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
|
#include "gmid.h"
#if defined(__FreeBSD__)
#include <sys/capsicum.h>
#include <err.h>
void
sandbox()
{
if (cap_enter() == -1)
err(1, "cap_enter");
}
#elif defined(__linux__)
#include <sys/prctl.h>
#include <sys/syscall.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <linux/audit.h>
#include <linux/filter.h>
#include <linux/seccomp.h>
#include <errno.h>
#include <stddef.h>
#include <stdio.h>
#include <seccomp.h>
#include <string.h>
/* thanks chromium' src/seccomp.c */
#if defined(__i386__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_I386
#elif defined(__x86_64__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_X86_64
#elif defined(__arm__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_ARM
#elif defined(__aarch64__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_AARCH64
#elif defined(__mips__)
# if defined(__mips64)
# if defined(__MIPSEB__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_MIPS64
# else
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_MIPSEL64
# endif
# else
# if defined(__MIPSEB__)
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_MIPS
# else
# define SECCOMP_AUDIT_ARCH AUDIT_ARCH_MIPSEL
# endif
# endif
#else
# error "Platform does not support seccomp filter yet"
#endif
/* uncomment to enable debugging. ONLY FOR DEVELOPMENT */
/* #define SC_DEBUG */
#ifdef SC_DEBUG
# define SC_FAIL SECCOMP_RET_TRAP
#else
# define SC_FAIL SECCOMP_RET_KILL
#endif
/* make the filter more readable */
#define SC_ALLOW(nr) \
BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_##nr, 0, 1), \
BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW)
#ifdef SC_DEBUG
#include <signal.h>
#include <unistd.h>
static void
sandbox_seccomp_violation(int signum, siginfo_t *info, void *ctx)
{
(void)signum;
(void)ctx;
fprintf(stderr, "%s: unexpected system call (arch:0x%x,syscall:%d @ %p)\n",
__func__, info->si_arch, info->si_syscall, info->si_call_addr);
_exit(1);
}
static void
sandbox_seccomp_catch_sigsys(void)
{
struct sigaction act;
sigset_t mask;
memset(&act, 0, sizeof(act));
sigemptyset(&mask);
sigaddset(&mask, SIGSYS);
act.sa_sigaction = &sandbox_seccomp_violation;
act.sa_flags = SA_SIGINFO;
if (sigaction(SIGSYS, &act, NULL) == -1) {
fprintf(stderr, "%s: sigaction(SIGSYS): %s\n",
__func__, strerror(errno));
exit(1);
}
if (sigprocmask(SIG_UNBLOCK, &mask, NULL) == -1) {
fprintf(stderr, "%s: sigprocmask(SIGSYS): %s\n",
__func__, strerror(errno));
exit(1);
}
}
#endif /* SC_DEBUG */
void
sandbox()
{
struct sock_filter filter[] = {
/* load the *current* architecture */
BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
(offsetof(struct seccomp_data, arch))),
/* ensure it's the same that we've been compiled on */
BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K,
SECCOMP_AUDIT_ARCH, 1, 0),
/* if not, kill the program */
BPF_STMT(BPF_RET | BPF_K, SC_FAIL),
/* load the syscall number */
BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
(offsetof(struct seccomp_data, nr))),
/* allow logging on stdout */
SC_ALLOW(write),
SC_ALLOW(writev),
SC_ALLOW(readv),
/* these are used to serve the files. note how we
* allow openat but not open. */
SC_ALLOW(ppoll),
SC_ALLOW(accept),
SC_ALLOW(fcntl),
SC_ALLOW(read),
SC_ALLOW(openat),
SC_ALLOW(fstat),
SC_ALLOW(close),
SC_ALLOW(lseek),
SC_ALLOW(brk),
SC_ALLOW(mmap),
SC_ALLOW(munmap),
/* we need recvmsg to receive fd */
SC_ALLOW(recvmsg),
/* XXX: ??? */
SC_ALLOW(getpid),
SC_ALLOW(exit),
SC_ALLOW(exit_group),
/* allow ioctl but only on fd 1, glibc doing stuff? */
BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, __NR_ioctl, 0, 3),
BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
(offsetof(struct seccomp_data, args[0]))),
BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 1, 0, 1),
BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW),
/* disallow enything else */
BPF_STMT(BPF_RET | BPF_K, SC_FAIL),
};
struct sock_fprog prog = {
.len = (unsigned short) (sizeof(filter) / sizeof(filter[0])),
.filter = filter,
};
#ifdef SC_DEBUG
sandbox_seccomp_catch_sigsys();
#endif
if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) == -1) {
fprintf(stderr, "%s: prctl(PR_SET_NO_NEW_PRIVS): %s\n",
__func__, strerror(errno));
exit(1);
}
if (prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog) == -1) {
fprintf(stderr, "%s: prctl(PR_SET_SECCOMP): %s\n",
__func__, strerror(errno));
exit(1);
}
}
#elif defined(__OpenBSD__)
#include <err.h>
#include <unistd.h>
void
sandbox()
{
struct vhost *h;
for (h = hosts; h->domain != NULL; ++h) {
if (unveil(h->dir, "rx") == -1)
err(1, "unveil %s for domain %s", h->dir, h->domain);
}
if (pledge("stdio recvfd rpath inet", NULL) == -1)
err(1, "pledge");
}
#else
void
sandbox()
{
LOGN(NULL, "%s", "no sandbox method known for this OS");
}
#endif
|
