1 files changed, 571 insertions, 8 deletions

diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index be59f9c34ea2..102262555a59 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -1,14 +1,139 @@
 /* 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 "kselftest.h"
 #include "cgroup_util.h"
 
+static bool nsdelegate;
+#ifndef CLONE_NEWCGROUP
+#define CLONE_NEWCGROUP 0
+#endif
+
+static int touch_anon(char *buf, size_t size)
+{
+	int fd;
+	char *pos = buf;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	while (size > 0) {
+		ssize_t ret = read(fd, pos, size);
+
+		if (ret < 0) {
+			if (errno != EINTR) {
+				close(fd);
+				return -1;
+			}
+		} else {
+			pos += ret;
+			size -= ret;
+		}
+	}
+	close(fd);
+
+	return 0;
+}
+
+static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+	size_t size = (size_t)arg;
+	void *buf;
+
+	buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+		   0, 0);
+	if (buf == MAP_FAILED)
+		return -1;
+
+	if (touch_anon((char *)buf, size)) {
+		munmap(buf, size);
+		return -1;
+	}
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	munmap(buf, size);
+	return 0;
+}
+
+/*
+ * Create a child process that allocates and touches 100MB, then waits to be
+ * killed. Wait until the child is attached to the cgroup, kill all processes
+ * in that cgroup and wait until "cgroup.procs" is empty. At this point try to
+ * destroy the empty cgroup. The test helps detect race conditions between
+ * dying processes leaving the cgroup and cgroup destruction path.
+ */
+static int test_cgcore_destroy(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_test = NULL;
+	int child_pid;
+	char buf[PAGE_SIZE];
+
+	cg_test = cg_name(root, "cg_test");
+
+	if (!cg_test)
+		goto cleanup;
+
+	for (int i = 0; i < 10; i++) {
+		if (cg_create(cg_test))
+			goto cleanup;
+
+		child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit,
+					  (void *) MB(100));
+
+		if (child_pid < 0)
+			goto cleanup;
+
+		/* wait for the child to enter cgroup */
+		if (cg_wait_for_proc_count(cg_test, 1))
+			goto cleanup;
+
+		if (cg_killall(cg_test))
+			goto cleanup;
+
+		/* wait for cgroup to be empty */
+		while (1) {
+			if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf)))
+				goto cleanup;
+			if (buf[0] == '\0')
+				break;
+			usleep(1000);
+		}
+
+		if (rmdir(cg_test))
+			goto cleanup;
+
+		if (waitpid(child_pid, NULL, 0) < 0)
+			goto cleanup;
+	}
+	ret = KSFT_PASS;
+cleanup:
+	if (cg_test)
+		cg_destroy(cg_test);
+	free(cg_test);
+	return ret;
+}
+
 /*
  * A(0) - B(0) - C(1)
  *        \ D(0)
@@ -22,8 +147,14 @@
 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");
@@ -75,6 +206,52 @@ static int test_cgcore_populated(const char *root)
 	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(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:
@@ -90,6 +267,8 @@ cleanup:
 	free(cg_test_c);
 	free(cg_test_b);
 	free(cg_test_a);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
 	return ret;
 }
 
@@ -106,6 +285,9 @@ 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");
@@ -133,6 +315,16 @@ static int test_cgcore_invalid_domain(const char *root)
 	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:
@@ -158,6 +350,9 @@ 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)
@@ -197,8 +392,9 @@ static int test_cgcore_no_internal_process_constraint_on_threads(const char *roo
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
-	if (cg_read_strstr(root, "cgroup.controllers", "cpu") ||
-	    cg_read_strstr(root, "cgroup.subtree_control", "cpu")) {
+	if (cg_test_v1_named ||
+	    cg_read_strstr(root, "cgroup.controllers", "cpu") ||
+	    cg_write(root, "cgroup.subtree_control", "+cpu")) {
 		ret = KSFT_SKIP;
 		goto cleanup;
 	}
@@ -249,6 +445,9 @@ 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)
@@ -284,6 +483,9 @@ 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)
@@ -325,6 +527,9 @@ 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)
@@ -342,6 +547,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
 	if (!cg_enter_current(parent))
 		goto cleanup;
 
+	if (!clone_into_cgroup_run_wait(parent))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
@@ -354,6 +562,344 @@ cleanup:
 	return ret;
 }
 
+static void *dummy_thread_fn(void *arg)
+{
+	return (void *)(size_t)pause();
+}
+
+/*
+ * Test threadgroup migration.
+ * All threads of a process are migrated together.
+ */
+static int test_cgcore_proc_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int t, c_threads = 0, n_threads = 13;
+	char *src = NULL, *dst = NULL;
+	pthread_t threads[n_threads];
+
+	src = cg_name(root, "cg_src");
+	dst = cg_name(root, "cg_dst");
+	if (!src || !dst)
+		goto cleanup;
+
+	if (cg_create(src))
+		goto cleanup;
+	if (cg_create(dst))
+		goto cleanup;
+
+	if (cg_enter_current(src))
+		goto cleanup;
+
+	for (c_threads = 0; c_threads < n_threads; ++c_threads) {
+		if (pthread_create(&threads[c_threads], NULL, dummy_thread_fn, NULL))
+			goto cleanup;
+	}
+
+	cg_enter_current(dst);
+	if (cg_read_lc(dst, CG_THREADS_FILE) != n_threads + 1)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (t = 0; t < c_threads; ++t) {
+		pthread_cancel(threads[t]);
+	}
+
+	for (t = 0; t < c_threads; ++t) {
+		pthread_join(threads[t], NULL);
+	}
+
+	cg_enter_current(root);
+
+	if (dst)
+		cg_destroy(dst);
+	if (src)
+		cg_destroy(src);
+	free(dst);
+	free(src);
+	return ret;
+}
+
+static void *migrating_thread_fn(void *arg)
+{
+	int g, i, n_iterations = 1000;
+	char **grps = arg;
+	char lines[3][PATH_MAX];
+
+	for (g = 1; g < 3; ++g)
+		snprintf(lines[g], sizeof(lines[g]), CG_PATH_FORMAT, grps[g] + strlen(grps[0]));
+
+	for (i = 0; i < n_iterations; ++i) {
+		cg_enter_current_thread(grps[(i % 2) + 1]);
+
+		if (proc_read_strstr(0, 1, "cgroup", lines[(i % 2) + 1]))
+			return (void *)-1;
+	}
+	return NULL;
+}
+
+/*
+ * Test single thread migration.
+ * Threaded cgroups allow successful migration of a thread.
+ */
+static int test_cgcore_thread_migration(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *dom = NULL;
+	char line[PATH_MAX];
+	char *grps[3] = { (char *)root, NULL, NULL };
+	pthread_t thr;
+	void *retval;
+
+	dom = cg_name(root, "cg_dom");
+	grps[1] = cg_name(root, "cg_dom/cg_src");
+	grps[2] = cg_name(root, "cg_dom/cg_dst");
+	if (!grps[1] || !grps[2] || !dom)
+		goto cleanup;
+
+	if (cg_create(dom))
+		goto cleanup;
+	if (cg_create(grps[1]))
+		goto cleanup;
+	if (cg_create(grps[2]))
+		goto cleanup;
+
+	if (!cg_test_v1_named) {
+		if (cg_write(grps[1], "cgroup.type", "threaded"))
+			goto cleanup;
+		if (cg_write(grps[2], "cgroup.type", "threaded"))
+			goto cleanup;
+	}
+
+	if (cg_enter_current(grps[1]))
+		goto cleanup;
+
+	if (pthread_create(&thr, NULL, migrating_thread_fn, grps))
+		goto cleanup;
+
+	if (pthread_join(thr, &retval))
+		goto cleanup;
+
+	if (retval)
+		goto cleanup;
+
+	snprintf(line, sizeof(line), CG_PATH_FORMAT, grps[1] + strlen(grps[0]));
+	if (proc_read_strstr(0, 1, "cgroup", line))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (grps[2])
+		cg_destroy(grps[2]);
+	if (grps[1])
+		cg_destroy(grps[1]);
+	if (dom)
+		cg_destroy(dom);
+	free(grps[2]);
+	free(grps[1]);
+	free(dom);
+	return ret;
+}
+
+/*
+ * cgroup migration permission check should be performed based on the
+ * credentials at the time of open instead of write.
+ */
+static int test_cgcore_lesser_euid_open(const char *root)
+{
+	const uid_t test_euid = TEST_UID;
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	uid_t saved_uid;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	saved_uid = geteuid();
+	if (seteuid(test_euid))
+		goto cleanup;
+
+	cg_test_b_procs_fd = open(cg_test_b_procs, O_RDWR);
+
+	if (seteuid(saved_uid))
+		goto cleanup;
+
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (write(cg_test_b_procs_fd, "0", 1) >= 0 || errno != EACCES)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
+struct lesser_ns_open_thread_arg {
+	const char	*path;
+	int		fd;
+	int		err;
+};
+
+static int lesser_ns_open_thread_fn(void *arg)
+{
+	struct lesser_ns_open_thread_arg *targ = arg;
+
+	targ->fd = open(targ->path, O_RDWR);
+	targ->err = errno;
+	return 0;
+}
+
+/*
+ * cgroup migration permission check should be performed based on the cgroup
+ * namespace at the time of open instead of write.
+ */
+static int test_cgcore_lesser_ns_open(const char *root)
+{
+	static char stack[65536];
+	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	int ret = KSFT_FAIL;
+	char *cg_test_a = NULL, *cg_test_b = NULL;
+	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
+	int cg_test_b_procs_fd = -1;
+	struct lesser_ns_open_thread_arg targ = { .fd = -1 };
+	pid_t pid;
+	int status;
+
+	if (!nsdelegate)
+		return KSFT_SKIP;
+
+	cg_test_a = cg_name(root, "cg_test_a");
+	cg_test_b = cg_name(root, "cg_test_b");
+
+	if (!cg_test_a || !cg_test_b)
+		goto cleanup;
+
+	cg_test_a_procs = cg_name(cg_test_a, "cgroup.procs");
+	cg_test_b_procs = cg_name(cg_test_b, "cgroup.procs");
+
+	if (!cg_test_a_procs || !cg_test_b_procs)
+		goto cleanup;
+
+	if (cg_create(cg_test_a) || cg_create(cg_test_b))
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_b))
+		goto cleanup;
+
+	if (chown(cg_test_a_procs, test_euid, -1) ||
+	    chown(cg_test_b_procs, test_euid, -1))
+		goto cleanup;
+
+	targ.path = cg_test_b_procs;
+	pid = clone(lesser_ns_open_thread_fn, stack + sizeof(stack),
+		    CLONE_NEWCGROUP | CLONE_FILES | CLONE_VM | SIGCHLD,
+		    &targ);
+	if (pid < 0)
+		goto cleanup;
+
+	if (waitpid(pid, &status, 0) < 0)
+		goto cleanup;
+
+	if (!WIFEXITED(status))
+		goto cleanup;
+
+	cg_test_b_procs_fd = targ.fd;
+	if (cg_test_b_procs_fd < 0)
+		goto cleanup;
+
+	if (cg_enter_current(cg_test_a))
+		goto cleanup;
+
+	if ((status = write(cg_test_b_procs_fd, "0", 1)) >= 0 || errno != ENOENT)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_test_b_procs_fd >= 0)
+		close(cg_test_b_procs_fd);
+	if (cg_test_b)
+		cg_destroy(cg_test_b);
+	if (cg_test_a)
+		cg_destroy(cg_test_a);
+	free(cg_test_b_procs);
+	free(cg_test_a_procs);
+	free(cg_test_b);
+	free(cg_test_a);
+	return ret;
+}
+
+static int setup_named_v1_root(char *root, size_t len, const char *name)
+{
+	char options[PATH_MAX];
+	int r;
+
+	r = snprintf(root, len, "/mnt/cg_selftest");
+	if (r < 0)
+		return r;
+
+	r = snprintf(options, sizeof(options), "none,name=%s", name);
+	if (r < 0)
+		return r;
+
+	r = mkdir(root, 0755);
+	if (r < 0 && errno != EEXIST)
+		return r;
+
+	r = mount("none", root, "cgroup", 0, options);
+	if (r < 0)
+		return r;
+
+	return 0;
+}
+
+static void cleanup_named_v1_root(char *root)
+{
+	if (!cg_test_v1_named)
+		return;
+	umount(root);
+	rmdir(root);
+}
+
 #define T(x) { x, #x }
 struct corecg_test {
 	int (*fn)(const char *root);
@@ -366,16 +912,33 @@ struct corecg_test {
 	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, ret = EXIT_SUCCESS;
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
+		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
+			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
+		cg_test_v1_named = true;
+		goto post_v2_setup;
+	}
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
 
-	if (cg_find_unified_root(root, sizeof(root)))
-		ksft_exit_skip("cgroup v2 isn't mounted\n");
+post_v2_setup:
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
@@ -385,11 +948,11 @@ int main(int argc, char *argv[])
 			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;
+	cleanup_named_v1_root(root);
+	ksft_finished();
 }