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
|
/*
* Copyright (C) 2023 Thomas Weißschuh <thomas@t-8ch.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include <stddef.h>
#include <stdbool.h>
#include <getopt.h>
#include <linux/unistd.h>
#include <linux/filter.h>
#include <linux/seccomp.h>
#include <linux/audit.h>
#include <sys/prctl.h>
#include "c.h"
#include "exitcodes.h"
#include "nls.h"
#if __x86_64__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_X86_64
#elif __i386__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_I386
#elif __arm__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_ARM
#elif __aarch64__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_AARCH64
#elif __riscv
# if __riscv_xlen == 32
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_RISCV32
# elif __riscv_xlen == 64
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_RISCV64
# endif
#elif __s390x__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_S390X
#elif __s390__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_S390
#elif __PPC64__
# if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_PPC64
# else
# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_PPC64LE
# endif
#else
# error Unknown target architecture
#endif
#define UL_BPF_NOP (struct sock_filter) BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0)
#define syscall_nr (offsetof(struct seccomp_data, nr))
#define syscall_arch (offsetof(struct seccomp_data, arch))
struct syscall {
const char *const name;
long number;
};
static const struct syscall syscalls[] = {
{ "move_mount", __NR_move_mount },
{ "open_tree", __NR_open_tree },
{ "fsopen", __NR_fsopen },
{ "fallocate", __NR_fallocate },
};
static void __attribute__((__noreturn__)) usage(void)
{
FILE *out = stdout;
fputs(USAGE_HEADER, out);
fprintf(out, _(" %s [options] -- <command>\n"), program_invocation_short_name);
fputs(USAGE_OPTIONS, out);
fputs(_(" -s, --syscall syscall to block\n"), out);
fputs(_(" -l, --list list known syscalls\n"), out);
fputs(USAGE_SEPARATOR, out);
fprintf(out, USAGE_HELP_OPTIONS(25));
fprintf(out, USAGE_MAN_TAIL("enosys(1)"));
exit(EXIT_SUCCESS);
}
int main(int argc, char **argv)
{
int c;
size_t i;
bool found;
static const struct option longopts[] = {
{ "syscall", required_argument, NULL, 's' },
{ "list", no_argument, NULL, 'l' },
{ "version", no_argument, NULL, 'V' },
{ "help", no_argument, NULL, 'h' },
{ 0 }
};
bool blocked_syscalls[ARRAY_SIZE(syscalls)] = {};
while ((c = getopt_long (argc, argv, "Vhs:l", longopts, NULL)) != -1) {
switch (c) {
case 's':
found = 0;
for (i = 0; i < ARRAY_SIZE(syscalls); i++) {
if (strcmp(optarg, syscalls[i].name) == 0) {
blocked_syscalls[i] = true;
found = 1;
break;
}
}
if (!found)
errx(EXIT_FAILURE, _("Unknown syscall '%s'"), optarg);
break;
case 'l':
for (i = 0; i < ARRAY_SIZE(syscalls); i++)
printf("%s\n", syscalls[i].name);
return EXIT_SUCCESS;
case 'V':
print_version(EXIT_SUCCESS);
case 'h':
usage();
default:
errtryhelp(EXIT_FAILURE);
}
}
if (optind >= argc)
errtryhelp(EXIT_FAILURE);
#define N_FILTERS (ARRAY_SIZE(syscalls) + 6)
struct sock_filter filter[N_FILTERS] = {
[0] = BPF_STMT(BPF_LD | BPF_W | BPF_ABS, syscall_arch),
[1] = BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, SECCOMP_ARCH_NATIVE, 1, 0),
[2] = BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_TRAP),
[3] = BPF_STMT(BPF_LD | BPF_W | BPF_ABS, syscall_nr),
[N_FILTERS - 2] = BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),
[N_FILTERS - 1] = BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ERRNO | ENOSYS),
};
for (i = 0; i < ARRAY_SIZE(syscalls); i++) {
if (blocked_syscalls[i]) {
filter[i + 4] = (struct sock_filter) BPF_JUMP(
BPF_JMP | BPF_JEQ | BPF_K,
syscalls[i].number,
N_FILTERS - 3 - i, 0);
} else {
filter[i + 4] = UL_BPF_NOP;
}
}
struct sock_fprog prog = {
.len = ARRAY_SIZE(filter),
.filter = filter,
};
/* *SET* below will return EINVAL when either the filter is invalid or
* seccomp is not supported. To distinguish those cases do a *GET* here
*/
if (prctl(PR_GET_SECCOMP) == -1 && errno == EINVAL)
err(EXIT_NOTSUPP, _("Seccomp non-functional"));
if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0))
err_nosys(EXIT_FAILURE, _("Could not run prctl(PR_SET_NO_NEW_PRIVS)"));
if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog))
err_nosys(EXIT_FAILURE, _("Could not run prctl(PR_SET_SECCOMP)"));
if (execvp(argv[optind], argv + optind))
err(EXIT_NOTSUPP, _("Could not exec"));
}
|
