Blame view
fs/coredump.c
27.8 KB
b24413180
|
1 |
// SPDX-License-Identifier: GPL-2.0 |
10c28d937
|
2 3 4 |
#include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> |
70d78fe7c
|
5 |
#include <linux/freezer.h> |
10c28d937
|
6 7 8 9 |
#include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> |
315c69261
|
10 |
#include <linux/ctype.h> |
10c28d937
|
11 12 13 14 15 16 17 18 19 |
#include <linux/string.h> #include <linux/init.h> #include <linux/pagemap.h> #include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> |
179899fd5
|
20 |
#include <linux/coredump.h> |
f7ccbae45
|
21 |
#include <linux/sched/coredump.h> |
3f07c0144
|
22 |
#include <linux/sched/signal.h> |
68db0cf10
|
23 |
#include <linux/sched/task_stack.h> |
10c28d937
|
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
#include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> #include <linux/tracehook.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/compat.h> |
378c6520e
|
41 42 |
#include <linux/fs.h> #include <linux/path.h> |
03927c8ac
|
43 |
#include <linux/timekeeping.h> |
10c28d937
|
44 |
|
7c0f6ba68
|
45 |
#include <linux/uaccess.h> |
10c28d937
|
46 47 48 49 50 51 52 53 54 55 |
#include <asm/mmu_context.h> #include <asm/tlb.h> #include <asm/exec.h> #include <trace/events/task.h> #include "internal.h" #include <trace/events/sched.h> int core_uses_pid; |
10c28d937
|
56 |
unsigned int core_pipe_limit; |
3ceadcf6d
|
57 58 |
char core_pattern[CORENAME_MAX_SIZE] = "core"; static int core_name_size = CORENAME_MAX_SIZE; |
10c28d937
|
59 60 61 62 63 |
struct core_name { char *corename; int used, size; }; |
10c28d937
|
64 65 |
/* The maximal length of core_pattern is also specified in sysctl.c */ |
3ceadcf6d
|
66 |
static int expand_corename(struct core_name *cn, int size) |
10c28d937
|
67 |
{ |
e7fd1549a
|
68 |
char *corename = krealloc(cn->corename, size, GFP_KERNEL); |
10c28d937
|
69 |
|
e7fd1549a
|
70 |
if (!corename) |
10c28d937
|
71 |
return -ENOMEM; |
10c28d937
|
72 |
|
3ceadcf6d
|
73 74 75 76 |
if (size > core_name_size) /* racy but harmless */ core_name_size = size; cn->size = ksize(corename); |
e7fd1549a
|
77 |
cn->corename = corename; |
10c28d937
|
78 79 |
return 0; } |
b4176b7c1
|
80 81 |
static __printf(2, 0) int cn_vprintf(struct core_name *cn, const char *fmt, va_list arg) |
10c28d937
|
82 |
{ |
5fe9d8ca2
|
83 |
int free, need; |
404ca80eb
|
84 |
va_list arg_copy; |
10c28d937
|
85 |
|
5fe9d8ca2
|
86 87 |
again: free = cn->size - cn->used; |
404ca80eb
|
88 89 90 91 |
va_copy(arg_copy, arg); need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy); va_end(arg_copy); |
5fe9d8ca2
|
92 93 94 95 |
if (need < free) { cn->used += need; return 0; } |
10c28d937
|
96 |
|
3ceadcf6d
|
97 |
if (!expand_corename(cn, cn->size + need - free + 1)) |
5fe9d8ca2
|
98 |
goto again; |
10c28d937
|
99 |
|
5fe9d8ca2
|
100 |
return -ENOMEM; |
10c28d937
|
101 |
} |
b4176b7c1
|
102 |
static __printf(2, 3) int cn_printf(struct core_name *cn, const char *fmt, ...) |
bc03c691a
|
103 104 105 106 107 108 109 110 111 112 |
{ va_list arg; int ret; va_start(arg, fmt); ret = cn_vprintf(cn, fmt, arg); va_end(arg); return ret; } |
b4176b7c1
|
113 114 |
static __printf(2, 3) int cn_esc_printf(struct core_name *cn, const char *fmt, ...) |
10c28d937
|
115 |
{ |
923bed030
|
116 117 118 119 120 121 122 |
int cur = cn->used; va_list arg; int ret; va_start(arg, fmt); ret = cn_vprintf(cn, fmt, arg); va_end(arg); |
ac94b6e3b
|
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
if (ret == 0) { /* * Ensure that this coredump name component can't cause the * resulting corefile path to consist of a ".." or ".". */ if ((cn->used - cur == 1 && cn->corename[cur] == '.') || (cn->used - cur == 2 && cn->corename[cur] == '.' && cn->corename[cur+1] == '.')) cn->corename[cur] = '!'; /* * Empty names are fishy and could be used to create a "//" in a * corefile name, causing the coredump to happen one directory * level too high. Enforce that all components of the core * pattern are at least one character long. */ if (cn->used == cur) ret = cn_printf(cn, "!"); } |
923bed030
|
142 143 144 145 146 |
for (; cur < cn->used; ++cur) { if (cn->corename[cur] == '/') cn->corename[cur] = '!'; } return ret; |
10c28d937
|
147 |
} |
f38c85f1b
|
148 |
static int cn_print_exe_file(struct core_name *cn, bool name_only) |
10c28d937
|
149 150 |
{ struct file *exe_file; |
f38c85f1b
|
151 |
char *pathbuf, *path, *ptr; |
10c28d937
|
152 153 154 |
int ret; exe_file = get_mm_exe_file(current->mm); |
923bed030
|
155 156 |
if (!exe_file) return cn_esc_printf(cn, "%s (path unknown)", current->comm); |
10c28d937
|
157 |
|
0ee931c4e
|
158 |
pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); |
10c28d937
|
159 160 161 162 |
if (!pathbuf) { ret = -ENOMEM; goto put_exe_file; } |
9bf39ab2a
|
163 |
path = file_path(exe_file, pathbuf, PATH_MAX); |
10c28d937
|
164 165 166 167 |
if (IS_ERR(path)) { ret = PTR_ERR(path); goto free_buf; } |
f38c85f1b
|
168 169 170 171 172 |
if (name_only) { ptr = strrchr(path, '/'); if (ptr) path = ptr + 1; } |
923bed030
|
173 |
ret = cn_esc_printf(cn, "%s", path); |
10c28d937
|
174 175 176 177 178 179 180 181 182 183 184 185 |
free_buf: kfree(pathbuf); put_exe_file: fput(exe_file); return ret; } /* format_corename will inspect the pattern parameter, and output a * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ |
315c69261
|
186 187 |
static int format_corename(struct core_name *cn, struct coredump_params *cprm, size_t **argv, int *argc) |
10c28d937
|
188 189 190 191 |
{ const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); |
315c69261
|
192 |
bool was_space = false; |
10c28d937
|
193 194 |
int pid_in_pattern = 0; int err = 0; |
e7fd1549a
|
195 |
cn->used = 0; |
3ceadcf6d
|
196 197 |
cn->corename = NULL; if (expand_corename(cn, core_name_size)) |
10c28d937
|
198 |
return -ENOMEM; |
888ffc592
|
199 |
cn->corename[0] = '\0'; |
315c69261
|
200 201 202 203 204 205 |
if (ispipe) { int argvs = sizeof(core_pattern) / 2; (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); if (!(*argv)) return -ENOMEM; (*argv)[(*argc)++] = 0; |
888ffc592
|
206 |
++pat_ptr; |
db973a728
|
207 208 |
if (!(*pat_ptr)) return -ENOMEM; |
315c69261
|
209 |
} |
10c28d937
|
210 211 212 213 |
/* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { |
315c69261
|
214 215 216 217 218 219 |
/* * Split on spaces before doing template expansion so that * %e and %E don't get split if they have spaces in them */ if (ispipe) { if (isspace(*pat_ptr)) { |
2bf509d96
|
220 221 |
if (cn->used != 0) was_space = true; |
315c69261
|
222 223 224 225 226 227 228 229 230 231 |
pat_ptr++; continue; } else if (was_space) { was_space = false; err = cn_printf(cn, "%c", '\0'); if (err) return err; (*argv)[(*argc)++] = cn->used; } } |
10c28d937
|
232 |
if (*pat_ptr != '%') { |
10c28d937
|
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 |
err = cn_printf(cn, "%c", *pat_ptr++); } else { switch (*++pat_ptr) { /* single % at the end, drop that */ case 0: goto out; /* Double percent, output one percent */ case '%': err = cn_printf(cn, "%c", '%'); break; /* pid */ case 'p': pid_in_pattern = 1; err = cn_printf(cn, "%d", task_tgid_vnr(current)); break; |
65aafb1e7
|
249 250 251 252 253 |
/* global pid */ case 'P': err = cn_printf(cn, "%d", task_tgid_nr(current)); break; |
b03023ecb
|
254 255 256 257 258 259 260 261 |
case 'i': err = cn_printf(cn, "%d", task_pid_vnr(current)); break; case 'I': err = cn_printf(cn, "%d", task_pid_nr(current)); break; |
10c28d937
|
262 263 |
/* uid */ case 'u': |
5202efe54
|
264 265 266 |
err = cn_printf(cn, "%u", from_kuid(&init_user_ns, cred->uid)); |
10c28d937
|
267 268 269 |
break; /* gid */ case 'g': |
5202efe54
|
270 271 272 |
err = cn_printf(cn, "%u", from_kgid(&init_user_ns, cred->gid)); |
10c28d937
|
273 |
break; |
12a2b4b22
|
274 275 276 277 |
case 'd': err = cn_printf(cn, "%d", __get_dumpable(cprm->mm_flags)); break; |
10c28d937
|
278 279 |
/* signal that caused the coredump */ case 's': |
b4176b7c1
|
280 281 |
err = cn_printf(cn, "%d", cprm->siginfo->si_signo); |
10c28d937
|
282 283 284 |
break; /* UNIX time of coredump */ case 't': { |
03927c8ac
|
285 286 287 288 |
time64_t time; time = ktime_get_real_seconds(); err = cn_printf(cn, "%lld", time); |
10c28d937
|
289 290 291 |
break; } /* hostname */ |
923bed030
|
292 |
case 'h': |
10c28d937
|
293 |
down_read(&uts_sem); |
923bed030
|
294 |
err = cn_esc_printf(cn, "%s", |
10c28d937
|
295 296 |
utsname()->nodename); up_read(&uts_sem); |
10c28d937
|
297 |
break; |
f38c85f1b
|
298 |
/* executable, could be changed by prctl PR_SET_NAME etc */ |
923bed030
|
299 300 |
case 'e': err = cn_esc_printf(cn, "%s", current->comm); |
10c28d937
|
301 |
break; |
f38c85f1b
|
302 303 304 305 |
/* file name of executable */ case 'f': err = cn_print_exe_file(cn, true); break; |
10c28d937
|
306 |
case 'E': |
f38c85f1b
|
307 |
err = cn_print_exe_file(cn, false); |
10c28d937
|
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 |
break; /* core limit size */ case 'c': err = cn_printf(cn, "%lu", rlimit(RLIMIT_CORE)); break; default: break; } ++pat_ptr; } if (err) return err; } |
888ffc592
|
323 |
out: |
10c28d937
|
324 325 326 327 328 329 330 331 332 333 |
/* Backward compatibility with core_uses_pid: * * If core_pattern does not include a %p (as is the default) * and core_uses_pid is set, then .%pid will be appended to * the filename. Do not do this for piped commands. */ if (!ispipe && !pid_in_pattern && core_uses_pid) { err = cn_printf(cn, ".%d", task_tgid_vnr(current)); if (err) return err; } |
10c28d937
|
334 335 |
return ispipe; } |
5fa534c98
|
336 |
static int zap_process(struct task_struct *start, int exit_code, int flags) |
10c28d937
|
337 338 339 |
{ struct task_struct *t; int nr = 0; |
5fa534c98
|
340 341 |
/* ignore all signals except SIGKILL, see prepare_signal() */ start->signal->flags = SIGNAL_GROUP_COREDUMP | flags; |
10c28d937
|
342 343 |
start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; |
d61ba5895
|
344 |
for_each_thread(start, t) { |
10c28d937
|
345 346 347 348 349 350 |
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); if (t != current && t->mm) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; } |
d61ba5895
|
351 |
} |
10c28d937
|
352 353 354 |
return nr; } |
403bad72b
|
355 356 |
static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, struct core_state *core_state, int exit_code) |
10c28d937
|
357 358 359 360 361 362 363 364 |
{ struct task_struct *g, *p; unsigned long flags; int nr = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { mm->core_state = core_state; |
6cd8f0aca
|
365 |
tsk->signal->group_exit_task = tsk; |
5fa534c98
|
366 |
nr = zap_process(tsk, exit_code, 0); |
403bad72b
|
367 |
clear_tsk_thread_flag(tsk, TIF_SIGPENDING); |
10c28d937
|
368 369 370 371 |
} spin_unlock_irq(&tsk->sighand->siglock); if (unlikely(nr < 0)) return nr; |
aed8adb76
|
372 |
tsk->flags |= PF_DUMPCORE; |
10c28d937
|
373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 |
if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* * We should find and kill all tasks which use this mm, and we should * count them correctly into ->nr_threads. We don't take tasklist * lock, but this is safe wrt: * * fork: * None of sub-threads can fork after zap_process(leader). All * processes which were created before this point should be * visible to zap_threads() because copy_process() adds the new * process to the tail of init_task.tasks list, and lock/unlock * of ->siglock provides a memory barrier. * * do_exit: |
c1e8d7c6a
|
388 |
* The caller holds mm->mmap_lock. This means that the task which |
10c28d937
|
389 390 391 392 393 394 395 |
* uses this mm can't pass exit_mm(), so it can't exit or clear * its ->mm. * * de_thread: * It does list_replace_rcu(&leader->tasks, ¤t->tasks), * we must see either old or new leader, this does not matter. * However, it can change p->sighand, so lock_task_sighand(p) |
c1e8d7c6a
|
396 |
* must be used. Since p->mm != NULL and we hold ->mmap_lock |
10c28d937
|
397 398 399 400 401 402 403 404 405 406 407 408 409 410 |
* it can't fail. * * Note also that "g" can be the old leader with ->mm == NULL * and already unhashed and thus removed from ->thread_group. * This is OK, __unhash_process()->list_del_rcu() does not * clear the ->next pointer, we will find the new leader via * next_thread(). */ rcu_read_lock(); for_each_process(g) { if (g == tsk->group_leader) continue; if (g->flags & PF_KTHREAD) continue; |
d61ba5895
|
411 412 413 414 415 416 417 418 419 |
for_each_thread(g, p) { if (unlikely(!p->mm)) continue; if (unlikely(p->mm == mm)) { lock_task_sighand(p, &flags); nr += zap_process(p, exit_code, SIGNAL_GROUP_EXIT); unlock_task_sighand(p, &flags); |
10c28d937
|
420 |
} |
d61ba5895
|
421 422 |
break; } |
10c28d937
|
423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 |
} rcu_read_unlock(); done: atomic_set(&core_state->nr_threads, nr); return nr; } static int coredump_wait(int exit_code, struct core_state *core_state) { struct task_struct *tsk = current; struct mm_struct *mm = tsk->mm; int core_waiters = -EBUSY; init_completion(&core_state->startup); core_state->dumper.task = tsk; core_state->dumper.next = NULL; |
d8ed45c5d
|
439 |
if (mmap_write_lock_killable(mm)) |
4136c26b6
|
440 |
return -EINTR; |
10c28d937
|
441 442 |
if (!mm->core_state) core_waiters = zap_threads(tsk, mm, core_state, exit_code); |
d8ed45c5d
|
443 |
mmap_write_unlock(mm); |
10c28d937
|
444 445 446 |
if (core_waiters > 0) { struct core_thread *ptr; |
70d78fe7c
|
447 |
freezer_do_not_count(); |
10c28d937
|
448 |
wait_for_completion(&core_state->startup); |
70d78fe7c
|
449 |
freezer_count(); |
10c28d937
|
450 451 452 453 454 455 456 457 458 459 460 461 462 463 |
/* * Wait for all the threads to become inactive, so that * all the thread context (extended register state, like * fpu etc) gets copied to the memory. */ ptr = core_state->dumper.next; while (ptr != NULL) { wait_task_inactive(ptr->task, 0); ptr = ptr->next; } } return core_waiters; } |
acdedd99b
|
464 |
static void coredump_finish(struct mm_struct *mm, bool core_dumped) |
10c28d937
|
465 466 467 |
{ struct core_thread *curr, *next; struct task_struct *task; |
6cd8f0aca
|
468 |
spin_lock_irq(¤t->sighand->siglock); |
acdedd99b
|
469 470 |
if (core_dumped && !__fatal_signal_pending(current)) current->signal->group_exit_code |= 0x80; |
6cd8f0aca
|
471 472 473 |
current->signal->group_exit_task = NULL; current->signal->flags = SIGNAL_GROUP_EXIT; spin_unlock_irq(¤t->sighand->siglock); |
10c28d937
|
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 |
next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; task = curr->task; /* * see exit_mm(), curr->task must not see * ->task == NULL before we read ->next. */ smp_mb(); curr->task = NULL; wake_up_process(task); } mm->core_state = NULL; } |
528f827ee
|
489 490 491 492 493 494 495 496 497 498 |
static bool dump_interrupted(void) { /* * SIGKILL or freezing() interrupt the coredumping. Perhaps we * can do try_to_freeze() and check __fatal_signal_pending(), * but then we need to teach dump_write() to restart and clear * TIF_SIGPENDING. */ return signal_pending(current); } |
10c28d937
|
499 500 |
static void wait_for_dump_helpers(struct file *file) { |
de32ec4cf
|
501 |
struct pipe_inode_info *pipe = file->private_data; |
10c28d937
|
502 503 504 505 |
pipe_lock(pipe); pipe->readers++; pipe->writers--; |
0ddad21d3
|
506 |
wake_up_interruptible_sync(&pipe->rd_wait); |
dc7ee2aac
|
507 508 |
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); pipe_unlock(pipe); |
10c28d937
|
509 |
|
dc7ee2aac
|
510 511 512 513 |
/* * We actually want wait_event_freezable() but then we need * to clear TIF_SIGPENDING and improve dump_interrupted(). */ |
0ddad21d3
|
514 |
wait_event_interruptible(pipe->rd_wait, pipe->readers == 1); |
10c28d937
|
515 |
|
dc7ee2aac
|
516 |
pipe_lock(pipe); |
10c28d937
|
517 518 519 |
pipe->readers--; pipe->writers++; pipe_unlock(pipe); |
10c28d937
|
520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 |
} /* * umh_pipe_setup * helper function to customize the process used * to collect the core in userspace. Specifically * it sets up a pipe and installs it as fd 0 (stdin) * for the process. Returns 0 on success, or * PTR_ERR on failure. * Note that it also sets the core limit to 1. This * is a special value that we use to trap recursive * core dumps */ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) { struct file *files[2]; struct coredump_params *cp = (struct coredump_params *)info->data; int err = create_pipe_files(files, 0); if (err) return err; cp->file = files[1]; |
45525b26a
|
542 543 |
err = replace_fd(0, files[0], 0); fput(files[0]); |
10c28d937
|
544 545 |
/* and disallow core files too */ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1}; |
45525b26a
|
546 |
return err; |
10c28d937
|
547 |
} |
ae7795bc6
|
548 |
void do_coredump(const kernel_siginfo_t *siginfo) |
10c28d937
|
549 550 551 552 553 554 555 556 |
{ struct core_state core_state; struct core_name cn; struct mm_struct *mm = current->mm; struct linux_binfmt * binfmt; const struct cred *old_cred; struct cred *cred; int retval = 0; |
10c28d937
|
557 |
int ispipe; |
315c69261
|
558 559 |
size_t *argv = NULL; int argc = 0; |
10c28d937
|
560 |
struct files_struct *displaced; |
fbb181694
|
561 562 |
/* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; |
acdedd99b
|
563 |
bool core_dumped = false; |
10c28d937
|
564 565 |
static atomic_t core_dump_count = ATOMIC_INIT(0); struct coredump_params cprm = { |
5ab1c309b
|
566 |
.siginfo = siginfo, |
541880d9a
|
567 |
.regs = signal_pt_regs(), |
10c28d937
|
568 569 570 571 572 573 574 575 |
.limit = rlimit(RLIMIT_CORE), /* * We must use the same mm->flags while dumping core to avoid * inconsistency of bit flags, since this flag is not protected * by any locks. */ .mm_flags = mm->flags, }; |
5ab1c309b
|
576 |
audit_core_dumps(siginfo->si_signo); |
10c28d937
|
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 |
binfmt = mm->binfmt; if (!binfmt || !binfmt->core_dump) goto fail; if (!__get_dumpable(cprm.mm_flags)) goto fail; cred = prepare_creds(); if (!cred) goto fail; /* * We cannot trust fsuid as being the "true" uid of the process * nor do we know its entire history. We only know it was tainted * so we dump it as root in mode 2, and only into a controlled * environment (pipe handler or fully qualified path). */ |
e579d2c25
|
593 |
if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) { |
10c28d937
|
594 |
/* Setuid core dump mode */ |
10c28d937
|
595 |
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ |
fbb181694
|
596 |
need_suid_safe = true; |
10c28d937
|
597 |
} |
5ab1c309b
|
598 |
retval = coredump_wait(siginfo->si_signo, &core_state); |
10c28d937
|
599 600 601 602 |
if (retval < 0) goto fail_creds; old_cred = override_creds(cred); |
315c69261
|
603 |
ispipe = format_corename(&cn, &cprm, &argv, &argc); |
10c28d937
|
604 |
|
fb96c475f
|
605 |
if (ispipe) { |
315c69261
|
606 |
int argi; |
10c28d937
|
607 608 |
int dump_count; char **helper_argv; |
907ed1328
|
609 |
struct subprocess_info *sub_info; |
10c28d937
|
610 611 612 613 614 615 |
if (ispipe < 0) { printk(KERN_WARNING "format_corename failed "); printk(KERN_WARNING "Aborting core "); |
e7fd1549a
|
616 |
goto fail_unlock; |
10c28d937
|
617 618 619 620 621 622 623 |
} if (cprm.limit == 1) { /* See umh_pipe_setup() which sets RLIMIT_CORE = 1. * * Normally core limits are irrelevant to pipes, since * we're not writing to the file system, but we use |
fcbc32bc6
|
624 |
* cprm.limit of 1 here as a special value, this is a |
10c28d937
|
625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 |
* consistent way to catch recursive crashes. * We can still crash if the core_pattern binary sets * RLIM_CORE = !1, but it runs as root, and can do * lots of stupid things. * * Note that we use task_tgid_vnr here to grab the pid * of the process group leader. That way we get the * right pid if a thread in a multi-threaded * core_pattern process dies. */ printk(KERN_WARNING "Process %d(%s) has RLIMIT_CORE set to 1 ", task_tgid_vnr(current), current->comm); printk(KERN_WARNING "Aborting core "); goto fail_unlock; } cprm.limit = RLIM_INFINITY; dump_count = atomic_inc_return(&core_dump_count); if (core_pipe_limit && (core_pipe_limit < dump_count)) { printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit ", task_tgid_vnr(current), current->comm); printk(KERN_WARNING "Skipping core dump "); goto fail_dropcount; } |
315c69261
|
654 655 |
helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), GFP_KERNEL); |
10c28d937
|
656 657 658 659 660 661 |
if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory ", __func__); goto fail_dropcount; } |
315c69261
|
662 663 664 |
for (argi = 0; argi < argc; argi++) helper_argv[argi] = cn.corename + argv[argi]; helper_argv[argi] = NULL; |
10c28d937
|
665 |
|
907ed1328
|
666 667 668 669 670 671 672 |
retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], helper_argv, NULL, GFP_KERNEL, umh_pipe_setup, NULL, &cprm); if (sub_info) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); |
315c69261
|
673 |
kfree(helper_argv); |
10c28d937
|
674 |
if (retval) { |
888ffc592
|
675 676 |
printk(KERN_INFO "Core dump to |%s pipe failed ", |
10c28d937
|
677 678 |
cn.corename); goto close_fail; |
fb96c475f
|
679 |
} |
10c28d937
|
680 681 |
} else { struct inode *inode; |
378c6520e
|
682 683 |
int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW | O_LARGEFILE | O_EXCL; |
10c28d937
|
684 685 686 |
if (cprm.limit < binfmt->min_coredump) goto fail_unlock; |
fbb181694
|
687 |
if (need_suid_safe && cn.corename[0] != '/') { |
10c28d937
|
688 689 690 691 692 693 694 695 |
printk(KERN_WARNING "Pid %d(%s) can only dump core "\ "to fully qualified path! ", task_tgid_vnr(current), current->comm); printk(KERN_WARNING "Skipping core dump "); goto fail_unlock; } |
fbb181694
|
696 697 698 699 700 701 |
/* * Unlink the file if it exists unless this is a SUID * binary - in that case, we're running around with root * privs and don't want to unlink another user's coredump. */ if (!need_suid_safe) { |
fbb181694
|
702 703 704 705 |
/* * If it doesn't exist, that's fine. If there's some * other problem, we'll catch it at the filp_open(). */ |
96271654f
|
706 |
do_unlinkat(AT_FDCWD, getname_kernel(cn.corename)); |
fbb181694
|
707 708 709 710 711 712 713 714 715 716 |
} /* * There is a race between unlinking and creating the * file, but if that causes an EEXIST here, that's * fine - another process raced with us while creating * the corefile, and the other process won. To userspace, * what matters is that at least one of the two processes * writes its coredump successfully, not which one. */ |
378c6520e
|
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 |
if (need_suid_safe) { /* * Using user namespaces, normal user tasks can change * their current->fs->root to point to arbitrary * directories. Since the intention of the "only dump * with a fully qualified path" rule is to control where * coredumps may be placed using root privileges, * current->fs->root must not be used. Instead, use the * root directory of init_task. */ struct path root; task_lock(&init_task); get_fs_root(init_task.fs, &root); task_unlock(&init_task); cprm.file = file_open_root(root.dentry, root.mnt, cn.corename, open_flags, 0600); path_put(&root); } else { cprm.file = filp_open(cn.corename, open_flags, 0600); } |
10c28d937
|
738 739 |
if (IS_ERR(cprm.file)) goto fail_unlock; |
496ad9aa8
|
740 |
inode = file_inode(cprm.file); |
10c28d937
|
741 742 743 744 745 746 747 748 749 750 751 |
if (inode->i_nlink > 1) goto close_fail; if (d_unhashed(cprm.file->f_path.dentry)) goto close_fail; /* * AK: actually i see no reason to not allow this for named * pipes etc, but keep the previous behaviour for now. */ if (!S_ISREG(inode->i_mode)) goto close_fail; /* |
40f705a73
|
752 753 754 755 |
* Don't dump core if the filesystem changed owner or mode * of the file during file creation. This is an issue when * a process dumps core while its cwd is e.g. on a vfat * filesystem. |
10c28d937
|
756 757 758 |
*/ if (!uid_eq(inode->i_uid, current_fsuid())) goto close_fail; |
40f705a73
|
759 760 |
if ((inode->i_mode & 0677) != 0600) goto close_fail; |
86cc05840
|
761 |
if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) |
10c28d937
|
762 763 764 765 766 767 768 769 770 771 772 |
goto close_fail; if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; } /* get us an unshared descriptor table; almost always a no-op */ retval = unshare_files(&displaced); if (retval) goto close_fail; if (displaced) put_files_struct(displaced); |
e86d35c38
|
773 |
if (!dump_interrupted()) { |
3740d93e3
|
774 775 776 777 778 779 780 781 782 |
/* * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would * have this set to NULL. */ if (!cprm.file) { pr_info("Core dump to |%s disabled ", cn.corename); goto close_fail; } |
e86d35c38
|
783 784 785 786 |
file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); } |
10c28d937
|
787 788 789 790 791 792 793 794 795 |
if (ispipe && core_pipe_limit) wait_for_dump_helpers(cprm.file); close_fail: if (cprm.file) filp_close(cprm.file, NULL); fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: |
315c69261
|
796 |
kfree(argv); |
10c28d937
|
797 |
kfree(cn.corename); |
acdedd99b
|
798 |
coredump_finish(mm, core_dumped); |
10c28d937
|
799 800 801 802 803 804 805 806 807 808 809 810 |
revert_creds(old_cred); fail_creds: put_cred(cred); fail: return; } /* * Core dumping helper functions. These are the only things you should * do on a core-file: use only these functions to write out all the * necessary info. */ |
ecc8c7725
|
811 812 813 |
int dump_emit(struct coredump_params *cprm, const void *addr, int nr) { struct file *file = cprm->file; |
2507a4fbd
|
814 815 |
loff_t pos = file->f_pos; ssize_t n; |
2c4cb0430
|
816 |
if (cprm->written + nr > cprm->limit) |
ecc8c7725
|
817 |
return 0; |
df0c09c01
|
818 819 820 821 822 823 824 825 826 827 |
if (dump_interrupted()) return 0; n = __kernel_write(file, addr, nr, &pos); if (n != nr) return 0; file->f_pos = pos; cprm->written += n; cprm->pos += n; |
ecc8c7725
|
828 829 830 |
return 1; } EXPORT_SYMBOL(dump_emit); |
9b56d5438
|
831 |
int dump_skip(struct coredump_params *cprm, size_t nr) |
10c28d937
|
832 |
{ |
9b56d5438
|
833 834 |
static char zeroes[PAGE_SIZE]; struct file *file = cprm->file; |
10c28d937
|
835 |
if (file->f_op->llseek && file->f_op->llseek != no_llseek) { |
528f827ee
|
836 |
if (dump_interrupted() || |
9b56d5438
|
837 |
file->f_op->llseek(file, nr, SEEK_CUR) < 0) |
10c28d937
|
838 |
return 0; |
1607f09c2
|
839 |
cprm->pos += nr; |
9b56d5438
|
840 |
return 1; |
10c28d937
|
841 |
} else { |
9b56d5438
|
842 843 844 845 |
while (nr > PAGE_SIZE) { if (!dump_emit(cprm, zeroes, PAGE_SIZE)) return 0; nr -= PAGE_SIZE; |
10c28d937
|
846 |
} |
9b56d5438
|
847 |
return dump_emit(cprm, zeroes, nr); |
10c28d937
|
848 |
} |
10c28d937
|
849 |
} |
9b56d5438
|
850 |
EXPORT_SYMBOL(dump_skip); |
22a8cb824
|
851 |
|
afc63a97b
|
852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 |
#ifdef CONFIG_ELF_CORE int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len) { unsigned long addr; for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page; int stop; /* * To avoid having to allocate page tables for virtual address * ranges that have never been used yet, and also to make it * easy to generate sparse core files, use a helper that returns * NULL when encountering an empty page table entry that would * otherwise have been filled with the zero page. */ page = get_dump_page(addr); if (page) { void *kaddr = kmap(page); stop = !dump_emit(cprm, kaddr, PAGE_SIZE); kunmap(page); put_page(page); } else { stop = !dump_skip(cprm, PAGE_SIZE); } if (stop) return 0; } return 1; } #endif |
22a8cb824
|
885 886 |
int dump_align(struct coredump_params *cprm, int align) { |
1607f09c2
|
887 |
unsigned mod = cprm->pos & (align - 1); |
22a8cb824
|
888 |
if (align & (align - 1)) |
db51242d8
|
889 890 |
return 0; return mod ? dump_skip(cprm, align - mod) : 1; |
22a8cb824
|
891 892 |
} EXPORT_SYMBOL(dump_align); |
4d22c75d4
|
893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 |
/* * Ensures that file size is big enough to contain the current file * postion. This prevents gdb from complaining about a truncated file * if the last "write" to the file was dump_skip. */ void dump_truncate(struct coredump_params *cprm) { struct file *file = cprm->file; loff_t offset; if (file->f_op->llseek && file->f_op->llseek != no_llseek) { offset = file->f_op->llseek(file, 0, SEEK_CUR); if (i_size_read(file->f_mapping->host) < offset) do_truncate(file->f_path.dentry, offset, 0, file); } } EXPORT_SYMBOL(dump_truncate); |
429a22e77
|
911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 |
/* * The purpose of always_dump_vma() is to make sure that special kernel mappings * that are useful for post-mortem analysis are included in every core dump. * In that way we ensure that the core dump is fully interpretable later * without matching up the same kernel and hardware config to see what PC values * meant. These special mappings include - vDSO, vsyscall, and other * architecture specific mappings */ static bool always_dump_vma(struct vm_area_struct *vma) { /* Any vsyscall mappings? */ if (vma == get_gate_vma(vma->vm_mm)) return true; /* * Assume that all vmas with a .name op should always be dumped. * If this changes, a new vm_ops field can easily be added. */ if (vma->vm_ops && vma->vm_ops->name && vma->vm_ops->name(vma)) return true; /* * arch_vma_name() returns non-NULL for special architecture mappings, * such as vDSO sections. */ if (arch_vma_name(vma)) return true; return false; } /* * Decide how much of @vma's contents should be included in a core dump. */ |
a07279c9a
|
946 947 |
static unsigned long vma_dump_size(struct vm_area_struct *vma, unsigned long mm_flags) |
429a22e77
|
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 |
{ #define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type)) /* always dump the vdso and vsyscall sections */ if (always_dump_vma(vma)) goto whole; if (vma->vm_flags & VM_DONTDUMP) return 0; /* support for DAX */ if (vma_is_dax(vma)) { if ((vma->vm_flags & VM_SHARED) && FILTER(DAX_SHARED)) goto whole; if (!(vma->vm_flags & VM_SHARED) && FILTER(DAX_PRIVATE)) goto whole; return 0; } /* Hugetlb memory check */ if (is_vm_hugetlb_page(vma)) { if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED)) goto whole; if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE)) goto whole; return 0; } /* Do not dump I/O mapped devices or special mappings */ if (vma->vm_flags & VM_IO) return 0; /* By default, dump shared memory if mapped from an anonymous file. */ if (vma->vm_flags & VM_SHARED) { if (file_inode(vma->vm_file)->i_nlink == 0 ? FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED)) goto whole; return 0; } /* Dump segments that have been written to. */ if ((!IS_ENABLED(CONFIG_MMU) || vma->anon_vma) && FILTER(ANON_PRIVATE)) goto whole; if (vma->vm_file == NULL) return 0; if (FILTER(MAPPED_PRIVATE)) goto whole; /* * If this is the beginning of an executable file mapping, * dump the first page to aid in determining what was mapped here. */ if (FILTER(ELF_HEADERS) && vma->vm_pgoff == 0 && (vma->vm_flags & VM_READ) && (READ_ONCE(file_inode(vma->vm_file)->i_mode) & 0111) != 0) return PAGE_SIZE; #undef FILTER return 0; whole: return vma->vm_end - vma->vm_start; } |
a07279c9a
|
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 |
static struct vm_area_struct *first_vma(struct task_struct *tsk, struct vm_area_struct *gate_vma) { struct vm_area_struct *ret = tsk->mm->mmap; if (ret) return ret; return gate_vma; } /* * Helper function for iterating across a vma list. It ensures that the caller * will visit `gate_vma' prior to terminating the search. */ static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma, struct vm_area_struct *gate_vma) { struct vm_area_struct *ret; ret = this_vma->vm_next; if (ret) return ret; if (this_vma == gate_vma) return NULL; return gate_vma; } /* * Under the mmap_lock, take a snapshot of relevant information about the task's * VMAs. */ int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count, struct core_vma_metadata **vma_meta, size_t *vma_data_size_ptr) { struct vm_area_struct *vma, *gate_vma; struct mm_struct *mm = current->mm; int i; size_t vma_data_size = 0; /* * Once the stack expansion code is fixed to not change VMA bounds * under mmap_lock in read mode, this can be changed to take the * mmap_lock in read mode. */ if (mmap_write_lock_killable(mm)) return -EINTR; gate_vma = get_gate_vma(mm); *vma_count = mm->map_count + (gate_vma ? 1 : 0); *vma_meta = kvmalloc_array(*vma_count, sizeof(**vma_meta), GFP_KERNEL); if (!*vma_meta) { mmap_write_unlock(mm); return -ENOMEM; } for (i = 0, vma = first_vma(current, gate_vma); vma != NULL; vma = next_vma(vma, gate_vma), i++) { struct core_vma_metadata *m = (*vma_meta) + i; m->start = vma->vm_start; m->end = vma->vm_end; m->flags = vma->vm_flags; m->dump_size = vma_dump_size(vma, cprm->mm_flags); vma_data_size += m->dump_size; } mmap_write_unlock(mm); if (WARN_ON(i != *vma_count)) return -EFAULT; *vma_data_size_ptr = vma_data_size; return 0; } |