summaryrefslogtreecommitdiffstats
path: root/kernel/events/uprobes.c
blob: 7edc95edfaee10ee0fe8bdafc8f1caf81d883762 (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
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
/*
 * User-space Probes (UProbes)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 *
 * Copyright (C) IBM Corporation, 2008-2012
 * Authors:
 *	Srikar Dronamraju
 *	Jim Keniston
 * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
 */

#include <linux/kernel.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>	/* read_mapping_page */
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>		/* anon_vma_prepare */
#include <linux/mmu_notifier.h>	/* set_pte_at_notify */
#include <linux/swap.h>		/* try_to_free_swap */
#include <linux/ptrace.h>	/* user_enable_single_step */
#include <linux/kdebug.h>	/* notifier mechanism */
#include "../../mm/internal.h"	/* munlock_vma_page */
#include <linux/percpu-rwsem.h>
#include <linux/task_work.h>
#include <linux/shmem_fs.h>

#include <linux/uprobes.h>

#define UINSNS_PER_PAGE			(PAGE_SIZE/UPROBE_XOL_SLOT_BYTES)
#define MAX_UPROBE_XOL_SLOTS		UINSNS_PER_PAGE

static struct rb_root uprobes_tree = RB_ROOT;
/*
 * allows us to skip the uprobe_mmap if there are no uprobe events active
 * at this time.  Probably a fine grained per inode count is better?
 */
#define no_uprobe_events()	RB_EMPTY_ROOT(&uprobes_tree)

static DEFINE_SPINLOCK(uprobes_treelock);	/* serialize rbtree access */

#define UPROBES_HASH_SZ	13
/* serialize uprobe->pending_list */
static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
#define uprobes_mmap_hash(v)	(&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])

static struct percpu_rw_semaphore dup_mmap_sem;

/* Have a copy of original instruction */
#define UPROBE_COPY_INSN	0

struct uprobe {
	struct rb_node		rb_node;	/* node in the rb tree */
	atomic_t		ref;
	struct rw_semaphore	register_rwsem;
	struct rw_semaphore	consumer_rwsem;
	struct list_head	pending_list;
	struct uprobe_consumer	*consumers;
	struct inode		*inode;		/* Also hold a ref to inode */
	loff_t			offset;
	unsigned long		flags;

	/*
	 * The generic code assumes that it has two members of unknown type
	 * owned by the arch-specific code:
	 *
	 * 	insn -	copy_insn() saves the original instruction here for
	 *		arch_uprobe_analyze_insn().
	 *
	 *	ixol -	potentially modified instruction to execute out of
	 *		line, copied to xol_area by xol_get_insn_slot().
	 */
	struct arch_uprobe	arch;
};

/*
 * Execute out of line area: anonymous executable mapping installed
 * by the probed task to execute the copy of the original instruction
 * mangled by set_swbp().
 *
 * On a breakpoint hit, thread contests for a slot.  It frees the
 * slot after singlestep. Currently a fixed number of slots are
 * allocated.
 */
struct xol_area {
	wait_queue_head_t 		wq;		/* if all slots are busy */
	atomic_t 			slot_count;	/* number of in-use slots */
	unsigned long 			*bitmap;	/* 0 = free slot */

	struct vm_special_mapping	xol_mapping;
	struct page 			*pages[2];
	/*
	 * We keep the vma's vm_start rather than a pointer to the vma
	 * itself.  The probed process or a naughty kernel module could make
	 * the vma go away, and we must handle that reasonably gracefully.
	 */
	unsigned long 			vaddr;		/* Page(s) of instruction slots */
};

/*
 * valid_vma: Verify if the specified vma is an executable vma
 * Relax restrictions while unregistering: vm_flags might have
 * changed after breakpoint was inserted.
 *	- is_register: indicates if we are in register context.
 *	- Return 1 if the specified virtual address is in an
 *	  executable vma.
 */
static bool valid_vma(struct vm_area_struct *vma, bool is_register)
{
	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE;

	if (is_register)
		flags |= VM_WRITE;

	return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC;
}

static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
{
	return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
}

static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr)
{
	return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start);
}

/**
 * __replace_page - replace page in vma by new page.
 * based on replace_page in mm/ksm.c
 *
 * @vma:      vma that holds the pte pointing to page
 * @addr:     address the old @page is mapped at
 * @page:     the cowed page we are replacing by kpage
 * @kpage:    the modified page we replace page by
 *
 * Returns 0 on success, -EFAULT on failure.
 */
static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
				struct page *page, struct page *kpage)
{
	struct mm_struct *mm = vma->vm_mm;
	spinlock_t *ptl;
	pte_t *ptep;
	int err;
	/* For mmu_notifiers */
	const unsigned long mmun_start = addr;
	const unsigned long mmun_end   = addr + PAGE_SIZE;
	struct mem_cgroup *memcg;

	err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg,
			false);
	if (err)
		return err;

	/* For try_to_free_swap() and munlock_vma_page() below */
	lock_page(page);

	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
	err = -EAGAIN;
	ptep = page_check_address(page, mm, addr, &ptl, 0);
	if (!ptep)
		goto unlock;

	get_page(kpage);
	page_add_new_anon_rmap(kpage, vma, addr, false);
	mem_cgroup_commit_charge(kpage, memcg, false, false);
	lru_cache_add_active_or_unevictable(kpage, vma);

	if (!PageAnon(page)) {
		dec_mm_counter(mm, mm_counter_file(page));
		inc_mm_counter(mm, MM_ANONPAGES);
	}

	flush_cache_page(vma, addr, pte_pfn(*ptep));
	ptep_clear_flush_notify(vma, addr, ptep);
	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));

	page_remove_rmap(page, false);
	if (!page_mapped(page))
		try_to_free_swap(page);
	pte_unmap_unlock(ptep, ptl);

	if (vma->vm_flags & VM_LOCKED)
		munlock_vma_page(page);
	put_page(page);

	err = 0;
 unlock:
	mem_cgroup_cancel_charge(kpage, memcg, false);
	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
	unlock_page(page);
	return err;
}

/**
 * is_swbp_insn - check if instruction is breakpoint instruction.
 * @insn: instruction to be checked.
 * Default implementation of is_swbp_insn
 * Returns true if @insn is a breakpoint instruction.
 */
bool __weak is_swbp_insn(uprobe_opcode_t *insn)
{
	return *insn == UPROBE_SWBP_INSN;
}

/**
 * is_trap_insn - check if instruction is breakpoint instruction.
 * @insn: instruction to be checked.
 * Default implementation of is_trap_insn
 * Returns true if @insn is a breakpoint instruction.
 *
 * This function is needed for the case where an architecture has multiple
 * trap instructions (like powerpc).
 */
bool __weak is_trap_insn(uprobe_opcode_t *insn)
{
	return is_swbp_insn(insn);
}

static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len)
{
	void *kaddr = kmap_atomic(page);
	memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len);
	kunmap_atomic(kaddr);
}

static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len)
{
	void *kaddr = kmap_atomic(page);
	memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len);
	kunmap_atomic(kaddr);
}

static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
{
	uprobe_opcode_t old_opcode;
	bool is_swbp;

	/*
	 * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here.
	 * We do not check if it is any other 'trap variant' which could
	 * be conditional trap instruction such as the one powerpc supports.
	 *
	 * The logic is that we do not care if the underlying instruction
	 * is a trap variant; uprobes always wins over any other (gdb)
	 * breakpoint.
	 */
	copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE);
	is_swbp = is_swbp_insn(&old_opcode);

	if (is_swbp_insn(new_opcode)) {
		if (is_swbp)		/* register: already installed? */
			return 0;
	} else {
		if (!is_swbp)		/* unregister: was it changed by us? */
			return 0;
	}

	return 1;
}

/*
 * NOTE:
 * Expect the breakpoint instruction to be the smallest size instruction for
 * the architecture. If an arch has variable length instruction and the
 * breakpoint instruction is not of the smallest length instruction
 * supported by that architecture then we need to modify is_trap_at_addr and
 * uprobe_write_opcode accordingly. This would never be a problem for archs
 * that have fixed length instructions.
 *
 * uprobe_write_opcode - write the opcode at a given virtual address.
 * @mm: the probed process address space.
 * @vaddr: the virtual address to store the opcode.
 * @opcode: opcode to be written at @vaddr.
 *
 * Called with mm->mmap_sem held for write.
 * Return 0 (success) or a negative errno.
 */
int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
			uprobe_opcode_t opcode)
{
	struct page *old_page, *new_page;
	struct vm_area_struct *vma;
	int ret;

retry:
	/* Read the page with vaddr into memory */
	ret = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
	if (ret <= 0)
		return ret;

	ret = verify_opcode(old_page, vaddr, &opcode);
	if (ret <= 0)
		goto put_old;

	ret = anon_vma_prepare(vma);
	if (ret)
		goto put_old;

	ret = -ENOMEM;
	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
	if (!new_page)
		goto put_old;

	__SetPageUptodate(new_page);
	copy_highpage(new_page, old_page);
	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);

	ret = __replace_page(vma, vaddr, old_page, new_page);
	put_page(new_page);
put_old:
	put_page(old_page);

	if (unlikely(ret == -EAGAIN))
		goto retry;
	return ret;
}

/**
 * set_swbp - store breakpoint at a given address.
 * @auprobe: arch specific probepoint information.
 * @mm: the probed process address space.
 * @vaddr: the virtual address to insert the opcode.
 *
 * For mm @mm, store the breakpoint instruction at @vaddr.
 * Return 0 (success) or a negative errno.
 */
int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
	return uprobe_write_opcode(mm, vaddr, UPROBE_SWBP_INSN);
}

/**
 * set_orig_insn - Restore the original instruction.
 * @mm: the probed process address space.
 * @auprobe: arch specific probepoint information.
 * @vaddr: the virtual address to insert the opcode.
 *
 * For mm @mm, restore the original opcode (opcode) at @vaddr.
 * Return 0 (success) or a negative errno.
 */
int __weak
set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
}

static struct uprobe *get_uprobe(struct uprobe *uprobe)
{
	atomic_inc(&uprobe->ref);
	return uprobe;
}

static void put_uprobe(struct uprobe *uprobe)
{
	if (atomic_dec_and_test(&uprobe->ref))
		kfree(uprobe);
}

static int match_uprobe(struct uprobe *l, struct uprobe *r)
{
	if (l->inode < r->inode)
		return -1;

	if (l->inode > r->inode)
		return 1;

	if (l->offset < r->offset)
		return -1;

	if (l->offset > r->offset)
		return 1;

	return 0;
}

static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe u = { .inode = inode, .offset = offset };
	struct rb_node *n = uprobes_tree.rb_node;
	struct uprobe *uprobe;
	int match;

	while (n) {
		uprobe = rb_entry(n, struct uprobe, rb_node);
		match = match_uprobe(&u, uprobe);
		if (!match)
			return get_uprobe(uprobe);

		if (match < 0)
			n = n->rb_left;
		else
			n = n->rb_right;
	}
	return NULL;
}

/*
 * Find a uprobe corresponding to a given inode:offset
 * Acquires uprobes_treelock
 */
static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe *uprobe;

	spin_lock(&uprobes_treelock);
	uprobe = __find_uprobe(inode, offset);
	spin_unlock(&uprobes_treelock);

	return uprobe;
}

static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
{
	struct rb_node **p = &uprobes_tree.rb_node;
	struct rb_node *parent = NULL;
	struct uprobe *u;
	int match;

	while (*p) {
		parent = *p;
		u = rb_entry(parent, struct uprobe, rb_node);
		match = match_uprobe(uprobe, u);
		if (!match)
			return get_uprobe(u);

		if (match < 0)
			p = &parent->rb_left;
		else
			p = &parent->rb_right;

	}

	u = NULL;
	rb_link_node(&uprobe->rb_node, parent, p);
	rb_insert_color(&uprobe->rb_node, &uprobes_tree);
	/* get access + creation ref */
	atomic_set(&uprobe->ref, 2);

	return u;
}

/*
 * Acquire uprobes_treelock.
 * Matching uprobe already exists in rbtree;
 *	increment (access refcount) and return the matching uprobe.
 *
 * No matching uprobe; insert the uprobe in rb_tree;
 *	get a double refcount (access + creation) and return NULL.
 */
static struct uprobe *insert_uprobe(struct uprobe *uprobe)
{
	struct uprobe *u;

	spin_lock(&uprobes_treelock);
	u = __insert_uprobe(uprobe);
	spin_unlock(&uprobes_treelock);

	return u;
}

static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
{
	struct uprobe *uprobe, *cur_uprobe;

	uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL);
	if (!uprobe)
		return NULL;

	uprobe->inode = igrab(inode);
	uprobe->offset = offset;
	init_rwsem(&uprobe->register_rwsem);
	init_rwsem(&uprobe->consumer_rwsem);

	/* add to uprobes_tree, sorted on inode:offset */
	cur_uprobe = insert_uprobe(uprobe);
	/* a uprobe exists for this inode:offset combination */
	if (cur_uprobe) {
		kfree(uprobe);
		uprobe = cur_uprobe;
		iput(inode);
	}

	return uprobe;
}

static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	down_write(&uprobe->consumer_rwsem);
	uc->next = uprobe->consumers;
	uprobe->consumers = uc;
	up_write(&uprobe->consumer_rwsem);
}

/*
 * For uprobe @uprobe, delete the consumer @uc.
 * Return true if the @uc is deleted successfully
 * or return false.
 */
static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	struct uprobe_consumer **con;
	bool ret = false;

	down_write(&uprobe->consumer_rwsem);
	for (con = &uprobe->consumers; *con; con = &(*con)->next) {
		if (*con == uc) {
			*con = uc->next;
			ret = true;
			break;
		}
	}
	up_write(&uprobe->consumer_rwsem);

	return ret;
}

static int __copy_insn(struct address_space *mapping, struct file *filp,
			void *insn, int nbytes, loff_t offset)
{
	struct page *page;
	/*
	 * Ensure that the page that has the original instruction is populated
	 * and in page-cache. If ->readpage == NULL it must be shmem_mapping(),
	 * see uprobe_register().
	 */
	if (mapping->a_ops->readpage)
		page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp);
	else
		page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT);
	if (IS_ERR(page))
		return PTR_ERR(page);

	copy_from_page(page, offset, insn, nbytes);
	put_page(page);

	return 0;
}

static int copy_insn(struct uprobe *uprobe, struct file *filp)
{
	struct address_space *mapping = uprobe->inode->i_mapping;
	loff_t offs = uprobe->offset;
	void *insn = &uprobe->arch.insn;
	int size = sizeof(uprobe->arch.insn);
	int len, err = -EIO;

	/* Copy only available bytes, -EIO if nothing was read */
	do {
		if (offs >= i_size_read(uprobe->inode))
			break;

		len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK));
		err = __copy_insn(mapping, filp, insn, len, offs);
		if (err)
			break;

		insn += len;
		offs += len;
		size -= len;
	} while (size);

	return err;
}

static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
				struct mm_struct *mm, unsigned long vaddr)
{
	int ret = 0;

	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
		return ret;

	/* TODO: move this into _register, until then we abuse this sem. */
	down_write(&uprobe->consumer_rwsem);
	if (test_bit(UPROBE_COPY_INSN, &uprobe->flags))
		goto out;

	ret = copy_insn(uprobe, file);
	if (ret)
		goto out;

	ret = -ENOTSUPP;
	if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
		goto out;

	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
	if (ret)
		goto out;

	/* uprobe_write_opcode() assumes we don't cross page boundary */
	BUG_ON((uprobe->offset & ~PAGE_MASK) +
			UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);

	smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
	set_bit(UPROBE_COPY_INSN, &uprobe->flags);

 out:
	up_write(&uprobe->consumer_rwsem);

	return ret;
}

static inline bool consumer_filter(struct uprobe_consumer *uc,
				   enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
	return !uc->filter || uc->filter(uc, ctx, mm);
}

static bool filter_chain(struct uprobe *uprobe,
			 enum uprobe_filter_ctx ctx, struct mm_struct *mm)
{
	struct uprobe_consumer *uc;
	bool ret = false;

	down_read(&uprobe->consumer_rwsem);
	for (uc = uprobe->consumers; uc; uc = uc->next) {
		ret = consumer_filter(uc, ctx, mm);
		if (ret)
			break;
	}
	up_read(&uprobe->consumer_rwsem);

	return ret;
}

static int
install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
			struct vm_area_struct *vma, unsigned long vaddr)
{
	bool first_uprobe;
	int ret;

	ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr);
	if (ret)
		return ret;

	/*
	 * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
	 * the task can hit this breakpoint right after __replace_page().
	 */
	first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags);
	if (first_uprobe)
		set_bit(MMF_HAS_UPROBES, &mm->flags);

	ret = set_swbp(&uprobe->arch, mm, vaddr);
	if (!ret)
		clear_bit(MMF_RECALC_UPROBES, &mm->flags);
	else if (first_uprobe)
		clear_bit(MMF_HAS_UPROBES, &mm->flags);

	return ret;
}

static int
remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
{
	set_bit(MMF_RECALC_UPROBES, &mm->flags);
	return set_orig_insn(&uprobe->arch, mm, vaddr);
}

static inline bool uprobe_is_active(struct uprobe *uprobe)
{
	return !RB_EMPTY_NODE(&uprobe->rb_node);
}
/*
 * There could be threads that have already hit the breakpoint. They
 * will recheck the current insn and restart if find_uprobe() fails.
 * See find_active_uprobe().
 */
static void delete_uprobe(struct uprobe *uprobe)
{
	if (WARN_ON(!uprobe_is_active(uprobe)))
		return;

	spin_lock(&uprobes_treelock);
	rb_erase(&uprobe->rb_node, &uprobes_tree);
	spin_unlock(&uprobes_treelock);
	RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */
	iput(uprobe->inode);
	put_uprobe(uprobe);
}

struct map_info {
	struct map_info *next;
	struct mm_struct *mm;
	unsigned long vaddr;
};

static inline struct map_info *free_map_info(struct map_info *info)
{
	struct map_info *next = info->next;
	kfree(info);
	return next;
}

static struct map_info *
build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
{
	unsigned long pgoff = offset >> PAGE_SHIFT;
	struct vm_area_struct *vma;
	struct map_info *curr = NULL;
	struct map_info *prev = NULL;
	struct map_info *info;
	int more = 0;

 again:
	i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
		if (!valid_vma(vma, is_register))
			continue;

		if (!prev && !more) {
			/*
			 * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through
			 * reclaim. This is optimistic, no harm done if it fails.
			 */
			prev = kmalloc(sizeof(struct map_info),
					GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN);
			if (prev)
				prev->next = NULL;
		}
		if (!prev) {
			more++;
			continue;
		}

		if (!atomic_inc_not_zero(&vma->vm_mm->mm_users))
			continue;

		info = prev;
		prev = prev->next;
		info->next = curr;
		curr = info;

		info->mm = vma->vm_mm;
		info->vaddr = offset_to_vaddr(vma, offset);
	}
	i_mmap_unlock_read(mapping);

	if (!more)
		goto out;

	prev = curr;
	while (curr) {
		mmput(curr->mm);
		curr = curr->next;
	}

	do {
		info = kmalloc(sizeof(struct map_info), GFP_KERNEL);
		if (!info) {
			curr = ERR_PTR(-ENOMEM);
			goto out;
		}
		info->next = prev;
		prev = info;
	} while (--more);

	goto again;
 out:
	while (prev)
		prev = free_map_info(prev);
	return curr;
}

static int
register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
{
	bool is_register = !!new;
	struct map_info *info;
	int err = 0;

	percpu_down_write(&dup_mmap_sem);
	info = build_map_info(uprobe->inode->i_mapping,
					uprobe->offset, is_register);
	if (IS_ERR(info)) {
		err = PTR_ERR(info);
		goto out;
	}

	while (info) {
		struct mm_struct *mm = info->mm;
		struct vm_area_struct *vma;

		if (err && is_register)
			goto free;

		down_write(&mm->mmap_sem);
		vma = find_vma(mm, info->vaddr);
		if (!vma || !valid_vma(vma, is_register) ||
		    file_inode(vma->vm_file) != uprobe->inode)
			goto unlock;

		if (vma->vm_start > info->vaddr ||
		    vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
			goto unlock;

		if (is_register) {
			/* consult only the "caller", new consumer. */
			if (consumer_filter(new,
					UPROBE_FILTER_REGISTER, mm))
				err = install_breakpoint(uprobe, mm, vma, info->vaddr);
		} else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) {
			if (!filter_chain(uprobe,
					UPROBE_FILTER_UNREGISTER, mm))
				err |= remove_breakpoint(uprobe, mm, info->vaddr);
		}

 unlock:
		up_write(&mm->mmap_sem);
 free:
		mmput(mm);
		info = free_map_info(info);
	}
 out:
	percpu_up_write(&dup_mmap_sem);
	return err;
}

static int __uprobe_register(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	consumer_add(uprobe, uc);
	return register_for_each_vma(uprobe, uc);
}

static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
{
	int err;

	if (WARN_ON(!consumer_del(uprobe, uc)))
		return;

	err = register_for_each_vma(uprobe, NULL);
	/* TODO : cant unregister? schedule a worker thread */
	if (!uprobe->consumers && !err)
		delete_uprobe(uprobe);
}

/*
 * uprobe_register - register a probe
 * @inode: the file in which the probe has to be placed.
 * @offset: offset from the start of the file.
 * @uc: information on howto handle the probe..
 *
 * Apart from the access refcount, uprobe_register() takes a creation
 * refcount (thro alloc_uprobe) if and only if this @uprobe is getting
 * inserted into the rbtree (i.e first consumer for a @inode:@offset
 * tuple).  Creation refcount stops uprobe_unregister from freeing the
 * @uprobe even before the register operation is complete. Creation
 * refcount is released when the last @uc for the @uprobe
 * unregisters.
 *
 * Return errno if it cannot successully install probes
 * else return 0 (success)
 */
int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
{
	struct uprobe *uprobe;
	int ret;

	/* Uprobe must have at least one set consumer */
	if (!uc->handler && !uc->ret_handler)
		return -EINVAL;

	/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
	if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping))
		return -EIO;
	/* Racy, just to catch the obvious mistakes */
	if (offset > i_size_read(inode))
		return -EINVAL;

 retry:
	uprobe = alloc_uprobe(inode, offset);
	if (!uprobe)
		return -ENOMEM;
	/*
	 * We can race with uprobe_unregister()->delete_uprobe().
	 * Check uprobe_is_active() and retry if it is false.
	 */
	down_write(&uprobe->register_rwsem);
	ret = -EAGAIN;
	if (likely(uprobe_is_active(uprobe))) {
		ret = __uprobe_register(uprobe, uc);
		if (ret)
			__uprobe_unregister(uprobe, uc);
	}
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);

	if (unlikely(ret == -EAGAIN))
		goto retry;
	return ret;
}
EXPORT_SYMBOL_GPL(uprobe_register);

/*
 * uprobe_apply - unregister a already registered probe.
 * @inode: the file in which the probe has to be removed.
 * @offset: offset from the start of the file.
 * @uc: consumer which wants to add more or remove some breakpoints
 * @add: add or remove the breakpoints
 */
int uprobe_apply(struct inode *inode, loff_t offset,
			struct uprobe_consumer *uc, bool add)
{
	struct uprobe *uprobe;
	struct uprobe_consumer *con;
	int ret = -ENOENT;

	uprobe = find_uprobe(inode, offset);
	if (WARN_ON(!uprobe))
		return ret;

	down_write(&uprobe->register_rwsem);
	for (con = uprobe->consumers; con && con != uc ; con = con->next)
		;
	if (con)
		ret = register_for_each_vma(uprobe, add ? uc : NULL);
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);

	return ret;
}

/*
 * uprobe_unregister - unregister a already registered probe.
 * @inode: the file in which the probe has to be removed.
 * @offset: offset from the start of the file.
 * @uc: identify which probe if multiple probes are colocated.
 */
void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
{
	struct uprobe *uprobe;

	uprobe = find_uprobe(inode, offset);
	if (WARN_ON(!uprobe))
		return;

	down_write(&uprobe->register_rwsem);
	__uprobe_unregister(uprobe, uc);
	up_write(&uprobe->register_rwsem);
	put_uprobe(uprobe);
}
EXPORT_SYMBOL_GPL(uprobe_unregister);

static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm)
{
	struct vm_area_struct *vma;
	int err = 0;

	down_read(&mm->mmap_sem);
	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		unsigned long vaddr;
		loff_t offset;

		if (!valid_vma(vma, false) ||
		    file_inode(vma->vm_file) != uprobe->inode)
			continue;

		offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
		if (uprobe->offset <  offset ||
		    uprobe->offset >= offset + vma->vm_end - vma->vm_start)
			continue;

		vaddr = offset_to_vaddr(vma, uprobe->offset);
		err |= remove_breakpoint(uprobe, mm, vaddr);
	}
	up_read(&mm->mmap_sem);

	return err;
}

static struct rb_node *
find_node_in_range(struct inode *inode, loff_t min, loff_t max)
{
	struct rb_node *n = uprobes_tree.rb_node;

	while (n) {
		struct uprobe *u = rb_entry(n, struct uprobe, rb_node);

		if (inode < u->inode) {
			n = n->rb_left;
		} else if (inode > u->inode) {
			n = n->rb_right;
		} else {
			if (max < u->offset)
				n = n->rb_left;
			else if (min > u->offset)
				n = n->rb_right;
			else
				break;
		}
	}

	return n;
}

/*
 * For a given range in vma, build a list of probes that need to be inserted.
 */
static void build_probe_list(struct inode *inode,
				struct vm_area_struct *vma,
				unsigned long start, unsigned long end,
				struct list_head *head)
{
	loff_t min, max;
	struct rb_node *n, *t;
	struct uprobe *u;

	INIT_LIST_HEAD(head);
	min = vaddr_to_offset(vma, start);
	max = min + (end - start) - 1;

	spin_lock(&uprobes_treelock);
	n = find_node_in_range(inode, min, max);
	if (n) {
		for (t = n; t; t = rb_prev(t)) {
			u = rb_entry(t, struct uprobe, rb_node);
			if (u->inode != inode || u->offset < min)
				break;
			list_add(&u->pending_list, head);
			get_uprobe(u);
		}
		for (t = n; (t = rb_next(t)); ) {
			u = rb_entry(t, struct uprobe, rb_node);
			if (u->inode != inode || u->offset > max)
				break;
			list_add(&u->pending_list, head);
			get_uprobe(u);
		}
	}
	spin_unlock(&uprobes_treelock);
}

/*
 * Called from mmap_region/vma_adjust with mm->mmap_sem acquired.
 *
 * Currently we ignore all errors and always return 0, the callers
 * can't handle the failure anyway.
 */
int uprobe_mmap(struct vm_area_struct *vma)
{
	struct list_head tmp_list;
	struct uprobe *uprobe, *u;
	struct inode *inode;

	if (no_uprobe_events() || !valid_vma(vma, true))
		return 0;

	inode = file_inode(vma->vm_file);
	if (!inode)
		return 0;

	mutex_lock(uprobes_mmap_hash(inode));
	build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
	/*
	 * We can race with uprobe_unregister(), this uprobe can be already
	 * removed. But in this case filter_chain() must return false, all
	 * consumers have gone away.
	 */
	list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
		if (!fatal_signal_pending(current) &&
		    filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) {
			unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
			install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
		}
		put_uprobe(uprobe);
	}
	mutex_unlock(uprobes_mmap_hash(inode));

	return 0;
}

static bool
vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
	loff_t min, max;
	struct inode *inode;
	struct rb_node *n;

	inode = file_inode(vma->vm_file);

	min = vaddr_to_offset(vma, start);
	max = min + (end - start) - 1;

	spin_lock(&uprobes_treelock);
	n = find_node_in_range(inode, min, max);
	spin_unlock(&uprobes_treelock);

	return !!n;
}

/*
 * Called in context of a munmap of a vma.
 */
void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
	if (no_uprobe_events() || !valid_vma(vma, false))
		return;

	if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
		return;

	if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) ||
	     test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags))
		return;

	if (vma_has_uprobes(vma, start, end))
		set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags);
}

/* Slot allocation for XOL */
static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
{
	struct vm_area_struct *vma;
	int ret;

	down_write(&mm->mmap_sem);
	if (mm->uprobes_state.xol_area) {
		ret = -EALREADY;
		goto fail;
	}

	if (!area->vaddr) {
		/* Try to map as high as possible, this is only a hint. */
		area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE,
						PAGE_SIZE, 0, 0);
		if (area->vaddr & ~PAGE_MASK) {
			ret = area->vaddr;
			goto fail;
		}
	}

	vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE,
				VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO,
				&area->xol_mapping);
	if (IS_ERR(vma)) {
		ret = PTR_ERR(vma);
		goto fail;
	}

	ret = 0;
	smp_wmb();	/* pairs with get_xol_area() */
	mm->uprobes_state.xol_area = area;
 fail:
	up_write(&mm->mmap_sem);

	return ret;
}

static struct xol_area *__create_xol_area(unsigned long vaddr)
{
	struct mm_struct *mm = current->mm;
	uprobe_opcode_t insn = UPROBE_SWBP_INSN;
	struct xol_area *area;

	area = kmalloc(sizeof(*area), GFP_KERNEL);
	if (unlikely(!area))
		goto out;

	area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL);
	if (!area->bitmap)
		goto free_area;

	area->xol_mapping.name = "[uprobes]";
	area->xol_mapping.fault = NULL;
	area->xol_mapping.pages = area->pages;
	area->pages[0] = alloc_page(GFP_HIGHUSER);
	if (!area->pages[0])
		goto free_bitmap;
	area->pages[1] = NULL;

	area->vaddr = vaddr;
	init_waitqueue_head(&area->wq);
	/* Reserve the 1st slot for get_trampoline_vaddr() */
	set_bit(0, area->bitmap);
	atomic_set(&area->slot_count, 1);
	copy_to_page(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);

	if (!xol_add_vma(mm, area))
		return area;

	__free_page(area->pages[0]);
 free_bitmap:
	kfree(area->bitmap);
 free_area:
	kfree(area);
 out:
	return NULL;
}

/*
 * get_xol_area - Allocate process's xol_area if necessary.
 * This area will be used for storing instructions for execution out of line.
 *
 * Returns the allocated area or NULL.
 */
static struct xol_area *get_xol_area(void)
{
	struct mm_struct *mm = current->mm;
	struct xol_area *area;

	if (!mm->uprobes_state.xol_area)
		__create_xol_area(0);

	area = mm->uprobes_state.xol_area;
	smp_read_barrier_depends();	/* pairs with wmb in xol_add_vma() */
	return area;
}

/*
 * uprobe_clear_state - Free the area allocated for slots.
 */
void uprobe_clear_state(struct mm_struct *mm)
{
	struct xol_area *area = mm->uprobes_state.xol_area;

	if (!area)
		return;

	put_page(area->pages[0]);
	kfree(area->bitmap);
	kfree(area);
}

void uprobe_start_dup_mmap(void)
{
	percpu_down_read(&dup_mmap_sem);
}

void uprobe_end_dup_mmap(void)
{
	percpu_up_read(&dup_mmap_sem);
}

void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
{
	newmm->uprobes_state.xol_area = NULL;

	if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) {
		set_bit(MMF_HAS_UPROBES, &newmm->flags);
		/* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */
		set_bit(MMF_RECALC_UPROBES, &newmm->flags);
	}
}

/*
 *  - search for a free slot.
 */
static unsigned long xol_take_insn_slot(struct xol_area *area)
{
	unsigned long slot_addr;
	int slot_nr;

	do {
		slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE);
		if (slot_nr < UINSNS_PER_PAGE) {
			if (!test_and_set_bit(slot_nr, area->bitmap))
				break;

			slot_nr = UINSNS_PER_PAGE;
			continue;
		}
		wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE));
	} while (slot_nr >= UINSNS_PER_PAGE);

	slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES);
	atomic_inc(&area->slot_count);

	return slot_addr;
}

/*
 * xol_get_insn_slot - allocate a slot for xol.
 * Returns the allocated slot address or 0.
 */
static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
{
	struct xol_area *area;
	unsigned long xol_vaddr;

	area = get_xol_area();
	if (!area)
		return 0;

	xol_vaddr = xol_take_insn_slot(area);
	if (unlikely(!xol_vaddr))
		return 0;

	arch_uprobe_copy_ixol(area->pages[0], xol_vaddr,
			      &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));

	return xol_vaddr;
}

/*
 * xol_free_insn_slot - If slot was earlier allocated by
 * @xol_get_insn_slot(), make the slot available for
 * subsequent requests.
 */
static void xol_free_insn_slot(struct task_struct *tsk)
{
	struct xol_area *area;
	unsigned long vma_end;
	unsigned long slot_addr;

	if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask)
		return;

	slot_addr = tsk->utask->xol_vaddr;
	if (unlikely(!slot_addr))
		return;

	area = tsk->mm->uprobes_state.xol_area;
	vma_end = area->vaddr + PAGE_SIZE;
	if (area->vaddr <= slot_addr && slot_addr < vma_end) {
		unsigned long offset;
		int slot_nr;

		offset = slot_addr - area->vaddr;
		slot_nr = offset / UPROBE_XOL_SLOT_BYTES;
		if (slot_nr >= UINSNS_PER_PAGE)
			return;

		clear_bit(slot_nr, area->bitmap);
		atomic_dec(&area->slot_count);
		smp_mb__after_atomic(); /* pairs with prepare_to_wait() */
		if (waitqueue_active(&area->wq))
			wake_up(&area->wq);

		tsk->utask->xol_vaddr = 0;
	}
}

void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
				  void *src, unsigned long len)
{
	/* Initialize the slot */
	copy_to_page(page, vaddr, src, len);

	/*
	 * We probably need flush_icache_user_range() but it needs vma.
	 * This should work on most of architectures by default. If
	 * architecture needs to do something different it can define
	 * its own version of the function.
	 */
	flush_dcache_page(page);
}

/**
 * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
 * @regs: Reflects the saved state of the task after it has hit a breakpoint
 * instruction.
 * Return the address of the breakpoint instruction.
 */
unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
{
	return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
}

unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
{
	struct uprobe_task *utask = current->utask;

	if (unlikely(utask && utask->active_uprobe))
		return utask->vaddr;

	return instruction_pointer(regs);
}

static struct return_instance *free_ret_instance(struct return_instance *ri)
{
	struct return_instance *next = ri->next;
	put_uprobe(ri->uprobe);
	kfree(ri);
	return next;
}

/*
 * Called with no locks held.
 * Called in context of a exiting or a exec-ing thread.
 */
void uprobe_free_utask(struct task_struct *t)
{
	struct uprobe_task *utask = t->utask;
	struct return_instance *ri;

	if (!utask)
		return;

	if (utask->active_uprobe)
		put_uprobe(utask->active_uprobe);

	ri = utask->return_instances;
	while (ri)
		ri = free_ret_instance(ri);

	xol_free_insn_slot(t);
	kfree(utask);
	t->utask = NULL;
}

/*
 * Allocate a uprobe_task object for the task if if necessary.
 * Called when the thread hits a breakpoint.
 *
 * Returns:
 * - pointer to new uprobe_task on success
 * - NULL otherwise
 */
static struct uprobe_task *get_utask(void)
{
	if (!current->utask)
		current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
	return current->utask;
}

static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask)
{
	struct uprobe_task *n_utask;
	struct return_instance **p, *o, *n;

	n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL);
	if (!n_utask)
		return -ENOMEM;
	t->utask = n_utask;

	p = &n_utask->return_instances;
	for (o = o_utask->return_instances; o; o = o->next) {
		n = kmalloc(sizeof(struct return_instance), GFP_KERNEL);
		if (!n)
			return -ENOMEM;

		*n = *o;
		get_uprobe(n->uprobe);
		n->next = NULL;

		*p = n;
		p = &n->next;
		n_utask->depth++;
	}

	return 0;
}

static void uprobe_warn(struct task_struct *t, const char *msg)
{
	pr_warn("uprobe: %s:%d failed to %s\n",
			current->comm, current->pid, msg);
}

static void dup_xol_work(struct callback_head *work)
{
	if (current->flags & PF_EXITING)
		return;

	if (!__create_xol_area(current->utask->dup_xol_addr))
		uprobe_warn(current, "dup xol area");
}

/*
 * Called in context of a new clone/fork from copy_process.
 */
void uprobe_copy_process(struct task_struct *t, unsigned long flags)
{
	struct uprobe_task *utask = current->utask;
	struct mm_struct *mm = current->mm;
	struct xol_area *area;

	t->utask = NULL;

	if (!utask || !utask->return_instances)
		return;

	if (mm == t->mm && !(flags & CLONE_VFORK))
		return;

	if (dup_utask(t, utask))
		return uprobe_warn(t, "dup ret instances");

	/* The task can fork() after dup_xol_work() fails */
	area = mm->uprobes_state.xol_area;
	if (!area)
		return uprobe_warn(t, "dup xol area");

	if (mm == t->mm)
		return;

	t->utask->dup_xol_addr = area->vaddr;
	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
	task_work_add(t, &t->utask->dup_xol_work, true);
}

/*
 * Current area->vaddr notion assume the trampoline address is always
 * equal area->vaddr.
 *
 * Returns -1 in case the xol_area is not allocated.
 */
static unsigned long get_trampoline_vaddr(void)
{
	struct xol_area *area;
	unsigned long trampoline_vaddr = -1;

	area = current->mm->uprobes_state.xol_area;
	smp_read_barrier_depends();
	if (area)
		trampoline_vaddr = area->vaddr;

	return trampoline_vaddr;
}

static void cleanup_return_instances(struct uprobe_task *utask, bool chained,
					struct pt_regs *regs)
{
	struct return_instance *ri = utask->return_instances;
	enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL;

	while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) {
		ri = free_ret_instance(ri);
		utask->depth--;
	}
	utask->return_instances = ri;
}

static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
{
	struct return_instance *ri;
	struct uprobe_task *utask;
	unsigned long orig_ret_vaddr, trampoline_vaddr;
	bool chained;

	if (!get_xol_area())
		return;

	utask = get_utask();
	if (!utask)
		return;

	if (utask->depth >= MAX_URETPROBE_DEPTH) {
		printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to"
				" nestedness limit pid/tgid=%d/%d\n",
				current->pid, current->tgid);
		return;
	}

	ri = kmalloc(sizeof(struct return_instance), GFP_KERNEL);
	if (!ri)
		return;

	trampoline_vaddr = get_trampoline_vaddr();
	orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
	if (orig_ret_vaddr == -1)
		goto fail;

	/* drop the entries invalidated by longjmp() */
	chained = (orig_ret_vaddr == trampoline_vaddr);
	cleanup_return_instances(utask, chained, regs);

	/*
	 * We don't want to keep trampoline address in stack, rather keep the
	 * original return address of first caller thru all the consequent
	 * instances. This also makes breakpoint unwrapping easier.
	 */
	if (chained) {
		if (!utask->return_instances) {
			/*
			 * This situation is not possible. Likely we have an
			 * attack from user-space.
			 */
			uprobe_warn(current, "handle tail call");
			goto fail;
		}
		orig_ret_vaddr = utask->return_instances->orig_ret_vaddr;
	}

	ri->uprobe = get_uprobe(uprobe);
	ri->func = instruction_pointer(regs);
	ri->stack = user_stack_pointer(regs);
	ri->orig_ret_vaddr = orig_ret_vaddr;
	ri->chained = chained;

	utask->depth++;
	ri->next = utask->return_instances;
	utask->return_instances = ri;

	return;
 fail:
	kfree(ri);
}

/* Prepare to single-step probed instruction out of line. */
static int
pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr)
{
	struct uprobe_task *utask;
	unsigned long xol_vaddr;
	int err;

	utask = get_utask();
	if (!utask)
		return -ENOMEM;

	xol_vaddr = xol_get_insn_slot(uprobe);
	if (!xol_vaddr)
		return -ENOMEM;

	utask->xol_vaddr = xol_vaddr;
	utask->vaddr = bp_vaddr;

	err = arch_uprobe_pre_xol(&uprobe->arch, regs);
	if (unlikely(err)) {
		xol_free_insn_slot(current);
		return err;
	}

	utask->active_uprobe = uprobe;
	utask->state = UTASK_SSTEP;
	return 0;
}

/*
 * If we are singlestepping, then ensure this thread is not connected to
 * non-fatal signals until completion of singlestep.  When xol insn itself
 * triggers the signal,  restart the original insn even if the task is
 * already SIGKILL'ed (since coredump should report the correct ip).  This
 * is even more important if the task has a handler for SIGSEGV/etc, The
 * _same_ instruction should be repeated again after return from the signal
 * handler, and SSTEP can never finish in this case.
 */
bool uprobe_deny_signal(void)
{
	struct task_struct *t = current;
	struct uprobe_task *utask = t->utask;

	if (likely(!utask || !utask->active_uprobe))
		return false;

	WARN_ON_ONCE(utask->state != UTASK_SSTEP);

	if (signal_pending(t)) {
		spin_lock_irq(&t->sighand->siglock);
		clear_tsk_thread_flag(t, TIF_SIGPENDING);
		spin_unlock_irq(&t->sighand->siglock);

		if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
			utask->state = UTASK_SSTEP_TRAPPED;
			set_tsk_thread_flag(t, TIF_UPROBE);
		}
	}

	return true;
}

static void mmf_recalc_uprobes(struct mm_struct *mm)
{
	struct vm_area_struct *vma;

	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (!valid_vma(vma, false))
			continue;
		/*
		 * This is not strictly accurate, we can race with
		 * uprobe_unregister() and see the already removed
		 * uprobe if delete_uprobe() was not yet called.
		 * Or this uprobe can be filtered out.
		 */
		if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end))
			return;
	}

	clear_bit(MMF_HAS_UPROBES, &mm->flags);
}

static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
{
	struct page *page;
	uprobe_opcode_t opcode;
	int result;

	pagefault_disable();
	result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
							sizeof(opcode));
	pagefault_enable();

	if (likely(result == 0))
		goto out;

	/*
	 * The NULL 'tsk' here ensures that any faults that occur here
	 * will not be accounted to the task.  'mm' *is* current->mm,
	 * but we treat this as a 'remote' access since it is
	 * essentially a kernel access to the memory.
	 */
	result = get_user_pages_remote(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
	if (result < 0)
		return result;

	copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
	put_page(page);
 out:
	/* This needs to return true for any variant of the trap insn */
	return is_trap_insn(&opcode);
}

static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp)
{
	struct mm_struct *mm = current->mm;
	struct uprobe *uprobe = NULL;
	struct vm_area_struct *vma;

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, bp_vaddr);
	if (vma && vma->vm_start <= bp_vaddr) {
		if (valid_vma(vma, false)) {
			struct inode *inode = file_inode(vma->vm_file);
			loff_t offset = vaddr_to_offset(vma, bp_vaddr);

			uprobe = find_uprobe(inode, offset);
		}

		if (!uprobe)
			*is_swbp = is_trap_at_addr(mm, bp_vaddr);
	} else {
		*is_swbp = -EFAULT;
	}

	if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags))
		mmf_recalc_uprobes(mm);
	up_read(&mm->mmap_sem);

	return uprobe;
}

static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
{
	struct uprobe_consumer *uc;
	int remove = UPROBE_HANDLER_REMOVE;
	bool need_prep = false; /* prepare return uprobe, when needed */

	down_read(&uprobe->register_rwsem);
	for (uc = uprobe->consumers; uc; uc = uc->next) {
		int rc = 0;

		if (uc->handler) {
			rc = uc->handler(uc, regs);
			WARN(rc & ~UPROBE_HANDLER_MASK,
				"bad rc=0x%x from %pf()\n", rc, uc->handler);
		}

		if (uc->ret_handler)
			need_prep = true;

		remove &= rc;
	}

	if (need_prep && !remove)
		prepare_uretprobe(uprobe, regs); /* put bp at return */

	if (remove && uprobe->consumers) {
		WARN_ON(!uprobe_is_active(uprobe));
		unapply_uprobe(uprobe, current->mm);
	}
	up_read(&uprobe->register_rwsem);
}

static void
handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs)
{
	struct uprobe *uprobe = ri->uprobe;
	struct uprobe_consumer *uc;

	down_read(&uprobe->register_rwsem);
	for (uc = uprobe->consumers; uc; uc = uc->next) {
		if (uc->ret_handler)
			uc->ret_handler(uc, ri->func, regs);
	}
	up_read(&uprobe->register_rwsem);
}

static struct return_instance *find_next_ret_chain(struct return_instance *ri)
{
	bool chained;

	do {
		chained = ri->chained;
		ri = ri->next;	/* can't be NULL if chained */
	} while (chained);

	return ri;
}

static void handle_trampoline(struct pt_regs *regs)
{
	struct uprobe_task *utask;
	struct return_instance *ri, *next;
	bool valid;

	utask = current->utask;
	if (!utask)
		goto sigill;

	ri = utask->return_instances;
	if (!ri)
		goto sigill;

	do {
		/*
		 * We should throw out the frames invalidated by longjmp().
		 * If this chain is valid, then the next one should be alive
		 * or NULL; the latter case means that nobody but ri->func
		 * could hit this trampoline on return. TODO: sigaltstack().
		 */
		next = find_next_ret_chain(ri);
		valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs);

		instruction_pointer_set(regs, ri->orig_ret_vaddr);
		do {
			if (valid)
				handle_uretprobe_chain(ri, regs);
			ri = free_ret_instance(ri);
			utask->depth--;
		} while (ri != next);
	} while (!valid);

	utask->return_instances = ri;
	return;

 sigill:
	uprobe_warn(current, "handle uretprobe, sending SIGILL.");
	force_sig_info(SIGILL, SEND_SIG_FORCED, current);

}

bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs)
{
	return false;
}

bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
					struct pt_regs *regs)
{
	return true;
}

/*
 * Run handler and ask thread to singlestep.
 * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
 */
static void handle_swbp(struct pt_regs *regs)
{
	struct uprobe *uprobe;
	unsigned long bp_vaddr;
	int uninitialized_var(is_swbp);

	bp_vaddr = uprobe_get_swbp_addr(regs);
	if (bp_vaddr == get_trampoline_vaddr())
		return handle_trampoline(regs);

	uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
	if (!uprobe) {
		if (is_swbp > 0) {
			/* No matching uprobe; signal SIGTRAP. */
			send_sig(SIGTRAP, current, 0);
		} else {
			/*
			 * Either we raced with uprobe_unregister() or we can't
			 * access this memory. The latter is only possible if
			 * another thread plays with our ->mm. In both cases
			 * we can simply restart. If this vma was unmapped we
			 * can pretend this insn was not executed yet and get
			 * the (correct) SIGSEGV after restart.
			 */
			instruction_pointer_set(regs, bp_vaddr);
		}
		return;
	}

	/* change it in advance for ->handler() and restart */
	instruction_pointer_set(regs, bp_vaddr);

	/*
	 * TODO: move copy_insn/etc into _register and remove this hack.
	 * After we hit the bp, _unregister + _register can install the
	 * new and not-yet-analyzed uprobe at the same address, restart.
	 */
	smp_rmb(); /* pairs with wmb() in install_breakpoint() */
	if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
		goto out;

	/* Tracing handlers use ->utask to communicate with fetch methods */
	if (!get_utask())
		goto out;

	if (arch_uprobe_ignore(&uprobe->arch, regs))
		goto out;

	handler_chain(uprobe, regs);

	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
		goto out;

	if (!pre_ssout(uprobe, regs, bp_vaddr))
		return;

	/* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */
out:
	put_uprobe(uprobe);
}

/*
 * Perform required fix-ups and disable singlestep.
 * Allow pending signals to take effect.
 */
static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
{
	struct uprobe *uprobe;
	int err = 0;

	uprobe = utask->active_uprobe;
	if (utask->state == UTASK_SSTEP_ACK)
		err = arch_uprobe_post_xol(&uprobe->arch, regs);
	else if (utask->state == UTASK_SSTEP_TRAPPED)
		arch_uprobe_abort_xol(&uprobe->arch, regs);
	else
		WARN_ON_ONCE(1);

	put_uprobe(uprobe);
	utask->active_uprobe = NULL;
	utask->state = UTASK_RUNNING;
	xol_free_insn_slot(current);

	spin_lock_irq(&current->sighand->siglock);
	recalc_sigpending(); /* see uprobe_deny_signal() */
	spin_unlock_irq(&current->sighand->siglock);

	if (unlikely(err)) {
		uprobe_warn(current, "execute the probed insn, sending SIGILL.");
		force_sig_info(SIGILL, SEND_SIG_FORCED, current);
	}
}

/*
 * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and
 * allows the thread to return from interrupt. After that handle_swbp()
 * sets utask->active_uprobe.
 *
 * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag
 * and allows the thread to return from interrupt.
 *
 * While returning to userspace, thread notices the TIF_UPROBE flag and calls
 * uprobe_notify_resume().
 */
void uprobe_notify_resume(struct pt_regs *regs)
{
	struct uprobe_task *utask;

	clear_thread_flag(TIF_UPROBE);

	utask = current->utask;
	if (utask && utask->active_uprobe)
		handle_singlestep(utask, regs);
	else
		handle_swbp(regs);
}

/*
 * uprobe_pre_sstep_notifier gets called from interrupt context as part of
 * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit.
 */
int uprobe_pre_sstep_notifier(struct pt_regs *regs)
{
	if (!current->mm)
		return 0;

	if (!test_bit(MMF_HAS_UPROBES, &current->mm->flags) &&
	    (!current->utask || !current->utask->return_instances))
		return 0;

	set_thread_flag(TIF_UPROBE);
	return 1;
}

/*
 * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier
 * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep.
 */
int uprobe_post_sstep_notifier(struct pt_regs *regs)
{
	struct uprobe_task *utask = current->utask;

	if (!current->mm || !utask || !utask->active_uprobe)
		/* task is currently not uprobed */
		return 0;

	utask->state = UTASK_SSTEP_ACK;
	set_thread_flag(TIF_UPROBE);
	return 1;
}

static struct notifier_block uprobe_exception_nb = {
	.notifier_call		= arch_uprobe_exception_notify,
	.priority		= INT_MAX-1,	/* notified after kprobes, kgdb */
};

static int __init init_uprobes(void)
{
	int i;

	for (i = 0; i < UPROBES_HASH_SZ; i++)
		mutex_init(&uprobes_mmap_mutex[i]);

	if (percpu_init_rwsem(&dup_mmap_sem))
		return -ENOMEM;

	return register_die_notifier(&uprobe_exception_nb);
}
__initcall(init_uprobes);
OpenPOWER on IntegriCloud