Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

23 files changed, 10322 insertions, 0 deletions

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
new file mode 100644
index 000000000..952e4448b
--- /dev/null
+++ b/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
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
new file mode 100644
index 000000000..e01584c21
--- /dev/null
+++ b/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)
diff --git a/tools/testing/selftests/cgroup/config b/tools/testing/selftests/cgroup/config
new file mode 100644
index 000000000..39f979690
--- /dev/null
+++ b/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
diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
new file mode 100644
index 000000000..2596c12cd
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/cgroup/lib/include/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
new file mode 100644
index 000000000..5d39c709a
--- /dev/null
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -0,0 +1,102 @@
+/* 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 GB(x) ((unsigned long long)(x) << 30)
+
+#define NSEC_PER_USEC	1000L
+#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;
diff --git a/tools/testing/selftests/cgroup/lib/libcgroup.mk b/tools/testing/selftests/cgroup/lib/libcgroup.mk
new file mode 100644
index 000000000..7a7300720
--- /dev/null
+++ b/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)
diff --git a/tools/testing/selftests/cgroup/memcg_protection.m b/tools/testing/selftests/cgroup/memcg_protection.m
new file mode 100644
index 000000000..051daa347
--- /dev/null
+++ b/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
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
new file mode 100644
index 000000000..20d2b6377
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -0,0 +1,951 @@
+/* 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);
+	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];
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *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_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!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;
+
+	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_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();
+	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:
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
new file mode 100644
index 000000000..735a53bb2
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -0,0 +1,858 @@
+// 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 (user_usec <= 0)
+			goto cleanup;
+		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);
+}
+
+/*
+ * Best effort attempt to get the kernel's HZ value from the config.
+ * Return the HZ value if found otherwise return 1000 (the default) to
+ * indicate failure.
+ */
+static long
+get_config_hz(void)
+{
+	long hz = 1000;
+	FILE *f;
+	char cmd[256] = "zcat /proc/config.gz 2>/dev/null | grep '^CONFIG_HZ='";
+
+	f = popen(cmd, "r");
+
+	if (!f)
+		return hz;
+
+	if (fscanf(f, "CONFIG_HZ=%ld", &hz) == EOF)
+		goto out;
+
+out:
+	pclose(f);
+	return hz;
+}
+
+/*
+ * 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 hz = get_config_hz();
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
+	char *cpucg;
+	char quota_buf[32];
+
+	duration_usec = duration_seconds * USEC_PER_SEC * 1000 / hz;
+
+	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_usec / USEC_PER_SEC,
+			.tv_nsec = duration_usec % USEC_PER_SEC * NSEC_PER_USEC,
+		},
+		.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 hz = get_config_hz();
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
+	char *parent, *child;
+	char quota_buf[32];
+
+	duration_usec = duration_seconds * USEC_PER_SEC * 1000 / hz;
+
+	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_usec / USEC_PER_SEC,
+			.tv_nsec = duration_usec % USEC_PER_SEC * NSEC_PER_USEC,
+		},
+		.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();
+	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");
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
new file mode 100644
index 000000000..3dfadd280
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -0,0 +1,523 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <linux/limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <signal.h>
+#include <sys/syscall.h>
+#include <unistd.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;
+}
+
+static int get_cpu_affinity(cpu_set_t *mask)
+{
+	CPU_ZERO(mask);
+	return sched_getaffinity(0, sizeof(*mask), mask);
+}
+
+static int cpu_set_equal(cpu_set_t *dst, unsigned long mask)
+{
+	cpu_set_t expected;
+
+	CPU_ZERO(&expected);
+	assert(sizeof(mask) < CPU_SETSIZE);
+
+	for (int cpu = 0; cpu < sizeof(mask) * 8; ++cpu)
+		if ((1UL << cpu) & mask)
+			CPU_SET(cpu, &expected);
+
+	return CPU_EQUAL(&expected, dst);
+}
+
+enum test_phase {
+	AFFINITY_SETUP,
+	AFFINITY_CONTROLLER_DISABLED,
+	AFFINITY_COMPLETE,
+	AFFINITY_ERROR
+};
+
+struct thread_args {
+	const char *cgroup;
+	cpu_set_t *affinity_before;
+	cpu_set_t *affinity_after;
+	int affinity_before_ready;
+};
+
+static pthread_mutex_t test_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t test_cond = PTHREAD_COND_INITIALIZER;
+static enum test_phase test_phase;
+
+static void *affinity_thread_fn(void *arg)
+{
+	struct thread_args *args = (struct thread_args *)arg;
+
+	if (cg_enter_current_thread(args->cgroup))
+		goto fail;
+
+	if (get_cpu_affinity(args->affinity_before) != 0)
+		goto fail;
+
+	pthread_mutex_lock(&test_mutex);
+	args->affinity_before_ready = 1;
+	pthread_cond_broadcast(&test_cond);
+
+	while (test_phase < AFFINITY_CONTROLLER_DISABLED)
+		pthread_cond_wait(&test_cond, &test_mutex);
+	pthread_mutex_unlock(&test_mutex);
+
+	if (get_cpu_affinity(args->affinity_after) != 0)
+		goto fail;
+
+
+	return NULL;
+
+fail:
+	pthread_mutex_lock(&test_mutex);
+	test_phase = AFFINITY_ERROR;
+	pthread_cond_broadcast(&test_cond);
+	pthread_mutex_unlock(&test_mutex);
+	return NULL;
+}
+
+/*
+ * Test that disabling cpuset controller properly updates thread affinity.
+ *
+ * This test exposes a bug in cpuset_attach() where threads in child cgroups
+ * don't get their affinity updated when the cpuset controller is disabled.
+ *
+ * Setup:
+ * - Create parent cgroup with cpuset.cpus=0-1
+ * - Create child A with cpuset.cpus=0-1
+ * - Create child B with cpuset.cpus=1
+ * - Place multithreaded process: group leader + thread_a in A, thread_b in B
+ * - Disable cpuset controller on parent
+ *
+ * Expected: thread_b's affinity should expand from {1} to {0-1}
+ * Buggy: thread_b's affinity remains {1}
+ */
+static int test_cpuset_affinity_on_controller_disable(const char *root)
+{
+	char *parent = NULL, *child_a = NULL, *child_b = NULL;
+	pthread_t thread_a, thread_b;
+	int thread_a_created = 0, thread_b_created = 0;
+	cpu_set_t affinity_a_before, affinity_a_after;
+	cpu_set_t affinity_b_before, affinity_b_after;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_affinity_test");
+	if (!parent)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+	if (cg_write(parent, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	child_a = cg_name(parent, "A");
+	if (!child_a)
+		goto cleanup;
+	if (cg_create(child_a))
+		goto cleanup;
+	if (cg_write(child_a, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	child_b = cg_name(parent, "B");
+	if (!child_b)
+		goto cleanup;
+	if (cg_create(child_b))
+		goto cleanup;
+	if (cg_write(child_b, "cgroup.type", "threaded"))
+		goto cleanup;
+
+	/* Now enable cpuset controller in parent */
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		goto skip;
+
+	/*
+	 * Set CPU affinity constraints
+	 * Skip the test if the setting of "cpuset.cpus" fails as the test
+	 * system may not have CPU 1.
+	 */
+	if (cg_write(parent, "cpuset.cpus", "0-1"))
+		goto skip;
+	if (cg_write(child_a, "cpuset.cpus", "0-1"))
+		goto skip;
+	if (cg_write(child_b, "cpuset.cpus", "1"))
+		goto skip;
+
+	/* Move group leader (main thread) to child A */
+	if (cg_enter_current(child_a))
+		goto cleanup;
+
+	/* Create threads - they will move themselves to their respective cgroups */
+	test_phase = AFFINITY_SETUP;
+
+	struct thread_args args_a = {
+		.cgroup = child_a,
+		.affinity_before = &affinity_a_before,
+		.affinity_after = &affinity_a_after,
+		.affinity_before_ready = 0,
+	};
+	if (pthread_create(&thread_a, NULL, affinity_thread_fn, &args_a))
+		goto cleanup;
+	thread_a_created = 1;
+
+	struct thread_args args_b = {
+		.cgroup = child_b,
+		.affinity_before = &affinity_b_before,
+		.affinity_after = &affinity_b_after,
+		.affinity_before_ready = 0,
+	};
+	if (pthread_create(&thread_b, NULL, affinity_thread_fn, &args_b))
+		goto cleanup_threads;
+	thread_b_created = 1;
+
+	pthread_mutex_lock(&test_mutex);
+	while ((test_phase < AFFINITY_ERROR) &&
+	       (args_a.affinity_before_ready + args_b.affinity_before_ready < 2))
+		pthread_cond_wait(&test_cond, &test_mutex);
+
+	/* If a thread failed during setup, bail out */
+	if (test_phase == AFFINITY_ERROR) {
+		pthread_mutex_unlock(&test_mutex);
+		goto cleanup_threads;
+	}
+	pthread_mutex_unlock(&test_mutex);
+
+	if (!cpu_set_equal(&affinity_a_before, 0x3)) {
+		ksft_print_msg("FAIL: thread_a initial affinity incorrect\n");
+		goto cleanup_threads;
+	}
+
+	if (!cpu_set_equal(&affinity_b_before, 0x2)) {
+		ksft_print_msg("FAIL: thread_b initial affinity incorrect\n");
+		goto cleanup_threads;
+	}
+
+	/* Disable cpuset controller - this should trigger affinity update */
+	if (cg_write(parent, "cgroup.subtree_control", "-cpuset"))
+		goto cleanup_threads;
+
+	/* Signal threads to save their final affinity and exit */
+	pthread_mutex_lock(&test_mutex);
+	test_phase = AFFINITY_CONTROLLER_DISABLED;
+	pthread_cond_broadcast(&test_cond);
+	pthread_mutex_unlock(&test_mutex);
+
+	pthread_join(thread_a, NULL);
+	pthread_join(thread_b, NULL);
+
+	/* Verify thread affinities AFTER disabling controller */
+	if (!cpu_set_equal(&affinity_a_after, 0x3)) {
+		ksft_print_msg("FAIL: thread_a final affinity incorrect\n");
+		goto cleanup;
+	}
+
+	if (!cpu_set_equal(&affinity_b_after, 0x3)) {
+		ksft_print_msg("FAIL: thread_b affinity did not expand to {0-1}\n");
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+	goto cleanup;
+
+skip:
+	ret = KSFT_SKIP;
+	goto cleanup;
+
+cleanup_threads:
+	pthread_mutex_lock(&test_mutex);
+	test_phase = AFFINITY_COMPLETE;
+	pthread_cond_broadcast(&test_cond);
+	pthread_mutex_unlock(&test_mutex);
+
+	if (thread_a_created)
+		pthread_join(thread_a, NULL);
+	if (thread_b_created)
+		pthread_join(thread_b, NULL);
+
+cleanup:
+	/* Move back to root before cleanup */
+	cg_enter_current(root);
+
+	cg_destroy(child_b);
+	free(child_b);
+	cg_destroy(child_a);
+	free(child_a);
+	cg_destroy(parent);
+	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),
+	T(test_cpuset_affinity_on_controller_disable),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	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");
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
new file mode 100755
index 000000000..131d8b455
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -0,0 +1,1288 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test for cpuset v2 partition root state (PRS)
+#
+# The sched verbose flag can be optionally set so that the console log
+# can be examined for the correct setting of scheduling domain.
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+
+# Get wait_inotify location
+WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify
+
+# Find cgroup v2 mount point
+CGROUP2=$(mount -t cgroup2 | head -1 | awk '{print $3}')
+[[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!"
+SUBPARTS_CPUS=$CGROUP2/.__DEBUG__.cpuset.cpus.subpartitions
+CPULIST=$(cat $CGROUP2/cpuset.cpus.effective)
+
+NR_CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//")
+[[ $NR_CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!"
+
+# Check to see if /dev/console exists and is writable
+if [[ -c /dev/console && -w /dev/console ]]
+then
+	CONSOLE=/dev/console
+else
+	CONSOLE=/dev/null
+fi
+
+# Set verbose flag and delay factor
+PROG=$1
+VERBOSE=0
+DELAY_FACTOR=1
+SCHED_DEBUG=
+while [[ "$1" = -* ]]
+do
+	case "$1" in
+		-v) ((VERBOSE++))
+		    # Enable sched/verbose can slow thing down
+		    [[ $DELAY_FACTOR -eq 1 ]] &&
+			DELAY_FACTOR=2
+		    ;;
+		-d) DELAY_FACTOR=$2
+		    shift
+		    ;;
+		*)  echo "Usage: $PROG [-v] [-d <delay-factor>"
+		    exit
+		    ;;
+	esac
+	shift
+done
+
+# Set sched verbose flag if available when "-v" option is specified
+if [[ $VERBOSE -gt 0 && -d /sys/kernel/debug/sched ]]
+then
+	# Used to restore the original setting during cleanup
+	SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose)
+	echo Y > /sys/kernel/debug/sched/verbose
+fi
+
+cd $CGROUP2
+echo +cpuset > cgroup.subtree_control
+
+#
+# If cpuset has been set up and used in child cgroups, we may not be able to
+# create partition under root cgroup because of the CPU exclusivity rule.
+# So we are going to skip the test if this is the case.
+#
+[[ -d test ]] || mkdir test
+echo 0-6 > test/cpuset.cpus
+echo root > test/cpuset.cpus.partition
+cat test/cpuset.cpus.partition | grep -q invalid
+RESULT=$?
+echo member > test/cpuset.cpus.partition
+echo "" > test/cpuset.cpus
+[[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!"
+
+#
+# If isolated CPUs have been reserved at boot time (as shown in
+# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
+# that will be used by this script for testing purpose. If not, some of
+# the tests may fail incorrectly. Wait a bit and retry again just in case
+# these isolated CPUs are leftover from previous run and have just been
+# cleaned up earlier in this script.
+#
+# These pre-isolated CPUs should stay in an isolated state throughout the
+# testing process for now.
+#
+BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+[[ -n "$BOOT_ISOLCPUS" ]] && {
+	sleep 0.5
+	BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+}
+if [[ -n "$BOOT_ISOLCPUS" ]]
+then
+	[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
+		skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
+	echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
+fi
+
+cleanup()
+{
+	online_cpus
+	cd $CGROUP2
+	rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
+	rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
+	      rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
+	[[ -n "$SCHED_DEBUG" ]] &&
+		echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
+}
+
+# Pause in ms
+pause()
+{
+	DELAY=$1
+	LOOP=0
+	while [[ $LOOP -lt $DELAY_FACTOR ]]
+	do
+		sleep $DELAY
+		((LOOP++))
+	done
+	return 0
+}
+
+console_msg()
+{
+	MSG=$1
+	echo "$MSG"
+	echo "" > $CONSOLE
+	echo "$MSG" > $CONSOLE
+	pause 0.01
+}
+
+test_partition()
+{
+	EXPECTED_VAL=$1
+	echo $EXPECTED_VAL > cpuset.cpus.partition
+	[[ $? -eq 0 ]] || exit 1
+	ACTUAL_VAL=$(cat cpuset.cpus.partition)
+	[[ $ACTUAL_VAL != $EXPECTED_VAL ]] && {
+		echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $ACTUAL_VAL"
+		echo "Test FAILED"
+		exit 1
+	}
+}
+
+test_effective_cpus()
+{
+	EXPECTED_VAL=$1
+	ACTUAL_VAL=$(cat cpuset.cpus.effective)
+	[[ "$ACTUAL_VAL" != "$EXPECTED_VAL" ]] && {
+		echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$ACTUAL_VAL'"
+		echo "Test FAILED"
+		exit 1
+	}
+}
+
+# Adding current process to cgroup.procs as a test
+test_add_proc()
+{
+	OUTSTR="$1"
+	ERRMSG=$((echo $$ > cgroup.procs) |& cat)
+	echo $ERRMSG | grep -q "$OUTSTR"
+	[[ $? -ne 0 ]] && {
+		echo "cgroup.procs: expect '$OUTSTR', got '$ERRMSG'"
+		echo "Test FAILED"
+		exit 1
+	}
+	echo $$ > $CGROUP2/cgroup.procs	# Move out the task
+}
+
+#
+# Cpuset controller state transition test matrix.
+#
+# Cgroup test hierarchy
+#
+#	      root
+#	        |
+#	 +------+------+
+#	 |             |
+#	 A1            B1
+#	 |
+#	 A2
+#	 |
+#	 A3
+#
+#  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
+#  C<l> = add cpu-list to cpuset.cpus
+#  X<l> = add cpu-list to cpuset.cpus.exclusive
+#  T    = put a task into cgroup
+#  CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
+#  O<c>=<v> = Write <v> to CPU online file of <c>
+#
+# ECPUs    - effective CPUs of cpusets
+# Pstate   - partition root state
+# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>])
+#
+# Note that if there are 2 fields in ISOLCPUS, the first one is for
+# sched-debug matching which includes offline CPUs and single-CPU partitions
+# while the second one is for matching cpuset.cpus.isolated.
+#
+SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1"
+TEST_MATRIX=(
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	"   C0-1     .      .    C2-3     .    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
+	"   C0-1     .      .    C2-3    P1   C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3    P1    C1:P1    .      .     0 "
+	"   C0-1     .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3     .     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3     .    C1:P1    .     P1     0 "
+	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
+	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
+	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
+	"  C0-3:P1 C2-3:P1  .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
+	"  C2-3:P1  C2:P1   .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
+	"  C2-3:P1  C3:P1   .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+
+	# CPU offlining cases:
+	"   C0-1     .      .    C2-3     .    C4-5     .     O2=0   0 A1:0-1|B1:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
+	"  C0-3:P1 C2-3:P1  .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
+	"  C0-3:P1 C2-3:P1  .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
+	"  C2-3:P1  C3:P1   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P2   .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"  C2-3:P1  C3:P1   .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
+	"  C2-3:P1  C3:P1   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P1   .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"  C2-3:P1  C3:P2   .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-2"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0   .      .     0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|"
+	"  C1-3:P1  C3:P2   .      .      .    T:O3=0  O3=1    .     0 A1:1-2|A2:3 A1:P1|A2:P2  3"
+	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0   .      .     0 A1:1|A2:3|A3:3 A1:P1|A2:P1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0   .     0 A1:1|A2:2|A3:2 A1:P1|A2:P1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O1=1    .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0  O2=1    .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0  O3=1   0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O1=1    .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O2=1    .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	#
+	# Remote partition and cpuset.cpus.exclusive tests
+	#
+	"   C0-3    C1-3  C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3   C2-3     .      .      .      P2    0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2"
+	"   C0-3    C1-3  C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	"   C0-3    C1-3  C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+	"  C4:X0-3  X1-3  X2-3     .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+	"  C4:X0-3  X1-3  X2-3     .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+
+	# Nested remote/local partition tests
+	"   C0-3    C1-3  C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
+	"   C0-3    C1-3  C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+								       A1:P0|A2:P1|A3:P0|B1:P1"
+	"   C0-3    C1-3   C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
+								       A1:P0|A2:P2|A3:P1 2-4|2-3"
+	"   C0-4    C1-4  C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
+								       A1:P0|A2:P2|A3:P1 2"
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
+				   .      .      X5      .      .    0 A1:0-4|A2:1-4|A3:2-4 \
+								       A1:P0|A2:P-2|A3:P-1 ."
+	" C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \
+				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
+								       A1:P0|A2:P2|A3:P-1 2-4"
+
+	# Remote partition offline tests
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3  C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+	"   C0-3    C1-3   C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+
+	# An invalidated remote partition cannot self-recover from hotplug
+	"   C0-3    C1-3   C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+
+	# cpus.exclusive.effective clearing test
+	"   C0-3    C1-3   C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
+
+	# Invalid to valid remote partition transition test
+	"   C0-3    C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+	"   C0-3 C1-3:X3:P2 .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+
+	# Invalid to valid local partition direct transition tests
+	" C1-3:P2  X4:P2    .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+	" C1-3:P2  X4:P2    .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+	" C0-3:P2    .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:5-6 A1:P2|B1:P0"
+	" C0-3:P2    .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+
+	# Local partition invalidation tests
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
+				   .      .      .      .      .     0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
+				   .      .     X4      .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
+	" C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \
+				   .      .    C4:X     .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
+	# Local partition CPU change tests
+	" C0-5:P2  C4-5:P1  .      .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+	" C0-5:P2  C4-5:P1  .      .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+
+	# cpus_allowed/exclusive_cpus update tests
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
+				   .    X:C4     .      P2     .     0 A1:4|A2:4|XA2:|XA3:|A3:4 \
+								       A1:P0|A3:P-2 ."
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
+				   .     X1      .      P2     .     0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
+								       A1:P0|A3:P-2 ."
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \
+				   .      .     X3      P2     .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
+								       A1:P0|A3:P2 3"
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
+				   .      .     X3      .      .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
+								       A1:P0|A3:P2 3"
+	" C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \
+				   .     X4      .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
+								       A1:P0|A3:P-2"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	#
+	# Incorrect change to cpuset.cpus[.exclusive] invalidates partition root
+	#
+	# Adding CPUs to partition root that are not in parent's
+	# cpuset.cpus is allowed, but those extra CPUs are ignored.
+	"  C2-3:P1   C3:P1  .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
+
+	# Taking away all CPUs from parent or itself if there are tasks
+	# will make the partition invalid.
+	"  C2-3:P1   C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+	"   C3:P1     C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+
+	# Changing a partition root to member makes child partitions invalid
+	"  C2-3:P1   C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
+
+	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
+	# as they overlap.
+	"  C2-3:P1   .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+
+	# Deletion of CPUs distributed to child cgroup is allowed.
+	"  C0-1:P1  C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
+
+	# To become a valid partition root, cpuset.cpus must overlap parent's
+	# cpuset.cpus.
+	"  C0-1:P1   .      .    C2-3     .   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
+
+	# Enabling partition with child cpusets is allowed
+	"   C0-1    C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
+
+	# A partition root with non-partition root parent is invalid| but it
+	# can be made valid if its parent becomes a partition root too.
+	"   C0-1    C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
+	"   C0-1   C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
+
+	# A non-exclusive cpuset.cpus change will not invalidate its siblings partition.
+	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2|B1:3 A1:P1|B1:P0"
+	"  C0-1:P1   .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-1|XA1:0-1|B1:2-3 A1:P1|B1:P1"
+	"   C0-1     .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-1|B1:2-3 A1:P0|B1:P1"
+
+	# cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it
+	"   C0-3     .      .    C4-5     X5     .      .      .     0 A1:0-3|B1:4-5"
+
+	# Child partition root that try to take all CPUs from parent partition
+	# with tasks will remain invalid.
+	"  C1-4:P1  P1      .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	"  C1-4:P1  P1      .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
+	"  C1-4:P1  P1      .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+
+	# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
+	# affect cpuset.cpus.exclusive.effective.
+	"  C1-4:X3 C1:X3    .      .       .     C      .      .     0 A2:1-4|XA2:3"
+
+	# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
+	# but creating a local partition out of it is not allowed. Similarly and change
+	# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
+	# invalidate it.
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+								       A1:P0|A2:P2:B1:P1 2-4"
+	"  CX1-4  CX2-4:P2  .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
+								       A1:P0|A2:P2:B1:P-1 2-4"
+	"  CX1-4  CX2-4:P2  .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
+								       A1:P0|A2:P2:B1:P-1 2-4"
+
+	# When multiple partitions with conflicting cpuset.cpus are created, the
+	# latter created ones will only get what are left of the available exclusive
+	# CPUs.
+	"  C1-3:P1   .      .      .       .     .      .   C3-5:P1  0 A1:1-3|B1:4-5:XB1:4-5 A1:P1|B1:P1"
+
+	# cpuset.cpus can be set to a subset of sibling's cpuset.cpus.exclusive
+	" C1-3:X1-3  .      .    C4-5      .     .      .     C1-2   0 A1:1-3|B1:1-2"
+
+	# cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs
+	"   C1-3    C2      .      .       .    T:C     .      .     0 A1:1-3|A2:1-3"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	# Failure cases:
+
+	# A task cannot be added to a partition with no cpu
+	"  C2-3:P1 C3:P1    .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
+
+	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
+	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3|B1:4-5"
+
+	# cpuset.cpus.exclusive cannot be set to a superset of sibling's cpuset.cpus
+	"   C0-3     .      .    C4-5   X3-5     .      .      .     1 A1:0-3|B1:4-5"
+)
+
+#
+# Cpuset controller remote partition test matrix.
+#
+# Cgroup test hierarchy
+#
+#	      root
+#	        |
+#	      rtest (cpuset.cpus.exclusive=1-7)
+#	        |
+#	 +------+------+
+#	 |             |
+#	 p1            p2
+#     +--+--+       +--+--+
+#     |     |       |     |
+#    c11   c12     c21   c22
+#
+# REMOTE_TEST_MATRIX uses the same notational convention as TEST_MATRIX.
+# Only CPUs 1-7 should be used.
+#
+REMOTE_TEST_MATRIX=(
+	#  old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
+	#  new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------- ------- ------- ------- ----- ------ --------
+	"   X1-3   X4-6  X1-2      X3     X4-5     X6 \
+	      .      .     P2      P2      P2      P2    c11:1-2|c12:3|c21:4-5|c22:6 \
+							 c11:P2|c12:P2|c21:P2|c22:P2 1-6"
+	"  CX1-4     .  X1-2:P2    C3      .       .  \
+	      .      .     .      C3-4     .       .     p1:3-4|c11:1-2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P0 1-2"
+	"  CX1-4     .  X1-2:P2    .       .       .  \
+	    X2-4     .     .       .       .       .     p1:1,3-4|c11:2 \
+							 p1:P0|c11:P2 2"
+	"  CX1-5     .  X1-2:P2  X3-5:P1   .       .  \
+	    X2-4     .     .       .       .       .     p1:1,5|c11:2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P1 2"
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
+	      .      .     X2      .       .       .     p1:1|c11:2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P1 2"
+	# p1 as member, will get its effective CPUs from its parent rtest
+	"  CX1-4     .  X1-2:P2  X3-4:P1   .       .  \
+	      .      .     X1     CX2-4    .       .     p1:5-7|c11:1|c12:2-4 \
+							 p1:P0|c11:P2|c12:P1 1"
+	"  CX1-4  X5-6:P1  .       .       .       .  \
+	      .      .  X1-2:P2  X4-5:P1   .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+							 p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
+							 1-2,4-6|1-2,5-6"
+	# c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition
+	"  C1-5:P1   .  C1-4:P1   C2-3     .       .  \
+	      .      .     .       P1      .       .     p1:5|c11:1-4|c12:5 \
+							 p1:P1|c11:P1|c12:P-1"
+	# Narrowing cpuset.cpus to previously sibling-excluded CPUs should
+	# not return CPUs that were never actually owned.
+	"  C1-4:P1   .   C1-2:P1  C1-3:P2  .       .  \
+	      .      .     .       C3      .       .     p1:4|c11:1-2|c12:3 \
+							 p1:P1|c11:P1|c12:P2 3"
+	# Expanding cpuset.cpus to include a previously sibling-excluded CPU
+	# after the sibling has become a member should correctly request it.
+	"  C1-4:P1   .   C1-2:P1  C1-3:P2  .       .  \
+	      .      .     P0      C2-3    .       .     p1:1,4|c11:1|c12:2-3 \
+							 p1:P1|c11:P0|c12:P2 2-3"
+	# Changing a sibling partition's cpuset.cpus to overlap with another
+	# sibling partition should invalidate itself and return only actually
+	# allocated CPUs (effective_xcpus) to the parent.
+	"  C1-4:P1   .   C1-2:P1  C2-4:P2  .       .  \
+	      .      .     .       C1-2    .       .     p1:3-4|c11:1-2|c12:3-4 \
+							 p1:P1|c11:P1|c12:P-2"
+	# Cpusets with empty cpuset.cpus should inherit parent's effective_cpus
+	"  C1-4:P1 C5-6   C1-2     .       C5      .  \
+	      .      P1    P1      .       .       .     p1:3-4|p2:5-6|c11:1-2|c12:3-4|c21:5|c22:5-6 \
+							 p1:P1|p2:P1|c11:P1"
+	"  C1-4:P1 C5-6   C1-2     .       C5      .  \
+	      .      P1    P1      .      O5=0     .     p1:3-4|p2:6|c11:1-2|c12:3-4|c21:6|c22:6 \
+							 p1:P1|p2:P1|c11:P1"
+)
+
+#
+# Write to the cpu online file
+#  $1 - <c>=<v> where <c> = cpu number, <v> value to be written
+#
+write_cpu_online()
+{
+	CPU=${1%=*}
+	VAL=${1#*=}
+	CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online
+	echo $VAL > $CPUFILE || return 1
+	if [[ $VAL -eq 0 ]]
+	then
+		OFFLINE_CPUS="$OFFLINE_CPUS $CPU"
+	else
+		[[ -n "$OFFLINE_CPUS" ]] && {
+			OFFLINE_CPUS=$(echo $CPU $CPU $OFFLINE_CPUS | fmt -1 |\
+					sort | uniq -u)
+		}
+	fi
+	pause 0.05
+}
+
+#
+# Set controller state
+#  $1 - cgroup directory
+#  $2 - state
+#  $3 - showerr
+#
+# The presence of ":" in state means transition from one to the next.
+#
+set_ctrl_state()
+{
+	TMPMSG=/tmp/.msg_$$
+	CGRP=$1
+	STATE=$2
+	SHOWERR=${3}
+	HASERR=0
+	REDIRECT="2> $TMPMSG"
+	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
+	[[ $VERBOSE -gt 0 ]] && SHOWERR=1
+
+	rm -f $TMPMSG
+	for CMD in $(echo $STATE | sed -e "s/:/ /g")
+	do
+		TFILE=$CGRP/cgroup.procs
+		PFILE=$CGRP/cpuset.cpus.partition
+		CFILE=$CGRP/cpuset.cpus
+		XFILE=$CGRP/cpuset.cpus.exclusive
+
+		# Enable cpuset controller if not enabled yet
+		[[ -f $CFILE ]] || {
+			COMM="echo +cpuset > $CGRP/../cgroup.subtree_control"
+			eval $COMM $REDIRECT
+		}
+		case $CMD in
+		    X*)
+			CPUS=${CMD#?}
+			COMM="echo $CPUS > $XFILE"
+			eval $COMM $REDIRECT
+			;;
+		    CX*)
+			CPUS=${CMD#??}
+			COMM="echo $CPUS > $CFILE; echo $CPUS > $XFILE"
+			eval $COMM $REDIRECT
+			;;
+		    C*) CPUS=${CMD#?}
+			COMM="echo $CPUS > $CFILE"
+			eval $COMM $REDIRECT
+			;;
+		    P*) VAL=${CMD#?}
+			case $VAL in
+			0)  VAL=member
+			    ;;
+			1)  VAL=root
+			    ;;
+			2)  VAL=isolated
+			    ;;
+			*)
+			    echo "Invalid partition state - $VAL"
+			    exit 1
+			    ;;
+			esac
+			COMM="echo $VAL > $PFILE"
+			eval $COMM $REDIRECT
+			;;
+		    O*) VAL=${CMD#?}
+			COMM="write_cpu_online $VAL"
+			eval $COMM $REDIRECT
+			;;
+		    T*) COMM="echo 0 > $TFILE"
+			eval $COMM $REDIRECT
+			;;
+		    *)  echo "Unknown command: $CMD"
+		        exit 1
+			;;
+		esac
+		RET=$?
+		[[ $RET -ne 0 ]] && {
+			[[ -n "$SHOWERR" ]] && {
+				echo "$COMM"
+				cat $TMPMSG
+			}
+			HASERR=1
+		}
+		pause 0.01
+		rm -f $TMPMSG
+	done
+	return $HASERR
+}
+
+set_ctrl_state_noerr()
+{
+	CGRP=$1
+	STATE=$2
+	[[ -d $CGRP ]] || mkdir $CGRP
+	set_ctrl_state $CGRP $STATE 1
+	[[ $? -ne 0 ]] && {
+		echo "ERROR: Failed to set $2 to cgroup $1!"
+		exit 1
+	}
+}
+
+online_cpus()
+{
+	[[ -n "$OFFLINE_CPUS" ]] && {
+		for C in $OFFLINE_CPUS
+		do
+			write_cpu_online ${C}=1
+		done
+	}
+}
+
+#
+# Remove all the test cgroup directories
+#
+reset_cgroup_states()
+{
+	echo 0 > $CGROUP2/cgroup.procs
+	online_cpus
+	rmdir $RESET_LIST > /dev/null 2>&1
+}
+
+dump_states()
+{
+	for DIR in $CGROUP_LIST
+	do
+		CPUS=$DIR/cpuset.cpus
+		ECPUS=$DIR/cpuset.cpus.effective
+		XCPUS=$DIR/cpuset.cpus.exclusive
+		XECPUS=$DIR/cpuset.cpus.exclusive.effective
+		PRS=$DIR/cpuset.cpus.partition
+		PCPUS=$DIR/.__DEBUG__.cpuset.cpus.subpartitions
+		ISCPUS=$DIR/cpuset.cpus.isolated
+		[[ -e $CPUS   ]] && echo "$CPUS: $(cat $CPUS)"
+		[[ -e $XCPUS  ]] && echo "$XCPUS: $(cat $XCPUS)"
+		[[ -e $ECPUS  ]] && echo "$ECPUS: $(cat $ECPUS)"
+		[[ -e $XECPUS ]] && echo "$XECPUS: $(cat $XECPUS)"
+		[[ -e $PRS    ]] && echo "$PRS: $(cat $PRS)"
+		[[ -e $PCPUS  ]] && echo "$PCPUS: $(cat $PCPUS)"
+		[[ -e $ISCPUS ]] && echo "$ISCPUS: $(cat $ISCPUS)"
+	done
+}
+
+#
+# Set the actual cgroup directory into $CGRP_DIR
+# $1 - cgroup name
+#
+set_cgroup_dir()
+{
+	CGRP_DIR=$1
+	[[ $CGRP_DIR = A2  ]] && CGRP_DIR=A1/A2
+	[[ $CGRP_DIR = A3  ]] && CGRP_DIR=A1/A2/A3
+	[[ $CGRP_DIR = c11 ]] && CGRP_DIR=p1/c11
+	[[ $CGRP_DIR = c12 ]] && CGRP_DIR=p1/c12
+	[[ $CGRP_DIR = c21 ]] && CGRP_DIR=p2/c21
+	[[ $CGRP_DIR = c22 ]] && CGRP_DIR=p2/c22
+}
+
+#
+# Check effective cpus
+# $1 - check string, format: <cgroup>:<cpu-list>[|<cgroup>:<cpu-list>]*
+#
+check_effective_cpus()
+{
+	CHK_STR=$1
+	for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
+	do
+		set -- $(echo $CHK | sed -e "s/:/ /g")
+		CGRP=$1
+		EXPECTED_CPUS=$2
+		ACTUAL_CPUS=
+		if [[ $CGRP = X* ]]
+		then
+			CGRP=${CGRP#X}
+			FILE=cpuset.cpus.exclusive.effective
+		else
+			FILE=cpuset.cpus.effective
+		fi
+		set_cgroup_dir $CGRP
+		[[ -e $CGRP_DIR/$FILE ]] || return 1
+		ACTUAL_CPUS=$(cat $CGRP_DIR/$FILE)
+		[[ $EXPECTED_CPUS = $ACTUAL_CPUS ]] || return 1
+	done
+}
+
+#
+# Check cgroup states
+#  $1 - check string, format: <cgroup>:<state>[|<cgroup>:<state>]*
+#
+check_cgroup_states()
+{
+	CHK_STR=$1
+	for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
+	do
+		set -- $(echo $CHK | sed -e "s/:/ /g")
+		CGRP=$1
+		EXPECTED_STATE=$2
+		FILE=
+		EVAL=$(expr substr $EXPECTED_STATE 2 2)
+
+		set_cgroup_dir $CGRP
+		case $EXPECTED_STATE in
+			P*) FILE=$CGRP_DIR/cpuset.cpus.partition
+			    ;;
+			*)  echo "Unknown state: $EXPECTED_STATE!"
+			    exit 1
+			    ;;
+		esac
+		ACTUAL_STATE=$(cat $FILE)
+
+		case "$ACTUAL_STATE" in
+			member) VAL=0
+				;;
+			root)	VAL=1
+				;;
+			isolated)
+				VAL=2
+				;;
+			"root invalid"*)
+				VAL=-1
+				;;
+			"isolated invalid"*)
+				VAL=-2
+				;;
+		esac
+		[[ $EVAL != $VAL ]] && return 1
+
+		#
+		# For root partition, dump sched-domains info to console if
+		# verbose mode set for manual comparison with sched debug info.
+		#
+		[[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && {
+			DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective)
+			[[ -n "$DOMS" ]] &&
+				echo " [$CGRP_DIR] sched-domain: $DOMS" > $CONSOLE
+		}
+	done
+	return 0
+}
+
+#
+# Get isolated (including offline) CPUs by looking at
+# /sys/kernel/debug/sched/domains and cpuset.cpus.isolated control file,
+# if available, and compare that with the expected value.
+#
+# Note that isolated CPUs from the sched/domains context include offline
+# CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may
+# not be included in the cpuset.cpus.isolated control file which contains
+# only CPUs in isolated partitions as well as those that are isolated at
+# boot time.
+#
+# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>}
+# <isolcpus1> - expected sched/domains value
+# <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
+#
+check_isolcpus()
+{
+	EXPECTED_ISOLCPUS=$1
+	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
+	ISOLCPUS=$(cat $ISCPUS)
+	LASTISOLCPU=
+	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
+	if [[ $EXPECTED_ISOLCPUS = . ]]
+	then
+		EXPECTED_ISOLCPUS=
+		EXPECTED_SDOMAIN=
+	elif [[ $(expr $EXPECTED_ISOLCPUS : ".*|.*") > 0 ]]
+	then
+		set -- $(echo $EXPECTED_ISOLCPUS | sed -e "s/|/ /g")
+		EXPECTED_ISOLCPUS=$2
+		EXPECTED_SDOMAIN=$1
+	else
+		EXPECTED_SDOMAIN=$EXPECTED_ISOLCPUS
+	fi
+
+	#
+	# Appending pre-isolated CPUs
+	# Even though CPU #8 isn't used for testing, it can't be pre-isolated
+	# to make appending those CPUs easier.
+	#
+	[[ -n "$BOOT_ISOLCPUS" ]] && {
+		EXPECTED_ISOLCPUS=${EXPECTED_ISOLCPUS:+${EXPECTED_ISOLCPUS},}${BOOT_ISOLCPUS}
+		EXPECTED_SDOMAIN=${EXPECTED_SDOMAIN:+${EXPECTED_SDOMAIN},}${BOOT_ISOLCPUS}
+	}
+
+	#
+	# Check cpuset.cpus.isolated cpumask
+	#
+	[[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && {
+		# Take a 50ms pause and try again
+		pause 0.05
+		ISOLCPUS=$(cat $ISCPUS)
+	}
+	[[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && return 1
+	ISOLCPUS=
+	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
+
+	#
+	# Use the sched domain in debugfs to check isolated CPUs, if available
+	#
+	[[ -d $SCHED_DOMAINS ]] || return 0
+
+	for ((CPU=0; CPU < $NR_CPUS; CPU++))
+	do
+		[[ -n "$(ls ${SCHED_DOMAINS}/cpu$CPU)" ]] && continue
+
+		if [[ -z "$LASTISOLCPU" ]]
+		then
+			ISOLCPUS=$CPU
+			LASTISOLCPU=$CPU
+		elif [[ "$LASTISOLCPU" -eq $((CPU - 1)) ]]
+		then
+			echo $ISOLCPUS | grep -q "\<$LASTISOLCPU\$"
+			if [[ $? -eq 0 ]]
+			then
+				ISOLCPUS=${ISOLCPUS}-
+			fi
+			LASTISOLCPU=$CPU
+		else
+			if [[ $ISOLCPUS = *- ]]
+			then
+				ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+			fi
+			ISOLCPUS=${ISOLCPUS},$CPU
+			LASTISOLCPU=$CPU
+		fi
+	done
+	[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+
+	[[ "$EXPECTED_SDOMAIN" = "$ISOLCPUS" ]]
+}
+
+test_fail()
+{
+	TESTNUM=$1
+	TESTTYPE=$2
+	ADDINFO=$3
+	echo "Test $TEST[$TESTNUM] failed $TESTTYPE check!"
+	[[ -n "$ADDINFO" ]] && echo "*** $ADDINFO ***"
+	eval echo \${$TEST[$I]}
+	echo
+	dump_states
+	exit 1
+}
+
+#
+# Check to see if there are unexpected isolated CPUs left beyond the boot
+# time isolated ones.
+#
+null_isolcpus_check()
+{
+	[[ $VERBOSE -gt 0 ]] || return 0
+	# Retry a few times before printing error
+	RETRY=0
+	while [[ $RETRY -lt 8 ]]
+	do
+		pause 0.02
+		check_isolcpus "."
+		[[ $? -eq 0 ]] && return 0
+		((RETRY++))
+	done
+	echo "Unexpected isolated CPUs: $ISOLCPUS"
+	dump_states
+	exit 1
+}
+
+#
+# Check state transition test result
+#  $1 - Test number
+#  $2 - Expected effective CPU values
+#  $3 - Expected partition states
+#  $4 - Expected isolated CPUs
+#
+check_test_results()
+{
+	_NR=$1
+	_ECPUS="$2"
+	_PSTATES="$3"
+	_ISOLCPUS="$4"
+
+	[[ -n "$_ECPUS" && "$_ECPUS" != . ]] && {
+		check_effective_cpus $_ECPUS
+		[[ $? -ne 0 ]] && test_fail $_NR "effective CPU" \
+			 "Cgroup $CGRP: expected $EXPECTED_CPUS, got $ACTUAL_CPUS"
+	}
+
+	[[ -n "$_PSTATES" && "$_PSTATES" != . ]] && {
+		check_cgroup_states $_PSTATES
+		[[ $? -ne 0 ]] && test_fail $_NR states \
+			"Cgroup $CGRP: expected $EXPECTED_STATE, got $ACTUAL_STATE"
+	}
+
+	# Compare the expected isolated CPUs with the actual ones,
+	# if available
+	[[ -n "$_ISOLCPUS" ]] && {
+		check_isolcpus $_ISOLCPUS
+		[[ $? -ne 0 ]] && {
+			[[ -n "$BOOT_ISOLCPUS" ]] && _ISOLCPUS=${_ISOLCPUS},${BOOT_ISOLCPUS}
+			test_fail $_NR "isolated CPU" \
+				"Expect $_ISOLCPUS, get $ISOLCPUS instead"
+		}
+	}
+	reset_cgroup_states
+	#
+	# Check to see if effective cpu list changes
+	#
+	_NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+	RETRY=0
+	while [[ $_NEWLIST != $CPULIST && $RETRY -lt 8 ]]
+	do
+		# Wait a bit longer & recheck a few times
+		pause 0.02
+		((RETRY++))
+		_NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+	done
+	[[ $_NEWLIST != $CPULIST ]] && {
+		echo "Effective cpus changed to $_NEWLIST after test $_NR!"
+		exit 1
+	}
+	null_isolcpus_check
+	[[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+}
+
+#
+# Run cpuset state transition test
+#  $1 - test matrix name
+#
+# This test is somewhat fragile as delays (sleep x) are added in various
+# places to make sure state changes are fully propagated before the next
+# action. These delays may need to be adjusted if running in a slower machine.
+#
+run_state_test()
+{
+	TEST=$1
+	CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
+	RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
+	I=0
+	eval CNT="\${#$TEST[@]}"
+
+	reset_cgroup_states
+	console_msg "Running state transition test ..."
+
+	while [[ $I -lt $CNT ]]
+	do
+		echo "Running test $I ..." > $CONSOLE
+		[[ $VERBOSE -gt 1 ]] && {
+			echo ""
+			eval echo \${$TEST[$I]}
+		}
+		eval set -- "\${$TEST[$I]}"
+		OLD_A1=$1
+		OLD_A2=$2
+		OLD_A3=$3
+		OLD_B1=$4
+		NEW_A1=$5
+		NEW_A2=$6
+		NEW_A3=$7
+		NEW_B1=$8
+		RESULT=$9
+		ECPUS=${10}
+		STATES=${11}
+		ICPUS=${12}
+
+		set_ctrl_state_noerr A1       $OLD_A1
+		set_ctrl_state_noerr A1/A2    $OLD_A2
+		set_ctrl_state_noerr A1/A2/A3 $OLD_A3
+		set_ctrl_state_noerr B1       $OLD_B1
+
+		RETVAL=0
+		set_ctrl_state A1       $NEW_A1; ((RETVAL += $?))
+		set_ctrl_state A1/A2    $NEW_A2; ((RETVAL += $?))
+		set_ctrl_state A1/A2/A3 $NEW_A3; ((RETVAL += $?))
+		set_ctrl_state B1       $NEW_B1; ((RETVAL += $?))
+
+		[[ $RETVAL -ne $RESULT ]] && test_fail $I result
+
+		check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
+		((I++))
+	done
+	echo "All $I tests of $TEST PASSED."
+}
+
+#
+# Run cpuset remote partition state transition test
+#  $1 - test matrix name
+#
+run_remote_state_test()
+{
+	TEST=$1
+	[[ -d rtest ]] || mkdir rtest
+	cd rtest
+	echo +cpuset > cgroup.subtree_control
+	echo "1-7" > cpuset.cpus
+	echo "1-7" > cpuset.cpus.exclusive
+	CGROUP_LIST=".. . p1 p2 p1/c11 p1/c12 p2/c21 p2/c22"
+	RESET_LIST="p1/c11 p1/c12 p2/c21 p2/c22 p1 p2"
+	I=0
+	eval CNT="\${#$TEST[@]}"
+
+	reset_cgroup_states
+	console_msg "Running remote partition state transition test ..."
+
+	while [[ $I -lt $CNT ]]
+	do
+		echo "Running test $I ..." > $CONSOLE
+		[[ $VERBOSE -gt 1 ]] && {
+			echo ""
+			eval echo \${$TEST[$I]}
+		}
+		eval set -- "\${$TEST[$I]}"
+		OLD_p1=$1
+		OLD_p2=$2
+		OLD_c11=$3
+		OLD_c12=$4
+		OLD_c21=$5
+		OLD_c22=$6
+		NEW_p1=$7
+		NEW_p2=$8
+		NEW_c11=$9
+		NEW_c12=${10}
+		NEW_c21=${11}
+		NEW_c22=${12}
+		ECPUS=${13}
+		STATES=${14}
+		ICPUS=${15}
+
+		set_ctrl_state_noerr p1     $OLD_p1
+		set_ctrl_state_noerr p2     $OLD_p2
+		set_ctrl_state_noerr p1/c11 $OLD_c11
+		set_ctrl_state_noerr p1/c12 $OLD_c12
+		set_ctrl_state_noerr p2/c21 $OLD_c21
+		set_ctrl_state_noerr p2/c22 $OLD_c22
+
+		RETVAL=0
+		set_ctrl_state p1     $NEW_p1 ; ((RETVAL += $?))
+		set_ctrl_state p2     $NEW_p2 ; ((RETVAL += $?))
+		set_ctrl_state p1/c11 $NEW_c11; ((RETVAL += $?))
+		set_ctrl_state p1/c12 $NEW_c12; ((RETVAL += $?))
+		set_ctrl_state p2/c21 $NEW_c21; ((RETVAL += $?))
+		set_ctrl_state p2/c22 $NEW_c22; ((RETVAL += $?))
+
+		[[ $RETVAL -ne 0 ]] && test_fail $I result
+
+		check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
+		((I++))
+	done
+	cd ..
+	rmdir rtest
+	echo "All $I tests of $TEST PASSED."
+}
+
+#
+# Testing the new "isolated" partition root type
+#
+test_isolated()
+{
+	cd $CGROUP2/test
+	echo 2-3 > cpuset.cpus
+	TYPE=$(cat cpuset.cpus.partition)
+	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
+
+	console_msg "Change from member to root"
+	test_partition root
+
+	console_msg "Change from root to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to member"
+	test_partition member
+
+	console_msg "Change from member to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to root"
+	test_partition root
+
+	console_msg "Change from root to member"
+	test_partition member
+
+	#
+	# Testing partition root with no cpu
+	#
+	console_msg "Distribute all cpus to child partition"
+	echo +cpuset > cgroup.subtree_control
+	test_partition root
+
+	mkdir A1
+	cd A1
+	echo 2-3 > cpuset.cpus
+	test_partition root
+	test_effective_cpus 2-3
+	cd ..
+	test_effective_cpus ""
+
+	console_msg "Moving task to partition test"
+	test_add_proc "No space left"
+	cd A1
+	test_add_proc ""
+	cd ..
+
+	console_msg "Shrink and expand child partition"
+	cd A1
+	echo 2 > cpuset.cpus
+	cd ..
+	test_effective_cpus 3
+	cd A1
+	echo 2-3 > cpuset.cpus
+	cd ..
+	test_effective_cpus ""
+
+	# Cleaning up
+	console_msg "Cleaning up"
+	echo $$ > $CGROUP2/cgroup.procs
+	[[ -d A1 ]] && rmdir A1
+	null_isolcpus_check
+	pause 0.05
+}
+
+#
+# Select an online CPU isolated from scheduler domains at boot.
+# $1: test name used in the skip message
+#
+get_boot_isolated_cpu()
+{
+	TEST_NAME=$1
+	BOOT_ISOLATED_FILE=/sys/devices/system/cpu/isolated
+
+	[[ -r $BOOT_ISOLATED_FILE ]] || {
+		echo "$TEST_NAME test SKIPPED: boot isolation state unavailable"
+		return 1
+	}
+	BOOT_CPUS=$(cat $BOOT_ISOLATED_FILE)
+	[[ -n "$BOOT_CPUS" ]] || {
+		echo "$TEST_NAME test SKIPPED: no boot-isolated CPU"
+		return 1
+	}
+
+	BOOT_CPU=$(echo "$BOOT_CPUS" | sed -e 's/[,-].*//')
+	CPU_ONLINE=/sys/devices/system/cpu/cpu${BOOT_CPU}/online
+	[[ ! -e $CPU_ONLINE || $(cat $CPU_ONLINE) -eq 1 ]] || {
+		echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is offline"
+		return 1
+	}
+}
+
+#
+# A CPU isolated at boot must stay isolated after it is released by a dynamic
+# isolated partition.
+#
+test_boot_isolated()
+{
+	TEST_NAME="Boot-isolated CPU partition release"
+	get_boot_isolated_cpu "$TEST_NAME" || return 0
+	echo "Running $TEST_NAME test ..."
+
+	cd $CGROUP2/test
+	echo member > cpuset.cpus.partition
+	echo $BOOT_CPU > cpuset.cpus
+	[[ $(cat cpuset.cpus.effective) = "$BOOT_CPU" ]] || {
+		echo "$TEST_NAME test SKIPPED: CPU $BOOT_CPU is unavailable"
+		echo "" > cpuset.cpus
+		cd $CGROUP2
+		return 0
+	}
+	test_partition isolated
+	test_partition member
+	check_isolcpus "." || {
+		echo "Boot-isolated CPU $BOOT_CPU was lost after partition release"
+		exit 1
+	}
+	echo "" > cpuset.cpus
+	cd $CGROUP2
+	echo "$TEST_NAME test PASSED."
+}
+
+#
+# Wait for inotify event for the given file and read it
+# $1: cgroup file to wait for
+# $2: file to store the read result
+#
+wait_inotify()
+{
+	CGROUP_FILE=$1
+	OUTPUT_FILE=$2
+
+	$WAIT_INOTIFY $CGROUP_FILE
+	cat $CGROUP_FILE > $OUTPUT_FILE
+}
+
+#
+# Test if inotify events are properly generated when going into and out of
+# invalid partition state.
+#
+test_inotify()
+{
+	ERR=0
+	PRS=/tmp/.prs_$$
+	cd $CGROUP2/test
+	[[ -f $WAIT_INOTIFY ]] || {
+		echo "wait_inotify not found, inotify test SKIPPED."
+		return
+	}
+
+	pause 0.01
+	echo 1 > cpuset.cpus
+	echo 0 > cgroup.procs
+	echo root > cpuset.cpus.partition
+	pause 0.01
+	rm -f $PRS
+	wait_inotify $PWD/cpuset.cpus.partition $PRS &
+	pause 0.01
+	set_ctrl_state . "O1=0"
+	pause 0.01
+	check_cgroup_states ".:P-1"
+	if [[ $? -ne 0 ]]
+	then
+		echo "FAILED: Inotify test - partition not invalid"
+		ERR=1
+	elif [[ ! -f $PRS ]]
+	then
+		echo "FAILED: Inotify test - event not generated"
+		ERR=1
+		kill %1
+	elif [[ $(cat $PRS) != "root invalid"* ]]
+	then
+		echo "FAILED: Inotify test - incorrect state"
+		cat $PRS
+		ERR=1
+	fi
+	online_cpus
+	echo member > cpuset.cpus.partition
+	echo 0 > ../cgroup.procs
+	if [[ $ERR -ne 0 ]]
+	then
+		exit 1
+	else
+		echo "Inotify test PASSED"
+	fi
+	echo member > cpuset.cpus.partition
+	echo "" > cpuset.cpus
+}
+
+trap cleanup 0 2 3 6
+run_state_test TEST_MATRIX
+run_remote_state_test REMOTE_TEST_MATRIX
+test_isolated
+test_boot_isolated
+test_inotify
+echo "All tests PASSED."
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
new file mode 100755
index 000000000..1c0444729
--- /dev/null
+++ b/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
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
new file mode 100755
index 000000000..da97f1643
--- /dev/null
+++ b/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 '{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
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
new file mode 100644
index 000000000..f28bb02e9
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -0,0 +1,1512 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdbool.h>
+#include <linux/limits.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/wait.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+#define DEBUG
+#ifdef DEBUG
+#define debug(args...) fprintf(stderr, args)
+#else
+#define debug(args...)
+#endif
+
+/*
+ * Check if the cgroup is frozen by looking at the cgroup.events::frozen value.
+ */
+static int cg_check_frozen(const char *cgroup, bool frozen)
+{
+	if (frozen) {
+		if (cg_read_strstr(cgroup, "cgroup.events", "frozen 1") != 0) {
+			debug("Cgroup %s isn't frozen\n", cgroup);
+			return -1;
+		}
+	} else {
+		/*
+		 * Check the cgroup.events::frozen value.
+		 */
+		if (cg_read_strstr(cgroup, "cgroup.events", "frozen 0") != 0) {
+			debug("Cgroup %s is frozen\n", cgroup);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Freeze the given cgroup.
+ */
+static int cg_freeze_nowait(const char *cgroup, bool freeze)
+{
+	return cg_write(cgroup, "cgroup.freeze", freeze ? "1" : "0");
+}
+
+/*
+ * Attach a task to the given cgroup and wait for a cgroup frozen event.
+ * All transient events (e.g. populated) are ignored.
+ */
+static int cg_enter_and_wait_for_frozen(const char *cgroup, int pid,
+					bool frozen)
+{
+	int fd, ret = -1;
+	int attempts;
+
+	fd = cg_prepare_for_wait(cgroup);
+	if (fd < 0)
+		return fd;
+
+	ret = cg_enter(cgroup, pid);
+	if (ret)
+		goto out;
+
+	for (attempts = 0; attempts < 10; attempts++) {
+		ret = cg_wait_for(fd);
+		if (ret)
+			break;
+
+		ret = cg_check_frozen(cgroup, frozen);
+		if (ret)
+			continue;
+	}
+
+out:
+	close(fd);
+	return ret;
+}
+
+/*
+ * Freeze 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_freeze_wait(const char *cgroup, bool freeze)
+{
+	int fd, ret = -1;
+
+	fd = cg_prepare_for_wait(cgroup);
+	if (fd < 0)
+		return fd;
+
+	ret = cg_freeze_nowait(cgroup, freeze);
+	if (ret) {
+		debug("Error: cg_freeze_nowait() failed\n");
+		goto out;
+	}
+
+	ret = cg_wait_for(fd);
+	if (ret)
+		goto out;
+
+	ret = cg_check_frozen(cgroup, freeze);
+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;
+}
+
+/*
+ * A simple test for the cgroup freezer: populated the cgroup with 100
+ * running processes and freeze it. Then unfreeze it. Then it kills all
+ * processes and destroys the cgroup.
+ */
+static int test_cgfreezer_simple(const char *root)
+{
+	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++)
+		cg_run_nowait(cgroup, child_fn, NULL);
+
+	if (cg_wait_for_proc_count(cgroup, 100))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup, false))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, false))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	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 freeze and unfreeze the whole tree.
+ */
+static int test_cgfreezer_tree(const char *root)
+{
+	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;
+
+	cg_run_nowait(cgroup[2], child_fn, NULL);
+	cg_run_nowait(cgroup[7], child_fn, NULL);
+	cg_run_nowait(cgroup[9], child_fn, NULL);
+	cg_run_nowait(cgroup[9], child_fn, NULL);
+	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;
+
+	/*
+	 * Freeze B.
+	 */
+	if (cg_freeze_wait(cgroup[1], true))
+		goto cleanup;
+
+	/*
+	 * Freeze F.
+	 */
+	if (cg_freeze_wait(cgroup[5], true))
+		goto cleanup;
+
+	/*
+	 * Freeze G.
+	 */
+	if (cg_freeze_wait(cgroup[6], true))
+		goto cleanup;
+
+	/*
+	 * Check that A and E are not frozen.
+	 */
+	if (cg_check_frozen(cgroup[0], false))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[4], false))
+		goto cleanup;
+
+	/*
+	 * Freeze A. Check that A, B and E are frozen.
+	 */
+	if (cg_freeze_wait(cgroup[0], true))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[1], true))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[4], true))
+		goto cleanup;
+
+	/*
+	 * Unfreeze B, F and G
+	 */
+	if (cg_freeze_nowait(cgroup[1], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[5], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[6], false))
+		goto cleanup;
+
+	/*
+	 * Check that C and H are still frozen.
+	 */
+	if (cg_check_frozen(cgroup[2], true))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[7], true))
+		goto cleanup;
+
+	/*
+	 * Unfreeze A. Check that A, C and K are not frozen.
+	 */
+	if (cg_freeze_wait(cgroup[0], false))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[2], false))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[9], false))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = 9; i >= 0 && cgroup[i]; i--) {
+		cg_destroy(cgroup[i]);
+		free(cgroup[i]);
+	}
+
+	return ret;
+}
+
+/*
+ * A fork bomb emulator.
+ */
+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 freeze it.
+ * Then it kills all processes and checks that cgroup isn't populated
+ * anymore.
+ */
+static int test_cgfreezer_forkbomb(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+
+	cgroup = cg_name(root, "cg_forkbomb_test");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	cg_run_nowait(cgroup, forkbomb_fn, NULL);
+
+	usleep(100000);
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	if (cg_killall(cgroup))
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup, 0))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * The test creates a cgroups and freezes it. Then it creates a child cgroup
+ * and populates it with a task. After that it checks that the child cgroup
+ * is frozen and the parent cgroup remains frozen too.
+ */
+static int test_cgfreezer_mkdir(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child = NULL;
+	int pid;
+
+	parent = cg_name(root, "cg_test_mkdir_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_mkdir_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_freeze_wait(parent, true))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	pid = cg_run_nowait(child, child_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(child, 1))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	if (cg_check_frozen(parent, true))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates two nested cgroups, freezes the parent
+ * and removes the child. Then it checks that the parent cgroup
+ * remains frozen and it's possible to create a new child
+ * without unfreezing. The new child is frozen too.
+ */
+static int test_cgfreezer_rmdir(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child = NULL;
+
+	parent = cg_name(root, "cg_test_rmdir_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_rmdir_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_freeze_wait(parent, true))
+		goto cleanup;
+
+	if (cg_destroy(child))
+		goto cleanup;
+
+	if (cg_check_frozen(parent, true))
+		goto cleanup;
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates two cgroups: A and B, runs a process in A
+ * and performs several migrations:
+ * 1) A (running) -> B (frozen)
+ * 2) B (frozen) -> A (running)
+ * 3) A (frozen) -> B (frozen)
+ *
+ * On each step it checks the actual state of both cgroups.
+ */
+static int test_cgfreezer_migrate(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup[2] = {0};
+	int pid;
+
+	cgroup[0] = cg_name(root, "cg_test_migrate_A");
+	if (!cgroup[0])
+		goto cleanup;
+
+	cgroup[1] = cg_name(root, "cg_test_migrate_B");
+	if (!cgroup[1])
+		goto cleanup;
+
+	if (cg_create(cgroup[0]))
+		goto cleanup;
+
+	if (cg_create(cgroup[1]))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup[0], child_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup[0], 1))
+		goto cleanup;
+
+	/*
+	 * Migrate from A (running) to B (frozen)
+	 */
+	if (cg_freeze_wait(cgroup[1], true))
+		goto cleanup;
+
+	if (cg_enter_and_wait_for_frozen(cgroup[1], pid, true))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[0], false))
+		goto cleanup;
+
+	/*
+	 * Migrate from B (frozen) to A (running)
+	 */
+	if (cg_enter_and_wait_for_frozen(cgroup[0], pid, false))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[1], true))
+		goto cleanup;
+
+	/*
+	 * Migrate from A (frozen) to B (frozen)
+	 */
+	if (cg_freeze_wait(cgroup[0], true))
+		goto cleanup;
+
+	if (cg_enter_and_wait_for_frozen(cgroup[1], pid, true))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup[0], true))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup[0])
+		cg_destroy(cgroup[0]);
+	free(cgroup[0]);
+	if (cgroup[1])
+		cg_destroy(cgroup[1]);
+	free(cgroup[1]);
+	return ret;
+}
+
+/*
+ * The test checks that ptrace works with a tracing process in a frozen cgroup.
+ */
+static int test_cgfreezer_ptrace(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	siginfo_t siginfo;
+	int pid;
+
+	cgroup = cg_name(root, "cg_test_ptrace");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup, child_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup, 1))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	if (ptrace(PTRACE_SEIZE, pid, NULL, NULL))
+		goto cleanup;
+
+	if (ptrace(PTRACE_INTERRUPT, pid, NULL, NULL))
+		goto cleanup;
+
+	waitpid(pid, NULL, 0);
+
+	/*
+	 * Cgroup has to remain frozen, however the test task
+	 * is in traced state.
+	 */
+	if (cg_check_frozen(cgroup, true))
+		goto cleanup;
+
+	if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo))
+		goto cleanup;
+
+	if (ptrace(PTRACE_DETACH, pid, NULL, NULL))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup, true))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Check if the process is stopped.
+ */
+static int proc_check_stopped(int pid)
+{
+	char buf[BUF_SIZE];
+	int len;
+
+	len = proc_read_text(pid, 0, "stat", buf, sizeof(buf));
+	if (len == -1) {
+		debug("Can't get %d stat\n", pid);
+		return -1;
+	}
+
+	if (strstr(buf, "(test_freezer) T ") == NULL) {
+		debug("Process %d in the unexpected state: %s\n", pid, buf);
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Test that it's possible to freeze a cgroup with a stopped process.
+ */
+static int test_cgfreezer_stopped(const char *root)
+{
+	int pid, ret = KSFT_FAIL;
+	char *cgroup = NULL;
+
+	cgroup = cg_name(root, "cg_test_stopped");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup, child_fn, NULL);
+
+	if (cg_wait_for_proc_count(cgroup, 1))
+		goto cleanup;
+
+	if (kill(pid, SIGSTOP))
+		goto cleanup;
+
+	if (cg_check_frozen(cgroup, false))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, false))
+		goto cleanup;
+
+	if (proc_check_stopped(pid))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Test that it's possible to freeze a cgroup with a ptraced process.
+ */
+static int test_cgfreezer_ptraced(const char *root)
+{
+	int pid, ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	siginfo_t siginfo;
+
+	cgroup = cg_name(root, "cg_test_ptraced");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup, child_fn, NULL);
+
+	if (cg_wait_for_proc_count(cgroup, 1))
+		goto cleanup;
+
+	if (ptrace(PTRACE_SEIZE, pid, NULL, NULL))
+		goto cleanup;
+
+	if (ptrace(PTRACE_INTERRUPT, pid, NULL, NULL))
+		goto cleanup;
+
+	waitpid(pid, NULL, 0);
+
+	if (cg_check_frozen(cgroup, false))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	/*
+	 * cg_check_frozen(cgroup, true) will fail here,
+	 * because the task is in the TRACEd state.
+	 */
+	if (cg_freeze_wait(cgroup, false))
+		goto cleanup;
+
+	if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo))
+		goto cleanup;
+
+	if (ptrace(PTRACE_DETACH, pid, NULL, NULL))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+static int vfork_fn(const char *cgroup, void *arg)
+{
+	int pid = vfork();
+
+	if (pid == 0)
+		while (true)
+			sleep(1);
+
+	return pid;
+}
+
+/*
+ * Test that it's possible to freeze a cgroup with a process,
+ * which called vfork() and is waiting for a child.
+ */
+static int test_cgfreezer_vfork(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+
+	cgroup = cg_name(root, "cg_test_vfork");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	cg_run_nowait(cgroup, vfork_fn, NULL);
+
+	if (cg_wait_for_proc_count(cgroup, 2))
+		goto cleanup;
+
+	if (cg_freeze_wait(cgroup, true))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Get the current frozen_usec for the cgroup.
+ */
+static long cg_check_freezetime(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "cgroup.stat.local",
+				"frozen_usec ");
+}
+
+/*
+ * Test that the freeze time will behave as expected for an empty cgroup.
+ */
+static int test_cgfreezer_time_empty(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+
+	cgroup = cg_name(root, "cg_time_test_empty");
+	if (!cgroup)
+		goto cleanup;
+
+	/*
+	 * 1) Create an empty cgroup and check that its freeze time
+	 *    is 0.
+	 */
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+
+	/*
+	 * 2) Sleep for 1000 us. Check that the freeze time is at
+	 *    least 1000 us.
+	 */
+	usleep(1000);
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 1000) {
+		debug("Expect time (%ld) to be at least 1000 us\n",
+		      curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 3) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 2).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Check the freeze time again to ensure that it has not
+	 *    changed.
+	 */
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * A simple test for cgroup freezer time accounting. This test follows
+ * the same flow as test_cgfreezer_time_empty, but with a single process
+ * in the cgroup.
+ */
+static int test_cgfreezer_time_simple(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+
+	cgroup = cg_name(root, "cg_time_test_simple");
+	if (!cgroup)
+		goto cleanup;
+
+	/*
+	 * 1) Create a cgroup and check that its freeze time is 0.
+	 */
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 2) Populate the cgroup with one child and check that the
+	 *    freeze time is still 0.
+	 */
+	cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr > prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+
+	/*
+	 * 3) Sleep for 1000 us. Check that the freeze time is at
+	 *    least 1000 us.
+	 */
+	usleep(1000);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 1000) {
+		debug("Expect time (%ld) to be at least 1000 us\n",
+		      curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 3).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 5) Sleep for 1000 us. Check that the freeze time is the
+	 *    same as at 4).
+	 */
+	usleep(1000);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Test that freezer time accounting works as expected, even while we're
+ * populating a cgroup with processes.
+ */
+static int test_cgfreezer_time_populate(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+	int i;
+
+	cgroup = cg_name(root, "cg_time_test_populate");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 1) Populate the cgroup with 100 processes. Check that
+	 *    the freeze time is 0.
+	 */
+	for (i = 0; i < 100; i++)
+		cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 2) Wait for the group to become fully populated. Check
+	 *    that the freeze time is 0.
+	 */
+	if (cg_wait_for_proc_count(cgroup, 100))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 3) Freeze the cgroup and then populate it with 100 more
+	 *    processes. Check that the freeze time continues to grow.
+	 */
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	for (i = 0; i < 100; i++)
+		cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Wait for the group to become fully populated. Check
+	 *    that the freeze time is larger than at 3).
+	 */
+	if (cg_wait_for_proc_count(cgroup, 200))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 5) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 4).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 6) Kill the processes. Check that the freeze time is the
+	 *    same as it was at 5).
+	 */
+	if (cg_killall(cgroup))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 7) Freeze and unfreeze the cgroup. Check that the freeze
+	 *    time is larger than it was at 6).
+	 */
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Test that frozen time for a cgroup continues to work as expected,
+ * even as processes are migrated. Frozen cgroup A's freeze time should
+ * continue to increase and running cgroup B's should stay 0.
+ */
+static int test_cgfreezer_time_migrate(const char *root)
+{
+	long prev_A, curr_A, curr_B;
+	char *cgroup[2] = {0};
+	int ret = KSFT_FAIL;
+	int pid;
+
+	cgroup[0] = cg_name(root, "cg_time_test_migrate_A");
+	if (!cgroup[0])
+		goto cleanup;
+
+	cgroup[1] = cg_name(root, "cg_time_test_migrate_B");
+	if (!cgroup[1])
+		goto cleanup;
+
+	if (cg_create(cgroup[0]))
+		goto cleanup;
+
+	if (cg_check_freezetime(cgroup[0]) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(cgroup[1]))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup[0], child_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup[0], 1))
+		goto cleanup;
+
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A) {
+		debug("Expect time (%ld) to be 0\n", curr_A);
+		goto cleanup;
+	}
+	curr_B = cg_check_freezetime(cgroup[1]);
+	if (curr_B) {
+		debug("Expect time (%ld) to be 0\n", curr_B);
+		goto cleanup;
+	}
+
+	/*
+	 * Freeze cgroup A.
+	 */
+	if (cg_freeze_wait(cgroup[0], true))
+		goto cleanup;
+	prev_A = curr_A;
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A <= prev_A) {
+		debug("Expect time (%ld) to be > 0\n", curr_A);
+		goto cleanup;
+	}
+
+	/*
+	 * Migrate from A (frozen) to B (running).
+	 */
+	if (cg_enter(cgroup[1], pid))
+		goto cleanup;
+
+	usleep(1000);
+	curr_B = cg_check_freezetime(cgroup[1]);
+	if (curr_B) {
+		debug("Expect time (%ld) to be 0\n", curr_B);
+		goto cleanup;
+	}
+
+	prev_A = curr_A;
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A <= prev_A) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr_A, prev_A);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup[0])
+		cg_destroy(cgroup[0]);
+	free(cgroup[0]);
+	if (cgroup[1])
+		cg_destroy(cgroup[1]);
+	free(cgroup[1]);
+	return ret;
+}
+
+/*
+ * The test creates a cgroup and freezes it. Then it creates a child cgroup.
+ * After that it checks that the child cgroup has a non-zero freeze time
+ * that is less than the parent's. Next, it freezes the child, unfreezes
+ * the parent, and sleeps. Finally, it checks that the child's freeze
+ * time has grown larger than the parent's.
+ */
+static int test_cgfreezer_time_parent(const char *root)
+{
+	char *parent, *child = NULL;
+	int ret = KSFT_FAIL;
+	long ptime, ctime;
+
+	parent = cg_name(root, "cg_test_parent_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_parent_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_check_freezetime(parent) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_freeze_wait(parent, true))
+		goto cleanup;
+
+	usleep(1000);
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	/*
+	 * Since the parent was frozen the entire time the child cgroup
+	 * was being created, we expect the parent's freeze time to be
+	 * larger than the child's.
+	 *
+	 * Ideally, we would be able to check both times simultaneously,
+	 * but here we get the child's after we get the parent's.
+	 */
+	ptime = cg_check_freezetime(parent);
+	ctime = cg_check_freezetime(child);
+	if (ptime <= ctime) {
+		debug("Expect ptime (%ld) > ctime (%ld)\n", ptime, ctime);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(child, true))
+		goto cleanup;
+
+	if (cg_freeze_wait(parent, false))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	usleep(100000);
+
+	ctime = cg_check_freezetime(child);
+	ptime = cg_check_freezetime(parent);
+
+	if (ctime <= ptime) {
+		debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates a parent cgroup and a child cgroup. Then, it freezes
+ * the child and checks that the child's freeze time is greater than the
+ * parent's, which should be zero.
+ */
+static int test_cgfreezer_time_child(const char *root)
+{
+	char *parent, *child = NULL;
+	int ret = KSFT_FAIL;
+	long ptime, ctime;
+
+	parent = cg_name(root, "cg_test_child_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_child_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_check_freezetime(parent) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_freeze_wait(child, true))
+		goto cleanup;
+
+	ctime = cg_check_freezetime(child);
+	ptime = cg_check_freezetime(parent);
+	if (ptime != 0) {
+		debug("Expect ptime (%ld) to be 0\n", ptime);
+		goto cleanup;
+	}
+
+	if (ctime <= ptime) {
+		debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates the following hierarchy:
+ *    A
+ *    |
+ *    B
+ *    |
+ *    C
+ *
+ * Then it freezes the cgroups in the order C, B, A.
+ * Then it unfreezes the cgroups in the order A, B, C.
+ * Then it checks that C's freeze time is larger than B's and
+ * that B's is larger than A's.
+ */
+static int test_cgfreezer_time_nested(const char *root)
+{
+	char *cgroup[3] = {0};
+	int ret = KSFT_FAIL;
+	long time[3] = {0};
+	int i;
+
+	cgroup[0] = cg_name(root, "cg_test_time_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;
+
+	if (cg_create(cgroup[0]))
+		goto cleanup;
+
+	if (cg_check_freezetime(cgroup[0]) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(cgroup[1]))
+		goto cleanup;
+
+	if (cg_create(cgroup[2]))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[2], true))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[1], true))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[0], true))
+		goto cleanup;
+
+	usleep(1000);
+
+	if (cg_freeze_nowait(cgroup[0], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[1], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[2], false))
+		goto cleanup;
+
+	time[2] = cg_check_freezetime(cgroup[2]);
+	time[1] = cg_check_freezetime(cgroup[1]);
+	time[0] = cg_check_freezetime(cgroup[0]);
+
+	if (time[2] <= time[1]) {
+		debug("Expect C's time (%ld) > B's time (%ld)", time[2], time[1]);
+		goto cleanup;
+	}
+
+	if (time[1] <= time[0]) {
+		debug("Expect B's time (%ld) > A's time (%ld)", time[1], time[0]);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = 2; i >= 0 && cgroup[i]; i--) {
+		cg_destroy(cgroup[i]);
+		free(cgroup[i]);
+	}
+
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct cgfreezer_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cgfreezer_simple),
+	T(test_cgfreezer_tree),
+	T(test_cgfreezer_forkbomb),
+	T(test_cgfreezer_mkdir),
+	T(test_cgfreezer_rmdir),
+	T(test_cgfreezer_migrate),
+	T(test_cgfreezer_ptrace),
+	T(test_cgfreezer_stopped),
+	T(test_cgfreezer_ptraced),
+	T(test_cgfreezer_vfork),
+	T(test_cgfreezer_time_empty),
+	T(test_cgfreezer_time_simple),
+	T(test_cgfreezer_time_populate),
+	T(test_cgfreezer_time_migrate),
+	T(test_cgfreezer_time_parent),
+	T(test_cgfreezer_time_child),
+	T(test_cgfreezer_time_nested),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
new file mode 100644
index 000000000..8c5aced81
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -0,0 +1,244 @@
+// 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 has_memory_hugetlb_acc;
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	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");
+		ksft_finished();
+	}
+
+	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:
+		ksft_test_result_fail("test_hugetlb_memcg\n");
+		break;
+	}
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
new file mode 100644
index 000000000..bac1ddd8c
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -0,0 +1,354 @@
+/* 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 <sys/wait.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;
+}
+
+/*
+ * Test that a cgroup that was killed in the past can still be the target
+ * of clone3(CLONE_INTO_CGROUP): writing cgroup.kill must only kill the
+ * tasks in the cgroup at the time of the write, not tasks cloned into
+ * it afterwards.
+ */
+static int test_cgkill_clone_into_killed(const char *root)
+{
+	pid_t pid;
+	int cgroup_fd = -EBADF;
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+
+	cgroup = cg_name(root, "cg_test_clone_into_killed");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	/* Kill the cgroup while it is still empty. */
+	if (cg_write(cgroup, "cgroup.kill", "1"))
+		goto cleanup;
+
+	cgroup_fd = dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		goto cleanup;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0) {
+		if (errno == ENOSYS)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	/* The child must not be SIGKILLed; it has to exit cleanly. */
+	if (clone_reap(pid, WEXITED) != EXIT_SUCCESS)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	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),
+	T(test_cgkill_clone_into_killed),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
new file mode 100644
index 000000000..437f2d35f
--- /dev/null
+++ b/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, arg)) {
+			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();
+	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");
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
new file mode 100644
index 000000000..3a84d068f
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -0,0 +1,1841 @@
+/* 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/inotify.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <netdb.h>
+#include <errno.h>
+#include <sys/mman.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+#define MEMCG_SOCKSTAT_WAIT_RETRIES        30
+
+static bool has_localevents;
+static bool has_recursiveprot;
+static int page_size;
+
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[BUF_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;
+}
+
+static char *alloc_and_populate_anon(size_t size)
+{
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	if (buf == NULL) {
+		fprintf(stderr, "malloc() failed\n");
+		return NULL;
+	}
+
+	for (ptr = buf; ptr < buf + size; ptr += page_size)
+		*ptr = 0;
+
+	return buf;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf;
+
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
+		return -1;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[BUF_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;
+}
+
+/*
+ * 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[BUF_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;
+	long anon, current;
+	int ret = -1;
+
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
+		return -1;
+
+	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 checks memory.current, memory.peak, and some memory.stat values.
+ */
+static int test_memcg_current_peak(const char *root)
+{
+	int ret = KSFT_FAIL;
+	long current, peak, peak_reset;
+	char *memcg;
+	bool fd2_closed = false, fd3_closed = false, fd4_closed = false;
+	int peak_fd = -1, peak_fd2 = -1, peak_fd3 = -1, peak_fd4 = -1;
+	struct stat ss;
+
+	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;
+
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak != 0)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_anon_50M_check, NULL))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/*
+	 * We'll open a few FDs for the same memory.peak file to exercise the free-path
+	 * We need at least three to be closed in a different order than writes occurred to test
+	 * the linked-list handling.
+	 */
+	peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.peak's fd, try to figure out whether
+	 * this kernel supports writing to that file in the first place. (by
+	 * checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	peak_fd2 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd2 == -1)
+		goto cleanup;
+
+	peak_fd3 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd3 == -1)
+		goto cleanup;
+
+	/* any non-empty string resets, but make it clear */
+	static const char reset_string[] = "reset\n";
+
+	peak_reset = write(peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd2, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd3, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	/* Make sure a completely independent read isn't affected by our  FD-local reset above*/
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd2_closed = true;
+	if (close(peak_fd2))
+		goto cleanup;
+
+	peak_fd4 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd4 == -1)
+		goto cleanup;
+
+	peak_reset = write(peak_fd4, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd);
+	if (peak > MB(30) || peak < 0)
+		goto cleanup;
+
+	if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/* Make sure everything is back to normal */
+	peak = cg_read_long_fd(peak_fd);
+	if (peak < MB(50))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd4);
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd3_closed = true;
+	if (close(peak_fd3))
+		goto cleanup;
+
+	fd4_closed = true;
+	if (close(peak_fd4))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	close(peak_fd);
+	if (!fd2_closed)
+		close(peak_fd2);
+	if (!fd3_closed)
+		close(peak_fd3);
+	if (!fd4_closed)
+		close(peak_fd4);
+	cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+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();
+	size_t size = (unsigned long)arg;
+	char *buf;
+
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
+		return -1;
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	free(buf);
+	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;
+}
+
+static bool reclaim_until(const char *memcg, long goal);
+
+/*
+ * First, this test creates the following hierarchy:
+ * A       memory.min = 0,    memory.max = 200M
+ * A/B     memory.min = 50M
+ * A/B/C   memory.min = 75M,  memory.current = 50M
+ * A/B/D   memory.min = 25M,  memory.current = 50M
+ * A/B/E   memory.min = 0,    memory.current = 50M
+ * A/B/F   memory.min = 500M, memory.current = 0
+ *
+ * (or memory.low if we test soft protection)
+ *
+ * Usages are pagecache and the test keeps a running
+ * process in every leaf cgroup.
+ * Then it creates A/G and creates a significant
+ * memory pressure in A.
+ *
+ * Then it checks actual memory usages and expects that:
+ * A/B    memory.current ~= 50M
+ * A/B/C  memory.current ~= 29M [memory.events:low > 0]
+ * A/B/D  memory.current ~= 21M [memory.events:low > 0]
+ * A/B/E  memory.current ~= 0   [memory.events:low == 0 if !memory_recursiveprot,
+ *				 undefined otherwise]
+ * A/B/F  memory.current  = 0   [memory.events:low == 0]
+ * (for origin of the numbers, see model in memcg_protection.m.)
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available, and checks that:
+ * a) memory.min protects pagecache even in this case,
+ * b) memory.low allows reclaiming page cache with low events.
+ *
+ * Then we try to reclaim from A/B/C using memory.reclaim until its
+ * usage reaches 10M.
+ * This makes sure that:
+ * (a) We ignore the protection of the reclaim target memcg.
+ * (b) The previously calculated emin value (~29M) should be dismissed.
+ */
+static int test_memcg_protection(const char *root, bool min)
+{
+	int ret = KSFT_FAIL, rc;
+	char *parent[3] = {NULL};
+	char *children[4] = {NULL};
+	const char *attribute = min ? "memory.min" : "memory.low";
+	long c[4];
+	long current;
+	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], attribute)) {
+		/* No memory.min on older kernels is fine */
+		if (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[1],   attribute, "50M"))
+		goto cleanup;
+	if (cg_write(children[0], attribute, "75M"))
+		goto cleanup;
+	if (cg_write(children[1], attribute, "25M"))
+		goto cleanup;
+	if (cg_write(children[2], attribute, "0"))
+		goto cleanup;
+	if (cg_write(children[3], attribute, "500M"))
+		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(29), 15))
+		goto cleanup;
+
+	if (!values_close(c[1], MB(21), 20))
+		goto cleanup;
+
+	if (c[3] != 0)
+		goto cleanup;
+
+	rc = cg_run(parent[2], alloc_anon, (void *)MB(170));
+	if (min && !rc)
+		goto cleanup;
+	else if (!min && rc) {
+		fprintf(stderr,
+			"memory.low prevents from allocating anon memory\n");
+		goto cleanup;
+	}
+
+	current = min ? MB(50) : MB(30);
+	if (!values_close(cg_read_long(parent[1], "memory.current"), current, 3))
+		goto cleanup;
+
+	if (!reclaim_until(children[0], MB(10)))
+		goto cleanup;
+
+	if (min) {
+		ret = KSFT_PASS;
+		goto cleanup;
+	}
+
+	/*
+	 * Child 2 has memory.low=0, but some low protection may still be
+	 * distributed down from its parent with memory.low=50M if cgroup2
+	 * memory_recursiveprot mount option is enabled. Ignore the low
+	 * event count in this case.
+	 */
+	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		int ignore_low_events_index = has_recursiveprot ? 2 : -1;
+		int no_low_events_index = 1;
+		long low, oom;
+
+		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 == ignore_low_events_index)
+			continue;
+		if (i <= no_low_events_index && low <= 0)
+			goto cleanup;
+		if (i > no_low_events_index && 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 test_memcg_min(const char *root)
+{
+	return test_memcg_protection(root, true);
+}
+
+static int test_memcg_low(const char *root)
+{
+	return test_memcg_protection(root, false);
+}
+
+static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
+{
+	size_t size = MB(50);
+	int ret = -1;
+	long current, high, max;
+	int fd;
+
+	high = cg_read_long(cgroup, "memory.high");
+	max = cg_read_long(cgroup, "memory.max");
+	if (high != MB(30) && max != MB(30))
+		return -1;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		return -1;
+
+	if (alloc_pagecache(fd, size))
+		goto cleanup;
+
+	current = cg_read_long(cgroup, "memory.current");
+	if (!values_close(current, MB(30), 5))
+		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(31)))
+		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;
+}
+
+static int alloc_anon_mlock(const char *cgroup, void *arg)
+{
+	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;
+
+	mlock(buf, size);
+	munmap(buf, size);
+	return 0;
+}
+
+/*
+ * This test checks that memory.high is able to throttle big single shot
+ * allocation i.e. large allocation within one kernel entry.
+ */
+static int test_memcg_high_sync(const char *root)
+{
+	int ret = KSFT_FAIL, pid, fd = -1;
+	char *memcg;
+	long pre_high, pre_max;
+	long post_high, post_max;
+
+	memcg = cg_name(root, "memcg_test");
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	pre_high = cg_read_key_long(memcg, "memory.events", "high ");
+	pre_max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (pre_high < 0 || pre_max < 0)
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.swap.max", "0"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.high", "30M"))
+		goto cleanup;
+
+	if (cg_write(memcg, "memory.max", "140M"))
+		goto cleanup;
+
+	fd = memcg_prepare_for_wait(memcg);
+	if (fd < 0)
+		goto cleanup;
+
+	pid = cg_run_nowait(memcg, alloc_anon_mlock, (void *)MB(200));
+	if (pid < 0)
+		goto cleanup;
+
+	cg_wait_for(fd);
+
+	post_high = cg_read_key_long(memcg, "memory.events", "high ");
+	post_max = cg_read_key_long(memcg, "memory.events", "max ");
+	if (post_high < 0 || post_max < 0)
+		goto cleanup;
+
+	if (pre_high == post_high || pre_max != post_max)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (fd >= 0)
+		close(fd);
+	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;
+}
+
+/*
+ * Reclaim from @memcg until usage reaches @goal by writing to
+ * memory.reclaim.
+ *
+ * This function will return false if the usage is already below the
+ * goal.
+ *
+ * This function assumes that writing to memory.reclaim is the only
+ * source of change in memory.current (no concurrent allocations or
+ * reclaim).
+ *
+ * This function makes sure memory.reclaim is sane. It will return
+ * false if memory.reclaim's error codes do not make sense, even if
+ * the usage goal was satisfied.
+ */
+static bool reclaim_until(const char *memcg, long goal)
+{
+	char buf[64];
+	int retries, err;
+	long current, to_reclaim;
+	bool reclaimed = false;
+
+	for (retries = 5; retries > 0; retries--) {
+		current = cg_read_long(memcg, "memory.current");
+
+		if (current < goal || values_close(current, goal, 3))
+			break;
+		/* Did memory.reclaim return 0 incorrectly? */
+		else if (reclaimed)
+			return false;
+
+		to_reclaim = current - goal;
+		snprintf(buf, sizeof(buf), "%ld", to_reclaim);
+		err = cg_write(memcg, "memory.reclaim", buf);
+		if (!err)
+			reclaimed = true;
+		else if (err != -EAGAIN)
+			return false;
+	}
+	return reclaimed;
+}
+
+/*
+ * This test checks that memory.reclaim reclaims the given
+ * amount of memory (from both anon and file, if possible).
+ */
+static int test_memcg_reclaim(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int fd = -1;
+	int retries;
+	char *memcg;
+	long current, expected_usage;
+
+	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;
+
+	fd = get_temp_fd();
+	if (fd < 0)
+		goto cleanup;
+
+	cg_run_nowait(memcg, alloc_pagecache_50M_noexit, (void *)(long)fd);
+
+	/*
+	 * If swap is enabled, try to reclaim from both anon and file, else try
+	 * to reclaim from file only.
+	 */
+	if (is_swap_enabled()) {
+		cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(50));
+		expected_usage = MB(100);
+	} else
+		expected_usage = MB(50);
+
+	/*
+	 * Wait until current usage reaches the expected usage (or we run out of
+	 * retries).
+	 */
+	retries = 5;
+	while (!values_close(cg_read_long(memcg, "memory.current"),
+			    expected_usage, 10)) {
+		if (retries--) {
+			sleep(1);
+			continue;
+		} else {
+			fprintf(stderr,
+				"failed to allocate %ld for memcg reclaim test\n",
+				expected_usage);
+			goto cleanup;
+		}
+	}
+
+	/*
+	 * Reclaim until current reaches 30M, this makes sure we hit both anon
+	 * and file if swap is enabled.
+	 */
+	if (!reclaim_until(memcg, MB(30)))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+cleanup:
+	cg_destroy(memcg);
+	free(memcg);
+	close(fd);
+
+	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;
+	long mem_current, swap_current;
+	int ret = -1;
+
+	buf = alloc_and_populate_anon(size);
+	if (!buf)
+		return -1;
+
+	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. Additionally, it verifies that
+ * memory.swap.peak reflects the high watermark and can be reset.
+ */
+static int test_memcg_swap_max_peak(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg;
+	long max, peak;
+	struct stat ss;
+	int swap_peak_fd = -1, mem_peak_fd = -1;
+
+	/* any non-empty string resets */
+	static const char reset_string[] = "foobarbaz";
+
+	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;
+	}
+
+	swap_peak_fd = cg_open(memcg, "memory.swap.peak",
+			       O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (swap_peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.swap.peak's fd, try to figure out
+	 * whether this kernel supports writing to that file in the first
+	 * place. (by checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(swap_peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	mem_peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (mem_peak_fd == -1)
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	/* switch the swap and mem fds into local-peak tracking mode*/
+	int peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		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;
+
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	/*
+	 * open, reset and close the peak swap on another FD to make sure
+	 * multiple extant fds don't corrupt the linked-list
+	 */
+	peak_reset = cg_write(memcg, "memory.swap.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	peak_reset = cg_write(memcg, "memory.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	/* actually reset on the fds */
+	peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak > MB(10))
+		goto cleanup;
+
+	/*
+	 * The cgroup is now empty, but there may be a page or two associated
+	 * with the open FD accounted to it.
+	 */
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak > MB(1))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak") < MB(29))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak") < MB(29))
+		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;
+
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(19))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (mem_peak_fd != -1 && close(mem_peak_fd))
+		ret = KSFT_FAIL;
+	if (swap_peak_fd != -1 && close(swap_peak_fd))
+		ret = KSFT_FAIL;
+	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) {
+		/* Pass back errno to the ctl_fd */
+		write(ctl_fd, &errno, sizeof(errno));
+		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;
+	long allocated;
+
+	allocated = cg_read_long(cgroup, "memory.current");
+	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;
+
+		/* exclude the memory not related to socket connection */
+		if (values_close(current - allocated, 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;
+	long sock_post = -1;
+
+	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]);
+
+		/* Skip if address family not supported by protocol */
+		if (err == EAFNOSUPPORT) {
+			ret = KSFT_SKIP;
+			goto cleanup;
+		}
+
+		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;
+
+	/*
+	 * memory.stat is updated asynchronously via the memcg rstat
+	 * flushing worker, which runs periodically (every 2 seconds,
+	 * see FLUSH_TIME). On a busy system, the "sock " counter may
+	 * stay non-zero for a short period of time after the TCP
+	 * connection is closed and all socket memory has been
+	 * uncharged.
+	 *
+	 * Poll memory.stat for up to 3 seconds (~FLUSH_TIME plus some
+	 * scheduling slack) and require that the "sock " counter
+	 * eventually drops to zero.
+	 */
+	sock_post = cg_read_key_long_poll(memcg, "memory.stat", "sock ", 0,
+					 MEMCG_SOCKSTAT_WAIT_RETRIES,
+					 DEFAULT_WAIT_INTERVAL_US);
+	if (sock_post)
+		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 were killed. It also checks that oom_events
+ * were propagated to the parent level.
+ */
+static int test_memcg_oom_group_leaf_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *parent, *child;
+	long parent_oom_events;
+
+	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;
+
+	parent_oom_events = cg_read_key_long(
+			parent, "memory.events", "oom_kill ");
+	/*
+	 * If memory_localevents is not enabled (the default), the parent should
+	 * count OOM events in its children groups. Otherwise, it should not
+	 * have observed any events.
+	 */
+	if (has_localevents && parent_oom_events != 0)
+		goto cleanup;
+	else if (!has_localevents && parent_oom_events <= 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;
+}
+
+static int read_event(int inotify_fd, int expected_event, int expected_wd)
+{
+	struct inotify_event event;
+	ssize_t len = 0;
+
+	len = read(inotify_fd, &event, sizeof(event));
+	if (len < (ssize_t)sizeof(event))
+		return -1;
+
+	if (event.mask != expected_event || event.wd != expected_wd) {
+		fprintf(stderr,
+			"event does not match expected values: mask %d (expected %d) wd %d (expected %d)\n",
+			event.mask, expected_event, event.wd, expected_wd);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int test_memcg_inotify_delete_file(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg = NULL;
+	int fd, wd;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	fd = inotify_init1(0);
+	if (fd == -1)
+		goto cleanup;
+
+	wd = inotify_add_watch(fd, cg_control(memcg, "memory.events"), IN_DELETE_SELF);
+	if (wd == -1)
+		goto cleanup;
+
+	if (cg_destroy(memcg))
+		goto cleanup;
+	free(memcg);
+	memcg = NULL;
+
+	if (read_event(fd, IN_DELETE_SELF, wd))
+		goto cleanup;
+
+	if (read_event(fd, IN_IGNORED, wd))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (fd >= 0)
+		close(fd);
+	if (memcg)
+		cg_destroy(memcg);
+	free(memcg);
+
+	return ret;
+}
+
+static int test_memcg_inotify_delete_dir(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *memcg = NULL;
+	int fd, wd;
+
+	memcg = cg_name(root, "memcg_test_0");
+
+	if (!memcg)
+		goto cleanup;
+
+	if (cg_create(memcg))
+		goto cleanup;
+
+	fd = inotify_init1(0);
+	if (fd == -1)
+		goto cleanup;
+
+	wd = inotify_add_watch(fd, memcg, IN_DELETE_SELF);
+	if (wd == -1)
+		goto cleanup;
+
+	if (cg_destroy(memcg))
+		goto cleanup;
+	free(memcg);
+	memcg = NULL;
+
+	if (read_event(fd, IN_DELETE_SELF, wd))
+		goto cleanup;
+
+	if (read_event(fd, IN_IGNORED, wd))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (fd >= 0)
+		close(fd);
+	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_peak),
+	T(test_memcg_min),
+	T(test_memcg_low),
+	T(test_memcg_high),
+	T(test_memcg_high_sync),
+	T(test_memcg_max),
+	T(test_memcg_reclaim),
+	T(test_memcg_oom_events),
+	T(test_memcg_swap_max_peak),
+	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),
+	T(test_memcg_inotify_delete_file),
+	T(test_memcg_inotify_delete_dir),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i, proc_status;
+
+	page_size = sysconf(_SC_PAGE_SIZE);
+	if (page_size <= 0)
+		page_size = BUF_SIZE;
+
+	ksft_print_header();
+	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");
+
+	proc_status = proc_mount_contains("memory_recursiveprot");
+	if (proc_status < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	has_recursiveprot = proc_status;
+
+	proc_status = proc_mount_contains("memory_localevents");
+	if (proc_status < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	has_localevents = proc_status;
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c
new file mode 100644
index 000000000..710109b53
--- /dev/null
+++ b/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();
+	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");
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/test_stress.sh b/tools/testing/selftests/cgroup/test_stress.sh
new file mode 100755
index 000000000..3c9c4554d
--- /dev/null
+++ b/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
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
new file mode 100644
index 000000000..609c48f38
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -0,0 +1,854 @@
+// 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"
+#define PATH_ZSWAP_STORED_PAGES "/sys/kernel/debug/zswap/stored_pages"
+
+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(PATH_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 > GB(4)) {
+		ksft_print_msg(
+			"requires less than 4GB total ram, sys_info.totalram: %.1fGB\n",
+			(double)sys_info.totalram / GB(1));
+		return KSFT_SKIP;
+	}
+	if (access(PATH_ZSWAP_STORED_PAGES, R_OK)) {
+		ksft_print_msg("debugfs not mounted at /sys/kernel/debug\n");
+		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();
+	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");
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+	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();
+}
diff --git a/tools/testing/selftests/cgroup/wait_inotify.c b/tools/testing/selftests/cgroup/wait_inotify.c
new file mode 100644
index 000000000..e11b431e1
--- /dev/null
+++ b/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;
+}
diff --git a/tools/testing/selftests/cgroup/with_stress.sh b/tools/testing/selftests/cgroup/with_stress.sh
new file mode 100755
index 000000000..e28c35008
--- /dev/null
+++ b/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