path: root/tools/testing/selftests/cgroup/test_core.c

/* SPDX-License-Identifier: GPL-2.0 */

#define _GNU_SOURCE
#include <linux/limits.h>
#include <linux/sched.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/wait.h>
#include <unistd.h>
#include <fcntl.h>
#include <sched.h>
#include <stdio.h>
#include <errno.h>
#include <signal.h>
#include <string.h>
#include <pthread.h>

#include "kselftest.h"
#include "cgroup_util.h"

static bool nsdelegate;
#ifndef CLONE_NEWCGROUP
#define CLONE_NEWCGROUP 0
#endif

static int touch_anon(char *buf, size_t size)
{
	int fd;
	char *pos = buf;

	fd = open("/dev/urandom", O_RDONLY);
	if (fd < 0)
		return -1;

	while (size > 0) {
		ssize_t ret = read(fd, pos, size);

		if (ret < 0) {
			if (errno != EINTR) {
				close(fd);
				return -1;
			}
		} else {
			pos += ret;
			size -= ret;
		}
	}
	close(fd);

	return 0;
}

static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg)
{
	int ppid = getppid();
	size_t size = (size_t)arg;
	void *buf;

	buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
		   0, 0);
	if (buf == MAP_FAILED)
		return -1;

	if (touch_anon((char *)buf, size)) {
		munmap(buf, size);
		return -1;
	}

	while (getppid() == ppid)
		sleep(1);

	munmap(buf, size);
	return 0;
}

/*
 * Create a child process that allocates and touches 100MB, then waits to be
 * killed. Wait until the child is attached to the cgroup, kill all processes
 * in that cgroup and wait until "cgroup.procs" is empty. At this point try to
 * destroy the empty cgroup. The test helps detect race conditions between
 * dying processes leaving the cgroup and cgroup destruction path.
 */
static int test_cgcore_destroy(const char *root)
{
	int ret = KSFT_FAIL;
	char *cg_test = NULL;
	int child_pid;
	char buf[PAGE_SIZE];

	cg_test = cg_name(root, "cg_test");

	if (!cg_test)
		goto cleanup;

	for (int i = 0; i < 10; i++) {
		if (cg_create(cg_test))
			goto cleanup;

		child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit,
					  (void *) MB(100));

		if (child_pid < 0)
			goto cleanup;

		/* wait for the child to enter cgroup */
		if (cg_wait_for_proc_count(cg_test, 1))
			goto cleanup;

		if (cg_killall(cg_test))
			goto cleanup;

		/* wait for cgroup to be empty */
		while (1) {
			if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf)))
				goto cleanup;
			if (buf[0] == '\0')
				break;
			usleep(1000);
		}

		if (rmdir(cg_test))
			goto cleanup;

		if (waitpid(child_pid, NULL, 0) < 0)
			goto cleanup;
	}
	ret = KSFT_PASS;
cleanup:
	if (cg_test)
		cg_destroy(cg_test);
	free(cg_test);
	return ret;
}

/*
 * A(0) - B(0) - C(1)
 *        \ D(0)
 *
 * A, B and C's "populated" fields would be 1 while D's 0.
 * test that after the one process in C is moved to root,
 * A,B and C's "populated" fields would flip to "0" and file
 * modified events will be generated on the
 * "cgroup.events" files of both cgroups.
 */
static int test_cgcore_populated(const char *root)
{
	int ret = KSFT_FAIL;
	int err;
	char *cg_test_a = NULL, *cg_test_b = NULL;
	char *cg_test_c = NULL, *cg_test_d = NULL;
	int cgroup_fd = -EBADF;
	pid_t pid;

	if (cg_test_v1_named)
		return KSFT_SKIP;

	cg_test_a = cg_name(root, "cg_test_a");
	cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
	cg_test_c = cg_name(root, "cg_test_a/cg_test_b/cg_test_c");
	cg_test_d = cg_name(root, "cg_test_a/cg_test_b/cg_test_d");

	if (!cg_test_a || !cg_test_b || !cg_test_c ||