Resguardo inicial

linux-7.2.3/tools/testing/selftests/cgroup/.gitignore

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_core
+test_cpu
+test_cpuset
+test_freezer
+test_hugetlb_memcg
+test_kill
+test_kmem
+test_memcontrol
+test_pids
+test_zswap
+wait_inotify

linux-7.2.3/tools/testing/selftests/cgroup/Makefile

@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall -pthread
+
+all: ${HELPER_PROGS}
+
+TEST_FILES     := with_stress.sh
+TEST_PROGS     := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh
+TEST_GEN_FILES := wait_inotify
+# Keep the lists lexicographically sorted
+TEST_GEN_PROGS  = test_core
+TEST_GEN_PROGS += test_cpu
+TEST_GEN_PROGS += test_cpuset
+TEST_GEN_PROGS += test_freezer
+TEST_GEN_PROGS += test_hugetlb_memcg
+TEST_GEN_PROGS += test_kill
+TEST_GEN_PROGS += test_kmem
+TEST_GEN_PROGS += test_memcontrol
+TEST_GEN_PROGS += test_pids
+TEST_GEN_PROGS += test_zswap
+
+LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
+
+include ../lib.mk
+include lib/libcgroup.mk
+
+$(OUTPUT)/test_core: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpu: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpuset: $(LIBCGROUP_O)
+$(OUTPUT)/test_freezer: $(LIBCGROUP_O)
+$(OUTPUT)/test_hugetlb_memcg: $(LIBCGROUP_O)
+$(OUTPUT)/test_kill: $(LIBCGROUP_O)
+$(OUTPUT)/test_kmem: $(LIBCGROUP_O)
+$(OUTPUT)/test_memcontrol: $(LIBCGROUP_O)
+$(OUTPUT)/test_pids: $(LIBCGROUP_O)
+$(OUTPUT)/test_zswap: $(LIBCGROUP_O)

linux-7.2.3/tools/testing/selftests/cgroup/config

@@ -0,0 +1,6 @@
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_MEMCG=y
+CONFIG_PAGE_COUNTER=y

linux-7.2.3/tools/testing/selftests/cgroup/lib/cgroup_util.c

@@ -0,0 +1,679 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/limits.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/inotify.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "cgroup_util.h"
+#include "../../clone3/clone3_selftests.h"
+
+bool cg_test_v1_named;
+
+/* Returns read len on success, or -errno on failure. */
+ssize_t read_text(const char *path, char *buf, size_t max_len)
+{
+	ssize_t len;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	len = read(fd, buf, max_len - 1);
+
+	if (len >= 0)
+		buf[len] = 0;
+
+	close(fd);
+	return len < 0 ? -errno : len;
+}
+
+/* Returns written len on success, or -errno on failure. */
+ssize_t write_text(const char *path, char *buf, ssize_t len)
+{
+	int fd;
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return -errno;
+
+	len = write(fd, buf, len);
+	close(fd);
+	return len < 0 ? -errno : len;
+}
+
+char *cg_name(const char *root, const char *name)
+{
+	size_t len = strlen(root) + strlen(name) + 2;
+	char *ret = malloc(len);
+
+	if (ret)
+		snprintf(ret, len, "%s/%s", root, name);
+
+	return ret;
+}
+
+char *cg_name_indexed(const char *root, const char *name, int index)
+{
+	size_t len = strlen(root) + strlen(name) + 10;
+	char *ret = malloc(len);
+
+	if (ret)
+		snprintf(ret, len, "%s/%s_%d", root, name, index);
+
+	return ret;
+}
+
+char *cg_control(const char *cgroup, const char *control)
+{
+	size_t len = strlen(cgroup) + strlen(control) + 2;
+	char *ret = malloc(len);
+
+	if (ret)
+		snprintf(ret, len, "%s/%s", cgroup, control);
+
+	return ret;
+}
+
+/* Returns 0 on success, or -errno on failure. */
+int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
+{
+	char path[PATH_MAX];
+	ssize_t ret;
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+	ret = read_text(path, buf, len);
+	return ret >= 0 ? 0 : ret;
+}
+
+int cg_read_strcmp(const char *cgroup, const char *control,
+		   const char *expected)
+{
+	size_t size;
+	char *buf;
+	int ret;
+
+	/* Handle the case of comparing against empty string */
+	if (!expected)
+		return -1;
+
+	/* needs size > 1, otherwise cg_read() reads 0 bytes */
+	size = (expected[0] == '\0') ? 2 : strlen(expected) + 1;
+
+	buf = malloc(size);
+	if (!buf)
+		return -1;
+
+	if (cg_read(cgroup, control, buf, size)) {
+		free(buf);
+		return -1;
+	}
+
+	ret = strcmp(expected, buf);
+	free(buf);
+	return ret;
+}
+
+int cg_read_strcmp_wait(const char *cgroup, const char *control,
+			    const char *expected)
+{
+	int i, ret;
+
+	for (i = 0; i < 100; i++) {
+		ret = cg_read_strcmp(cgroup, control, expected);
+		if (!ret)
+			return ret;
+		usleep(10000);
+	}
+
+	return ret;
+}
+
+int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
+{
+	char buf[BUF_SIZE];
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	return strstr(buf, needle) ? 0 : -1;
+}
+
+long cg_read_long(const char *cgroup, const char *control)
+{
+	char buf[128];
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	return atol(buf);
+}
+
+long cg_read_long_fd(int fd)
+{
+	char buf[128];
+
+	if (pread(fd, buf, sizeof(buf), 0) <= 0)
+		return -1;
+
+	return atol(buf);
+}
+
+long cg_read_key_long(const char *cgroup, const char *control, const char *key)
+{
+	char buf[BUF_SIZE];
+	char *ptr;
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	ptr = strstr(buf, key);
+	if (!ptr)
+		return -1;
+
+	return atol(ptr + strlen(key));
+}
+
+long cg_read_key_long_poll(const char *cgroup, const char *control,
+			   const char *key, long expected, int retries,
+			   useconds_t wait_interval_us)
+{
+	long val = -1;
+	int i;
+
+	for (i = 0; i < retries; i++) {
+		val = cg_read_key_long(cgroup, control, key);
+		if (val < 0)
+			return val;
+
+		if (val == expected)
+			break;
+
+		usleep(wait_interval_us);
+	}
+
+	return val;
+}
+
+long cg_read_lc(const char *cgroup, const char *control)
+{
+	char buf[BUF_SIZE];
+	const char delim[] = "\n";
+	char *line;
+	long cnt = 0;
+
+	if (cg_read(cgroup, control, buf, sizeof(buf)))
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt;
+}
+
+/* Returns 0 on success, or -errno on failure. */
+int cg_write(const char *cgroup, const char *control, char *buf)
+{
+	char path[PATH_MAX];
+	ssize_t len = strlen(buf), ret;
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+	ret = write_text(path, buf, len);
+	return ret == len ? 0 : ret;
+}
+
+/*
+ * Returns fd on success, or -1 on failure.
+ * (fd should be closed with close() as usual)
+ */
+int cg_open(const char *cgroup, const char *control, int flags)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+	return open(path, flags);
+}
+
+int cg_write_numeric(const char *cgroup, const char *control, long value)
+{
+	char buf[64];
+	int ret;
+
+	ret = sprintf(buf, "%lu", value);
+	if (ret < 0)
+		return ret;
+
+	return cg_write(cgroup, control, buf);
+}
+
+static int cg_find_root(char *root, size_t len, const char *controller,
+			bool *nsdelegate)
+{
+	char buf[10 * BUF_SIZE];
+	char *fs, *mount, *type, *options;
+	const char delim[] = "\n\t ";
+
+	if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	/*
+	 * Example:
+	 * cgroup /sys/fs/cgroup cgroup2 rw,seclabel,noexec,relatime 0 0
+	 */
+	for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
+		mount = strtok(NULL, delim);
+		type = strtok(NULL, delim);
+		options = strtok(NULL, delim);
+		strtok(NULL, delim);
+		strtok(NULL, delim);
+		if (strcmp(type, "cgroup") == 0) {
+			if (!controller || !strstr(options, controller))
+				continue;
+		} else if (strcmp(type, "cgroup2") == 0) {
+			if (controller &&
+					cg_read_strstr(mount, "cgroup.controllers", controller))
+				continue;
+		} else {
+			continue;
+		}
+		strncpy(root, mount, len);
+
+		if (nsdelegate)
+			*nsdelegate = !!strstr(options, "nsdelegate");
+		return 0;
+
+	}
+
+	return -1;
+}
+
+int cg_find_controller_root(char *root, size_t len, const char *controller)
+{
+	return cg_find_root(root, len, controller, NULL);
+}
+
+int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
+{
+	return cg_find_root(root, len, NULL, nsdelegate);
+}
+
+int cg_create(const char *cgroup)
+{
+	return mkdir(cgroup, 0755);
+}
+
+int cg_wait_for_proc_count(const char *cgroup, int count)
+{
+	char buf[10 * BUF_SIZE] = {0};
+	int attempts;
+	char *ptr;
+
+	for (attempts = 10; attempts >= 0; attempts--) {
+		int nr = 0;
+
+		if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
+			break;
+
+		for (ptr = buf; *ptr; ptr++)
+			if (*ptr == '\n')
+				nr++;
+
+		if (nr >= count)
+			return 0;
+
+		usleep(100000);
+	}
+
+	return -1;
+}
+
+int cg_killall(const char *cgroup)
+{
+	char buf[BUF_SIZE];
+	char *ptr = buf;
+
+	/* If cgroup.kill exists use it. */
+	if (!cg_write(cgroup, "cgroup.kill", "1"))
+		return 0;
+
+	if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
+		return -1;
+
+	while (ptr < buf + sizeof(buf)) {
+		int pid = strtol(ptr, &ptr, 10);
+
+		if (pid == 0)
+			break;
+		if (*ptr)
+			ptr++;
+		else
+			break;
+		if (kill(pid, SIGKILL))
+			return -1;
+	}
+
+	return 0;
+}
+
+int cg_destroy(const char *cgroup)
+{
+	int ret;
+
+	if (!cgroup)
+		return 0;
+retry:
+	ret = rmdir(cgroup);
+	if (ret && errno == EBUSY) {
+		cg_killall(cgroup);
+		usleep(100);
+		goto retry;
+	}
+
+	if (ret && errno == ENOENT)
+		ret = 0;
+
+	return ret;
+}
+
+int cg_enter(const char *cgroup, int pid)
+{
+	char pidbuf[64];
+
+	snprintf(pidbuf, sizeof(pidbuf), "%d", pid);
+	return cg_write(cgroup, "cgroup.procs", pidbuf);
+}
+
+int cg_enter_current(const char *cgroup)
+{
+	return cg_write(cgroup, "cgroup.procs", "0");
+}
+
+int cg_enter_current_thread(const char *cgroup)
+{
+	return cg_write(cgroup, CG_THREADS_FILE, "0");
+}
+
+int cg_run(const char *cgroup,
+	   int (*fn)(const char *cgroup, void *arg),
+	   void *arg)
+{
+	int pid, retcode;
+
+	pid = fork();
+	if (pid < 0) {
+		return pid;
+	} else if (pid == 0) {
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cgroup, "cgroup.procs", buf))
+			exit(EXIT_FAILURE);
+		exit(fn(cgroup, arg));
+	} else {
+		waitpid(pid, &retcode, 0);
+		if (WIFEXITED(retcode))
+			return WEXITSTATUS(retcode);
+		else
+			return -1;
+	}
+}
+
+pid_t clone_into_cgroup(int cgroup_fd)
+{
+#ifdef CLONE_ARGS_SIZE_VER2
+	pid_t pid;
+
+	struct __clone_args args = {
+		.flags = CLONE_INTO_CGROUP,
+		.exit_signal = SIGCHLD,
+		.cgroup = cgroup_fd,
+	};
+
+	pid = sys_clone3(&args, sizeof(struct __clone_args));
+	/*
+	 * Verify that this is a genuine test failure:
+	 * ENOSYS -> clone3() not available
+	 * E2BIG  -> CLONE_INTO_CGROUP not available
+	 */
+	if (pid < 0 && (errno == ENOSYS || errno == E2BIG))
+		goto pretend_enosys;
+
+	return pid;
+
+pretend_enosys:
+#endif
+	errno = ENOSYS;
+	return -ENOSYS;
+}
+
+int clone_reap(pid_t pid, int options)
+{
+	int ret;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+again:
+	ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD);
+	if (ret < 0) {
+		if (errno == EINTR)
+			goto again;
+		return -1;
+	}
+
+	if (options & WEXITED) {
+		if (WIFEXITED(info.si_status))
+			return WEXITSTATUS(info.si_status);
+	}
+
+	if (options & WSTOPPED) {
+		if (WIFSTOPPED(info.si_status))
+			return WSTOPSIG(info.si_status);
+	}
+
+	if (options & WCONTINUED) {
+		if (WIFCONTINUED(info.si_status))
+			return 0;
+	}
+
+	return -1;
+}
+
+int dirfd_open_opath(const char *dir)
+{
+	return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH);
+}
+
+#define close_prot_errno(fd)                                                   \
+	if (fd >= 0) {                                                         \
+		int _e_ = errno;                                               \
+		close(fd);                                                     \
+		errno = _e_;                                                   \
+	}
+
+static int clone_into_cgroup_run_nowait(const char *cgroup,
+					int (*fn)(const char *cgroup, void *arg),
+					void *arg)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid == 0)
+		exit(fn(cgroup, arg));
+
+	return pid;
+}
+
+int cg_run_nowait(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg)
+{
+	int pid;
+
+	pid = clone_into_cgroup_run_nowait(cgroup, fn, arg);
+	if (pid > 0)
+		return pid;
+
+	/* Genuine test failure. */
+	if (pid < 0 && errno != ENOSYS)
+		return -1;
+
+	pid = fork();
+	if (pid == 0) {
+		char buf[64];
+
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cgroup, "cgroup.procs", buf))
+			exit(EXIT_FAILURE);
+		exit(fn(cgroup, arg));
+	}
+
+	return pid;
+}
+
+int proc_mount_contains(const char *option)
+{
+	char buf[4 * BUF_SIZE];
+	ssize_t read;
+
+	read = read_text("/proc/mounts", buf, sizeof(buf));
+	if (read < 0)
+		return read;
+
+	return strstr(buf, option) != NULL;
+}
+
+int cgroup_feature(const char *feature)
+{
+	char buf[BUF_SIZE];
+	ssize_t read;
+
+	read = read_text("/sys/kernel/cgroup/features", buf, sizeof(buf));
+	if (read < 0)
+		return read;
+
+	return strstr(buf, feature) != NULL;
+}
+
+ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
+{
+	char path[PATH_MAX];
+	ssize_t ret;
+
+	if (!pid)
+		snprintf(path, sizeof(path), "/proc/%s/%s",
+			 thread ? "thread-self" : "self", item);
+	else
+		snprintf(path, sizeof(path), "/proc/%d/%s", pid, item);
+
+	ret = read_text(path, buf, size);
+	return ret < 0 ? -1 : ret;
+}
+
+int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
+{
+	char buf[BUF_SIZE];
+
+	if (proc_read_text(pid, thread, item, buf, sizeof(buf)) < 0)
+		return -1;
+
+	return strstr(buf, needle) ? 0 : -1;
+}
+
+int clone_into_cgroup_run_wait(const char *cgroup)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid < 0)
+		return -1;
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	/*
+	 * We don't care whether this fails. We only care whether the initial
+	 * clone succeeded.
+	 */
+	(void)clone_reap(pid, WEXITED);
+	return 0;
+}
+
+static int __prepare_for_wait(const char *cgroup, const char *filename)
+{
+	int fd, ret = -1;
+
+	fd = inotify_init1(0);
+	if (fd == -1)
+		return fd;
+
+	ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY);
+	if (ret == -1) {
+		close(fd);
+		fd = -1;
+	}
+
+	return fd;
+}
+
+int cg_prepare_for_wait(const char *cgroup)
+{
+	return __prepare_for_wait(cgroup, "cgroup.events");
+}
+
+int memcg_prepare_for_wait(const char *cgroup)
+{
+	return __prepare_for_wait(cgroup, "memory.events");
+}
+
+int cg_wait_for(int fd)
+{
+	int ret = -1;
+	struct pollfd fds = {
+		.fd = fd,
+		.events = POLLIN,
+	};
+
+	while (true) {
+		ret = poll(&fds, 1, 10000);
+
+		if (ret == -1) {
+			if (errno == EINTR)
+				continue;
+
+			break;
+		}
+
+		if (ret > 0 && fds.revents & POLLIN) {
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}

linux-7.2.3/tools/testing/selftests/cgroup/lib/include/cgroup_util.h

@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdbool.h>
+#include <stdlib.h>
+
+#ifndef BUF_SIZE
+#define BUF_SIZE 4096
+#endif
+
+#define MB(x) (x << 20)
+
+#define USEC_PER_SEC	1000000L
+#define NSEC_PER_SEC	1000000000L
+
+#define TEST_UID	65534 /* usually nobody, any !root is fine */
+
+#define CG_THREADS_FILE (!cg_test_v1_named ? "cgroup.threads" : "tasks")
+#define CG_NAMED_NAME "selftest"
+#define CG_PATH_FORMAT (!cg_test_v1_named ? "0::%s" : (":name=" CG_NAMED_NAME ":%s"))
+
+#define DEFAULT_WAIT_INTERVAL_US (100 * 1000) /* 100 ms */
+
+/*
+ * Checks if two given values differ by less than err% of their sum.
+ */
+static inline int values_close(long a, long b, int err)
+{
+	return labs(a - b) <= (a + b) / 100 * err;
+}
+
+/*
+ * Checks if two given values differ by less than err% of their sum and assert
+ * with detailed debug info if not.
+ */
+static inline int values_close_report(long a, long b, int err)
+{
+	long diff  = labs(a - b);
+	long limit = (a + b) / 100 * err;
+	double actual_err = (a + b) ? (100.0 * diff / (a + b)) : 0.0;
+	int close = diff <= limit;
+
+	if (!close)
+		fprintf(stderr,
+			"[FAIL] actual=%ld expected=%ld | diff=%ld | limit=%ld | "
+			"tolerance=%d%% | actual_error=%.2f%%\n",
+			a, b, diff, limit, err, actual_err);
+
+	return close;
+}
+
+extern ssize_t read_text(const char *path, char *buf, size_t max_len);
+extern ssize_t write_text(const char *path, char *buf, ssize_t len);
+
+extern int cg_find_controller_root(char *root, size_t len, const char *controller);
+extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
+extern char *cg_name(const char *root, const char *name);
+extern char *cg_name_indexed(const char *root, const char *name, int index);
+extern char *cg_control(const char *cgroup, const char *control);
+extern int cg_create(const char *cgroup);
+extern int cg_destroy(const char *cgroup);
+extern int cg_read(const char *cgroup, const char *control,
+		   char *buf, size_t len);
+extern int cg_read_strcmp(const char *cgroup, const char *control,
+			  const char *expected);
+extern int cg_read_strcmp_wait(const char *cgroup, const char *control,
+				   const char *expected);
+extern int cg_read_strstr(const char *cgroup, const char *control,
+			  const char *needle);
+extern long cg_read_long(const char *cgroup, const char *control);
+extern long cg_read_long_fd(int fd);
+long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+long cg_read_key_long_poll(const char *cgroup, const char *control,
+			   const char *key, long expected, int retries,
+			   useconds_t wait_interval_us);
+extern long cg_read_lc(const char *cgroup, const char *control);
+extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_open(const char *cgroup, const char *control, int flags);
+int cg_write_numeric(const char *cgroup, const char *control, long value);
+extern int cg_run(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg);
+extern int cg_enter(const char *cgroup, int pid);
+extern int cg_enter_current(const char *cgroup);
+extern int cg_enter_current_thread(const char *cgroup);
+extern int cg_run_nowait(const char *cgroup,
+			 int (*fn)(const char *cgroup, void *arg),
+			 void *arg);
+extern int cg_wait_for_proc_count(const char *cgroup, int count);
+extern int cg_killall(const char *cgroup);
+int proc_mount_contains(const char *option);
+int cgroup_feature(const char *feature);
+extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
+extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
+extern pid_t clone_into_cgroup(int cgroup_fd);
+extern int clone_reap(pid_t pid, int options);
+extern int clone_into_cgroup_run_wait(const char *cgroup);
+extern int dirfd_open_opath(const char *dir);
+extern int cg_prepare_for_wait(const char *cgroup);
+extern int memcg_prepare_for_wait(const char *cgroup);
+extern int cg_wait_for(int fd);
+extern bool cg_test_v1_named;

linux-7.2.3/tools/testing/selftests/cgroup/lib/libcgroup.mk

@@ -0,0 +1,19 @@
+CGROUP_DIR := $(selfdir)/cgroup
+
+LIBCGROUP_C := lib/cgroup_util.c
+
+LIBCGROUP_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBCGROUP_C))
+
+LIBCGROUP_O_DIRS := $(shell dirname $(LIBCGROUP_O) | uniq)
+
+CFLAGS += -I$(CGROUP_DIR)/lib/include
+
+EXTRA_HDRS := $(selfdir)/clone3/clone3_selftests.h
+
+$(LIBCGROUP_O_DIRS):
+	mkdir -p $@
+
+$(LIBCGROUP_O): $(OUTPUT)/%.o : $(CGROUP_DIR)/%.c $(EXTRA_HDRS) $(LIBCGROUP_O_DIRS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+EXTRA_CLEAN += $(LIBCGROUP_O)

linux-7.2.3/tools/testing/selftests/cgroup/memcg_protection.m

@@ -0,0 +1,89 @@
+% SPDX-License-Identifier: GPL-2.0
+%
+% run as: octave-cli memcg_protection.m
+%
+% This script simulates reclaim protection behavior on a single level of memcg
+% hierarchy to illustrate how overcommitted protection spreads among siblings
+% (as it depends also on their current consumption).
+%
+% Simulation assumes siblings consumed the initial amount of memory (w/out
+% reclaim) and then the reclaim starts, all memory is reclaimable, i.e. treated
+% same. It simulates only non-low reclaim and assumes all memory.min = 0.
+%
+% Input configurations
+% --------------------
+% E number	parent effective protection
+% n vector	nominal protection of siblings set at the given level (memory.low)
+% c vector	current consumption -,,- (memory.current)
+
+% example from testcase (values in GB)
+E = 50 / 1024;
+n = [75 25 0 500 ] / 1024;
+c = [50 50 50 0] / 1024;
+
+% Reclaim parameters
+% ------------------
+
+% Minimal reclaim amount (GB)
+cluster = 32*4 / 2**20;
+
+% Reclaim coefficient (think as 0.5^sc->priority)
+alpha = .1
+
+% Simulation parameters
+% ---------------------
+epsilon = 1e-7;
+timeout = 1000;
+
+% Simulation loop
+% ---------------
+
+ch = [];
+eh = [];
+rh = [];
+
+for t = 1:timeout
+        % low_usage
+        u = min(c, n);
+        siblings = sum(u);
+
+        % effective_protection()
+        protected = min(n, c);                % start with nominal
+        e = protected * min(1, E / siblings); % normalize overcommit
+
+        % recursive protection
+        unclaimed = max(0, E - siblings);
+        parent_overuse = sum(c) - siblings;
+        if (unclaimed > 0 && parent_overuse > 0)
+                overuse = max(0, c - protected);
+                e += unclaimed * (overuse / parent_overuse);
+        endif
+
+        % get_scan_count()
+        r = alpha * c;             % assume all memory is in a single LRU list
+
+        % commit 1bc63fb1272b ("mm, memcg: make scan aggression always exclude protection")
+        sz = max(e, c);
+        r .*= (1 - (e+epsilon) ./ (sz+epsilon));
+
+        % uncomment to debug prints
+        % e, c, r
+
+        % nothing to reclaim, reached equilibrium
+        if max(r) < epsilon
+                break;
+        endif
+
+        % SWAP_CLUSTER_MAX roundup
+        r = max(r, (r > epsilon) .* cluster);
+        % XXX here I do parallel reclaim of all siblings
+        % in reality reclaim is serialized and each sibling recalculates own residual
+        c = max(c - r, 0);
+
+        ch = [ch ; c];
+        eh = [eh ; e];
+        rh = [rh ; r];
+endfor
+
+t
+c, e

linux-7.2.3/tools/testing/selftests/cgroup/test_core.c

@@ -0,0 +1,959 @@
+/* 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[BUF_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 || !cg_test_d)
+		goto cleanup;
+
+	if (cg_create(cg_test_a))
+		goto cleanup;
+
+	if (cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_create(cg_test_c))
+		goto cleanup;
+
+	if (cg_create(cg_test_d))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_c))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_a, "cgroup.events", "populated 1\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_b, "cgroup.events", "populated 1\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_c, "cgroup.events", "populated 1\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	if (cg_enter_current(root))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_a, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_b, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_c, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	/* Test that we can directly clone into a new cgroup. */
+	cgroup_fd = dirfd_open_opath(cg_test_d);
+	if (cgroup_fd < 0)
+		goto cleanup;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0) {
+		if (errno == ENOSYS)
+			goto cleanup_pass;
+		goto cleanup;
+	}
+
+	if (pid == 0) {
+		if (raise(SIGSTOP))
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n");
+
+	(void)clone_reap(pid, WSTOPPED);
+	(void)kill(pid, SIGCONT);
+	(void)clone_reap(pid, WEXITED);
+
+	if (err)
+		goto cleanup;
+
+	if (cg_read_strcmp_wait(cg_test_d, "cgroup.events",
+				   "populated 0\n"))
+		goto cleanup;
+
+	/* Remove cgroup. */
+	if (cg_test_d) {
+		cg_destroy(cg_test_d);
+		free(cg_test_d);
+		cg_test_d = NULL;
+	}
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0)
+		goto cleanup_pass;
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+	(void)clone_reap(pid, WEXITED);
+	goto cleanup;
+
+cleanup_pass:
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cg_test_d)
+		cg_destroy(cg_test_d);
+	if (cg_test_c)
+		cg_destroy(cg_test_c);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_d);
+	free(cg_test_c);
+	free(cg_test_b);
+	free(cg_test_a);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	return ret;
+}
+
+/*
+ * A (domain threaded) - B (threaded) - C (domain)
+ *
+ * test that C can't be used until it is turned into a
+ * threaded cgroup.  "cgroup.type" file will report "domain (invalid)" in
+ * these cases. Operations which fail due to invalid topology use
+ * EOPNOTSUPP as the errno.
+ */
+static int test_cgcore_invalid_domain(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *grandparent = NULL, *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
+	grandparent = cg_name(root, "cg_test_grandparent");
+	parent = cg_name(root, "cg_test_grandparent/cg_test_parent");
+	child = cg_name(root, "cg_test_grandparent/cg_test_parent/cg_test_child");
+	if (!parent || !child || !grandparent)
+		goto cleanup;
+
+	if (cg_create(grandparent))
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	if (cg_read_strcmp(child, "cgroup.type", "domain invalid\n"))
+		goto cleanup;
+
+	if (!cg_enter_current(child))
+		goto cleanup;
+
+	if (errno != EOPNOTSUPP)
+		goto cleanup;
+
+	if (!clone_into_cgroup_run_wait(child))
+		goto cleanup;
+
+	if (errno == ENOSYS)
+		goto cleanup_pass;
+
+	if (errno != EOPNOTSUPP)
+		goto cleanup;
+
+cleanup_pass:
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	if (grandparent)
+		cg_destroy(grandparent);
+	free(child);
+	free(parent);
+	free(grandparent);
+	return ret;
+}
+
+/*
+ * Test that when a child becomes threaded
+ * the parent type becomes domain threaded.
+ */
+static int test_cgcore_parent_becomes_threaded(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
+	parent = cg_name(root, "cg_test_parent");
+	child = cg_name(root, "cg_test_parent/cg_test_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(child, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	if (cg_read_strcmp(parent, "cgroup.type", "domain threaded\n"))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	return ret;
+
+}
+
+/*
+ * Test that there's no internal process constrain on threaded cgroups.
+ * You can add threads/processes on a parent with a controller enabled.
+ */
+static int test_cgcore_no_internal_process_constraint_on_threads(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named ||
+	    cg_read_strstr(root, "cgroup.controllers", "cpu") ||
+	    cg_write(root, "cgroup.subtree_control", "+cpu")) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	parent = cg_name(root, "cg_test_parent");
+	child = cg_name(root, "cg_test_parent/cg_test_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	if (cg_write(child, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+
+	if (cg_enter_current(parent))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	cg_enter_current(root);
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	return ret;
+}
+
+/*
+ * Test that you can't enable a controller on a child if it's not enabled
+ * on the parent.
+ */
+static int test_cgcore_top_down_constraint_enable(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
+	parent = cg_name(root, "cg_test_parent");
+	child = cg_name(root, "cg_test_parent/cg_test_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (!cg_write(child, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	return ret;
+}
+
+/*
+ * Test that you can't disable a controller on a parent
+ * if it's enabled in a child.
+ */
+static int test_cgcore_top_down_constraint_disable(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
+	parent = cg_name(root, "cg_test_parent");
+	child = cg_name(root, "cg_test_parent/cg_test_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(child, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (!cg_write(parent, "cgroup.subtree_control", "-memory"))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	return ret;
+}
+
+/*
+ * Test internal process constraint.
+ * You can't add a pid to a domain parent if a controller is enabled.
+ */
+static int test_cgcore_internal_process_constraint(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent = NULL, *child = NULL;
+
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
+	parent = cg_name(root, "cg_test_parent");
+	child = cg_name(root, "cg_test_parent/cg_test_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (!cg_enter_current(parent))
+		goto cleanup;
+
+	if (!clone_into_cgroup_run_wait(parent))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	return ret;
+}
+
+static void *dummy_thread_fn(void *arg)
+{
+	return (void *)(size_t)pause();
+}
+
+/*
+ * Test threadgroup migration.
+ * All threads of a process are migrated together.
+ */
+static int test_cgcore_proc_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int t, c_threads = 0, n_threads = 13;
+	char *src = NULL, *dst = NULL;
+	pthread_t threads[n_threads];
+
+	src = cg_name(root, "cg_src");
+	dst = cg_name(root, "cg_dst");
+	if (!src || !dst)
+		goto cleanup;
+
+	if (cg_create(src))
+		goto cleanup;
+	if (cg_create(dst))
+		goto cleanup;
+
+	if (cg_enter_current(src))
+		goto cleanup;
+
+	for (c_threads = 0; c_threads < n_threads; ++c_threads) {
+		if (pthread_create(&threads[c_threads], NULL, dummy_thread_fn, NULL))
+			goto cleanup;
+	}
+
+	cg_enter_current(dst);
+	if (cg_read_lc(dst, CG_THREADS_FILE) != n_threads + 1)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (t = 0; t < c_threads; ++t) {
+		pthread_cancel(threads[t]);
+	}
+
+	for (t = 0; t < c_threads; ++t) {
+		pthread_join(threads[t], NULL);
+	}
+
+	cg_enter_current(root);
+
+	if (dst)
+		cg_destroy(dst);
+	if (src)
+		cg_destroy(src);
+	free(dst);
+	free(src);
+	return ret;
+}
+
+static void *migrating_thread_fn(void *arg)
+{
+	int g, i, n_iterations = 1000;
+	char **grps = arg;
+	char lines[3][PATH_MAX];
+
+	for (g = 1; g < 3; ++g)
+		snprintf(lines[g], sizeof(lines[g]), CG_PATH_FORMAT, grps[g] + strlen(grps[0]));
+
+	for (i = 0; i < n_iterations; ++i) {
+		cg_enter_current_thread(grps[(i % 2) + 1]);
+
+		if (proc_read_strstr(0, 1, "cgroup", lines[(i % 2) + 1]))
+			return (void *)-1;
+	}
+	return NULL;
+}
+
+/*
+ * Test single thread migration.
+ * Threaded cgroups allow successful migration of a thread.
+ */
+static int test_cgcore_thread_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *dom = NULL;
+	char line[PATH_MAX];
+	char *grps[3] = { (char *)root, NULL, NULL };
+	pthread_t thr;
+	void *retval;
+
+	dom = cg_name(root, "cg_dom");
+	grps[1] = cg_name(root, "cg_dom/cg_src");
+	grps[2] = cg_name(root, "cg_dom/cg_dst");
+	if (!grps[1] || !grps[2] || !dom)
+		goto cleanup;
+
+	if (cg_create(dom))
+		goto cleanup;
+	if (cg_create(grps[1]))
+		goto cleanup;
+	if (cg_create(grps[2]))
+		goto cleanup;
+
+	if (!cg_test_v1_named) {
+		if (cg_write(grps[1], "cgroup.type", "threaded"))
+			goto cleanup;
+		if (cg_write(grps[2], "cgroup.type", "threaded"))
+			goto cleanup;
+	}
+
+	if (cg_enter_current(grps[1]))
+		goto cleanup;
+
+	if (pthread_create(&thr, NULL, migrating_thread_fn, grps))
+		goto cleanup;
+
+	if (pthread_join(thr, &retval))
+		goto cleanup;
+
+	if (retval)
+		goto cleanup;
+
+	snprintf(line, sizeof(line), CG_PATH_FORMAT, grps[1] + strlen(grps[0]));
+	if (proc_read_strstr(0, 1, "cgroup", line))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (grps[2])
+		cg_destroy(grps[2]);
+	if (grps[1])
+		cg_destroy(grps[1]);
+	if (dom)
+		cg_destroy(dom);
+	free(grps[2]);
+	free(grps[1]);
+	free(dom);
+	return ret;
+}
+
+/*
+ * cgroup migration permission check should be performed based on the
+ * credentials at the time of open instead of write.
+ */
+static int test_cgcore_lesser_euid_open(const char *root)
+{
+	const uid_t test_euid = TEST_UID;
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	uid_t saved_uid;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	saved_uid = geteuid();
+	if (seteuid(test_euid))
+		goto cleanup;
+
+	cg_test_b_procs_fd = open(cg_test_b_procs, O_RDWR);
+
+	if (seteuid(saved_uid))
+		goto cleanup;
+
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (write(cg_test_b_procs_fd, "0", 1) >= 0 || errno != EACCES)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
+struct lesser_ns_open_thread_arg {
+	const char	*path;
+	int		fd;
+	int		err;
+};
+
+static int lesser_ns_open_thread_fn(void *arg)
+{
+	struct lesser_ns_open_thread_arg *targ = arg;
+
+	targ->fd = open(targ->path, O_RDWR);
+	targ->err = errno;
+	return 0;
+}
+
+/*
+ * cgroup migration permission check should be performed based on the cgroup
+ * namespace at the time of open instead of write.
+ */
+static int test_cgcore_lesser_ns_open(const char *root)
+{
+	static char stack[65536];
+	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	struct lesser_ns_open_thread_arg targ = { .fd = -1 };
+	pid_t pid;
+	int status;
+
+	if (!nsdelegate)
+		return KSFT_SKIP;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_b))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	targ.path = cg_test_b_procs;
+	pid = clone(lesser_ns_open_thread_fn, stack + sizeof(stack),
+		    CLONE_NEWCGROUP | CLONE_FILES | CLONE_VM | SIGCHLD,
+		    &targ);
+	if (pid < 0)
+		goto cleanup;
+
+	if (waitpid(pid, &status, 0) < 0)
+		goto cleanup;
+
+	if (!WIFEXITED(status))
+		goto cleanup;
+
+	cg_test_b_procs_fd = targ.fd;
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if ((status = write(cg_test_b_procs_fd, "0", 1)) >= 0 || errno != ENOENT)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
+static int setup_named_v1_root(char *root, size_t len, const char *name)
+{
+	char options[PATH_MAX];
+	int r;
+
+	r = snprintf(root, len, "/mnt/cg_selftest");
+	if (r < 0)
+		return r;
+
+	r = snprintf(options, sizeof(options), "none,name=%s", name);
+	if (r < 0)
+		return r;
+
+	r = mkdir(root, 0755);
+	if (r < 0 && errno != EEXIST)
+		return r;
+
+	r = mount("none", root, "cgroup", 0, options);
+	if (r < 0)
+		return r;
+
+	return 0;
+}
+
+static void cleanup_named_v1_root(char *root)
+{
+	if (!cg_test_v1_named)
+		return;
+	umount(root);
+	rmdir(root);
+}
+
+#define T(x) { x, #x }
+struct corecg_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cgcore_internal_process_constraint),
+	T(test_cgcore_top_down_constraint_enable),
+	T(test_cgcore_top_down_constraint_disable),
+	T(test_cgcore_no_internal_process_constraint_on_threads),
+	T(test_cgcore_parent_becomes_threaded),
+	T(test_cgcore_invalid_domain),
+	T(test_cgcore_populated),
+	T(test_cgcore_proc_migration),
+	T(test_cgcore_thread_migration),
+	T(test_cgcore_destroy),
+	T(test_cgcore_lesser_euid_open),
+	T(test_cgcore_lesser_ns_open),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
+		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
+			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
+		cg_test_v1_named = true;
+		goto post_v2_setup;
+	}
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+post_v2_setup:
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	cleanup_named_v1_root(root);
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_cpu.c

@@ -0,0 +1,825 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <linux/limits.h>
+#include <sys/param.h>
+#include <sys/sysinfo.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+enum hog_clock_type {
+	// Count elapsed time using the CLOCK_PROCESS_CPUTIME_ID clock.
+	CPU_HOG_CLOCK_PROCESS,
+	// Count elapsed time using system wallclock time.
+	CPU_HOG_CLOCK_WALL,
+};
+
+struct cpu_hogger {
+	char *cgroup;
+	pid_t pid;
+	long usage;
+};
+
+struct cpu_hog_func_param {
+	int nprocs;
+	struct timespec ts;
+	enum hog_clock_type clock_type;
+};
+
+/*
+ * This test creates two nested cgroups with and without enabling
+ * the cpu controller.
+ */
+static int test_cpucg_subtree_control(const char *root)
+{
+	char *parent = NULL, *child = NULL, *parent2 = NULL, *child2 = NULL;
+	int ret = KSFT_FAIL;
+
+	// Create two nested cgroups with the cpu controller enabled.
+	parent = cg_name(root, "cpucg_test_0");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+
+	child = cg_name(parent, "cpucg_test_child");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "cpu"))
+		goto cleanup;
+
+	// Create two nested cgroups without enabling the cpu controller.
+	parent2 = cg_name(root, "cpucg_test_1");
+	if (!parent2)
+		goto cleanup;
+
+	if (cg_create(parent2))
+		goto cleanup;
+
+	child2 = cg_name(parent2, "cpucg_test_child");
+	if (!child2)
+		goto cleanup;
+
+	if (cg_create(child2))
+		goto cleanup;
+
+	if (!cg_read_strstr(child2, "cgroup.controllers", "cpu"))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(child);
+	free(child);
+	cg_destroy(child2);
+	free(child2);
+	cg_destroy(parent);
+	free(parent);
+	cg_destroy(parent2);
+	free(parent2);
+
+	return ret;
+}
+
+static void *hog_cpu_thread_func(void *arg)
+{
+	while (1)
+		;
+
+	return NULL;
+}
+
+static struct timespec
+timespec_sub(const struct timespec *lhs, const struct timespec *rhs)
+{
+	struct timespec zero = {
+		.tv_sec = 0,
+		.tv_nsec = 0,
+	};
+	struct timespec ret;
+
+	if (lhs->tv_sec < rhs->tv_sec)
+		return zero;
+
+	ret.tv_sec = lhs->tv_sec - rhs->tv_sec;
+
+	if (lhs->tv_nsec < rhs->tv_nsec) {
+		if (ret.tv_sec == 0)
+			return zero;
+
+		ret.tv_sec--;
+		ret.tv_nsec = NSEC_PER_SEC - rhs->tv_nsec + lhs->tv_nsec;
+	} else
+		ret.tv_nsec = lhs->tv_nsec - rhs->tv_nsec;
+
+	return ret;
+}
+
+static int hog_cpus_timed(const char *cgroup, void *arg)
+{
+	const struct cpu_hog_func_param *param =
+		(struct cpu_hog_func_param *)arg;
+	struct timespec ts_run = param->ts;
+	struct timespec ts_remaining = ts_run;
+	struct timespec ts_start;
+	int i, ret;
+
+	ret = clock_gettime(CLOCK_MONOTONIC, &ts_start);
+	if (ret != 0)
+		return ret;
+
+	for (i = 0; i < param->nprocs; i++) {
+		pthread_t tid;
+
+		ret = pthread_create(&tid, NULL, &hog_cpu_thread_func, NULL);
+		if (ret != 0)
+			return ret;
+	}
+
+	while (ts_remaining.tv_sec > 0 || ts_remaining.tv_nsec > 0) {
+		struct timespec ts_total;
+
+		ret = nanosleep(&ts_remaining, NULL);
+		if (ret && errno != EINTR)
+			return ret;
+
+		if (param->clock_type == CPU_HOG_CLOCK_PROCESS) {
+			ret = clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts_total);
+			if (ret != 0)
+				return ret;
+		} else {
+			struct timespec ts_current;
+
+			ret = clock_gettime(CLOCK_MONOTONIC, &ts_current);
+			if (ret != 0)
+				return ret;
+
+			ts_total = timespec_sub(&ts_current, &ts_start);
+		}
+
+		ts_remaining = timespec_sub(&ts_run, &ts_total);
+	}
+
+	return 0;
+}
+
+/*
+ * Creates a cpu cgroup, burns a CPU for a few quanta, and verifies that
+ * cpu.stat shows the expected output.
+ */
+static int test_cpucg_stats(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long usage_usec, user_usec, system_usec;
+	long usage_seconds = 2;
+	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
+	char *cpucg;
+
+	cpucg = cg_name(root, "cpucg_test");
+	if (!cpucg)
+		goto cleanup;
+
+	if (cg_create(cpucg))
+		goto cleanup;
+
+	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
+	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+	system_usec = cg_read_key_long(cpucg, "cpu.stat", "system_usec");
+	if (usage_usec != 0 || user_usec != 0 || system_usec != 0)
+		goto cleanup;
+
+	struct cpu_hog_func_param param = {
+		.nprocs = 1,
+		.ts = {
+			.tv_sec = usage_seconds,
+			.tv_nsec = 0,
+		},
+		.clock_type = CPU_HOG_CLOCK_PROCESS,
+	};
+	if (cg_run(cpucg, hog_cpus_timed, (void *)&param))
+		goto cleanup;
+
+	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
+	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+	if (user_usec <= 0)
+		goto cleanup;
+
+	if (!values_close_report(usage_usec, expected_usage_usec, 1))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(cpucg);
+	free(cpucg);
+
+	return ret;
+}
+
+/*
+ * Creates a nice process that consumes CPU and checks that the elapsed
+ * usertime in the cgroup is close to the expected time.
+ */
+static int test_cpucg_nice(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int status;
+	long user_usec, nice_usec;
+	long usage_seconds = 2;
+	long expected_nice_usec = usage_seconds * USEC_PER_SEC;
+	char *cpucg;
+	pid_t pid;
+
+	cpucg = cg_name(root, "cpucg_test");
+	if (!cpucg)
+		goto cleanup;
+
+	if (cg_create(cpucg))
+		goto cleanup;
+
+	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+	nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+	if (nice_usec == -1)
+		ret = KSFT_SKIP;
+	if (user_usec != 0 || nice_usec != 0)
+		goto cleanup;
+
+	/*
+	 * We fork here to create a new process that can be niced without
+	 * polluting the nice value of other selftests
+	 */
+	pid = fork();
+	if (pid < 0) {
+		goto cleanup;
+	} else if (pid == 0) {
+		struct cpu_hog_func_param param = {
+			.nprocs = 1,
+			.ts = {
+				.tv_sec = usage_seconds,
+				.tv_nsec = 0,
+			},
+			.clock_type = CPU_HOG_CLOCK_PROCESS,
+		};
+		char buf[64];
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cpucg, "cgroup.procs", buf))
+			exit(EXIT_FAILURE);
+
+		/* Try to keep niced CPU usage as constrained to hog_cpu as possible */
+		nice(1);
+		hog_cpus_timed(cpucg, &param);
+		exit(0);
+	} else {
+		waitpid(pid, &status, 0);
+		if (!WIFEXITED(status))
+			goto cleanup;
+
+		user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+		nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+		if (!values_close_report(nice_usec, expected_nice_usec, 1))
+			goto cleanup;
+
+		ret = KSFT_PASS;
+	}
+
+cleanup:
+	cg_destroy(cpucg);
+	free(cpucg);
+
+	return ret;
+}
+
+static int
+run_cpucg_weight_test(
+		const char *root,
+		pid_t (*spawn_child)(const struct cpu_hogger *child),
+		int (*validate)(const struct cpu_hogger *children, int num_children))
+{
+	int ret = KSFT_FAIL, i;
+	char *parent = NULL;
+	struct cpu_hogger children[3] = {};
+
+	parent = cg_name(root, "cpucg_test_0");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		children[i].cgroup = cg_name_indexed(parent, "cpucg_child", i);
+		if (!children[i].cgroup)
+			goto cleanup;
+
+		if (cg_create(children[i].cgroup))
+			goto cleanup;
+
+		if (cg_write_numeric(children[i].cgroup, "cpu.weight",
+					50 * (i + 1)))
+			goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		pid_t pid = spawn_child(&children[i]);
+		if (pid <= 0)
+			goto cleanup;
+		children[i].pid = pid;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		int retcode;
+
+		waitpid(children[i].pid, &retcode, 0);
+		if (!WIFEXITED(retcode))
+			goto cleanup;
+		if (WEXITSTATUS(retcode))
+			goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(children); i++)
+		children[i].usage = cg_read_key_long(children[i].cgroup,
+				"cpu.stat", "usage_usec");
+
+	if (validate(children, ARRAY_SIZE(children)))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		cg_destroy(children[i].cgroup);
+		free(children[i].cgroup);
+	}
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+static pid_t weight_hog_ncpus(const struct cpu_hogger *child, int ncpus)
+{
+	long usage_seconds = 10;
+	struct cpu_hog_func_param param = {
+		.nprocs = ncpus,
+		.ts = {
+			.tv_sec = usage_seconds,
+			.tv_nsec = 0,
+		},
+		.clock_type = CPU_HOG_CLOCK_WALL,
+	};
+	return cg_run_nowait(child->cgroup, hog_cpus_timed, (void *)&param);
+}
+
+static pid_t weight_hog_all_cpus(const struct cpu_hogger *child)
+{
+	return weight_hog_ncpus(child, get_nprocs());
+}
+
+static int
+overprovision_validate(const struct cpu_hogger *children, int num_children)
+{
+	int ret = KSFT_FAIL, i;
+
+	for (i = 0; i < num_children - 1; i++) {
+		long delta;
+
+		if (children[i + 1].usage <= children[i].usage)
+			goto cleanup;
+
+		delta = children[i + 1].usage - children[i].usage;
+		if (!values_close_report(delta, children[0].usage, 35))
+			goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+cleanup:
+	return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A
+ * A/B     cpu.weight = 50
+ * A/C     cpu.weight = 100
+ * A/D     cpu.weight = 150
+ *
+ * A separate process is then created for each child cgroup which spawns as
+ * many threads as there are cores, and hogs each CPU as much as possible
+ * for some time interval.
+ *
+ * Once all of the children have exited, we verify that each child cgroup
+ * was given proportional runtime as informed by their cpu.weight.
+ */
+static int test_cpucg_weight_overprovisioned(const char *root)
+{
+	return run_cpucg_weight_test(root, weight_hog_all_cpus,
+			overprovision_validate);
+}
+
+static pid_t weight_hog_one_cpu(const struct cpu_hogger *child)
+{
+	return weight_hog_ncpus(child, 1);
+}
+
+static int
+underprovision_validate(const struct cpu_hogger *children, int num_children)
+{
+	int ret = KSFT_FAIL, i;
+
+	for (i = 0; i < num_children - 1; i++) {
+		if (!values_close_report(children[i + 1].usage, children[0].usage, 15))
+			goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+cleanup:
+	return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A
+ * A/B     cpu.weight = 50
+ * A/C     cpu.weight = 100
+ * A/D     cpu.weight = 150
+ *
+ * A separate process is then created for each child cgroup which spawns a
+ * single thread that hogs a CPU. The testcase is only run on systems that
+ * have at least one core per-thread in the child processes.
+ *
+ * Once all of the children have exited, we verify that each child cgroup
+ * had roughly the same runtime despite having different cpu.weight.
+ */
+static int test_cpucg_weight_underprovisioned(const char *root)
+{
+	// Only run the test if there are enough cores to avoid overprovisioning
+	// the system.
+	if (get_nprocs() < 4)
+		return KSFT_SKIP;
+
+	return run_cpucg_weight_test(root, weight_hog_one_cpu,
+			underprovision_validate);
+}
+
+static int
+run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
+{
+	int ret = KSFT_FAIL, i;
+	char *parent = NULL, *child = NULL;
+	struct cpu_hogger leaf[3] = {};
+	long nested_leaf_usage, child_usage;
+	int nprocs = get_nprocs();
+
+	if (!overprovisioned) {
+		if (nprocs < 4)
+			/*
+			 * Only run the test if there are enough cores to avoid overprovisioning
+			 * the system.
+			 */
+			return KSFT_SKIP;
+		nprocs /= 4;
+	}
+
+	parent = cg_name(root, "cpucg_test");
+	child = cg_name(parent, "cpucg_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+	if (cg_write(child, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+	if (cg_write(child, "cpu.weight", "1000"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
+		const char *ancestor;
+		long weight;
+
+		if (i == 0) {
+			ancestor = parent;
+			weight = 1000;
+		} else {
+			ancestor = child;
+			weight = 5000;
+		}
+		leaf[i].cgroup = cg_name_indexed(ancestor, "cpucg_leaf", i);
+		if (!leaf[i].cgroup)
+			goto cleanup;
+
+		if (cg_create(leaf[i].cgroup))
+			goto cleanup;
+
+		if (cg_write_numeric(leaf[i].cgroup, "cpu.weight", weight))
+			goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
+		pid_t pid;
+		struct cpu_hog_func_param param = {
+			.nprocs = nprocs,
+			.ts = {
+				.tv_sec = 10,
+				.tv_nsec = 0,
+			},
+			.clock_type = CPU_HOG_CLOCK_WALL,
+		};
+
+		pid = cg_run_nowait(leaf[i].cgroup, hog_cpus_timed,
+				(void *)&param);
+		if (pid <= 0)
+			goto cleanup;
+		leaf[i].pid = pid;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
+		int retcode;
+
+		waitpid(leaf[i].pid, &retcode, 0);
+		if (!WIFEXITED(retcode))
+			goto cleanup;
+		if (WEXITSTATUS(retcode))
+			goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
+		leaf[i].usage = cg_read_key_long(leaf[i].cgroup,
+				"cpu.stat", "usage_usec");
+		if (leaf[i].usage <= 0)
+			goto cleanup;
+	}
+
+	nested_leaf_usage = leaf[1].usage + leaf[2].usage;
+	if (overprovisioned) {
+		if (!values_close_report(leaf[0].usage, nested_leaf_usage, 15))
+			goto cleanup;
+	} else if (!values_close_report(leaf[0].usage * 2, nested_leaf_usage, 15))
+		goto cleanup;
+
+
+	child_usage = cg_read_key_long(child, "cpu.stat", "usage_usec");
+	if (child_usage <= 0)
+		goto cleanup;
+	if (!values_close_report(child_usage, nested_leaf_usage, 1))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	for (i = 0; i < ARRAY_SIZE(leaf); i++) {
+		cg_destroy(leaf[i].cgroup);
+		free(leaf[i].cgroup);
+	}
+	cg_destroy(child);
+	free(child);
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A
+ * A/B     cpu.weight = 1000
+ * A/C     cpu.weight = 1000
+ * A/C/D   cpu.weight = 5000
+ * A/C/E   cpu.weight = 5000
+ *
+ * A separate process is then created for each leaf, which spawn nproc threads
+ * that burn a CPU for a few seconds.
+ *
+ * Once all of those processes have exited, we verify that each of the leaf
+ * cgroups have roughly the same usage from cpu.stat.
+ */
+static int
+test_cpucg_nested_weight_overprovisioned(const char *root)
+{
+	return run_cpucg_nested_weight_test(root, true);
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A
+ * A/B     cpu.weight = 1000
+ * A/C     cpu.weight = 1000
+ * A/C/D   cpu.weight = 5000
+ * A/C/E   cpu.weight = 5000
+ *
+ * A separate process is then created for each leaf, which nproc / 4 threads
+ * that burns a CPU for a few seconds.
+ *
+ * Once all of those processes have exited, we verify that each of the leaf
+ * cgroups have roughly the same usage from cpu.stat.
+ */
+static int
+test_cpucg_nested_weight_underprovisioned(const char *root)
+{
+	return run_cpucg_nested_weight_test(root, false);
+}
+
+/*
+ * This test creates a cgroup with some maximum value within a period, and
+ * verifies that a process in the cgroup is not overscheduled.
+ */
+static int test_cpucg_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
+	char *cpucg;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
+
+	cpucg = cg_name(root, "cpucg_test");
+	if (!cpucg)
+		goto cleanup;
+
+	if (cg_create(cpucg))
+		goto cleanup;
+
+	if (cg_write(cpucg, "cpu.max", quota_buf))
+		goto cleanup;
+
+	struct cpu_hog_func_param param = {
+		.nprocs = 1,
+		.ts = {
+			.tv_sec = duration_seconds,
+			.tv_nsec = 0,
+		},
+		.clock_type = CPU_HOG_CLOCK_WALL,
+	};
+	if (cg_run(cpucg, hog_cpus_timed, (void *)&param))
+		goto cleanup;
+
+	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
+	if (usage_usec <= 0)
+		goto cleanup;
+
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
+
+	if (!values_close_report(usage_usec, expected_usage_usec, 10))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(cpucg);
+	free(cpucg);
+
+	return ret;
+}
+
+/*
+ * This test verifies that a process inside of a nested cgroup whose parent
+ * group has a cpu.max value set, is properly throttled.
+ */
+static int test_cpucg_max_nested(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
+	char *parent, *child;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
+
+	parent = cg_name(root, "cpucg_parent");
+	child = cg_name(parent, "cpucg_child");
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpu"))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "cpu.max", quota_buf))
+		goto cleanup;
+
+	struct cpu_hog_func_param param = {
+		.nprocs = 1,
+		.ts = {
+			.tv_sec = duration_seconds,
+			.tv_nsec = 0,
+		},
+		.clock_type = CPU_HOG_CLOCK_WALL,
+	};
+	if (cg_run(child, hog_cpus_timed, (void *)&param))
+		goto cleanup;
+
+	usage_usec = cg_read_key_long(child, "cpu.stat", "usage_usec");
+	if (usage_usec <= 0)
+		goto cleanup;
+
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
+
+	if (!values_close_report(usage_usec, expected_usage_usec, 10))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(child);
+	free(child);
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct cpucg_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cpucg_subtree_control),
+	T(test_cpucg_stats),
+	T(test_cpucg_nice),
+	T(test_cpucg_weight_overprovisioned),
+	T(test_cpucg_weight_underprovisioned),
+	T(test_cpucg_nested_weight_overprovisioned),
+	T(test_cpucg_nested_weight_underprovisioned),
+	T(test_cpucg_max),
+	T(test_cpucg_max_nested),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "cpu"))
+		if (cg_write(root, "cgroup.subtree_control", "+cpu"))
+			ksft_exit_skip("Failed to set cpu controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_cpuset.c

@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/limits.h>
+#include <signal.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int idle_process_fn(const char *cgroup, void *arg)
+{
+	(void)pause();
+	return 0;
+}
+
+static int do_migration_fn(const char *cgroup, void *arg)
+{
+	int object_pid = (int)(size_t)arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	// XXX checking /proc/$pid/cgroup would be quicker than wait
+	if (cg_enter(cgroup, object_pid) ||
+	    cg_wait_for_proc_count(cgroup, 1))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+static int do_controller_fn(const char *cgroup, void *arg)
+{
+	const char *child = cgroup;
+	const char *parent = arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "-cpuset"))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+/*
+ * Migrate a process between two sibling cgroups.
+ * The success should only depend on the parent cgroup permissions and not the
+ * migrated process itself (cpuset controller is in place because it uses
+ * security_task_setscheduler() in cgroup v1).
+ *
+ * Deliberately don't set cpuset.cpus in children to avoid definining migration
+ * permissions between two different cpusets.
+ */
+static int test_cpuset_perms_object(const char *root, bool allow)
+{
+	char *parent = NULL, *child_src = NULL, *child_dst = NULL;
+	char *parent_procs = NULL, *child_src_procs = NULL, *child_dst_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child_src = cg_name(parent, "cpuset_test_1");
+	if (!child_src)
+		goto cleanup;
+	child_src_procs = cg_name(child_src, "cgroup.procs");
+	if (!child_src_procs)
+		goto cleanup;
+	if (cg_create(child_src))
+		goto cleanup;
+
+	child_dst = cg_name(parent, "cpuset_test_2");
+	if (!child_dst)
+		goto cleanup;
+	child_dst_procs = cg_name(child_dst, "cgroup.procs");
+	if (!child_dst_procs)
+		goto cleanup;
+	if (cg_create(child_dst))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		goto cleanup;
+
+	if (cg_read_strstr(child_src, "cgroup.controllers", "cpuset") ||
+	    cg_read_strstr(child_dst, "cgroup.controllers", "cpuset"))
+		goto cleanup;
+
+	/* Enable permissions along src->dst tree path */
+	if (chown(child_src_procs, test_euid, -1) ||
+	    chown(child_dst_procs, test_euid, -1))
+		goto cleanup;
+
+	if (allow && chown(parent_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Fork a privileged child as a test object */
+	object_pid = cg_run_nowait(child_src, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	/* Carry out migration in a child process that can drop all privileges
+	 * (including capabilities), the main process must remain privileged for
+	 * cleanup.
+	 * Child process's cgroup is irrelevant but we place it into child_dst
+	 * as hacky way to pass information about migration target to the child.
+	 */
+	if (allow ^ (cg_run(child_dst, do_migration_fn, (void *)(size_t)object_pid) == EXIT_SUCCESS))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child_dst);
+	free(child_dst_procs);
+	free(child_dst);
+
+	cg_destroy(child_src);
+	free(child_src_procs);
+	free(child_src);
+
+	cg_destroy(parent);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+static int test_cpuset_perms_object_allow(const char *root)
+{
+	return test_cpuset_perms_object(root, true);
+}
+
+static int test_cpuset_perms_object_deny(const char *root)
+{
+	return test_cpuset_perms_object(root, false);
+}
+
+/*
+ * Migrate a process between parent and child implicitely
+ * Implicit migration happens when a controller is enabled/disabled.
+ *
+ */
+static int test_cpuset_perms_subtree(const char *root)
+{
+	char *parent = NULL, *child = NULL;
+	char *parent_procs = NULL, *parent_subctl = NULL, *child_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	parent_subctl = cg_name(parent, "cgroup.subtree_control");
+	if (!parent_subctl)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child = cg_name(parent, "cpuset_test_1");
+	if (!child)
+		goto cleanup;
+	child_procs = cg_name(child, "cgroup.procs");
+	if (!child_procs)
+		goto cleanup;
+	if (cg_create(child))
+		goto cleanup;
+
+	/* Enable permissions as in a delegated subtree */
+	if (chown(parent_procs, test_euid, -1) ||
+	    chown(parent_subctl, test_euid, -1) ||
+	    chown(child_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Put a privileged child in the subtree and modify controller state
+	 * from an unprivileged process, the main process remains privileged
+	 * for cleanup.
+	 * The unprivileged child runs in subtree too to avoid parent and
+	 * internal-node constraing violation.
+	 */
+	object_pid = cg_run_nowait(child, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	if (cg_run(child, do_controller_fn, parent) != EXIT_SUCCESS)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child);
+	free(child_procs);
+	free(child);
+
+	cg_destroy(parent);
+	free(parent_subctl);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+
+#define T(x) { x, #x }
+struct cpuset_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cpuset_perms_object_allow),
+	T(test_cpuset_perms_object_deny),
+	T(test_cpuset_perms_subtree),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset"))
+		if (cg_write(root, "cgroup.subtree_control", "+cpuset"))
+			ksft_exit_skip("Failed to set cpuset controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh

@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Basc test for cpuset v1 interfaces write/read
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+write_test() {
+	dir=$1
+	interface=$2
+	value=$3
+	original=$(cat $dir/$interface)
+	echo "testing $interface $value"
+	echo $value > $dir/$interface
+	new=$(cat $dir/$interface)
+	[[ "$value" != "$new" ]] && {
+		echo "$interface write $value failed: new:$new"
+		exit 1
+	}
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, read write test
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+
+ITF_MATRIX=(
+	#interface			value		expect 	root_only
+	'cpuset.cpus			0-1		0-1	0'
+	'cpuset.mem_exclusive		1		1	0'
+	'cpuset.mem_exclusive		0		0	0'
+	'cpuset.mem_hardwall		1		1	0'
+	'cpuset.mem_hardwall		0		0	0'
+	'cpuset.memory_migrate		1		1	0'
+	'cpuset.memory_migrate		0		0	0'
+	'cpuset.memory_spread_page	1		1	0'
+	'cpuset.memory_spread_page	0		0	0'
+	'cpuset.memory_spread_slab	1		1	0'
+	'cpuset.memory_spread_slab	0		0	0'
+	'cpuset.mems			0		0	0'
+	'cpuset.sched_load_balance	1		1	0'
+	'cpuset.sched_load_balance	0		0	0'
+	'cpuset.sched_relax_domain_level	2	2	0'
+	'cpuset.memory_pressure_enabled	1		1	1'
+	'cpuset.memory_pressure_enabled	0		0	1'
+)
+
+run_test()
+{
+	cnt="${ITF_MATRIX[@]}"
+	for i in "${ITF_MATRIX[@]}" ; do
+		args=($i)
+		root_only=${args[3]}
+		[[ $root_only -eq 1 ]] && {
+			write_test "$CPUSET" "${args[0]}" "${args[1]}" "${args[2]}"
+			continue
+		}
+		write_test "$CPUSET/$TDIR" "${args[0]}" "${args[1]}" "${args[2]}"
+	done
+}
+
+run_test
+rmdir $CPUSET/$TDIR
+echo "Test PASSED"
+exit 0

linux-7.2.3/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test the special cpuset v1 hotplug case where a cpuset become empty of
+# CPUs will force migration of tasks out to an ancestor.
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk -e '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, put a CPU and a task there and offline that CPU
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+echo 1 > $CPUSET/$TDIR/cpuset.cpus
+echo 0 > $CPUSET/$TDIR/cpuset.mems
+sleep 10&
+TASK=$!
+echo $TASK > $CPUSET/$TDIR/tasks
+NEWCS=$(cat /proc/$TASK/cpuset)
+[[ $NEWCS != "/$TDIR" ]] && {
+	echo "Unexpected cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+
+echo 0 > /sys/devices/system/cpu/cpu1/online
+sleep 0.5
+echo 1 > /sys/devices/system/cpu/cpu1/online
+NEWCS=$(cat /proc/$TASK/cpuset)
+rmdir $CPUSET/$TDIR
+[[ $NEWCS != "/" ]] && {
+	echo "cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+echo "Test PASSED"
+exit 0

linux-7.2.3/tools/testing/selftests/cgroup/test_hugetlb_memcg.c

@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <sys/mman.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+#define ADDR ((void *)(0x0UL))
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+/* mapping 8 MBs == 4 hugepages */
+#define LENGTH (8UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* borrowed from mm/hmm-tests.c */
+static long get_hugepage_size(void)
+{
+	int fd;
+	char buf[2048];
+	int len;
+	char *p, *q, *path = "/proc/meminfo", *tag = "Hugepagesize:";
+	long val;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		/* Error opening the file */
+		return -1;
+	}
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0) {
+		/* Error in reading the file */
+		return -1;
+	}
+	if (len == sizeof(buf)) {
+		/* Error file is too large */
+		return -1;
+	}
+	buf[len] = '\0';
+
+	/* Search for a tag if provided */
+	if (tag) {
+		p = strstr(buf, tag);
+		if (!p)
+			return -1; /* looks like the line we want isn't there */
+		p += strlen(tag);
+	} else
+		p = buf;
+
+	val = strtol(p, &q, 0);
+	if (*q != ' ') {
+		/* Error parsing the file */
+		return -1;
+	}
+
+	return val;
+}
+
+static int set_file(const char *path, long value)
+{
+	FILE *file;
+	int ret;
+
+	file = fopen(path, "w");
+	if (!file)
+		return -1;
+	ret = fprintf(file, "%ld\n", value);
+	fclose(file);
+	return ret;
+}
+
+static int set_nr_hugepages(long value)
+{
+	return set_file("/proc/sys/vm/nr_hugepages", value);
+}
+
+static unsigned int check_first(char *addr)
+{
+	return *(unsigned int *)addr;
+}
+
+static void write_data(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int hugetlb_test_program(const char *cgroup, void *arg)
+{
+	char *test_group = (char *)arg;
+	void *addr;
+	long old_current, expected_current, current;
+	int ret = EXIT_FAILURE;
+
+	old_current = cg_read_long(test_group, "memory.current");
+	set_nr_hugepages(20);
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg(
+			"setting nr_hugepages should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		return EXIT_FAILURE;
+	}
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
+	if (addr == MAP_FAILED) {
+		ksft_print_msg("fail to mmap.\n");
+		return EXIT_FAILURE;
+	}
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg("mmap should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		goto out_failed_munmap;
+	}
+	old_current = current;
+
+	/* read the first page */
+	check_first(addr);
+	expected_current = old_current + MB(2);
+	current = cg_read_long(test_group, "memory.current");
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 2MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* write to the whole range */
+	write_data(addr);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current + MB(8);
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 8MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* unmap the whole range */
+	munmap(addr, LENGTH);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current;
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should go back down.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		return ret;
+	}
+
+	ret = EXIT_SUCCESS;
+	return ret;
+
+out_failed_munmap:
+	munmap(addr, LENGTH);
+	return ret;
+}
+
+static int test_hugetlb_memcg(char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "hugetlb_memcg_test");
+	if (!test_group || cg_create(test_group)) {
+		ksft_print_msg("fail to create cgroup.\n");
+		goto out;
+	}
+
+	if (cg_write(test_group, "memory.max", "100M")) {
+		ksft_print_msg("fail to set cgroup memory limit.\n");
+		goto out;
+	}
+
+	/* disable swap */
+	if (cg_write(test_group, "memory.swap.max", "0")) {
+		ksft_print_msg("fail to disable swap.\n");
+		goto out;
+	}
+
+	if (!cg_run(test_group, hugetlb_test_program, (void *)test_group))
+		ret = KSFT_PASS;
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int ret = EXIT_SUCCESS, has_memory_hugetlb_acc;
+
+	has_memory_hugetlb_acc = proc_mount_contains("memory_hugetlb_accounting");
+	if (has_memory_hugetlb_acc < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	else if (!has_memory_hugetlb_acc)
+		ksft_exit_skip("memory hugetlb accounting is disabled\n");
+
+	/* Unit is kB! */
+	if (get_hugepage_size() != 2048) {
+		ksft_print_msg("test_hugetlb_memcg requires 2MB hugepages\n");
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		return ret;
+	}
+
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory")) {
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+	}
+
+	switch (test_hugetlb_memcg(root)) {
+	case KSFT_PASS:
+		ksft_test_result_pass("test_hugetlb_memcg\n");
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		break;
+	default:
+		ret = EXIT_FAILURE;
+		ksft_test_result_fail("test_hugetlb_memcg\n");
+		break;
+	}
+
+	return ret;
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_kill.c

@@ -0,0 +1,299 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <errno.h>
+#include <linux/limits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+#include "../pidfd/pidfd.h"
+#include "cgroup_util.h"
+
+/*
+ * Kill the given cgroup and wait for the inotify signal.
+ * If there are no events in 10 seconds, treat this as an error.
+ * Then check that the cgroup is in the desired state.
+ */
+static int cg_kill_wait(const char *cgroup)
+{
+	int fd, ret = -1;
+
+	fd = cg_prepare_for_wait(cgroup);
+	if (fd < 0)
+		return fd;
+
+	ret = cg_write(cgroup, "cgroup.kill", "1");
+	if (ret)
+		goto out;
+
+	ret = cg_wait_for(fd);
+	if (ret)
+		goto out;
+
+out:
+	close(fd);
+	return ret;
+}
+
+/*
+ * A simple process running in a sleep loop until being
+ * re-parented.
+ */
+static int child_fn(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+
+	while (getppid() == ppid)
+		usleep(1000);
+
+	return getppid() == ppid;
+}
+
+static int test_cgkill_simple(const char *root)
+{
+	pid_t pids[100];
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	int i;
+
+	cgroup = cg_name(root, "cg_test_simple");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	for (i = 0; i < 100; i++)
+		pids[i] = cg_run_nowait(cgroup, child_fn, NULL);
+
+	if (cg_wait_for_proc_count(cgroup, 100))
+		goto cleanup;
+
+	if (cg_read_strcmp(cgroup, "cgroup.events", "populated 1\n"))
+		goto cleanup;
+
+	if (cg_kill_wait(cgroup))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = 0; i < 100; i++)
+		wait_for_pid(pids[i]);
+
+	if (ret == KSFT_PASS &&
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
+		ret = KSFT_FAIL;
+
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * The test creates the following hierarchy:
+ *       A
+ *    / / \ \
+ *   B  E  I K
+ *  /\  |
+ * C  D F
+ *      |
+ *      G
+ *      |
+ *      H
+ *
+ * with a process in C, H and 3 processes in K.
+ * Then it tries to kill the whole tree.
+ */
+static int test_cgkill_tree(const char *root)
+{
+	pid_t pids[5];
+	char *cgroup[10] = {0};
+	int ret = KSFT_FAIL;
+	int i;
+
+	cgroup[0] = cg_name(root, "cg_test_tree_A");
+	if (!cgroup[0])
+		goto cleanup;
+
+	cgroup[1] = cg_name(cgroup[0], "B");
+	if (!cgroup[1])
+		goto cleanup;
+
+	cgroup[2] = cg_name(cgroup[1], "C");
+	if (!cgroup[2])
+		goto cleanup;
+
+	cgroup[3] = cg_name(cgroup[1], "D");
+	if (!cgroup[3])
+		goto cleanup;
+
+	cgroup[4] = cg_name(cgroup[0], "E");
+	if (!cgroup[4])
+		goto cleanup;
+
+	cgroup[5] = cg_name(cgroup[4], "F");
+	if (!cgroup[5])
+		goto cleanup;
+
+	cgroup[6] = cg_name(cgroup[5], "G");
+	if (!cgroup[6])
+		goto cleanup;
+
+	cgroup[7] = cg_name(cgroup[6], "H");
+	if (!cgroup[7])
+		goto cleanup;
+
+	cgroup[8] = cg_name(cgroup[0], "I");
+	if (!cgroup[8])
+		goto cleanup;
+
+	cgroup[9] = cg_name(cgroup[0], "K");
+	if (!cgroup[9])
+		goto cleanup;
+
+	for (i = 0; i < 10; i++)
+		if (cg_create(cgroup[i]))
+			goto cleanup;
+
+	pids[0] = cg_run_nowait(cgroup[2], child_fn, NULL);
+	pids[1] = cg_run_nowait(cgroup[7], child_fn, NULL);
+	pids[2] = cg_run_nowait(cgroup[9], child_fn, NULL);
+	pids[3] = cg_run_nowait(cgroup[9], child_fn, NULL);
+	pids[4] = cg_run_nowait(cgroup[9], child_fn, NULL);
+
+	/*
+	 * Wait until all child processes will enter
+	 * corresponding cgroups.
+	 */
+
+	if (cg_wait_for_proc_count(cgroup[2], 1) ||
+	    cg_wait_for_proc_count(cgroup[7], 1) ||
+	    cg_wait_for_proc_count(cgroup[9], 3))
+		goto cleanup;
+
+	/*
+	 * Kill A and check that we get an empty notification.
+	 */
+	if (cg_kill_wait(cgroup[0]))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = 0; i < 5; i++)
+		wait_for_pid(pids[i]);
+
+	if (ret == KSFT_PASS &&
+	    cg_read_strcmp_wait(cgroup[0], "cgroup.events",
+				   "populated 0\n"))
+		ret = KSFT_FAIL;
+
+	for (i = 9; i >= 0 && cgroup[i]; i--) {
+		cg_destroy(cgroup[i]);
+		free(cgroup[i]);
+	}
+
+	return ret;
+}
+
+static int forkbomb_fn(const char *cgroup, void *arg)
+{
+	int ppid;
+
+	fork();
+	fork();
+
+	ppid = getppid();
+
+	while (getppid() == ppid)
+		usleep(1000);
+
+	return getppid() == ppid;
+}
+
+/*
+ * The test runs a fork bomb in a cgroup and tries to kill it.
+ */
+static int test_cgkill_forkbomb(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	pid_t pid = -ESRCH;
+
+	cgroup = cg_name(root, "cg_forkbomb_test");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup, forkbomb_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	usleep(100000);
+
+	if (cg_kill_wait(cgroup))
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup, 0))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (pid > 0)
+		wait_for_pid(pid);
+
+	if (ret == KSFT_PASS &&
+	    cg_read_strcmp_wait(cgroup, "cgroup.events", "populated 0\n"))
+		ret = KSFT_FAIL;
+
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct cgkill_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cgkill_simple),
+	T(test_cgkill_tree),
+	T(test_cgkill_forkbomb),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_kmem.c

@@ -0,0 +1,459 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <sys/sysinfo.h>
+#include <pthread.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+
+/*
+ * Memory cgroup charging is performed using percpu batches 64 pages
+ * big (look at MEMCG_CHARGE_BATCH), whereas memory.stat is exact. So
+ * the maximum discrepancy between charge and vmstat entries is number
+ * of cpus multiplied by 64 pages.
+ */
+#define MAX_VMSTAT_ERROR (sysconf(_SC_PAGESIZE) * 64 * get_nprocs())
+
+#define KMEM_DEAD_WAIT_RETRIES        80
+
+static int alloc_dcache(const char *cgroup, void *arg)
+{
+	unsigned long i;
+	struct stat st;
+	char buf[128];
+
+	for (i = 0; i < (unsigned long)arg; i++) {
+		snprintf(buf, sizeof(buf),
+			"/something-non-existent-with-a-long-name-%64lu-%d",
+			 i, getpid());
+		stat(buf, &st);
+	}
+
+	return 0;
+}
+
+/*
+ * This test allocates 100000 of negative dentries with long names.
+ * Then it checks that "slab" in memory.stat is larger than 1M.
+ * Then it sets memory.high to 1M and checks that at least 1/2
+ * of slab memory has been reclaimed.
+ */
+static int test_kmem_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+	long slab0, slab1, current;
+
+	cg = cg_name(root, "kmem_basic_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, alloc_dcache, (void *)100000))
+		goto cleanup;
+
+	slab0 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab0 < (1 << 20))
+		goto cleanup;
+
+	cg_write(cg, "memory.high", "1M");
+
+	/* wait for RCU freeing */
+	sleep(1);
+
+	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
+	if (slab1 < 0)
+		goto cleanup;
+
+	current = cg_read_long(cg, "memory.current");
+	if (current < 0)
+		goto cleanup;
+
+	if (slab1 < slab0 / 2 && current < slab0 / 2)
+		ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+static void *alloc_kmem_fn(void *arg)
+{
+	alloc_dcache(NULL, (void *)100);
+	return NULL;
+}
+
+static int alloc_kmem_smp(const char *cgroup, void *arg)
+{
+	int nr_threads = 2 * get_nprocs();
+	pthread_t *tinfo;
+	unsigned long i;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &alloc_kmem_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return -1;
+		}
+	}
+
+	for (i = 0; i < nr_threads; i++) {
+		ret = pthread_join(tinfo[i], NULL);
+		if (ret)
+			break;
+	}
+
+	free(tinfo);
+	return ret;
+}
+
+static int cg_run_in_subcgroups(const char *parent,
+				int (*fn)(const char *cgroup, void *arg),
+				void *arg, int times)
+{
+	char *child;
+	int i;
+
+	for (i = 0; i < times; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child)
+			return -1;
+
+		if (cg_create(child)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		if (cg_run(child, fn, NULL)) {
+			cg_destroy(child);
+			free(child);
+			return -1;
+		}
+
+		cg_destroy(child);
+		free(child);
+	}
+
+	return 0;
+}
+
+/*
+ * The test creates and destroys a large number of cgroups. In each cgroup it
+ * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS
+ * threads. Then it checks the sanity of numbers on the parent level:
+ * the total size of the cgroups should be roughly equal to
+ * anon + file + kernel + sock.
+ */
+static int test_kmem_memcg_deletion(const char *root)
+{
+	long current, anon, file, kernel, sock, sum;
+	int ret = KSFT_FAIL;
+	char *parent;
+
+	parent = cg_name(root, "kmem_memcg_deletion_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_kmem_smp, NULL, 100))
+		goto cleanup;
+
+	current = cg_read_long(parent, "memory.current");
+	anon = cg_read_key_long(parent, "memory.stat", "anon ");
+	file = cg_read_key_long(parent, "memory.stat", "file ");
+	kernel = cg_read_key_long(parent, "memory.stat", "kernel ");
+	sock = cg_read_key_long(parent, "memory.stat", "sock ");
+	if (current < 0 || anon < 0 || file < 0 || kernel < 0 || sock < 0)
+		goto cleanup;
+
+	sum = anon + file + kernel + sock;
+	if (labs(sum - current) < MAX_VMSTAT_ERROR) {
+		ret = KSFT_PASS;
+	} else {
+		printf("memory.current = %ld\n", current);
+		printf("anon + file + kernel + sock = %ld\n", sum);
+		printf("anon = %ld\n", anon);
+		printf("file = %ld\n", file);
+		printf("kernel = %ld\n", kernel);
+		printf("sock = %ld\n", sock);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * The test reads the entire /proc/kpagecgroup. If the operation went
+ * successfully (and the kernel didn't panic), the test is treated as passed.
+ */
+static int test_kmem_proc_kpagecgroup(const char *root)
+{
+	unsigned long buf[128];
+	int ret = KSFT_FAIL;
+	ssize_t len;
+	int fd;
+
+	fd = open("/proc/kpagecgroup", O_RDONLY);
+	if (fd < 0)
+		return ret;
+
+	do {
+		len = read(fd, buf, sizeof(buf));
+	} while (len > 0);
+
+	if (len == 0)
+		ret = KSFT_PASS;
+
+	close(fd);
+	return ret;
+}
+
+static void *pthread_wait_fn(void *arg)
+{
+	sleep(100);
+	return NULL;
+}
+
+static int spawn_1000_threads(const char *cgroup, void *arg)
+{
+	int nr_threads = 1000;
+	pthread_t *tinfo;
+	unsigned long i;
+	long stack;
+	int ret = -1;
+
+	tinfo = calloc(nr_threads, sizeof(pthread_t));
+	if (tinfo == NULL)
+		return -1;
+
+	for (i = 0; i < nr_threads; i++) {
+		if (pthread_create(&tinfo[i], NULL, &pthread_wait_fn,
+				   (void *)i)) {
+			free(tinfo);
+			return(-1);
+		}
+	}
+
+	stack = cg_read_key_long(cgroup, "memory.stat", "kernel_stack ");
+	if (stack >= 4096 * 1000)
+		ret = 0;
+
+	free(tinfo);
+	return ret;
+}
+
+/*
+ * The test spawns a process, which spawns 1000 threads. Then it checks
+ * that memory.stat's kernel_stack is at least 1000 pages large.
+ */
+static int test_kmem_kernel_stacks(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg = NULL;
+
+	cg = cg_name(root, "kmem_kernel_stacks_test");
+	if (!cg)
+		goto cleanup;
+
+	if (cg_create(cg))
+		goto cleanup;
+
+	if (cg_run(cg, spawn_1000_threads, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(cg);
+	free(cg);
+
+	return ret;
+}
+
+/*
+ * This test sequentionally creates 30 child cgroups, allocates some
+ * kernel memory in each of them, and deletes them. Then it checks
+ * that the number of dying cgroups on the parent level is 0.
+ */
+static int test_kmem_dead_cgroups(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent;
+	long dead = -1;
+
+	parent = cg_name(root, "kmem_dead_cgroups_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
+		goto cleanup;
+
+	/*
+	 * Allow up to ~8s for reclaim of dying descendants to complete.
+	 * This is a generous upper bound derived from stress testing, not
+	 * from a specific kernel constant, and can be adjusted if reclaim
+	 * behavior changes in the future.
+	 */
+	dead = cg_read_key_long_poll(parent, "cgroup.stat",
+					"nr_dying_descendants ", 0, KMEM_DEAD_WAIT_RETRIES,
+					DEFAULT_WAIT_INTERVAL_US);
+	if (dead)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test creates a sub-tree with 1000 memory cgroups.
+ * Then it checks that the memory.current on the parent level
+ * is greater than 0 and approximates matches the percpu value
+ * from memory.stat.
+ */
+static int test_percpu_basic(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+	long current, percpu, slab;
+	int i;
+
+	parent = cg_name(root, "percpu_basic_test");
+	if (!parent)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		if (!child) {
+			ret = -1;
+			goto cleanup_children;
+		}
+
+		if (cg_create(child)) {
+			free(child);
+			goto cleanup_children;
+		}
+
+		free(child);
+	}
+
+	current = cg_read_long(parent, "memory.current");
+	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+	slab = cg_read_key_long(parent, "memory.stat", "slab ");
+
+	if (current > 0 && percpu > 0 && slab >= 0 &&
+			labs(current - (percpu + slab)) < MAX_VMSTAT_ERROR)
+		ret = KSFT_PASS;
+	else
+		printf("memory.current %ld\npercpu %ld\nslab %ld\ndelta %ld\n",
+			current, percpu, slab, current - (percpu + slab));
+
+cleanup_children:
+	for (i = 0; i < 1000; i++) {
+		child = cg_name_indexed(parent, "child", i);
+		cg_destroy(child);
+		free(child);
+	}
+
+cleanup:
+	cg_destroy(parent);
+	free(parent);
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct kmem_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_kmem_basic),
+	T(test_kmem_memcg_deletion),
+	T(test_kmem_proc_kpagecgroup),
+	T(test_kmem_kernel_stacks),
+	T(test_kmem_dead_cgroups),
+	T(test_percpu_basic),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_pids.c

@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <linux/limits.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int run_success(const char *cgroup, void *arg)
+{
+	return 0;
+}
+
+static int run_pause(const char *cgroup, void *arg)
+{
+	return pause();
+}
+
+/*
+ * This test checks that pids.max prevents forking new children above the
+ * specified limit in the cgroup.
+ */
+static int test_pids_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_pids;
+	int pid;
+
+	cg_pids = cg_name(root, "pids_test");
+	if (!cg_pids)
+		goto cleanup;
+
+	if (cg_create(cg_pids))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_pids, "pids.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(cg_pids, "pids.max", "2"))
+		goto cleanup;
+
+	if (cg_enter_current(cg_pids))
+		goto cleanup;
+
+	pid = cg_run_nowait(cg_pids, run_pause, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_run_nowait(cg_pids, run_success, NULL) != -1 || errno != EAGAIN)
+		goto cleanup;
+
+	if (kill(pid, SIGINT))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	cg_destroy(cg_pids);
+	free(cg_pids);
+
+	return ret;
+}
+
+/*
+ * This test checks that pids.events are counted in cgroup associated with pids.max
+ */
+static int test_pids_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_parent = NULL, *cg_child = NULL;
+	int pid;
+
+	if (cgroup_feature("pids_localevents") <= 0)
+		return KSFT_SKIP;
+
+	cg_parent = cg_name(root, "pids_parent");
+	cg_child = cg_name(cg_parent, "pids_child");
+	if (!cg_parent || !cg_child)
+		goto cleanup;
+
+	if (cg_create(cg_parent))
+		goto cleanup;
+	if (cg_write(cg_parent, "cgroup.subtree_control", "+pids"))
+		goto cleanup;
+	if (cg_create(cg_child))
+		goto cleanup;
+
+	if (cg_write(cg_parent, "pids.max", "2"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_child, "pids.max", "max\n"))
+		goto cleanup;
+
+	if (cg_enter_current(cg_child))
+		goto cleanup;
+
+	pid = cg_run_nowait(cg_child, run_pause, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_run_nowait(cg_child, run_success, NULL) != -1 || errno != EAGAIN)
+		goto cleanup;
+
+	if (kill(pid, SIGINT))
+		goto cleanup;
+
+	if (cg_read_key_long(cg_child, "pids.events", "max ") != 0)
+		goto cleanup;
+	if (cg_read_key_long(cg_parent, "pids.events", "max ") != 1)
+		goto cleanup;
+
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_child)
+		cg_destroy(cg_child);
+	if (cg_parent)
+		cg_destroy(cg_parent);
+	free(cg_child);
+	free(cg_parent);
+
+	return ret;
+}
+
+
+
+#define T(x) { x, #x }
+struct pids_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_pids_max),
+	T(test_pids_events),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that pids controller is available:
+	 * pids is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "pids"))
+		ksft_exit_skip("pids controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "pids"))
+		if (cg_write(root, "cgroup.subtree_control", "+pids"))
+			ksft_exit_skip("Failed to set pids controller\n");
+
+	for (int i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/test_stress.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+./with_stress.sh -s subsys -s fork ${OUTPUT:-.}/test_core

linux-7.2.3/tools/testing/selftests/cgroup/test_zswap.c

@@ -0,0 +1,845 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <signal.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/sysinfo.h>
+#include <string.h>
+#include <sys/wait.h>
+#include <sys/mman.h>
+#include <sys/random.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int page_size;
+
+#define PATH_ZSWAP "/sys/module/zswap"
+#define PATH_ZSWAP_ENABLED "/sys/module/zswap/parameters/enabled"
+
+static int read_int(const char *path, size_t *value)
+{
+	FILE *file;
+	int ret = 0;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -1;
+	if (fscanf(file, "%ld", value) != 1)
+		ret = -1;
+	fclose(file);
+	return ret;
+}
+
+static int set_min_free_kb(size_t value)
+{
+	FILE *file;
+	int ret;
+
+	file = fopen("/proc/sys/vm/min_free_kbytes", "w");
+	if (!file)
+		return -1;
+	ret = fprintf(file, "%ld\n", value);
+	fclose(file);
+	return ret;
+}
+
+static int read_min_free_kb(size_t *value)
+{
+	return read_int("/proc/sys/vm/min_free_kbytes", value);
+}
+
+static int get_zswap_stored_pages(size_t *value)
+{
+	return read_int("/sys/kernel/debug/zswap/stored_pages", value);
+}
+
+static long get_cg_wb_count(const char *cg)
+{
+	return cg_read_key_long(cg, "memory.stat", "zswpwb");
+}
+
+static long get_zswpout(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "memory.stat", "zswpout ");
+}
+
+static int allocate_and_read_bytes(const char *cgroup, void *arg)
+{
+	size_t size = (size_t)arg;
+	char *mem = (char *)malloc(size);
+	int ret = 0;
+
+	if (!mem)
+		return -1;
+	for (int i = 0; i < size; i += page_size)
+		mem[i] = 'a';
+
+	/* Go through the allocated memory to (z)swap in and out pages */
+	for (int i = 0; i < size; i += page_size) {
+		if (mem[i] != 'a')
+			ret = -1;
+	}
+
+	free(mem);
+	return ret;
+}
+
+static int allocate_bytes(const char *cgroup, void *arg)
+{
+	size_t size = (size_t)arg;
+	char *mem = (char *)malloc(size);
+
+	if (!mem)
+		return -1;
+	for (int i = 0; i < size; i += page_size)
+		mem[i] = 'a';
+	free(mem);
+	return 0;
+}
+
+static char *setup_test_group_1M(const char *root, const char *name)
+{
+	char *group_name = cg_name(root, name);
+
+	if (!group_name)
+		return NULL;
+	if (cg_create(group_name))
+		goto fail;
+	if (cg_write(group_name, "memory.max", "1M")) {
+		cg_destroy(group_name);
+		goto fail;
+	}
+	return group_name;
+fail:
+	free(group_name);
+	return NULL;
+}
+
+/*
+ * Writeback is asynchronous; poll until at least one writeback has
+ * been recorded for @cg, or until @timeout_ms has elapsed.
+ */
+static long wait_for_writeback(const char *cg, int timeout_ms)
+{
+	long elapsed, count;
+	for (elapsed = 0; elapsed < timeout_ms; elapsed += 100) {
+		count = get_cg_wb_count(cg);
+
+		if (count < 0)
+			return -1;
+		if (count > 0)
+			return count;
+
+		usleep(100000);
+	}
+
+	return 0;
+}
+
+/*
+ * Sanity test to check that pages are written into zswap.
+ */
+static int test_zswap_usage(const char *root)
+{
+	long zswpout_before, zswpout_after;
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "no_shrink_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "1M"))
+		goto out;
+
+	zswpout_before = get_zswpout(test_group);
+	if (zswpout_before < 0) {
+		ksft_print_msg("Failed to get zswpout\n");
+		goto out;
+	}
+
+	/* Allocate more than memory.max to push memory into zswap */
+	if (cg_run(test_group, allocate_bytes, (void *)MB(4)))
+		goto out;
+
+	/* Verify that pages come into zswap */
+	zswpout_after = get_zswpout(test_group);
+	if (zswpout_after <= zswpout_before) {
+		ksft_print_msg("zswpout does not increase after test program\n");
+		goto out;
+	}
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
+ * Check that when memory.zswap.max = 0, no pages can go to the zswap pool for
+ * the cgroup.
+ */
+static int test_swapin_nozswap(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group, mem_max_buf[32];
+	long swap_peak, zswpout, min_swap;
+	size_t allocation_size = page_size * 512;
+
+	min_swap = allocation_size / 4;
+	snprintf(mem_max_buf, sizeof(mem_max_buf), "%zu", allocation_size * 3/4);
+
+	test_group = cg_name(root, "no_zswap_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", mem_max_buf))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "0"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger swapin */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)allocation_size))
+		goto out;
+
+	/* Verify that pages are swapped out, but no zswap happened */
+	swap_peak = cg_read_long(test_group, "memory.swap.peak");
+	if (swap_peak < 0) {
+		ksft_print_msg("failed to get cgroup's swap_peak\n");
+		goto out;
+	}
+
+	if (swap_peak < min_swap) {
+		ksft_print_msg("at least %ldKB of memory should be swapped out\n",
+				min_swap / 1024);
+		goto out;
+	}
+
+	zswpout = get_zswpout(test_group);
+	if (zswpout < 0) {
+		ksft_print_msg("failed to get zswpout\n");
+		goto out;
+	}
+
+	if (zswpout > 0) {
+		ksft_print_msg("zswapout > 0 when memory.zswap.max = 0\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/* Simple test to verify the (z)swapin code paths */
+static int test_zswapin(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+	long zswpin;
+
+	test_group = cg_name(root, "zswapin_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "8M"))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger (z)swap in */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+		goto out;
+
+	zswpin = cg_read_key_long(test_group, "memory.stat", "zswpin ");
+	if (zswpin < 0) {
+		ksft_print_msg("failed to get zswpin\n");
+		goto out;
+	}
+
+	if (zswpin < MB(24) / page_size) {
+		ksft_print_msg("at least 24MB should be brought back from zswap\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
+ * Attempt writeback with the following steps:
+ * 1. Allocate memory.
+ * 2. Reclaim memory equal to the amount that was allocated in step 1.
+      This will move it into zswap.
+ * 3. Save current zswap usage.
+ * 4. Move the memory allocated in step 1 back in from zswap.
+ * 5. Set zswap.max to 1/4 of the amount that was recorded in step 3.
+ * 6. Attempt to reclaim memory equal to the amount that was allocated,
+      this will either trigger writeback if it's enabled, or reclamation
+      will fail if writeback is disabled as there isn't enough zswap space.
+ */
+static int attempt_writeback(const char *cgroup, void *arg)
+{
+	size_t memsize = page_size * 1024;
+	char buf[page_size];
+	long zswap_usage;
+	bool wb_enabled = *(bool *) arg;
+	int ret = -1;
+	char *mem;
+
+	mem = (char *)malloc(memsize);
+	if (!mem)
+		return ret;
+
+	/*
+	 * Fill half of each page with increasing data, and keep other
+	 * half empty, this will result in data that is still compressible
+	 * and ends up in zswap, with material zswap usage.
+	 */
+	for (int i = 0; i < page_size; i++)
+		buf[i] = i < page_size/2 ? (char) i : 0;
+
+	for (int i = 0; i < memsize; i += page_size)
+		memcpy(&mem[i], buf, page_size);
+
+	/* Try and reclaim allocated memory */
+	if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
+		ksft_print_msg("Failed to reclaim all of the requested memory\n");
+		goto out;
+	}
+
+	zswap_usage = cg_read_long(cgroup, "memory.zswap.current");
+
+	/* zswpin */
+	for (int i = 0; i < memsize; i += page_size) {
+		if (memcmp(&mem[i], buf, page_size)) {
+			ksft_print_msg("invalid memory\n");
+			goto out;
+		}
+	}
+
+	if (cg_write_numeric(cgroup, "memory.zswap.max", zswap_usage/4))
+		goto out;
+
+	/*
+	 * If writeback is enabled, trying to reclaim memory now will trigger a
+	 * writeback as zswap.max is 1/4 of what was needed when reclaim ran the first time.
+	 * If writeback is disabled, memory reclaim will fail as zswap is limited and
+	 * it can't writeback to swap.
+	 */
+	ret = cg_write_numeric(cgroup, "memory.reclaim", memsize);
+	if (!wb_enabled)
+		ret = (ret == -EAGAIN) ? 0 : -1;
+
+out:
+	free(mem);
+	return ret;
+}
+
+static int test_zswap_writeback_one(const char *cgroup, bool wb)
+{
+	long zswpwb_before, zswpwb_after;
+
+	zswpwb_before = get_cg_wb_count(cgroup);
+	if (zswpwb_before != 0) {
+		ksft_print_msg("zswpwb_before = %ld instead of 0\n", zswpwb_before);
+		return -1;
+	}
+
+	if (cg_run(cgroup, attempt_writeback, (void *) &wb))
+		return -1;
+
+	/* Verify that zswap writeback occurred only if writeback was enabled */
+	if (wb)
+		zswpwb_after = wait_for_writeback(cgroup, 5000);
+	else
+		zswpwb_after = get_cg_wb_count(cgroup);
+	if (zswpwb_after < 0)
+		return -1;
+
+	if (wb != !!zswpwb_after) {
+		ksft_print_msg("zswpwb_after is %ld while wb is %s\n",
+				zswpwb_after, wb ? "enabled" : "disabled");
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Test to verify the zswap writeback path */
+static int test_zswap_writeback(const char *root, bool wb)
+{
+	int ret = KSFT_FAIL;
+	char *test_group, *test_group_child = NULL;
+
+	if (cg_read_strcmp(root, "memory.zswap.writeback", "1"))
+		return KSFT_SKIP;
+
+	test_group = cg_name(root, "zswap_writeback_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.writeback", wb ? "1" : "0"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group, wb))
+		goto out;
+
+	/* Reset memory.zswap.max to max (modified by attempt_writeback), and
+	 * set up child cgroup, whose memory.zswap.writeback is hardcoded to 1.
+	 * Thus, the parent's setting shall be what's in effect. */
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+	if (cg_write(test_group, "cgroup.subtree_control", "+memory"))
+		goto out;
+
+	test_group_child = cg_name(test_group, "zswap_writeback_test_child");
+	if (!test_group_child)
+		goto out;
+	if (cg_create(test_group_child))
+		goto out;
+	if (cg_write(test_group_child, "memory.zswap.writeback", "1"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group_child, wb))
+		goto out;
+
+	ret = KSFT_PASS;
+
+out:
+	if (test_group_child) {
+		cg_destroy(test_group_child);
+		free(test_group_child);
+	}
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+static int test_zswap_writeback_enabled(const char *root)
+{
+	return test_zswap_writeback(root, true);
+}
+
+static int test_zswap_writeback_disabled(const char *root)
+{
+	return test_zswap_writeback(root, false);
+}
+
+/*
+ * When trying to store a memcg page in zswap, if the memcg hits its memory
+ * limit in zswap, writeback should affect only the zswapped pages of that
+ * memcg.
+ */
+static int test_no_invasive_cgroup_shrink(const char *root)
+{
+	int ret = KSFT_FAIL;
+	unsigned int off;
+	size_t allocation_size = page_size * 1024;
+	unsigned int nr_pages = allocation_size / page_size;
+	char zswap_max_buf[32], mem_max_buf[32];
+	char *zw_allocation = NULL, *wb_allocation = NULL;
+	char *zw_group = NULL, *wb_group = NULL;
+
+	snprintf(zswap_max_buf, sizeof(zswap_max_buf), "%d", page_size);
+	snprintf(mem_max_buf, sizeof(mem_max_buf), "%zu", allocation_size / 2);
+
+	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
+	if (!wb_group)
+		return KSFT_FAIL;
+	if (cg_write(wb_group, "memory.zswap.max", zswap_max_buf))
+		goto out;
+	if (cg_write(wb_group, "memory.max", mem_max_buf))
+		goto out;
+
+	zw_group = setup_test_group_1M(root, "per_memcg_wb_test2");
+	if (!zw_group)
+		goto out;
+	if (cg_write(zw_group, "memory.max", mem_max_buf))
+		goto out;
+
+	/* Push some zw_group memory into zswap (simple data, easy to compress) */
+	if (cg_enter_current(zw_group))
+		goto out;
+	zw_allocation = malloc(allocation_size);
+	for (int i = 0; i < nr_pages; i++) {
+		off = (unsigned long)i * page_size;
+		memset(&zw_allocation[off], 0, page_size);
+		memset(&zw_allocation[off], 'a', page_size/4);
+	}
+	if (cg_read_key_long(zw_group, "memory.stat", "zswapped") < 1)
+		goto out;
+
+	/* Push wb_group memory into zswap with hard-to-compress data to trigger wb */
+	if (cg_enter_current(wb_group))
+		goto out;
+	wb_allocation = malloc(allocation_size);
+	if (!wb_allocation)
+		goto out;
+	for (int i = 0; i < nr_pages; i++) {
+		off = (unsigned long)i * page_size;
+		memset(&wb_allocation[off], 0, page_size);
+		getrandom(&wb_allocation[off], page_size/4, 0);
+	}
+
+	/* Verify that only zswapped memory from gwb_group has been written back */
+	if (wait_for_writeback(wb_group, 5000) > 0 && get_cg_wb_count(zw_group) == 0)
+		ret = KSFT_PASS;
+out:
+	cg_enter_current(root);
+	if (zw_group) {
+		cg_destroy(zw_group);
+		free(zw_group);
+	}
+	if (wb_group) {
+		cg_destroy(wb_group);
+		free(wb_group);
+	}
+	if (zw_allocation)
+		free(zw_allocation);
+	if (wb_allocation)
+		free(wb_allocation);
+	return ret;
+}
+
+struct no_kmem_bypass_child_args {
+	size_t target_alloc_bytes;
+	size_t child_allocated;
+};
+
+static int no_kmem_bypass_child(const char *cgroup, void *arg)
+{
+	struct no_kmem_bypass_child_args *values = arg;
+	void *allocation;
+
+	allocation = malloc(values->target_alloc_bytes);
+	if (!allocation) {
+		values->child_allocated = true;
+		return -1;
+	}
+	for (long i = 0; i < values->target_alloc_bytes; i += page_size)
+		((char *)allocation)[i] = 'a';
+	values->child_allocated = true;
+	pause();
+	free(allocation);
+	return 0;
+}
+
+/*
+ * When pages owned by a memcg are pushed to zswap by kswapd, they should be
+ * charged to that cgroup. This wasn't the case before commit
+ * cd08d80ecdac("mm: correctly charge compressed memory to its memcg").
+ *
+ * The test first allocates memory in a memcg, then raises min_free_kbytes to
+ * a very high value so that the allocation falls below low wm, then makes
+ * another allocation to trigger kswapd that should push the memcg-owned pages
+ * to zswap and verifies that the zswap pages are correctly charged.
+ *
+ * To be run on a VM with at most 4G of memory.
+ */
+static int test_no_kmem_bypass(const char *root)
+{
+	size_t min_free_kb_high, min_free_kb_low, min_free_kb_original;
+	struct no_kmem_bypass_child_args *values;
+	size_t trigger_allocation_size;
+	int wait_child_iteration = 0;
+	long stored_pages_threshold;
+	struct sysinfo sys_info;
+	int ret = KSFT_FAIL;
+	int child_status;
+	char *test_group = NULL;
+	pid_t child_pid;
+
+	/* Read sys info and compute test values accordingly */
+	if (sysinfo(&sys_info) != 0)
+		return KSFT_FAIL;
+	if (sys_info.totalram > 5000000000)
+		return KSFT_SKIP;
+	values = mmap(0, sizeof(struct no_kmem_bypass_child_args), PROT_READ |
+			PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (values == MAP_FAILED)
+		return KSFT_FAIL;
+	if (read_min_free_kb(&min_free_kb_original))
+		return KSFT_FAIL;
+	min_free_kb_high = sys_info.totalram / 2000;
+	min_free_kb_low = sys_info.totalram / 500000;
+	values->target_alloc_bytes = (sys_info.totalram - min_free_kb_high * 1000) +
+		sys_info.totalram * 5 / 100;
+	stored_pages_threshold = sys_info.totalram / 5 / page_size;
+	trigger_allocation_size = sys_info.totalram / 20;
+
+	/* Set up test memcg */
+	test_group = cg_name(root, "kmem_bypass_test");
+	if (!test_group)
+		goto out;
+
+	/* Spawn memcg child and wait for it to allocate */
+	set_min_free_kb(min_free_kb_low);
+	if (cg_create(test_group))
+		goto out;
+	values->child_allocated = false;
+	child_pid = cg_run_nowait(test_group, no_kmem_bypass_child, values);
+	if (child_pid < 0)
+		goto out;
+	while (!values->child_allocated && wait_child_iteration++ < 10000)
+		usleep(1000);
+
+	/* Try to wakeup kswapd and let it push child memory to zswap */
+	set_min_free_kb(min_free_kb_high);
+	for (int i = 0; i < 20; i++) {
+		size_t stored_pages;
+		char *trigger_allocation = malloc(trigger_allocation_size);
+
+		if (!trigger_allocation)
+			break;
+		for (int i = 0; i < trigger_allocation_size; i += page_size)
+			trigger_allocation[i] = 'b';
+		usleep(100000);
+		free(trigger_allocation);
+		if (get_zswap_stored_pages(&stored_pages))
+			break;
+		if (stored_pages < 0)
+			break;
+		/* If memory was pushed to zswap, verify it belongs to memcg */
+		if (stored_pages > stored_pages_threshold) {
+			int zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped ");
+			int delta = stored_pages * page_size - zswapped;
+			int result_ok = delta < stored_pages * page_size / 4;
+
+			ret = result_ok ? KSFT_PASS : KSFT_FAIL;
+			break;
+		}
+	}
+
+	kill(child_pid, SIGTERM);
+	waitpid(child_pid, &child_status, 0);
+out:
+	set_min_free_kb(min_free_kb_original);
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+struct incomp_child_args {
+	size_t size;
+	int pipefd[2];
+	int madvise_ret;
+	int madvise_errno;
+};
+
+static int allocate_random_and_wait(const char *cgroup, void *arg)
+{
+	struct incomp_child_args *values = arg;
+	size_t size = values->size;
+	char *mem;
+	int fd;
+	ssize_t n;
+
+	close(values->pipefd[0]);
+
+	mem = mmap(NULL, size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (mem == MAP_FAILED)
+		return -1;
+
+	/* Fill with random data from /dev/urandom - incompressible */
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd < 0) {
+		munmap(mem, size);
+		return -1;
+	}
+
+	for (size_t i = 0; i < size; ) {
+		n = read(fd, mem + i, size - i);
+		if (n <= 0)
+			break;
+		i += n;
+	}
+	close(fd);
+
+	/* Touch all pages to ensure they're faulted in */
+	for (size_t i = 0; i < size; i += page_size)
+		mem[i] = mem[i];
+
+	/* Use MADV_PAGEOUT to push pages into zswap */
+	values->madvise_ret = madvise(mem, size, MADV_PAGEOUT);
+	values->madvise_errno = errno;
+
+	/* Notify parent that allocation and pageout are done */
+	write(values->pipefd[1], "x", 1);
+	close(values->pipefd[1]);
+
+	/* Keep memory alive for parent to check stats */
+	pause();
+	munmap(mem, size);
+	return 0;
+}
+
+static long get_zswap_incomp(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "memory.stat", "zswap_incomp ");
+}
+
+/*
+ * Test that incompressible pages (random data) are tracked by zswap_incomp.
+ *
+ * The child process allocates random data within memory.max, then uses
+ * MADV_PAGEOUT to push pages into zswap. The parent waits on a pipe for
+ * the child to finish, then checks the zswap_incomp stat before the child
+ * exits (zswap_incomp is a gauge that decreases on free).
+ */
+static int test_zswap_incompressible(const char *root)
+{
+	int ret = KSFT_FAIL;
+	struct incomp_child_args *values;
+	char *test_group;
+	long zswap_incomp;
+	pid_t child_pid;
+	int child_status;
+	char buf;
+
+	values = mmap(0, sizeof(struct incomp_child_args), PROT_READ |
+			PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (values == MAP_FAILED)
+		return KSFT_FAIL;
+
+	if (pipe(values->pipefd)) {
+		munmap(values, sizeof(struct incomp_child_args));
+		return KSFT_FAIL;
+	}
+
+	test_group = cg_name(root, "zswap_incompressible_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "32M"))
+		goto out;
+
+	values->size = MB(4);
+	child_pid = cg_run_nowait(test_group, allocate_random_and_wait, values);
+	if (child_pid < 0)
+		goto out;
+
+	close(values->pipefd[1]);
+
+	/* Wait for child to finish allocating and pageout */
+	read(values->pipefd[0], &buf, 1);
+	close(values->pipefd[0]);
+
+	zswap_incomp = get_zswap_incomp(test_group);
+	if (zswap_incomp <= 0) {
+		long zswpout = get_zswpout(test_group);
+		long zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped ");
+		long zswap_b = cg_read_key_long(test_group, "memory.stat", "zswap ");
+
+		ksft_print_msg("zswap_incomp not increased: %ld\n", zswap_incomp);
+		ksft_print_msg("debug: zswpout=%ld zswapped=%ld zswap_b=%ld\n",
+			       zswpout, zswapped, zswap_b);
+		ksft_print_msg("debug: madvise ret=%d errno=%d\n",
+			       values->madvise_ret, values->madvise_errno);
+		goto out_kill;
+	}
+
+	ret = KSFT_PASS;
+
+out_kill:
+	kill(child_pid, SIGTERM);
+	waitpid(child_pid, &child_status, 0);
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	munmap(values, sizeof(struct incomp_child_args));
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct zswap_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_zswap_usage),
+	T(test_swapin_nozswap),
+	T(test_zswapin),
+	T(test_zswap_writeback_enabled),
+	T(test_zswap_writeback_disabled),
+	T(test_no_kmem_bypass),
+	T(test_no_invasive_cgroup_shrink),
+	T(test_zswap_incompressible),
+};
+#undef T
+
+static void check_zswap_enabled(void)
+{
+	char value[2];
+
+	if (access(PATH_ZSWAP, F_OK))
+		ksft_exit_skip("zswap isn't configured\n");
+
+	if (read_text(PATH_ZSWAP_ENABLED, value, sizeof(value)) <= 0)
+		ksft_exit_fail_msg("Failed to read " PATH_ZSWAP_ENABLED "\n");
+
+	if (value[0] == 'N')
+		ksft_exit_skip("zswap is disabled (hint: echo 1 > " PATH_ZSWAP_ENABLED ")\n");
+}
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+	if (page_size <= 0)
+		page_size = BUF_SIZE;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	check_zswap_enabled();
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}

linux-7.2.3/tools/testing/selftests/cgroup/wait_inotify.c

@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Wait until an inotify event on the given cgroup file.
+ */
+#include <linux/limits.h>
+#include <sys/inotify.h>
+#include <sys/mman.h>
+#include <sys/ptrace.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static const char usage[] = "Usage: %s [-v] <cgroup_file>\n";
+static char *file;
+static int verbose;
+
+static inline void fail_message(char *msg)
+{
+	fprintf(stderr, msg, file);
+	exit(1);
+}
+
+int main(int argc, char *argv[])
+{
+	char *cmd = argv[0];
+	int c, fd;
+	struct pollfd fds = { .events = POLLIN, };
+
+	while ((c = getopt(argc, argv, "v")) != -1) {
+		switch (c) {
+		case 'v':
+			verbose++;
+			break;
+		}
+		argv++, argc--;
+	}
+
+	if (argc != 2) {
+		fprintf(stderr, usage, cmd);
+		return -1;
+	}
+	file = argv[1];
+	fd = open(file, O_RDONLY);
+	if (fd < 0)
+		fail_message("Cgroup file %s not found!\n");
+	close(fd);
+
+	fd = inotify_init();
+	if (fd < 0)
+		fail_message("inotify_init() fails on %s!\n");
+	if (inotify_add_watch(fd, file, IN_MODIFY) < 0)
+		fail_message("inotify_add_watch() fails on %s!\n");
+	fds.fd = fd;
+
+	/*
+	 * poll waiting loop
+	 */
+	for (;;) {
+		int ret = poll(&fds, 1, 10000);
+
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			perror("poll");
+			exit(1);
+		}
+		if ((ret > 0) && (fds.revents & POLLIN))
+			break;
+	}
+	if (verbose) {
+		struct inotify_event events[10];
+		long len;
+
+		usleep(1000);
+		len = read(fd, events, sizeof(events));
+		printf("Number of events read = %ld\n",
+			len/sizeof(struct inotify_event));
+	}
+	close(fd);
+	return 0;
+}

linux-7.2.3/tools/testing/selftests/cgroup/with_stress.sh

@@ -0,0 +1,101 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+stress_fork()
+{
+	while true ; do
+		/usr/bin/true
+		sleep 0.01
+	done
+}
+
+stress_subsys()
+{
+	local verb=+
+	while true ; do
+		echo $verb$subsys_ctrl >$sysfs/cgroup.subtree_control
+		[ $verb = "+" ] && verb=- || verb=+
+		# incommensurable period with other stresses
+		sleep 0.011
+	done
+}
+
+init_and_check()
+{
+	sysfs=`mount -t cgroup2 | head -1 | awk '{ print $3 }'`
+	if [ ! -d "$sysfs" ]; then
+		echo "Skipping: cgroup2 is not mounted" >&2
+		exit $ksft_skip
+	fi
+
+	if ! echo +$subsys_ctrl >$sysfs/cgroup.subtree_control ; then
+		echo "Skipping: cannot enable $subsys_ctrl in $sysfs" >&2
+		exit $ksft_skip
+	fi
+
+	if ! echo -$subsys_ctrl >$sysfs/cgroup.subtree_control ; then
+		echo "Skipping: cannot disable $subsys_ctrl in $sysfs" >&2
+		exit $ksft_skip
+	fi
+}
+
+declare -a stresses
+declare -a stress_pids
+duration=5
+rc=0
+subsys_ctrl=cpuset
+sysfs=
+
+while getopts c:d:hs: opt; do
+	case $opt in
+	c)
+		subsys_ctrl=$OPTARG
+		;;
+	d)
+		duration=$OPTARG
+		;;
+	h)
+		echo "Usage $0 [ -s stress ] ... [ -d duration ] [-c controller] cmd args .."
+		echo -e "\t default duration $duration seconds"
+		echo -e "\t default controller $subsys_ctrl"
+		exit
+		;;
+	s)
+		func=stress_$OPTARG
+		if [ "x$(type -t $func)" != "xfunction" ] ; then
+			echo "Unknown stress $OPTARG"
+			exit 1
+		fi
+		stresses+=($func)
+		;;
+	esac
+done
+shift $((OPTIND - 1))
+
+init_and_check
+
+for s in ${stresses[*]} ; do
+	$s &
+	stress_pids+=($!)
+done
+
+
+time=0
+start=$(date +%s)
+
+while [ $time -lt $duration ] ; do
+	$*
+	rc=$?
+	[ $rc -eq 0 ] || break
+	time=$(($(date +%s) - $start))
+done
+
+for pid in ${stress_pids[*]} ; do
+	kill -SIGTERM $pid
+	wait $pid
+done
+
+exit $rc