forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
coredump.c
1197 lines (1060 loc) · 29.2 KB
/
coredump.c
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
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
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
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
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
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
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
946
947
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
// SPDX-License-Identifier: GPL-2.0
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/freezer.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
#include <linux/ctype.h>
#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>
#include <linux/coredump.h>
#include <linux/sched/coredump.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#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/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>
#include <linux/fs.h>
#include <linux/path.h>
#include <linux/timekeeping.h>
#include <linux/sysctl.h>
#include <linux/elf.h>
#include <linux/uaccess.h>
#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>
static bool dump_vma_snapshot(struct coredump_params *cprm);
static void free_vma_snapshot(struct coredump_params *cprm);
static int core_uses_pid;
static unsigned int core_pipe_limit;
static char core_pattern[CORENAME_MAX_SIZE] = "core";
static int core_name_size = CORENAME_MAX_SIZE;
struct core_name {
char *corename;
int used, size;
};
static int expand_corename(struct core_name *cn, int size)
{
char *corename = krealloc(cn->corename, size, GFP_KERNEL);
if (!corename)
return -ENOMEM;
if (size > core_name_size) /* racy but harmless */
core_name_size = size;
cn->size = ksize(corename);
cn->corename = corename;
return 0;
}
static __printf(2, 0) int cn_vprintf(struct core_name *cn, const char *fmt,
va_list arg)
{
int free, need;
va_list arg_copy;
again:
free = cn->size - cn->used;
va_copy(arg_copy, arg);
need = vsnprintf(cn->corename + cn->used, free, fmt, arg_copy);
va_end(arg_copy);
if (need < free) {
cn->used += need;
return 0;
}
if (!expand_corename(cn, cn->size + need - free + 1))
goto again;
return -ENOMEM;
}
static __printf(2, 3) int cn_printf(struct core_name *cn, const char *fmt, ...)
{
va_list arg;
int ret;
va_start(arg, fmt);
ret = cn_vprintf(cn, fmt, arg);
va_end(arg);
return ret;
}
static __printf(2, 3)
int cn_esc_printf(struct core_name *cn, const char *fmt, ...)
{
int cur = cn->used;
va_list arg;
int ret;
va_start(arg, fmt);
ret = cn_vprintf(cn, fmt, arg);
va_end(arg);
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, "!");
}
for (; cur < cn->used; ++cur) {
if (cn->corename[cur] == '/')
cn->corename[cur] = '!';
}
return ret;
}
static int cn_print_exe_file(struct core_name *cn, bool name_only)
{
struct file *exe_file;
char *pathbuf, *path, *ptr;
int ret;
exe_file = get_mm_exe_file(current->mm);
if (!exe_file)
return cn_esc_printf(cn, "%s (path unknown)", current->comm);
pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
if (!pathbuf) {
ret = -ENOMEM;
goto put_exe_file;
}
path = file_path(exe_file, pathbuf, PATH_MAX);
if (IS_ERR(path)) {
ret = PTR_ERR(path);
goto free_buf;
}
if (name_only) {
ptr = strrchr(path, '/');
if (ptr)
path = ptr + 1;
}
ret = cn_esc_printf(cn, "%s", path);
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.
*/
static int format_corename(struct core_name *cn, struct coredump_params *cprm,
size_t **argv, int *argc)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
bool was_space = false;
int pid_in_pattern = 0;
int err = 0;
cn->used = 0;
cn->corename = NULL;
if (expand_corename(cn, core_name_size))
return -ENOMEM;
cn->corename[0] = '\0';
if (ispipe) {
int argvs = sizeof(core_pattern) / 2;
(*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL);
if (!(*argv))
return -ENOMEM;
(*argv)[(*argc)++] = 0;
++pat_ptr;
if (!(*pat_ptr))
return -ENOMEM;
}
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
/*
* 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)) {
if (cn->used != 0)
was_space = true;
pat_ptr++;
continue;
} else if (was_space) {
was_space = false;
err = cn_printf(cn, "%c", '\0');
if (err)
return err;
(*argv)[(*argc)++] = cn->used;
}
}
if (*pat_ptr != '%') {
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;
/* global pid */
case 'P':
err = cn_printf(cn, "%d",
task_tgid_nr(current));
break;
case 'i':
err = cn_printf(cn, "%d",
task_pid_vnr(current));
break;
case 'I':
err = cn_printf(cn, "%d",
task_pid_nr(current));
break;
/* uid */
case 'u':
err = cn_printf(cn, "%u",
from_kuid(&init_user_ns,
cred->uid));
break;
/* gid */
case 'g':
err = cn_printf(cn, "%u",
from_kgid(&init_user_ns,
cred->gid));
break;
case 'd':
err = cn_printf(cn, "%d",
__get_dumpable(cprm->mm_flags));
break;
/* signal that caused the coredump */
case 's':
err = cn_printf(cn, "%d",
cprm->siginfo->si_signo);
break;
/* UNIX time of coredump */
case 't': {
time64_t time;
time = ktime_get_real_seconds();
err = cn_printf(cn, "%lld", time);
break;
}
/* hostname */
case 'h':
down_read(&uts_sem);
err = cn_esc_printf(cn, "%s",
utsname()->nodename);
up_read(&uts_sem);
break;
/* executable, could be changed by prctl PR_SET_NAME etc */
case 'e':
err = cn_esc_printf(cn, "%s", current->comm);
break;
/* file name of executable */
case 'f':
err = cn_print_exe_file(cn, true);
break;
case 'E':
err = cn_print_exe_file(cn, false);
break;
/* core limit size */
case 'c':
err = cn_printf(cn, "%lu",
rlimit(RLIMIT_CORE));
break;
default:
break;
}
++pat_ptr;
}
if (err)
return err;
}
out:
/* 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;
}
return ispipe;
}
static int zap_process(struct task_struct *start, int exit_code)
{
struct task_struct *t;
int nr = 0;
/* Allow SIGKILL, see prepare_signal() */
start->signal->flags = SIGNAL_GROUP_EXIT;
start->signal->group_exit_code = exit_code;
start->signal->group_stop_count = 0;
for_each_thread(start, t) {
task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
if (t != current && !(t->flags & PF_POSTCOREDUMP)) {
sigaddset(&t->pending.signal, SIGKILL);
signal_wake_up(t, 1);
nr++;
}
}
return nr;
}
static int zap_threads(struct task_struct *tsk,
struct core_state *core_state, int exit_code)
{
struct signal_struct *signal = tsk->signal;
int nr = -EAGAIN;
spin_lock_irq(&tsk->sighand->siglock);
if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) {
signal->core_state = core_state;
nr = zap_process(tsk, exit_code);
clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
tsk->flags |= PF_DUMPCORE;
atomic_set(&core_state->nr_threads, nr);
}
spin_unlock_irq(&tsk->sighand->siglock);
return nr;
}
static int coredump_wait(int exit_code, struct core_state *core_state)
{
struct task_struct *tsk = current;
int core_waiters = -EBUSY;
init_completion(&core_state->startup);
core_state->dumper.task = tsk;
core_state->dumper.next = NULL;
core_waiters = zap_threads(tsk, core_state, exit_code);
if (core_waiters > 0) {
struct core_thread *ptr;
wait_for_completion_state(&core_state->startup,
TASK_UNINTERRUPTIBLE|TASK_FREEZABLE);
/*
* 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, TASK_ANY);
ptr = ptr->next;
}
}
return core_waiters;
}
static void coredump_finish(bool core_dumped)
{
struct core_thread *curr, *next;
struct task_struct *task;
spin_lock_irq(¤t->sighand->siglock);
if (core_dumped && !__fatal_signal_pending(current))
current->signal->group_exit_code |= 0x80;
next = current->signal->core_state->dumper.next;
current->signal->core_state = NULL;
spin_unlock_irq(¤t->sighand->siglock);
while ((curr = next) != NULL) {
next = curr->next;
task = curr->task;
/*
* see coredump_task_exit(), curr->task must not see
* ->task == NULL before we read ->next.
*/
smp_mb();
curr->task = NULL;
wake_up_process(task);
}
}
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 fatal_signal_pending(current) || freezing(current);
}
static void wait_for_dump_helpers(struct file *file)
{
struct pipe_inode_info *pipe = file->private_data;
pipe_lock(pipe);
pipe->readers++;
pipe->writers--;
wake_up_interruptible_sync(&pipe->rd_wait);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
pipe_unlock(pipe);
/*
* We actually want wait_event_freezable() but then we need
* to clear TIF_SIGPENDING and improve dump_interrupted().
*/
wait_event_interruptible(pipe->rd_wait, pipe->readers == 1);
pipe_lock(pipe);
pipe->readers--;
pipe->writers++;
pipe_unlock(pipe);
}
/*
* 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];
err = replace_fd(0, files[0], 0);
fput(files[0]);
/* and disallow core files too */
current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
return err;
}
void do_coredump(const kernel_siginfo_t *siginfo)
{
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;
int ispipe;
size_t *argv = NULL;
int argc = 0;
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
bool core_dumped = false;
static atomic_t core_dump_count = ATOMIC_INIT(0);
struct coredump_params cprm = {
.siginfo = siginfo,
.regs = signal_pt_regs(),
.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,
.vma_meta = NULL,
};
audit_core_dumps(siginfo->si_signo);
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).
*/
if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {
/* Setuid core dump mode */
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */
need_suid_safe = true;
}
retval = coredump_wait(siginfo->si_signo, &core_state);
if (retval < 0)
goto fail_creds;
old_cred = override_creds(cred);
ispipe = format_corename(&cn, &cprm, &argv, &argc);
if (ispipe) {
int argi;
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
if (ispipe < 0) {
printk(KERN_WARNING "format_corename failed\n");
printk(KERN_WARNING "Aborting core\n");
goto fail_unlock;
}
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
* cprm.limit of 1 here as a special value, this is a
* 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\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Aborting core\n");
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\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_dropcount;
}
helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
GFP_KERNEL);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
for (argi = 0; argi < argc; argi++)
helper_argv[argi] = cn.corename + argv[argi];
helper_argv[argi] = NULL;
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);
kfree(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
goto close_fail;
}
} else {
struct user_namespace *mnt_userns;
struct inode *inode;
int open_flags = O_CREAT | O_RDWR | O_NOFOLLOW |
O_LARGEFILE | O_EXCL;
if (cprm.limit < binfmt->min_coredump)
goto fail_unlock;
if (need_suid_safe && cn.corename[0] != '/') {
printk(KERN_WARNING "Pid %d(%s) can only dump core "\
"to fully qualified path!\n",
task_tgid_vnr(current), current->comm);
printk(KERN_WARNING "Skipping core dump\n");
goto fail_unlock;
}
/*
* 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) {
/*
* If it doesn't exist, that's fine. If there's some
* other problem, we'll catch it at the filp_open().
*/
do_unlinkat(AT_FDCWD, getname_kernel(cn.corename));
}
/*
* 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.
*/
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, cn.corename,
open_flags, 0600);
path_put(&root);
} else {
cprm.file = filp_open(cn.corename, open_flags, 0600);
}
if (IS_ERR(cprm.file))
goto fail_unlock;
inode = file_inode(cprm.file);
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;
/*
* 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.
*/
mnt_userns = file_mnt_user_ns(cprm.file);
if (!uid_eq(i_uid_into_mnt(mnt_userns, inode),
current_fsuid())) {
pr_info_ratelimited("Core dump to %s aborted: cannot preserve file owner\n",
cn.corename);
goto close_fail;
}
if ((inode->i_mode & 0677) != 0600) {
pr_info_ratelimited("Core dump to %s aborted: cannot preserve file permissions\n",
cn.corename);
goto close_fail;
}
if (!(cprm.file->f_mode & FMODE_CAN_WRITE))
goto close_fail;
if (do_truncate(mnt_userns, cprm.file->f_path.dentry,
0, 0, cprm.file))
goto close_fail;
}
/* get us an unshared descriptor table; almost always a no-op */
/* The cell spufs coredump code reads the file descriptor tables */
retval = unshare_files();
if (retval)
goto close_fail;
if (!dump_interrupted()) {
/*
* umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
* have this set to NULL.
*/
if (!cprm.file) {
pr_info("Core dump to |%s disabled\n", cn.corename);
goto close_fail;
}
if (!dump_vma_snapshot(&cprm))
goto close_fail;
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);
/*
* 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.
*/
if (cprm.to_skip) {
cprm.to_skip--;
dump_emit(&cprm, "", 1);
}
file_end_write(cprm.file);
free_vma_snapshot(&cprm);
}
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:
kfree(argv);
kfree(cn.corename);
coredump_finish(core_dumped);
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.
*/
static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
struct file *file = cprm->file;
loff_t pos = file->f_pos;
ssize_t n;
if (cprm->written + nr > cprm->limit)
return 0;
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;
return 1;
}
static int __dump_skip(struct coredump_params *cprm, size_t nr)
{
static char zeroes[PAGE_SIZE];
struct file *file = cprm->file;
if (file->f_mode & FMODE_LSEEK) {
if (dump_interrupted() ||
vfs_llseek(file, nr, SEEK_CUR) < 0)
return 0;
cprm->pos += nr;
return 1;
} else {
while (nr > PAGE_SIZE) {
if (!__dump_emit(cprm, zeroes, PAGE_SIZE))
return 0;
nr -= PAGE_SIZE;
}
return __dump_emit(cprm, zeroes, nr);
}
}
static int dump_emit_page(struct coredump_params *cprm, struct page *page)
{
struct bio_vec bvec = {
.bv_page = page,
.bv_offset = 0,
.bv_len = PAGE_SIZE,
};
struct iov_iter iter;
struct file *file = cprm->file;
loff_t pos;
ssize_t n;
if (cprm->to_skip) {
if (!__dump_skip(cprm, cprm->to_skip))
return 0;
cprm->to_skip = 0;
}
if (cprm->written + PAGE_SIZE > cprm->limit)
return 0;
if (dump_interrupted())
return 0;
pos = file->f_pos;
iov_iter_bvec(&iter, WRITE, &bvec, 1, PAGE_SIZE);
n = __kernel_write_iter(cprm->file, &iter, &pos);
if (n != PAGE_SIZE)
return 0;
file->f_pos = pos;
cprm->written += PAGE_SIZE;
cprm->pos += PAGE_SIZE;
return 1;
}
int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
{
if (cprm->to_skip) {
if (!__dump_skip(cprm, cprm->to_skip))
return 0;
cprm->to_skip = 0;
}
return __dump_emit(cprm, addr, nr);
}
EXPORT_SYMBOL(dump_emit);
void dump_skip_to(struct coredump_params *cprm, unsigned long pos)
{
cprm->to_skip = pos - cprm->pos;
}
EXPORT_SYMBOL(dump_skip_to);
void dump_skip(struct coredump_params *cprm, size_t nr)
{
cprm->to_skip += nr;
}
EXPORT_SYMBOL(dump_skip);
#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;
/*
* 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) {
int stop = !dump_emit_page(cprm, page);
put_page(page);
if (stop)
return 0;
} else {
dump_skip(cprm, PAGE_SIZE);
}
}
return 1;
}
#endif
int dump_align(struct coredump_params *cprm, int align)
{
unsigned mod = (cprm->pos + cprm->to_skip) & (align - 1);
if (align & (align - 1))
return 0;
if (mod)
cprm->to_skip += align - mod;
return 1;
}
EXPORT_SYMBOL(dump_align);
#ifdef CONFIG_SYSCTL
void validate_coredump_safety(void)
{
if (suid_dumpable == SUID_DUMP_ROOT &&
core_pattern[0] != '/' && core_pattern[0] != '|') {
pr_warn(
"Unsafe core_pattern used with fs.suid_dumpable=2.\n"
"Pipe handler or fully qualified core dump path required.\n"
"Set kernel.core_pattern before fs.suid_dumpable.\n"
);
}
}
static int proc_dostring_coredump(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int error = proc_dostring(table, write, buffer, lenp, ppos);
if (!error)
validate_coredump_safety();
return error;
}
static struct ctl_table coredump_sysctls[] = {
{
.procname = "core_uses_pid",
.data = &core_uses_pid,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "core_pattern",
.data = core_pattern,
.maxlen = CORENAME_MAX_SIZE,
.mode = 0644,
.proc_handler = proc_dostring_coredump,
},
{
.procname = "core_pipe_limit",
.data = &core_pipe_limit,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
static int __init init_fs_coredump_sysctls(void)
{
register_sysctl_init("kernel", coredump_sysctls);
return 0;
}
fs_initcall(init_fs_coredump_sysctls);
#endif /* CONFIG_SYSCTL */
/*
* 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;