forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
exec.c
1581 lines (1372 loc) · 35.7 KB
/
exec.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
/*
* linux/fs/exec.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* #!-checking implemented by tytso.
*/
/*
* Demand-loading implemented 01.12.91 - no need to read anything but
* the header into memory. The inode of the executable is put into
* "current->executable", and page faults do the actual loading. Clean.
*
* Once more I can proudly say that linux stood up to being changed: it
* was less than 2 hours work to get demand-loading completely implemented.
*
* Demand loading changed July 1993 by Eric Youngdale. Use mmap instead,
* current->executable is only used by the procfs. This allows a dispatch
* table to check for several different types of binary formats. We keep
* trying until we recognize the file or we run out of supported binary
* formats.
*/
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/a.out.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
#include <linux/key.h>
#include <linux/personality.h>
#include <linux/binfmts.h>
#include <linux/swap.h>
#include <linux/utsname.h>
#include <linux/pid_namespace.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/proc_fs.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/rmap.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
#include <linux/signalfd.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#ifdef CONFIG_KMOD
#include <linux/kmod.h>
#endif
int core_uses_pid;
char core_pattern[128] = "core";
int suid_dumpable = 0;
EXPORT_SYMBOL(suid_dumpable);
/* The maximal length of core_pattern is also specified in sysctl.c */
static struct linux_binfmt *formats;
static DEFINE_RWLOCK(binfmt_lock);
int register_binfmt(struct linux_binfmt * fmt)
{
struct linux_binfmt ** tmp = &formats;
if (!fmt)
return -EINVAL;
if (fmt->next)
return -EBUSY;
write_lock(&binfmt_lock);
while (*tmp) {
if (fmt == *tmp) {
write_unlock(&binfmt_lock);
return -EBUSY;
}
tmp = &(*tmp)->next;
}
fmt->next = formats;
formats = fmt;
write_unlock(&binfmt_lock);
return 0;
}
EXPORT_SYMBOL(register_binfmt);
int unregister_binfmt(struct linux_binfmt * fmt)
{
struct linux_binfmt ** tmp = &formats;
write_lock(&binfmt_lock);
while (*tmp) {
if (fmt == *tmp) {
*tmp = fmt->next;
fmt->next = NULL;
write_unlock(&binfmt_lock);
return 0;
}
tmp = &(*tmp)->next;
}
write_unlock(&binfmt_lock);
return -EINVAL;
}
EXPORT_SYMBOL(unregister_binfmt);
static inline void put_binfmt(struct linux_binfmt * fmt)
{
module_put(fmt->module);
}
/*
* Note that a shared library must be both readable and executable due to
* security reasons.
*
* Also note that we take the address to load from from the file itself.
*/
asmlinkage long sys_uselib(const char __user * library)
{
struct file * file;
struct nameidata nd;
int error;
error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
if (error)
goto out;
error = -EINVAL;
if (!S_ISREG(nd.dentry->d_inode->i_mode))
goto exit;
error = vfs_permission(&nd, MAY_READ | MAY_EXEC);
if (error)
goto exit;
file = nameidata_to_filp(&nd, O_RDONLY);
error = PTR_ERR(file);
if (IS_ERR(file))
goto out;
error = -ENOEXEC;
if(file->f_op) {
struct linux_binfmt * fmt;
read_lock(&binfmt_lock);
for (fmt = formats ; fmt ; fmt = fmt->next) {
if (!fmt->load_shlib)
continue;
if (!try_module_get(fmt->module))
continue;
read_unlock(&binfmt_lock);
error = fmt->load_shlib(file);
read_lock(&binfmt_lock);
put_binfmt(fmt);
if (error != -ENOEXEC)
break;
}
read_unlock(&binfmt_lock);
}
fput(file);
out:
return error;
exit:
release_open_intent(&nd);
path_release(&nd);
goto out;
}
/*
* count() counts the number of strings in array ARGV.
*/
static int count(char __user * __user * argv, int max)
{
int i = 0;
if (argv != NULL) {
for (;;) {
char __user * p;
if (get_user(p, argv))
return -EFAULT;
if (!p)
break;
argv++;
if(++i > max)
return -E2BIG;
cond_resched();
}
}
return i;
}
/*
* 'copy_strings()' copies argument/environment strings from user
* memory to free pages in kernel mem. These are in a format ready
* to be put directly into the top of new user memory.
*/
static int copy_strings(int argc, char __user * __user * argv,
struct linux_binprm *bprm)
{
struct page *kmapped_page = NULL;
char *kaddr = NULL;
int ret;
while (argc-- > 0) {
char __user *str;
int len;
unsigned long pos;
if (get_user(str, argv+argc) ||
!(len = strnlen_user(str, bprm->p))) {
ret = -EFAULT;
goto out;
}
if (bprm->p < len) {
ret = -E2BIG;
goto out;
}
bprm->p -= len;
/* XXX: add architecture specific overflow check here. */
pos = bprm->p;
while (len > 0) {
int i, new, err;
int offset, bytes_to_copy;
struct page *page;
offset = pos % PAGE_SIZE;
i = pos/PAGE_SIZE;
page = bprm->page[i];
new = 0;
if (!page) {
page = alloc_page(GFP_HIGHUSER);
bprm->page[i] = page;
if (!page) {
ret = -ENOMEM;
goto out;
}
new = 1;
}
if (page != kmapped_page) {
if (kmapped_page)
kunmap(kmapped_page);
kmapped_page = page;
kaddr = kmap(kmapped_page);
}
if (new && offset)
memset(kaddr, 0, offset);
bytes_to_copy = PAGE_SIZE - offset;
if (bytes_to_copy > len) {
bytes_to_copy = len;
if (new)
memset(kaddr+offset+len, 0,
PAGE_SIZE-offset-len);
}
err = copy_from_user(kaddr+offset, str, bytes_to_copy);
if (err) {
ret = -EFAULT;
goto out;
}
pos += bytes_to_copy;
str += bytes_to_copy;
len -= bytes_to_copy;
}
}
ret = 0;
out:
if (kmapped_page)
kunmap(kmapped_page);
return ret;
}
/*
* Like copy_strings, but get argv and its values from kernel memory.
*/
int copy_strings_kernel(int argc,char ** argv, struct linux_binprm *bprm)
{
int r;
mm_segment_t oldfs = get_fs();
set_fs(KERNEL_DS);
r = copy_strings(argc, (char __user * __user *)argv, bprm);
set_fs(oldfs);
return r;
}
EXPORT_SYMBOL(copy_strings_kernel);
#ifdef CONFIG_MMU
/*
* This routine is used to map in a page into an address space: needed by
* execve() for the initial stack and environment pages.
*
* vma->vm_mm->mmap_sem is held for writing.
*/
void install_arg_page(struct vm_area_struct *vma,
struct page *page, unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
pte_t * pte;
spinlock_t *ptl;
if (unlikely(anon_vma_prepare(vma)))
goto out;
flush_dcache_page(page);
pte = get_locked_pte(mm, address, &ptl);
if (!pte)
goto out;
if (!pte_none(*pte)) {
pte_unmap_unlock(pte, ptl);
goto out;
}
inc_mm_counter(mm, anon_rss);
lru_cache_add_active(page);
set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
page, vma->vm_page_prot))));
page_add_new_anon_rmap(page, vma, address);
pte_unmap_unlock(pte, ptl);
/* no need for flush_tlb */
return;
out:
__free_page(page);
force_sig(SIGKILL, current);
}
#define EXTRA_STACK_VM_PAGES 20 /* random */
int setup_arg_pages(struct linux_binprm *bprm,
unsigned long stack_top,
int executable_stack)
{
unsigned long stack_base;
struct vm_area_struct *mpnt;
struct mm_struct *mm = current->mm;
int i, ret;
long arg_size;
#ifdef CONFIG_STACK_GROWSUP
/* Move the argument and environment strings to the bottom of the
* stack space.
*/
int offset, j;
char *to, *from;
/* Start by shifting all the pages down */
i = 0;
for (j = 0; j < MAX_ARG_PAGES; j++) {
struct page *page = bprm->page[j];
if (!page)
continue;
bprm->page[i++] = page;
}
/* Now move them within their pages */
offset = bprm->p % PAGE_SIZE;
to = kmap(bprm->page[0]);
for (j = 1; j < i; j++) {
memmove(to, to + offset, PAGE_SIZE - offset);
from = kmap(bprm->page[j]);
memcpy(to + PAGE_SIZE - offset, from, offset);
kunmap(bprm->page[j - 1]);
to = from;
}
memmove(to, to + offset, PAGE_SIZE - offset);
kunmap(bprm->page[j - 1]);
/* Limit stack size to 1GB */
stack_base = current->signal->rlim[RLIMIT_STACK].rlim_max;
if (stack_base > (1 << 30))
stack_base = 1 << 30;
stack_base = PAGE_ALIGN(stack_top - stack_base);
/* Adjust bprm->p to point to the end of the strings. */
bprm->p = stack_base + PAGE_SIZE * i - offset;
mm->arg_start = stack_base;
arg_size = i << PAGE_SHIFT;
/* zero pages that were copied above */
while (i < MAX_ARG_PAGES)
bprm->page[i++] = NULL;
#else
stack_base = arch_align_stack(stack_top - MAX_ARG_PAGES*PAGE_SIZE);
stack_base = PAGE_ALIGN(stack_base);
bprm->p += stack_base;
mm->arg_start = bprm->p;
arg_size = stack_top - (PAGE_MASK & (unsigned long) mm->arg_start);
#endif
arg_size += EXTRA_STACK_VM_PAGES * PAGE_SIZE;
if (bprm->loader)
bprm->loader += stack_base;
bprm->exec += stack_base;
mpnt = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
if (!mpnt)
return -ENOMEM;
down_write(&mm->mmap_sem);
{
mpnt->vm_mm = mm;
#ifdef CONFIG_STACK_GROWSUP
mpnt->vm_start = stack_base;
mpnt->vm_end = stack_base + arg_size;
#else
mpnt->vm_end = stack_top;
mpnt->vm_start = mpnt->vm_end - arg_size;
#endif
/* Adjust stack execute permissions; explicitly enable
* for EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X
* and leave alone (arch default) otherwise. */
if (unlikely(executable_stack == EXSTACK_ENABLE_X))
mpnt->vm_flags = VM_STACK_FLAGS | VM_EXEC;
else if (executable_stack == EXSTACK_DISABLE_X)
mpnt->vm_flags = VM_STACK_FLAGS & ~VM_EXEC;
else
mpnt->vm_flags = VM_STACK_FLAGS;
mpnt->vm_flags |= mm->def_flags;
mpnt->vm_page_prot = protection_map[mpnt->vm_flags & 0x7];
if ((ret = insert_vm_struct(mm, mpnt))) {
up_write(&mm->mmap_sem);
kmem_cache_free(vm_area_cachep, mpnt);
return ret;
}
mm->stack_vm = mm->total_vm = vma_pages(mpnt);
}
for (i = 0 ; i < MAX_ARG_PAGES ; i++) {
struct page *page = bprm->page[i];
if (page) {
bprm->page[i] = NULL;
install_arg_page(mpnt, page, stack_base);
}
stack_base += PAGE_SIZE;
}
up_write(&mm->mmap_sem);
return 0;
}
EXPORT_SYMBOL(setup_arg_pages);
#define free_arg_pages(bprm) do { } while (0)
#else
static inline void free_arg_pages(struct linux_binprm *bprm)
{
int i;
for (i = 0; i < MAX_ARG_PAGES; i++) {
if (bprm->page[i])
__free_page(bprm->page[i]);
bprm->page[i] = NULL;
}
}
#endif /* CONFIG_MMU */
struct file *open_exec(const char *name)
{
struct nameidata nd;
int err;
struct file *file;
err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
file = ERR_PTR(err);
if (!err) {
struct inode *inode = nd.dentry->d_inode;
file = ERR_PTR(-EACCES);
if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
S_ISREG(inode->i_mode)) {
int err = vfs_permission(&nd, MAY_EXEC);
file = ERR_PTR(err);
if (!err) {
file = nameidata_to_filp(&nd, O_RDONLY);
if (!IS_ERR(file)) {
err = deny_write_access(file);
if (err) {
fput(file);
file = ERR_PTR(err);
}
}
out:
return file;
}
}
release_open_intent(&nd);
path_release(&nd);
}
goto out;
}
EXPORT_SYMBOL(open_exec);
int kernel_read(struct file *file, unsigned long offset,
char *addr, unsigned long count)
{
mm_segment_t old_fs;
loff_t pos = offset;
int result;
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
result = vfs_read(file, (void __user *)addr, count, &pos);
set_fs(old_fs);
return result;
}
EXPORT_SYMBOL(kernel_read);
static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
struct mm_struct * old_mm, *active_mm;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
mm_release(tsk, old_mm);
if (old_mm) {
/*
* Make sure that if there is a core dump in progress
* for the old mm, we get out and die instead of going
* through with the exec. We must hold mmap_sem around
* checking core_waiters and changing tsk->mm. The
* core-inducing thread will increment core_waiters for
* each thread whose ->mm == old_mm.
*/
down_read(&old_mm->mmap_sem);
if (unlikely(old_mm->core_waiters)) {
up_read(&old_mm->mmap_sem);
return -EINTR;
}
}
task_lock(tsk);
active_mm = tsk->active_mm;
tsk->mm = mm;
tsk->active_mm = mm;
activate_mm(active_mm, mm);
task_unlock(tsk);
arch_pick_mmap_layout(mm);
if (old_mm) {
up_read(&old_mm->mmap_sem);
BUG_ON(active_mm != old_mm);
mmput(old_mm);
return 0;
}
mmdrop(active_mm);
return 0;
}
/*
* This function makes sure the current process has its own signal table,
* so that flush_signal_handlers can later reset the handlers without
* disturbing other processes. (Other processes might share the signal
* table via the CLONE_SIGHAND option to clone().)
*/
static int de_thread(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
struct sighand_struct *newsighand, *oldsighand = tsk->sighand;
spinlock_t *lock = &oldsighand->siglock;
struct task_struct *leader = NULL;
int count;
/*
* Tell all the sighand listeners that this sighand has
* been detached. The signalfd_detach() function grabs the
* sighand lock, if signal listeners are present on the sighand.
*/
signalfd_detach(tsk);
/*
* If we don't share sighandlers, then we aren't sharing anything
* and we can just re-use it all.
*/
if (atomic_read(&oldsighand->count) <= 1) {
BUG_ON(atomic_read(&sig->count) != 1);
exit_itimers(sig);
return 0;
}
newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
if (!newsighand)
return -ENOMEM;
if (thread_group_empty(tsk))
goto no_thread_group;
/*
* Kill all other threads in the thread group.
* We must hold tasklist_lock to call zap_other_threads.
*/
read_lock(&tasklist_lock);
spin_lock_irq(lock);
if (sig->flags & SIGNAL_GROUP_EXIT) {
/*
* Another group action in progress, just
* return so that the signal is processed.
*/
spin_unlock_irq(lock);
read_unlock(&tasklist_lock);
kmem_cache_free(sighand_cachep, newsighand);
return -EAGAIN;
}
/*
* child_reaper ignores SIGKILL, change it now.
* Reparenting needs write_lock on tasklist_lock,
* so it is safe to do it under read_lock.
*/
if (unlikely(tsk->group_leader == child_reaper(tsk)))
tsk->nsproxy->pid_ns->child_reaper = tsk;
zap_other_threads(tsk);
read_unlock(&tasklist_lock);
/*
* Account for the thread group leader hanging around:
*/
count = 1;
if (!thread_group_leader(tsk)) {
count = 2;
/*
* The SIGALRM timer survives the exec, but needs to point
* at us as the new group leader now. We have a race with
* a timer firing now getting the old leader, so we need to
* synchronize with any firing (by calling del_timer_sync)
* before we can safely let the old group leader die.
*/
sig->tsk = tsk;
spin_unlock_irq(lock);
if (hrtimer_cancel(&sig->real_timer))
hrtimer_restart(&sig->real_timer);
spin_lock_irq(lock);
}
while (atomic_read(&sig->count) > count) {
sig->group_exit_task = tsk;
sig->notify_count = count;
__set_current_state(TASK_UNINTERRUPTIBLE);
spin_unlock_irq(lock);
schedule();
spin_lock_irq(lock);
}
sig->group_exit_task = NULL;
sig->notify_count = 0;
spin_unlock_irq(lock);
/*
* At this point all other threads have exited, all we have to
* do is to wait for the thread group leader to become inactive,
* and to assume its PID:
*/
if (!thread_group_leader(tsk)) {
/*
* Wait for the thread group leader to be a zombie.
* It should already be zombie at this point, most
* of the time.
*/
leader = tsk->group_leader;
while (leader->exit_state != EXIT_ZOMBIE)
yield();
/*
* The only record we have of the real-time age of a
* process, regardless of execs it's done, is start_time.
* All the past CPU time is accumulated in signal_struct
* from sister threads now dead. But in this non-leader
* exec, nothing survives from the original leader thread,
* whose birth marks the true age of this process now.
* When we take on its identity by switching to its PID, we
* also take its birthdate (always earlier than our own).
*/
tsk->start_time = leader->start_time;
write_lock_irq(&tasklist_lock);
BUG_ON(leader->tgid != tsk->tgid);
BUG_ON(tsk->pid == tsk->tgid);
/*
* An exec() starts a new thread group with the
* TGID of the previous thread group. Rehash the
* two threads with a switched PID, and release
* the former thread group leader:
*/
/* Become a process group leader with the old leader's pid.
* The old leader becomes a thread of the this thread group.
* Note: The old leader also uses this pid until release_task
* is called. Odd but simple and correct.
*/
detach_pid(tsk, PIDTYPE_PID);
tsk->pid = leader->pid;
attach_pid(tsk, PIDTYPE_PID, find_pid(tsk->pid));
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks);
tsk->group_leader = tsk;
leader->group_leader = tsk;
tsk->exit_signal = SIGCHLD;
BUG_ON(leader->exit_state != EXIT_ZOMBIE);
leader->exit_state = EXIT_DEAD;
write_unlock_irq(&tasklist_lock);
}
/*
* There may be one thread left which is just exiting,
* but it's safe to stop telling the group to kill themselves.
*/
sig->flags = 0;
no_thread_group:
exit_itimers(sig);
if (leader)
release_task(leader);
BUG_ON(atomic_read(&sig->count) != 1);
if (atomic_read(&oldsighand->count) == 1) {
/*
* Now that we nuked the rest of the thread group,
* it turns out we are not sharing sighand any more either.
* So we can just keep it.
*/
kmem_cache_free(sighand_cachep, newsighand);
} else {
/*
* Move our state over to newsighand and switch it in.
*/
atomic_set(&newsighand->count, 1);
memcpy(newsighand->action, oldsighand->action,
sizeof(newsighand->action));
write_lock_irq(&tasklist_lock);
spin_lock(&oldsighand->siglock);
spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING);
rcu_assign_pointer(tsk->sighand, newsighand);
recalc_sigpending();
spin_unlock(&newsighand->siglock);
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
__cleanup_sighand(oldsighand);
}
BUG_ON(!thread_group_leader(tsk));
return 0;
}
/*
* These functions flushes out all traces of the currently running executable
* so that a new one can be started
*/
static void flush_old_files(struct files_struct * files)
{
long j = -1;
struct fdtable *fdt;
spin_lock(&files->file_lock);
for (;;) {
unsigned long set, i;
j++;
i = j * __NFDBITS;
fdt = files_fdtable(files);
if (i >= fdt->max_fds)
break;
set = fdt->close_on_exec->fds_bits[j];
if (!set)
continue;
fdt->close_on_exec->fds_bits[j] = 0;
spin_unlock(&files->file_lock);
for ( ; set ; i++,set >>= 1) {
if (set & 1) {
sys_close(i);
}
}
spin_lock(&files->file_lock);
}
spin_unlock(&files->file_lock);
}
void get_task_comm(char *buf, struct task_struct *tsk)
{
/* buf must be at least sizeof(tsk->comm) in size */
task_lock(tsk);
strncpy(buf, tsk->comm, sizeof(tsk->comm));
task_unlock(tsk);
}
void set_task_comm(struct task_struct *tsk, char *buf)
{
task_lock(tsk);
strlcpy(tsk->comm, buf, sizeof(tsk->comm));
task_unlock(tsk);
}
int flush_old_exec(struct linux_binprm * bprm)
{
char * name;
int i, ch, retval;
struct files_struct *files;
char tcomm[sizeof(current->comm)];
/*
* Make sure we have a private signal table and that
* we are unassociated from the previous thread group.
*/
retval = de_thread(current);
if (retval)
goto out;
/*
* Make sure we have private file handles. Ask the
* fork helper to do the work for us and the exit
* helper to do the cleanup of the old one.
*/
files = current->files; /* refcounted so safe to hold */
retval = unshare_files();
if (retval)
goto out;
/*
* Release all of the old mmap stuff
*/
retval = exec_mmap(bprm->mm);
if (retval)
goto mmap_failed;
bprm->mm = NULL; /* We're using it now */
/* This is the point of no return */
put_files_struct(files);
current->sas_ss_sp = current->sas_ss_size = 0;
if (current->euid == current->uid && current->egid == current->gid)
current->mm->dumpable = 1;
else
current->mm->dumpable = suid_dumpable;
name = bprm->filename;
/* Copies the binary name from after last slash */
for (i=0; (ch = *(name++)) != '\0';) {
if (ch == '/')
i = 0; /* overwrite what we wrote */
else
if (i < (sizeof(tcomm) - 1))
tcomm[i++] = ch;
}
tcomm[i] = '\0';
set_task_comm(current, tcomm);
current->flags &= ~PF_RANDOMIZE;
flush_thread();
/* Set the new mm task size. We have to do that late because it may
* depend on TIF_32BIT which is only updated in flush_thread() on
* some architectures like powerpc
*/
current->mm->task_size = TASK_SIZE;
if (bprm->e_uid != current->euid || bprm->e_gid != current->egid ||
file_permission(bprm->file, MAY_READ) ||
(bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) {
suid_keys(current);
current->mm->dumpable = suid_dumpable;
}
/* An exec changes our domain. We are no longer part of the thread
group */
current->self_exec_id++;
flush_signal_handlers(current, 0);
flush_old_files(current->files);
return 0;
mmap_failed:
reset_files_struct(current, files);
out:
return retval;
}
EXPORT_SYMBOL(flush_old_exec);
/*
* Fill the binprm structure from the inode.
* Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
*/
int prepare_binprm(struct linux_binprm *bprm)
{
int mode;
struct inode * inode = bprm->file->f_path.dentry->d_inode;
int retval;
mode = inode->i_mode;
if (bprm->file->f_op == NULL)
return -EACCES;
bprm->e_uid = current->euid;
bprm->e_gid = current->egid;
if(!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
/* Set-uid? */
if (mode & S_ISUID) {
current->personality &= ~PER_CLEAR_ON_SETID;
bprm->e_uid = inode->i_uid;
}
/* Set-gid? */
/*
* If setgid is set but no group execute bit then this
* is a candidate for mandatory locking, not a setgid
* executable.
*/
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
current->personality &= ~PER_CLEAR_ON_SETID;
bprm->e_gid = inode->i_gid;
}
}
/* fill in binprm security blob */
retval = security_bprm_set(bprm);
if (retval)
return retval;
memset(bprm->buf,0,BINPRM_BUF_SIZE);
return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE);
}
EXPORT_SYMBOL(prepare_binprm);
static int unsafe_exec(struct task_struct *p)
{
int unsafe = 0;
if (p->ptrace & PT_PTRACED) {
if (p->ptrace & PT_PTRACE_CAP)
unsafe |= LSM_UNSAFE_PTRACE_CAP;
else
unsafe |= LSM_UNSAFE_PTRACE;
}
if (atomic_read(&p->fs->count) > 1 ||
atomic_read(&p->files->count) > 1 ||
atomic_read(&p->sighand->count) > 1)
unsafe |= LSM_UNSAFE_SHARE;
return unsafe;
}
void compute_creds(struct linux_binprm *bprm)
{
int unsafe;
if (bprm->e_uid != current->uid)
suid_keys(current);
exec_keys(current);
task_lock(current);
unsafe = unsafe_exec(current);
security_bprm_apply_creds(bprm, unsafe);
task_unlock(current);
security_bprm_post_apply_creds(bprm);
}
EXPORT_SYMBOL(compute_creds);
/*
* Arguments are '\0' separated strings found at the location bprm->p
* points to; chop off the first by relocating brpm->p to right after
* the first '\0' encountered.
*/
void remove_arg_zero(struct linux_binprm *bprm)