summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
blob: 749856a2e736738feab416e3980054e5b5a699b3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
/*
 * User interface for Resource Alloction in Resource Director Technology(RDT)
 *
 * Copyright (C) 2016 Intel Corporation
 *
 * Author: Fenghua Yu <fenghua.yu@intel.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope 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.
 *
 * More information about RDT be found in the Intel (R) x86 Architecture
 * Software Developer Manual.
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
#include <linux/seq_buf.h>
#include <linux/seq_file.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
#include <linux/task_work.h>

#include <uapi/linux/magic.h>

#include <asm/intel_rdt_sched.h>
#include "intel_rdt.h"

DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
static struct kernfs_root *rdt_root;
struct rdtgroup rdtgroup_default;
LIST_HEAD(rdt_all_groups);

/* Kernel fs node for "info" directory under root */
static struct kernfs_node *kn_info;

/* Kernel fs node for "mon_groups" directory under root */
static struct kernfs_node *kn_mongrp;

/* Kernel fs node for "mon_data" directory under root */
static struct kernfs_node *kn_mondata;

static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];

void rdt_last_cmd_clear(void)
{
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_clear(&last_cmd_status);
}

void rdt_last_cmd_puts(const char *s)
{
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_puts(&last_cmd_status, s);
}

void rdt_last_cmd_printf(const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	lockdep_assert_held(&rdtgroup_mutex);
	seq_buf_vprintf(&last_cmd_status, fmt, ap);
	va_end(ap);
}

/*
 * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
 * we can keep a bitmap of free CLOSIDs in a single integer.
 *
 * Using a global CLOSID across all resources has some advantages and
 * some drawbacks:
 * + We can simply set "current->closid" to assign a task to a resource
 *   group.
 * + Context switch code can avoid extra memory references deciding which
 *   CLOSID to load into the PQR_ASSOC MSR
 * - We give up some options in configuring resource groups across multi-socket
 *   systems.
 * - Our choices on how to configure each resource become progressively more
 *   limited as the number of resources grows.
 */
static int closid_free_map;

static void closid_init(void)
{
	struct rdt_resource *r;
	int rdt_min_closid = 32;

	/* Compute rdt_min_closid across all resources */
	for_each_alloc_enabled_rdt_resource(r)
		rdt_min_closid = min(rdt_min_closid, r->num_closid);

	closid_free_map = BIT_MASK(rdt_min_closid) - 1;

	/* CLOSID 0 is always reserved for the default group */
	closid_free_map &= ~1;
}

static int closid_alloc(void)
{
	u32 closid = ffs(closid_free_map);

	if (closid == 0)
		return -ENOSPC;
	closid--;
	closid_free_map &= ~(1 << closid);

	return closid;
}

static void closid_free(int closid)
{
	closid_free_map |= 1 << closid;
}

/* set uid and gid of rdtgroup dirs and files to that of the creator */
static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
{
	struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
				.ia_uid = current_fsuid(),
				.ia_gid = current_fsgid(), };

	if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
	    gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
		return 0;

	return kernfs_setattr(kn, &iattr);
}

static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
{
	struct kernfs_node *kn;
	int ret;

	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
				  0, rft->kf_ops, rft, NULL, NULL);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		kernfs_remove(kn);
		return ret;
	}

	return 0;
}

static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
{
	struct kernfs_open_file *of = m->private;
	struct rftype *rft = of->kn->priv;

	if (rft->seq_show)
		return rft->seq_show(of, m, arg);
	return 0;
}

static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
				   size_t nbytes, loff_t off)
{
	struct rftype *rft = of->kn->priv;

	if (rft->write)
		return rft->write(of, buf, nbytes, off);

	return -EINVAL;
}

static struct kernfs_ops rdtgroup_kf_single_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.write			= rdtgroup_file_write,
	.seq_show		= rdtgroup_seqfile_show,
};

static struct kernfs_ops kf_mondata_ops = {
	.atomic_write_len	= PAGE_SIZE,
	.seq_show		= rdtgroup_mondata_show,
};

static bool is_cpu_list(struct kernfs_open_file *of)
{
	struct rftype *rft = of->kn->priv;

	return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
}

static int rdtgroup_cpus_show(struct kernfs_open_file *of,
			      struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);

	if (rdtgrp) {
		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
			   cpumask_pr_args(&rdtgrp->cpu_mask));
	} else {
		ret = -ENOENT;
	}
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

/*
 * This is safe against intel_rdt_sched_in() called from __switch_to()
 * because __switch_to() is executed with interrupts disabled. A local call
 * from update_closid_rmid() is proteced against __switch_to() because
 * preemption is disabled.
 */
static void update_cpu_closid_rmid(void *info)
{
	struct rdtgroup *r = info;

	if (r) {
		this_cpu_write(pqr_state.default_closid, r->closid);
		this_cpu_write(pqr_state.default_rmid, r->mon.rmid);
	}

	/*
	 * We cannot unconditionally write the MSR because the current
	 * executing task might have its own closid selected. Just reuse
	 * the context switch code.
	 */
	intel_rdt_sched_in();
}

/*
 * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
 *
 * Per task closids/rmids must have been set up before calling this function.
 */
static void
update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
{
	int cpu = get_cpu();

	if (cpumask_test_cpu(cpu, cpu_mask))
		update_cpu_closid_rmid(r);
	smp_call_function_many(cpu_mask, update_cpu_closid_rmid, r, 1);
	put_cpu();
}

static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
			  cpumask_var_t tmpmask)
{
	struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
	struct list_head *head;

	/* Check whether cpus belong to parent ctrl group */
	cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
	if (cpumask_weight(tmpmask)) {
		rdt_last_cmd_puts("can only add CPUs to mongroup that belong to parent\n");
		return -EINVAL;
	}

	/* Check whether cpus are dropped from this group */
	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
	if (cpumask_weight(tmpmask)) {
		/* Give any dropped cpus to parent rdtgroup */
		cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
		update_closid_rmid(tmpmask, prgrp);
	}

	/*
	 * If we added cpus, remove them from previous group that owned them
	 * and update per-cpu rmid
	 */
	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
	if (cpumask_weight(tmpmask)) {
		head = &prgrp->mon.crdtgrp_list;
		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
			if (crgrp == rdtgrp)
				continue;
			cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
				       tmpmask);
		}
		update_closid_rmid(tmpmask, rdtgrp);
	}

	/* Done pushing/pulling - update this group with new mask */
	cpumask_copy(&rdtgrp->cpu_mask, newmask);

	return 0;
}

static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
{
	struct rdtgroup *crgrp;

	cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
	/* update the child mon group masks as well*/
	list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
		cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
}

static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
			   cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
{
	struct rdtgroup *r, *crgrp;
	struct list_head *head;

	/* Check whether cpus are dropped from this group */
	cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
	if (cpumask_weight(tmpmask)) {
		/* Can't drop from default group */
		if (rdtgrp == &rdtgroup_default) {
			rdt_last_cmd_puts("Can't drop CPUs from default group\n");
			return -EINVAL;
		}

		/* Give any dropped cpus to rdtgroup_default */
		cpumask_or(&rdtgroup_default.cpu_mask,
			   &rdtgroup_default.cpu_mask, tmpmask);
		update_closid_rmid(tmpmask, &rdtgroup_default);
	}

	/*
	 * If we added cpus, remove them from previous group and
	 * the prev group's child groups that owned them
	 * and update per-cpu closid/rmid.
	 */
	cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
	if (cpumask_weight(tmpmask)) {
		list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
			if (r == rdtgrp)
				continue;
			cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
			if (cpumask_weight(tmpmask1))
				cpumask_rdtgrp_clear(r, tmpmask1);
		}
		update_closid_rmid(tmpmask, rdtgrp);
	}

	/* Done pushing/pulling - update this group with new mask */
	cpumask_copy(&rdtgrp->cpu_mask, newmask);

	/*
	 * Clear child mon group masks since there is a new parent mask
	 * now and update the rmid for the cpus the child lost.
	 */
	head = &rdtgrp->mon.crdtgrp_list;
	list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
		cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
		update_closid_rmid(tmpmask, rdtgrp);
		cpumask_clear(&crgrp->cpu_mask);
	}

	return 0;
}

static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
				   char *buf, size_t nbytes, loff_t off)
{
	cpumask_var_t tmpmask, newmask, tmpmask1;
	struct rdtgroup *rdtgrp;
	int ret;

	if (!buf)
		return -EINVAL;

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;
	if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
		free_cpumask_var(tmpmask);
		return -ENOMEM;
	}
	if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
		free_cpumask_var(tmpmask);
		free_cpumask_var(newmask);
		return -ENOMEM;
	}

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	rdt_last_cmd_clear();
	if (!rdtgrp) {
		ret = -ENOENT;
		rdt_last_cmd_puts("directory was removed\n");
		goto unlock;
	}

	if (is_cpu_list(of))
		ret = cpulist_parse(buf, newmask);
	else
		ret = cpumask_parse(buf, newmask);

	if (ret) {
		rdt_last_cmd_puts("bad cpu list/mask\n");
		goto unlock;
	}

	/* check that user didn't specify any offline cpus */
	cpumask_andnot(tmpmask, newmask, cpu_online_mask);
	if (cpumask_weight(tmpmask)) {
		ret = -EINVAL;
		rdt_last_cmd_puts("can only assign online cpus\n");
		goto unlock;
	}

	if (rdtgrp->type == RDTCTRL_GROUP)
		ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
	else if (rdtgrp->type == RDTMON_GROUP)
		ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
	else
		ret = -EINVAL;

unlock:
	rdtgroup_kn_unlock(of->kn);
	free_cpumask_var(tmpmask);
	free_cpumask_var(newmask);
	free_cpumask_var(tmpmask1);

	return ret ?: nbytes;
}

struct task_move_callback {
	struct callback_head	work;
	struct rdtgroup		*rdtgrp;
};

static void move_myself(struct callback_head *head)
{
	struct task_move_callback *callback;
	struct rdtgroup *rdtgrp;

	callback = container_of(head, struct task_move_callback, work);
	rdtgrp = callback->rdtgrp;

	/*
	 * If resource group was deleted before this task work callback
	 * was invoked, then assign the task to root group and free the
	 * resource group.
	 */
	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
	    (rdtgrp->flags & RDT_DELETED)) {
		current->closid = 0;
		current->rmid = 0;
		kfree(rdtgrp);
	}

	preempt_disable();
	/* update PQR_ASSOC MSR to make resource group go into effect */
	intel_rdt_sched_in();
	preempt_enable();

	kfree(callback);
}

static int __rdtgroup_move_task(struct task_struct *tsk,
				struct rdtgroup *rdtgrp)
{
	struct task_move_callback *callback;
	int ret;

	callback = kzalloc(sizeof(*callback), GFP_KERNEL);
	if (!callback)
		return -ENOMEM;
	callback->work.func = move_myself;
	callback->rdtgrp = rdtgrp;

	/*
	 * Take a refcount, so rdtgrp cannot be freed before the
	 * callback has been invoked.
	 */
	atomic_inc(&rdtgrp->waitcount);
	ret = task_work_add(tsk, &callback->work, true);
	if (ret) {
		/*
		 * Task is exiting. Drop the refcount and free the callback.
		 * No need to check the refcount as the group cannot be
		 * deleted before the write function unlocks rdtgroup_mutex.
		 */
		atomic_dec(&rdtgrp->waitcount);
		kfree(callback);
		rdt_last_cmd_puts("task exited\n");
	} else {
		/*
		 * For ctrl_mon groups move both closid and rmid.
		 * For monitor groups, can move the tasks only from
		 * their parent CTRL group.
		 */
		if (rdtgrp->type == RDTCTRL_GROUP) {
			tsk->closid = rdtgrp->closid;
			tsk->rmid = rdtgrp->mon.rmid;
		} else if (rdtgrp->type == RDTMON_GROUP) {
			if (rdtgrp->mon.parent->closid == tsk->closid) {
				tsk->rmid = rdtgrp->mon.rmid;
			} else {
				rdt_last_cmd_puts("Can't move task to different control group\n");
				ret = -EINVAL;
			}
		}
	}
	return ret;
}

static int rdtgroup_task_write_permission(struct task_struct *task,
					  struct kernfs_open_file *of)
{
	const struct cred *tcred = get_task_cred(task);
	const struct cred *cred = current_cred();
	int ret = 0;

	/*
	 * Even if we're attaching all tasks in the thread group, we only
	 * need to check permissions on one of them.
	 */
	if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
	    !uid_eq(cred->euid, tcred->uid) &&
	    !uid_eq(cred->euid, tcred->suid)) {
		rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
		ret = -EPERM;
	}

	put_cred(tcred);
	return ret;
}

static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
			      struct kernfs_open_file *of)
{
	struct task_struct *tsk;
	int ret;

	rcu_read_lock();
	if (pid) {
		tsk = find_task_by_vpid(pid);
		if (!tsk) {
			rcu_read_unlock();
			rdt_last_cmd_printf("No task %d\n", pid);
			return -ESRCH;
		}
	} else {
		tsk = current;
	}

	get_task_struct(tsk);
	rcu_read_unlock();

	ret = rdtgroup_task_write_permission(tsk, of);
	if (!ret)
		ret = __rdtgroup_move_task(tsk, rdtgrp);

	put_task_struct(tsk);
	return ret;
}

static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
				    char *buf, size_t nbytes, loff_t off)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;
	pid_t pid;

	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
		return -EINVAL;
	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	rdt_last_cmd_clear();

	if (rdtgrp)
		ret = rdtgroup_move_task(pid, rdtgrp, of);
	else
		ret = -ENOENT;

	rdtgroup_kn_unlock(of->kn);

	return ret ?: nbytes;
}

static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
{
	struct task_struct *p, *t;

	rcu_read_lock();
	for_each_process_thread(p, t) {
		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
			seq_printf(s, "%d\n", t->pid);
	}
	rcu_read_unlock();
}

static int rdtgroup_tasks_show(struct kernfs_open_file *of,
			       struct seq_file *s, void *v)
{
	struct rdtgroup *rdtgrp;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (rdtgrp)
		show_rdt_tasks(rdtgrp, s);
	else
		ret = -ENOENT;
	rdtgroup_kn_unlock(of->kn);

	return ret;
}

static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
				    struct seq_file *seq, void *v)
{
	int len;

	mutex_lock(&rdtgroup_mutex);
	len = seq_buf_used(&last_cmd_status);
	if (len)
		seq_printf(seq, "%.*s", len, last_cmd_status_buf);
	else
		seq_puts(seq, "ok\n");
	mutex_unlock(&rdtgroup_mutex);
	return 0;
}

static int rdt_num_closids_show(struct kernfs_open_file *of,
				struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%d\n", r->num_closid);
	return 0;
}

static int rdt_default_ctrl_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%x\n", r->default_ctrl);
	return 0;
}

static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
	return 0;
}

static int rdt_shareable_bits_show(struct kernfs_open_file *of,
				   struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%x\n", r->cache.shareable_bits);
	return 0;
}

static int rdt_min_bw_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", r->membw.min_bw);
	return 0;
}

static int rdt_num_rmids_show(struct kernfs_open_file *of,
			      struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%d\n", r->num_rmid);

	return 0;
}

static int rdt_mon_features_show(struct kernfs_open_file *of,
				 struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;
	struct mon_evt *mevt;

	list_for_each_entry(mevt, &r->evt_list, list)
		seq_printf(seq, "%s\n", mevt->name);

	return 0;
}

static int rdt_bw_gran_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", r->membw.bw_gran);
	return 0;
}

static int rdt_delay_linear_show(struct kernfs_open_file *of,
			     struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", r->membw.delay_linear);
	return 0;
}

static int max_threshold_occ_show(struct kernfs_open_file *of,
				  struct seq_file *seq, void *v)
{
	struct rdt_resource *r = of->kn->parent->priv;

	seq_printf(seq, "%u\n", intel_cqm_threshold * r->mon_scale);

	return 0;
}

static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
				       char *buf, size_t nbytes, loff_t off)
{
	struct rdt_resource *r = of->kn->parent->priv;
	unsigned int bytes;
	int ret;

	ret = kstrtouint(buf, 0, &bytes);
	if (ret)
		return ret;

	if (bytes > (boot_cpu_data.x86_cache_size * 1024))
		return -EINVAL;

	intel_cqm_threshold = bytes / r->mon_scale;

	return nbytes;
}

/* rdtgroup information files for one cache resource. */
static struct rftype res_common_files[] = {
	{
		.name		= "last_cmd_status",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_last_cmd_status_show,
		.fflags		= RF_TOP_INFO,
	},
	{
		.name		= "num_closids",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_num_closids_show,
		.fflags		= RF_CTRL_INFO,
	},
	{
		.name		= "mon_features",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_mon_features_show,
		.fflags		= RF_MON_INFO,
	},
	{
		.name		= "num_rmids",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_num_rmids_show,
		.fflags		= RF_MON_INFO,
	},
	{
		.name		= "cbm_mask",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_default_ctrl_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "min_cbm_bits",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_min_cbm_bits_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "shareable_bits",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_shareable_bits_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "min_bandwidth",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_min_bw_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
	},
	{
		.name		= "bandwidth_gran",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_bw_gran_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
	},
	{
		.name		= "delay_linear",
		.mode		= 0444,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.seq_show	= rdt_delay_linear_show,
		.fflags		= RF_CTRL_INFO | RFTYPE_RES_MB,
	},
	{
		.name		= "max_threshold_occupancy",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= max_threshold_occ_write,
		.seq_show	= max_threshold_occ_show,
		.fflags		= RF_MON_INFO | RFTYPE_RES_CACHE,
	},
	{
		.name		= "cpus",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_cpus_write,
		.seq_show	= rdtgroup_cpus_show,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "cpus_list",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_cpus_write,
		.seq_show	= rdtgroup_cpus_show,
		.flags		= RFTYPE_FLAGS_CPUS_LIST,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "tasks",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_tasks_write,
		.seq_show	= rdtgroup_tasks_show,
		.fflags		= RFTYPE_BASE,
	},
	{
		.name		= "schemata",
		.mode		= 0644,
		.kf_ops		= &rdtgroup_kf_single_ops,
		.write		= rdtgroup_schemata_write,
		.seq_show	= rdtgroup_schemata_show,
		.fflags		= RF_CTRL_BASE,
	},
};

static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
{
	struct rftype *rfts, *rft;
	int ret, len;

	rfts = res_common_files;
	len = ARRAY_SIZE(res_common_files);

	lockdep_assert_held(&rdtgroup_mutex);

	for (rft = rfts; rft < rfts + len; rft++) {
		if ((fflags & rft->fflags) == rft->fflags) {
			ret = rdtgroup_add_file(kn, rft);
			if (ret)
				goto error;
		}
	}

	return 0;
error:
	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
	while (--rft >= rfts) {
		if ((fflags & rft->fflags) == rft->fflags)
			kernfs_remove_by_name(kn, rft->name);
	}
	return ret;
}

static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
				      unsigned long fflags)
{
	struct kernfs_node *kn_subdir;
	int ret;

	kn_subdir = kernfs_create_dir(kn_info, name,
				      kn_info->mode, r);
	if (IS_ERR(kn_subdir))
		return PTR_ERR(kn_subdir);

	kernfs_get(kn_subdir);
	ret = rdtgroup_kn_set_ugid(kn_subdir);
	if (ret)
		return ret;

	ret = rdtgroup_add_files(kn_subdir, fflags);
	if (!ret)
		kernfs_activate(kn_subdir);

	return ret;
}

static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
{
	struct rdt_resource *r;
	unsigned long fflags;
	char name[32];
	int ret;

	/* create the directory */
	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
	if (IS_ERR(kn_info))
		return PTR_ERR(kn_info);
	kernfs_get(kn_info);

	ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
	if (ret)
		goto out_destroy;

	for_each_alloc_enabled_rdt_resource(r) {
		fflags =  r->fflags | RF_CTRL_INFO;
		ret = rdtgroup_mkdir_info_resdir(r, r->name, fflags);
		if (ret)
			goto out_destroy;
	}

	for_each_mon_enabled_rdt_resource(r) {
		fflags =  r->fflags | RF_MON_INFO;
		sprintf(name, "%s_MON", r->name);
		ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
		if (ret)
			goto out_destroy;
	}

	/*
	 * This extra ref will be put in kernfs_remove() and guarantees
	 * that @rdtgrp->kn is always accessible.
	 */
	kernfs_get(kn_info);

	ret = rdtgroup_kn_set_ugid(kn_info);
	if (ret)
		goto out_destroy;

	kernfs_activate(kn_info);

	return 0;

out_destroy:
	kernfs_remove(kn_info);
	return ret;
}

static int
mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
		    char *name, struct kernfs_node **dest_kn)
{
	struct kernfs_node *kn;
	int ret;

	/* create the directory */
	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	if (dest_kn)
		*dest_kn = kn;

	/*
	 * This extra ref will be put in kernfs_remove() and guarantees
	 * that @rdtgrp->kn is always accessible.
	 */
	kernfs_get(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	kernfs_activate(kn);

	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

static void l3_qos_cfg_update(void *arg)
{
	bool *enable = arg;

	wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
}

static void l2_qos_cfg_update(void *arg)
{
	bool *enable = arg;

	wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
}

static inline bool is_mba_linear(void)
{
	return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear;
}

static int set_cache_qos_cfg(int level, bool enable)
{
	void (*update)(void *arg);
	struct rdt_resource *r_l;
	cpumask_var_t cpu_mask;
	struct rdt_domain *d;
	int cpu;

	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
		return -ENOMEM;

	if (level == RDT_RESOURCE_L3)
		update = l3_qos_cfg_update;
	else if (level == RDT_RESOURCE_L2)
		update = l2_qos_cfg_update;
	else
		return -EINVAL;

	r_l = &rdt_resources_all[level];
	list_for_each_entry(d, &r_l->domains, list) {
		/* Pick one CPU from each domain instance to update MSR */
		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
	}
	cpu = get_cpu();
	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
	if (cpumask_test_cpu(cpu, cpu_mask))
		update(&enable);
	/* Update QOS_CFG MSR on all other cpus in cpu_mask. */
	smp_call_function_many(cpu_mask, update, &enable, 1);
	put_cpu();

	free_cpumask_var(cpu_mask);

	return 0;
}

/*
 * Enable or disable the MBA software controller
 * which helps user specify bandwidth in MBps.
 * MBA software controller is supported only if
 * MBM is supported and MBA is in linear scale.
 */
static int set_mba_sc(bool mba_sc)
{
	struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA];
	struct rdt_domain *d;

	if (!is_mbm_enabled() || !is_mba_linear() ||
	    mba_sc == is_mba_sc(r))
		return -EINVAL;

	r->membw.mba_sc = mba_sc;
	list_for_each_entry(d, &r->domains, list)
		setup_default_ctrlval(r, d->ctrl_val, d->mbps_val);

	return 0;
}

static int cdp_enable(int level, int data_type, int code_type)
{
	struct rdt_resource *r_ldata = &rdt_resources_all[data_type];
	struct rdt_resource *r_lcode = &rdt_resources_all[code_type];
	struct rdt_resource *r_l = &rdt_resources_all[level];
	int ret;

	if (!r_l->alloc_capable || !r_ldata->alloc_capable ||
	    !r_lcode->alloc_capable)
		return -EINVAL;

	ret = set_cache_qos_cfg(level, true);
	if (!ret) {
		r_l->alloc_enabled = false;
		r_ldata->alloc_enabled = true;
		r_lcode->alloc_enabled = true;
	}
	return ret;
}

static int cdpl3_enable(void)
{
	return cdp_enable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA,
			  RDT_RESOURCE_L3CODE);
}

static int cdpl2_enable(void)
{
	return cdp_enable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA,
			  RDT_RESOURCE_L2CODE);
}

static void cdp_disable(int level, int data_type, int code_type)
{
	struct rdt_resource *r = &rdt_resources_all[level];

	r->alloc_enabled = r->alloc_capable;

	if (rdt_resources_all[data_type].alloc_enabled) {
		rdt_resources_all[data_type].alloc_enabled = false;
		rdt_resources_all[code_type].alloc_enabled = false;
		set_cache_qos_cfg(level, false);
	}
}

static void cdpl3_disable(void)
{
	cdp_disable(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA, RDT_RESOURCE_L3CODE);
}

static void cdpl2_disable(void)
{
	cdp_disable(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA, RDT_RESOURCE_L2CODE);
}

static void cdp_disable_all(void)
{
	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
		cdpl3_disable();
	if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled)
		cdpl2_disable();
}

static int parse_rdtgroupfs_options(char *data)
{
	char *token, *o = data;
	int ret = 0;

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token) {
			ret = -EINVAL;
			goto out;
		}

		if (!strcmp(token, "cdp")) {
			ret = cdpl3_enable();
			if (ret)
				goto out;
		} else if (!strcmp(token, "cdpl2")) {
			ret = cdpl2_enable();
			if (ret)
				goto out;
		} else if (!strcmp(token, "mba_MBps")) {
			ret = set_mba_sc(true);
			if (ret)
				goto out;
		} else {
			ret = -EINVAL;
			goto out;
		}
	}

	return 0;

out:
	pr_err("Invalid mount option \"%s\"\n", token);

	return ret;
}

/*
 * We don't allow rdtgroup directories to be created anywhere
 * except the root directory. Thus when looking for the rdtgroup
 * structure for a kernfs node we are either looking at a directory,
 * in which case the rdtgroup structure is pointed at by the "priv"
 * field, otherwise we have a file, and need only look to the parent
 * to find the rdtgroup.
 */
static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
{
	if (kernfs_type(kn) == KERNFS_DIR) {
		/*
		 * All the resource directories use "kn->priv"
		 * to point to the "struct rdtgroup" for the
		 * resource. "info" and its subdirectories don't
		 * have rdtgroup structures, so return NULL here.
		 */
		if (kn == kn_info || kn->parent == kn_info)
			return NULL;
		else
			return kn->priv;
	} else {
		return kn->parent->priv;
	}
}

struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return NULL;

	atomic_inc(&rdtgrp->waitcount);
	kernfs_break_active_protection(kn);

	mutex_lock(&rdtgroup_mutex);

	/* Was this group deleted while we waited? */
	if (rdtgrp->flags & RDT_DELETED)
		return NULL;

	return rdtgrp;
}

void rdtgroup_kn_unlock(struct kernfs_node *kn)
{
	struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);

	if (!rdtgrp)
		return;

	mutex_unlock(&rdtgroup_mutex);

	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
	    (rdtgrp->flags & RDT_DELETED)) {
		kernfs_unbreak_active_protection(kn);
		kernfs_put(rdtgrp->kn);
		kfree(rdtgrp);
	} else {
		kernfs_unbreak_active_protection(kn);
	}
}

static int mkdir_mondata_all(struct kernfs_node *parent_kn,
			     struct rdtgroup *prgrp,
			     struct kernfs_node **mon_data_kn);

static struct dentry *rdt_mount(struct file_system_type *fs_type,
				int flags, const char *unused_dev_name,
				void *data)
{
	struct rdt_domain *dom;
	struct rdt_resource *r;
	struct dentry *dentry;
	int ret;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);
	/*
	 * resctrl file system can only be mounted once.
	 */
	if (static_branch_unlikely(&rdt_enable_key)) {
		dentry = ERR_PTR(-EBUSY);
		goto out;
	}

	ret = parse_rdtgroupfs_options(data);
	if (ret) {
		dentry = ERR_PTR(ret);
		goto out_cdp;
	}

	closid_init();

	ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
	if (ret) {
		dentry = ERR_PTR(ret);
		goto out_cdp;
	}

	if (rdt_mon_capable) {
		ret = mongroup_create_dir(rdtgroup_default.kn,
					  NULL, "mon_groups",
					  &kn_mongrp);
		if (ret) {
			dentry = ERR_PTR(ret);
			goto out_info;
		}
		kernfs_get(kn_mongrp);

		ret = mkdir_mondata_all(rdtgroup_default.kn,
					&rdtgroup_default, &kn_mondata);
		if (ret) {
			dentry = ERR_PTR(ret);
			goto out_mongrp;
		}
		kernfs_get(kn_mondata);
		rdtgroup_default.mon.mon_data_kn = kn_mondata;
	}

	dentry = kernfs_mount(fs_type, flags, rdt_root,
			      RDTGROUP_SUPER_MAGIC, NULL);
	if (IS_ERR(dentry))
		goto out_mondata;

	if (rdt_alloc_capable)
		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
	if (rdt_mon_capable)
		static_branch_enable_cpuslocked(&rdt_mon_enable_key);

	if (rdt_alloc_capable || rdt_mon_capable)
		static_branch_enable_cpuslocked(&rdt_enable_key);

	if (is_mbm_enabled()) {
		r = &rdt_resources_all[RDT_RESOURCE_L3];
		list_for_each_entry(dom, &r->domains, list)
			mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
	}

	goto out;

out_mondata:
	if (rdt_mon_capable)
		kernfs_remove(kn_mondata);
out_mongrp:
	if (rdt_mon_capable)
		kernfs_remove(kn_mongrp);
out_info:
	kernfs_remove(kn_info);
out_cdp:
	cdp_disable_all();
out:
	rdt_last_cmd_clear();
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();

	return dentry;
}

static int reset_all_ctrls(struct rdt_resource *r)
{
	struct msr_param msr_param;
	cpumask_var_t cpu_mask;
	struct rdt_domain *d;
	int i, cpu;

	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
		return -ENOMEM;

	msr_param.res = r;
	msr_param.low = 0;
	msr_param.high = r->num_closid;

	/*
	 * Disable resource control for this resource by setting all
	 * CBMs in all domains to the maximum mask value. Pick one CPU
	 * from each domain to update the MSRs below.
	 */
	list_for_each_entry(d, &r->domains, list) {
		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);

		for (i = 0; i < r->num_closid; i++)
			d->ctrl_val[i] = r->default_ctrl;
	}
	cpu = get_cpu();
	/* Update CBM on this cpu if it's in cpu_mask. */
	if (cpumask_test_cpu(cpu, cpu_mask))
		rdt_ctrl_update(&msr_param);
	/* Update CBM on all other cpus in cpu_mask. */
	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
	put_cpu();

	free_cpumask_var(cpu_mask);

	return 0;
}

static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
{
	return (rdt_alloc_capable &&
		(r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
}

static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
{
	return (rdt_mon_capable &&
		(r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
}

/*
 * Move tasks from one to the other group. If @from is NULL, then all tasks
 * in the systems are moved unconditionally (used for teardown).
 *
 * If @mask is not NULL the cpus on which moved tasks are running are set
 * in that mask so the update smp function call is restricted to affected
 * cpus.
 */
static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
				 struct cpumask *mask)
{
	struct task_struct *p, *t;

	read_lock(&tasklist_lock);
	for_each_process_thread(p, t) {
		if (!from || is_closid_match(t, from) ||
		    is_rmid_match(t, from)) {
			t->closid = to->closid;
			t->rmid = to->mon.rmid;

#ifdef CONFIG_SMP
			/*
			 * This is safe on x86 w/o barriers as the ordering
			 * of writing to task_cpu() and t->on_cpu is
			 * reverse to the reading here. The detection is
			 * inaccurate as tasks might move or schedule
			 * before the smp function call takes place. In
			 * such a case the function call is pointless, but
			 * there is no other side effect.
			 */
			if (mask && t->on_cpu)
				cpumask_set_cpu(task_cpu(t), mask);
#endif
		}
	}
	read_unlock(&tasklist_lock);
}

static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
{
	struct rdtgroup *sentry, *stmp;
	struct list_head *head;

	head = &rdtgrp->mon.crdtgrp_list;
	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
		free_rmid(sentry->mon.rmid);
		list_del(&sentry->mon.crdtgrp_list);
		kfree(sentry);
	}
}

/*
 * Forcibly remove all of subdirectories under root.
 */
static void rmdir_all_sub(void)
{
	struct rdtgroup *rdtgrp, *tmp;

	/* Move all tasks to the default resource group */
	rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);

	list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
		/* Free any child rmids */
		free_all_child_rdtgrp(rdtgrp);

		/* Remove each rdtgroup other than root */
		if (rdtgrp == &rdtgroup_default)
			continue;

		/*
		 * Give any CPUs back to the default group. We cannot copy
		 * cpu_online_mask because a CPU might have executed the
		 * offline callback already, but is still marked online.
		 */
		cpumask_or(&rdtgroup_default.cpu_mask,
			   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);

		free_rmid(rdtgrp->mon.rmid);

		kernfs_remove(rdtgrp->kn);
		list_del(&rdtgrp->rdtgroup_list);
		kfree(rdtgrp);
	}
	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
	update_closid_rmid(cpu_online_mask, &rdtgroup_default);

	kernfs_remove(kn_info);
	kernfs_remove(kn_mongrp);
	kernfs_remove(kn_mondata);
}

static void rdt_kill_sb(struct super_block *sb)
{
	struct rdt_resource *r;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	set_mba_sc(false);

	/*Put everything back to default values. */
	for_each_alloc_enabled_rdt_resource(r)
		reset_all_ctrls(r);
	cdp_disable_all();
	rmdir_all_sub();
	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
	static_branch_disable_cpuslocked(&rdt_enable_key);
	kernfs_kill_sb(sb);
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();
}

static struct file_system_type rdt_fs_type = {
	.name    = "resctrl",
	.mount   = rdt_mount,
	.kill_sb = rdt_kill_sb,
};

static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
		       void *priv)
{
	struct kernfs_node *kn;
	int ret = 0;

	kn = __kernfs_create_file(parent_kn, name, 0444, 0,
				  &kf_mondata_ops, priv, NULL, NULL);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		kernfs_remove(kn);
		return ret;
	}

	return ret;
}

/*
 * Remove all subdirectories of mon_data of ctrl_mon groups
 * and monitor groups with given domain id.
 */
void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id)
{
	struct rdtgroup *prgrp, *crgrp;
	char name[32];

	if (!r->mon_enabled)
		return;

	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
		sprintf(name, "mon_%s_%02d", r->name, dom_id);
		kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);

		list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
			kernfs_remove_by_name(crgrp->mon.mon_data_kn, name);
	}
}

static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
				struct rdt_domain *d,
				struct rdt_resource *r, struct rdtgroup *prgrp)
{
	union mon_data_bits priv;
	struct kernfs_node *kn;
	struct mon_evt *mevt;
	struct rmid_read rr;
	char name[32];
	int ret;

	sprintf(name, "mon_%s_%02d", r->name, d->id);
	/* create the directory */
	kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
	if (IS_ERR(kn))
		return PTR_ERR(kn);

	/*
	 * This extra ref will be put in kernfs_remove() and guarantees
	 * that kn is always accessible.
	 */
	kernfs_get(kn);
	ret = rdtgroup_kn_set_ugid(kn);
	if (ret)
		goto out_destroy;

	if (WARN_ON(list_empty(&r->evt_list))) {
		ret = -EPERM;
		goto out_destroy;
	}

	priv.u.rid = r->rid;
	priv.u.domid = d->id;
	list_for_each_entry(mevt, &r->evt_list, list) {
		priv.u.evtid = mevt->evtid;
		ret = mon_addfile(kn, mevt->name, priv.priv);
		if (ret)
			goto out_destroy;

		if (is_mbm_event(mevt->evtid))
			mon_event_read(&rr, d, prgrp, mevt->evtid, true);
	}
	kernfs_activate(kn);
	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

/*
 * Add all subdirectories of mon_data for "ctrl_mon" groups
 * and "monitor" groups with given domain id.
 */
void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
				    struct rdt_domain *d)
{
	struct kernfs_node *parent_kn;
	struct rdtgroup *prgrp, *crgrp;
	struct list_head *head;

	if (!r->mon_enabled)
		return;

	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
		parent_kn = prgrp->mon.mon_data_kn;
		mkdir_mondata_subdir(parent_kn, d, r, prgrp);

		head = &prgrp->mon.crdtgrp_list;
		list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
			parent_kn = crgrp->mon.mon_data_kn;
			mkdir_mondata_subdir(parent_kn, d, r, crgrp);
		}
	}
}

static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
				       struct rdt_resource *r,
				       struct rdtgroup *prgrp)
{
	struct rdt_domain *dom;
	int ret;

	list_for_each_entry(dom, &r->domains, list) {
		ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
		if (ret)
			return ret;
	}

	return 0;
}

/*
 * This creates a directory mon_data which contains the monitored data.
 *
 * mon_data has one directory for each domain whic are named
 * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
 * with L3 domain looks as below:
 * ./mon_data:
 * mon_L3_00
 * mon_L3_01
 * mon_L3_02
 * ...
 *
 * Each domain directory has one file per event:
 * ./mon_L3_00/:
 * llc_occupancy
 *
 */
static int mkdir_mondata_all(struct kernfs_node *parent_kn,
			     struct rdtgroup *prgrp,
			     struct kernfs_node **dest_kn)
{
	struct rdt_resource *r;
	struct kernfs_node *kn;
	int ret;

	/*
	 * Create the mon_data directory first.
	 */
	ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn);
	if (ret)
		return ret;

	if (dest_kn)
		*dest_kn = kn;

	/*
	 * Create the subdirectories for each domain. Note that all events
	 * in a domain like L3 are grouped into a resource whose domain is L3
	 */
	for_each_mon_enabled_rdt_resource(r) {
		ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
		if (ret)
			goto out_destroy;
	}

	return 0;

out_destroy:
	kernfs_remove(kn);
	return ret;
}

static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
			     struct kernfs_node *prgrp_kn,
			     const char *name, umode_t mode,
			     enum rdt_group_type rtype, struct rdtgroup **r)
{
	struct rdtgroup *prdtgrp, *rdtgrp;
	struct kernfs_node *kn;
	uint files = 0;
	int ret;

	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
	rdt_last_cmd_clear();
	if (!prdtgrp) {
		ret = -ENODEV;
		rdt_last_cmd_puts("directory was removed\n");
		goto out_unlock;
	}

	/* allocate the rdtgroup. */
	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
	if (!rdtgrp) {
		ret = -ENOSPC;
		rdt_last_cmd_puts("kernel out of memory\n");
		goto out_unlock;
	}
	*r = rdtgrp;
	rdtgrp->mon.parent = prdtgrp;
	rdtgrp->type = rtype;
	INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);

	/* kernfs creates the directory for rdtgrp */
	kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
	if (IS_ERR(kn)) {
		ret = PTR_ERR(kn);
		rdt_last_cmd_puts("kernfs create error\n");
		goto out_free_rgrp;
	}
	rdtgrp->kn = kn;

	/*
	 * kernfs_remove() will drop the reference count on "kn" which
	 * will free it. But we still need it to stick around for the
	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
	 * here, which will be dropped inside rdtgroup_kn_unlock().
	 */
	kernfs_get(kn);

	ret = rdtgroup_kn_set_ugid(kn);
	if (ret) {
		rdt_last_cmd_puts("kernfs perm error\n");
		goto out_destroy;
	}

	files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype);
	ret = rdtgroup_add_files(kn, files);
	if (ret) {
		rdt_last_cmd_puts("kernfs fill error\n");
		goto out_destroy;
	}

	if (rdt_mon_capable) {
		ret = alloc_rmid();
		if (ret < 0) {
			rdt_last_cmd_puts("out of RMIDs\n");
			goto out_destroy;
		}
		rdtgrp->mon.rmid = ret;

		ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
		if (ret) {
			rdt_last_cmd_puts("kernfs subdir error\n");
			goto out_idfree;
		}
	}
	kernfs_activate(kn);

	/*
	 * The caller unlocks the prgrp_kn upon success.
	 */
	return 0;

out_idfree:
	free_rmid(rdtgrp->mon.rmid);
out_destroy:
	kernfs_remove(rdtgrp->kn);
out_free_rgrp:
	kfree(rdtgrp);
out_unlock:
	rdtgroup_kn_unlock(prgrp_kn);
	return ret;
}

static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
{
	kernfs_remove(rgrp->kn);
	free_rmid(rgrp->mon.rmid);
	kfree(rgrp);
}

/*
 * Create a monitor group under "mon_groups" directory of a control
 * and monitor group(ctrl_mon). This is a resource group
 * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
 */
static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
			      struct kernfs_node *prgrp_kn,
			      const char *name,
			      umode_t mode)
{
	struct rdtgroup *rdtgrp, *prgrp;
	int ret;

	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP,
				&rdtgrp);
	if (ret)
		return ret;

	prgrp = rdtgrp->mon.parent;
	rdtgrp->closid = prgrp->closid;

	/*
	 * Add the rdtgrp to the list of rdtgrps the parent
	 * ctrl_mon group has to track.
	 */
	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);

	rdtgroup_kn_unlock(prgrp_kn);
	return ret;
}

/*
 * These are rdtgroups created under the root directory. Can be used
 * to allocate and monitor resources.
 */
static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
				   struct kernfs_node *prgrp_kn,
				   const char *name, umode_t mode)
{
	struct rdtgroup *rdtgrp;
	struct kernfs_node *kn;
	u32 closid;
	int ret;

	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP,
				&rdtgrp);
	if (ret)
		return ret;

	kn = rdtgrp->kn;
	ret = closid_alloc();
	if (ret < 0) {
		rdt_last_cmd_puts("out of CLOSIDs\n");
		goto out_common_fail;
	}
	closid = ret;
	ret = 0;

	rdtgrp->closid = closid;
	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);

	if (rdt_mon_capable) {
		/*
		 * Create an empty mon_groups directory to hold the subset
		 * of tasks and cpus to monitor.
		 */
		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
		if (ret) {
			rdt_last_cmd_puts("kernfs subdir error\n");
			goto out_id_free;
		}
	}

	goto out_unlock;

out_id_free:
	closid_free(closid);
	list_del(&rdtgrp->rdtgroup_list);
out_common_fail:
	mkdir_rdt_prepare_clean(rdtgrp);
out_unlock:
	rdtgroup_kn_unlock(prgrp_kn);
	return ret;
}

/*
 * We allow creating mon groups only with in a directory called "mon_groups"
 * which is present in every ctrl_mon group. Check if this is a valid
 * "mon_groups" directory.
 *
 * 1. The directory should be named "mon_groups".
 * 2. The mon group itself should "not" be named "mon_groups".
 *   This makes sure "mon_groups" directory always has a ctrl_mon group
 *   as parent.
 */
static bool is_mon_groups(struct kernfs_node *kn, const char *name)
{
	return (!strcmp(kn->name, "mon_groups") &&
		strcmp(name, "mon_groups"));
}

static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
			  umode_t mode)
{
	/* Do not accept '\n' to avoid unparsable situation. */
	if (strchr(name, '\n'))
		return -EINVAL;

	/*
	 * If the parent directory is the root directory and RDT
	 * allocation is supported, add a control and monitoring
	 * subdirectory
	 */
	if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn)
		return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode);

	/*
	 * If RDT monitoring is supported and the parent directory is a valid
	 * "mon_groups" directory, add a monitoring subdirectory.
	 */
	if (rdt_mon_capable && is_mon_groups(parent_kn, name))
		return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode);

	return -EPERM;
}

static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
			      cpumask_var_t tmpmask)
{
	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
	int cpu;

	/* Give any tasks back to the parent group */
	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);

	/* Update per cpu rmid of the moved CPUs first */
	for_each_cpu(cpu, &rdtgrp->cpu_mask)
		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
	/*
	 * Update the MSR on moved CPUs and CPUs which have moved
	 * task running on them.
	 */
	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
	update_closid_rmid(tmpmask, NULL);

	rdtgrp->flags = RDT_DELETED;
	free_rmid(rdtgrp->mon.rmid);

	/*
	 * Remove the rdtgrp from the parent ctrl_mon group's list
	 */
	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
	list_del(&rdtgrp->mon.crdtgrp_list);

	/*
	 * one extra hold on this, will drop when we kfree(rdtgrp)
	 * in rdtgroup_kn_unlock()
	 */
	kernfs_get(kn);
	kernfs_remove(rdtgrp->kn);

	return 0;
}

static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
			       cpumask_var_t tmpmask)
{
	int cpu;

	/* Give any tasks back to the default group */
	rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);

	/* Give any CPUs back to the default group */
	cpumask_or(&rdtgroup_default.cpu_mask,
		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);

	/* Update per cpu closid and rmid of the moved CPUs first */
	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
	}

	/*
	 * Update the MSR on moved CPUs and CPUs which have moved
	 * task running on them.
	 */
	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
	update_closid_rmid(tmpmask, NULL);

	rdtgrp->flags = RDT_DELETED;
	closid_free(rdtgrp->closid);
	free_rmid(rdtgrp->mon.rmid);

	/*
	 * Free all the child monitor group rmids.
	 */
	free_all_child_rdtgrp(rdtgrp);

	list_del(&rdtgrp->rdtgroup_list);

	/*
	 * one extra hold on this, will drop when we kfree(rdtgrp)
	 * in rdtgroup_kn_unlock()
	 */
	kernfs_get(kn);
	kernfs_remove(rdtgrp->kn);

	return 0;
}

static int rdtgroup_rmdir(struct kernfs_node *kn)
{
	struct kernfs_node *parent_kn = kn->parent;
	struct rdtgroup *rdtgrp;
	cpumask_var_t tmpmask;
	int ret = 0;

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	rdtgrp = rdtgroup_kn_lock_live(kn);
	if (!rdtgrp) {
		ret = -EPERM;
		goto out;
	}

	/*
	 * If the rdtgroup is a ctrl_mon group and parent directory
	 * is the root directory, remove the ctrl_mon group.
	 *
	 * If the rdtgroup is a mon group and parent directory
	 * is a valid "mon_groups" directory, remove the mon group.
	 */
	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
		ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
	else if (rdtgrp->type == RDTMON_GROUP &&
		 is_mon_groups(parent_kn, kn->name))
		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
	else
		ret = -EPERM;

out:
	rdtgroup_kn_unlock(kn);
	free_cpumask_var(tmpmask);
	return ret;
}

static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
{
	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled)
		seq_puts(seq, ",cdp");
	return 0;
}

static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
	.mkdir		= rdtgroup_mkdir,
	.rmdir		= rdtgroup_rmdir,
	.show_options	= rdtgroup_show_options,
};

static int __init rdtgroup_setup_root(void)
{
	int ret;

	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
				      KERNFS_ROOT_CREATE_DEACTIVATED,
				      &rdtgroup_default);
	if (IS_ERR(rdt_root))
		return PTR_ERR(rdt_root);

	mutex_lock(&rdtgroup_mutex);

	rdtgroup_default.closid = 0;
	rdtgroup_default.mon.rmid = 0;
	rdtgroup_default.type = RDTCTRL_GROUP;
	INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);

	list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);

	ret = rdtgroup_add_files(rdt_root->kn, RF_CTRL_BASE);
	if (ret) {
		kernfs_destroy_root(rdt_root);
		goto out;
	}

	rdtgroup_default.kn = rdt_root->kn;
	kernfs_activate(rdtgroup_default.kn);

out:
	mutex_unlock(&rdtgroup_mutex);

	return ret;
}

/*
 * rdtgroup_init - rdtgroup initialization
 *
 * Setup resctrl file system including set up root, create mount point,
 * register rdtgroup filesystem, and initialize files under root directory.
 *
 * Return: 0 on success or -errno
 */
int __init rdtgroup_init(void)
{
	int ret = 0;

	seq_buf_init(&last_cmd_status, last_cmd_status_buf,
		     sizeof(last_cmd_status_buf));

	ret = rdtgroup_setup_root();
	if (ret)
		return ret;

	ret = sysfs_create_mount_point(fs_kobj, "resctrl");
	if (ret)
		goto cleanup_root;

	ret = register_filesystem(&rdt_fs_type);
	if (ret)
		goto cleanup_mountpoint;

	return 0;

cleanup_mountpoint:
	sysfs_remove_mount_point(fs_kobj, "resctrl");
cleanup_root:
	kernfs_destroy_root(rdt_root);

	return ret;
}