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
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
#define _GNU_SOURCE /* See feature_test_macros(7) */
#include <unistd.h>
#include <sched.h>
#include <pthread.h>
#include <sys/syscall.h> /* For SYS_xxx definitions */
#include <sys/types.h>
#include <test_progs.h>
#include "task_local_storage.skel.h"
#include "task_local_storage_exit_creds.skel.h"
#include "task_ls_recursion.skel.h"
#include "task_storage_nodeadlock.skel.h"
static void test_sys_enter_exit(void)
{
struct task_local_storage *skel;
int err;
skel = task_local_storage__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
skel->bss->target_pid = syscall(SYS_gettid);
err = task_local_storage__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto out;
syscall(SYS_gettid);
syscall(SYS_gettid);
/* 3x syscalls: 1x attach and 2x gettid */
ASSERT_EQ(skel->bss->enter_cnt, 3, "enter_cnt");
ASSERT_EQ(skel->bss->exit_cnt, 3, "exit_cnt");
ASSERT_EQ(skel->bss->mismatch_cnt, 0, "mismatch_cnt");
out:
task_local_storage__destroy(skel);
}
static void test_exit_creds(void)
{
struct task_local_storage_exit_creds *skel;
int err, run_count, sync_rcu_calls = 0;
const int MAX_SYNC_RCU_CALLS = 1000;
skel = task_local_storage_exit_creds__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
err = task_local_storage_exit_creds__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto out;
/* trigger at least one exit_creds() */
if (CHECK_FAIL(system("ls > /dev/null")))
goto out;
/* kern_sync_rcu is not enough on its own as the read section we want
* to wait for may start after we enter synchronize_rcu, so our call
* won't wait for the section to finish. Loop on the run counter
* as well to ensure the program has run.
*/
do {
kern_sync_rcu();
run_count = __atomic_load_n(&skel->bss->run_count, __ATOMIC_SEQ_CST);
} while (run_count == 0 && ++sync_rcu_calls < MAX_SYNC_RCU_CALLS);
ASSERT_NEQ(sync_rcu_calls, MAX_SYNC_RCU_CALLS,
"sync_rcu count too high");
ASSERT_NEQ(run_count, 0, "run_count");
ASSERT_EQ(skel->bss->valid_ptr_count, 0, "valid_ptr_count");
ASSERT_NEQ(skel->bss->null_ptr_count, 0, "null_ptr_count");
out:
task_local_storage_exit_creds__destroy(skel);
}
static void test_recursion(void)
{
struct task_ls_recursion *skel;
int err;
skel = task_ls_recursion__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
return;
err = task_ls_recursion__attach(skel);
if (!ASSERT_OK(err, "skel_attach"))
goto out;
/* trigger sys_enter, make sure it does not cause deadlock */
syscall(SYS_gettid);
out:
task_ls_recursion__destroy(skel);
}
static bool stop;
static void waitall(const pthread_t *tids, int nr)
{
int i;
stop = true;
for (i = 0; i < nr; i++)
pthread_join(tids[i], NULL);
}
static void *sock_create_loop(void *arg)
{
struct task_storage_nodeadlock *skel = arg;
int fd;
while (!stop) {
fd = socket(AF_INET, SOCK_STREAM, 0);
close(fd);
if (skel->bss->nr_get_errs || skel->bss->nr_del_errs)
stop = true;
}
return NULL;
}
static void test_nodeadlock(void)
{
struct task_storage_nodeadlock *skel;
struct bpf_prog_info info = {};
__u32 info_len = sizeof(info);
const int nr_threads = 32;
pthread_t tids[nr_threads];
int i, prog_fd, err;
cpu_set_t old, new;
/* Pin all threads to one cpu to increase the chance of preemption
* in a sleepable bpf prog.
*/
CPU_ZERO(&new);
CPU_SET(0, &new);
err = sched_getaffinity(getpid(), sizeof(old), &old);
if (!ASSERT_OK(err, "getaffinity"))
return;
err = sched_setaffinity(getpid(), sizeof(new), &new);
if (!ASSERT_OK(err, "setaffinity"))
return;
skel = task_storage_nodeadlock__open_and_load();
if (!ASSERT_OK_PTR(skel, "open_and_load"))
goto done;
/* Unnecessary recursion and deadlock detection are reproducible
* in the preemptible kernel.
*/
if (!skel->kconfig->CONFIG_PREEMPT) {
test__skip();
goto done;
}
err = task_storage_nodeadlock__attach(skel);
ASSERT_OK(err, "attach prog");
for (i = 0; i < nr_threads; i++) {
err = pthread_create(&tids[i], NULL, sock_create_loop, skel);
if (err) {
/* Only assert once here to avoid excessive
* PASS printing during test failure.
*/
ASSERT_OK(err, "pthread_create");
waitall(tids, i);
goto done;
}
}
/* With 32 threads, 1s is enough to reproduce the issue */
sleep(1);
waitall(tids, nr_threads);
info_len = sizeof(info);
prog_fd = bpf_program__fd(skel->progs.socket_post_create);
err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
ASSERT_OK(err, "get prog info");
ASSERT_EQ(info.recursion_misses, 0, "prog recursion");
ASSERT_EQ(skel->bss->nr_get_errs, 0, "bpf_task_storage_get busy");
ASSERT_EQ(skel->bss->nr_del_errs, 0, "bpf_task_storage_delete busy");
done:
task_storage_nodeadlock__destroy(skel);
sched_setaffinity(getpid(), sizeof(old), &old);
}
void test_task_local_storage(void)
{
if (test__start_subtest("sys_enter_exit"))
test_sys_enter_exit();
if (test__start_subtest("exit_creds"))
test_exit_creds();
if (test__start_subtest("recursion"))
test_recursion();
if (test__start_subtest("nodeadlock"))
test_nodeadlock();
}
|
