cgroup__load")) { + err = -errno; + goto cleanup_skel; + } + + /* First attach the LSM Program that is triggered on bpf() calls + * especially on TP_BTF programs when attached. + */ + skel->links.lsm_freeze_cgroup = + bpf_program__attach_lsm(skel->progs.lsm_freeze_cgroup); + if (!ASSERT_OK_PTR(skel->links.lsm_freeze_cgroup, "attach_lsm")) { + err = -errno; + goto cleanup_detach; + } + + /* Attaching this must fail with -EPERM and freeze current task */ + skel->links.tp_newchild = + bpf_program__attach_trace(skel->progs.tp_newchild); + if (!ASSERT_EQ(errno, EPERM, "attach_trace() must fail here")) { + err = -EINVAL; + goto cleanup_detach; + } + + /* Continue */ + + /* Attach again now with success */ + skel->links.tp_newchild = + bpf_program__attach_trace(skel->progs.tp_newchild); + if (!ASSERT_OK_PTR(skel->links.tp_newchild, "attach_trace")) { + err = -EINVAL; + goto cleanup_detach; + } + + /* Fork, update vars from BPF and assert the unfrozen state */ + new_pid2 = fork(); + if (new_pid2 == 0) + exit(0); + + err = (new_pid2 == -1); + if (ASSERT_OK(err, "fork process")) + wait(NULL); + + /* Now assert that new_pid2 reflects this new child */ + ASSERT_NEQ(0, skel->bss->new_pid, + "test task_freeze_cgroup failed at new_pid != 0"); + ASSERT_NEQ(skel->rodata->monitor_pid, skel->bss->new_pid, + "test task_freeze_cgroup failed at old monitor_pid != new_pid"); + /* Assert that bpf sets new_pid to new forked child new_pid2 */ + ASSERT_EQ(skel->bss->new_pid, new_pid2, + "test task_freeze_cgroup failed first child new_pid == new_pid2"); + +cleanup_detach: + test_task_freeze_cgroup__detach(skel); +cleanup_skel: + test_task_freeze_cgroup__destroy(skel); +cleanup_cgroup: + close(cgroup_fd); + cleanup_cgroup_environment(); + return err; +} + +void test_task_freeze_cgroup(void) +{ + pid_t pid, result; + char buf[512] = {0}; + char path[PATH_MAX] = {0}; + int ret, status, attempts, frozen = 0, fd; + struct test_task_freeze_cgroup *skel = NULL; + + pid = fork(); + ret = (pid == -1); + if (!ASSERT_OK(ret, "fork process")) + return; + + if (pid == 0) { + ret = bpf_sleepable(skel); + ASSERT_EQ(0, ret, "child bpf_sleepable failed"); + exit(ret); + } + + skel = test_task_freeze_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_freeze_cgroup__open")) + goto out; + + snprintf(path, sizeof(path), + "/sys/fs/cgroup/cgroup-test-work-dir%d%s/cgroup.freeze", + pid, CGROUP_PATH); + + for (attempts = 10; attempts >= 0; attempts--) { + ret = 0; + + fd = open(path, O_RDONLY); + if (fd > 0) + ret = read(fd, buf, sizeof(buf) - 1); + if (ret > 0) { + errno = 0; + frozen = strtol(buf, NULL, 10); + if (errno) + frozen = 0; + } + + close(fd); + if (frozen) + break; + sleep(1); + } + + /* Assert that child cgroup is frozen */ + if (!ASSERT_EQ(1, frozen, "child cgroup not frozen")) + goto out; + + ret = test_task_freeze_cgroup__load(skel); + if (!ASSERT_OK(ret, "test_task_freeze_cgroup__load")) + goto out; + + /* Trigger the unthaw child cgroup from parent */ + skel->links.lsm_task_free = + bpf_program__attach_lsm(skel->progs.lsm_task_free); + if (!ASSERT_OK_PTR(skel->links.lsm_task_free, "attach_lsm")) + goto out; + + result = waitpid(pid, &status, WUNTRACED); + if (!ASSERT_NEQ(result, -1, "waitpid")) + goto detach; + + result = WIFEXITED(status); + if (!ASSERT_EQ(result, 1, "forked process did not terminate normally")) + goto detach; + + result = WEXITSTATUS(status); + if (!ASSERT_EQ(result, 0, "forked process did not exit successfully")) + goto detach; + +detach: + test_task_freeze_cgroup__detach(skel); + +out: + if (skel) + test_task_freeze_cgroup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c new file mode 100644 index 000000000000..07b4b65abc36 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_freeze_cgroup.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <linux/types.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <errno.h> +#include "bpf_kfuncs.h" +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +extern int bpf_cgroup_write_interface(struct cgroup *cgrp, + const char *name__str, + const struct bpf_dynptr *value_p, + loff_t off) __ksym __weak; + +char freeze_val[] = "1"; +char unthaw_val[] = "0"; + +const volatile int parent_pid; +const volatile int monitor_pid; +const volatile __u64 cgid; +int new_pid; +int freeze; + +SEC("tp_btf/task_newtask") +int BPF_PROG(tp_newchild, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (monitor_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + /* Update new_pid with current pid */ + if (bpf_task_under_cgroup(acquired, cgrp)) + new_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +/* Try to attach from parent to trigger the bpf lsm hook, so from + * parent context we unthaw child cgroup. + */ +SEC("lsm/task_free") +int BPF_PROG(lsm_task_free, struct task_struct *task) +{ + return 0; +} + +static int process_freeze_cgroup(int pid, int freeze) +{ + int ret = 0; + struct task_struct *task; + struct bpf_dynptr dyn_ptr; + struct cgroup *cgrp = NULL; + + task = bpf_task_from_pid(pid); + if (!task) + return -EINVAL; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) { + ret = -EINVAL; + goto out; + } + + if (!bpf_task_under_cgroup(task, cgrp)) + goto out; + + if (freeze) + bpf_dynptr_from_mem(freeze_val, sizeof(freeze_val), 0, &dyn_ptr); + else + bpf_dynptr_from_mem(unthaw_val, sizeof(unthaw_val), 0, &dyn_ptr); + + ret = bpf_cgroup_write_interface(cgrp, "cgroup.freeze", &dyn_ptr, 0); + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(task); + return ret; +} + +SEC("lsm.s/bpf") +int BPF_PROG(lsm_freeze_cgroup, int cmd, union bpf_attr *attr, unsigned int size) +{ + int ret = 0; + struct task_struct *task; + struct cgroup *cgrp = NULL; + + if (cmd != BPF_LINK_CREATE) + return 0; + + task = bpf_get_current_task_btf(); + if (parent_pid == task->pid) { + /* Parent context: unthaw child */ + process_freeze_cgroup(monitor_pid, 0); + return 0; + } + + /* Nothing todo */ + if (!freeze) + return 0; + + /* Child context */ + if (monitor_pid != task->pid) + return 0; + + /* Ensure we are under the corresponding cgroup so we freeze + * current child from its context + */ + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + return 0; + + if (!bpf_task_under_cgroup(task, cgrp)) + goto out; + + /* Schedule freeze task and return -EPERM */ + ret = process_freeze_cgroup(monitor_pid, freeze); + + /* On error or 0 we return zero and we catch at + * user space if the cgroup was not frozen. + */ + ret = (ret > 0) ? -EPERM : 0; + + /* Reset for next calls */ + freeze = 0; +out: + if (cgrp) + bpf_cgroup_release(cgrp); + return ret; +} + +char _license[] SEC("license") = "GPL";