Merge tag 'cgroup-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Per-cpu cpu usage stats are now tracked

   This currently isn't printed out in the cgroupfs interface and can
   only be accessed through e.g. BPF. Should decide on a not-too-ugly
   way to show per-cpu stats in cgroupfs

 - cpuset received some cleanups and prepatory patches for the pending
   cpus.exclusive patchset which will allow cpuset partitions to be
   created below non-partition parents, which should ease the management
   of partition cpusets

 - A lot of code and documentation cleanup patches

 - tools/testing/selftests/cgroup/test_cpuset.c added

* tag 'cgroup-for-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (32 commits)
  cgroup: Avoid -Wstringop-overflow warnings
  cgroup:namespace: Remove unused cgroup_namespaces_init()
  cgroup/rstat: Record the cumulative per-cpu time of cgroup and its descendants
  cgroup: clean up if condition in cgroup_pidlist_start()
  cgroup: fix obsolete function name in cgroup_destroy_locked()
  Documentation: cgroup-v2.rst: Correct number of stats entries
  cgroup: fix obsolete function name above css_free_rwork_fn()
  cgroup/cpuset: fix kernel-doc
  cgroup: clean up printk()
  cgroup: fix obsolete comment above cgroup_create()
  docs: cgroup-v1: fix typo
  docs: cgroup-v1: correct the term of Page Cache organization in inode
  cgroup/misc: Store atomic64_t reads to u64
  cgroup/misc: Change counters to be explicit 64bit types
  cgroup/misc: update struct members descriptions
  cgroup: remove cgrp->kn check in css_populate_dir()
  cgroup: fix obsolete function name
  cgroup: use cached local variable parent in for loop
  cgroup: remove obsolete comment above struct cgroupstats
  cgroup: put cgroup_tryget_css() inside CONFIG_CGROUP_SCHED
  ...

7 files changed, 284 insertions, 2 deletions

diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index 4d556df4f77b..af8c3f30b9c1 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -5,5 +5,6 @@ test_freezer
 test_kmem
 test_kill
 test_cpu
+test_cpuset
 test_zswap
 wait_inotify
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 27dbdd7bb4bb..c27f05f6ce9b 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -12,6 +12,7 @@ TEST_GEN_PROGS += test_core
 TEST_GEN_PROGS += test_freezer
 TEST_GEN_PROGS += test_kill
 TEST_GEN_PROGS += test_cpu
+TEST_GEN_PROGS += test_cpuset
 TEST_GEN_PROGS += test_zswap
 
 LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
@@ -24,4 +25,5 @@ $(OUTPUT)/test_core: cgroup_util.c
 $(OUTPUT)/test_freezer: cgroup_util.c
 $(OUTPUT)/test_kill: cgroup_util.c
 $(OUTPUT)/test_cpu: cgroup_util.c
+$(OUTPUT)/test_cpuset: cgroup_util.c
 $(OUTPUT)/test_zswap: cgroup_util.c
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index e8bbbdb77e0d..0340d4ca8f51 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -286,6 +286,8 @@ int cg_destroy(const char *cgroup)
 {
 	int ret;
 
+	if (!cgroup)
+		return 0;
 retry:
 	ret = rmdir(cgroup);
 	if (ret && errno == EBUSY) {
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index c92df4e5d395..1df7f202214a 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -11,6 +11,8 @@
 #define USEC_PER_SEC	1000000L
 #define NSEC_PER_SEC	1000000000L
 
+#define TEST_UID	65534 /* usually nobody, any !root is fine */
+
 /*
  * Checks if two given values differ by less than err% of their sum.
  */
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 600123503063..80aa6b2373b9 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -683,7 +683,7 @@ cleanup:
  */
 static int test_cgcore_lesser_euid_open(const char *root)
 {
-	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	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;
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
new file mode 100644
index 000000000000..b061ed1e05b4
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/limits.h>
+#include <signal.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+static int idle_process_fn(const char *cgroup, void *arg)
+{
+	(void)pause();
+	return 0;
+}
+
+static int do_migration_fn(const char *cgroup, void *arg)
+{
+	int object_pid = (int)(size_t)arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	// XXX checking /proc/$pid/cgroup would be quicker than wait
+	if (cg_enter(cgroup, object_pid) ||
+	    cg_wait_for_proc_count(cgroup, 1))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+static int do_controller_fn(const char *cgroup, void *arg)
+{
+	const char *child = cgroup;
+	const char *parent = arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "-cpuset"))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+/*
+ * Migrate a process between two sibling cgroups.
+ * The success should only depend on the parent cgroup permissions and not the
+ * migrated process itself (cpuset controller is in place because it uses
+ * security_task_setscheduler() in cgroup v1).
+ *
+ * Deliberately don't set cpuset.cpus in children to avoid definining migration
+ * permissions between two different cpusets.
+ */
+static int test_cpuset_perms_object(const char *root, bool allow)
+{
+	char *parent = NULL, *child_src = NULL, *child_dst = NULL;
+	char *parent_procs = NULL, *child_src_procs = NULL, *child_dst_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child_src = cg_name(parent, "cpuset_test_1");
+	if (!child_src)
+		goto cleanup;
+	child_src_procs = cg_name(child_src, "cgroup.procs");
+	if (!child_src_procs)
+		goto cleanup;
+	if (cg_create(child_src))
+		goto cleanup;
+
+	child_dst = cg_name(parent, "cpuset_test_2");
+	if (!child_dst)
+		goto cleanup;
+	child_dst_procs = cg_name(child_dst, "cgroup.procs");
+	if (!child_dst_procs)
+		goto cleanup;
+	if (cg_create(child_dst))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		goto cleanup;
+
+	if (cg_read_strstr(child_src, "cgroup.controllers", "cpuset") ||
+	    cg_read_strstr(child_dst, "cgroup.controllers", "cpuset"))
+		goto cleanup;
+
+	/* Enable permissions along src->dst tree path */
+	if (chown(child_src_procs, test_euid, -1) ||
+	    chown(child_dst_procs, test_euid, -1))
+		goto cleanup;
+
+	if (allow && chown(parent_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Fork a privileged child as a test object */
+	object_pid = cg_run_nowait(child_src, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	/* Carry out migration in a child process that can drop all privileges
+	 * (including capabilities), the main process must remain privileged for
+	 * cleanup.
+	 * Child process's cgroup is irrelevant but we place it into child_dst
+	 * as hacky way to pass information about migration target to the child.
+	 */
+	if (allow ^ (cg_run(child_dst, do_migration_fn, (void *)(size_t)object_pid) == EXIT_SUCCESS))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child_dst);
+	free(child_dst_procs);
+	free(child_dst);
+
+	cg_destroy(child_src);
+	free(child_src_procs);
+	free(child_src);
+
+	cg_destroy(parent);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+static int test_cpuset_perms_object_allow(const char *root)
+{
+	return test_cpuset_perms_object(root, true);
+}
+
+static int test_cpuset_perms_object_deny(const char *root)
+{
+	return test_cpuset_perms_object(root, false);
+}
+
+/*
+ * Migrate a process between parent and child implicitely
+ * Implicit migration happens when a controller is enabled/disabled.
+ *
+ */
+static int test_cpuset_perms_subtree(const char *root)
+{
+	char *parent = NULL, *child = NULL;
+	char *parent_procs = NULL, *parent_subctl = NULL, *child_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	parent_subctl = cg_name(parent, "cgroup.subtree_control");
+	if (!parent_subctl)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child = cg_name(parent, "cpuset_test_1");
+	if (!child)
+		goto cleanup;
+	child_procs = cg_name(child, "cgroup.procs");
+	if (!child_procs)
+		goto cleanup;
+	if (cg_create(child))
+		goto cleanup;
+
+	/* Enable permissions as in a delegated subtree */
+	if (chown(parent_procs, test_euid, -1) ||
+	    chown(parent_subctl, test_euid, -1) ||
+	    chown(child_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Put a privileged child in the subtree and modify controller state
+	 * from an unprivileged process, the main process remains privileged
+	 * for cleanup.
+	 * The unprivileged child runs in subtree too to avoid parent and
+	 * internal-node constraing violation.
+	 */
+	object_pid = cg_run_nowait(child, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	if (cg_run(child, do_controller_fn, parent) != EXIT_SUCCESS)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child);
+	free(child_procs);
+	free(child);
+
+	cg_destroy(parent);
+	free(parent_subctl);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+
+#define T(x) { x, #x }
+struct cpuset_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cpuset_perms_object_allow),
+	T(test_cpuset_perms_object_deny),
+	T(test_cpuset_perms_subtree),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i, ret = EXIT_SUCCESS;
+
+	if (cg_find_unified_root(root, sizeof(root)))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset"))
+		if (cg_write(root, "cgroup.subtree_control", "+cpuset"))
+			ksft_exit_skip("Failed to set cpuset controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ret = EXIT_FAILURE;
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 2b5215cc599f..4afb132e4e4f 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -10,7 +10,7 @@
 skip_test() {
 	echo "$1"
 	echo "Test SKIPPED"
-	exit 0
+	exit 4 # ksft_skip
 }
 
 [[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"