summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
blob: f8c260d522ca045f33a675e47a225c908854be5d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Resource Director Technology (RDT)
 *
 * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
 *
 * Copyright (C) 2018 Intel Corporation
 *
 * Author: Reinette Chatre <reinette.chatre@intel.com>
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/cacheinfo.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
#include <linux/kthread.h>
#include <linux/mman.h>
#include <linux/pm_qos.h>
#include <linux/slab.h>
#include <linux/uaccess.h>

#include <asm/cacheflush.h>
#include <asm/intel-family.h>
#include <asm/intel_rdt_sched.h>
#include <asm/perf_event.h>

#include "intel_rdt.h"

#define CREATE_TRACE_POINTS
#include "intel_rdt_pseudo_lock_event.h"

/*
 * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
 * prefetcher state. Details about this register can be found in the MSR
 * tables for specific platforms found in Intel's SDM.
 */
#define MSR_MISC_FEATURE_CONTROL	0x000001a4

/*
 * The bits needed to disable hardware prefetching varies based on the
 * platform. During initialization we will discover which bits to use.
 */
static u64 prefetch_disable_bits;

/*
 * Major number assigned to and shared by all devices exposing
 * pseudo-locked regions.
 */
static unsigned int pseudo_lock_major;
static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
static struct class *pseudo_lock_class;

/**
 * get_prefetch_disable_bits - prefetch disable bits of supported platforms
 *
 * Capture the list of platforms that have been validated to support
 * pseudo-locking. This includes testing to ensure pseudo-locked regions
 * with low cache miss rates can be created under variety of load conditions
 * as well as that these pseudo-locked regions can maintain their low cache
 * miss rates under variety of load conditions for significant lengths of time.
 *
 * After a platform has been validated to support pseudo-locking its
 * hardware prefetch disable bits are included here as they are documented
 * in the SDM.
 *
 * When adding a platform here also add support for its cache events to
 * measure_cycles_perf_fn()
 *
 * Return:
 * If platform is supported, the bits to disable hardware prefetchers, 0
 * if platform is not supported.
 */
static u64 get_prefetch_disable_bits(void)
{
	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
	    boot_cpu_data.x86 != 6)
		return 0;

	switch (boot_cpu_data.x86_model) {
	case INTEL_FAM6_BROADWELL_X:
		/*
		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
		 * as:
		 * 0    L2 Hardware Prefetcher Disable (R/W)
		 * 1    L2 Adjacent Cache Line Prefetcher Disable (R/W)
		 * 2    DCU Hardware Prefetcher Disable (R/W)
		 * 3    DCU IP Prefetcher Disable (R/W)
		 * 63:4 Reserved
		 */
		return 0xF;
	case INTEL_FAM6_ATOM_GOLDMONT:
	case INTEL_FAM6_ATOM_GEMINI_LAKE:
		/*
		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
		 * as:
		 * 0     L2 Hardware Prefetcher Disable (R/W)
		 * 1     Reserved
		 * 2     DCU Hardware Prefetcher Disable (R/W)
		 * 63:3  Reserved
		 */
		return 0x5;
	}

	return 0;
}

/*
 * Helper to write 64bit value to MSR without tracing. Used when
 * use of the cache should be restricted and use of registers used
 * for local variables avoided.
 */
static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
{
	__wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
}

/**
 * pseudo_lock_minor_get - Obtain available minor number
 * @minor: Pointer to where new minor number will be stored
 *
 * A bitmask is used to track available minor numbers. Here the next free
 * minor number is marked as unavailable and returned.
 *
 * Return: 0 on success, <0 on failure.
 */
static int pseudo_lock_minor_get(unsigned int *minor)
{
	unsigned long first_bit;

	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);

	if (first_bit == MINORBITS)
		return -ENOSPC;

	__clear_bit(first_bit, &pseudo_lock_minor_avail);
	*minor = first_bit;

	return 0;
}

/**
 * pseudo_lock_minor_release - Return minor number to available
 * @minor: The minor number made available
 */
static void pseudo_lock_minor_release(unsigned int minor)
{
	__set_bit(minor, &pseudo_lock_minor_avail);
}

/**
 * region_find_by_minor - Locate a pseudo-lock region by inode minor number
 * @minor: The minor number of the device representing pseudo-locked region
 *
 * When the character device is accessed we need to determine which
 * pseudo-locked region it belongs to. This is done by matching the minor
 * number of the device to the pseudo-locked region it belongs.
 *
 * Minor numbers are assigned at the time a pseudo-locked region is associated
 * with a cache instance.
 *
 * Return: On success return pointer to resource group owning the pseudo-locked
 *         region, NULL on failure.
 */
static struct rdtgroup *region_find_by_minor(unsigned int minor)
{
	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;

	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
			rdtgrp_match = rdtgrp;
			break;
		}
	}
	return rdtgrp_match;
}

/**
 * pseudo_lock_pm_req - A power management QoS request list entry
 * @list:	Entry within the @pm_reqs list for a pseudo-locked region
 * @req:	PM QoS request
 */
struct pseudo_lock_pm_req {
	struct list_head list;
	struct dev_pm_qos_request req;
};

static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
{
	struct pseudo_lock_pm_req *pm_req, *next;

	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
		dev_pm_qos_remove_request(&pm_req->req);
		list_del(&pm_req->list);
		kfree(pm_req);
	}
}

/**
 * pseudo_lock_cstates_constrain - Restrict cores from entering C6
 *
 * To prevent the cache from being affected by power management entering
 * C6 has to be avoided. This is accomplished by requesting a latency
 * requirement lower than lowest C6 exit latency of all supported
 * platforms as found in the cpuidle state tables in the intel_idle driver.
 * At this time it is possible to do so with a single latency requirement
 * for all supported platforms.
 *
 * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
 * the ACPI latencies need to be considered while keeping in mind that C2
 * may be set to map to deeper sleep states. In this case the latency
 * requirement needs to prevent entering C2 also.
 */
static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
{
	struct pseudo_lock_pm_req *pm_req;
	int cpu;
	int ret;

	for_each_cpu(cpu, &plr->d->cpu_mask) {
		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
		if (!pm_req) {
			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
			ret = -ENOMEM;
			goto out_err;
		}
		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
					     &pm_req->req,
					     DEV_PM_QOS_RESUME_LATENCY,
					     30);
		if (ret < 0) {
			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
					    cpu);
			kfree(pm_req);
			ret = -1;
			goto out_err;
		}
		list_add(&pm_req->list, &plr->pm_reqs);
	}

	return 0;

out_err:
	pseudo_lock_cstates_relax(plr);
	return ret;
}

/**
 * pseudo_lock_region_clear - Reset pseudo-lock region data
 * @plr: pseudo-lock region
 *
 * All content of the pseudo-locked region is reset - any memory allocated
 * freed.
 *
 * Return: void
 */
static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
{
	plr->size = 0;
	plr->line_size = 0;
	kfree(plr->kmem);
	plr->kmem = NULL;
	plr->r = NULL;
	if (plr->d)
		plr->d->plr = NULL;
	plr->d = NULL;
	plr->cbm = 0;
	plr->debugfs_dir = NULL;
}

/**
 * pseudo_lock_region_init - Initialize pseudo-lock region information
 * @plr: pseudo-lock region
 *
 * Called after user provided a schemata to be pseudo-locked. From the
 * schemata the &struct pseudo_lock_region is on entry already initialized
 * with the resource, domain, and capacity bitmask. Here the information
 * required for pseudo-locking is deduced from this data and &struct
 * pseudo_lock_region initialized further. This information includes:
 * - size in bytes of the region to be pseudo-locked
 * - cache line size to know the stride with which data needs to be accessed
 *   to be pseudo-locked
 * - a cpu associated with the cache instance on which the pseudo-locking
 *   flow can be executed
 *
 * Return: 0 on success, <0 on failure. Descriptive error will be written
 * to last_cmd_status buffer.
 */
static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
{
	struct cpu_cacheinfo *ci;
	int ret;
	int i;

	/* Pick the first cpu we find that is associated with the cache. */
	plr->cpu = cpumask_first(&plr->d->cpu_mask);

	if (!cpu_online(plr->cpu)) {
		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
				    plr->cpu);
		ret = -ENODEV;
		goto out_region;
	}

	ci = get_cpu_cacheinfo(plr->cpu);

	plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);

	for (i = 0; i < ci->num_leaves; i++) {
		if (ci->info_list[i].level == plr->r->cache_level) {
			plr->line_size = ci->info_list[i].coherency_line_size;
			return 0;
		}
	}

	ret = -1;
	rdt_last_cmd_puts("unable to determine cache line size\n");
out_region:
	pseudo_lock_region_clear(plr);
	return ret;
}

/**
 * pseudo_lock_init - Initialize a pseudo-lock region
 * @rdtgrp: resource group to which new pseudo-locked region will belong
 *
 * A pseudo-locked region is associated with a resource group. When this
 * association is created the pseudo-locked region is initialized. The
 * details of the pseudo-locked region are not known at this time so only
 * allocation is done and association established.
 *
 * Return: 0 on success, <0 on failure
 */
static int pseudo_lock_init(struct rdtgroup *rdtgrp)
{
	struct pseudo_lock_region *plr;

	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
	if (!plr)
		return -ENOMEM;

	init_waitqueue_head(&plr->lock_thread_wq);
	INIT_LIST_HEAD(&plr->pm_reqs);
	rdtgrp->plr = plr;
	return 0;
}

/**
 * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
 * @plr: pseudo-lock region
 *
 * Initialize the details required to set up the pseudo-locked region and
 * allocate the contiguous memory that will be pseudo-locked to the cache.
 *
 * Return: 0 on success, <0 on failure.  Descriptive error will be written
 * to last_cmd_status buffer.
 */
static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
{
	int ret;

	ret = pseudo_lock_region_init(plr);
	if (ret < 0)
		return ret;

	/*
	 * We do not yet support contiguous regions larger than
	 * KMALLOC_MAX_SIZE.
	 */
	if (plr->size > KMALLOC_MAX_SIZE) {
		rdt_last_cmd_puts("requested region exceeds maximum size\n");
		ret = -E2BIG;
		goto out_region;
	}

	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
	if (!plr->kmem) {
		rdt_last_cmd_puts("unable to allocate memory\n");
		ret = -ENOMEM;
		goto out_region;
	}

	ret = 0;
	goto out;
out_region:
	pseudo_lock_region_clear(plr);
out:
	return ret;
}

/**
 * pseudo_lock_free - Free a pseudo-locked region
 * @rdtgrp: resource group to which pseudo-locked region belonged
 *
 * The pseudo-locked region's resources have already been released, or not
 * yet created at this point. Now it can be freed and disassociated from the
 * resource group.
 *
 * Return: void
 */
static void pseudo_lock_free(struct rdtgroup *rdtgrp)
{
	pseudo_lock_region_clear(rdtgrp->plr);
	kfree(rdtgrp->plr);
	rdtgrp->plr = NULL;
}

/**
 * pseudo_lock_fn - Load kernel memory into cache
 * @_rdtgrp: resource group to which pseudo-lock region belongs
 *
 * This is the core pseudo-locking flow.
 *
 * First we ensure that the kernel memory cannot be found in the cache.
 * Then, while taking care that there will be as little interference as
 * possible, the memory to be loaded is accessed while core is running
 * with class of service set to the bitmask of the pseudo-locked region.
 * After this is complete no future CAT allocations will be allowed to
 * overlap with this bitmask.
 *
 * Local register variables are utilized to ensure that the memory region
 * to be locked is the only memory access made during the critical locking
 * loop.
 *
 * Return: 0. Waiter on waitqueue will be woken on completion.
 */
static int pseudo_lock_fn(void *_rdtgrp)
{
	struct rdtgroup *rdtgrp = _rdtgrp;
	struct pseudo_lock_region *plr = rdtgrp->plr;
	u32 rmid_p, closid_p;
	unsigned long i;
#ifdef CONFIG_KASAN
	/*
	 * The registers used for local register variables are also used
	 * when KASAN is active. When KASAN is active we use a regular
	 * variable to ensure we always use a valid pointer, but the cost
	 * is that this variable will enter the cache through evicting the
	 * memory we are trying to lock into the cache. Thus expect lower
	 * pseudo-locking success rate when KASAN is active.
	 */
	unsigned int line_size;
	unsigned int size;
	void *mem_r;
#else
	register unsigned int line_size asm("esi");
	register unsigned int size asm("edi");
#ifdef CONFIG_X86_64
	register void *mem_r asm("rbx");
#else
	register void *mem_r asm("ebx");
#endif /* CONFIG_X86_64 */
#endif /* CONFIG_KASAN */

	/*
	 * Make sure none of the allocated memory is cached. If it is we
	 * will get a cache hit in below loop from outside of pseudo-locked
	 * region.
	 * wbinvd (as opposed to clflush/clflushopt) is required to
	 * increase likelihood that allocated cache portion will be filled
	 * with associated memory.
	 */
	native_wbinvd();

	/*
	 * Always called with interrupts enabled. By disabling interrupts
	 * ensure that we will not be preempted during this critical section.
	 */
	local_irq_disable();

	/*
	 * Call wrmsr and rdmsr as directly as possible to avoid tracing
	 * clobbering local register variables or affecting cache accesses.
	 *
	 * Disable the hardware prefetcher so that when the end of the memory
	 * being pseudo-locked is reached the hardware will not read beyond
	 * the buffer and evict pseudo-locked memory read earlier from the
	 * cache.
	 */
	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
	closid_p = this_cpu_read(pqr_state.cur_closid);
	rmid_p = this_cpu_read(pqr_state.cur_rmid);
	mem_r = plr->kmem;
	size = plr->size;
	line_size = plr->line_size;
	/*
	 * Critical section begin: start by writing the closid associated
	 * with the capacity bitmask of the cache region being
	 * pseudo-locked followed by reading of kernel memory to load it
	 * into the cache.
	 */
	__wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
	/*
	 * Cache was flushed earlier. Now access kernel memory to read it
	 * into cache region associated with just activated plr->closid.
	 * Loop over data twice:
	 * - In first loop the cache region is shared with the page walker
	 *   as it populates the paging structure caches (including TLB).
	 * - In the second loop the paging structure caches are used and
	 *   cache region is populated with the memory being referenced.
	 */
	for (i = 0; i < size; i += PAGE_SIZE) {
		/*
		 * Add a barrier to prevent speculative execution of this
		 * loop reading beyond the end of the buffer.
		 */
		rmb();
		asm volatile("mov (%0,%1,1), %%eax\n\t"
			:
			: "r" (mem_r), "r" (i)
			: "%eax", "memory");
	}
	for (i = 0; i < size; i += line_size) {
		/*
		 * Add a barrier to prevent speculative execution of this
		 * loop reading beyond the end of the buffer.
		 */
		rmb();
		asm volatile("mov (%0,%1,1), %%eax\n\t"
			:
			: "r" (mem_r), "r" (i)
			: "%eax", "memory");
	}
	/*
	 * Critical section end: restore closid with capacity bitmask that
	 * does not overlap with pseudo-locked region.
	 */
	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);

	/* Re-enable the hardware prefetcher(s) */
	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
	local_irq_enable();

	plr->thread_done = 1;
	wake_up_interruptible(&plr->lock_thread_wq);
	return 0;
}

/**
 * rdtgroup_monitor_in_progress - Test if monitoring in progress
 * @r: resource group being queried
 *
 * Return: 1 if monitor groups have been created for this resource
 * group, 0 otherwise.
 */
static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
{
	return !list_empty(&rdtgrp->mon.crdtgrp_list);
}

/**
 * rdtgroup_locksetup_user_restrict - Restrict user access to group
 * @rdtgrp: resource group needing access restricted
 *
 * A resource group used for cache pseudo-locking cannot have cpus or tasks
 * assigned to it. This is communicated to the user by restricting access
 * to all the files that can be used to make such changes.
 *
 * Permissions restored with rdtgroup_locksetup_user_restore()
 *
 * Return: 0 on success, <0 on failure. If a failure occurs during the
 * restriction of access an attempt will be made to restore permissions but
 * the state of the mode of these files will be uncertain when a failure
 * occurs.
 */
static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
{
	int ret;

	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
	if (ret)
		return ret;

	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
	if (ret)
		goto err_tasks;

	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
	if (ret)
		goto err_cpus;

	if (rdt_mon_capable) {
		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
		if (ret)
			goto err_cpus_list;
	}

	ret = 0;
	goto out;

err_cpus_list:
	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
err_cpus:
	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
err_tasks:
	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
out:
	return ret;
}

/**
 * rdtgroup_locksetup_user_restore - Restore user access to group
 * @rdtgrp: resource group needing access restored
 *
 * Restore all file access previously removed using
 * rdtgroup_locksetup_user_restrict()
 *
 * Return: 0 on success, <0 on failure.  If a failure occurs during the
 * restoration of access an attempt will be made to restrict permissions
 * again but the state of the mode of these files will be uncertain when
 * a failure occurs.
 */
static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
{
	int ret;

	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
	if (ret)
		return ret;

	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
	if (ret)
		goto err_tasks;

	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
	if (ret)
		goto err_cpus;

	if (rdt_mon_capable) {
		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
		if (ret)
			goto err_cpus_list;
	}

	ret = 0;
	goto out;

err_cpus_list:
	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
err_cpus:
	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
err_tasks:
	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
out:
	return ret;
}

/**
 * rdtgroup_locksetup_enter - Resource group enters locksetup mode
 * @rdtgrp: resource group requested to enter locksetup mode
 *
 * A resource group enters locksetup mode to reflect that it would be used
 * to represent a pseudo-locked region and is in the process of being set
 * up to do so. A resource group used for a pseudo-locked region would
 * lose the closid associated with it so we cannot allow it to have any
 * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
 * future. Monitoring of a pseudo-locked region is not allowed either.
 *
 * The above and more restrictions on a pseudo-locked region are checked
 * for and enforced before the resource group enters the locksetup mode.
 *
 * Returns: 0 if the resource group successfully entered locksetup mode, <0
 * on failure. On failure the last_cmd_status buffer is updated with text to
 * communicate details of failure to the user.
 */
int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
{
	int ret;

	/*
	 * The default resource group can neither be removed nor lose the
	 * default closid associated with it.
	 */
	if (rdtgrp == &rdtgroup_default) {
		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
		return -EINVAL;
	}

	/*
	 * Cache Pseudo-locking not supported when CDP is enabled.
	 *
	 * Some things to consider if you would like to enable this
	 * support (using L3 CDP as example):
	 * - When CDP is enabled two separate resources are exposed,
	 *   L3DATA and L3CODE, but they are actually on the same cache.
	 *   The implication for pseudo-locking is that if a
	 *   pseudo-locked region is created on a domain of one
	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
	 *   be created on that same domain of the other resource
	 *   (eg. L3DATA). This is because the creation of a
	 *   pseudo-locked region involves a call to wbinvd that will
	 *   affect all cache allocations on particular domain.
	 * - Considering the previous, it may be possible to only
	 *   expose one of the CDP resources to pseudo-locking and
	 *   hide the other. For example, we could consider to only
	 *   expose L3DATA and since the L3 cache is unified it is
	 *   still possible to place instructions there are execute it.
	 * - If only one region is exposed to pseudo-locking we should
	 *   still keep in mind that availability of a portion of cache
	 *   for pseudo-locking should take into account both resources.
	 *   Similarly, if a pseudo-locked region is created in one
	 *   resource, the portion of cache used by it should be made
	 *   unavailable to all future allocations from both resources.
	 */
	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
	    rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
		rdt_last_cmd_puts("CDP enabled\n");
		return -EINVAL;
	}

	/*
	 * Not knowing the bits to disable prefetching implies that this
	 * platform does not support Cache Pseudo-Locking.
	 */
	prefetch_disable_bits = get_prefetch_disable_bits();
	if (prefetch_disable_bits == 0) {
		rdt_last_cmd_puts("pseudo-locking not supported\n");
		return -EINVAL;
	}

	if (rdtgroup_monitor_in_progress(rdtgrp)) {
		rdt_last_cmd_puts("monitoring in progress\n");
		return -EINVAL;
	}

	if (rdtgroup_tasks_assigned(rdtgrp)) {
		rdt_last_cmd_puts("tasks assigned to resource group\n");
		return -EINVAL;
	}

	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
		rdt_last_cmd_puts("CPUs assigned to resource group\n");
		return -EINVAL;
	}

	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
		return -EIO;
	}

	ret = pseudo_lock_init(rdtgrp);
	if (ret) {
		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
		goto out_release;
	}

	/*
	 * If this system is capable of monitoring a rmid would have been
	 * allocated when the control group was created. This is not needed
	 * anymore when this group would be used for pseudo-locking. This
	 * is safe to call on platforms not capable of monitoring.
	 */
	free_rmid(rdtgrp->mon.rmid);

	ret = 0;
	goto out;

out_release:
	rdtgroup_locksetup_user_restore(rdtgrp);
out:
	return ret;
}

/**
 * rdtgroup_locksetup_exit - resource group exist locksetup mode
 * @rdtgrp: resource group
 *
 * When a resource group exits locksetup mode the earlier restrictions are
 * lifted.
 *
 * Return: 0 on success, <0 on failure
 */
int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
{
	int ret;

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

	ret = rdtgroup_locksetup_user_restore(rdtgrp);
	if (ret) {
		free_rmid(rdtgrp->mon.rmid);
		return ret;
	}

	pseudo_lock_free(rdtgrp);
	return 0;
}

/**
 * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
 * @d: RDT domain
 * @cbm: CBM to test
 *
 * @d represents a cache instance and @cbm a capacity bitmask that is
 * considered for it. Determine if @cbm overlaps with any existing
 * pseudo-locked region on @d.
 *
 * @cbm is unsigned long, even if only 32 bits are used, to make the
 * bitmap functions work correctly.
 *
 * Return: true if @cbm overlaps with pseudo-locked region on @d, false
 * otherwise.
 */
bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
{
	unsigned int cbm_len;
	unsigned long cbm_b;

	if (d->plr) {
		cbm_len = d->plr->r->cache.cbm_len;
		cbm_b = d->plr->cbm;
		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
			return true;
	}
	return false;
}

/**
 * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
 * @d: RDT domain under test
 *
 * The setup of a pseudo-locked region affects all cache instances within
 * the hierarchy of the region. It is thus essential to know if any
 * pseudo-locked regions exist within a cache hierarchy to prevent any
 * attempts to create new pseudo-locked regions in the same hierarchy.
 *
 * Return: true if a pseudo-locked region exists in the hierarchy of @d or
 *         if it is not possible to test due to memory allocation issue,
 *         false otherwise.
 */
bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
{
	cpumask_var_t cpu_with_psl;
	struct rdt_resource *r;
	struct rdt_domain *d_i;
	bool ret = false;

	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
		return true;

	/*
	 * First determine which cpus have pseudo-locked regions
	 * associated with them.
	 */
	for_each_alloc_enabled_rdt_resource(r) {
		list_for_each_entry(d_i, &r->domains, list) {
			if (d_i->plr)
				cpumask_or(cpu_with_psl, cpu_with_psl,
					   &d_i->cpu_mask);
		}
	}

	/*
	 * Next test if new pseudo-locked region would intersect with
	 * existing region.
	 */
	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
		ret = true;

	free_cpumask_var(cpu_with_psl);
	return ret;
}

/**
 * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
 * @_plr: pseudo-lock region to measure
 *
 * There is no deterministic way to test if a memory region is cached. One
 * way is to measure how long it takes to read the memory, the speed of
 * access is a good way to learn how close to the cpu the data was. Even
 * more, if the prefetcher is disabled and the memory is read at a stride
 * of half the cache line, then a cache miss will be easy to spot since the
 * read of the first half would be significantly slower than the read of
 * the second half.
 *
 * Return: 0. Waiter on waitqueue will be woken on completion.
 */
static int measure_cycles_lat_fn(void *_plr)
{
	struct pseudo_lock_region *plr = _plr;
	unsigned long i;
	u64 start, end;
#ifdef CONFIG_KASAN
	/*
	 * The registers used for local register variables are also used
	 * when KASAN is active. When KASAN is active we use a regular
	 * variable to ensure we always use a valid pointer to access memory.
	 * The cost is that accessing this pointer, which could be in
	 * cache, will be included in the measurement of memory read latency.
	 */
	void *mem_r;
#else
#ifdef CONFIG_X86_64
	register void *mem_r asm("rbx");
#else
	register void *mem_r asm("ebx");
#endif /* CONFIG_X86_64 */
#endif /* CONFIG_KASAN */

	local_irq_disable();
	/*
	 * The wrmsr call may be reordered with the assignment below it.
	 * Call wrmsr as directly as possible to avoid tracing clobbering
	 * local register variable used for memory pointer.
	 */
	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
	mem_r = plr->kmem;
	/*
	 * Dummy execute of the time measurement to load the needed
	 * instructions into the L1 instruction cache.
	 */
	start = rdtsc_ordered();
	for (i = 0; i < plr->size; i += 32) {
		start = rdtsc_ordered();
		asm volatile("mov (%0,%1,1), %%eax\n\t"
			     :
			     : "r" (mem_r), "r" (i)
			     : "%eax", "memory");
		end = rdtsc_ordered();
		trace_pseudo_lock_mem_latency((u32)(end - start));
	}
	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
	local_irq_enable();
	plr->thread_done = 1;
	wake_up_interruptible(&plr->lock_thread_wq);
	return 0;
}

static int measure_cycles_perf_fn(void *_plr)
{
	unsigned long long l3_hits = 0, l3_miss = 0;
	u64 l3_hit_bits = 0, l3_miss_bits = 0;
	struct pseudo_lock_region *plr = _plr;
	unsigned long long l2_hits, l2_miss;
	u64 l2_hit_bits, l2_miss_bits;
	unsigned long i;
#ifdef CONFIG_KASAN
	/*
	 * The registers used for local register variables are also used
	 * when KASAN is active. When KASAN is active we use regular variables
	 * at the cost of including cache access latency to these variables
	 * in the measurements.
	 */
	unsigned int line_size;
	unsigned int size;
	void *mem_r;
#else
	register unsigned int line_size asm("esi");
	register unsigned int size asm("edi");
#ifdef CONFIG_X86_64
	register void *mem_r asm("rbx");
#else
	register void *mem_r asm("ebx");
#endif /* CONFIG_X86_64 */
#endif /* CONFIG_KASAN */

	/*
	 * Non-architectural event for the Goldmont Microarchitecture
	 * from Intel x86 Architecture Software Developer Manual (SDM):
	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
	 * Umask values:
	 *     L1_HIT   01H
	 *     L2_HIT   02H
	 *     L1_MISS  08H
	 *     L2_MISS  10H
	 *
	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
	 * this platform we use the following events instead:
	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
	 *       REFERENCES FFH
	 *       MISS       3FH
	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
	 *       REFERENCE 4FH
	 *       MISS      41H
	 */

	/*
	 * Start by setting flags for IA32_PERFEVTSELx:
	 *     OS  (Operating system mode)  0x2
	 *     INT (APIC interrupt enable)  0x10
	 *     EN  (Enable counter)         0x40
	 *
	 * Then add the Umask value and event number to select performance
	 * event.
	 */

	switch (boot_cpu_data.x86_model) {
	case INTEL_FAM6_ATOM_GOLDMONT:
	case INTEL_FAM6_ATOM_GEMINI_LAKE:
		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
		break;
	case INTEL_FAM6_BROADWELL_X:
		/* On BDW the l2_hit_bits count references, not hits */
		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
		/* On BDW the l3_hit_bits count references, not hits */
		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
		break;
	default:
		goto out;
	}

	local_irq_disable();
	/*
	 * Call wrmsr direcly to avoid the local register variables from
	 * being overwritten due to reordering of their assignment with
	 * the wrmsr calls.
	 */
	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
	/* Disable events and reset counters */
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
	if (l3_hit_bits > 0) {
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
	}
	/* Set and enable the L2 counters */
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
	if (l3_hit_bits > 0) {
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
				      l3_hit_bits);
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
				      l3_miss_bits);
	}
	mem_r = plr->kmem;
	size = plr->size;
	line_size = plr->line_size;
	for (i = 0; i < size; i += line_size) {
		asm volatile("mov (%0,%1,1), %%eax\n\t"
			     :
			     : "r" (mem_r), "r" (i)
			     : "%eax", "memory");
	}
	/*
	 * Call wrmsr directly (no tracing) to not influence
	 * the cache access counters as they are disabled.
	 */
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
			      l2_hit_bits & ~(0x40ULL << 16));
	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
			      l2_miss_bits & ~(0x40ULL << 16));
	if (l3_hit_bits > 0) {
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
				      l3_hit_bits & ~(0x40ULL << 16));
		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
				      l3_miss_bits & ~(0x40ULL << 16));
	}
	l2_hits = native_read_pmc(0);
	l2_miss = native_read_pmc(1);
	if (l3_hit_bits > 0) {
		l3_hits = native_read_pmc(2);
		l3_miss = native_read_pmc(3);
	}
	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
	local_irq_enable();
	/*
	 * On BDW we count references and misses, need to adjust. Sometimes
	 * the "hits" counter is a bit more than the references, for
	 * example, x references but x + 1 hits. To not report invalid
	 * hit values in this case we treat that as misses eaqual to
	 * references.
	 */
	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
	trace_pseudo_lock_l2(l2_hits, l2_miss);
	if (l3_hit_bits > 0) {
		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
		trace_pseudo_lock_l3(l3_hits, l3_miss);
	}

out:
	plr->thread_done = 1;
	wake_up_interruptible(&plr->lock_thread_wq);
	return 0;
}

/**
 * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
 *
 * The measurement of latency to access a pseudo-locked region should be
 * done from a cpu that is associated with that pseudo-locked region.
 * Determine which cpu is associated with this region and start a thread on
 * that cpu to perform the measurement, wait for that thread to complete.
 *
 * Return: 0 on success, <0 on failure
 */
static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
{
	struct pseudo_lock_region *plr = rdtgrp->plr;
	struct task_struct *thread;
	unsigned int cpu;
	int ret = -1;

	cpus_read_lock();
	mutex_lock(&rdtgroup_mutex);

	if (rdtgrp->flags & RDT_DELETED) {
		ret = -ENODEV;
		goto out;
	}

	plr->thread_done = 0;
	cpu = cpumask_first(&plr->d->cpu_mask);
	if (!cpu_online(cpu)) {
		ret = -ENODEV;
		goto out;
	}

	if (sel == 1)
		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
						cpu_to_node(cpu),
						"pseudo_lock_measure/%u",
						cpu);
	else if (sel == 2)
		thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
						cpu_to_node(cpu),
						"pseudo_lock_measure/%u",
						cpu);
	else
		goto out;

	if (IS_ERR(thread)) {
		ret = PTR_ERR(thread);
		goto out;
	}
	kthread_bind(thread, cpu);
	wake_up_process(thread);

	ret = wait_event_interruptible(plr->lock_thread_wq,
				       plr->thread_done == 1);
	if (ret < 0)
		goto out;

	ret = 0;

out:
	mutex_unlock(&rdtgroup_mutex);
	cpus_read_unlock();
	return ret;
}

static ssize_t pseudo_lock_measure_trigger(struct file *file,
					   const char __user *user_buf,
					   size_t count, loff_t *ppos)
{
	struct rdtgroup *rdtgrp = file->private_data;
	size_t buf_size;
	char buf[32];
	int ret;
	int sel;

	buf_size = min(count, (sizeof(buf) - 1));
	if (copy_from_user(buf, user_buf, buf_size))
		return -EFAULT;

	buf[buf_size] = '\0';
	ret = kstrtoint(buf, 10, &sel);
	if (ret == 0) {
		if (sel != 1)
			return -EINVAL;
		ret = debugfs_file_get(file->f_path.dentry);
		if (ret)
			return ret;
		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
		if (ret == 0)
			ret = count;
		debugfs_file_put(file->f_path.dentry);
	}

	return ret;
}

static const struct file_operations pseudo_measure_fops = {
	.write = pseudo_lock_measure_trigger,
	.open = simple_open,
	.llseek = default_llseek,
};

/**
 * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
 * @rdtgrp: resource group to which pseudo-lock region belongs
 *
 * Called when a resource group in the pseudo-locksetup mode receives a
 * valid schemata that should be pseudo-locked. Since the resource group is
 * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
 * allocated and initialized with the essential information. If a failure
 * occurs the resource group remains in the pseudo-locksetup mode with the
 * &struct pseudo_lock_region associated with it, but cleared from all
 * information and ready for the user to re-attempt pseudo-locking by
 * writing the schemata again.
 *
 * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
 * on failure. Descriptive error will be written to last_cmd_status buffer.
 */
int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
{
	struct pseudo_lock_region *plr = rdtgrp->plr;
	struct task_struct *thread;
	unsigned int new_minor;
	struct device *dev;
	int ret;

	ret = pseudo_lock_region_alloc(plr);
	if (ret < 0)
		return ret;

	ret = pseudo_lock_cstates_constrain(plr);
	if (ret < 0) {
		ret = -EINVAL;
		goto out_region;
	}

	plr->thread_done = 0;

	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
					cpu_to_node(plr->cpu),
					"pseudo_lock/%u", plr->cpu);
	if (IS_ERR(thread)) {
		ret = PTR_ERR(thread);
		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
		goto out_cstates;
	}

	kthread_bind(thread, plr->cpu);
	wake_up_process(thread);

	ret = wait_event_interruptible(plr->lock_thread_wq,
				       plr->thread_done == 1);
	if (ret < 0) {
		/*
		 * If the thread does not get on the CPU for whatever
		 * reason and the process which sets up the region is
		 * interrupted then this will leave the thread in runnable
		 * state and once it gets on the CPU it will derefence
		 * the cleared, but not freed, plr struct resulting in an
		 * empty pseudo-locking loop.
		 */
		rdt_last_cmd_puts("locking thread interrupted\n");
		goto out_cstates;
	}

	ret = pseudo_lock_minor_get(&new_minor);
	if (ret < 0) {
		rdt_last_cmd_puts("unable to obtain a new minor number\n");
		goto out_cstates;
	}

	/*
	 * Unlock access but do not release the reference. The
	 * pseudo-locked region will still be here on return.
	 *
	 * The mutex has to be released temporarily to avoid a potential
	 * deadlock with the mm->mmap_sem semaphore which is obtained in
	 * the device_create() and debugfs_create_dir() callpath below
	 * as well as before the mmap() callback is called.
	 */
	mutex_unlock(&rdtgroup_mutex);

	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
						      debugfs_resctrl);
		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
			debugfs_create_file("pseudo_lock_measure", 0200,
					    plr->debugfs_dir, rdtgrp,
					    &pseudo_measure_fops);
	}

	dev = device_create(pseudo_lock_class, NULL,
			    MKDEV(pseudo_lock_major, new_minor),
			    rdtgrp, "%s", rdtgrp->kn->name);

	mutex_lock(&rdtgroup_mutex);

	if (IS_ERR(dev)) {
		ret = PTR_ERR(dev);
		rdt_last_cmd_printf("failed to create character device: %d\n",
				    ret);
		goto out_debugfs;
	}

	/* We released the mutex - check if group was removed while we did so */
	if (rdtgrp->flags & RDT_DELETED) {
		ret = -ENODEV;
		goto out_device;
	}

	plr->minor = new_minor;

	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
	closid_free(rdtgrp->closid);
	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);

	ret = 0;
	goto out;

out_device:
	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
out_debugfs:
	debugfs_remove_recursive(plr->debugfs_dir);
	pseudo_lock_minor_release(new_minor);
out_cstates:
	pseudo_lock_cstates_relax(plr);
out_region:
	pseudo_lock_region_clear(plr);
out:
	return ret;
}

/**
 * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
 * @rdtgrp: resource group to which the pseudo-locked region belongs
 *
 * The removal of a pseudo-locked region can be initiated when the resource
 * group is removed from user space via a "rmdir" from userspace or the
 * unmount of the resctrl filesystem. On removal the resource group does
 * not go back to pseudo-locksetup mode before it is removed, instead it is
 * removed directly. There is thus assymmetry with the creation where the
 * &struct pseudo_lock_region is removed here while it was not created in
 * rdtgroup_pseudo_lock_create().
 *
 * Return: void
 */
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
{
	struct pseudo_lock_region *plr = rdtgrp->plr;

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
		/*
		 * Default group cannot be a pseudo-locked region so we can
		 * free closid here.
		 */
		closid_free(rdtgrp->closid);
		goto free;
	}

	pseudo_lock_cstates_relax(plr);
	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
	pseudo_lock_minor_release(plr->minor);

free:
	pseudo_lock_free(rdtgrp);
}

static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
{
	struct rdtgroup *rdtgrp;

	mutex_lock(&rdtgroup_mutex);

	rdtgrp = region_find_by_minor(iminor(inode));
	if (!rdtgrp) {
		mutex_unlock(&rdtgroup_mutex);
		return -ENODEV;
	}

	filp->private_data = rdtgrp;
	atomic_inc(&rdtgrp->waitcount);
	/* Perform a non-seekable open - llseek is not supported */
	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);

	mutex_unlock(&rdtgroup_mutex);

	return 0;
}

static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
{
	struct rdtgroup *rdtgrp;

	mutex_lock(&rdtgroup_mutex);
	rdtgrp = filp->private_data;
	WARN_ON(!rdtgrp);
	if (!rdtgrp) {
		mutex_unlock(&rdtgroup_mutex);
		return -ENODEV;
	}
	filp->private_data = NULL;
	atomic_dec(&rdtgrp->waitcount);
	mutex_unlock(&rdtgroup_mutex);
	return 0;
}

static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
{
	/* Not supported */
	return -EINVAL;
}

static const struct vm_operations_struct pseudo_mmap_ops = {
	.mremap = pseudo_lock_dev_mremap,
};

static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
{
	unsigned long vsize = vma->vm_end - vma->vm_start;
	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
	struct pseudo_lock_region *plr;
	struct rdtgroup *rdtgrp;
	unsigned long physical;
	unsigned long psize;

	mutex_lock(&rdtgroup_mutex);

	rdtgrp = filp->private_data;
	WARN_ON(!rdtgrp);
	if (!rdtgrp) {
		mutex_unlock(&rdtgroup_mutex);
		return -ENODEV;
	}

	plr = rdtgrp->plr;

	/*
	 * Task is required to run with affinity to the cpus associated
	 * with the pseudo-locked region. If this is not the case the task
	 * may be scheduled elsewhere and invalidate entries in the
	 * pseudo-locked region.
	 */
	if (!cpumask_subset(&current->cpus_allowed, &plr->d->cpu_mask)) {
		mutex_unlock(&rdtgroup_mutex);
		return -EINVAL;
	}

	physical = __pa(plr->kmem) >> PAGE_SHIFT;
	psize = plr->size - off;

	if (off > plr->size) {
		mutex_unlock(&rdtgroup_mutex);
		return -ENOSPC;
	}

	/*
	 * Ensure changes are carried directly to the memory being mapped,
	 * do not allow copy-on-write mapping.
	 */
	if (!(vma->vm_flags & VM_SHARED)) {
		mutex_unlock(&rdtgroup_mutex);
		return -EINVAL;
	}

	if (vsize > psize) {
		mutex_unlock(&rdtgroup_mutex);
		return -ENOSPC;
	}

	memset(plr->kmem + off, 0, vsize);

	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
			    vsize, vma->vm_page_prot)) {
		mutex_unlock(&rdtgroup_mutex);
		return -EAGAIN;
	}
	vma->vm_ops = &pseudo_mmap_ops;
	mutex_unlock(&rdtgroup_mutex);
	return 0;
}

static const struct file_operations pseudo_lock_dev_fops = {
	.owner =	THIS_MODULE,
	.llseek =	no_llseek,
	.read =		NULL,
	.write =	NULL,
	.open =		pseudo_lock_dev_open,
	.release =	pseudo_lock_dev_release,
	.mmap =		pseudo_lock_dev_mmap,
};

static char *pseudo_lock_devnode(struct device *dev, umode_t *mode)
{
	struct rdtgroup *rdtgrp;

	rdtgrp = dev_get_drvdata(dev);
	if (mode)
		*mode = 0600;
	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
}

int rdt_pseudo_lock_init(void)
{
	int ret;

	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
	if (ret < 0)
		return ret;

	pseudo_lock_major = ret;

	pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock");
	if (IS_ERR(pseudo_lock_class)) {
		ret = PTR_ERR(pseudo_lock_class);
		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
		return ret;
	}

	pseudo_lock_class->devnode = pseudo_lock_devnode;
	return 0;
}

void rdt_pseudo_lock_release(void)
{
	class_destroy(pseudo_lock_class);
	pseudo_lock_class = NULL;
	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
	pseudo_lock_major = 0;
}