1 files changed, 250 insertions, 15 deletions

diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 3df648c37876..102262555a59 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -1,20 +1,30 @@
 /* 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;
@@ -143,6 +153,9 @@ static int test_cgcore_populated(const char *root)
 	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");
@@ -272,6 +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");
@@ -334,6 +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)
@@ -373,7 +392,8 @@ 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") ||
+	if (cg_test_v1_named ||
+	    cg_read_strstr(root, "cgroup.controllers", "cpu") ||
 	    cg_write(root, "cgroup.subtree_control", "+cpu")) {
 		ret = KSFT_SKIP;
 		goto cleanup;
@@ -425,6 +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)
@@ -460,6 +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)
@@ -501,6 +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)
@@ -568,7 +597,7 @@ static int test_cgcore_proc_migration(const char *root)
 	}
 
 	cg_enter_current(dst);
-	if (cg_read_lc(dst, "cgroup.threads") != n_threads + 1)
+	if (cg_read_lc(dst, CG_THREADS_FILE) != n_threads + 1)
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -600,7 +629,7 @@ static void *migrating_thread_fn(void *arg)
 	char lines[3][PATH_MAX];
 
 	for (g = 1; g < 3; ++g)
-		snprintf(lines[g], sizeof(lines[g]), "0::%s", grps[g] + strlen(grps[0]));
+		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]);
@@ -637,10 +666,12 @@ static int test_cgcore_thread_migration(const char *root)
 	if (cg_create(grps[2]))
 		goto cleanup;
 
-	if (cg_write(grps[1], "cgroup.type", "threaded"))
-		goto cleanup;
-	if (cg_write(grps[2], "cgroup.type", "threaded"))
-		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;
@@ -654,7 +685,7 @@ static int test_cgcore_thread_migration(const char *root)
 	if (retval)
 		goto cleanup;
 
-	snprintf(line, sizeof(line), "0::%s", grps[1] + strlen(grps[0]));
+	snprintf(line, sizeof(line), CG_PATH_FORMAT, grps[1] + strlen(grps[0]));
 	if (proc_read_strstr(0, 1, "cgroup", line))
 		goto cleanup;
 
@@ -674,6 +705,201 @@ cleanup:
 	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);
@@ -689,21 +915,30 @@ struct corecg_test {
 	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;
-
-	if (cg_find_unified_root(root, sizeof(root)))
-		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
+		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
+			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
+		cg_test_v1_named = true;
+		goto post_v2_setup;
+	}
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+post_v2_setup:
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
@@ -713,11 +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();
 }