aboutsummaryrefslogtreecommitdiffstats
path: root/mm/kmemleak.c
blob: e126b0ef9ad20023d6a8d3ff505ae71ad96fdaa0 (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
/*
 * mm/kmemleak.c
 *
 * Copyright (C) 2008 ARM Limited
 * Written by Catalin Marinas <catalin.marinas@arm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * 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
 *
 *
 * For more information on the algorithm and kmemleak usage, please see
 * Documentation/kmemleak.txt.
 *
 * Notes on locking
 * ----------------
 *
 * The following locks and mutexes are used by kmemleak:
 *
 * - kmemleak_lock (rwlock): protects the object_list modifications and
 *   accesses to the object_tree_root. The object_list is the main list
 *   holding the metadata (struct kmemleak_object) for the allocated memory
 *   blocks. The object_tree_root is a red black tree used to look-up
 *   metadata based on a pointer to the corresponding memory block.  The
 *   kmemleak_object structures are added to the object_list and
 *   object_tree_root in the create_object() function called from the
 *   kmemleak_alloc() callback and removed in delete_object() called from the
 *   kmemleak_free() callback
 * - kmemleak_object.lock (spinlock): protects a kmemleak_object. Accesses to
 *   the metadata (e.g. count) are protected by this lock. Note that some
 *   members of this structure may be protected by other means (atomic or
 *   kmemleak_lock). This lock is also held when scanning the corresponding
 *   memory block to avoid the kernel freeing it via the kmemleak_free()
 *   callback. This is less heavyweight than holding a global lock like
 *   kmemleak_lock during scanning
 * - scan_mutex (mutex): ensures that only one thread may scan the memory for
 *   unreferenced objects at a time. The gray_list contains the objects which
 *   are already referenced or marked as false positives and need to be
 *   scanned. This list is only modified during a scanning episode when the
 *   scan_mutex is held. At the end of a scan, the gray_list is always empty.
 *   Note that the kmemleak_object.use_count is incremented when an object is
 *   added to the gray_list and therefore cannot be freed. This mutex also
 *   prevents multiple users of the "kmemleak" debugfs file together with
 *   modifications to the memory scanning parameters including the scan_thread
 *   pointer
 *
 * The kmemleak_object structures have a use_count incremented or decremented
 * using the get_object()/put_object() functions. When the use_count becomes
 * 0, this count can no longer be incremented and put_object() schedules the
 * kmemleak_object freeing via an RCU callback. All calls to the get_object()
 * function must be protected by rcu_read_lock() to avoid accessing a freed
 * structure.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/sched.h>
#include <linux/jiffies.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/kthread.h>
#include <linux/rbtree.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/cpumask.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/stacktrace.h>
#include <linux/cache.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/thread_info.h>
#include <linux/err.h>
#include <linux/uaccess.h>
#include <linux/string.h>
#include <linux/nodemask.h>
#include <linux/mm.h>
#include <linux/workqueue.h>
#include <linux/crc32.h>

#include <asm/sections.h>
#include <asm/processor.h>
#include <linux/atomic.h>

#include <linux/kmemcheck.h>
#include <linux/kmemleak.h>
#include <linux/memory_hotplug.h>

/*
 * Kmemleak configuration and common defines.
 */
#define MAX_TRACE		16	/* stack trace length */
#define MSECS_MIN_AGE		5000	/* minimum object age for reporting */
#define SECS_FIRST_SCAN		60	/* delay before the first scan */
#define SECS_SCAN_WAIT		600	/* subsequent auto scanning delay */
#define MAX_SCAN_SIZE		4096	/* maximum size of a scanned block */

#define BYTES_PER_POINTER	sizeof(void *)

/* GFP bitmask for kmemleak internal allocations */
#define gfp_kmemleak_mask(gfp)	(((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
				 __GFP_NORETRY | __GFP_NOMEMALLOC | \
				 __GFP_NOWARN)

/* scanning area inside a memory block */
struct kmemleak_scan_area {
	struct hlist_node node;
	unsigned long start;
	size_t size;
};

#define KMEMLEAK_GREY	0
#define KMEMLEAK_BLACK	-1

/*
 * Structure holding the metadata for each allocated memory block.
 * Modifications to such objects should be made while holding the
 * object->lock. Insertions or deletions from object_list, gray_list or
 * rb_node are already protected by the corresponding locks or mutex (see
 * the notes on locking above). These objects are reference-counted
 * (use_count) and freed using the RCU mechanism.
 */
struct kmemleak_object {
	spinlock_t lock;
	unsigned long flags;		/* object status flags */
	struct list_head object_list;
	struct list_head gray_list;
	struct rb_node rb_node;
	struct rcu_head rcu;		/* object_list lockless traversal */
	/* object usage count; object freed when use_count == 0 */
	atomic_t use_count;
	unsigned long pointer;
	size_t size;
	/* minimum number of a pointers found before it is considered leak */
	int min_count;
	/* the total number of pointers found pointing to this object */
	int count;
	/* checksum for detecting modified objects */
	u32 checksum;
	/* memory ranges to be scanned inside an object (empty for all) */
	struct hlist_head area_list;
	unsigned long trace[MAX_TRACE];
	unsigned int trace_len;
	unsigned long jiffies;		/* creation timestamp */
	pid_t pid;			/* pid of the current task */
	char comm[TASK_COMM_LEN];	/* executable name */
};

/* flag representing the memory block allocation status */
#define OBJECT_ALLOCATED	(1 << 0)
/* flag set after the first reporting of an unreference object */
#define OBJECT_REPORTED		(1 << 1)
/* flag set to not scan the object */
#define OBJECT_NO_SCAN		(1 << 2)

/* number of bytes to print per line; must be 16 or 32 */
#define HEX_ROW_SIZE		16
/* number of bytes to print at a time (1, 2, 4, 8) */
#define HEX_GROUP_SIZE		1
/* include ASCII after the hex output */
#define HEX_ASCII		1
/* max number of lines to be printed */
#define HEX_MAX_LINES		2

/* the list of all allocated objects */
static LIST_HEAD(object_list);
/* the list of gray-colored objects (see color_gray comment below) */
static LIST_HEAD(gray_list);
/* search tree for object boundaries */
static struct rb_root object_tree_root = RB_ROOT;
/* rw_lock protecting the access to object_list and object_tree_root */
static DEFINE_RWLOCK(kmemleak_lock);

/* allocation caches for kmemleak internal data */
static struct kmem_cache *object_cache;
static struct kmem_cache *scan_area_cache;

/* set if tracing memory operations is enabled */
static atomic_t kmemleak_enabled = ATOMIC_INIT(0);
/* set in the late_initcall if there were no errors */
static atomic_t kmemleak_initialized = ATOMIC_INIT(0);
/* enables or disables early logging of the memory operations */
static atomic_t kmemleak_early_log = ATOMIC_INIT(1);
/* set if a kmemleak warning was issued */
static atomic_t kmemleak_warning = ATOMIC_INIT(0);
/* set if a fatal kmemleak error has occurred */
static atomic_t kmemleak_error = ATOMIC_INIT(0);

/* minimum and maximum address that may be valid pointers */
static unsigned long min_addr = ULONG_MAX;
static unsigned long max_addr;

static struct task_struct *scan_thread;
/* used to avoid reporting of recently allocated objects */
static unsigned long jiffies_min_age;
static unsigned long jiffies_last_scan;
/* delay between automatic memory scannings */
static signed long jiffies_scan_wait;
/* enables or disables the task stacks scanning */
static int kmemleak_stack_scan = 1;
/* protects the memory scanning, parameters and debug/kmemleak file access */
static DEFINE_MUTEX(scan_mutex);
/* setting kmemleak=on, will set this var, skipping the disable */
static int kmemleak_skip_disable;


/*
 * Early object allocation/freeing logging. Kmemleak is initialized after the
 * kernel allocator. However, both the kernel allocator and kmemleak may
 * allocate memory blocks which need to be tracked. Kmemleak defines an
 * arbitrary buffer to hold the allocation/freeing information before it is
 * fully initialized.
 */

/* kmemleak operation type for early logging */
enum {
	KMEMLEAK_ALLOC,
	KMEMLEAK_ALLOC_PERCPU,
	KMEMLEAK_FREE,
	KMEMLEAK_FREE_PART,
	KMEMLEAK_FREE_PERCPU,
	KMEMLEAK_NOT_LEAK,
	KMEMLEAK_IGNORE,
	KMEMLEAK_SCAN_AREA,
	KMEMLEAK_NO_SCAN
};

/*
 * Structure holding the information passed to kmemleak callbacks during the
 * early logging.
 */
struct early_log {
	int op_type;			/* kmemleak operation type */
	const void *ptr;		/* allocated/freed memory block */
	size_t size;			/* memory block size */
	int min_count;			/* minimum reference count */
	unsigned long trace[MAX_TRACE];	/* stack trace */
	unsigned int trace_len;		/* stack trace length */
};

/* early logging buffer and current position */
static struct early_log
	early_log[CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE] __initdata;
static int crt_early_log __initdata;

static void kmemleak_disable(void);

/*
 * Print a warning and dump the stack trace.
 */
#define kmemleak_warn(x...)	do {		\
	pr_warning(x);				\
	dump_stack();				\
	atomic_set(&kmemleak_warning, 1);	\
} while (0)

/*
 * Macro invoked when a serious kmemleak condition occurred and cannot be
 * recovered from. Kmemleak will be disabled and further allocation/freeing
 * tracing no longer available.
 */
#define kmemleak_stop(x...)	do {	\
	kmemleak_warn(x);		\
	kmemleak_disable();		\
} while (0)

/*
 * Printing of the objects hex dump to the seq file. The number of lines to be
 * printed is limited to HEX_MAX_LINES to prevent seq file spamming. The
 * actual number of printed bytes depends on HEX_ROW_SIZE. It must be called
 * with the object->lock held.
 */
static void hex_dump_object(struct seq_file *seq,
			    struct kmemleak_object *object)
{
	const u8 *ptr = (const u8 *)object->pointer;
	int i, len, remaining;
	unsigned char linebuf[HEX_ROW_SIZE * 5];

	/* limit the number of lines to HEX_MAX_LINES */
	remaining = len =
		min(object->size, (size_t)(HEX_MAX_LINES * HEX_ROW_SIZE));

	seq_printf(seq, "  hex dump (first %d bytes):\n", len);
	for (i = 0; i < len; i += HEX_ROW_SIZE) {
		int linelen = min(remaining, HEX_ROW_SIZE);

		remaining -= HEX_ROW_SIZE;
		hex_dump_to_buffer(ptr + i, linelen, HEX_ROW_SIZE,
				   HEX_GROUP_SIZE, linebuf, sizeof(linebuf),
				   HEX_ASCII);
		seq_printf(seq, "    %s\n", linebuf);
	}
}

/*
 * Object colors, encoded with count and min_count:
 * - white - orphan object, not enough references to it (count < min_count)
 * - gray  - not orphan, not marked as false positive (min_count == 0) or
 *		sufficient references to it (count >= min_count)
 * - black - ignore, it doesn't contain references (e.g. text section)
 *		(min_count == -1). No function defined for this color.
 * Newly created objects don't have any color assigned (object->count == -1)
 * before the next memory scan when they become white.
 */
static bool color_white(const struct kmemleak_object *object)
{
	return object->count != KMEMLEAK_BLACK &&
		object->count < object->min_count;
}

static bool color_gray(const struct kmemleak_object *object)
{
	return object->min_count != KMEMLEAK_BLACK &&
		object->count >= object->min_count;
}

/*
 * Objects are considered unreferenced only if their color is white, they have
 * not be deleted and have a minimum age to avoid false positives caused by
 * pointers temporarily stored in CPU registers.
 */
static bool unreferenced_object(struct kmemleak_object *object)
{
	return (color_white(object) && object->flags & OBJECT_ALLOCATED) &&
		time_before_eq(object->jiffies + jiffies_min_age,
			       jiffies_last_scan);
}

/*
 * Printing of the unreferenced objects information to the seq file. The
 * print_unreferenced function must be called with the object->lock held.
 */
static void print_unreferenced(struct seq_file *seq,
			       struct kmemleak_object *object)
{
	int i;
	unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies);

	seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n",
		   object->pointer, object->size);
	seq_printf(seq, "  comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n",
		   object->comm, object->pid, object->jiffies,
		   msecs_age / 1000, msecs_age % 1000);
	hex_dump_object(seq, object);
	seq_printf(seq, "  backtrace:\n");

	for (i = 0; i < object->trace_len; i++) {
		void *ptr = (void *)object->trace[i];
		seq_printf(seq, "    [<%p>] %pS\n", ptr, ptr);
	}
}

/*
 * Print the kmemleak_object information. This function is used mainly for
 * debugging special cases when kmemleak operations. It must be called with
 * the object->lock held.
 */
static void dump_object_info(struct kmemleak_object *object)
{
	struct stack_trace trace;

	trace.nr_entries = object->trace_len;
	trace.entries = object->trace;

	pr_notice("Object 0x%08lx (size %zu):\n",
		  object->pointer, object->size);
	pr_notice("  comm \"%s\", pid %d, jiffies %lu\n",
		  object->comm, object->pid, object->jiffies);
	pr_notice("  min_count = %d\n", object->min_count);
	pr_notice("  count = %d\n", object->count);
	pr_notice("  flags = 0x%lx\n", object->flags);
	pr_notice("  checksum = %d\n", object->checksum);
	pr_notice("  backtrace:\n");
	print_stack_trace(&trace, 4);
}

/*
 * Look-up a memory block metadata (kmemleak_object) in the object search
 * tree based on a pointer value. If alias is 0, only values pointing to the
 * beginning of the memory block are allowed. The kmemleak_lock must be held
 * when calling this function.
 */
static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
{
	struct rb_node *rb = object_tree_root.rb_node;

	while (rb) {
		struct kmemleak_object *object =
			rb_entry(rb, struct kmemleak_object, rb_node);
		if (ptr < object->pointer)
			rb = object->rb_node.rb_left;
		else if (object->pointer + object->size <= ptr)
			rb = object->rb_node.rb_right;
		else if (object->pointer == ptr || alias)
			return object;
		else {
			kmemleak_warn("Found object by alias at 0x%08lx\n",
				      ptr);
			dump_object_info(object);
			break;
		}
	}
	return NULL;
}

/*
 * Increment the object use_count. Return 1 if successful or 0 otherwise. Note
 * that once an object's use_count reached 0, the RCU freeing was already
 * registered and the object should no longer be used. This function must be
 * called under the protection of rcu_read_lock().
 */
static int get_object(struct kmemleak_object *object)
{
	return atomic_inc_not_zero(&object->use_count);
}

/*
 * RCU callback to free a kmemleak_object.
 */
static void free_object_rcu(struct rcu_head *rcu)
{
	struct hlist_node *tmp;
	struct kmemleak_scan_area *area;
	struct kmemleak_object *object =
		container_of(rcu, struct kmemleak_object, rcu);

	/*
	 * Once use_count is 0 (guaranteed by put_object), there is no other
	 * code accessing this object, hence no need for locking.
	 */
	hlist_for_each_entry_safe(area, tmp, &object->area_list, node) {
		hlist_del(&area->node);
		kmem_cache_free(scan_area_cache, area);
	}
	kmem_cache_free(object_cache, object);
}

/*
 * Decrement the object use_count. Once the count is 0, free the object using
 * an RCU callback. Since put_object() may be called via the kmemleak_free() ->
 * delete_object() path, the delayed RCU freeing ensures that there is no
 * recursive call to the kernel allocator. Lock-less RCU object_list traversal
 * is also possible.
 */
static void put_object(struct kmemleak_object *object)
{
	if (!atomic_dec_and_test(&object->use_count))
		return;

	/* should only get here after delete_object was called */
	WARN_ON(object->flags & OBJECT_ALLOCATED);

	call_rcu(&object->rcu, free_object_rcu);
}

/*
 * Look up an object in the object search tree and increase its use_count.
 */
static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
{
	unsigned long flags;
	struct kmemleak_object *object = NULL;

	rcu_read_lock();
	read_lock_irqsave(&kmemleak_lock, flags);
	if (ptr >= min_addr && ptr < max_addr)
		object = lookup_object(ptr, alias);
	read_unlock_irqrestore(&kmemleak_lock, flags);

	/* check whether the object is still available */
	if (object && !get_object(object))
		object = NULL;
	rcu_read_unlock();

	return object;
}

/*
 * Save stack trace to the given array of MAX_TRACE size.
 */
static int __save_stack_trace(unsigned long *trace)
{
	struct stack_trace stack_trace;

	stack_trace.max_entries = MAX_TRACE;
	stack_trace.nr_entries = 0;
	stack_trace.entries = trace;
	stack_trace.skip = 2;
	save_stack_trace(&stack_trace);

	return stack_trace.nr_entries;
}

/*
 * Create the metadata (struct kmemleak_object) corresponding to an allocated
 * memory block and add it to the object_list and object_tree_root.
 */
static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
					     int min_count, gfp_t gfp)
{
	unsigned long flags;
	struct kmemleak_object *object, *parent;
	struct rb_node **link, *rb_parent;

	object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp));
	if (!object) {
		pr_warning("Cannot allocate a kmemleak_object structure\n");
		kmemleak_disable();
		return NULL;
	}

	INIT_LIST_HEAD(&object->object_list);
	INIT_LIST_HEAD(&object->gray_list);
	INIT_HLIST_HEAD(&object->area_list);
	spin_lock_init(&object->lock);
	atomic_set(&object->use_count, 1);
	object->flags = OBJECT_ALLOCATED;
	object->pointer = ptr;
	object->size = size;
	object->min_count = min_count;
	object->count = 0;			/* white color initially */
	object->jiffies = jiffies;
	object->checksum = 0;

	/* task information */
	if (in_irq()) {
		object->pid = 0;
		strncpy(object->comm, "hardirq", sizeof(object->comm));
	} else if (in_softirq()) {
		object->pid = 0;
		strncpy(object->comm, "softirq", sizeof(object->comm));
	} else {
		object->pid = current->pid;
		/*
		 * There is a small chance of a race with set_task_comm(),
		 * however using get_task_comm() here may cause locking
		 * dependency issues with current->alloc_lock. In the worst
		 * case, the command line is not correct.
		 */
		strncpy(object->comm, current->comm, sizeof(object->comm));
	}

	/* kernel backtrace */
	object->trace_len = __save_stack_trace(object->trace);

	write_lock_irqsave(&kmemleak_lock, flags);

	min_addr = min(min_addr, ptr);
	max_addr = max(max_addr, ptr + size);
	link = &object_tree_root.rb_node;
	rb_parent = NULL;
	while (*link) {
		rb_parent = *link;
		parent = rb_entry(rb_parent, struct kmemleak_object, rb_node);
		if (ptr + size <= parent->pointer)
			link = &parent->rb_node.rb_left;
		else if (parent->pointer + parent->size <= ptr)
			link = &parent->rb_node.rb_right;
		else {
			kmemleak_stop("Cannot insert 0x%lx into the object "
				      "search tree (overlaps existing)\n",
				      ptr);
			kmem_cache_free(object_cache, object);
			object = parent;
			spin_lock(&object->lock);
			dump_object_info(object);
			spin_unlock(&object->lock);
			goto out;
		}
	}
	rb_link_node(&object->rb_node, rb_parent, link);
	rb_insert_color(&object->rb_node, &object_tree_root);

	list_add_tail_rcu(&object->object_list, &object_list);
out:
	write_unlock_irqrestore(&kmemleak_lock, flags);
	return object;
}

/*
 * Remove the metadata (struct kmemleak_object) for a memory block from the
 * object_list and object_tree_root and decrement its use_count.
 */
static void __delete_object(struct kmemleak_object *object)
{
	unsigned long flags;

	write_lock_irqsave(&kmemleak_lock, flags);
	rb_erase(&object->rb_node, &object_tree_root);
	list_del_rcu(&object->object_list);
	write_unlock_irqrestore(&kmemleak_lock, flags);

	WARN_ON(!(object->flags & OBJECT_ALLOCATED));
	WARN_ON(atomic_read(&object->use_count) < 2);

	/*
	 * Locking here also ensures that the corresponding memory block
	 * cannot be freed when it is being scanned.
	 */
	spin_lock_irqsave(&object->lock, flags);
	object->flags &= ~OBJECT_ALLOCATED;
	spin_unlock_irqrestore(&object->lock, flags);
	put_object(object);
}

/*
 * Look up the metadata (struct kmemleak_object) corresponding to ptr and
 * delete it.
 */
static void delete_object_full(unsigned long ptr)
{
	struct kmemleak_object *object;

	object = find_and_get_object(ptr, 0);
	if (!object) {
#ifdef DEBUG
		kmemleak_warn("Freeing unknown object at 0x%08lx\n",
			      ptr);
#endif
		return;
	}
	__delete_object(object);
	put_object(object);
}

/*
 * Look up the metadata (struct kmemleak_object) corresponding to ptr and
 * delete it. If the memory block is partially freed, the function may create
 * additional metadata for the remaining parts of the block.
 */
static void delete_object_part(unsigned long ptr, size_t size)
{
	struct kmemleak_object *object;
	unsigned long start, end;

	object = find_and_get_object(ptr, 1);
	if (!object) {
#ifdef DEBUG
		kmemleak_warn("Partially freeing unknown object at 0x%08lx "
			      "(size %zu)\n", ptr, size);
#endif
		return;
	}
	__delete_object(object);

	/*
	 * Create one or two objects that may result from the memory block
	 * split. Note that partial freeing is only done by free_bootmem() and
	 * this happens before kmemleak_init() is called. The path below is
	 * only executed during early log recording in kmemleak_init(), so
	 * GFP_KERNEL is enough.
	 */
	start = object->pointer;
	end = object->pointer + object->size;
	if (ptr > start)
		create_object(start, ptr - start, object->min_count,
			      GFP_KERNEL);
	if (ptr + size < end)
		create_object(ptr + size, end - ptr - size, object->min_count,
			      GFP_KERNEL);

	put_object(object);
}

static void __paint_it(struct kmemleak_object *object, int color)
{
	object->min_count = color;
	if (color == KMEMLEAK_BLACK)
		object->flags |= OBJECT_NO_SCAN;
}

static void paint_it(struct kmemleak_object *object, int color)
{
	unsigned long flags;

	spin_lock_irqsave(&object->lock, flags);
	__paint_it(object, color);
	spin_unlock_irqrestore(&object->lock, flags);
}

static void paint_ptr(unsigned long ptr, int color)
{
	struct kmemleak_object *object;

	object = find_and_get_object(ptr, 0);
	if (!object) {
		kmemleak_warn("Trying to color unknown object "
			      "at 0x%08lx as %s\n", ptr,
			      (color == KMEMLEAK_GREY) ? "Grey" :
			      (color == KMEMLEAK_BLACK) ? "Black" : "Unknown");
		return;
	}
	paint_it(object, color);
	put_object(object);
}

/*
 * Mark an object permanently as gray-colored so that it can no longer be
 * reported as a leak. This is used in general to mark a false positive.
 */
static void make_gray_object(unsigned long ptr)
{
	paint_ptr(ptr, KMEMLEAK_GREY);
}

/*
 * Mark the object as black-colored so that it is ignored from scans and
 * reporting.
 */
static void make_black_object(unsigned long ptr)
{
	paint_ptr(ptr, KMEMLEAK_BLACK);
}

/*
 * Add a scanning area to the object. If at least one such area is added,
 * kmemleak will only scan these ranges rather than the whole memory block.
 */
static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
{
	unsigned long flags;
	struct kmemleak_object *object;
	struct kmemleak_scan_area *area;

	object = find_and_get_object(ptr, 1);
	if (!object) {
		kmemleak_warn("Adding scan area to unknown object at 0x%08lx\n",
			      ptr);
		return;
	}

	area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
	if (!area) {
		pr_warning("Cannot allocate a scan area\n");
		goto out;
	}

	spin_lock_irqsave(&object->lock, flags);
	if (ptr + size > object->pointer + object->size) {
		kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
		dump_object_info(object);
		kmem_cache_free(scan_area_cache, area);
		goto out_unlock;
	}

	INIT_HLIST_NODE(&area->node);
	area->start = ptr;
	area->size = size;

	hlist_add_head(&area->node, &object->area_list);
out_unlock:
	spin_unlock_irqrestore(&object->lock, flags);
out:
	put_object(object);
}

/*
 * Set the OBJECT_NO_SCAN flag for the object corresponding to the give
 * pointer. Such object will not be scanned by kmemleak but references to it
 * are searched.
 */
static void object_no_scan(unsigned long ptr)
{
	unsigned long flags;
	struct kmemleak_object *object;

	object = find_and_get_object(ptr, 0);
	if (!object) {
		kmemleak_warn("Not scanning unknown object at 0x%08lx\n", ptr);
		return;
	}

	spin_lock_irqsave(&object->lock, flags);
	object->flags |= OBJECT_NO_SCAN;
	spin_unlock_irqrestore(&object->lock, flags);
	put_object(object);
}

/*
 * Log an early kmemleak_* call to the early_log buffer. These calls will be
 * processed later once kmemleak is fully initialized.
 */
static void __init log_early(int op_type, const void *ptr, size_t size,
			     int min_count)
{
	unsigned long flags;
	struct early_log *log;

	if (atomic_read(&kmemleak_error)) {
		/* kmemleak stopped recording, just count the requests */
		crt_early_log++;
		return;
	}

	if (crt_early_log >= ARRAY_SIZE(early_log)) {
		kmemleak_disable();
		return;
	}

	/*
	 * There is no need for locking since the kernel is still in UP mode
	 * at this stage. Disabling the IRQs is enough.
	 */
	local_irq_save(flags);
	log = &early_log[crt_early_log];
	log->op_type = op_type;
	log->ptr = ptr;
	log->size = size;
	log->min_count = min_count;
	log->trace_len = __save_stack_trace(log->trace);
	crt_early_log++;
	local_irq_restore(flags);
}

/*
 * Log an early allocated block and populate the stack trace.
 */
static void early_alloc(struct early_log *log)
{
	struct kmemleak_object *object;
	unsigned long flags;
	int i;

	if (!atomic_read(&kmemleak_enabled) || !log->ptr || IS_ERR(log->ptr))
		return;

	/*
	 * RCU locking needed to ensure object is not freed via put_object().
	 */
	rcu_read_lock();
	object = create_object((unsigned long)log->ptr, log->size,
			       log->min_count, GFP_ATOMIC);
	if (!object)
		goto out;
	spin_lock_irqsave(&object->lock, flags);
	for (i = 0; i < log->trace_len; i++)
		object->trace[i] = log->trace[i];
	object->trace_len = log->trace_len;
	spin_unlock_irqrestore(&object->lock, flags);
out:
	rcu_read_unlock();
}

/*
 * Log an early allocated block and populate the stack trace.
 */
static void early_alloc_percpu(struct early_log *log)
{
	unsigned int cpu;
	const void __percpu *ptr = log->ptr;

	for_each_possible_cpu(cpu) {
		log->ptr = per_cpu_ptr(ptr, cpu);
		early_alloc(log);
	}
}

/**
 * kmemleak_alloc - register a newly allocated object
 * @ptr:	pointer to beginning of the object
 * @size:	size of the object
 * @min_count:	minimum number of references to this object. If during memory
 *		scanning a number of references less than @min_count is found,
 *		the object is reported as a memory leak. If @min_count is 0,
 *		the object is never reported as a leak. If @min_count is -1,
 *		the object is ignored (not scanned and not reported as a leak)
 * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
 *
 * This function is called from the kernel allocators when a new object
 * (memory block) is allocated (kmem_cache_alloc, kmalloc, vmalloc etc.).
 */
void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
			  gfp_t gfp)
{
	pr_debug("%s(0x%p, %zu, %d)\n", __func__, ptr, size, min_count);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		create_object((unsigned long)ptr, size, min_count, gfp);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_ALLOC, ptr, size, min_count);
}
EXPORT_SYMBOL_GPL(kmemleak_alloc);

/**
 * kmemleak_alloc_percpu - register a newly allocated __percpu object
 * @ptr:	__percpu pointer to beginning of the object
 * @size:	size of the object
 *
 * This function is called from the kernel percpu allocator when a new object
 * (memory block) is allocated (alloc_percpu). It assumes GFP_KERNEL
 * allocation.
 */
void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size)
{
	unsigned int cpu;

	pr_debug("%s(0x%p, %zu)\n", __func__, ptr, size);

	/*
	 * Percpu allocations are only scanned and not reported as leaks
	 * (min_count is set to 0).
	 */
	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		for_each_possible_cpu(cpu)
			create_object((unsigned long)per_cpu_ptr(ptr, cpu),
				      size, 0, GFP_KERNEL);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_ALLOC_PERCPU, ptr, size, 0);
}
EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu);

/**
 * kmemleak_free - unregister a previously registered object
 * @ptr:	pointer to beginning of the object
 *
 * This function is called from the kernel allocators when an object (memory
 * block) is freed (kmem_cache_free, kfree, vfree etc.).
 */
void __ref kmemleak_free(const void *ptr)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		delete_object_full((unsigned long)ptr);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_FREE, ptr, 0, 0);
}
EXPORT_SYMBOL_GPL(kmemleak_free);

/**
 * kmemleak_free_part - partially unregister a previously registered object
 * @ptr:	pointer to the beginning or inside the object. This also
 *		represents the start of the range to be freed
 * @size:	size to be unregistered
 *
 * This function is called when only a part of a memory block is freed
 * (usually from the bootmem allocator).
 */
void __ref kmemleak_free_part(const void *ptr, size_t size)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		delete_object_part((unsigned long)ptr, size);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_FREE_PART, ptr, size, 0);
}
EXPORT_SYMBOL_GPL(kmemleak_free_part);

/**
 * kmemleak_free_percpu - unregister a previously registered __percpu object
 * @ptr:	__percpu pointer to beginning of the object
 *
 * This function is called from the kernel percpu allocator when an object
 * (memory block) is freed (free_percpu).
 */
void __ref kmemleak_free_percpu(const void __percpu *ptr)
{
	unsigned int cpu;

	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		for_each_possible_cpu(cpu)
			delete_object_full((unsigned long)per_cpu_ptr(ptr,
								      cpu));
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_FREE_PERCPU, ptr, 0, 0);
}
EXPORT_SYMBOL_GPL(kmemleak_free_percpu);

/**
 * kmemleak_not_leak - mark an allocated object as false positive
 * @ptr:	pointer to beginning of the object
 *
 * Calling this function on an object will cause the memory block to no longer
 * be reported as leak and always be scanned.
 */
void __ref kmemleak_not_leak(const void *ptr)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		make_gray_object((unsigned long)ptr);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_NOT_LEAK, ptr, 0, 0);
}
EXPORT_SYMBOL(kmemleak_not_leak);

/**
 * kmemleak_ignore - ignore an allocated object
 * @ptr:	pointer to beginning of the object
 *
 * Calling this function on an object will cause the memory block to be
 * ignored (not scanned and not reported as a leak). This is usually done when
 * it is known that the corresponding block is not a leak and does not contain
 * any references to other allocated memory blocks.
 */
void __ref kmemleak_ignore(const void *ptr)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		make_black_object((unsigned long)ptr);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_IGNORE, ptr, 0, 0);
}
EXPORT_SYMBOL(kmemleak_ignore);

/**
 * kmemleak_scan_area - limit the range to be scanned in an allocated object
 * @ptr:	pointer to beginning or inside the object. This also
 *		represents the start of the scan area
 * @size:	size of the scan area
 * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
 *
 * This function is used when it is known that only certain parts of an object
 * contain references to other objects. Kmemleak will only scan these areas
 * reducing the number false negatives.
 */
void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && size && !IS_ERR(ptr))
		add_scan_area((unsigned long)ptr, size, gfp);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_SCAN_AREA, ptr, size, 0);
}
EXPORT_SYMBOL(kmemleak_scan_area);

/**
 * kmemleak_no_scan - do not scan an allocated object
 * @ptr:	pointer to beginning of the object
 *
 * This function notifies kmemleak not to scan the given memory block. Useful
 * in situations where it is known that the given object does not contain any
 * references to other objects. Kmemleak will not scan such objects reducing
 * the number of false negatives.
 */
void __ref kmemleak_no_scan(const void *ptr)
{
	pr_debug("%s(0x%p)\n", __func__, ptr);

	if (atomic_read(&kmemleak_enabled) && ptr && !IS_ERR(ptr))
		object_no_scan((unsigned long)ptr);
	else if (atomic_read(&kmemleak_early_log))
		log_early(KMEMLEAK_NO_SCAN, ptr, 0, 0);
}
EXPORT_SYMBOL(kmemleak_no_scan);

/*
 * Update an object's checksum and return true if it was modified.
 */
static bool update_checksum(struct kmemleak_object *object)
{
	u32 old_csum = object->checksum;

	if (!kmemcheck_is_obj_initialized(object->pointer, object->size))
		return false;

	object->checksum = crc32(0, (void *)object->pointer, object->size);
	return object->checksum != old_csum;
}

/*
 * Memory scanning is a long process and it needs to be interruptable. This
 * function checks whether such interrupt condition occurred.
 */
static int scan_should_stop(void)
{
	if (!atomic_read(&kmemleak_enabled))
		return 1;

	/*
	 * This function may be called from either process or kthread context,
	 * hence the need to check for both stop conditions.
	 */
	if (current->mm)
		return signal_pending(current);
	else
		return kthread_should_stop();

	return 0;
}

/*
 * Scan a memory block (exclusive range) for valid pointers and add those
 * found to the gray list.
 */
static void scan_block(void *_start, void *_end,
		       struct kmemleak_object *scanned, int allow_resched)
{
	unsigned long *ptr;
	unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER);
	unsigned long *end = _end - (BYTES_PER_POINTER - 1);

	for (ptr = start; ptr < end; ptr++) {
		struct kmemleak_object *object;
		unsigned long flags;
		unsigned long pointer;

		if (allow_resched)
			cond_resched();
		if (scan_should_stop())
			break;

		/* don't scan uninitialized memory */
		if (!kmemcheck_is_obj_initialized((unsigned long)ptr,
						  BYTES_PER_POINTER))
			continue;

		pointer = *ptr;

		object = find_and_get_object(pointer, 1);
		if (!object)
			continue;
		if (object == scanned) {
			/* self referenced, ignore */
			put_object(object);
			continue;
		}

		/*
		 * Avoid the lockdep recursive warning on object->lock being
		 * previously acquired in scan_object(). These locks are
		 * enclosed by scan_mutex.
		 */
		spin_lock_irqsave_nested(&object->lock, flags,
					 SINGLE_DEPTH_NESTING);
		if (!color_white(object)) {
			/* non-orphan, ignored or new */
			spin_unlock_irqrestore(&object->lock, flags);
			put_object(object);
			continue;
		}

		/*
		 * Increase the object's reference count (number of pointers
		 * to the memory block). If this count reaches the required
		 * minimum, the object's color will become gray and it will be
		 * added to the gray_list.
		 */
		object->count++;
		if (color_gray(object)) {
			list_add_tail(&object->gray_list, &gray_list);
			spin_unlock_irqrestore(&object->lock, flags);
			continue;
		}

		spin_unlock_irqrestore(&object->lock, flags);
		put_object(object);
	}
}

/*
 * Scan a memory block corresponding to a kmemleak_object. A condition is
 * that object->use_count >= 1.
 */
static void scan_object(struct kmemleak_object *object)
{
	struct kmemleak_scan_area *area;
	unsigned long flags;

	/*
	 * Once the object->lock is acquired, the corresponding memory block
	 * cannot be freed (the same lock is acquired in delete_object).
	 */
	spin_lock_irqsave(&object->lock, flags);
	if (object->flags & OBJECT_NO_SCAN)
		goto out;
	if (!(object->flags & OBJECT_ALLOCATED))
		/* already freed object */
		goto out;
	if (hlist_empty(&object->area_list)) {
		void *start = (void *)object->pointer;
		void *end = (void *)(object->pointer + object->size);

		while (start < end && (object->flags & OBJECT_ALLOCATED) &&
		       !(object->flags & OBJECT_NO_SCAN)) {
			scan_block(start, min(start + MAX_SCAN_SIZE, end),
				   object, 0);
			start += MAX_SCAN_SIZE;

			spin_unlock_irqrestore(&object->lock, flags);
			cond_resched();
			spin_lock_irqsave(&object->lock, flags);
		}
	} else
		hlist_for_each_entry(area, &object->area_list, node)
			scan_block((void *)area->start,
				   (void *)(area->start + area->size),
				   object, 0);
out:
	spin_unlock_irqrestore(&object->lock, flags);
}

/*
 * Scan the objects already referenced (gray objects). More objects will be
 * referenced and, if there are no memory leaks, all the objects are scanned.
 */
static void scan_gray_list(void)
{
	struct kmemleak_object *object, *tmp;

	/*
	 * The list traversal is safe for both tail additions and removals
	 * from inside the loop. The kmemleak objects cannot be freed from
	 * outside the loop because their use_count was incremented.
	 */
	object = list_entry(gray_list.next, typeof(*object), gray_list);
	while (&object->gray_list != &gray_list) {
		cond_resched();

		/* may add new objects to the list */
		if (!scan_should_stop())
			scan_object(object);

		tmp = list_entry(object->gray_list.next, typeof(*object),
				 gray_list);

		/* remove the object from the list and release it */
		list_del(&object->gray_list);
		put_object(object);

		object = tmp;
	}
	WARN_ON(!list_empty(&gray_list));
}

/*
 * Scan data sections and all the referenced memory blocks allocated via the
 * kernel's standard allocators. This function must be called with the
 * scan_mutex held.
 */
static void kmemleak_scan(void)
{
	unsigned long flags;
	struct kmemleak_object *object;
	int i;
	int new_leaks = 0;

	jiffies_last_scan = jiffies;

	/* prepare the kmemleak_object's */
	rcu_read_lock();
	list_for_each_entry_rcu(object, &object_list, object_list) {
		spin_lock_irqsave(&object->lock, flags);
#ifdef DEBUG
		/*
		 * With a few exceptions there should be a maximum of
		 * 1 reference to any object at this point.
		 */
		if (atomic_read(&object->use_count) > 1) {
			pr_debug("object->use_count = %d\n",
				 atomic_read(&object->use_count));
			dump_object_info(object);
		}
#endif
		/* reset the reference count (whiten the object) */
		object->count = 0;
		if (color_gray(object) && get_object(object))
			list_add_tail(&object->gray_list, &gray_list);

		spin_unlock_irqrestore(&object->lock, flags);
	}
	rcu_read_unlock();

	/* data/bss scanning */
	scan_block(_sdata, _edata, NULL, 1);
	scan_block(__bss_start, __bss_stop, NULL, 1);

#ifdef CONFIG_SMP
	/* per-cpu sections scanning */
	for_each_possible_cpu(i)
		scan_block(__per_cpu_start + per_cpu_offset(i),
			   __per_cpu_end + per_cpu_offset(i), NULL, 1);
#endif

	/*
	 * Struct page scanning for each node.
	 */
	lock_memory_hotplug();
	for_each_online_node(i) {
		unsigned long start_pfn = node_start_pfn(i);
		unsigned long end_pfn = node_end_pfn(i);
		unsigned long pfn;

		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
			struct page *page;

			if (!pfn_valid(pfn))
				continue;
			page = pfn_to_page(pfn);
			/* only scan if page is in use */
			if (page_count(page) == 0)
				continue;
			scan_block(page, page + 1, NULL, 1);
		}
	}
	unlock_memory_hotplug();

	/*
	 * Scanning the task stacks (may introduce false negatives).
	 */
	if (kmemleak_stack_scan) {
		struct task_struct *p, *g;

		read_lock(&tasklist_lock);
		do_each_thread(g, p) {
			scan_block(task_stack_page(p), task_stack_page(p) +
				   THREAD_SIZE, NULL, 0);
		} while_each_thread(g, p);
		read_unlock(&tasklist_lock);
	}

	/*
	 * Scan the objects already referenced from the sections scanned
	 * above.
	 */
	scan_gray_list();

	/*
	 * Check for new or unreferenced objects modified since the previous
	 * scan and color them gray until the next scan.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(object, &object_list, object_list) {
		spin_lock_irqsave(&object->lock, flags);
		if (color_white(object) && (object->flags & OBJECT_ALLOCATED)
		    && update_checksum(object) && get_object(object)) {
			/* color it gray temporarily */
			object->count = object->min_count;
			list_add_tail(&object->gray_list, &gray_list);
		}
		spin_unlock_irqrestore(&object->lock, flags);
	}
	rcu_read_unlock();

	/*
	 * Re-scan the gray list for modified unreferenced objects.
	 */
	scan_gray_list();

	/*
	 * If scanning was stopped do not report any new unreferenced objects.
	 */
	if (scan_should_stop())
		return;

	/*
	 * Scanning result reporting.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(object, &object_list, object_list) {
		spin_lock_irqsave(&object->lock, flags);
		if (unreferenced_object(object) &&
		    !(object->flags & OBJECT_REPORTED)) {
			object->flags |= OBJECT_REPORTED;
			new_leaks++;
		}
		spin_unlock_irqrestore(&object->lock, flags);
	}
	rcu_read_unlock();

	if (new_leaks)
		pr_info("%d new suspected memory leaks (see "
			"/sys/kernel/debug/kmemleak)\n", new_leaks);

}

/*
 * Thread function performing automatic memory scanning. Unreferenced objects
 * at the end of a memory scan are reported but only the first time.
 */
static int kmemleak_scan_thread(void *arg)
{
	static int first_run = 1;

	pr_info("Automatic memory scanning thread started\n");
	set_user_nice(current, 10);

	/*
	 * Wait before the first scan to allow the system to fully initialize.
	 */
	if (first_run) {
		first_run = 0;
		ssleep(SECS_FIRST_SCAN);
	}

	while (!kthread_should_stop()) {
		signed long timeout = jiffies_scan_wait;

		mutex_lock(&scan_mutex);
		kmemleak_scan();
		mutex_unlock(&scan_mutex);

		/* wait before the next scan */
		while (timeout && !kthread_should_stop())
			timeout = schedule_timeout_interruptible(timeout);
	}

	pr_info("Automatic memory scanning thread ended\n");

	return 0;
}

/*
 * Start the automatic memory scanning thread. This function must be called
 * with the scan_mutex held.
 */
static void start_scan_thread(void)
{
	if (scan_thread)
		return;
	scan_thread = kthread_run(kmemleak_scan_thread, NULL, "kmemleak");
	if (IS_ERR(scan_thread)) {
		pr_warning("Failed to create the scan thread\n");
		scan_thread = NULL;
	}
}

/*
 * Stop the automatic memory scanning thread. This function must be called
 * with the scan_mutex held.
 */
static void stop_scan_thread(void)
{
	if (scan_thread) {
		kthread_stop(scan_thread);
		scan_thread = NULL;
	}
}

/*
 * Iterate over the object_list and return the first valid object at or after
 * the required position with its use_count incremented. The function triggers
 * a memory scanning when the pos argument points to the first position.
 */
static void *kmemleak_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct kmemleak_object *object;
	loff_t n = *pos;
	int err;

	err = mutex_lock_interruptible(&scan_mutex);
	if (err < 0)
		return ERR_PTR(err);

	rcu_read_lock();
	list_for_each_entry_rcu(object, &object_list, object_list) {
		if (n-- > 0)
			continue;
		if (get_object(object))
			goto out;
	}
	object = NULL;
out:
	return object;
}

/*
 * Return the next object in the object_list. The function decrements the
 * use_count of the previous object and increases that of the next one.
 */
static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct kmemleak_object *prev_obj = v;
	struct kmemleak_object *next_obj = NULL;
	struct kmemleak_object *obj = prev_obj;

	++(*pos);

	list_for_each_entry_continue_rcu(obj, &object_list, object_list) {
		if (get_object(obj)) {
			next_obj = obj;
			break;
		}
	}

	put_object(prev_obj);
	return next_obj;
}

/*
 * Decrement the use_count of the last object required, if any.
 */
static void kmemleak_seq_stop(struct seq_file *seq, void *v)
{
	if (!IS_ERR(v)) {
		/*
		 * kmemleak_seq_start may return ERR_PTR if the scan_mutex
		 * waiting was interrupted, so only release it if !IS_ERR.
		 */
		rcu_read_unlock();
		mutex_unlock(&scan_mutex);
		if (v)
			put_object(v);
	}
}

/*
 * Print the information for an unreferenced object to the seq file.
 */
static int kmemleak_seq_show(struct seq_file *seq, void *v)
{
	struct kmemleak_object *object = v;
	unsigned long flags;

	spin_lock_irqsave(&object->lock, flags);
	if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
		print_unreferenced(seq, object);
	spin_unlock_irqrestore(&object->lock, flags);
	return 0;
}

static const struct seq_operations kmemleak_seq_ops = {
	.start = kmemleak_seq_start,
	.next  = kmemleak_seq_next,
	.stop  = kmemleak_seq_stop,
	.show  = kmemleak_seq_show,
};

static int kmemleak_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &kmemleak_seq_ops);
}

static int kmemleak_release(struct inode *inode, struct file *file)
{
	return seq_release(inode, file);
}

static int dump_str_object_info(const char *str)
{
	unsigned long flags;
	struct kmemleak_object *object;
	unsigned long addr;

	if (kstrtoul(str, 0, &addr))
		return -EINVAL;
	object = find_and_get_object(addr, 0);
	if (!object) {
		pr_info("Unknown object at 0x%08lx\n", addr);
		return -EINVAL;
	}

	spin_lock_irqsave(&object->lock, flags);
	dump_object_info(object);
	spin_unlock_irqrestore(&object->lock, flags);

	put_object(object);
	return 0;
}

/*
 * We use grey instead of black to ensure we can do future scans on the same
 * objects. If we did not do future scans these black objects could
 * potentially contain references to newly allocated objects in the future and
 * we'd end up with false positives.
 */
static void kmemleak_clear(void)
{
	struct kmemleak_object *object;
	unsigned long flags;

	rcu_read_lock();
	list_for_each_entry_rcu(object, &object_list, object_list) {
		spin_lock_irqsave(&object->lock, flags);
		if ((object->flags & OBJECT_REPORTED) &&
		    unreferenced_object(object))
			__paint_it(object, KMEMLEAK_GREY);
		spin_unlock_irqrestore(&object->lock, flags);
	}
	rcu_read_unlock();
}

/*
 * File write operation to configure kmemleak at run-time. The following
 * commands can be written to the /sys/kernel/debug/kmemleak file:
 *   off	- disable kmemleak (irreversible)
 *   stack=on	- enable the task stacks scanning
 *   stack=off	- disable the tasks stacks scanning
 *   scan=on	- start the automatic memory scanning thread
 *   scan=off	- stop the automatic memory scanning thread
 *   scan=...	- set the automatic memory scanning period in seconds (0 to
 *		  disable it)
 *   scan	- trigger a memory scan
 *   clear	- mark all current reported unreferenced kmemleak objects as
 *		  grey to ignore printing them
 *   dump=...	- dump information about the object found at the given address
 */
static ssize_t kmemleak_write(struct file *file, const char __user *user_buf,
			      size_t size, loff_t *ppos)
{
	char buf[64];
	int buf_size;
	int ret;

	if (!atomic_read(&kmemleak_enabled))
		return -EBUSY;

	buf_size = min(size, (sizeof(buf) - 1));
	if (strncpy_from_user(buf, user_buf, buf_size) < 0)
		return -EFAULT;
	buf[buf_size] = 0;

	ret = mutex_lock_interruptible(&scan_mutex);
	if (ret < 0)
		return ret;

	if (strncmp(buf, "off", 3) == 0)
		kmemleak_disable();
	else if (strncmp(buf, "stack=on", 8) == 0)
		kmemleak_stack_scan = 1;
	else if (strncmp(buf, "stack=off", 9) == 0)
		kmemleak_stack_scan = 0;
	else if (strncmp(buf, "scan=on", 7) == 0)
		start_scan_thread();
	else if (strncmp(buf, "scan=off", 8) == 0)
		stop_scan_thread();
	else if (strncmp(buf, "scan=", 5) == 0) {
		unsigned long secs;

		ret = kstrtoul(buf + 5, 0, &secs);
		if (ret < 0)
			goto out;
		stop_scan_thread();
		if (secs) {
			jiffies_scan_wait = msecs_to_jiffies(secs * 1000);
			start_scan_thread();
		}
	} else if (strncmp(buf, "scan", 4) == 0)
		kmemleak_scan();
	else if (strncmp(buf, "clear", 5) == 0)
		kmemleak_clear();
	else if (strncmp(buf, "dump=", 5) == 0)
		ret = dump_str_object_info(buf + 5);
	else
		ret = -EINVAL;

out:
	mutex_unlock(&scan_mutex);
	if (ret < 0)
		return ret;

	/* ignore the rest of the buffer, only one command at a time */
	*ppos += size;
	return size;
}

static const struct file_operations kmemleak_fops = {
	.owner		= THIS_MODULE,
	.open		= kmemleak_open,
	.read		= seq_read,
	.write		= kmemleak_write,
	.llseek		= seq_lseek,
	.release	= kmemleak_release,
};

/*
 * Stop the memory scanning thread and free the kmemleak internal objects if
 * no previous scan thread (otherwise, kmemleak may still have some useful
 * information on memory leaks).
 */
static void kmemleak_do_cleanup(struct work_struct *work)
{
	struct kmemleak_object *object;
	bool cleanup = scan_thread == NULL;

	mutex_lock(&scan_mutex);
	stop_scan_thread();

	if (cleanup) {
		rcu_read_lock();
		list_for_each_entry_rcu(object, &object_list, object_list)
			delete_object_full(object->pointer);
		rcu_read_unlock();
	}
	mutex_unlock(&scan_mutex);
}

static DECLARE_WORK(cleanup_work, kmemleak_do_cleanup);

/*
 * Disable kmemleak. No memory allocation/freeing will be traced once this
 * function is called. Disabling kmemleak is an irreversible operation.
 */
static void kmemleak_disable(void)
{
	/* atomically check whether it was already invoked */
	if (atomic_cmpxchg(&kmemleak_error, 0, 1))
		return;

	/* stop any memory operation tracing */
	atomic_set(&kmemleak_enabled, 0);

	/* check whether it is too early for a kernel thread */
	if (atomic_read(&kmemleak_initialized))
		schedule_work(&cleanup_work);

	pr_info("Kernel memory leak detector disabled\n");
}

/*
 * Allow boot-time kmemleak disabling (enabled by default).
 */
static int kmemleak_boot_config(char *str)
{
	if (!str)
		return -EINVAL;
	if (strcmp(str, "off") == 0)
		kmemleak_disable();
	else if (strcmp(str, "on") == 0)
		kmemleak_skip_disable = 1;
	else
		return -EINVAL;
	return 0;
}
early_param("kmemleak", kmemleak_boot_config);

static void __init print_log_trace(struct early_log *log)
{
	struct stack_trace trace;

	trace.nr_entries = log->trace_len;
	trace.entries = log->trace;

	pr_notice("Early log backtrace:\n");
	print_stack_trace(&trace, 2);
}

/*
 * Kmemleak initialization.
 */
void __init kmemleak_init(void)
{
	int i;
	unsigned long flags;

#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
	if (!kmemleak_skip_disable) {
		atomic_set(&kmemleak_early_log, 0);
		kmemleak_disable();
		return;
	}
#endif

	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);

	object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE);
	scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE);

	if (crt_early_log >= ARRAY_SIZE(early_log))
		pr_warning("Early log buffer exceeded (%d), please increase "
			   "DEBUG_KMEMLEAK_EARLY_LOG_SIZE\n", crt_early_log);

	/* the kernel is still in UP mode, so disabling the IRQs is enough */
	local_irq_save(flags);
	atomic_set(&kmemleak_early_log, 0);
	if (atomic_read(&kmemleak_error)) {
		local_irq_restore(flags);
		return;
	} else
		atomic_set(&kmemleak_enabled, 1);
	local_irq_restore(flags);

	/*
	 * This is the point where tracking allocations is safe. Automatic
	 * scanning is started during the late initcall. Add the early logged
	 * callbacks to the kmemleak infrastructure.
	 */
	for (i = 0; i < crt_early_log; i++) {
		struct early_log *log = &early_log[i];

		switch (log->op_type) {
		case KMEMLEAK_ALLOC:
			early_alloc(log);
			break;
		case KMEMLEAK_ALLOC_PERCPU:
			early_alloc_percpu(log);
			break;
		case KMEMLEAK_FREE:
			kmemleak_free(log->ptr);
			break;
		case KMEMLEAK_FREE_PART:
			kmemleak_free_part(log->ptr, log->size);
			break;
		case KMEMLEAK_FREE_PERCPU:
			kmemleak_free_percpu(log->ptr);
			break;
		case KMEMLEAK_NOT_LEAK:
			kmemleak_not_leak(log->ptr);
			break;
		case KMEMLEAK_IGNORE:
			kmemleak_ignore(log->ptr);
			break;
		case KMEMLEAK_SCAN_AREA:
			kmemleak_scan_area(log->ptr, log->size, GFP_KERNEL);
			break;
		case KMEMLEAK_NO_SCAN:
			kmemleak_no_scan(log->ptr);
			break;
		default:
			kmemleak_warn("Unknown early log operation: %d\n",
				      log->op_type);
		}

		if (atomic_read(&kmemleak_warning)) {
			print_log_trace(log);
			atomic_set(&kmemleak_warning, 0);
		}
	}
}

/*
 * Late initialization function.
 */
static int __init kmemleak_late_init(void)
{
	struct dentry *dentry;

	atomic_set(&kmemleak_initialized, 1);

	if (atomic_read(&kmemleak_error)) {
		/*
		 * Some error occurred and kmemleak was disabled. There is a
		 * small chance that kmemleak_disable() was called immediately
		 * after setting kmemleak_initialized and we may end up with
		 * two clean-up threads but serialized by scan_mutex.
		 */
		schedule_work(&cleanup_work);
		return -ENOMEM;
	}

	dentry = debugfs_create_file("kmemleak", S_IRUGO, NULL, NULL,
				     &kmemleak_fops);
	if (!dentry)
		pr_warning("Failed to create the debugfs kmemleak file\n");
	mutex_lock(&scan_mutex);
	start_scan_thread();
	mutex_unlock(&scan_mutex);

	pr_info("Kernel memory leak detector initialized\n");

	return 0;
}
late_initcall(kmemleak_late_init);