Blame view
kernel/seccomp.c
13.8 KB
1da177e4c
|
1 2 3 4 5 |
/* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * |
e2cfabdfd
|
6 7 8 9 10 11 12 13 |
* 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. |
1da177e4c
|
14 |
*/ |
e2cfabdfd
|
15 |
#include <linux/atomic.h> |
85e7bac33
|
16 |
#include <linux/audit.h> |
5b1017404
|
17 |
#include <linux/compat.h> |
e2cfabdfd
|
18 19 |
#include <linux/sched.h> #include <linux/seccomp.h> |
1da177e4c
|
20 21 |
/* #define SECCOMP_DEBUG 1 */ |
e2cfabdfd
|
22 23 24 25 |
#ifdef CONFIG_SECCOMP_FILTER #include <asm/syscall.h> #include <linux/filter.h> |
fb0fadf9b
|
26 |
#include <linux/ptrace.h> |
e2cfabdfd
|
27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
#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 |
119ce5c8b
|
41 |
* @insnsi: the BPF program instructions to evaluate |
e2cfabdfd
|
42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
* * 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; |
8f577cadf
|
56 |
struct sk_filter *prog; |
e2cfabdfd
|
57 58 59 60 |
}; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) |
bd4cf0ed3
|
61 |
/* |
e2cfabdfd
|
62 63 64 |
* Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ |
bd4cf0ed3
|
65 |
static void populate_seccomp_data(struct seccomp_data *sd) |
e2cfabdfd
|
66 |
{ |
bd4cf0ed3
|
67 68 |
struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); |
2eac76483
|
69 |
unsigned long args[6]; |
e2cfabdfd
|
70 |
|
bd4cf0ed3
|
71 |
sd->nr = syscall_get_nr(task, regs); |
0b747172d
|
72 |
sd->arch = syscall_get_arch(); |
2eac76483
|
73 74 75 76 77 78 79 |
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]; |
bd4cf0ed3
|
80 |
sd->instruction_pointer = KSTK_EIP(task); |
e2cfabdfd
|
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
} /** * 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) { |
348059313
|
104 |
case BPF_LD | BPF_W | BPF_ABS: |
bd4cf0ed3
|
105 |
ftest->code = BPF_LDX | BPF_W | BPF_ABS; |
e2cfabdfd
|
106 107 108 109 |
/* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; |
348059313
|
110 |
case BPF_LD | BPF_W | BPF_LEN: |
bd4cf0ed3
|
111 |
ftest->code = BPF_LD | BPF_IMM; |
e2cfabdfd
|
112 113 |
ftest->k = sizeof(struct seccomp_data); continue; |
348059313
|
114 |
case BPF_LDX | BPF_W | BPF_LEN: |
bd4cf0ed3
|
115 |
ftest->code = BPF_LDX | BPF_IMM; |
e2cfabdfd
|
116 117 118 |
ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ |
348059313
|
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 |
case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: |
e2cfabdfd
|
157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
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; |
bd4cf0ed3
|
174 |
struct seccomp_data sd; |
acf3b2c71
|
175 176 177 178 179 |
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; |
bd4cf0ed3
|
180 |
populate_seccomp_data(&sd); |
e2cfabdfd
|
181 182 |
/* * All filters in the list are evaluated and the lowest BPF return |
acf3b2c71
|
183 |
* value always takes priority (ignoring the DATA). |
e2cfabdfd
|
184 185 |
*/ for (f = current->seccomp.filter; f; f = f->prev) { |
8f577cadf
|
186 |
u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd); |
acf3b2c71
|
187 188 |
if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) ret = cur_ret; |
e2cfabdfd
|
189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 |
} 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; |
bd4cf0ed3
|
204 205 |
struct sock_filter *fp; int new_len; |
e2cfabdfd
|
206 207 208 209 210 211 |
long ret; if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return -EINVAL; for (filter = current->seccomp.filter; filter; filter = filter->prev) |
8f577cadf
|
212 |
total_insns += filter->prog->len + 4; /* include a 4 instr penalty */ |
e2cfabdfd
|
213 214 215 216 |
if (total_insns > MAX_INSNS_PER_PATH) return -ENOMEM; /* |
119ce5c8b
|
217 |
* Installing a seccomp filter requires that the task has |
e2cfabdfd
|
218 219 220 221 222 223 224 225 |
* 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; |
bd4cf0ed3
|
226 227 |
fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN); if (!fp) |
e2cfabdfd
|
228 |
return -ENOMEM; |
e2cfabdfd
|
229 230 231 |
/* Copy the instructions from fprog. */ ret = -EFAULT; |
bd4cf0ed3
|
232 233 |
if (copy_from_user(fp, fprog->filter, fp_size)) goto free_prog; |
e2cfabdfd
|
234 235 |
/* Check and rewrite the fprog via the skb checker */ |
bd4cf0ed3
|
236 |
ret = sk_chk_filter(fp, fprog->len); |
e2cfabdfd
|
237 |
if (ret) |
bd4cf0ed3
|
238 |
goto free_prog; |
e2cfabdfd
|
239 240 |
/* Check and rewrite the fprog for seccomp use */ |
bd4cf0ed3
|
241 242 243 244 245 246 247 248 249 250 |
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 */ |
0acf07d24
|
251 |
ret = -ENOMEM; |
8f577cadf
|
252 |
filter = kzalloc(sizeof(struct seccomp_filter), |
bd4cf0ed3
|
253 254 255 |
GFP_KERNEL|__GFP_NOWARN); if (!filter) goto free_prog; |
8f577cadf
|
256 257 258 |
filter->prog = kzalloc(sk_filter_size(new_len), GFP_KERNEL|__GFP_NOWARN); if (!filter->prog) |
bd4cf0ed3
|
259 |
goto free_filter; |
8f577cadf
|
260 261 262 263 |
ret = sk_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len); if (ret) goto free_filter_prog; |
0acf07d24
|
264 |
kfree(fp); |
bd4cf0ed3
|
265 266 |
atomic_set(&filter->usage, 1); |
8f577cadf
|
267 |
filter->prog->len = new_len; |
8f577cadf
|
268 |
|
5fe821a9d
|
269 |
sk_filter_select_runtime(filter->prog); |
e2cfabdfd
|
270 271 272 273 274 275 276 277 |
/* * If there is an existing filter, make it the prev and don't drop its * task reference. */ filter->prev = current->seccomp.filter; current->seccomp.filter = filter; return 0; |
bd4cf0ed3
|
278 |
|
8f577cadf
|
279 280 |
free_filter_prog: kfree(filter->prog); |
bd4cf0ed3
|
281 |
free_filter: |
e2cfabdfd
|
282 |
kfree(filter); |
bd4cf0ed3
|
283 284 |
free_prog: kfree(fp); |
e2cfabdfd
|
285 286 287 288 289 290 291 292 293 |
return ret; } /** * seccomp_attach_user_filter - attaches a user-supplied sock_fprog * @user_filter: pointer to the user data containing a sock_fprog. * * Returns 0 on success and non-zero otherwise. */ |
864f32a52
|
294 |
static long seccomp_attach_user_filter(char __user *user_filter) |
e2cfabdfd
|
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 |
{ struct sock_fprog fprog; long ret = -EFAULT; #ifdef CONFIG_COMPAT if (is_compat_task()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; fprog.len = fprog32.len; fprog.filter = compat_ptr(fprog32.filter); } else /* falls through to the if below. */ #endif if (copy_from_user(&fprog, user_filter, sizeof(fprog))) goto out; ret = seccomp_attach_filter(&fprog); out: return ret; } /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; /* Reference count is bounded by the number of total processes. */ atomic_inc(&orig->usage); } /* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ void put_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && atomic_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; orig = orig->prev; |
5fe821a9d
|
333 |
sk_filter_free(freeme->prog); |
e2cfabdfd
|
334 335 336 |
kfree(freeme); } } |
bb6ea4301
|
337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 |
/** * seccomp_send_sigsys - signals the task to allow in-process syscall emulation * @syscall: syscall number to send to userland * @reason: filter-supplied reason code to send to userland (via si_errno) * * Forces a SIGSYS with a code of SYS_SECCOMP and related sigsys info. */ static void seccomp_send_sigsys(int syscall, int reason) { struct siginfo info; memset(&info, 0, sizeof(info)); info.si_signo = SIGSYS; info.si_code = SYS_SECCOMP; info.si_call_addr = (void __user *)KSTK_EIP(current); info.si_errno = reason; |
5e937a9ae
|
353 |
info.si_arch = syscall_get_arch(); |
bb6ea4301
|
354 355 356 |
info.si_syscall = syscall; force_sig_info(SIGSYS, &info, current); } |
e2cfabdfd
|
357 |
#endif /* CONFIG_SECCOMP_FILTER */ |
1da177e4c
|
358 359 360 361 362 363 364 365 366 367 |
/* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit * to limit the stack allocations too. */ static int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, 0, /* null terminated */ }; |
5b1017404
|
368 |
#ifdef CONFIG_COMPAT |
1da177e4c
|
369 370 371 372 373 |
static int mode1_syscalls_32[] = { __NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32, 0, /* null terminated */ }; #endif |
acf3b2c71
|
374 |
int __secure_computing(int this_syscall) |
1da177e4c
|
375 376 |
{ int mode = current->seccomp.mode; |
e2cfabdfd
|
377 378 |
int exit_sig = 0; int *syscall; |
8156b451f
|
379 |
u32 ret; |
1da177e4c
|
380 381 |
switch (mode) { |
e2cfabdfd
|
382 |
case SECCOMP_MODE_STRICT: |
1da177e4c
|
383 |
syscall = mode1_syscalls; |
5b1017404
|
384 385 |
#ifdef CONFIG_COMPAT if (is_compat_task()) |
1da177e4c
|
386 387 388 389 |
syscall = mode1_syscalls_32; #endif do { if (*syscall == this_syscall) |
acf3b2c71
|
390 |
return 0; |
1da177e4c
|
391 |
} while (*++syscall); |
e2cfabdfd
|
392 |
exit_sig = SIGKILL; |
8156b451f
|
393 |
ret = SECCOMP_RET_KILL; |
1da177e4c
|
394 |
break; |
e2cfabdfd
|
395 |
#ifdef CONFIG_SECCOMP_FILTER |
8156b451f
|
396 397 |
case SECCOMP_MODE_FILTER: { int data; |
87b526d34
|
398 |
struct pt_regs *regs = task_pt_regs(current); |
acf3b2c71
|
399 400 |
ret = seccomp_run_filters(this_syscall); data = ret & SECCOMP_RET_DATA; |
8156b451f
|
401 402 |
ret &= SECCOMP_RET_ACTION; switch (ret) { |
acf3b2c71
|
403 404 |
case SECCOMP_RET_ERRNO: /* Set the low-order 16-bits as a errno. */ |
87b526d34
|
405 |
syscall_set_return_value(current, regs, |
acf3b2c71
|
406 407 |
-data, 0); goto skip; |
bb6ea4301
|
408 409 |
case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ |
87b526d34
|
410 |
syscall_rollback(current, regs); |
bb6ea4301
|
411 412 413 |
/* Let the filter pass back 16 bits of data. */ seccomp_send_sigsys(this_syscall, data); goto skip; |
fb0fadf9b
|
414 415 |
case SECCOMP_RET_TRACE: /* Skip these calls if there is no tracer. */ |
87b526d34
|
416 417 418 |
if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { syscall_set_return_value(current, regs, -ENOSYS, 0); |
fb0fadf9b
|
419 |
goto skip; |
87b526d34
|
420 |
} |
fb0fadf9b
|
421 422 423 424 425 426 427 428 429 430 |
/* Allow the BPF to provide the event message */ ptrace_event(PTRACE_EVENT_SECCOMP, data); /* * The delivery of a fatal signal during event * notification may silently skip tracer notification. * Terminating the task now avoids executing a system * call that may not be intended. */ if (fatal_signal_pending(current)) break; |
87b526d34
|
431 432 |
if (syscall_get_nr(current, regs) < 0) goto skip; /* Explicit request to skip. */ |
fb0fadf9b
|
433 |
return 0; |
acf3b2c71
|
434 435 436 437 438 439 |
case SECCOMP_RET_ALLOW: return 0; case SECCOMP_RET_KILL: default: break; } |
e2cfabdfd
|
440 441 |
exit_sig = SIGSYS; break; |
8156b451f
|
442 |
} |
e2cfabdfd
|
443 |
#endif |
1da177e4c
|
444 445 446 447 448 449 450 |
default: BUG(); } #ifdef SECCOMP_DEBUG dump_stack(); #endif |
acf3b2c71
|
451 |
audit_seccomp(this_syscall, exit_sig, ret); |
e2cfabdfd
|
452 |
do_exit(exit_sig); |
8156b451f
|
453 |
#ifdef CONFIG_SECCOMP_FILTER |
acf3b2c71
|
454 455 |
skip: audit_seccomp(this_syscall, exit_sig, ret); |
8156b451f
|
456 |
#endif |
acf3b2c71
|
457 |
return -1; |
1da177e4c
|
458 |
} |
1d9d02fee
|
459 460 461 462 463 |
long prctl_get_seccomp(void) { return current->seccomp.mode; } |
e2cfabdfd
|
464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 |
/** * prctl_set_seccomp: configures current->seccomp.mode * @seccomp_mode: requested mode to use * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER * * This function may be called repeatedly with a @seccomp_mode of * SECCOMP_MODE_FILTER to install additional filters. Every filter * successfully installed will be evaluated (in reverse order) for each system * call the task makes. * * Once current->seccomp.mode is non-zero, it may not be changed. * * Returns 0 on success or -EINVAL on failure. */ long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter) |
1d9d02fee
|
479 |
{ |
e2cfabdfd
|
480 |
long ret = -EINVAL; |
1d9d02fee
|
481 |
|
e2cfabdfd
|
482 483 |
if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) |
1d9d02fee
|
484 |
goto out; |
e2cfabdfd
|
485 486 487 |
switch (seccomp_mode) { case SECCOMP_MODE_STRICT: ret = 0; |
cf99abace
|
488 489 490 |
#ifdef TIF_NOTSC disable_TSC(); #endif |
e2cfabdfd
|
491 492 493 494 495 496 497 498 499 500 |
break; #ifdef CONFIG_SECCOMP_FILTER case SECCOMP_MODE_FILTER: ret = seccomp_attach_user_filter(filter); if (ret) goto out; break; #endif default: goto out; |
1d9d02fee
|
501 |
} |
e2cfabdfd
|
502 503 504 |
current->seccomp.mode = seccomp_mode; set_thread_flag(TIF_SECCOMP); out: |
1d9d02fee
|
505 506 |
return ret; } |