File: task_mmu.c

package info (click to toggle)
linux 3.16.56-1+deb8u1
  • links: PTS, VCS
  • area: main
  • in suites: jessie
  • size: 739,780 kB
  • sloc: ansic: 12,238,760; asm: 277,795; perl: 53,071; xml: 47,771; makefile: 30,548; sh: 7,977; python: 6,699; cpp: 5,132; yacc: 4,254; lex: 2,215; awk: 741; pascal: 231; lisp: 218; sed: 30
file content (1571 lines) | stat: -rw-r--r-- 39,770 bytes parent folder | download | duplicates (3)
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
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>

#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"

void task_mem(struct seq_file *m, struct mm_struct *mm)
{
	unsigned long data, text, lib, swap;
	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;

	/*
	 * Note: to minimize their overhead, mm maintains hiwater_vm and
	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
	 * collector of these hiwater stats must therefore get total_vm
	 * and rss too, which will usually be the higher.  Barriers? not
	 * worth the effort, such snapshots can always be inconsistent.
	 */
	hiwater_vm = total_vm = mm->total_vm;
	if (hiwater_vm < mm->hiwater_vm)
		hiwater_vm = mm->hiwater_vm;
	hiwater_rss = total_rss = get_mm_rss(mm);
	if (hiwater_rss < mm->hiwater_rss)
		hiwater_rss = mm->hiwater_rss;

	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
	swap = get_mm_counter(mm, MM_SWAPENTS);
	seq_printf(m,
		"VmPeak:\t%8lu kB\n"
		"VmSize:\t%8lu kB\n"
		"VmLck:\t%8lu kB\n"
		"VmPin:\t%8lu kB\n"
		"VmHWM:\t%8lu kB\n"
		"VmRSS:\t%8lu kB\n"
		"VmData:\t%8lu kB\n"
		"VmStk:\t%8lu kB\n"
		"VmExe:\t%8lu kB\n"
		"VmLib:\t%8lu kB\n"
		"VmPTE:\t%8lu kB\n"
		"VmSwap:\t%8lu kB\n",
		hiwater_vm << (PAGE_SHIFT-10),
		total_vm << (PAGE_SHIFT-10),
		mm->locked_vm << (PAGE_SHIFT-10),
		mm->pinned_vm << (PAGE_SHIFT-10),
		hiwater_rss << (PAGE_SHIFT-10),
		total_rss << (PAGE_SHIFT-10),
		data << (PAGE_SHIFT-10),
		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
		(PTRS_PER_PTE * sizeof(pte_t) *
		 atomic_long_read(&mm->nr_ptes)) >> 10,
		swap << (PAGE_SHIFT-10));
}

unsigned long task_vsize(struct mm_struct *mm)
{
	return PAGE_SIZE * mm->total_vm;
}

unsigned long task_statm(struct mm_struct *mm,
			 unsigned long *shared, unsigned long *text,
			 unsigned long *data, unsigned long *resident)
{
	*shared = get_mm_counter(mm, MM_FILEPAGES);
	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
								>> PAGE_SHIFT;
	*data = mm->total_vm - mm->shared_vm;
	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
	return mm->total_vm;
}

#ifdef CONFIG_NUMA
/*
 * These functions are for numa_maps but called in generic **maps seq_file
 * ->start(), ->stop() ops.
 *
 * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
 * Each mempolicy object is controlled by reference counting. The problem here
 * is how to avoid accessing dead mempolicy object.
 *
 * Because we're holding mmap_sem while reading seq_file, it's safe to access
 * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
 *
 * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
 * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
 * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
 * gurantee the task never exits under us. But taking task_lock() around
 * get_vma_plicy() causes lock order problem.
 *
 * To access task->mempolicy without lock, we hold a reference count of an
 * object pointed by task->mempolicy and remember it. This will guarantee
 * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
 */
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
	struct task_struct *task = priv->task;

	task_lock(task);
	priv->task_mempolicy = task->mempolicy;
	mpol_get(priv->task_mempolicy);
	task_unlock(task);
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
	mpol_put(priv->task_mempolicy);
}
#else
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
}
#endif

static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
	if (vma && vma != priv->tail_vma) {
		struct mm_struct *mm = vma->vm_mm;
		release_task_mempolicy(priv);
		up_read(&mm->mmap_sem);
		mmput(mm);
	}
}

static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	unsigned long last_addr = m->version;
	struct mm_struct *mm;
	struct vm_area_struct *vma, *tail_vma = NULL;
	loff_t l = *pos;

	/* Clear the per syscall fields in priv */
	priv->task = NULL;
	priv->tail_vma = NULL;

	/*
	 * We remember last_addr rather than next_addr to hit with
	 * vmacache most of the time. We have zero last_addr at
	 * the beginning and also after lseek. We will have -1 last_addr
	 * after the end of the vmas.
	 */

	if (last_addr == -1UL)
		return NULL;

	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
	if (!priv->task)
		return ERR_PTR(-ESRCH);

	mm = mm_access(priv->task, PTRACE_MODE_READ_FSCREDS);
	if (!mm || IS_ERR(mm))
		return mm;
	down_read(&mm->mmap_sem);

	tail_vma = get_gate_vma(priv->task->mm);
	priv->tail_vma = tail_vma;
	hold_task_mempolicy(priv);
	/* Start with last addr hint */
	vma = find_vma(mm, last_addr);
	if (last_addr && vma) {
		vma = vma->vm_next;
		goto out;
	}

	/*
	 * Check the vma index is within the range and do
	 * sequential scan until m_index.
	 */
	vma = NULL;
	if ((unsigned long)l < mm->map_count) {
		vma = mm->mmap;
		while (l-- && vma)
			vma = vma->vm_next;
		goto out;
	}

	if (l != mm->map_count)
		tail_vma = NULL; /* After gate vma */

out:
	if (vma)
		return vma;

	release_task_mempolicy(priv);
	/* End of vmas has been reached */
	m->version = (tail_vma != NULL)? 0: -1UL;
	up_read(&mm->mmap_sem);
	mmput(mm);
	return tail_vma;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;
	struct vm_area_struct *tail_vma = priv->tail_vma;

	(*pos)++;
	if (vma && (vma != tail_vma) && vma->vm_next)
		return vma->vm_next;
	vma_stop(priv, vma);
	return (vma != tail_vma)? tail_vma: NULL;
}

static void m_stop(struct seq_file *m, void *v)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;

	if (!IS_ERR(vma))
		vma_stop(priv, vma);
	if (priv->task)
		put_task_struct(priv->task);
}

static int do_maps_open(struct inode *inode, struct file *file,
			const struct seq_operations *ops)
{
	struct proc_maps_private *priv;
	int ret = -ENOMEM;
	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (priv) {
		priv->pid = proc_pid(inode);
		ret = seq_open(file, ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = priv;
		} else {
			kfree(priv);
		}
	}
	return ret;
}

static void
show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
	struct mm_struct *mm = vma->vm_mm;
	struct file *file = vma->vm_file;
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;
	vm_flags_t flags = vma->vm_flags;
	unsigned long ino = 0;
	unsigned long long pgoff = 0;
	unsigned long start, end;
	dev_t dev = 0;
	const char *name = NULL;

	if (file) {
		struct inode *inode;

		file = vma_pr_or_file(vma);
		inode = file_inode(file);
		dev = inode->i_sb->s_dev;
		ino = inode->i_ino;
		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
	}

	/* We don't show the stack guard page in /proc/maps */
	start = vma->vm_start;
	end = vma->vm_end;

	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
			start,
			end,
			flags & VM_READ ? 'r' : '-',
			flags & VM_WRITE ? 'w' : '-',
			flags & VM_EXEC ? 'x' : '-',
			flags & VM_MAYSHARE ? 's' : 'p',
			pgoff,
			MAJOR(dev), MINOR(dev), ino);

	/*
	 * Print the dentry name for named mappings, and a
	 * special [heap] marker for the heap:
	 */
	if (file) {
		seq_pad(m, ' ');
		seq_path(m, &file->f_path, "\n");
		goto done;
	}

	if (vma->vm_ops && vma->vm_ops->name) {
		name = vma->vm_ops->name(vma);
		if (name)
			goto done;
	}

	name = arch_vma_name(vma);
	if (!name) {
		pid_t tid;

		if (!mm) {
			name = "[vdso]";
			goto done;
		}

		if (vma->vm_start <= mm->brk &&
		    vma->vm_end >= mm->start_brk) {
			name = "[heap]";
			goto done;
		}

		tid = vm_is_stack(task, vma, is_pid);

		if (tid != 0) {
			/*
			 * Thread stack in /proc/PID/task/TID/maps or
			 * the main process stack.
			 */
			if (!is_pid || (vma->vm_start <= mm->start_stack &&
			    vma->vm_end >= mm->start_stack)) {
				name = "[stack]";
			} else {
				/* Thread stack in /proc/PID/maps */
				seq_pad(m, ' ');
				seq_printf(m, "[stack:%d]", tid);
			}
		}
	}

done:
	if (name) {
		seq_pad(m, ' ');
		seq_puts(m, name);
	}
	seq_putc(m, '\n');
}

static int show_map(struct seq_file *m, void *v, int is_pid)
{
	struct vm_area_struct *vma = v;
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;

	show_map_vma(m, vma, is_pid);

	if (m->count < m->size)  /* vma is copied successfully */
		m->version = (vma != get_gate_vma(task->mm))
			? vma->vm_start : 0;
	return 0;
}

static int show_pid_map(struct seq_file *m, void *v)
{
	return show_map(m, v, 1);
}

static int show_tid_map(struct seq_file *m, void *v)
{
	return show_map(m, v, 0);
}

static const struct seq_operations proc_pid_maps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_pid_map
};

static const struct seq_operations proc_tid_maps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_tid_map
};

static int pid_maps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_pid_maps_op);
}

static int tid_maps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_tid_maps_op);
}

const struct file_operations proc_pid_maps_operations = {
	.open		= pid_maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

const struct file_operations proc_tid_maps_operations = {
	.open		= tid_maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

/*
 * Proportional Set Size(PSS): my share of RSS.
 *
 * PSS of a process is the count of pages it has in memory, where each
 * page is divided by the number of processes sharing it.  So if a
 * process has 1000 pages all to itself, and 1000 shared with one other
 * process, its PSS will be 1500.
 *
 * To keep (accumulated) division errors low, we adopt a 64bit
 * fixed-point pss counter to minimize division errors. So (pss >>
 * PSS_SHIFT) would be the real byte count.
 *
 * A shift of 12 before division means (assuming 4K page size):
 * 	- 1M 3-user-pages add up to 8KB errors;
 * 	- supports mapcount up to 2^24, or 16M;
 * 	- supports PSS up to 2^52 bytes, or 4PB.
 */
#define PSS_SHIFT 12

#ifdef CONFIG_PROC_PAGE_MONITOR
struct mem_size_stats {
	struct vm_area_struct *vma;
	unsigned long resident;
	unsigned long shared_clean;
	unsigned long shared_dirty;
	unsigned long private_clean;
	unsigned long private_dirty;
	unsigned long referenced;
	unsigned long anonymous;
	unsigned long anonymous_thp;
	unsigned long swap;
	unsigned long nonlinear;
	u64 pss;
};


static void smaps_pte_entry(pte_t ptent, unsigned long addr,
		unsigned long ptent_size, struct mm_walk *walk)
{
	struct mem_size_stats *mss = walk->private;
	struct vm_area_struct *vma = mss->vma;
	pgoff_t pgoff = linear_page_index(vma, addr);
	struct page *page = NULL;
	int mapcount;

	if (pte_present(ptent)) {
		page = vm_normal_page(vma, addr, ptent);
	} else if (is_swap_pte(ptent)) {
		swp_entry_t swpent = pte_to_swp_entry(ptent);

		if (!non_swap_entry(swpent))
			mss->swap += ptent_size;
		else if (is_migration_entry(swpent))
			page = migration_entry_to_page(swpent);
	} else if (pte_file(ptent)) {
		if (pte_to_pgoff(ptent) != pgoff)
			mss->nonlinear += ptent_size;
	}

	if (!page)
		return;

	if (PageAnon(page))
		mss->anonymous += ptent_size;

	if (page->index != pgoff)
		mss->nonlinear += ptent_size;

	mss->resident += ptent_size;
	/* Accumulate the size in pages that have been accessed. */
	if (pte_young(ptent) || PageReferenced(page))
		mss->referenced += ptent_size;
	mapcount = page_mapcount(page);
	if (mapcount >= 2) {
		if (pte_dirty(ptent) || PageDirty(page))
			mss->shared_dirty += ptent_size;
		else
			mss->shared_clean += ptent_size;
		mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
	} else {
		if (pte_dirty(ptent) || PageDirty(page))
			mss->private_dirty += ptent_size;
		else
			mss->private_clean += ptent_size;
		mss->pss += (ptent_size << PSS_SHIFT);
	}
}

static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			   struct mm_walk *walk)
{
	struct mem_size_stats *mss = walk->private;
	struct vm_area_struct *vma = mss->vma;
	pte_t *pte;
	spinlock_t *ptl;

	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
		spin_unlock(ptl);
		mss->anonymous_thp += HPAGE_PMD_SIZE;
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
	/*
	 * The mmap_sem held all the way back in m_start() is what
	 * keeps khugepaged out of here and from collapsing things
	 * in here.
	 */
	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE)
		smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();
	return 0;
}

static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
{
	/*
	 * Don't forget to update Documentation/ on changes.
	 */
	static const char mnemonics[BITS_PER_LONG][2] = {
		/*
		 * In case if we meet a flag we don't know about.
		 */
		[0 ... (BITS_PER_LONG-1)] = "??",

		[ilog2(VM_READ)]	= "rd",
		[ilog2(VM_WRITE)]	= "wr",
		[ilog2(VM_EXEC)]	= "ex",
		[ilog2(VM_SHARED)]	= "sh",
		[ilog2(VM_MAYREAD)]	= "mr",
		[ilog2(VM_MAYWRITE)]	= "mw",
		[ilog2(VM_MAYEXEC)]	= "me",
		[ilog2(VM_MAYSHARE)]	= "ms",
		[ilog2(VM_GROWSDOWN)]	= "gd",
		[ilog2(VM_PFNMAP)]	= "pf",
		[ilog2(VM_DENYWRITE)]	= "dw",
		[ilog2(VM_LOCKED)]	= "lo",
		[ilog2(VM_IO)]		= "io",
		[ilog2(VM_SEQ_READ)]	= "sr",
		[ilog2(VM_RAND_READ)]	= "rr",
		[ilog2(VM_DONTCOPY)]	= "dc",
		[ilog2(VM_DONTEXPAND)]	= "de",
		[ilog2(VM_ACCOUNT)]	= "ac",
		[ilog2(VM_NORESERVE)]	= "nr",
		[ilog2(VM_HUGETLB)]	= "ht",
		[ilog2(VM_NONLINEAR)]	= "nl",
		[ilog2(VM_ARCH_1)]	= "ar",
		[ilog2(VM_DONTDUMP)]	= "dd",
#ifdef CONFIG_MEM_SOFT_DIRTY
		[ilog2(VM_SOFTDIRTY)]	= "sd",
#endif
		[ilog2(VM_MIXEDMAP)]	= "mm",
		[ilog2(VM_HUGEPAGE)]	= "hg",
		[ilog2(VM_NOHUGEPAGE)]	= "nh",
		[ilog2(VM_MERGEABLE)]	= "mg",
	};
	size_t i;

	seq_puts(m, "VmFlags: ");
	for (i = 0; i < BITS_PER_LONG; i++) {
		if (vma->vm_flags & (1UL << i)) {
			seq_printf(m, "%c%c ",
				   mnemonics[i][0], mnemonics[i][1]);
		}
	}
	seq_putc(m, '\n');
}

static int show_smap(struct seq_file *m, void *v, int is_pid)
{
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;
	struct vm_area_struct *vma = v;
	struct mem_size_stats mss;
	struct mm_walk smaps_walk = {
		.pmd_entry = smaps_pte_range,
		.mm = vma->vm_mm,
		.private = &mss,
	};

	memset(&mss, 0, sizeof mss);
	mss.vma = vma;
	/* mmap_sem is held in m_start */
	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);

	show_map_vma(m, vma, is_pid);

	seq_printf(m,
		   "Size:           %8lu kB\n"
		   "Rss:            %8lu kB\n"
		   "Pss:            %8lu kB\n"
		   "Shared_Clean:   %8lu kB\n"
		   "Shared_Dirty:   %8lu kB\n"
		   "Private_Clean:  %8lu kB\n"
		   "Private_Dirty:  %8lu kB\n"
		   "Referenced:     %8lu kB\n"
		   "Anonymous:      %8lu kB\n"
		   "AnonHugePages:  %8lu kB\n"
		   "Swap:           %8lu kB\n"
		   "KernelPageSize: %8lu kB\n"
		   "MMUPageSize:    %8lu kB\n"
		   "Locked:         %8lu kB\n",
		   (vma->vm_end - vma->vm_start) >> 10,
		   mss.resident >> 10,
		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
		   mss.shared_clean  >> 10,
		   mss.shared_dirty  >> 10,
		   mss.private_clean >> 10,
		   mss.private_dirty >> 10,
		   mss.referenced >> 10,
		   mss.anonymous >> 10,
		   mss.anonymous_thp >> 10,
		   mss.swap >> 10,
		   vma_kernel_pagesize(vma) >> 10,
		   vma_mmu_pagesize(vma) >> 10,
		   (vma->vm_flags & VM_LOCKED) ?
			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);

	if (vma->vm_flags & VM_NONLINEAR)
		seq_printf(m, "Nonlinear:      %8lu kB\n",
				mss.nonlinear >> 10);

	show_smap_vma_flags(m, vma);

	if (m->count < m->size)  /* vma is copied successfully */
		m->version = (vma != get_gate_vma(task->mm))
			? vma->vm_start : 0;
	return 0;
}

static int show_pid_smap(struct seq_file *m, void *v)
{
	return show_smap(m, v, 1);
}

static int show_tid_smap(struct seq_file *m, void *v)
{
	return show_smap(m, v, 0);
}

static const struct seq_operations proc_pid_smaps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_pid_smap
};

static const struct seq_operations proc_tid_smaps_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_tid_smap
};

static int pid_smaps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_pid_smaps_op);
}

static int tid_smaps_open(struct inode *inode, struct file *file)
{
	return do_maps_open(inode, file, &proc_tid_smaps_op);
}

const struct file_operations proc_pid_smaps_operations = {
	.open		= pid_smaps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

const struct file_operations proc_tid_smaps_operations = {
	.open		= tid_smaps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

/*
 * We do not want to have constant page-shift bits sitting in
 * pagemap entries and are about to reuse them some time soon.
 *
 * Here's the "migration strategy":
 * 1. when the system boots these bits remain what they are,
 *    but a warning about future change is printed in log;
 * 2. once anyone clears soft-dirty bits via clear_refs file,
 *    these flag is set to denote, that user is aware of the
 *    new API and those page-shift bits change their meaning.
 *    The respective warning is printed in dmesg;
 * 3. In a couple of releases we will remove all the mentions
 *    of page-shift in pagemap entries.
 */

static bool soft_dirty_cleared __read_mostly;

enum clear_refs_types {
	CLEAR_REFS_ALL = 1,
	CLEAR_REFS_ANON,
	CLEAR_REFS_MAPPED,
	CLEAR_REFS_SOFT_DIRTY,
	CLEAR_REFS_LAST,
};

struct clear_refs_private {
	struct vm_area_struct *vma;
	enum clear_refs_types type;
};

static inline void clear_soft_dirty(struct vm_area_struct *vma,
		unsigned long addr, pte_t *pte)
{
#ifdef CONFIG_MEM_SOFT_DIRTY
	/*
	 * The soft-dirty tracker uses #PF-s to catch writes
	 * to pages, so write-protect the pte as well. See the
	 * Documentation/vm/soft-dirty.txt for full description
	 * of how soft-dirty works.
	 */
	pte_t ptent = *pte;

	if (pte_present(ptent)) {
		ptent = pte_wrprotect(ptent);
		ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
	} else if (is_swap_pte(ptent)) {
		ptent = pte_swp_clear_soft_dirty(ptent);
	} else if (pte_file(ptent)) {
		ptent = pte_file_clear_soft_dirty(ptent);
	}

	set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}

static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
				unsigned long end, struct mm_walk *walk)
{
	struct clear_refs_private *cp = walk->private;
	struct vm_area_struct *vma = cp->vma;
	pte_t *pte, ptent;
	spinlock_t *ptl;
	struct page *page;

	split_huge_page_pmd(vma, addr, pmd);
	if (pmd_trans_unstable(pmd))
		return 0;

	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
	for (; addr != end; pte++, addr += PAGE_SIZE) {
		ptent = *pte;

		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
			clear_soft_dirty(vma, addr, pte);
			continue;
		}

		if (!pte_present(ptent))
			continue;

		page = vm_normal_page(vma, addr, ptent);
		if (!page)
			continue;

		/* Clear accessed and referenced bits. */
		ptep_test_and_clear_young(vma, addr, pte);
		ClearPageReferenced(page);
	}
	pte_unmap_unlock(pte - 1, ptl);
	cond_resched();
	return 0;
}

static ssize_t clear_refs_write(struct file *file, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct task_struct *task;
	char buffer[PROC_NUMBUF];
	struct mm_struct *mm;
	struct vm_area_struct *vma;
	enum clear_refs_types type;
	int itype;
	int rv;

	memset(buffer, 0, sizeof(buffer));
	if (count > sizeof(buffer) - 1)
		count = sizeof(buffer) - 1;
	if (copy_from_user(buffer, buf, count))
		return -EFAULT;
	rv = kstrtoint(strstrip(buffer), 10, &itype);
	if (rv < 0)
		return rv;
	type = (enum clear_refs_types)itype;
	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
		return -EINVAL;

	if (type == CLEAR_REFS_SOFT_DIRTY) {
		soft_dirty_cleared = true;
		pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
			     " See the linux/Documentation/vm/pagemap.txt for "
			     "details.\n");
	}

	task = get_proc_task(file_inode(file));
	if (!task)
		return -ESRCH;
	mm = get_task_mm(task);
	if (mm) {
		struct clear_refs_private cp = {
			.type = type,
		};
		struct mm_walk clear_refs_walk = {
			.pmd_entry = clear_refs_pte_range,
			.mm = mm,
			.private = &cp,
		};
		down_read(&mm->mmap_sem);
		if (type == CLEAR_REFS_SOFT_DIRTY)
			mmu_notifier_invalidate_range_start(mm, 0, -1);
		for (vma = mm->mmap; vma; vma = vma->vm_next) {
			cp.vma = vma;
			if (is_vm_hugetlb_page(vma))
				continue;
			/*
			 * Writing 1 to /proc/pid/clear_refs affects all pages.
			 *
			 * Writing 2 to /proc/pid/clear_refs only affects
			 * Anonymous pages.
			 *
			 * Writing 3 to /proc/pid/clear_refs only affects file
			 * mapped pages.
			 *
			 * Writing 4 to /proc/pid/clear_refs affects all pages.
			 */
			if (type == CLEAR_REFS_ANON && vma->vm_file)
				continue;
			if (type == CLEAR_REFS_MAPPED && !vma->vm_file)
				continue;
			if (type == CLEAR_REFS_SOFT_DIRTY) {
				if (vma->vm_flags & VM_SOFTDIRTY)
					vma->vm_flags &= ~VM_SOFTDIRTY;
			}
			walk_page_range(vma->vm_start, vma->vm_end,
					&clear_refs_walk);
		}
		if (type == CLEAR_REFS_SOFT_DIRTY)
			mmu_notifier_invalidate_range_end(mm, 0, -1);
		flush_tlb_mm(mm);
		up_read(&mm->mmap_sem);
		mmput(mm);
	}
	put_task_struct(task);

	return count;
}

const struct file_operations proc_clear_refs_operations = {
	.write		= clear_refs_write,
	.llseek		= noop_llseek,
};

typedef struct {
	u64 pme;
} pagemap_entry_t;

struct pagemapread {
	int pos, len;		/* units: PM_ENTRY_BYTES, not bytes */
	pagemap_entry_t *buffer;
	bool v2;
};

#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
#define PAGEMAP_WALK_MASK	(PMD_MASK)

#define PM_ENTRY_BYTES      sizeof(pagemap_entry_t)
#define PM_STATUS_BITS      3
#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
#define PM_PSHIFT_BITS      6
#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
/* in "new" pagemap pshift bits are occupied with more status bits */
#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))

#define __PM_SOFT_DIRTY      (1LL)
#define PM_PRESENT          PM_STATUS(4LL)
#define PM_SWAP             PM_STATUS(2LL)
#define PM_FILE             PM_STATUS(1LL)
#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
#define PM_END_OF_BUFFER    1

static inline pagemap_entry_t make_pme(u64 val)
{
	return (pagemap_entry_t) { .pme = val };
}

static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
			  struct pagemapread *pm)
{
	pm->buffer[pm->pos++] = *pme;
	if (pm->pos >= pm->len)
		return PM_END_OF_BUFFER;
	return 0;
}

static int pagemap_pte_hole(unsigned long start, unsigned long end,
				struct mm_walk *walk)
{
	struct pagemapread *pm = walk->private;
	unsigned long addr;
	int err = 0;
	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));

	for (addr = start; addr < end; addr += PAGE_SIZE) {
		err = add_to_pagemap(addr, &pme, pm);
		if (err)
			break;
	}
	return err;
}

static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
	u64 frame, flags;
	struct page *page = NULL;
	int flags2 = 0;

	if (pte_present(pte)) {
		frame = pte_pfn(pte);
		flags = PM_PRESENT;
		page = vm_normal_page(vma, addr, pte);
		if (pte_soft_dirty(pte))
			flags2 |= __PM_SOFT_DIRTY;
	} else if (is_swap_pte(pte)) {
		swp_entry_t entry;
		if (pte_swp_soft_dirty(pte))
			flags2 |= __PM_SOFT_DIRTY;
		entry = pte_to_swp_entry(pte);
		frame = swp_type(entry) |
			(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
		flags = PM_SWAP;
		if (is_migration_entry(entry))
			page = migration_entry_to_page(entry);
	} else {
		if (vma->vm_flags & VM_SOFTDIRTY)
			flags2 |= __PM_SOFT_DIRTY;
		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
		return;
	}

	if (page && !PageAnon(page))
		flags |= PM_FILE;
	if ((vma->vm_flags & VM_SOFTDIRTY))
		flags2 |= __PM_SOFT_DIRTY;

	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
		pmd_t pmd, int offset, int pmd_flags2)
{
	/*
	 * Currently pmd for thp is always present because thp can not be
	 * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
	 * This if-check is just to prepare for future implementation.
	 */
	if (pmd_present(pmd))
		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
	else
		*pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
}
#else
static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
		pmd_t pmd, int offset, int pmd_flags2)
{
}
#endif

static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			     struct mm_walk *walk)
{
	struct vm_area_struct *vma;
	struct pagemapread *pm = walk->private;
	spinlock_t *ptl;
	pte_t *pte, *orig_pte;
	int err = 0;

	/* find the first VMA at or above 'addr' */
	vma = find_vma(walk->mm, addr);
	if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
		int pmd_flags2;

		if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
			pmd_flags2 = __PM_SOFT_DIRTY;
		else
			pmd_flags2 = 0;

		for (; addr != end; addr += PAGE_SIZE) {
			unsigned long offset;
			pagemap_entry_t pme;

			offset = (addr & ~PAGEMAP_WALK_MASK) >>
					PAGE_SHIFT;
			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
			err = add_to_pagemap(addr, &pme, pm);
			if (err)
				break;
		}
		spin_unlock(ptl);
		return err;
	}

	if (pmd_trans_unstable(pmd))
		return 0;

	while (1) {
		/* End of address space hole, which we mark as non-present. */
		unsigned long hole_end;

		if (vma)
			hole_end = min(end, vma->vm_start);
		else
			hole_end = end;

		for (; addr < hole_end; addr += PAGE_SIZE) {
			pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));

			err = add_to_pagemap(addr, &pme, pm);
			if (err)
				return err;
		}

		if (!vma || vma->vm_start >= end)
			break;
		/*
		 * We can't possibly be in a hugetlb VMA. In general,
		 * for a mm_walk with a pmd_entry and a hugetlb_entry,
		 * the pmd_entry can only be called on addresses in a
		 * hugetlb if the walk starts in a non-hugetlb VMA and
		 * spans a hugepage VMA. Since pagemap_read walks are
		 * PMD-sized and PMD-aligned, this will never be true.
		 */
		BUG_ON(is_vm_hugetlb_page(vma));

		/* Addresses in the VMA. */
		orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
		for (; addr < min(end, vma->vm_end); pte++, addr += PAGE_SIZE) {
			pagemap_entry_t pme;

			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
			err = add_to_pagemap(addr, &pme, pm);
			if (err)
				break;
		}
		pte_unmap_unlock(orig_pte, ptl);

		if (err)
			return err;

		if (addr == end)
			break;

		vma = find_vma(walk->mm, addr);
	}

	cond_resched();

	return err;
}

#ifdef CONFIG_HUGETLB_PAGE
static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
					pte_t pte, int offset, int flags2)
{
	if (pte_present(pte))
		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)	|
				PM_STATUS2(pm->v2, flags2)		|
				PM_PRESENT);
	else
		*pme = make_pme(PM_NOT_PRESENT(pm->v2)			|
				PM_STATUS2(pm->v2, flags2));
}

/* This function walks within one hugetlb entry in the single call */
static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
				 unsigned long addr, unsigned long end,
				 struct mm_walk *walk)
{
	struct pagemapread *pm = walk->private;
	struct vm_area_struct *vma;
	int err = 0;
	int flags2;
	pagemap_entry_t pme;

	vma = find_vma(walk->mm, addr);
	WARN_ON_ONCE(!vma);

	if (vma && (vma->vm_flags & VM_SOFTDIRTY))
		flags2 = __PM_SOFT_DIRTY;
	else
		flags2 = 0;

	for (; addr != end; addr += PAGE_SIZE) {
		int offset = (addr & ~hmask) >> PAGE_SHIFT;
		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
		err = add_to_pagemap(addr, &pme, pm);
		if (err)
			return err;
	}

	cond_resched();

	return err;
}
#endif /* HUGETLB_PAGE */

/*
 * /proc/pid/pagemap - an array mapping virtual pages to pfns
 *
 * For each page in the address space, this file contains one 64-bit entry
 * consisting of the following:
 *
 * Bits 0-54  page frame number (PFN) if present
 * Bits 0-4   swap type if swapped
 * Bits 5-54  swap offset if swapped
 * Bits 55-60 page shift (page size = 1<<page shift)
 * Bit  61    page is file-page or shared-anon
 * Bit  62    page swapped
 * Bit  63    page present
 *
 * If the page is not present but in swap, then the PFN contains an
 * encoding of the swap file number and the page's offset into the
 * swap. Unmapped pages return a null PFN. This allows determining
 * precisely which pages are mapped (or in swap) and comparing mapped
 * pages between processes.
 *
 * Efficient users of this interface will use /proc/pid/maps to
 * determine which areas of memory are actually mapped and llseek to
 * skip over unmapped regions.
 */
static ssize_t pagemap_read(struct file *file, char __user *buf,
			    size_t count, loff_t *ppos)
{
	struct task_struct *task = get_proc_task(file_inode(file));
	struct mm_struct *mm;
	struct pagemapread pm;
	int ret = -ESRCH;
	struct mm_walk pagemap_walk = {};
	unsigned long src;
	unsigned long svpfn;
	unsigned long start_vaddr;
	unsigned long end_vaddr;
	int copied = 0;

	if (!task)
		goto out;

	ret = -EINVAL;
	/* file position must be aligned */
	if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
		goto out_task;

	ret = 0;
	if (!count)
		goto out_task;

	pm.v2 = soft_dirty_cleared;
	pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
	pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
	ret = -ENOMEM;
	if (!pm.buffer)
		goto out_task;

	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
	ret = PTR_ERR(mm);
	if (!mm || IS_ERR(mm))
		goto out_free;

	pagemap_walk.pmd_entry = pagemap_pte_range;
	pagemap_walk.pte_hole = pagemap_pte_hole;
#ifdef CONFIG_HUGETLB_PAGE
	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
#endif
	pagemap_walk.mm = mm;
	pagemap_walk.private = &pm;

	src = *ppos;
	svpfn = src / PM_ENTRY_BYTES;
	start_vaddr = svpfn << PAGE_SHIFT;
	end_vaddr = TASK_SIZE_OF(task);

	/* watch out for wraparound */
	if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
		start_vaddr = end_vaddr;

	/*
	 * The odds are that this will stop walking way
	 * before end_vaddr, because the length of the
	 * user buffer is tracked in "pm", and the walk
	 * will stop when we hit the end of the buffer.
	 */
	ret = 0;
	while (count && (start_vaddr < end_vaddr)) {
		int len;
		unsigned long end;

		pm.pos = 0;
		end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK;
		/* overflow ? */
		if (end < start_vaddr || end > end_vaddr)
			end = end_vaddr;
		down_read(&mm->mmap_sem);
		ret = walk_page_range(start_vaddr, end, &pagemap_walk);
		up_read(&mm->mmap_sem);
		start_vaddr = end;

		len = min(count, PM_ENTRY_BYTES * pm.pos);
		if (copy_to_user(buf, pm.buffer, len)) {
			ret = -EFAULT;
			goto out_mm;
		}
		copied += len;
		buf += len;
		count -= len;
	}
	*ppos += copied;
	if (!ret || ret == PM_END_OF_BUFFER)
		ret = copied;

out_mm:
	mmput(mm);
out_free:
	kfree(pm.buffer);
out_task:
	put_task_struct(task);
out:
	return ret;
}

static int pagemap_open(struct inode *inode, struct file *file)
{
	/* do not disclose physical addresses: attack vector */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
			"to stop being page-shift some time soon. See the "
			"linux/Documentation/vm/pagemap.txt for details.\n");
	return 0;
}

const struct file_operations proc_pagemap_operations = {
	.llseek		= mem_lseek, /* borrow this */
	.read		= pagemap_read,
	.open		= pagemap_open,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */

#ifdef CONFIG_NUMA

struct numa_maps {
	struct vm_area_struct *vma;
	unsigned long pages;
	unsigned long anon;
	unsigned long active;
	unsigned long writeback;
	unsigned long mapcount_max;
	unsigned long dirty;
	unsigned long swapcache;
	unsigned long node[MAX_NUMNODES];
};

struct numa_maps_private {
	struct proc_maps_private proc_maps;
	struct numa_maps md;
};

static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
			unsigned long nr_pages)
{
	int count = page_mapcount(page);

	md->pages += nr_pages;
	if (pte_dirty || PageDirty(page))
		md->dirty += nr_pages;

	if (PageSwapCache(page))
		md->swapcache += nr_pages;

	if (PageActive(page) || PageUnevictable(page))
		md->active += nr_pages;

	if (PageWriteback(page))
		md->writeback += nr_pages;

	if (PageAnon(page))
		md->anon += nr_pages;

	if (count > md->mapcount_max)
		md->mapcount_max = count;

	md->node[page_to_nid(page)] += nr_pages;
}

static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
		unsigned long addr)
{
	struct page *page;
	int nid;

	if (!pte_present(pte))
		return NULL;

	page = vm_normal_page(vma, addr, pte);
	if (!page)
		return NULL;

	if (PageReserved(page))
		return NULL;

	nid = page_to_nid(page);
	if (!node_isset(nid, node_states[N_MEMORY]))
		return NULL;

	return page;
}

static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
		unsigned long end, struct mm_walk *walk)
{
	struct numa_maps *md;
	spinlock_t *ptl;
	pte_t *orig_pte;
	pte_t *pte;

	md = walk->private;

	if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
		pte_t huge_pte = *(pte_t *)pmd;
		struct page *page;

		page = can_gather_numa_stats(huge_pte, md->vma, addr);
		if (page)
			gather_stats(page, md, pte_dirty(huge_pte),
				     HPAGE_PMD_SIZE/PAGE_SIZE);
		spin_unlock(ptl);
		return 0;
	}

	if (pmd_trans_unstable(pmd))
		return 0;
	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
	do {
		struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
		if (!page)
			continue;
		gather_stats(page, md, pte_dirty(*pte), 1);

	} while (pte++, addr += PAGE_SIZE, addr != end);
	pte_unmap_unlock(orig_pte, ptl);
	return 0;
}
#ifdef CONFIG_HUGETLB_PAGE
static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
		unsigned long addr, unsigned long end, struct mm_walk *walk)
{
	struct numa_maps *md;
	struct page *page;

	if (!pte_present(*pte))
		return 0;

	page = pte_page(*pte);
	if (!page)
		return 0;

	md = walk->private;
	gather_stats(page, md, pte_dirty(*pte), 1);
	return 0;
}

#else
static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
		unsigned long addr, unsigned long end, struct mm_walk *walk)
{
	return 0;
}
#endif

/*
 * Display pages allocated per node and memory policy via /proc.
 */
static int show_numa_map(struct seq_file *m, void *v, int is_pid)
{
	struct numa_maps_private *numa_priv = m->private;
	struct proc_maps_private *proc_priv = &numa_priv->proc_maps;
	struct vm_area_struct *vma = v;
	struct numa_maps *md = &numa_priv->md;
	struct file *file = vma_pr_or_file(vma);
	struct task_struct *task = proc_priv->task;
	struct mm_struct *mm = vma->vm_mm;
	struct mm_walk walk = {};
	struct mempolicy *pol;
	char buffer[64];
	int nid;

	if (!mm)
		return 0;

	/* Ensure we start with an empty set of numa_maps statistics. */
	memset(md, 0, sizeof(*md));

	md->vma = vma;

	walk.hugetlb_entry = gather_hugetbl_stats;
	walk.pmd_entry = gather_pte_stats;
	walk.private = md;
	walk.mm = mm;

	pol = get_vma_policy(task, vma, vma->vm_start);
	mpol_to_str(buffer, sizeof(buffer), pol);
	mpol_cond_put(pol);

	seq_printf(m, "%08lx %s", vma->vm_start, buffer);

	if (file) {
		seq_puts(m, " file=");
		seq_path(m, &file->f_path, "\n\t= ");
	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
		seq_puts(m, " heap");
	} else {
		pid_t tid = vm_is_stack(task, vma, is_pid);
		if (tid != 0) {
			/*
			 * Thread stack in /proc/PID/task/TID/maps or
			 * the main process stack.
			 */
			if (!is_pid || (vma->vm_start <= mm->start_stack &&
			    vma->vm_end >= mm->start_stack))
				seq_puts(m, " stack");
			else
				seq_printf(m, " stack:%d", tid);
		}
	}

	if (is_vm_hugetlb_page(vma))
		seq_puts(m, " huge");

	walk_page_range(vma->vm_start, vma->vm_end, &walk);

	if (!md->pages)
		goto out;

	if (md->anon)
		seq_printf(m, " anon=%lu", md->anon);

	if (md->dirty)
		seq_printf(m, " dirty=%lu", md->dirty);

	if (md->pages != md->anon && md->pages != md->dirty)
		seq_printf(m, " mapped=%lu", md->pages);

	if (md->mapcount_max > 1)
		seq_printf(m, " mapmax=%lu", md->mapcount_max);

	if (md->swapcache)
		seq_printf(m, " swapcache=%lu", md->swapcache);

	if (md->active < md->pages && !is_vm_hugetlb_page(vma))
		seq_printf(m, " active=%lu", md->active);

	if (md->writeback)
		seq_printf(m, " writeback=%lu", md->writeback);

	for_each_node_state(nid, N_MEMORY)
		if (md->node[nid])
			seq_printf(m, " N%d=%lu", nid, md->node[nid]);
out:
	seq_putc(m, '\n');

	if (m->count < m->size)
		m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0;
	return 0;
}

static int show_pid_numa_map(struct seq_file *m, void *v)
{
	return show_numa_map(m, v, 1);
}

static int show_tid_numa_map(struct seq_file *m, void *v)
{
	return show_numa_map(m, v, 0);
}

static const struct seq_operations proc_pid_numa_maps_op = {
	.start  = m_start,
	.next   = m_next,
	.stop   = m_stop,
	.show   = show_pid_numa_map,
};

static const struct seq_operations proc_tid_numa_maps_op = {
	.start  = m_start,
	.next   = m_next,
	.stop   = m_stop,
	.show   = show_tid_numa_map,
};

static int numa_maps_open(struct inode *inode, struct file *file,
			  const struct seq_operations *ops)
{
	struct numa_maps_private *priv;
	int ret = -ENOMEM;
	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (priv) {
		priv->proc_maps.pid = proc_pid(inode);
		ret = seq_open(file, ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = priv;
		} else {
			kfree(priv);
		}
	}
	return ret;
}

static int pid_numa_maps_open(struct inode *inode, struct file *file)
{
	return numa_maps_open(inode, file, &proc_pid_numa_maps_op);
}

static int tid_numa_maps_open(struct inode *inode, struct file *file)
{
	return numa_maps_open(inode, file, &proc_tid_numa_maps_op);
}

const struct file_operations proc_pid_numa_maps_operations = {
	.open		= pid_numa_maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};

const struct file_operations proc_tid_numa_maps_operations = {
	.open		= tid_numa_maps_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release_private,
};
#endif /* CONFIG_NUMA */