summaryrefslogtreecommitdiffstats
path: root/fs/exec.c
blob: 9e81c630dfa76469cdd452e179882403a93b03c8 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
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
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
/*
 *  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/fdtable.h>
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.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/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>

#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>

#include <trace/events/task.h>
#include "internal.h"

#include <trace/events/sched.h>

int suid_dumpable = 0;

static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);

void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
	BUG_ON(!fmt);
	if (WARN_ON(!fmt->load_binary))
		return;
	write_lock(&binfmt_lock);
	insert ? list_add(&fmt->lh, &formats) :
		 list_add_tail(&fmt->lh, &formats);
	write_unlock(&binfmt_lock);
}

EXPORT_SYMBOL(__register_binfmt);

void unregister_binfmt(struct linux_binfmt * fmt)
{
	write_lock(&binfmt_lock);
	list_del(&fmt->lh);
	write_unlock(&binfmt_lock);
}

EXPORT_SYMBOL(unregister_binfmt);

static inline void put_binfmt(struct linux_binfmt * fmt)
{
	module_put(fmt->module);
}

#ifdef CONFIG_USELIB
/*
 * 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.
 */
SYSCALL_DEFINE1(uselib, const char __user *, library)
{
	struct linux_binfmt *fmt;
	struct file *file;
	struct filename *tmp = getname(library);
	int error = PTR_ERR(tmp);
	static const struct open_flags uselib_flags = {
		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
		.acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN,
		.intent = LOOKUP_OPEN,
		.lookup_flags = LOOKUP_FOLLOW,
	};

	if (IS_ERR(tmp))
		goto out;

	file = do_filp_open(AT_FDCWD, tmp, &uselib_flags);
	putname(tmp);
	error = PTR_ERR(file);
	if (IS_ERR(file))
		goto out;

	error = -EINVAL;
	if (!S_ISREG(file_inode(file)->i_mode))
		goto exit;

	error = -EACCES;
	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
		goto exit;

	fsnotify_open(file);

	error = -ENOEXEC;

	read_lock(&binfmt_lock);
	list_for_each_entry(fmt, &formats, lh) {
		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);
exit:
	fput(file);
out:
  	return error;
}
#endif /* #ifdef CONFIG_USELIB */

#ifdef CONFIG_MMU
/*
 * The nascent bprm->mm is not visible until exec_mmap() but it can
 * use a lot of memory, account these pages in current->mm temporary
 * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we
 * change the counter back via acct_arg_size(0).
 */
static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
	struct mm_struct *mm = current->mm;
	long diff = (long)(pages - bprm->vma_pages);

	if (!mm || !diff)
		return;

	bprm->vma_pages = pages;
	add_mm_counter(mm, MM_ANONPAGES, diff);
}

static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
		int write)
{
	struct page *page;
	int ret;

#ifdef CONFIG_STACK_GROWSUP
	if (write) {
		ret = expand_downwards(bprm->vma, pos);
		if (ret < 0)
			return NULL;
	}
#endif
	ret = get_user_pages(current, bprm->mm, pos,
			1, write, 1, &page, NULL);
	if (ret <= 0)
		return NULL;

	if (write) {
		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
		struct rlimit *rlim;

		acct_arg_size(bprm, size / PAGE_SIZE);

		/*
		 * We've historically supported up to 32 pages (ARG_MAX)
		 * of argument strings even with small stacks
		 */
		if (size <= ARG_MAX)
			return page;

		/*
		 * Limit to 1/4-th the stack size for the argv+env strings.
		 * This ensures that:
		 *  - the remaining binfmt code will not run out of stack space,
		 *  - the program will have a reasonable amount of stack left
		 *    to work from.
		 */
		rlim = current->signal->rlim;
		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
			put_page(page);
			return NULL;
		}
	}

	return page;
}

static void put_arg_page(struct page *page)
{
	put_page(page);
}

static void free_arg_page(struct linux_binprm *bprm, int i)
{
}

static void free_arg_pages(struct linux_binprm *bprm)
{
}

static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
		struct page *page)
{
	flush_cache_page(bprm->vma, pos, page_to_pfn(page));
}

static int __bprm_mm_init(struct linux_binprm *bprm)
{
	int err;
	struct vm_area_struct *vma = NULL;
	struct mm_struct *mm = bprm->mm;

	bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
	if (!vma)
		return -ENOMEM;

	down_write(&mm->mmap_sem);
	vma->vm_mm = mm;

	/*
	 * Place the stack at the largest stack address the architecture
	 * supports. Later, we'll move this to an appropriate place. We don't
	 * use STACK_TOP because that can depend on attributes which aren't
	 * configured yet.
	 */
	BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
	vma->vm_end = STACK_TOP_MAX;
	vma->vm_start = vma->vm_end - PAGE_SIZE;
	vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
	INIT_LIST_HEAD(&vma->anon_vma_chain);

	err = insert_vm_struct(mm, vma);
	if (err)
		goto err;

	mm->stack_vm = mm->total_vm = 1;
	up_write(&mm->mmap_sem);
	bprm->p = vma->vm_end - sizeof(void *);
	return 0;
err:
	up_write(&mm->mmap_sem);
	bprm->vma = NULL;
	kmem_cache_free(vm_area_cachep, vma);
	return err;
}

static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
	return len <= MAX_ARG_STRLEN;
}

#else

static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages)
{
}

static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
		int write)
{
	struct page *page;

	page = bprm->page[pos / PAGE_SIZE];
	if (!page && write) {
		page = alloc_page(GFP_HIGHUSER|__GFP_ZERO);
		if (!page)
			return NULL;
		bprm->page[pos / PAGE_SIZE] = page;
	}

	return page;
}

static void put_arg_page(struct page *page)
{
}

static void free_arg_page(struct linux_binprm *bprm, int i)
{
	if (bprm->page[i]) {
		__free_page(bprm->page[i]);
		bprm->page[i] = NULL;
	}
}

static void free_arg_pages(struct linux_binprm *bprm)
{
	int i;

	for (i = 0; i < MAX_ARG_PAGES; i++)
		free_arg_page(bprm, i);
}

static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos,
		struct page *page)
{
}

static int __bprm_mm_init(struct linux_binprm *bprm)
{
	bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *);
	return 0;
}

static bool valid_arg_len(struct linux_binprm *bprm, long len)
{
	return len <= bprm->p;
}

#endif /* CONFIG_MMU */

/*
 * Create a new mm_struct and populate it with a temporary stack
 * vm_area_struct.  We don't have enough context at this point to set the stack
 * flags, permissions, and offset, so we use temporary values.  We'll update
 * them later in setup_arg_pages().
 */
static int bprm_mm_init(struct linux_binprm *bprm)
{
	int err;
	struct mm_struct *mm = NULL;

	bprm->mm = mm = mm_alloc();
	err = -ENOMEM;
	if (!mm)
		goto err;

	err = init_new_context(current, mm);
	if (err)
		goto err;

	err = __bprm_mm_init(bprm);
	if (err)
		goto err;

	return 0;

err:
	if (mm) {
		bprm->mm = NULL;
		mmdrop(mm);
	}

	return err;
}

struct user_arg_ptr {
#ifdef CONFIG_COMPAT
	bool is_compat;
#endif
	union {
		const char __user *const __user *native;
#ifdef CONFIG_COMPAT
		const compat_uptr_t __user *compat;
#endif
	} ptr;
};

static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr)
{
	const char __user *native;

#ifdef CONFIG_COMPAT
	if (unlikely(argv.is_compat)) {
		compat_uptr_t compat;

		if (get_user(compat, argv.ptr.compat + nr))
			return ERR_PTR(-EFAULT);

		return compat_ptr(compat);
	}
#endif

	if (get_user(native, argv.ptr.native + nr))
		return ERR_PTR(-EFAULT);

	return native;
}

/*
 * count() counts the number of strings in array ARGV.
 */
static int count(struct user_arg_ptr argv, int max)
{
	int i = 0;

	if (argv.ptr.native != NULL) {
		for (;;) {
			const char __user *p = get_user_arg_ptr(argv, i);

			if (!p)
				break;

			if (IS_ERR(p))
				return -EFAULT;

			if (i >= max)
				return -E2BIG;
			++i;

			if (fatal_signal_pending(current))
				return -ERESTARTNOHAND;
			cond_resched();
		}
	}
	return i;
}

/*
 * 'copy_strings()' copies argument/environment strings from the old
 * processes's memory to the new process's stack.  The call to get_user_pages()
 * ensures the destination page is created and not swapped out.
 */
static int copy_strings(int argc, struct user_arg_ptr argv,
			struct linux_binprm *bprm)
{
	struct page *kmapped_page = NULL;
	char *kaddr = NULL;
	unsigned long kpos = 0;
	int ret;

	while (argc-- > 0) {
		const char __user *str;
		int len;
		unsigned long pos;

		ret = -EFAULT;
		str = get_user_arg_ptr(argv, argc);
		if (IS_ERR(str))
			goto out;

		len = strnlen_user(str, MAX_ARG_STRLEN);
		if (!len)
			goto out;

		ret = -E2BIG;
		if (!valid_arg_len(bprm, len))
			goto out;

		/* We're going to work our way backwords. */
		pos = bprm->p;
		str += len;
		bprm->p -= len;

		while (len > 0) {
			int offset, bytes_to_copy;

			if (fatal_signal_pending(current)) {
				ret = -ERESTARTNOHAND;
				goto out;
			}
			cond_resched();

			offset = pos % PAGE_SIZE;
			if (offset == 0)
				offset = PAGE_SIZE;

			bytes_to_copy = offset;
			if (bytes_to_copy > len)
				bytes_to_copy = len;

			offset -= bytes_to_copy;
			pos -= bytes_to_copy;
			str -= bytes_to_copy;
			len -= bytes_to_copy;

			if (!kmapped_page || kpos != (pos & PAGE_MASK)) {
				struct page *page;

				page = get_arg_page(bprm, pos, 1);
				if (!page) {
					ret = -E2BIG;
					goto out;
				}

				if (kmapped_page) {
					flush_kernel_dcache_page(kmapped_page);
					kunmap(kmapped_page);
					put_arg_page(kmapped_page);
				}
				kmapped_page = page;
				kaddr = kmap(kmapped_page);
				kpos = pos & PAGE_MASK;
				flush_arg_page(bprm, kpos, kmapped_page);
			}
			if (copy_from_user(kaddr+offset, str, bytes_to_copy)) {
				ret = -EFAULT;
				goto out;
			}
		}
	}
	ret = 0;
out:
	if (kmapped_page) {
		flush_kernel_dcache_page(kmapped_page);
		kunmap(kmapped_page);
		put_arg_page(kmapped_page);
	}
	return ret;
}

/*
 * Like copy_strings, but get argv and its values from kernel memory.
 */
int copy_strings_kernel(int argc, const char *const *__argv,
			struct linux_binprm *bprm)
{
	int r;
	mm_segment_t oldfs = get_fs();
	struct user_arg_ptr argv = {
		.ptr.native = (const char __user *const  __user *)__argv,
	};

	set_fs(KERNEL_DS);
	r = copy_strings(argc, argv, bprm);
	set_fs(oldfs);

	return r;
}
EXPORT_SYMBOL(copy_strings_kernel);

#ifdef CONFIG_MMU

/*
 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
 * the binfmt code determines where the new stack should reside, we shift it to
 * its final location.  The process proceeds as follows:
 *
 * 1) Use shift to calculate the new vma endpoints.
 * 2) Extend vma to cover both the old and new ranges.  This ensures the
 *    arguments passed to subsequent functions are consistent.
 * 3) Move vma's page tables to the new range.
 * 4) Free up any cleared pgd range.
 * 5) Shrink the vma to cover only the new range.
 */
static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long old_start = vma->vm_start;
	unsigned long old_end = vma->vm_end;
	unsigned long length = old_end - old_start;
	unsigned long new_start = old_start - shift;
	unsigned long new_end = old_end - shift;
	struct mmu_gather tlb;

	BUG_ON(new_start > new_end);

	/*
	 * ensure there are no vmas between where we want to go
	 * and where we are
	 */
	if (vma != find_vma(mm, new_start))
		return -EFAULT;

	/*
	 * cover the whole range: [new_start, old_end)
	 */
	if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL))
		return -ENOMEM;

	/*
	 * move the page tables downwards, on failure we rely on
	 * process cleanup to remove whatever mess we made.
	 */
	if (length != move_page_tables(vma, old_start,
				       vma, new_start, length, false))
		return -ENOMEM;

	lru_add_drain();
	tlb_gather_mmu(&tlb, mm, old_start, old_end);
	if (new_end > old_start) {
		/*
		 * when the old and new regions overlap clear from new_end.
		 */
		free_pgd_range(&tlb, new_end, old_end, new_end,
			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
	} else {
		/*
		 * otherwise, clean from old_start; this is done to not touch
		 * the address space in [new_end, old_start) some architectures
		 * have constraints on va-space that make this illegal (IA64) -
		 * for the others its just a little faster.
		 */
		free_pgd_range(&tlb, old_start, old_end, new_end,
			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
	}
	tlb_finish_mmu(&tlb, old_start, old_end);

	/*
	 * Shrink the vma to just the new range.  Always succeeds.
	 */
	vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL);

	return 0;
}

/*
 * Finalizes the stack vm_area_struct. The flags and permissions are updated,
 * the stack is optionally relocated, and some extra space is added.
 */
int setup_arg_pages(struct linux_binprm *bprm,
		    unsigned long stack_top,
		    int executable_stack)
{
	unsigned long ret;
	unsigned long stack_shift;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma = bprm->vma;
	struct vm_area_struct *prev = NULL;
	unsigned long vm_flags;
	unsigned long stack_base;
	unsigned long stack_size;
	unsigned long stack_expand;
	unsigned long rlim_stack;

#ifdef CONFIG_STACK_GROWSUP
	/* Limit stack size to 1GB */
	stack_base = rlimit_max(RLIMIT_STACK);
	if (stack_base > (1 << 30))
		stack_base = 1 << 30;

	/* Make sure we didn't let the argument array grow too large. */
	if (vma->vm_end - vma->vm_start > stack_base)
		return -ENOMEM;

	stack_base = PAGE_ALIGN(stack_top - stack_base);

	stack_shift = vma->vm_start - stack_base;
	mm->arg_start = bprm->p - stack_shift;
	bprm->p = vma->vm_end - stack_shift;
#else
	stack_top = arch_align_stack(stack_top);
	stack_top = PAGE_ALIGN(stack_top);

	if (unlikely(stack_top < mmap_min_addr) ||
	    unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr))
		return -ENOMEM;

	stack_shift = vma->vm_end - stack_top;

	bprm->p -= stack_shift;
	mm->arg_start = bprm->p;
#endif

	if (bprm->loader)
		bprm->loader -= stack_shift;
	bprm->exec -= stack_shift;

	down_write(&mm->mmap_sem);
	vm_flags = VM_STACK_FLAGS;

	/*
	 * 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))
		vm_flags |= VM_EXEC;
	else if (executable_stack == EXSTACK_DISABLE_X)
		vm_flags &= ~VM_EXEC;
	vm_flags |= mm->def_flags;
	vm_flags |= VM_STACK_INCOMPLETE_SETUP;

	ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end,
			vm_flags);
	if (ret)
		goto out_unlock;
	BUG_ON(prev != vma);

	/* Move stack pages down in memory. */
	if (stack_shift) {
		ret = shift_arg_pages(vma, stack_shift);
		if (ret)
			goto out_unlock;
	}

	/* mprotect_fixup is overkill to remove the temporary stack flags */
	vma->vm_flags &= ~VM_STACK_INCOMPLETE_SETUP;

	stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */
	stack_size = vma->vm_end - vma->vm_start;
	/*
	 * Align this down to a page boundary as expand_stack
	 * will align it up.
	 */
	rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK;
#ifdef CONFIG_STACK_GROWSUP
	if (stack_size + stack_expand > rlim_stack)
		stack_base = vma->vm_start + rlim_stack;
	else
		stack_base = vma->vm_end + stack_expand;
#else
	if (stack_size + stack_expand > rlim_stack)
		stack_base = vma->vm_end - rlim_stack;
	else
		stack_base = vma->vm_start - stack_expand;
#endif
	current->mm->start_stack = bprm->p;
	ret = expand_stack(vma, stack_base);
	if (ret)
		ret = -EFAULT;

out_unlock:
	up_write(&mm->mmap_sem);
	return ret;
}
EXPORT_SYMBOL(setup_arg_pages);

#endif /* CONFIG_MMU */

static struct file *do_open_exec(struct filename *name)
{
	struct file *file;
	int err;
	static const struct open_flags open_exec_flags = {
		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
		.acc_mode = MAY_EXEC | MAY_OPEN,
		.intent = LOOKUP_OPEN,
		.lookup_flags = LOOKUP_FOLLOW,
	};

	file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
	if (IS_ERR(file))
		goto out;

	err = -EACCES;
	if (!S_ISREG(file_inode(file)->i_mode))
		goto exit;

	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
		goto exit;

	fsnotify_open(file);

	err = deny_write_access(file);
	if (err)
		goto exit;

out:
	return file;

exit:
	fput(file);
	return ERR_PTR(err);
}

struct file *open_exec(const char *name)
{
	struct filename tmp = { .name = name };
	return do_open_exec(&tmp);
}
EXPORT_SYMBOL(open_exec);

int kernel_read(struct file *file, loff_t 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);

ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
{
	ssize_t res = file->f_op->read(file, (void __user *)addr, len, &pos);
	if (res > 0)
		flush_icache_range(addr, addr + len);
	return res;
}
EXPORT_SYMBOL(read_code);

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) {
		sync_mm_rss(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_state and changing tsk->mm.
		 */
		down_read(&old_mm->mmap_sem);
		if (unlikely(old_mm->core_state)) {
			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);
	tsk->mm->vmacache_seqnum = 0;
	vmacache_flush(tsk);
	task_unlock(tsk);
	if (old_mm) {
		up_read(&old_mm->mmap_sem);
		BUG_ON(active_mm != old_mm);
		setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
		mm_update_next_owner(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 *oldsighand = tsk->sighand;
	spinlock_t *lock = &oldsighand->siglock;

	if (thread_group_empty(tsk))
		goto no_thread_group;

	/*
	 * Kill all other threads in the thread group.
	 */
	spin_lock_irq(lock);
	if (signal_group_exit(sig)) {
		/*
		 * Another group action in progress, just
		 * return so that the signal is processed.
		 */
		spin_unlock_irq(lock);
		return -EAGAIN;
	}

	sig->group_exit_task = tsk;
	sig->notify_count = zap_other_threads(tsk);
	if (!thread_group_leader(tsk))
		sig->notify_count--;

	while (sig->notify_count) {
		__set_current_state(TASK_KILLABLE);
		spin_unlock_irq(lock);
		schedule();
		if (unlikely(__fatal_signal_pending(tsk)))
			goto killed;
		spin_lock_irq(lock);
	}
	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)) {
		struct task_struct *leader = tsk->group_leader;

		sig->notify_count = -1;	/* for exit_notify() */
		for (;;) {
			threadgroup_change_begin(tsk);
			write_lock_irq(&tasklist_lock);
			if (likely(leader->exit_state))
				break;
			__set_current_state(TASK_KILLABLE);
			write_unlock_irq(&tasklist_lock);
			threadgroup_change_end(tsk);
			schedule();
			if (unlikely(__fatal_signal_pending(tsk)))
				goto killed;
		}

		/*
		 * 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;
		tsk->real_start_time = leader->real_start_time;

		BUG_ON(!same_thread_group(leader, tsk));
		BUG_ON(has_group_leader_pid(tsk));
		/*
		 * 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.
		 */
		tsk->pid = leader->pid;
		change_pid(tsk, PIDTYPE_PID, task_pid(leader));
		transfer_pid(leader, tsk, PIDTYPE_PGID);
		transfer_pid(leader, tsk, PIDTYPE_SID);

		list_replace_rcu(&leader->tasks, &tsk->tasks);
		list_replace_init(&leader->sibling, &tsk->sibling);

		tsk->group_leader = tsk;
		leader->group_leader = tsk;

		tsk->exit_signal = SIGCHLD;
		leader->exit_signal = -1;

		BUG_ON(leader->exit_state != EXIT_ZOMBIE);
		leader->exit_state = EXIT_DEAD;

		/*
		 * We are going to release_task()->ptrace_unlink() silently,
		 * the tracer can sleep in do_wait(). EXIT_DEAD guarantees
		 * the tracer wont't block again waiting for this thread.
		 */
		if (unlikely(leader->ptrace))
			__wake_up_parent(leader, leader->parent);
		write_unlock_irq(&tasklist_lock);
		threadgroup_change_end(tsk);

		release_task(leader);
	}

	sig->group_exit_task = NULL;
	sig->notify_count = 0;

no_thread_group:
	/* we have changed execution domain */
	tsk->exit_signal = SIGCHLD;

	exit_itimers(sig);
	flush_itimer_signals();

	if (atomic_read(&oldsighand->count) != 1) {
		struct sighand_struct *newsighand;
		/*
		 * This ->sighand is shared with the CLONE_SIGHAND
		 * but not CLONE_THREAD task, switch to the new one.
		 */
		newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
		if (!newsighand)
			return -ENOMEM;

		atomic_set(&newsighand->count, 1);
		memcpy(newsighand->action, oldsighand->action,
		       sizeof(newsighand->action));

		write_lock_irq(&tasklist_lock);
		spin_lock(&oldsighand->siglock);
		rcu_assign_pointer(tsk->sighand, newsighand);
		spin_unlock(&oldsighand->siglock);
		write_unlock_irq(&tasklist_lock);

		__cleanup_sighand(oldsighand);
	}

	BUG_ON(!thread_group_leader(tsk));
	return 0;

killed:
	/* protects against exit_notify() and __exit_signal() */
	read_lock(&tasklist_lock);
	sig->group_exit_task = NULL;
	sig->notify_count = 0;
	read_unlock(&tasklist_lock);
	return -EAGAIN;
}

char *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);
	return buf;
}
EXPORT_SYMBOL_GPL(get_task_comm);

/*
 * These functions flushes out all traces of the currently running executable
 * so that a new one can be started
 */

void set_task_comm(struct task_struct *tsk, const char *buf)
{
	task_lock(tsk);
	trace_task_rename(tsk, buf);
	strlcpy(tsk->comm, buf, sizeof(tsk->comm));
	task_unlock(tsk);
	perf_event_comm(tsk);
}

int flush_old_exec(struct linux_binprm * bprm)
{
	int retval;

	/*
	 * 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;

	set_mm_exe_file(bprm->mm, bprm->file);
	/*
	 * Release all of the old mmap stuff
	 */
	acct_arg_size(bprm, 0);
	retval = exec_mmap(bprm->mm);
	if (retval)
		goto out;

	bprm->mm = NULL;		/* We're using it now */

	set_fs(USER_DS);
	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD |
					PF_NOFREEZE | PF_NO_SETAFFINITY);
	flush_thread();
	current->personality &= ~bprm->per_clear;

	return 0;

out:
	return retval;
}
EXPORT_SYMBOL(flush_old_exec);

void would_dump(struct linux_binprm *bprm, struct file *file)
{
	if (inode_permission(file_inode(file), MAY_READ) < 0)
		bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
}
EXPORT_SYMBOL(would_dump);

void setup_new_exec(struct linux_binprm * bprm)
{
	arch_pick_mmap_layout(current->mm);

	/* This is the point of no return */
	current->sas_ss_sp = current->sas_ss_size = 0;

	if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
		set_dumpable(current->mm, SUID_DUMP_USER);
	else
		set_dumpable(current->mm, suid_dumpable);

	set_task_comm(current, kbasename(bprm->filename));

	/* 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;

	/* install the new credentials */
	if (!uid_eq(bprm->cred->uid, current_euid()) ||
	    !gid_eq(bprm->cred->gid, current_egid())) {
		current->pdeath_signal = 0;
	} else {
		would_dump(bprm, bprm->file);
		if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)
			set_dumpable(current->mm, 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);
	do_close_on_exec(current->files);
}
EXPORT_SYMBOL(setup_new_exec);

/*
 * Prepare credentials and lock ->cred_guard_mutex.
 * install_exec_creds() commits the new creds and drops the lock.
 * Or, if exec fails before, free_bprm() should release ->cred and
 * and unlock.
 */
int prepare_bprm_creds(struct linux_binprm *bprm)
{
	if (mutex_lock_interruptible(&current->signal->cred_guard_mutex))
		return -ERESTARTNOINTR;

	bprm->cred = prepare_exec_creds();
	if (likely(bprm->cred))
		return 0;

	mutex_unlock(&current->signal->cred_guard_mutex);
	return -ENOMEM;
}

static void free_bprm(struct linux_binprm *bprm)
{
	free_arg_pages(bprm);
	if (bprm->cred) {
		mutex_unlock(&current->signal->cred_guard_mutex);
		abort_creds(bprm->cred);
	}
	if (bprm->file) {
		allow_write_access(bprm->file);
		fput(bprm->file);
	}
	/* If a binfmt changed the interp, free it. */
	if (bprm->interp != bprm->filename)
		kfree(bprm->interp);
	kfree(bprm);
}

int bprm_change_interp(char *interp, struct linux_binprm *bprm)
{
	/* If a binfmt changed the interp, free it first. */
	if (bprm->interp != bprm->filename)
		kfree(bprm->interp);
	bprm->interp = kstrdup(interp, GFP_KERNEL);
	if (!bprm->interp)
		return -ENOMEM;
	return 0;
}
EXPORT_SYMBOL(bprm_change_interp);

/*
 * install the new credentials for this executable
 */
void install_exec_creds(struct linux_binprm *bprm)
{
	security_bprm_committing_creds(bprm);

	commit_creds(bprm->cred);
	bprm->cred = NULL;

	/*
	 * Disable monitoring for regular users
	 * when executing setuid binaries. Must
	 * wait until new credentials are committed
	 * by commit_creds() above
	 */
	if (get_dumpable(current->mm) != SUID_DUMP_USER)
		perf_event_exit_task(current);
	/*
	 * cred_guard_mutex must be held at least to this point to prevent
	 * ptrace_attach() from altering our determination of the task's
	 * credentials; any time after this it may be unlocked.
	 */
	security_bprm_committed_creds(bprm);
	mutex_unlock(&current->signal->cred_guard_mutex);
}
EXPORT_SYMBOL(install_exec_creds);

/*
 * determine how safe it is to execute the proposed program
 * - the caller must hold ->cred_guard_mutex to protect against
 *   PTRACE_ATTACH
 */
static void check_unsafe_exec(struct linux_binprm *bprm)
{
	struct task_struct *p = current, *t;
	unsigned n_fs;

	if (p->ptrace) {
		if (p->ptrace & PT_PTRACE_CAP)
			bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
		else
			bprm->unsafe |= LSM_UNSAFE_PTRACE;
	}

	/*
	 * This isn't strictly necessary, but it makes it harder for LSMs to
	 * mess up.
	 */
	if (current->no_new_privs)
		bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;

	t = p;
	n_fs = 1;
	spin_lock(&p->fs->lock);
	rcu_read_lock();
	while_each_thread(p, t) {
		if (t->fs == p->fs)
			n_fs++;
	}
	rcu_read_unlock();

	if (p->fs->users > n_fs)
		bprm->unsafe |= LSM_UNSAFE_SHARE;
	else
		p->fs->in_exec = 1;
	spin_unlock(&p->fs->lock);
}

/*
 * Fill the binprm structure from the inode.
 * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
 *
 * This may be called multiple times for binary chains (scripts for example).
 */
int prepare_binprm(struct linux_binprm *bprm)
{
	struct inode *inode = file_inode(bprm->file);
	umode_t mode = inode->i_mode;
	int retval;


	/* clear any previous set[ug]id data from a previous binary */
	bprm->cred->euid = current_euid();
	bprm->cred->egid = current_egid();

	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
	    !current->no_new_privs &&
	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
		/* Set-uid? */
		if (mode & S_ISUID) {
			bprm->per_clear |= PER_CLEAR_ON_SETID;
			bprm->cred->euid = 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)) {
			bprm->per_clear |= PER_CLEAR_ON_SETID;
			bprm->cred->egid = inode->i_gid;
		}
	}

	/* fill in binprm security blob */
	retval = security_bprm_set_creds(bprm);
	if (retval)
		return retval;
	bprm->cred_prepared = 1;

	memset(bprm->buf, 0, BINPRM_BUF_SIZE);
	return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
}

EXPORT_SYMBOL(prepare_binprm);

/*
 * 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.
 */
int remove_arg_zero(struct linux_binprm *bprm)
{
	int ret = 0;
	unsigned long offset;
	char *kaddr;
	struct page *page;

	if (!bprm->argc)
		return 0;

	do {
		offset = bprm->p & ~PAGE_MASK;
		page = get_arg_page(bprm, bprm->p, 0);
		if (!page) {
			ret = -EFAULT;
			goto out;
		}
		kaddr = kmap_atomic(page);

		for (; offset < PAGE_SIZE && kaddr[offset];
				offset++, bprm->p++)
			;

		kunmap_atomic(kaddr);
		put_arg_page(page);

		if (offset == PAGE_SIZE)
			free_arg_page(bprm, (bprm->p >> PAGE_SHIFT) - 1);
	} while (offset == PAGE_SIZE);

	bprm->p++;
	bprm->argc--;
	ret = 0;

out:
	return ret;
}
EXPORT_SYMBOL(remove_arg_zero);

#define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
/*
 * cycle the list of binary formats handler, until one recognizes the image
 */
int search_binary_handler(struct linux_binprm *bprm)
{
	bool need_retry = IS_ENABLED(CONFIG_MODULES);
	struct linux_binfmt *fmt;
	int retval;

	/* This allows 4 levels of binfmt rewrites before failing hard. */
	if (bprm->recursion_depth > 5)
		return -ELOOP;

	retval = security_bprm_check(bprm);
	if (retval)
		return retval;

	retval = -ENOENT;
 retry:
	read_lock(&binfmt_lock);
	list_for_each_entry(fmt, &formats, lh) {
		if (!try_module_get(fmt->module))
			continue;
		read_unlock(&binfmt_lock);
		bprm->recursion_depth++;
		retval = fmt->load_binary(bprm);
		bprm->recursion_depth--;
		if (retval >= 0 || retval != -ENOEXEC ||
		    bprm->mm == NULL || bprm->file == NULL) {
			put_binfmt(fmt);
			return retval;
		}
		read_lock(&binfmt_lock);
		put_binfmt(fmt);
	}
	read_unlock(&binfmt_lock);

	if (need_retry && retval == -ENOEXEC) {
		if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
		    printable(bprm->buf[2]) && printable(bprm->buf[3]))
			return retval;
		if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0)
			return retval;
		need_retry = false;
		goto retry;
	}

	return retval;
}
EXPORT_SYMBOL(search_binary_handler);

static int exec_binprm(struct linux_binprm *bprm)
{
	pid_t old_pid, old_vpid;
	int ret;

	/* Need to fetch pid before load_binary changes it */
	old_pid = current->pid;
	rcu_read_lock();
	old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent));
	rcu_read_unlock();

	ret = search_binary_handler(bprm);
	if (ret >= 0) {
		audit_bprm(bprm);
		trace_sched_process_exec(current, old_pid, bprm);
		ptrace_event(PTRACE_EVENT_EXEC, old_vpid);
		proc_exec_connector(current);
	}

	return ret;
}

/*
 * sys_execve() executes a new program.
 */
static int do_execve_common(struct filename *filename,
				struct user_arg_ptr argv,
				struct user_arg_ptr envp)
{
	struct linux_binprm *bprm;
	struct file *file;
	struct files_struct *displaced;
	int retval;

	if (IS_ERR(filename))
		return PTR_ERR(filename);

	/*
	 * We move the actual failure in case of RLIMIT_NPROC excess from
	 * set*uid() to execve() because too many poorly written programs
	 * don't check setuid() return code.  Here we additionally recheck
	 * whether NPROC limit is still exceeded.
	 */
	if ((current->flags & PF_NPROC_EXCEEDED) &&
	    atomic_read(&current_user()->processes) > rlimit(RLIMIT_NPROC)) {
		retval = -EAGAIN;
		goto out_ret;
	}

	/* We're below the limit (still or again), so we don't want to make
	 * further execve() calls fail. */
	current->flags &= ~PF_NPROC_EXCEEDED;

	retval = unshare_files(&displaced);
	if (retval)
		goto out_ret;

	retval = -ENOMEM;
	bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
	if (!bprm)
		goto out_files;

	retval = prepare_bprm_creds(bprm);
	if (retval)
		goto out_free;

	check_unsafe_exec(bprm);
	current->in_execve = 1;

	file = do_open_exec(filename);
	retval = PTR_ERR(file);
	if (IS_ERR(file))
		goto out_unmark;

	sched_exec();

	bprm->file = file;
	bprm->filename = bprm->interp = filename->name;

	retval = bprm_mm_init(bprm);
	if (retval)
		goto out_unmark;

	bprm->argc = count(argv, MAX_ARG_STRINGS);
	if ((retval = bprm->argc) < 0)
		goto out;

	bprm->envc = count(envp, MAX_ARG_STRINGS);
	if ((retval = bprm->envc) < 0)
		goto out;

	retval = prepare_binprm(bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings_kernel(1, &bprm->filename, bprm);
	if (retval < 0)
		goto out;

	bprm->exec = bprm->p;
	retval = copy_strings(bprm->envc, envp, bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings(bprm->argc, argv, bprm);
	if (retval < 0)
		goto out;

	retval = exec_binprm(bprm);
	if (retval < 0)
		goto out;

	/* execve succeeded */
	current->fs->in_exec = 0;
	current->in_execve = 0;
	acct_update_integrals(current);
	task_numa_free(current);
	free_bprm(bprm);
	putname(filename);
	if (displaced)
		put_files_struct(displaced);
	return retval;

out:
	if (bprm->mm) {
		acct_arg_size(bprm, 0);
		mmput(bprm->mm);
	}

out_unmark:
	current->fs->in_exec = 0;
	current->in_execve = 0;

out_free:
	free_bprm(bprm);

out_files:
	if (displaced)
		reset_files_struct(displaced);
out_ret:
	putname(filename);
	return retval;
}

int do_execve(struct filename *filename,
	const char __user *const __user *__argv,
	const char __user *const __user *__envp)
{
	struct user_arg_ptr argv = { .ptr.native = __argv };
	struct user_arg_ptr envp = { .ptr.native = __envp };
	return do_execve_common(filename, argv, envp);
}

#ifdef CONFIG_COMPAT
static int compat_do_execve(struct filename *filename,
	const compat_uptr_t __user *__argv,
	const compat_uptr_t __user *__envp)
{
	struct user_arg_ptr argv = {
		.is_compat = true,
		.ptr.compat = __argv,
	};
	struct user_arg_ptr envp = {
		.is_compat = true,
		.ptr.compat = __envp,
	};
	return do_execve_common(filename, argv, envp);
}
#endif

void set_binfmt(struct linux_binfmt *new)
{
	struct mm_struct *mm = current->mm;

	if (mm->binfmt)
		module_put(mm->binfmt->module);

	mm->binfmt = new;
	if (new)
		__module_get(new->module);
}
EXPORT_SYMBOL(set_binfmt);

/*
 * set_dumpable stores three-value SUID_DUMP_* into mm->flags.
 */
void set_dumpable(struct mm_struct *mm, int value)
{
	unsigned long old, new;

	if (WARN_ON((unsigned)value > SUID_DUMP_ROOT))
		return;

	do {
		old = ACCESS_ONCE(mm->flags);
		new = (old & ~MMF_DUMPABLE_MASK) | value;
	} while (cmpxchg(&mm->flags, old, new) != old);
}

SYSCALL_DEFINE3(execve,
		const char __user *, filename,
		const char __user *const __user *, argv,
		const char __user *const __user *, envp)
{
	return do_execve(getname(filename), argv, envp);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
	const compat_uptr_t __user *, argv,
	const compat_uptr_t __user *, envp)
{
	return compat_do_execve(getname(filename), argv, envp);
}
#endif
OpenPOWER on IntegriCloud