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
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
|
/*
* linux/kernel/seccomp.c
*
* Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com>
*
* Copyright (C) 2012 Google, Inc.
* Will Drewry <wad@chromium.org>
*
* This defines a simple but solid secure-computing facility.
*
* Mode 1 uses a fixed list of allowed system calls.
* Mode 2 allows user-defined system call filters in the form
* of Berkeley Packet Filters/Linux Socket Filters.
*/
#include <linux/atomic.h>
#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
/* #define SECCOMP_DEBUG 1 */
#ifdef CONFIG_SECCOMP_FILTER
#include <asm/syscall.h>
#include <linux/filter.h>
#include <linux/ptrace.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>
/**
* struct seccomp_filter - container for seccomp BPF programs
*
* @usage: reference count to manage the object lifetime.
* get/put helpers should be used when accessing an instance
* outside of a lifetime-guarded section. In general, this
* is only needed for handling filters shared across tasks.
* @prev: points to a previously installed, or inherited, filter
* @len: the number of instructions in the program
* @insns: the BPF program instructions to evaluate
*
* seccomp_filter objects are organized in a tree linked via the @prev
* pointer. For any task, it appears to be a singly-linked list starting
* with current->seccomp.filter, the most recently attached or inherited filter.
* However, multiple filters may share a @prev node, by way of fork(), which
* results in a unidirectional tree existing in memory. This is similar to
* how namespaces work.
*
* seccomp_filter objects should never be modified after being attached
* to a task_struct (other than @usage).
*/
struct seccomp_filter {
atomic_t usage;
struct seccomp_filter *prev;
unsigned short len; /* Instruction count */
struct sock_filter_int insnsi[];
};
/* Limit any path through the tree to 256KB worth of instructions. */
#define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
/*
* Endianness is explicitly ignored and left for BPF program authors to manage
* as per the specific architecture.
*/
static void populate_seccomp_data(struct seccomp_data *sd)
{
struct task_struct *task = current;
struct pt_regs *regs = task_pt_regs(task);
unsigned long args[6];
sd->nr = syscall_get_nr(task, regs);
sd->arch = syscall_get_arch();
syscall_get_arguments(task, regs, 0, 6, args);
sd->args[0] = args[0];
sd->args[1] = args[1];
sd->args[2] = args[2];
sd->args[3] = args[3];
sd->args[4] = args[4];
sd->args[5] = args[5];
sd->instruction_pointer = KSTK_EIP(task);
}
/**
* seccomp_check_filter - verify seccomp filter code
* @filter: filter to verify
* @flen: length of filter
*
* Takes a previously checked filter (by sk_chk_filter) and
* redirects all filter code that loads struct sk_buff data
* and related data through seccomp_bpf_load. It also
* enforces length and alignment checking of those loads.
*
* Returns 0 if the rule set is legal or -EINVAL if not.
*/
static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
{
int pc;
for (pc = 0; pc < flen; pc++) {
struct sock_filter *ftest = &filter[pc];
u16 code = ftest->code;
u32 k = ftest->k;
switch (code) {
case BPF_S_LD_W_ABS:
ftest->code = BPF_LDX | BPF_W | BPF_ABS;
/* 32-bit aligned and not out of bounds. */
if (k >= sizeof(struct seccomp_data) || k & 3)
return -EINVAL;
continue;
case BPF_S_LD_W_LEN:
ftest->code = BPF_LD | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
case BPF_S_LDX_W_LEN:
ftest->code = BPF_LDX | BPF_IMM;
ftest->k = sizeof(struct seccomp_data);
continue;
/* Explicitly include allowed calls. */
case BPF_S_RET_K:
case BPF_S_RET_A:
case BPF_S_ALU_ADD_K:
case BPF_S_ALU_ADD_X:
case BPF_S_ALU_SUB_K:
case BPF_S_ALU_SUB_X:
case BPF_S_ALU_MUL_K:
case BPF_S_ALU_MUL_X:
case BPF_S_ALU_DIV_X:
case BPF_S_ALU_AND_K:
case BPF_S_ALU_AND_X:
case BPF_S_ALU_OR_K:
case BPF_S_ALU_OR_X:
case BPF_S_ALU_XOR_K:
case BPF_S_ALU_XOR_X:
case BPF_S_ALU_LSH_K:
case BPF_S_ALU_LSH_X:
case BPF_S_ALU_RSH_K:
case BPF_S_ALU_RSH_X:
case BPF_S_ALU_NEG:
case BPF_S_LD_IMM:
case BPF_S_LDX_IMM:
case BPF_S_MISC_TAX:
case BPF_S_MISC_TXA:
case BPF_S_ALU_DIV_K:
case BPF_S_LD_MEM:
case BPF_S_LDX_MEM:
case BPF_S_ST:
case BPF_S_STX:
case BPF_S_JMP_JA:
case BPF_S_JMP_JEQ_K:
case BPF_S_JMP_JEQ_X:
case BPF_S_JMP_JGE_K:
case BPF_S_JMP_JGE_X:
case BPF_S_JMP_JGT_K:
case BPF_S_JMP_JGT_X:
case BPF_S_JMP_JSET_K:
case BPF_S_JMP_JSET_X:
sk_decode_filter(ftest, ftest);
continue;
default:
return -EINVAL;
}
}
return 0;
}
/**
* seccomp_run_filters - evaluates all seccomp filters against @syscall
* @syscall: number of the current system call
*
* Returns valid seccomp BPF response codes.
*/
static u32 seccomp_run_filters(int syscall)
{
struct seccomp_filter *f;
struct seccomp_data sd;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
if (WARN_ON(current->seccomp.filter == NULL))
return SECCOMP_RET_KILL;
populate_seccomp_data(&sd);
/*
* All filters in the list are evaluated and the lowest BPF return
* value always takes priority (ignoring the DATA).
*/
for (f = current->seccomp.filter; f; f = f->prev) {
u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
ret = cur_ret;
}
return ret;
}
/**
* seccomp_attach_filter: Attaches a seccomp filter to current.
* @fprog: BPF program to install
*
* Returns 0 on success or an errno on failure.
*/
static long seccomp_attach_filter(struct sock_fprog *fprog)
{
struct seccomp_filter *filter;
unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
unsigned long total_insns = fprog->len;
struct sock_filter *fp;
int new_len;
long ret;
if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
return -EINVAL;
for (filter = current->seccomp.filter; filter; filter = filter->prev)
total_insns += filter->len + 4; /* include a 4 instr penalty */
if (total_insns > MAX_INSNS_PER_PATH)
return -ENOMEM;
/*
* Installing a seccomp filter requires that the task have
* CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
* This avoids scenarios where unprivileged tasks can affect the
* behavior of privileged children.
*/
if (!current->no_new_privs &&
security_capable_noaudit(current_cred(), current_user_ns(),
CAP_SYS_ADMIN) != 0)
return -EACCES;
fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
if (!fp)
return -ENOMEM;
/* Copy the instructions from fprog. */
ret = -EFAULT;
if (copy_from_user(fp, fprog->filter, fp_size))
goto free_prog;
/* Check and rewrite the fprog via the skb checker */
ret = sk_chk_filter(fp, fprog->len);
if (ret)
goto free_prog;
/* Check and rewrite the fprog for seccomp use */
ret = seccomp_check_filter(fp, fprog->len);
if (ret)
goto free_prog;
/* Convert 'sock_filter' insns to 'sock_filter_int' insns */
ret = sk_convert_filter(fp, fprog->len, NULL, &new_len);
if (ret)
goto free_prog;
/* Allocate a new seccomp_filter */
ret = -ENOMEM;
filter = kzalloc(sizeof(struct seccomp_filter) +
sizeof(struct sock_filter_int) * new_len,
GFP_KERNEL|__GFP_NOWARN);
if (!filter)
goto free_prog;
ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
if (ret)
goto free_filter;
kfree(fp);
atomic_set(&filter->usage, 1);
filter->len = new_len;
/*
* If there is an existing filter, make it the prev and don't drop its
* task reference.
*/
filter->prev = current->seccomp.
|