// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2022 Google */

#include <test_progs.h>
#include <bpf/libbpf.h>
#include <bpf/btf.h>
#include "iters_css_task.skel.h"
#include "cgroup_iter.skel.h"
#include "cgroup_helpers.h"

#define ROOT           0
#define PARENT         1
#define CHILD1         2
#define CHILD2         3
#define NUM_CGROUPS    4

#define PROLOGUE       "prologue\n"
#define EPILOGUE       "epilogue\n"

static const char *cg_path[] = {
	"/", "/parent", "/parent/child1", "/parent/child2"
};

static int cg_fd[] = {-1, -1, -1, -1};
static unsigned long long cg_id[] = {0, 0, 0, 0};
static char expected_output[64];

static int setup_cgroups(void)
{
	int fd, i = 0;

	for (i = 0; i < NUM_CGROUPS; i++) {
		fd = create_and_get_cgroup(cg_path[i]);
		if (fd < 0)
			return fd;

		cg_fd[i] = fd;
		cg_id[i] = get_cgroup_id(cg_path[i]);
	}
	return 0;
}

static void cleanup_cgroups(void)
{
	int i;

	for (i = 0; i < NUM_CGROUPS; i++)
		close(cg_fd[i]);
}

static void read_from_cgroup_iter(struct bpf_program *prog, int cgroup_fd,
				  int order, const char *testname)
{
	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
	union bpf_iter_link_info linfo;
	struct bpf_link *link;
	int len, iter_fd;
	static char buf[128];
	size_t left;
	char *p;

	memset(&linfo, 0, sizeof(linfo));
	linfo.cgroup.cgroup_fd = cgroup_fd;
	linfo.cgroup.order = order;
	opts.link_info = &linfo;
	opts.link_info_len = sizeof(linfo);

	link = bpf_program__attach_iter(prog, &opts);
	if (!ASSERT_OK_PTR(link, "attach_iter"))
		return;

	iter_fd = bpf_iter_create(bpf_link__fd(link));
	if (iter_fd < 0)
		goto free_link;

	memset(buf, 0, sizeof(buf));
	left = ARRAY_SIZE(buf);
	p = buf;
	while ((len = read(iter_fd, p, left)) > 0) {
		p += len;
		left -= len;
	}

	ASSERT_STREQ(buf, expected_output, testname);

	/* read() after iter finishes should be ok. */
	if (len == 0)
		ASSERT_OK(read(iter_fd, buf, sizeof(buf)), "second_read");

	close(iter_fd);
free_link:
	bpf_link__destroy(link);
}

/* Invalid cgroup. */
static void test_invalid_cgroup(struct cgroup_iter *skel)
{
	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
	union bpf_iter_link_info linfo;
	struct bpf_link *link;

	memset(&linfo, 0, sizeof(linfo));
	linfo.cgroup.cgroup_fd = (__u32)-1;
	opts.link_info = &linfo;
	opts.link_info_len = sizeof(linfo);

	link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
	ASSERT_ERR_PTR(link, "attach_iter");
	bpf_link__destroy(link);
}

/* Specifying both cgroup_fd and cgroup_id is invalid. */
static void test_invalid_cgroup_spec(struct cgroup_iter *skel)
{
	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
	union bpf_iter_link_info linfo;
	struct bpf_link *link;

	memset(&linfo, 0, sizeof(linfo));
	linfo.cgroup.cgroup_fd = (__u32)cg_fd[PARENT];
	linfo.cgroup.cgroup_id = (__u64)cg_id[PARENT];
	opts.link_info = &linfo;
	opts.link_info_len = sizeof(linfo);

	link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
	ASSERT_ERR_PTR(link, "attach_iter");
	bpf_link__destroy(link);
}

/* Preorder walk prints parent and child in order. */
static void test_walk_preorder(struct cgroup_iter *skel)
{
	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
		 cg_id[PARENT], cg_id[CHILD1], cg_id[CHILD2]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_DESCENDANTS_PRE, "preorder");
}

/* Postorder walk prints child and parent in order. */
static void test_walk_postorder(struct cgroup_iter *skel)
{
	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n%8llu\n%8llu\n" EPILOGUE,
		 cg_id[CHILD1], cg_id[CHILD2], cg_id[PARENT]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_DESCENDANTS_POST, "postorder");
}

/* Walking parents prints parent and then root. */
static void test_walk_ancestors_up(struct cgroup_iter *skel)
{
	/* terminate the walk when ROOT is met. */
	skel->bss->terminal_cgroup = cg_id[ROOT];

	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n%8llu\n" EPILOGUE,
		 cg_id[PARENT], cg_id[ROOT]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_ANCESTORS_UP, "ancestors_up");

	skel->bss->terminal_cgroup = 0;
}

/* Early termination prints parent only. */
static void test_early_termination(struct cgroup_iter *skel)
{
	/* terminate the walk after the first element is processed. */
	skel->bss->terminate_early = 1;

	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_DESCENDANTS_PRE, "early_termination");

	skel->bss->terminate_early = 0;
}

/* Waling self prints self only. */
static void test_walk_self_only(struct cgroup_iter *skel)
{
	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n" EPILOGUE, cg_id[PARENT]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_SELF_ONLY, "self_only");
}

static void test_walk_children(struct cgroup_iter *skel)
{
	snprintf(expected_output, sizeof(expected_output),
		 PROLOGUE "%8llu\n%8llu\n" EPILOGUE, cg_id[CHILD1],
		 cg_id[CHILD2]);

	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[PARENT],
			      BPF_CGROUP_ITER_CHILDREN, "children");
}

static void test_walk_dead_self_only(struct cgroup_iter *skel)
{
	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
	char expected_output[128], buf[128];
	const char *cgrp_name = "/dead";
	union bpf_iter_link_info linfo;
	int len, cgrp_fd, iter_fd;
	struct bpf_link *link;
	size_t left;
	char *p;

	cgrp_fd = create_and_get_cgroup(cgrp_name);
	if (!ASSERT_GE(cgrp_fd, 0, "create cgrp"))
		return;

	/* The cgroup will be dead during read() iteration, so it only has
	 * epilogue in the output
	 */
	snprintf(expected_output, sizeof(expected_output), EPILOGUE);

	memset(&linfo, 0, sizeof(linfo));
	linfo.cgroup.cgroup_fd = cgrp_fd;
	linfo.cgroup.order = BPF_CGROUP_ITER_SELF_ONLY;
	opts.link_info = &linfo;
	opts.link_info_len = sizeof(linfo);

	link = bpf_program__attach_iter(skel->progs.cgroup_id_printer, &opts);
	if (!ASSERT_OK_PTR(link, "attach_iter"))
		goto close_cgrp;

	iter_fd = bpf_iter_create(bpf_link__fd(link));
	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
		goto free_link;

	/* Close link fd and cgroup fd */
	bpf_link__destroy(link);
	close(cgrp_fd);

	/* Remove cgroup to mark it as dead */
	remove_cgroup(cgrp_name);

	/* Two kern_sync_rcu() and usleep() pairs are used to wait for the
	 * releases of cgroup css, and the last kern_sync_rcu() and usleep()
	 * pair is used to wait for the free of cgroup itself.
	 */
	kern_sync_rcu();
	usleep(8000);
	kern_sync_rcu();
	usleep(8000);
	kern_sync_rcu();
	usleep(1000);

	memset(buf, 0, sizeof(buf));
	left = ARRAY_SIZE(buf);
	p = buf;
	while ((len = read(iter_fd, p, left)) > 0) {
		p += len;
		left -= len;
	}

	ASSERT_STREQ(buf, expected_output, "dead cgroup output");

	/* read() after iter finishes should be ok. */
	if (len == 0)
		ASSERT_OK(read(iter_fd, buf, sizeof(buf)), "second_read");

	close(iter_fd);
	return;
free_link:
	bpf_link__destroy(link);
close_cgrp:
	close(cgrp_fd);
}

static void test_walk_self_only_css_task(void)
{
	struct iters_css_task *skel;
	int err;

	skel = iters_css_task__open();
	if (!ASSERT_OK_PTR(skel, "skel_open"))
		return;

	bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);

	err = iters_css_task__load(skel);
	if (!ASSERT_OK(err, "skel_load"))
		goto cleanup;

	err = join_cgroup(cg_path[CHILD2]);
	if (!ASSERT_OK(err, "join_cgroup"))
		goto cleanup;

	skel->bss->target_pid = getpid();
	snprintf(expected_output, sizeof(expected_output),
		PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
		BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
cleanup:
	iters_css_task__destroy(skel);
}

void test_cgroup_iter(void)
{
	struct cgroup_iter *skel = NULL;

	if (setup_cgroup_environment())
		return;

	if (setup_cgroups())
		goto out;

	skel = cgroup_iter__open_and_load();
	if (!ASSERT_OK_PTR(skel, "cgroup_iter__open_and_load"))
		goto out;

	if (test__start_subtest("cgroup_iter__invalid_cgroup"))
		test_invalid_cgroup(skel);
	if (test__start_subtest("cgroup_iter__invalid_cgroup_spec"))
		test_invalid_cgroup_spec(skel);
	if (test__start_subtest("cgroup_iter__preorder"))
		test_walk_preorder(skel);
	if (test__start_subtest("cgroup_iter__postorder"))
		test_walk_postorder(skel);
	if (test__start_subtest("cgroup_iter__ancestors_up_walk"))
		test_walk_ancestors_up(skel);
	if (test__start_subtest("cgroup_iter__early_termination"))
		test_early_termination(skel);
	if (test__start_subtest("cgroup_iter__self_only"))
		test_walk_self_only(skel);
	if (test__start_subtest("cgroup_iter__dead_self_only"))
		test_walk_dead_self_only(skel);
	if (test__start_subtest("cgroup_iter__self_only_css_task"))
		test_walk_self_only_css_task();
	if (test__start_subtest("cgroup_iter__children"))
		test_walk_children(skel);

out:
	cgroup_iter__destroy(skel);
	cleanup_cgroups();
	cleanup_cgroup_environment();
}