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
|
/* SPDX-License-Identifier: LGPL-2.1+ */
#include <errno.h>
#include <linux/netlink.h>
#include <sys/capability.h>
#include <sys/types.h>
#if HAVE_SECCOMP
#include <seccomp.h>
#endif
#include "alloc-util.h"
#include "log.h"
#include "nspawn-seccomp.h"
#if HAVE_SECCOMP
#include "seccomp-util.h"
#endif
#include "string-util.h"
#include "strv.h"
#if HAVE_SECCOMP
static int seccomp_add_default_syscall_filter(
scmp_filter_ctx ctx,
uint32_t arch,
uint64_t cap_list_retain,
char **syscall_whitelist,
char **syscall_blacklist) {
static const struct {
uint64_t capability;
const char* name;
} whitelist[] = {
/* Let's use set names where we can */
{ 0, "@aio" },
{ 0, "@basic-io" },
{ 0, "@chown" },
{ 0, "@default" },
{ 0, "@file-system" },
{ 0, "@io-event" },
{ 0, "@ipc" },
{ 0, "@mount" },
{ 0, "@network-io" },
{ 0, "@process" },
{ 0, "@resources" },
{ 0, "@setuid" },
{ 0, "@signal" },
{ 0, "@sync" },
{ 0, "@timer" },
/* The following four are sets we optionally enable, in case the caps have been configured for it */
{ CAP_SYS_TIME, "@clock" },
{ CAP_SYS_MODULE, "@module" },
{ CAP_SYS_RAWIO, "@raw-io" },
{ CAP_IPC_LOCK, "@memlock" },
/* Plus a good set of additional syscalls which are not part of any of the groups above */
{ 0, "brk" },
{ 0, "capget" },
{ 0, "capset" },
{ 0, "copy_file_range" },
{ 0, "fadvise64" },
{ 0, "fadvise64_64" },
{ 0, "flock" },
{ 0, "get_mempolicy" },
{ 0, "getcpu" },
{ 0, "getpriority" },
{ 0, "getrandom" },
{ 0, "ioctl" },
{ 0, "ioprio_get" },
{ 0, "kcmp" },
{ 0, "madvise" },
{ 0, "mincore" },
{ 0, "mprotect" },
{ 0, "mremap" },
{ 0, "name_to_handle_at" },
{ 0, "oldolduname" },
{ 0, "olduname" },
{ 0, "personality" },
{ 0, "readahead" },
{ 0, "readdir" },
{ 0, "remap_file_pages" },
{ 0, "sched_get_priority_max" },
{ 0, "sched_get_priority_min" },
{ 0, "sched_getaffinity" },
{ 0, "sched_getattr" },
{ 0, "sched_getparam" },
{ 0, "sched_getscheduler" },
{ 0, "sched_rr_get_interval" },
{ 0, "sched_yield" },
{ 0, "seccomp" },
{ 0, "sendfile" },
{ 0, "sendfile64" },
{ 0, "setdomainname" },
{ 0, "setfsgid" },
{ 0, "setfsgid32" },
{ 0, "setfsuid" },
{ 0, "setfsuid32" },
{ 0, "sethostname" },
{ 0, "setpgid" },
{ 0, "setsid" },
{ 0, "splice" },
{ 0, "sysinfo" },
{ 0, "tee" },
{ 0, "umask" },
{ 0, "uname" },
{ 0, "userfaultfd" },
{ 0, "vmsplice" },
/* The following individual syscalls are added depending on specified caps */
{ CAP_SYS_PACCT, "acct" },
{ CAP_SYS_PTRACE, "process_vm_readv" },
{ CAP_SYS_PTRACE, "process_vm_writev" },
{ CAP_SYS_PTRACE, "ptrace" },
{ CAP_SYS_BOOT, "reboot" },
{ CAP_SYSLOG, "syslog" },
{ CAP_SYS_TTY_CONFIG, "vhangup" },
/*
* The following syscalls and groups are knowingly excluded:
*
* @cpu-emulation
* @keyring (NB: keyring is not namespaced!)
* @obsolete
* @swap
*
* bpf (NB: bpffs is not namespaced!)
* fanotify_init
* fanotify_mark
* kexec_file_load
* kexec_load
* lookup_dcookie
* nfsservctl
* open_by_handle_at
* perf_event_open
* pkey_alloc
* pkey_free
* pkey_mprotect
* quotactl
*/
};
int r, c = 0;
size_t i;
char **p;
for (i = 0; i < ELEMENTSOF(whitelist); i++) {
if (whitelist[i].capability != 0 && (cap_list_retain & (1ULL << whitelist[i].capability)) == 0)
continue;
r = seccomp_add_syscall_filter_item(ctx, whitelist[i].name, SCMP_ACT_ALLOW, syscall_blacklist);
if (r < 0)
/* If the system call is not known on this architecture, then that's fine, let's ignore it */
log_debug_errno(r, "Failed to add rule for system call %s on %s, ignoring: %m", whitelist[i].name, seccomp_arch_to_string(arch));
else
c++;
}
STRV_FOREACH(p, syscall_whitelist) {
r = seccomp_add_syscall_filter_item(ctx, *p, SCMP_ACT_ALLOW, syscall_blacklist);
if (r < 0)
log_debug_errno(r, "Failed to add rule for system call %s on %s, ignoring: %m", *p, seccomp_arch_to_string(arch));
else
c++;
}
return c;
}
int setup_seccomp(uint64_t cap_list_retain, char **syscall_whitelist, char **syscall_blacklist) {
uint32_t arch;
int r;
if (!is_seccomp_available()) {
log_debug("SECCOMP features not detected in the kernel, disabling SECCOMP filterering");
return 0;
}
SECCOMP_FOREACH_LOCAL_ARCH(arch) {
_cleanup_(seccomp_releasep) scmp_filter_ctx seccomp = NULL;
log_debug("Applying whitelist on architecture: %s", seccomp_arch_to_string(arch));
r = seccomp_init_for_arch(&seccomp, arch, SCMP_ACT_ERRNO(EPERM));
if (r < 0)
return log_error_errno(r, "Failed to allocate seccomp object: %m");
r = seccomp_add_default_syscall_filter(seccomp, arch, cap_list_retain, syscall_whitelist, syscall_blacklist);
if (r < 0)
return r;
r = seccomp_load(seccomp);
if (IN_SET(r, -EPERM, -EACCES))
return log_error_errno(r, "Failed to install seccomp filter: %m");
if (r < 0)
log_debug_errno(r, "Failed to install filter set for architecture %s, skipping: %m", seccomp_arch_to_string(arch));
}
SECCOMP_FOREACH_LOCAL_ARCH(arch) {
_cleanup_(seccomp_releasep) scmp_filter_ctx seccomp = NULL;
log_debug("Applying NETLINK_AUDIT mask on architecture: %s", seccomp_arch_to_string(arch));
r = seccomp_init_for_arch(&seccomp, arch, SCMP_ACT_ALLOW);
if (r < 0)
return log_error_errno(r, "Failed to allocate seccomp object: %m");
/*
Audit is broken in containers, much of the userspace audit hookup will fail if running inside a
container. We don't care and just turn off creation of audit sockets.
This will make socket(AF_NETLINK, *, NETLINK_AUDIT) fail with EAFNOSUPPORT which audit userspace uses
as indication that audit is disabled in the kernel.
*/
r = seccomp_rule_add_exact(
seccomp,
SCMP_ACT_ERRNO(EAFNOSUPPORT),
SCMP_SYS(socket),
2,
SCMP_A0(SCMP_CMP_EQ, AF_NETLINK),
SCMP_A2(SCMP_CMP_EQ, NETLINK_AUDIT));
if (r < 0) {
log_debug_errno(r, "Failed to add audit seccomp rule, ignoring: %m");
continue;
}
r = seccomp_load(seccomp);
if (IN_SET(r, -EPERM, -EACCES))
return log_error_errno(r, "Failed to install seccomp audit filter: %m");
if (r < 0)
log_debug_errno(r, "Failed to install filter set for architecture %s, skipping: %m", seccomp_arch_to_string(arch));
}
return 0;
}
#else
int setup_seccomp(uint64_t cap_list_retain, char **syscall_whitelist, char **syscall_blacklist) {
return 0;
}
#endif
|
