aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu/intel_rdt.c
blob: b99a04da70f618d1668d66390a9bb749e364c798 (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
/*
 * Resource Director Technology(RDT)
 * - Cache Allocation code.
 *
 * Copyright (C) 2016 Intel Corporation
 *
 * Authors:
 *    Fenghua Yu <fenghua.yu@intel.com>
 *    Tony Luck <tony.luck@intel.com>
 *    Vikas Shivappa <vikas.shivappa@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 June 2016, volume 3, section 17.17.
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/slab.h>
#include <linux/err.h>
#include <linux/cacheinfo.h>
#include <linux/cpuhotplug.h>

#include <asm/intel-family.h>
#include <asm/intel_rdt_sched.h>
#include "intel_rdt.h"

#define MBA_IS_LINEAR	0x4
#define MBA_MAX_MBPS	U32_MAX

/* Mutex to protect rdtgroup access. */
DEFINE_MUTEX(rdtgroup_mutex);

/*
 * The cached intel_pqr_state is strictly per CPU and can never be
 * updated from a remote CPU. Functions which modify the state
 * are called with interrupts disabled and no preemption, which
 * is sufficient for the protection.
 */
DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);

/*
 * Used to store the max resource name width and max resource data width
 * to display the schemata in a tabular format
 */
int max_name_width, max_data_width;

/*
 * Global boolean for rdt_alloc which is true if any
 * resource allocation is enabled.
 */
bool rdt_alloc_capable;

static void
mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
static void
cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);

#define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].domains)

struct rdt_resource rdt_resources_all[] = {
	[RDT_RESOURCE_L3] =
	{
		.rid			= RDT_RESOURCE_L3,
		.name			= "L3",
		.domains		= domain_init(RDT_RESOURCE_L3),
		.msr_base		= IA32_L3_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 3,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 1,
			.cbm_idx_offset	= 0,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_L3DATA] =
	{
		.rid			= RDT_RESOURCE_L3DATA,
		.name			= "L3DATA",
		.domains		= domain_init(RDT_RESOURCE_L3DATA),
		.msr_base		= IA32_L3_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 3,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 2,
			.cbm_idx_offset	= 0,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_L3CODE] =
	{
		.rid			= RDT_RESOURCE_L3CODE,
		.name			= "L3CODE",
		.domains		= domain_init(RDT_RESOURCE_L3CODE),
		.msr_base		= IA32_L3_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 3,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 2,
			.cbm_idx_offset	= 1,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_L2] =
	{
		.rid			= RDT_RESOURCE_L2,
		.name			= "L2",
		.domains		= domain_init(RDT_RESOURCE_L2),
		.msr_base		= IA32_L2_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 2,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 1,
			.cbm_idx_offset	= 0,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_L2DATA] =
	{
		.rid			= RDT_RESOURCE_L2DATA,
		.name			= "L2DATA",
		.domains		= domain_init(RDT_RESOURCE_L2DATA),
		.msr_base		= IA32_L2_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 2,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 2,
			.cbm_idx_offset	= 0,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_L2CODE] =
	{
		.rid			= RDT_RESOURCE_L2CODE,
		.name			= "L2CODE",
		.domains		= domain_init(RDT_RESOURCE_L2CODE),
		.msr_base		= IA32_L2_CBM_BASE,
		.msr_update		= cat_wrmsr,
		.cache_level		= 2,
		.cache = {
			.min_cbm_bits	= 1,
			.cbm_idx_mult	= 2,
			.cbm_idx_offset	= 1,
		},
		.parse_ctrlval		= parse_cbm,
		.format_str		= "%d=%0*x",
		.fflags			= RFTYPE_RES_CACHE,
	},
	[RDT_RESOURCE_MBA] =
	{
		.rid			= RDT_RESOURCE_MBA,
		.name			= "MB",
		.domains		= domain_init(RDT_RESOURCE_MBA),
		.msr_base		= IA32_MBA_THRTL_BASE,
		.msr_update		= mba_wrmsr,
		.cache_level		= 3,
		.parse_ctrlval		= parse_bw,
		.format_str		= "%d=%*u",
		.fflags			= RFTYPE_RES_MB,
	},
};

static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid)
{
	return closid * r->cache.cbm_idx_mult + r->cache.cbm_idx_offset;
}

/*
 * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
 * as they do not have CPUID enumeration support for Cache allocation.
 * The check for Vendor/Family/Model is not enough to guarantee that
 * the MSRs won't #GP fault because only the following SKUs support
 * CAT:
 *	Intel(R) Xeon(R)  CPU E5-2658  v3  @  2.20GHz
 *	Intel(R) Xeon(R)  CPU E5-2648L v3  @  1.80GHz
 *	Intel(R) Xeon(R)  CPU E5-2628L v3  @  2.00GHz
 *	Intel(R) Xeon(R)  CPU E5-2618L v3  @  2.30GHz
 *	Intel(R) Xeon(R)  CPU E5-2608L v3  @  2.00GHz
 *	Intel(R) Xeon(R)  CPU E5-2658A v3  @  2.20GHz
 *
 * Probe by trying to write the first of the L3 cach mask registers
 * and checking that the bits stick. Max CLOSids is always 4 and max cbm length
 * is always 20 on hsw server parts. The minimum cache bitmask length
 * allowed for HSW server is always 2 bits. Hardcode all of them.
 */
static inline void cache_alloc_hsw_probe(void)
{
	struct rdt_resource *r  = &rdt_resources_all[RDT_RESOURCE_L3];
	u32 l, h, max_cbm = BIT_MASK(20) - 1;

	if (wrmsr_safe(IA32_L3_CBM_BASE, max_cbm, 0))
		return;
	rdmsr(IA32_L3_CBM_BASE, l, h);

	/* If all the bits were set in MSR, return success */
	if (l != max_cbm)
		return;

	r->num_closid = 4;
	r->default_ctrl = max_cbm;
	r->cache.cbm_len = 20;
	r->cache.shareable_bits = 0xc0000;
	r->cache.min_cbm_bits = 2;
	r->alloc_capable = true;
	r->alloc_enabled = true;

	rdt_alloc_capable = true;
}

bool is_mba_sc(struct rdt_resource *r)
{
	if (!r)
		return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc;

	return r->membw.mba_sc;
}

/*
 * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
 * exposed to user interface and the h/w understandable delay values.
 *
 * The non-linear delay values have the granularity of power of two
 * and also the h/w does not guarantee a curve for configured delay
 * values vs. actual b/w enforced.
 * Hence we need a mapping that is pre calibrated so the user can
 * express the memory b/w as a percentage value.
 */
static inline bool rdt_get_mb_table(struct rdt_resource *r)
{
	/*
	 * There are no Intel SKUs as of now to support non-linear delay.
	 */
	pr_info("MBA b/w map not implemented for cpu:%d, model:%d",
		boot_cpu_data.x86, boot_cpu_data.x86_model);

	return false;
}

static bool rdt_get_mem_config(struct rdt_resource *r)
{
	union cpuid_0x10_3_eax eax;
	union cpuid_0x10_x_edx edx;
	u32 ebx, ecx;

	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
	r->num_closid = edx.split.cos_max + 1;
	r->membw.max_delay = eax.split.max_delay + 1;
	r->default_ctrl = MAX_MBA_BW;
	if (ecx & MBA_IS_LINEAR) {
		r->membw.delay_linear = true;
		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
	} else {
		if (!rdt_get_mb_table(r))
			return false;
	}
	r->data_width = 3;

	r->alloc_capable = true;
	r->alloc_enabled = true;

	return true;
}

static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
{
	union cpuid_0x10_1_eax eax;
	union cpuid_0x10_x_edx edx;
	u32 ebx, ecx;

	cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
	r->num_closid = edx.split.cos_max + 1;
	r->cache.cbm_len = eax.split.cbm_len + 1;
	r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
	r->cache.shareable_bits = ebx & r->default_ctrl;
	r->data_width = (r->cache.cbm_len + 3) / 4;
	r->alloc_capable = true;
	r->alloc_enabled = true;
}

static void rdt_get_cdp_config(int level, int type)
{
	struct rdt_resource *r_l = &rdt_resources_all[level];
	struct rdt_resource *r = &rdt_resources_all[type];

	r->num_closid = r_l->num_closid / 2;
	r->cache.cbm_len = r_l->cache.cbm_len;
	r->default_ctrl = r_l->default_ctrl;
	r->cache.shareable_bits = r_l->cache.shareable_bits;
	r->data_width = (r->cache.cbm_len + 3) / 4;
	r->alloc_capable = true;
	/*
	 * By default, CDP is disabled. CDP can be enabled by mount parameter
	 * "cdp" during resctrl file system mount time.
	 */
	r->alloc_enabled = false;
}

static void rdt_get_cdp_l3_config(void)
{
	rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3DATA);
	rdt_get_cdp_config(RDT_RESOURCE_L3, RDT_RESOURCE_L3CODE);
}

static void rdt_get_cdp_l2_config(void)
{
	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2DATA);
	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
}

static int get_cache_id(int cpu, int level)
{
	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
	int i;

	for (i = 0; i < ci->num_leaves; i++) {
		if (ci->info_list[i].level == level)
			return ci->info_list[i].id;
	}

	return -1;
}

/*
 * Map the memory b/w percentage value to delay values
 * that can be written to QOS_MSRs.
 * There are currently no SKUs which support non linear delay values.
 */
u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
{
	if (r->membw.delay_linear)
		return MAX_MBA_BW - bw;

	pr_warn_once("Non Linear delay-bw map not supported but queried\n");
	return r->default_ctrl;
}

static void
mba_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
{
	unsigned int i;

	/*  Write the delay values for mba. */
	for (i = m->low; i < m->high; i++)
		wrmsrl(r->msr_base + i, delay_bw_map(d->ctrl_val[i], r));
}

static void
cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
{
	unsigned int i;

	for (i = m->low; i < m->high; i++)
		wrmsrl(r->msr_base + cbm_idx(r, i), d->ctrl_val[i]);
}

struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r)
{
	struct rdt_domain *d;

	list_for_each_entry(d, &r->domains, list) {
		/* Find the domain that contains this CPU */
		if (cpumask_test_cpu(cpu, &d->cpu_mask))
			return d;
	}

	return NULL;
}

void rdt_ctrl_update(void *arg)
{
	struct msr_param *m = arg;
	struct rdt_resource *r = m->res;
	int cpu = smp_processor_id();
	struct rdt_domain *d;

	d = get_domain_from_cpu(cpu, r);
	if (d) {
		r->msr_update(d, m, r);
		return;
	}
	pr_warn_once("cpu %d not found in any domain for resource %s\n",
		     cpu, r->name);
}

/*
 * rdt_find_domain - Find a domain in a resource that matches input resource id
 *
 * Search resource r's domain list to find the resource id. If the resource
 * id is found in a domain, return the domain. Otherwise, if requested by
 * caller, return the first domain whose id is bigger than the input id.
 * The domain list is sorted by id in ascending order.
 */
struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
				   struct list_head **pos)
{
	struct rdt_domain *d;
	struct list_head *l;

	if (id < 0)
		return ERR_PTR(-ENODEV);

	list_for_each(l, &r->domains) {
		d = list_entry(l, struct rdt_domain, list);
		/* When id is found, return its domain. */
		if (id == d->id)
			return d;
		/* Stop searching when finding id's position in sorted list. */
		if (id < d->id)
			break;
	}

	if (pos)
		*pos = l;

	return NULL;
}

void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
{
	int i;

	/*
	 * Initialize the Control MSRs to having no control.
	 * For Cache Allocation: Set all bits in cbm
	 * For Memory Allocation: Set b/w requested to 100%
	 * and the bandwidth in MBps to U32_MAX
	 */
	for (i = 0; i < r->num_closid; i++, dc++, dm++) {
		*dc = r->default_ctrl;
		*dm = MBA_MAX_MBPS;
	}
}

static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
{
	struct msr_param m;
	u32 *dc, *dm;

	dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL);
	if (!dc)
		return -ENOMEM;

	dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL);
	if (!dm) {
		kfree(dc);
		return -ENOMEM;
	}

	d->ctrl_val = dc;
	d->mbps_val = dm;
	setup_default_ctrlval(r, dc, dm);

	m.low = 0;
	m.high = r->num_closid;
	r->msr_update(d, &m, r);
	return 0;
}

static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
{
	size_t tsize;

	if (is_llc_occupancy_enabled()) {
		d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid),
					   sizeof(unsigned long),
					   GFP_KERNEL);
		if (!d->rmid_busy_llc)
			return -ENOMEM;
		INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
	}
	if (is_mbm_total_enabled()) {
		tsize = sizeof(*d->mbm_total);
		d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
		if (!d->mbm_total) {
			kfree(d->rmid_busy_llc);
			return -ENOMEM;
		}
	}
	if (is_mbm_local_enabled()) {
		tsize = sizeof(*d->mbm_local);
		d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
		if (!d->mbm_local) {
			kfree(d->rmid_busy_llc);
			kfree(d->mbm_total);
			return -ENOMEM;
		}
	}

	if (is_mbm_enabled()) {
		INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
		mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
	}

	return 0;
}

/*
 * domain_add_cpu - Add a cpu to a resource's domain list.
 *
 * If an existing domain in the resource r's domain list matches the cpu's
 * resource id, add the cpu in the domain.
 *
 * Otherwise, a new domain is allocated and inserted into the right position
 * in the domain list sorted by id in ascending order.
 *
 * The order in the domain list is visible to users when we print entries
 * in the schemata file and schemata input is validated to have the same order
 * as this list.
 */
static void domain_add_cpu(int cpu, struct rdt_resource *r)
{
	int id = get_cache_id(cpu, r->cache_level);
	struct list_head *add_pos = NULL;
	struct rdt_domain *d;

	d = rdt_find_domain(r, id, &add_pos);
	if (IS_ERR(d)) {
		pr_warn("Could't find cache id for cpu %d\n", cpu);
		return;
	}

	if (d) {
		cpumask_set_cpu(cpu, &d->cpu_mask);
		return;
	}

	d = kzalloc_node(sizeof(*d), GFP_KERNEL, cpu_to_node(cpu));
	if (!d)
		return;

	d->id = id;
	cpumask_set_cpu(cpu, &d->cpu_mask);

	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
		kfree(d);
		return;
	}

	if (r->mon_capable && domain_setup_mon_state(r, d)) {
		kfree(d);
		return;
	}

	list_add_tail(&d->list, add_pos);

	/*
	 * If resctrl is mounted, add
	 * per domain monitor data directories.
	 */
	if (static_branch_unlikely(&rdt_mon_enable_key))
		mkdir_mondata_subdir_allrdtgrp(r, d);
}

static void domain_remove_cpu(int cpu, struct rdt_resource *r)
{
	int id = get_cache_id(cpu, r->cache_level);
	struct rdt_domain *d;

	d = rdt_find_domain(r, id, NULL);
	if (IS_ERR_OR_NULL(d)) {
		pr_warn("Could't find cache id for cpu %d\n", cpu);
		return;
	}

	cpumask_clear_cpu(cpu, &d->cpu_mask);
	if (cpumask_empty(&d->cpu_mask)) {
		/*
		 * If resctrl is mounted, remove all the
		 * per domain monitor data directories.
		 */
		if (static_branch_unlikely(&rdt_mon_enable_key))
			rmdir_mondata_subdir_allrdtgrp(r, d->id);
		list_del(&d->list);
		if (is_mbm_enabled())
			cancel_delayed_work(&d->mbm_over);
		if (is_llc_occupancy_enabled() &&  has_busy_rmid(r, d)) {
			/*
			 * When a package is going down, forcefully
			 * decrement rmid->ebusy. There is no way to know
			 * that the L3 was flushed and hence may lead to
			 * incorrect counts in rare scenarios, but leaving
			 * the RMID as busy creates RMID leaks if the
			 * package never comes back.
			 */
			__check_limbo(d, true);
			cancel_delayed_work(&d->cqm_limbo);
		}

		/*
		 * rdt_domain "d" is going to be freed below, so clear
		 * its pointer from pseudo_lock_region struct.
		 */
		if (d->plr)
			d->plr->d = NULL;

		kfree(d->ctrl_val);
		kfree(d->mbps_val);
		kfree(d->rmid_busy_llc);
		kfree(d->mbm_total);
		kfree(d->mbm_local);
		kfree(d);
		return;
	}

	if (r == &rdt_resources_all[RDT_RESOURCE_L3]) {
		if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
			cancel_delayed_work(&d->mbm_over);
			mbm_setup_overflow_handler(d, 0);
		}
		if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
		    has_busy_rmid(r, d)) {
			cancel_delayed_work(&d->cqm_limbo);
			cqm_setup_limbo_handler(d, 0);
		}
	}
}

static void clear_closid_rmid(int cpu)
{
	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);

	state->default_closid = 0;
	state->default_rmid = 0;
	state->cur_closid = 0;
	state->cur_rmid = 0;
	wrmsr(IA32_PQR_ASSOC, 0, 0);
}

static int intel_rdt_online_cpu(unsigned int cpu)
{
	struct rdt_resource *r;

	mutex_lock(&rdtgroup_mutex);
	for_each_capable_rdt_resource(r)
		domain_add_cpu(cpu, r);
	/* The cpu is set in default rdtgroup after online. */
	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
	clear_closid_rmid(cpu);
	mutex_unlock(&rdtgroup_mutex);

	return 0;
}

static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
{
	struct rdtgroup *cr;

	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) {
			break;
		}
	}
}

static int intel_rdt_offline_cpu(unsigned int cpu)
{
	struct rdtgroup *rdtgrp;
	struct rdt_resource *r;

	mutex_lock(&rdtgroup_mutex);
	for_each_capable_rdt_resource(r)
		domain_remove_cpu(cpu, r);
	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
			clear_childcpus(rdtgrp, cpu);
			break;
		}
	}
	clear_closid_rmid(cpu);
	mutex_unlock(&rdtgroup_mutex);

	return 0;
}

/*
 * Choose a width for the resource name and resource data based on the
 * resource that has widest name and cbm.
 */
static __init void rdt_init_padding(void)
{
	struct rdt_resource *r;
	int cl;

	for_each_alloc_capable_rdt_resource(r) {
		cl = strlen(r->name);
		if (cl > max_name_width)
			max_name_width = cl;

		if (r->data_width > max_data_width)
			max_data_width = r->data_width;
	}
}

enum {
	RDT_FLAG_CMT,
	RDT_FLAG_MBM_TOTAL,
	RDT_FLAG_MBM_LOCAL,
	RDT_FLAG_L3_CAT,
	RDT_FLAG_L3_CDP,
	RDT_FLAG_L2_CAT,
	RDT_FLAG_L2_CDP,
	RDT_FLAG_MBA,
};

#define RDT_OPT(idx, n, f)	\
[idx] = {			\
	.name = n,		\
	.flag = f		\
}

struct rdt_options {
	char	*name;
	int	flag;
	bool	force_off, force_on;
};

static struct rdt_options rdt_options[]  __initdata = {
	RDT_OPT(RDT_FLAG_CMT,	    "cmt",	X86_FEATURE_CQM_OCCUP_LLC),
	RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL),
	RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL),
	RDT_OPT(RDT_FLAG_L3_CAT,    "l3cat",	X86_FEATURE_CAT_L3),
	RDT_OPT(RDT_FLAG_L3_CDP,    "l3cdp",	X86_FEATURE_CDP_L3),
	RDT_OPT(RDT_FLAG_L2_CAT,    "l2cat",	X86_FEATURE_CAT_L2),
	RDT_OPT(RDT_FLAG_L2_CDP,    "l2cdp",	X86_FEATURE_CDP_L2),
	RDT_OPT(RDT_FLAG_MBA,	    "mba",	X86_FEATURE_MBA),
};
#define NUM_RDT_OPTIONS ARRAY_SIZE(rdt_options)

static int __init set_rdt_options(char *str)
{
	struct rdt_options *o;
	bool force_off;
	char *tok;

	if (*str == '=')
		str++;
	while ((tok = strsep(&str, ",")) != NULL) {
		force_off = *tok == '!';
		if (force_off)
			tok++;
		for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
			if (strcmp(tok, o->name) == 0) {
				if (force_off)
					o->force_off = true;
				else
					o->force_on = true;
				break;
			}
		}
	}
	return 1;
}
__setup("rdt", set_rdt_options);

static bool __init rdt_cpu_has(int flag)
{
	bool ret = boot_cpu_has(flag);
	struct rdt_options *o;

	if (!ret)
		return ret;

	for (o = rdt_options; o < &rdt_options[NUM_RDT_OPTIONS]; o++) {
		if (flag == o->flag) {
			if (o->force_off)
				ret = false;
			if (o->force_on)
				ret = true;
			break;
		}
	}
	return ret;
}

static __init bool get_rdt_alloc_resources(void)
{
	bool ret = false;

	if (rdt_alloc_capable)
		return true;

	if (!boot_cpu_has(X86_FEATURE_RDT_A))
		return false;

	if (rdt_cpu_has(X86_FEATURE_CAT_L3)) {
		rdt_get_cache_alloc_cfg(1, &rdt_resources_all[RDT_RESOURCE_L3]);
		if (rdt_cpu_has(X86_FEATURE_CDP_L3))
			rdt_get_cdp_l3_config();
		ret = true;
	}
	if (rdt_cpu_has(X86_FEATURE_CAT_L2)) {
		/* CPUID 0x10.2 fields are same format at 0x10.1 */
		rdt_get_cache_alloc_cfg(2, &rdt_resources_all[RDT_RESOURCE_L2]);
		if (rdt_cpu_has(X86_FEATURE_CDP_L2))
			rdt_get_cdp_l2_config();
		ret = true;
	}

	if (rdt_cpu_has(X86_FEATURE_MBA)) {
		if (rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]))
			ret = true;
	}
	return ret;
}

static __init bool get_rdt_mon_resources(void)
{
	if (rdt_cpu_has(X86_FEATURE_CQM_OCCUP_LLC))
		rdt_mon_features |= (1 << QOS_L3_OCCUP_EVENT_ID);
	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL))
		rdt_mon_features |= (1 << QOS_L3_MBM_TOTAL_EVENT_ID);
	if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL))
		rdt_mon_features |= (1 << QOS_L3_MBM_LOCAL_EVENT_ID);

	if (!rdt_mon_features)
		return false;

	return !rdt_get_mon_l3_config(&rdt_resources_all[RDT_RESOURCE_L3]);
}

static __init void rdt_quirks(void)
{
	switch (boot_cpu_data.x86_model) {
	case INTEL_FAM6_HASWELL_X:
		if (!rdt_options[RDT_FLAG_L3_CAT].force_off)
			cache_alloc_hsw_probe();
		break;
	case INTEL_FAM6_SKYLAKE_X:
		if (boot_cpu_data.x86_stepping <= 4)
			set_rdt_options("!cmt,!mbmtotal,!mbmlocal,!l3cat");
		else
			set_rdt_options("!l3cat");
	}
}

static __init bool get_rdt_resources(void)
{
	rdt_quirks();
	rdt_alloc_capable = get_rdt_alloc_resources();
	rdt_mon_capable = get_rdt_mon_resources();

	return (rdt_mon_capable || rdt_alloc_capable);
}

static enum cpuhp_state rdt_online;

static int __init intel_rdt_late_init(void)
{
	struct rdt_resource *r;
	int state, ret;

	if (!get_rdt_resources())
		return -ENODEV;

	rdt_init_padding();

	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
				  "x86/rdt/cat:online:",
				  intel_rdt_online_cpu, intel_rdt_offline_cpu);
	if (state < 0)
		return state;

	ret = rdtgroup_init();
	if (ret) {
		cpuhp_remove_state(state);
		return ret;
	}
	rdt_online = state;

	for_each_alloc_capable_rdt_resource(r)
		pr_info("Intel RDT %s allocation detected\n", r->name);

	for_each_mon_capable_rdt_resource(r)
		pr_info("Intel RDT %s monitoring detected\n", r->name);

	return 0;
}

late_initcall(intel_rdt_late_init);

static void __exit intel_rdt_exit(void)
{
	cpuhp_remove_state(rdt_online);
	rdtgroup_exit();
}

__exitcall(intel_rdt_exit);