selftests/bpf: Add tests for open-coded task and css iter

This patch adds 4 subtests to demonstrate these patterns and validating
correctness.

subtest1:

1) We use task_iter to iterate all process in the system and search for the
current process with a given pid.

2) We create some threads in current process context, and use
BPF_TASK_ITER_PROC_THREADS to iterate all threads of current process. As
expected, we would find all the threads of current process.

3) We create some threads and use BPF_TASK_ITER_ALL_THREADS to iterate all
threads in the system. As expected, we would find all the threads which was
created.

subtest2:

We create a cgroup and add the current task to the cgroup. In the
BPF program, we would use bpf_for_each(css_task, task, css) to iterate all
tasks under the cgroup. As expected, we would find the current process.

subtest3:

1) We create a cgroup tree. In the BPF program, we use
bpf_for_each(css, pos, root, XXX) to iterate all descendant under the root
with pre and post order. As expected, we would find all descendant and the
last iterating cgroup in post-order is root cgroup, the first iterating
cgroup in pre-order is root cgroup.

2) We wse BPF_CGROUP_ITER_ANCESTORS_UP to traverse the cgroup tree starting
from leaf and root separately, and record the height. The diff of the
hights would be the total tree-high - 1.

subtest4:

Add some failure testcase when using css_task, task and css iters, e.g,
unlock when using task-iters to iterate tasks.

Signed-off-by: Chuyi Zhou <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

tools/testing/selftests/bpf/prog_tests/iters.c

···
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
 
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <malloc.h>
+#include <stdlib.h>
 #include <test_progs.h>
+#include "cgroup_helpers.h"
 
 #include "iters.skel.h"
 #include "iters_state_safety.skel.h"
···
 #include "iters_num.skel.h"
 #include "iters_testmod_seq.skel.h"
 #include "iters_task_vma.skel.h"
+#include "iters_task.skel.h"
+#include "iters_css_task.skel.h"
+#include "iters_css.skel.h"
+#include "iters_task_failure.skel.h"
 
 static void subtest_num_iters(void)
 {
···
 	iters_task_vma__destroy(skel);
 }
 
+static pthread_mutex_t do_nothing_mutex;
+
+static void *do_nothing_wait(void *arg)
+{
+	pthread_mutex_lock(&do_nothing_mutex);
+	pthread_mutex_unlock(&do_nothing_mutex);
+
+	pthread_exit(arg);
+}
+
+#define thread_num 2
+
+static void subtest_task_iters(void)
+{
+	struct iters_task *skel = NULL;
+	pthread_t thread_ids[thread_num];
+	void *ret;
+	int err;
+
+	skel = iters_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+	skel->bss->target_pid = getpid();
+	err = iters_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	pthread_mutex_lock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL),
+			"pthread_create");
+
+	syscall(SYS_getpgid);
+	iters_task__detach(skel);
+	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
+	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt");
+	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt");
+	pthread_mutex_unlock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
+cleanup:
+	iters_task__destroy(skel);
+}
+
+extern int stack_mprotect(void);
+
+static void subtest_css_task_iters(void)
+{
+	struct iters_css_task *skel = NULL;
+	int err, cg_fd, cg_id;
+	const char *cgrp_path = "/cg1";
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	cg_fd = create_and_get_cgroup(cgrp_path);
+	if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup"))
+		goto cleanup;
+	cg_id = get_cgroup_id(cgrp_path);
+	err = join_cgroup(cgrp_path);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel = iters_css_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->cg_id = cg_id;
+	err = iters_css_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	err = stack_mprotect();
+	if (!ASSERT_EQ(err, -1, "stack_mprotect") ||
+	    !ASSERT_EQ(errno, EPERM, "stack_mprotect"))
+		goto cleanup;
+	iters_css_task__detach(skel);
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css_task__destroy(skel);
+}
+
+static void subtest_css_iters(void)
+{
+	struct iters_css *skel = NULL;
+	struct {
+		const char *path;
+		int fd;
+	} cgs[] = {
+		{ "/cg1" },
+		{ "/cg1/cg2" },
+		{ "/cg1/cg2/cg3" },
+		{ "/cg1/cg2/cg3/cg4" },
+	};
+	int err, cg_nr = ARRAY_SIZE(cgs);
+	int i;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	for (i = 0; i < cg_nr; i++) {
+		cgs[i].fd = create_and_get_cgroup(cgs[i].path);
+		if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup"))
+			goto cleanup;
+	}
+
+	skel = iters_css__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->root_cg_id = get_cgroup_id(cgs[0].path);
+	skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path);
+	err = iters_css__attach(skel);
+
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+
+	syscall(SYS_getpgid);
+	ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt");
+	ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id");
+
+	ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt");
+	ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id");
+	ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high");
+	iters_css__detach(skel);
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css__destroy(skel);
+}
+
 void test_iters(void)
 {
 	RUN_TESTS(iters_state_safety);
···
 		subtest_testmod_seq_iters();
 	if (test__start_subtest("task_vma"))
 		subtest_task_vma_iters();
+	if (test__start_subtest("task"))
+		subtest_task_iters();
+	if (test__start_subtest("css_task"))
+		subtest_css_task_iters();
+	if (test__start_subtest("css"))
+		subtest_css_iters();
+	RUN_TESTS(iters_task_failure);
 }

tools/testing/selftests/bpf/progs/iters_css.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <[e-mail]> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+u64 root_cg_id, leaf_cg_id;
+u64 first_cg_id, last_cg_id;
+
+int pre_order_cnt, post_order_cnt, tree_high;
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_css_for_each(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *root_css, *leaf_css, *pos;
+	struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+
+	root_cgrp = bpf_cgroup_from_id(root_cg_id);
+
+	if (!root_cgrp)
+		return 0;
+
+	leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id);
+
+	if (!leaf_cgrp) {
+		bpf_cgroup_release(root_cgrp);
+		return 0;
+	}
+	root_css = &root_cgrp->self;
+	leaf_css = &leaf_cgrp->self;
+	pre_order_cnt = post_order_cnt = tree_high = 0;
+	first_cg_id = last_cg_id = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		cur_cgrp = pos->cgroup;
+		post_order_cnt++;
+		last_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) {
+		cur_cgrp = pos->cgroup;
+		pre_order_cnt++;
+		if (!first_cg_id)
+			first_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high++;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high--;
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(root_cgrp);
+	bpf_cgroup_release(leaf_cgrp);
+	return 0;
+}

tools/testing/selftests/bpf/progs/iters_css_task.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <[e-mail]> */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+
+pid_t target_pid;
+int css_task_cnt;
+u64 cg_id;
+
+SEC("lsm/file_mprotect")
+int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
+	    unsigned long reqprot, unsigned long prot, int ret)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (cur_task->pid != target_pid)
+		return ret;
+
+	cgrp = bpf_cgroup_from_id(cg_id);
+
+	if (!cgrp)
+		return -EPERM;
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS)
+		if (task->pid == target_pid)
+			css_task_cnt++;
+
+	bpf_cgroup_release(cgrp);
+
+	return -EPERM;
+}

tools/testing/selftests/bpf/progs/iters_task.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <[e-mail]> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+int procs_cnt, threads_cnt, proc_threads_cnt;
+
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_task_for_each_sleep(void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct task_struct *pos;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+	procs_cnt = threads_cnt = proc_threads_cnt = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
+		if (pos->pid == target_pid)
+			procs_cnt++;
+
+	bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS)
+		proc_threads_cnt++;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS)
+		if (pos->tgid == target_pid)
+			threads_cnt++;
+	bpf_rcu_read_unlock();
+	return 0;
+}

tools/testing/selftests/bpf/progs/iters_task_failure.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <[e-mail]> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+int BPF_PROG(iter_tasks_without_lock)
+{
+	struct task_struct *pos;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+
+	}
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+int BPF_PROG(iter_css_without_lock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+int BPF_PROG(iter_tasks_lock_and_unlock)
+{
+	struct task_struct *pos;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+int BPF_PROG(iter_css_lock_and_unlock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+int BPF_PROG(iter_css_task_for_each)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}