Adding upstream version 4.19.249.upstream/4.19.249upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 2222 insertions, 0 deletions

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
new file mode 100644
index 000000000..adacda50a
--- /dev/null
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -0,0 +1,2 @@
+test_memcontrol
+test_core
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
new file mode 100644
index 000000000..23fbaa4a9
--- /dev/null
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall
+
+all:
+
+TEST_GEN_PROGS = test_memcontrol
+TEST_GEN_PROGS += test_core
+
+include ../lib.mk
+
+$(OUTPUT)/test_memcontrol: cgroup_util.c
+$(OUTPUT)/test_core: cgroup_util.c
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
new file mode 100644
index 000000000..a516d01f0
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -0,0 +1,370 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/limits.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "cgroup_util.h"
+
+static 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 fd;
+
+	len = read(fd, buf, max_len - 1);
+	if (len < 0)
+		goto out;
+
+	buf[len] = 0;
+out:
+	close(fd);
+	return len;
+}
+
+static 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 fd;
+
+	len = write(fd, buf, len);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+
+	return len;
+}
+
+char *cg_name(const char *root, const char *name)
+{
+	size_t len = strlen(root) + strlen(name) + 2;
+	char *ret = malloc(len);
+
+	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);
+
+	snprintf(ret, len, "%s/%s_%d", root, name, index);
+
+	return ret;
+}
+
+int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+	if (read_text(path, buf, len) >= 0)
+		return 0;
+
+	return -1;
+}
+
+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;
+	else
+		size = 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_strstr(const char *cgroup, const char *control, const char *needle)
+{
+	char buf[PAGE_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_key_long(const char *cgroup, const char *control, const char *key)
+{
+	char buf[PAGE_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));
+}
+
+int cg_write(const char *cgroup, const char *control, char *buf)
+{
+	char path[PATH_MAX];
+	ssize_t len = strlen(buf);
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+	if (write_text(path, buf, len) == len)
+		return 0;
+
+	return -1;
+}
+
+int cg_find_unified_root(char *root, size_t len)
+{
+	char buf[10 * PAGE_SIZE];
+	char *fs, *mount, *type;
+	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);
+		strtok(NULL, delim);
+		strtok(NULL, delim);
+		strtok(NULL, delim);
+
+		if (strcmp(type, "cgroup2") == 0) {
+			strncpy(root, mount, len);
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+int cg_create(const char *cgroup)
+{
+	return mkdir(cgroup, 0755);
+}
+
+static int cg_killall(const char *cgroup)
+{
+	char buf[PAGE_SIZE];
+	char *ptr = buf;
+
+	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;
+
+retry:
+	ret = rmdir(cgroup);
+	if (ret && errno == EBUSY) {
+		ret = cg_killall(cgroup);
+		if (ret)
+			return ret;
+		usleep(100);
+		goto retry;
+	}
+
+	if (ret && errno == ENOENT)
+		ret = 0;
+
+	return ret;
+}
+
+int cg_enter_current(const char *cgroup)
+{
+	char pidbuf[64];
+
+	snprintf(pidbuf, sizeof(pidbuf), "%d", getpid());
+	return cg_write(cgroup, "cgroup.procs", pidbuf);
+}
+
+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;
+	}
+}
+
+int cg_run_nowait(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg)
+{
+	int pid;
+
+	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 get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[PAGE_SIZE];
+	struct stat st;
+	int i;
+
+	if (fstat(fd, &st))
+		goto cleanup;
+
+	size += st.st_size;
+
+	if (ftruncate(fd, size))
+		goto cleanup;
+
+	for (i = 0; i < size; i += sizeof(buf))
+		read(fd, buf, sizeof(buf));
+
+	return 0;
+
+cleanup:
+	return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	int cnt = 0;
+	char *line;
+
+	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt > 1;
+}
+
+int set_oom_adj_score(int pid, int score)
+{
+	char path[PATH_MAX];
+	int fd, len;
+
+	sprintf(path, "/proc/%d/oom_score_adj", pid);
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = dprintf(fd, "%d", score);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+	return 0;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
new file mode 100644
index 000000000..9ac8b7958
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+
+#define PAGE_SIZE 4096
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define MB(x) (x << 20)
+
+/*
+ * 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 abs(a - b) <= (a + b) / 100 * err;
+}
+
+extern int cg_find_unified_root(char *root, size_t len);
+extern char *cg_name(const char *root, const char *name);
+extern char *cg_name_indexed(const char *root, const char *name, int index);
+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_strstr(const char *cgroup, const char *control,
+			  const char *needle);
+extern long cg_read_long(const char *cgroup, const char *control);
+long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_run(const char *cgroup,
+		  int (*fn)(const char *cgroup, void *arg),
+		  void *arg);
+extern int cg_enter_current(const char *cgroup);
+extern int cg_run_nowait(const char *cgroup,
+			 int (*fn)(const char *cgroup, void *arg),
+			 void *arg);
+extern int get_temp_fd(void);
+extern int alloc_pagecache(int fd, size_t size);
+extern int alloc_anon(const char *cgroup, void *arg);
+extern int is_swap_enabled(void);
+extern int set_oom_adj_score(int pid, int score);
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
new file mode 100644
index 000000000..599234c5e
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -0,0 +1,567 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+#include <linux/limits.h>
+#include <linux/sched.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+/*
+ * 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;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_c = NULL, *cg_test_d = NULL;
+
+	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;
+
+	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);
+	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;
+
+	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;
+
+	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;
+
+	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_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;
+
+	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;
+
+	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;
+
+	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;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+	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 = 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;
+	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;
+
+	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;
+}
+
+#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_lesser_euid_open),
+	T(test_cgcore_lesser_ns_open),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\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:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
new file mode 100644
index 000000000..c19a97dd0
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -0,0 +1,1228 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <linux/oom.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/socket.h>
+#include <sys/wait.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <netdb.h>
+#include <errno.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+/*
+ * This test creates two nested cgroups with and without enabling
+ * the memory controller.
+ */
+static int test_memcg_subtree_control(const char *root)
+{
+	char *parent, *child, *parent2 = NULL, *child2 = NULL;
+	int ret = KSFT_FAIL;
+	char buf[PAGE_SIZE];
+
+	/* Create two nested cgroups with the memory controller enabled */
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+	if (!parent || !child)
+		goto cleanup_free;
+
+	if (cg_create(parent))
+		goto cleanup_free;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+		goto cleanup_parent;
+
+	if (cg_create(child))
+		goto cleanup_parent;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "memory"))
+		goto cleanup_child;
+
+	/* Create two nested cgroups without enabling memory controller */
+	parent2 = cg_name(root, "memcg_test_1");
+	child2 = cg_name(root, "memcg_test_1/memcg_test_1");
+	if (!parent2 || !child2)
+		goto cleanup_free2;
+
+	if (cg_create(parent2))
+		goto cleanup_free2;
+
+	if (cg_create(child2))
+		goto cleanup_parent2;
+
+	if (cg_read(child2, "cgroup.controllers", buf, sizeof(buf)))
+		goto cleanup_all;
+
+	if (!cg_read_strstr(child2, "cgroup.controllers", "memory"))
+		goto cleanup_all;
+
+	ret = KSFT_PASS;
+
+cleanup_all:
+	cg_destroy(child2);
+cleanup_parent2:
+	cg_destroy(parent2);
+cleanup_free2:
+	free(parent2);
+	free(child2);
+cleanup_child:
+	cg_destroy(child);
+cleanup_parent:
+	cg_destroy(parent);
+cleanup_free:
+	free(parent);
+	free(child);
+
+	return ret;
+}
+
+static int alloc_anon_50M_check(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	char *buf, *ptr;
+	long anon, current;
+	int ret = -1;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current < size)
+		goto cleanup;
+
+	if (!values_close(size, current, 3))
+		goto cleanup;
+
+	anon = cg_read_key_long(cgroup, "memory.stat", "anon ");
+	if (anon < 0)
+		goto cleanup;
+
+	if (!values_close(anon, current, 3))
+		goto cleanup;
+
+	ret = 0;
+cleanup:
+	free(buf);
+	return ret;
+}
+
+static int alloc_pagecache_50M_check(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	int ret = -1;
+	long current, file;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		return -1;
+
+	if (alloc_pagecache(fd, size))
+		goto cleanup;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current < size)
+		goto cleanup;
+
+	file = cg_read_key_long(cgroup, "memory.stat", "file ");
+	if (file < 0)
+		goto cleanup;
+
+	if (!values_close(file, current, 10))
+		goto cleanup;
+
+	ret = 0;
+
+cleanup:
+	close(fd);
+	return ret;
+}
+
+/*
+ * This test create a memory cgroup, allocates
+ * some anonymous memory and some pagecache
+ * and check memory.current and some memory.stat values.
+ */
+static int test_memcg_current(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long current;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	current = cg_read_long(memcg, "memory.current");
+	if (current != 0)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon_50M_check, NULL))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int alloc_pagecache_50M(const char *cgroup, void *arg)
+{
+	int fd = (long)arg;
+
+	return alloc_pagecache(fd, MB(50));
+}
+
+static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg)
+{
+	int fd = (long)arg;
+	int ppid = getppid();
+
+	if (alloc_pagecache(fd, MB(50)))
+		return -1;
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	return 0;
+}
+
+static int alloc_anon_noexit(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+
+	if (alloc_anon(cgroup, arg))
+		return -1;
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	return 0;
+}
+
+/*
+ * Wait until processes are killed asynchronously by the OOM killer
+ * If we exceed a timeout, fail.
+ */
+static int cg_test_proc_killed(const char *cgroup)
+{
+	int limit;
+
+	for (limit = 10; limit > 0; limit--) {
+		if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0)
+			return 0;
+
+		usleep(100000);
+	}
+	return -1;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A       memory.min = 50M,  memory.max = 200M
+ * A/B     memory.min = 50M,  memory.current = 50M
+ * A/B/C   memory.min = 75M,  memory.current = 50M
+ * A/B/D   memory.min = 25M,  memory.current = 50M
+ * A/B/E   memory.min = 500M, memory.current = 0
+ * A/B/F   memory.min = 0,    memory.current = 50M
+ *
+ * Usages are pagecache, but the test keeps a running
+ * process in every leaf cgroup.
+ * Then it creates A/G and creates a significant
+ * memory pressure in it.
+ *
+ * A/B    memory.current ~= 50M
+ * A/B/C  memory.current ~= 33M
+ * A/B/D  memory.current ~= 17M
+ * A/B/E  memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available, and checks
+ * checks that memory.min protects pagecache even
+ * in this case.
+ */
+static int test_memcg_min(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent[3] = {NULL};
+	char *children[4] = {NULL};
+	long c[4];
+	int i, attempts;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	parent[0] = cg_name(root, "memcg_test_0");
+	if (!parent[0])
+		goto cleanup;
+
+	parent[1] = cg_name(parent[0], "memcg_test_1");
+	if (!parent[1])
+		goto cleanup;
+
+	parent[2] = cg_name(parent[0], "memcg_test_2");
+	if (!parent[2])
+		goto cleanup;
+
+	if (cg_create(parent[0]))
+		goto cleanup;
+
+	if (cg_read_long(parent[0], "memory.min")) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.max", "200M"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_create(parent[1]))
+		goto cleanup;
+
+	if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_create(parent[2]))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+		if (!children[i])
+			goto cleanup;
+
+		if (cg_create(children[i]))
+			goto cleanup;
+
+		if (i == 2)
+			continue;
+
+		cg_run_nowait(children[i], alloc_pagecache_50M_noexit,
+			      (void *)(long)fd);
+	}
+
+	if (cg_write(parent[0], "memory.min", "50M"))
+		goto cleanup;
+	if (cg_write(parent[1], "memory.min", "50M"))
+		goto cleanup;
+	if (cg_write(children[0], "memory.min", "75M"))
+		goto cleanup;
+	if (cg_write(children[1], "memory.min", "25M"))
+		goto cleanup;
+	if (cg_write(children[2], "memory.min", "500M"))
+		goto cleanup;
+	if (cg_write(children[3], "memory.min", "0"))
+		goto cleanup;
+
+	attempts = 0;
+	while (!values_close(cg_read_long(parent[1], "memory.current"),
+			     MB(150), 3)) {
+		if (attempts++ > 5)
+			break;
+		sleep(1);
+	}
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++)
+		c[i] = cg_read_long(children[i], "memory.current");
+
+	if (!values_close(c[0], MB(33), 10))
+		goto cleanup;
+
+	if (!values_close(c[1], MB(17), 10))
+		goto cleanup;
+
+	if (!values_close(c[2], 0, 1))
+		goto cleanup;
+
+	if (!cg_run(parent[2], alloc_anon, (void *)MB(170)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+		if (!children[i])
+			continue;
+
+		cg_destroy(children[i]);
+		free(children[i]);
+	}
+
+	for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+		if (!parent[i])
+			continue;
+
+		cg_destroy(parent[i]);
+		free(parent[i]);
+	}
+	close(fd);
+	return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A       memory.low = 50M,  memory.max = 200M
+ * A/B     memory.low = 50M,  memory.current = 50M
+ * A/B/C   memory.low = 75M,  memory.current = 50M
+ * A/B/D   memory.low = 25M,  memory.current = 50M
+ * A/B/E   memory.low = 500M, memory.current = 0
+ * A/B/F   memory.low = 0,    memory.current = 50M
+ *
+ * Usages are pagecache.
+ * Then it creates A/G an creates a significant
+ * memory pressure in it.
+ *
+ * Then it checks actual memory usages and expects that:
+ * A/B    memory.current ~= 50M
+ * A/B/   memory.current ~= 33M
+ * A/B/D  memory.current ~= 17M
+ * A/B/E  memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available,
+ * and checks low and oom events in memory.events.
+ */
+static int test_memcg_low(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent[3] = {NULL};
+	char *children[4] = {NULL};
+	long low, oom;
+	long c[4];
+	int i;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	parent[0] = cg_name(root, "memcg_test_0");
+	if (!parent[0])
+		goto cleanup;
+
+	parent[1] = cg_name(parent[0], "memcg_test_1");
+	if (!parent[1])
+		goto cleanup;
+
+	parent[2] = cg_name(parent[0], "memcg_test_2");
+	if (!parent[2])
+		goto cleanup;
+
+	if (cg_create(parent[0]))
+		goto cleanup;
+
+	if (cg_read_long(parent[0], "memory.low"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.max", "200M"))
+		goto cleanup;
+
+	if (cg_write(parent[0], "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_create(parent[1]))
+		goto cleanup;
+
+	if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+		goto cleanup;
+
+	if (cg_create(parent[2]))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+		if (!children[i])
+			goto cleanup;
+
+		if (cg_create(children[i]))
+			goto cleanup;
+
+		if (i == 2)
+			continue;
+
+		if (cg_run(children[i], alloc_pagecache_50M, (void *)(long)fd))
+			goto cleanup;
+	}
+
+	if (cg_write(parent[0], "memory.low", "50M"))
+		goto cleanup;
+	if (cg_write(parent[1], "memory.low", "50M"))
+		goto cleanup;
+	if (cg_write(children[0], "memory.low", "75M"))
+		goto cleanup;
+	if (cg_write(children[1], "memory.low", "25M"))
+		goto cleanup;
+	if (cg_write(children[2], "memory.low", "500M"))
+		goto cleanup;
+	if (cg_write(children[3], "memory.low", "0"))
+		goto cleanup;
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+		goto cleanup;
+
+	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(children); i++)
+		c[i] = cg_read_long(children[i], "memory.current");
+
+	if (!values_close(c[0], MB(33), 10))
+		goto cleanup;
+
+	if (!values_close(c[1], MB(17), 10))
+		goto cleanup;
+
+	if (!values_close(c[2], 0, 1))
+		goto cleanup;
+
+	if (cg_run(parent[2], alloc_anon, (void *)MB(166))) {
+		fprintf(stderr,
+			"memory.low prevents from allocating anon memory\n");
+		goto cleanup;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		oom = cg_read_key_long(children[i], "memory.events", "oom ");
+		low = cg_read_key_long(children[i], "memory.events", "low ");
+
+		if (oom)
+			goto cleanup;
+		if (i < 2 && low <= 0)
+			goto cleanup;
+		if (i >= 2 && low)
+			goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+		if (!children[i])
+			continue;
+
+		cg_destroy(children[i]);
+		free(children[i]);
+	}
+
+	for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+		if (!parent[i])
+			continue;
+
+		cg_destroy(parent[i]);
+		free(parent[i]);
+	}
+	close(fd);
+	return ret;
+}
+
+static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	int ret = -1;
+	long current;
+	int fd;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		return -1;
+
+	if (alloc_pagecache(fd, size))
+		goto cleanup;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (current <= MB(29) || current > MB(30))
+		goto cleanup;
+
+	ret = 0;
+
+cleanup:
+	close(fd);
+	return ret;
+
+}
+
+/*
+ * This test checks that memory.high limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_high(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long high;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.high", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.high", "30M"))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (!cg_run(memcg, alloc_pagecache_50M_check, NULL))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+		goto cleanup;
+
+	high = cg_read_key_long(memcg, "memory.events", "high ");
+	if (high <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+/*
+ * This test checks that memory.max limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long current, max;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	/* Should be killed by OOM killer */
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+		goto cleanup;
+
+	current = cg_read_long(memcg, "memory.current");
+	if (current > MB(30) || !current)
+		goto cleanup;
+
+	max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (max <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
+{
+	long mem_max = (long)arg;
+	size_t size = MB(50);
+	char *buf, *ptr;
+	long mem_current, swap_current;
+	int ret = -1;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	mem_current = cg_read_long(cgroup, "memory.current");
+	if (!mem_current || !values_close(mem_current, mem_max, 3))
+		goto cleanup;
+
+	swap_current = cg_read_long(cgroup, "memory.swap.current");
+	if (!swap_current ||
+	    !values_close(mem_current + swap_current, size, 3))
+		goto cleanup;
+
+	ret = 0;
+cleanup:
+	free(buf);
+	return ret;
+}
+
+/*
+ * This test checks that memory.swap.max limits the amount of
+ * anonymous memory which can be swapped out.
+ */
+static int test_memcg_swap_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long max;
+
+	if (!is_swap_enabled())
+		return KSFT_SKIP;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.current")) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "memory.swap.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "30M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	/* Should be killed by OOM killer */
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30)))
+		goto cleanup;
+
+	max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (max <= 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM. Then it checks for oom and oom_kill events in
+ * memory.events.
+ */
+static int test_memcg_oom_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "30M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_strcmp(memcg, "cgroup.procs", ""))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+struct tcp_server_args {
+	unsigned short port;
+	int ctl[2];
+};
+
+static int tcp_server(const char *cgroup, void *arg)
+{
+	struct tcp_server_args *srv_args = arg;
+	struct sockaddr_in6 saddr = { 0 };
+	socklen_t slen = sizeof(saddr);
+	int sk, client_sk, ctl_fd, yes = 1, ret = -1;
+
+	close(srv_args->ctl[0]);
+	ctl_fd = srv_args->ctl[1];
+
+	saddr.sin6_family = AF_INET6;
+	saddr.sin6_addr = in6addr_any;
+	saddr.sin6_port = htons(srv_args->port);
+
+	sk = socket(AF_INET6, SOCK_STREAM, 0);
+	if (sk < 0)
+		return ret;
+
+	if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0)
+		goto cleanup;
+
+	if (bind(sk, (struct sockaddr *)&saddr, slen)) {
+		write(ctl_fd, &errno, sizeof(errno));
+		goto cleanup;
+	}
+
+	if (listen(sk, 1))
+		goto cleanup;
+
+	ret = 0;
+	if (write(ctl_fd, &ret, sizeof(ret)) != sizeof(ret)) {
+		ret = -1;
+		goto cleanup;
+	}
+
+	client_sk = accept(sk, NULL, NULL);
+	if (client_sk < 0)
+		goto cleanup;
+
+	ret = -1;
+	for (;;) {
+		uint8_t buf[0x100000];
+
+		if (write(client_sk, buf, sizeof(buf)) <= 0) {
+			if (errno == ECONNRESET)
+				ret = 0;
+			break;
+		}
+	}
+
+	close(client_sk);
+
+cleanup:
+	close(sk);
+	return ret;
+}
+
+static int tcp_client(const char *cgroup, unsigned short port)
+{
+	const char server[] = "localhost";
+	struct addrinfo *ai;
+	char servport[6];
+	int retries = 0x10; /* nice round number */
+	int sk, ret;
+
+	snprintf(servport, sizeof(servport), "%hd", port);
+	ret = getaddrinfo(server, servport, NULL, &ai);
+	if (ret)
+		return ret;
+
+	sk = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+	if (sk < 0)
+		goto free_ainfo;
+
+	ret = connect(sk, ai->ai_addr, ai->ai_addrlen);
+	if (ret < 0)
+		goto close_sk;
+
+	ret = KSFT_FAIL;
+	while (retries--) {
+		uint8_t buf[0x100000];
+		long current, sock;
+
+		if (read(sk, buf, sizeof(buf)) <= 0)
+			goto close_sk;
+
+		current = cg_read_long(cgroup, "memory.current");
+		sock = cg_read_key_long(cgroup, "memory.stat", "sock ");
+
+		if (current < 0 || sock < 0)
+			goto close_sk;
+
+		if (current < sock)
+			goto close_sk;
+
+		if (values_close(current, sock, 10)) {
+			ret = KSFT_PASS;
+			break;
+		}
+	}
+
+close_sk:
+	close(sk);
+free_ainfo:
+	freeaddrinfo(ai);
+	return ret;
+}
+
+/*
+ * This test checks socket memory accounting.
+ * The test forks a TCP server listens on a random port between 1000
+ * and 61000. Once it gets a client connection, it starts writing to
+ * its socket.
+ * The TCP client interleaves reads from the socket with check whether
+ * memory.current and memory.stat.sock are similar.
+ */
+static int test_memcg_sock(const char *root)
+{
+	int bind_retries = 5, ret = KSFT_FAIL, pid, err;
+	unsigned short port;
+	char *memcg;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	while (bind_retries--) {
+		struct tcp_server_args args;
+
+		if (pipe(args.ctl))
+			goto cleanup;
+
+		port = args.port = 1000 + rand() % 60000;
+
+		pid = cg_run_nowait(memcg, tcp_server, &args);
+		if (pid < 0)
+			goto cleanup;
+
+		close(args.ctl[1]);
+		if (read(args.ctl[0], &err, sizeof(err)) != sizeof(err))
+			goto cleanup;
+		close(args.ctl[0]);
+
+		if (!err)
+			break;
+		if (err != EADDRINUSE)
+			goto cleanup;
+
+		waitpid(pid, NULL, 0);
+	}
+
+	if (err == EADDRINUSE) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (tcp_client(memcg, port) != KSFT_PASS)
+		goto cleanup;
+
+	waitpid(pid, &err, 0);
+	if (WEXITSTATUS(err))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.current") < 0)
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.stat", "sock "))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes in the leaf (but not the parent) were killed.
+ */
+static int test_memcg_oom_group_leaf_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+
+	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, "memory.max", "50M"))
+		goto cleanup;
+
+	if (cg_write(child, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(child, "memory.oom.group", "1"))
+		goto cleanup;
+
+	cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	if (!cg_run(child, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_test_proc_killed(child))
+		goto cleanup;
+
+	if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0)
+		goto cleanup;
+
+	if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes in the parent and leaf were killed.
+ */
+static int test_memcg_oom_group_parent_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+
+	parent = cg_name(root, "memcg_test_0");
+	child = cg_name(root, "memcg_test_0/memcg_test_1");
+
+	if (!parent || !child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.max", "80M"))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(parent, "memory.oom.group", "1"))
+		goto cleanup;
+
+	cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+	cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1));
+
+	if (!cg_run(child, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_test_proc_killed(child))
+		goto cleanup;
+	if (cg_test_proc_killed(parent))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	if (parent)
+		cg_destroy(parent);
+	free(child);
+	free(parent);
+
+	return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM with memory.group.oom set. Then it checks that all
+ * processes were killed except those set with OOM_SCORE_ADJ_MIN
+ */
+static int test_memcg_oom_group_score_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	int safe_pid;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "50M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.oom.group", "1"))
+		goto cleanup;
+
+	safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1));
+	if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN))
+		goto cleanup;
+
+	cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1));
+	if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+		goto cleanup;
+
+	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3)
+		goto cleanup;
+
+	if (kill(safe_pid, SIGKILL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (memcg)
+		cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+
+#define T(x) { x, #x }
+struct memcg_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_memcg_subtree_control),
+	T(test_memcg_current),
+	T(test_memcg_min),
+	T(test_memcg_low),
+	T(test_memcg_high),
+	T(test_memcg_max),
+	T(test_memcg_oom_events),
+	T(test_memcg_swap_max),
+	T(test_memcg_sock),
+	T(test_memcg_oom_group_leaf_events),
+	T(test_memcg_oom_group_parent_events),
+	T(test_memcg_oom_group_score_events),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		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:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}