1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
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), 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");
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;
}
|
