summaryrefslogtreecommitdiff
path: root/tools/testing/selftests/bpf/cgroup_helpers.c
blob: e95c33e333a40ad9c1c439e668c7a8c1d2000f8c (plain)
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
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE
#include <sched.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <linux/limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <linux/sched.h>
#include <fcntl.h>
#include <unistd.h>
#include <ftw.h>


#include "cgroup_helpers.h"

/*
 * To avoid relying on the system setup, when setup_cgroup_env is called
 * we create a new mount namespace, and cgroup namespace. The cgroup2
 * root is mounted at CGROUP_MOUNT_PATH
 *
 * Unfortunately, most people don't have cgroupv2 enabled at this point in time.
 * It's easier to create our own mount namespace and manage it ourselves.
 *
 * We assume /mnt exists.
 */

#define WALK_FD_LIMIT			16
#define CGROUP_MOUNT_PATH		"/mnt"
#define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
#define format_cgroup_path(buf, path) \
	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
		 CGROUP_WORK_DIR, path)

/**
 * enable_all_controllers() - Enable all available cgroup v2 controllers
 *
 * Enable all available cgroup v2 controllers in order to increase
 * the code coverage.
 *
 * If successful, 0 is returned.
 */
int enable_all_controllers(char *cgroup_path)
{
	char path[PATH_MAX + 1];
	char buf[PATH_MAX];
	char *c, *c2;
	int fd, cfd;
	ssize_t len;

	snprintf(path, sizeof(path), "%s/cgroup.controllers", cgroup_path);
	fd = open(path, O_RDONLY);
	if (fd < 0) {
		log_err("Opening cgroup.controllers: %s", path);
		return 1;
	}

	len = read(fd, buf, sizeof(buf) - 1);
	if (len < 0) {
		close(fd);
		log_err("Reading cgroup.controllers: %s", path);
		return 1;
	}
	buf[len] = 0;
	close(fd);

	/* No controllers available? We're probably on cgroup v1. */
	if (len == 0)
		return 0;

	snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path);
	cfd = open(path, O_RDWR);
	if (cfd < 0) {
		log_err("Opening cgroup.subtree_control: %s", path);
		return 1;
	}

	for (c = strtok_r(buf, " ", &c2); c; c = strtok_r(NULL, " ", &c2)) {
		if (dprintf(cfd, "+%s\n", c) <= 0) {
			log_err("Enabling controller %s: %s", c, path);
			close(cfd);
			return 1;
		}
	}
	close(cfd);
	return 0;
}

/**
 * setup_cgroup_environment() - Setup the cgroup environment
 *
 * After calling this function, cleanup_cgroup_environment should be called
 * once testing is complete.
 *
 * This function will print an error to stderr and return 1 if it is unable
 * to setup the cgroup environment. If setup is successful, 0 is returned.
 */
int setup_cgroup_environment(void)
{
	char cgroup_workdir[PATH_MAX + 1];

	format_cgroup_path(cgroup_workdir, "");

	if (unshare(CLONE_NEWNS)) {
		log_err("unshare");
		return 1;
	}

	if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
		log_err("mount fakeroot");
		return 1;
	}

	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
		log_err("mount cgroup2");
		return 1;
	}

	/* Cleanup existing failed runs, now that the environment is setup */
	cleanup_cgroup_environment();

	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
		log_err("mkdir cgroup work dir");
		return 1;
	}

	if (enable_all_controllers(cgroup_workdir))
		return 1;

	return 0;
}

static int nftwfunc(const char *filename, const struct stat *statptr,
		    int fileflags, struct FTW *pfwt)
{
	if ((fileflags & FTW_D) && rmdir(filename))
		log_err("Removing cgroup: %s", filename);
	return 0;
}


static int join_cgroup_from_top(char *cgroup_path)
{
	char cgroup_procs_path[PATH_MAX + 1];
	pid_t pid = getpid();
	int fd, rc = 0;

	snprintf(cgroup_procs_path, sizeof(cgroup_procs_path),
		 "%s/cgroup.procs", cgroup_path);

	fd = open(cgroup_procs_path, O_WRONLY);
	if (fd < 0) {
		log_err("Opening Cgroup Procs: %s", cgroup_procs_path);
		return 1;
	}

	if (dprintf(fd, "%d\n", pid) < 0) {
		log_err("Joining Cgroup");
		rc = 1;
	}

	close(fd);
	return rc;
}

/**
 * join_cgroup() - Join a cgroup
 * @path: The cgroup path, relative to the workdir, to join
 *
 * This function expects a cgroup to already be created, relative to the cgroup
 * work dir, and it joins it. For example, passing "/my-cgroup" as the path
 * would actually put the calling process into the cgroup
 * "/cgroup-test-work-dir/my-cgroup"
 *
 * On success, it returns 0, otherwise on failure it returns 1.
 */
int join_cgroup(const char *path)
{
	char cgroup_path[PATH_MAX + 1];

	format_cgroup_path(cgroup_path, path);
	return join_cgroup_from_top(cgroup_path);
}

/**
 * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
 *
 * This is an idempotent function to delete all temporary cgroups that
 * have been created during the test, including the cgroup testing work
 * directory.
 *
 * At call time, it moves the calling process to the root cgroup, and then
 * runs the deletion process. It is idempotent, and should not fail, unless
 * a process is lingering.
 *
 * On failure, it will print an error to stderr, and try to continue.
 */
void cleanup_cgroup_environment(void)
{
	char cgroup_workdir[PATH_MAX + 1];

	format_cgroup_path(cgroup_workdir, "");
	join_cgroup_from_top(CGROUP_MOUNT_PATH);
	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
}

/**
 * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
 * @path: The cgroup path, relative to the workdir, to join
 *
 * This function creates a cgroup under the top level workdir and returns the
 * file descriptor. It is idempotent.
 *
 * On success, it returns the file descriptor. On failure it returns -1.
 * If there is a failure, it prints the error to stderr.
 */
int create_and_get_cgroup(const char *path)
{
	char cgroup_path[PATH_MAX + 1];
	int fd;

	format_cgroup_path(cgroup_path, path);
	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
		return -1;
	}

	fd = open(cgroup_path, O_RDONLY);
	if (fd < 0) {
		log_err("Opening Cgroup");
		return -1;
	}

	return fd;
}

/**
 * get_cgroup_id() - Get cgroup id for a particular cgroup path
 * @path: The cgroup path, relative to the workdir, to join
 *
 * On success, it returns the cgroup id. On failure it returns 0,
 * which is an invalid cgroup id.
 * If there is a failure, it prints the error to stderr.
 */
unsigned long long get_cgroup_id(const char *path)
{
	int dirfd, err, flags, mount_id, fhsize;
	union {
		unsigned long long cgid;
		unsigned char raw_bytes[8];
	} id;
	char cgroup_workdir[PATH_MAX + 1];
	struct file_handle *fhp, *fhp2;
	unsigned long long ret = 0;

	format_cgroup_path(cgroup_workdir, path);

	dirfd = AT_FDCWD;
	flags = 0;
	fhsize = sizeof(*fhp);
	fhp = calloc(1, fhsize);
	if (!fhp) {
		log_err("calloc");
		return 0;
	}
	err = name_to_handle_at(dirfd, cgroup_workdir, fhp, &mount_id, flags);
	if (err >= 0 || fhp->handle_bytes != 8) {
		log_err("name_to_handle_at");
		goto free_mem;
	}

	fhsize = sizeof(struct file_handle) + fhp->handle_bytes;
	fhp2 = realloc(fhp, fhsize);
	if (!fhp2) {
		log_err("realloc");
		goto free_mem;
	}
	err = name_to_handle_at(dirfd, cgroup_workdir, fhp2, &mount_id, flags);
	fhp = fhp2;
	if (err < 0) {
		log_err("name_to_handle_at");
		goto free_mem;
	}

	memcpy(id.raw_bytes, fhp->f_handle, 8);
	ret = id.cgid;

free_mem:
	free(fhp);
	return ret;
}