@@ -1,13 +1,24 @@
// 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_looping.skel.h"
#include "iters_num.skel.h"
#include "iters_testmod_seq.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)
{
@@ -90,6 +101,149 @@ static void subtest_testmod_seq_iters(void)
iters_testmod_seq__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();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+ err = iters_task__load(skel);
+ if (!ASSERT_OK(err, "skel_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->process_cnt, 1, "process_cnt");
+ ASSERT_EQ(skel->bss->thread_cnt, thread_num + 1, "thread_cnt");
+ ASSERT_EQ(skel->bss->all_thread_cnt, thread_num + 1, "all_thread_cnt");
+ pthread_mutex_unlock(&do_nothing_mutex);
+ for (int i = 0; i < thread_num; i++)
+ pthread_join(thread_ids[i], &ret);
+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, "cg_create"))
+ goto cleanup;
+ cg_id = get_cgroup_id(cgrp_path);
+ err = join_cgroup(cgrp_path);
+ if (!ASSERT_OK(err, "setup_cgroup_environment"))
+ goto cleanup;
+
+ skel = iters_css_task__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+
+ err = iters_css_task__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ skel->bss->target_pid = getpid();
+ skel->bss->cg_id = cg_id;
+ err = iters_css_task__attach(skel);
+
+ err = stack_mprotect();
+ if (!ASSERT_OK(err, "iters_task__attach"))
+ 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, "cg_create"))
+ goto cleanup;
+ }
+
+ skel = iters_css__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ goto cleanup;
+ err = iters_css__load(skel);
+ if (!ASSERT_OK(err, "skel_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_css_dec_cnt, cg_nr, "pre order search dec count");
+ ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path),
+ "pre order search first cgroup id");
+
+ ASSERT_EQ(skel->bss->post_css_dec_cnt, cg_nr, "post order search dec count");
+ ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path),
+ "post order search last cgroup 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);
@@ -103,4 +257,11 @@ void test_iters(void)
subtest_num_iters();
if (test__start_subtest("testmod_seq"))
subtest_testmod_seq_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);
}
new file mode 100644
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#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 = 0;
+u64 root_cg_id;
+u64 leaf_cg_id;
+
+u64 last_cg_id = 0;
+u64 first_cg_id = 0;
+
+int post_css_dec_cnt = 0;
+int pre_css_dec_cnt = 0;
+int tree_high = 0;
+
+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;
+ bpf_rcu_read_lock();
+ bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+ cur_cgrp = pos->cgroup;
+ post_css_dec_cnt += 1;
+ last_cg_id = cur_cgrp->kn->id;
+ }
+
+ bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) {
+ cur_cgrp = pos->cgroup;
+ pre_css_dec_cnt += 1;
+ 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 += 1;
+
+ bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+ tree_high -= 1;
+ bpf_rcu_read_unlock();
+ bpf_cgroup_release(root_cgrp);
+ bpf_cgroup_release(leaf_cgrp);
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#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;
+
+pid_t target_pid = 0;
+int css_task_cnt = 0;
+u64 cg_id;
+
+SEC("lsm/file_mprotect")
+int BPF_PROG(iter_css_task_for_each)
+{
+ 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 0;
+
+ cgrp = bpf_cgroup_from_id(cg_id);
+
+ if (cgrp == NULL)
+ return 0;
+ css = &cgrp->self;
+
+ bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS)
+ if (task->pid == target_pid)
+ css_task_cnt += 1;
+
+ bpf_cgroup_release(cgrp);
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#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 = 0;
+int process_cnt = 0;
+int thread_cnt = 0;
+int all_thread_cnt = 0;
+
+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;
+ bpf_rcu_read_lock();
+ bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
+ if (pos->pid == target_pid)
+ process_cnt += 1;
+
+ bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS)
+ thread_cnt += 1;
+
+ bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS)
+ if (pos->tgid == target_pid)
+ all_thread_cnt += 1;
+ bpf_rcu_read_unlock();
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#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;
+}
This patch adds three 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. Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com> --- .../testing/selftests/bpf/prog_tests/iters.c | 161 ++++++++++++++++++ tools/testing/selftests/bpf/progs/iters_css.c | 74 ++++++++ .../selftests/bpf/progs/iters_css_task.c | 42 +++++ .../testing/selftests/bpf/progs/iters_task.c | 41 +++++ .../selftests/bpf/progs/iters_task_failure.c | 105 ++++++++++++ 5 files changed, 423 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/iters_css.c create mode 100644 tools/testing/selftests/bpf/progs/iters_css_task.c create mode 100644 tools/testing/selftests/bpf/progs/iters_task.c create mode 100644 tools/testing/selftests/bpf/progs/iters_task_failure.c