summaryrefslogtreecommitdiff
path: root/drivers/nvdimm/region_devs.c
blob: 473a71bbd9c9e68176adaaa8364a0213ab90c8b9 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
 */
#include <linux/scatterlist.h>
#include <linux/memregion.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/hash.h>
#include <linux/sort.h>
#include <linux/io.h>
#include <linux/nd.h>
#include "nd-core.h"
#include "nd.h"

/*
 * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
 * irrelevant.
 */
#include <linux/io-64-nonatomic-hi-lo.h>

static DEFINE_PER_CPU(int, flush_idx);

static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
		struct nd_region_data *ndrd)
{
	int i, j;

	dev_dbg(dev, "%s: map %d flush address%s\n", nvdimm_name(nvdimm),
			nvdimm->num_flush, nvdimm->num_flush == 1 ? "" : "es");
	for (i = 0; i < (1 << ndrd->hints_shift); i++) {
		struct resource *res = &nvdimm->flush_wpq[i];
		unsigned long pfn = PHYS_PFN(res->start);
		void __iomem *flush_page;

		/* check if flush hints share a page */
		for (j = 0; j < i; j++) {
			struct resource *res_j = &nvdimm->flush_wpq[j];
			unsigned long pfn_j = PHYS_PFN(res_j->start);

			if (pfn == pfn_j)
				break;
		}

		if (j < i)
			flush_page = (void __iomem *) ((unsigned long)
					ndrd_get_flush_wpq(ndrd, dimm, j)
					& PAGE_MASK);
		else
			flush_page = devm_nvdimm_ioremap(dev,
					PFN_PHYS(pfn), PAGE_SIZE);
		if (!flush_page)
			return -ENXIO;
		ndrd_set_flush_wpq(ndrd, dimm, i, flush_page
				+ (res->start & ~PAGE_MASK));
	}

	return 0;
}

int nd_region_activate(struct nd_region *nd_region)
{
	int i, j, num_flush = 0;
	struct nd_region_data *ndrd;
	struct device *dev = &nd_region->dev;
	size_t flush_data_size = sizeof(void *);

	nvdimm_bus_lock(&nd_region->dev);
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;

		if (test_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags)) {
			nvdimm_bus_unlock(&nd_region->dev);
			return -EBUSY;
		}

		/* at least one null hint slot per-dimm for the "no-hint" case */
		flush_data_size += sizeof(void *);
		num_flush = min_not_zero(num_flush, nvdimm->num_flush);
		if (!nvdimm->num_flush)
			continue;
		flush_data_size += nvdimm->num_flush * sizeof(void *);
	}
	nvdimm_bus_unlock(&nd_region->dev);

	ndrd = devm_kzalloc(dev, sizeof(*ndrd) + flush_data_size, GFP_KERNEL);
	if (!ndrd)
		return -ENOMEM;
	dev_set_drvdata(dev, ndrd);

	if (!num_flush)
		return 0;

	ndrd->hints_shift = ilog2(num_flush);
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;
		int rc = nvdimm_map_flush(&nd_region->dev, nvdimm, i, ndrd);

		if (rc)
			return rc;
	}

	/*
	 * Clear out entries that are duplicates. This should prevent the
	 * extra flushings.
	 */
	for (i = 0; i < nd_region->ndr_mappings - 1; i++) {
		/* ignore if NULL already */
		if (!ndrd_get_flush_wpq(ndrd, i, 0))
			continue;

		for (j = i + 1; j < nd_region->ndr_mappings; j++)
			if (ndrd_get_flush_wpq(ndrd, i, 0) ==
			    ndrd_get_flush_wpq(ndrd, j, 0))
				ndrd_set_flush_wpq(ndrd, j, 0, NULL);
	}

	return 0;
}

static void nd_region_release(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev);
	u16 i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;

		put_device(&nvdimm->dev);
	}
	free_percpu(nd_region->lane);
	if (!test_bit(ND_REGION_CXL, &nd_region->flags))
		memregion_free(nd_region->id);
	kfree(nd_region);
}

struct nd_region *to_nd_region(struct device *dev)
{
	struct nd_region *nd_region = container_of(dev, struct nd_region, dev);

	WARN_ON(dev->type->release != nd_region_release);
	return nd_region;
}
EXPORT_SYMBOL_GPL(to_nd_region);

struct device *nd_region_dev(struct nd_region *nd_region)
{
	if (!nd_region)
		return NULL;
	return &nd_region->dev;
}
EXPORT_SYMBOL_GPL(nd_region_dev);

void *nd_region_provider_data(struct nd_region *nd_region)
{
	return nd_region->provider_data;
}
EXPORT_SYMBOL_GPL(nd_region_provider_data);

/**
 * nd_region_to_nstype() - region to an integer namespace type
 * @nd_region: region-device to interrogate
 *
 * This is the 'nstype' attribute of a region as well, an input to the
 * MODALIAS for namespace devices, and bit number for a nvdimm_bus to match
 * namespace devices with namespace drivers.
 */
int nd_region_to_nstype(struct nd_region *nd_region)
{
	if (is_memory(&nd_region->dev)) {
		u16 i, label;

		for (i = 0, label = 0; i < nd_region->ndr_mappings; i++) {
			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
			struct nvdimm *nvdimm = nd_mapping->nvdimm;

			if (test_bit(NDD_LABELING, &nvdimm->flags))
				label++;
		}
		if (label)
			return ND_DEVICE_NAMESPACE_PMEM;
		else
			return ND_DEVICE_NAMESPACE_IO;
	}

	return 0;
}
EXPORT_SYMBOL(nd_region_to_nstype);

static unsigned long long region_size(struct nd_region *nd_region)
{
	if (is_memory(&nd_region->dev)) {
		return nd_region->ndr_size;
	} else if (nd_region->ndr_mappings == 1) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[0];

		return nd_mapping->size;
	}

	return 0;
}

static ssize_t size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%llu\n", region_size(nd_region));
}
static DEVICE_ATTR_RO(size);

static ssize_t deep_flush_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	/*
	 * NOTE: in the nvdimm_has_flush() error case this attribute is
	 * not visible.
	 */
	return sprintf(buf, "%d\n", nvdimm_has_flush(nd_region));
}

static ssize_t deep_flush_store(struct device *dev, struct device_attribute *attr,
		const char *buf, size_t len)
{
	bool flush;
	int rc = strtobool(buf, &flush);
	struct nd_region *nd_region = to_nd_region(dev);

	if (rc)
		return rc;
	if (!flush)
		return -EINVAL;
	rc = nvdimm_flush(nd_region, NULL);
	if (rc)
		return rc;

	return len;
}
static DEVICE_ATTR_RW(deep_flush);

static ssize_t mappings_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%d\n", nd_region->ndr_mappings);
}
static DEVICE_ATTR_RO(mappings);

static ssize_t nstype_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
}
static DEVICE_ATTR_RO(nstype);

static ssize_t set_cookie_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_interleave_set *nd_set = nd_region->nd_set;
	ssize_t rc = 0;

	if (is_memory(dev) && nd_set)
		/* pass, should be precluded by region_visible */;
	else
		return -ENXIO;

	/*
	 * The cookie to show depends on which specification of the
	 * labels we are using. If there are not labels then default to
	 * the v1.1 namespace label cookie definition. To read all this
	 * data we need to wait for probing to settle.
	 */
	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	if (nd_region->ndr_mappings) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

		if (ndd) {
			struct nd_namespace_index *nsindex;

			nsindex = to_namespace_index(ndd, ndd->ns_current);
			rc = sprintf(buf, "%#llx\n",
					nd_region_interleave_set_cookie(nd_region,
						nsindex));
		}
	}
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

	if (rc)
		return rc;
	return sprintf(buf, "%#llx\n", nd_set->cookie1);
}
static DEVICE_ATTR_RO(set_cookie);

resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
{
	resource_size_t available;
	int i;

	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));

	available = 0;
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

		/* if a dimm is disabled the available capacity is zero */
		if (!ndd)
			return 0;

		available += nd_pmem_available_dpa(nd_region, nd_mapping);
	}

	return available;
}

resource_size_t nd_region_allocatable_dpa(struct nd_region *nd_region)
{
	resource_size_t avail = 0;
	int i;

	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];

		avail = min_not_zero(avail, nd_pmem_max_contiguous_dpa(
						    nd_region, nd_mapping));
	}
	return avail * nd_region->ndr_mappings;
}

static ssize_t available_size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	unsigned long long available = 0;

	/*
	 * Flush in-flight updates and grab a snapshot of the available
	 * size.  Of course, this value is potentially invalidated the
	 * memory nvdimm_bus_lock() is dropped, but that's userspace's
	 * problem to not race itself.
	 */
	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	available = nd_region_available_dpa(nd_region);
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

	return sprintf(buf, "%llu\n", available);
}
static DEVICE_ATTR_RO(available_size);

static ssize_t max_available_extent_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	unsigned long long available = 0;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	available = nd_region_allocatable_dpa(nd_region);
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

	return sprintf(buf, "%llu\n", available);
}
static DEVICE_ATTR_RO(max_available_extent);

static ssize_t init_namespaces_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region_data *ndrd = dev_get_drvdata(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (ndrd)
		rc = sprintf(buf, "%d/%d\n", ndrd->ns_active, ndrd->ns_count);
	else
		rc = -ENXIO;
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(init_namespaces);

static ssize_t namespace_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->ns_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);
	return rc;
}
static DEVICE_ATTR_RO(namespace_seed);

static ssize_t btt_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->btt_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->btt_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(btt_seed);

static ssize_t pfn_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->pfn_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->pfn_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(pfn_seed);

static ssize_t dax_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->dax_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->dax_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(dax_seed);

static ssize_t read_only_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%d\n", nd_region->ro);
}

static int revalidate_read_only(struct device *dev, void *data)
{
	nd_device_notify(dev, NVDIMM_REVALIDATE_REGION);
	return 0;
}

static ssize_t read_only_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	bool ro;
	int rc = strtobool(buf, &ro);
	struct nd_region *nd_region = to_nd_region(dev);

	if (rc)
		return rc;

	nd_region->ro = ro;
	device_for_each_child(dev, NULL, revalidate_read_only);
	return len;
}
static DEVICE_ATTR_RW(read_only);

static ssize_t align_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%#lx\n", nd_region->align);
}

static ssize_t align_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_region *nd_region = to_nd_region(dev);
	unsigned long val, dpa;
	u32 remainder;
	int rc;

	rc = kstrtoul(buf, 0, &val);
	if (rc)
		return rc;

	if (!nd_region->ndr_mappings)
		return -ENXIO;

	/*
	 * Ensure space-align is evenly divisible by the region
	 * interleave-width because the kernel typically has no facility
	 * to determine which DIMM(s), dimm-physical-addresses, would
	 * contribute to the tail capacity in system-physical-address
	 * space for the namespace.
	 */
	dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder);
	if (!is_power_of_2(dpa) || dpa < PAGE_SIZE
			|| val > region_size(nd_region) || remainder)
		return -EINVAL;

	/*
	 * Given that space allocation consults this value multiple
	 * times ensure it does not change for the duration of the
	 * allocation.
	 */
	nvdimm_bus_lock(dev);
	nd_region->align = val;
	nvdimm_bus_unlock(dev);

	return len;
}
static DEVICE_ATTR_RW(align);

static ssize_t region_badblocks_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	device_lock(dev);
	if (dev->driver)
		rc = badblocks_show(&nd_region->bb, buf, 0);
	else
		rc = -ENXIO;
	device_unlock(dev);

	return rc;
}
static DEVICE_ATTR(badblocks, 0444, region_badblocks_show, NULL);

static ssize_t resource_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%#llx\n", nd_region->ndr_start);
}
static DEVICE_ATTR_ADMIN_RO(resource);

static ssize_t persistence_domain_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	if (test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags))
		return sprintf(buf, "cpu_cache\n");
	else if (test_bit(ND_REGION_PERSIST_MEMCTRL, &nd_region->flags))
		return sprintf(buf, "memory_controller\n");
	else
		return sprintf(buf, "\n");
}
static DEVICE_ATTR_RO(persistence_domain);

static struct attribute *nd_region_attributes[] = {
	&dev_attr_size.attr,
	&dev_attr_align.attr,
	&dev_attr_nstype.attr,
	&dev_attr_mappings.attr,
	&dev_attr_btt_seed.attr,
	&dev_attr_pfn_seed.attr,
	&dev_attr_dax_seed.attr,
	&dev_attr_deep_flush.attr,
	&dev_attr_read_only.attr,
	&dev_attr_set_cookie.attr,
	&dev_attr_available_size.attr,
	&dev_attr_max_available_extent.attr,
	&dev_attr_namespace_seed.attr,
	&dev_attr_init_namespaces.attr,
	&dev_attr_badblocks.attr,
	&dev_attr_resource.attr,
	&dev_attr_persistence_domain.attr,
	NULL,
};

static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, typeof(*dev), kobj);
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_interleave_set *nd_set = nd_region->nd_set;
	int type = nd_region_to_nstype(nd_region);

	if (!is_memory(dev) && a == &dev_attr_pfn_seed.attr)
		return 0;

	if (!is_memory(dev) && a == &dev_attr_dax_seed.attr)
		return 0;

	if (!is_memory(dev) && a == &dev_attr_badblocks.attr)
		return 0;

	if (a == &dev_attr_resource.attr && !is_memory(dev))
		return 0;

	if (a == &dev_attr_deep_flush.attr) {
		int has_flush = nvdimm_has_flush(nd_region);

		if (has_flush == 1)
			return a->mode;
		else if (has_flush == 0)
			return 0444;
		else
			return 0;
	}

	if (a == &dev_attr_persistence_domain.attr) {
		if ((nd_region->flags & (BIT(ND_REGION_PERSIST_CACHE)
					| BIT(ND_REGION_PERSIST_MEMCTRL))) == 0)
			return 0;
		return a->mode;
	}

	if (a == &dev_attr_align.attr)
		return a->mode;

	if (a != &dev_attr_set_cookie.attr
			&& a != &dev_attr_available_size.attr)
		return a->mode;

	if (type == ND_DEVICE_NAMESPACE_PMEM &&
	    a == &dev_attr_available_size.attr)
		return a->mode;
	else if (is_memory(dev) && nd_set)
		return a->mode;

	return 0;
}

static ssize_t mappingN(struct device *dev, char *buf, int n)
{
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_mapping *nd_mapping;
	struct nvdimm *nvdimm;

	if (n >= nd_region->ndr_mappings)
		return -ENXIO;
	nd_mapping = &nd_region->mapping[n];
	nvdimm = nd_mapping->nvdimm;

	return sprintf(buf, "%s,%llu,%llu,%d\n", dev_name(&nvdimm->dev),
			nd_mapping->start, nd_mapping->size,
			nd_mapping->position);
}

#define REGION_MAPPING(idx) \
static ssize_t mapping##idx##_show(struct device *dev,		\
		struct device_attribute *attr, char *buf)	\
{								\
	return mappingN(dev, buf, idx);				\
}								\
static DEVICE_ATTR_RO(mapping##idx)

/*
 * 32 should be enough for a while, even in the presence of socket
 * interleave a 32-way interleave set is a degenerate case.
 */
REGION_MAPPING(0);
REGION_MAPPING(1);
REGION_MAPPING(2);
REGION_MAPPING(3);
REGION_MAPPING(4);
REGION_MAPPING(5);
REGION_MAPPING(6);
REGION_MAPPING(7);
REGION_MAPPING(8);
REGION_MAPPING(9);
REGION_MAPPING(10);
REGION_MAPPING(11);
REGION_MAPPING(12);
REGION_MAPPING(13);
REGION_MAPPING(14);
REGION_MAPPING(15);
REGION_MAPPING(16);
REGION_MAPPING(17);
REGION_MAPPING(18);
REGION_MAPPING(19);
REGION_MAPPING(20);
REGION_MAPPING(21);
REGION_MAPPING(22);
REGION_MAPPING(23);
REGION_MAPPING(24);
REGION_MAPPING(25);
REGION_MAPPING(26);
REGION_MAPPING(27);
REGION_MAPPING(28);
REGION_MAPPING(29);
REGION_MAPPING(30);
REGION_MAPPING(31);

static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct nd_region *nd_region = to_nd_region(dev);

	if (n < nd_region->ndr_mappings)
		return a->mode;
	return 0;
}

static struct attribute *mapping_attributes[] = {
	&dev_attr_mapping0.attr,
	&dev_attr_mapping1.attr,
	&dev_attr_mapping2.attr,
	&dev_attr_mapping3.attr,
	&dev_attr_mapping4.attr,
	&dev_attr_mapping5.attr,
	&dev_attr_mapping6.attr,
	&dev_attr_mapping7.attr,
	&dev_attr_mapping8.attr,
	&dev_attr_mapping9.attr,
	&dev_attr_mapping10.attr,
	&dev_attr_mapping11.attr,
	&dev_attr_mapping12.attr,
	&dev_attr_mapping13.attr,
	&dev_attr_mapping14.attr,
	&dev_attr_mapping15.attr,
	&dev_attr_mapping16.attr,
	&dev_attr_mapping17.attr,
	&dev_attr_mapping18.attr,
	&dev_attr_mapping19.attr,
	&dev_attr_mapping20.attr,
	&dev_attr_mapping21.attr,
	&dev_attr_mapping22.attr,
	&dev_attr_mapping23.attr,
	&dev_attr_mapping24.attr,
	&dev_attr_mapping25.attr,
	&dev_attr_mapping26.attr,
	&dev_attr_mapping27.attr,
	&dev_attr_mapping28.attr,
	&dev_attr_mapping29.attr,
	&dev_attr_mapping30.attr,
	&dev_attr_mapping31.attr,
	NULL,
};

static const struct attribute_group nd_mapping_attribute_group = {
	.is_visible = mapping_visible,
	.attrs = mapping_attributes,
};

static const struct attribute_group nd_region_attribute_group = {
	.attrs = nd_region_attributes,
	.is_visible = region_visible,
};

static const struct attribute_group *nd_region_attribute_groups[] = {
	&nd_device_attribute_group,
	&nd_region_attribute_group,
	&nd_numa_attribute_group,
	&nd_mapping_attribute_group,
	NULL,
};

static const struct device_type nd_pmem_device_type = {
	.name = "nd_pmem",
	.release = nd_region_release,
	.groups = nd_region_attribute_groups,
};

static const struct device_type nd_volatile_device_type = {
	.name = "nd_volatile",
	.release = nd_region_release,
	.groups = nd_region_attribute_groups,
};

bool is_nd_pmem(struct device *dev)
{
	return dev ? dev->type == &nd_pmem_device_type : false;
}

bool is_nd_volatile(struct device *dev)
{
	return dev ? dev->type == &nd_volatile_device_type : false;
}

u64 nd_region_interleave_set_cookie(struct nd_region *nd_region,
		struct nd_namespace_index *nsindex)
{
	struct nd_interleave_set *nd_set = nd_region->nd_set;

	if (!nd_set)
		return 0;

	if (nsindex && __le16_to_cpu(nsindex->major) == 1
			&& __le16_to_cpu(nsindex->minor) == 1)
		return nd_set->cookie1;
	return nd_set->cookie2;
}

u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region)
{
	struct nd_interleave_set *nd_set = nd_region->nd_set;

	if (nd_set)
		return nd_set->altcookie;
	return 0;
}

void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
{
	struct nd_label_ent *label_ent, *e;

	lockdep_assert_held(&nd_mapping->lock);
	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
		list_del(&label_ent->list);
		kfree(label_ent);
	}
}

/*
 * When a namespace is activated create new seeds for the next
 * namespace, or namespace-personality to be configured.
 */
void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev)
{
	nvdimm_bus_lock(dev);
	if (nd_region->ns_seed == dev) {
		nd_region_create_ns_seed(nd_region);
	} else if (is_nd_btt(dev)) {
		struct nd_btt *nd_btt = to_nd_btt(dev);

		if (nd_region->btt_seed == dev)
			nd_region_create_btt_seed(nd_region);
		if (nd_region->ns_seed == &nd_btt->ndns->dev)
			nd_region_create_ns_seed(nd_region);
	} else if (is_nd_pfn(dev)) {
		struct nd_pfn *nd_pfn = to_nd_pfn(dev);

		if (nd_region->pfn_seed == dev)
			nd_region_create_pfn_seed(nd_region);
		if (nd_region->ns_seed == &nd_pfn->ndns->dev)
			nd_region_create_ns_seed(nd_region);
	} else if (is_nd_dax(dev)) {
		struct nd_dax *nd_dax = to_nd_dax(dev);

		if (nd_region->dax_seed == dev)
			nd_region_create_dax_seed(nd_region);
		if (nd_region->ns_seed == &nd_dax->nd_pfn.ndns->dev)
			nd_region_create_ns_seed(nd_region);
	}
	nvdimm_bus_unlock(dev);
}

/**
 * nd_region_acquire_lane - allocate and lock a lane
 * @nd_region: region id and number of lanes possible
 *
 * A lane correlates to a BLK-data-window and/or a log slot in the BTT.
 * We optimize for the common case where there are 256 lanes, one
 * per-cpu.  For larger systems we need to lock to share lanes.  For now
 * this implementation assumes the cost of maintaining an allocator for
 * free lanes is on the order of the lock hold time, so it implements a
 * static lane = cpu % num_lanes mapping.
 *
 * In the case of a BTT instance on top of a BLK namespace a lane may be
 * acquired recursively.  We lock on the first instance.
 *
 * In the case of a BTT instance on top of PMEM, we only acquire a lane
 * for the BTT metadata updates.
 */
unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
{
	unsigned int cpu, lane;

	cpu = get_cpu();
	if (nd_region->num_lanes < nr_cpu_ids) {
		struct nd_percpu_lane *ndl_lock, *ndl_count;

		lane = cpu % nd_region->num_lanes;
		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
		if (ndl_count->count++ == 0)
			spin_lock(&ndl_lock->lock);
	} else
		lane = cpu;

	return lane;
}
EXPORT_SYMBOL(nd_region_acquire_lane);

void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
{
	if (nd_region->num_lanes < nr_cpu_ids) {
		unsigned int cpu = get_cpu();
		struct nd_percpu_lane *ndl_lock, *ndl_count;

		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
		if (--ndl_count->count == 0)
			spin_unlock(&ndl_lock->lock);
		put_cpu();
	}
	put_cpu();
}
EXPORT_SYMBOL(nd_region_release_lane);

/*
 * PowerPC requires this alignment for memremap_pages(). All other archs
 * should be ok with SUBSECTION_SIZE (see memremap_compat_align()).
 */
#define MEMREMAP_COMPAT_ALIGN_MAX SZ_16M

static unsigned long default_align(struct nd_region *nd_region)
{
	unsigned long align;
	u32 remainder;
	int mappings;

	align = MEMREMAP_COMPAT_ALIGN_MAX;
	if (nd_region->ndr_size < MEMREMAP_COMPAT_ALIGN_MAX)
		align = PAGE_SIZE;

	mappings = max_t(u16, 1, nd_region->ndr_mappings);
	div_u64_rem(align, mappings, &remainder);
	if (remainder)
		align *= mappings;

	return align;
}

static struct lock_class_key nvdimm_region_key;

static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc,
		const struct device_type *dev_type, const char *caller)
{
	struct nd_region *nd_region;
	struct device *dev;
	unsigned int i;
	int ro = 0;

	for (i = 0; i < ndr_desc->num_mappings; i++) {
		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
		struct nvdimm *nvdimm = mapping->nvdimm;

		if ((mapping->start | mapping->size) % PAGE_SIZE) {
			dev_err(&nvdimm_bus->dev,
				"%s: %s mapping%d is not %ld aligned\n",
				caller, dev_name(&nvdimm->dev), i, PAGE_SIZE);
			return NULL;
		}

		if (test_bit(NDD_UNARMED, &nvdimm->flags))
			ro = 1;

	}

	nd_region =
		kzalloc(struct_size(nd_region, mapping, ndr_desc->num_mappings),
			GFP_KERNEL);

	if (!nd_region)
		return NULL;
	/* CXL pre-assigns memregion ids before creating nvdimm regions */
	if (test_bit(ND_REGION_CXL, &ndr_desc->flags)) {
		nd_region->id = ndr_desc->memregion;
	} else {
		nd_region->id = memregion_alloc(GFP_KERNEL);
		if (nd_region->id < 0)
			goto err_id;
	}

	nd_region->lane = alloc_percpu(struct nd_percpu_lane);
	if (!nd_region->lane)
		goto err_percpu;

        for (i = 0; i < nr_cpu_ids; i++) {
		struct nd_percpu_lane *ndl;

		ndl = per_cpu_ptr(nd_region->lane, i);
		spin_lock_init(&ndl->lock);
		ndl->count = 0;
	}

	for (i = 0; i < ndr_desc->num_mappings; i++) {
		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
		struct nvdimm *nvdimm = mapping->nvdimm;

		nd_region->mapping[i].nvdimm = nvdimm;
		nd_region->mapping[i].start = mapping->start;
		nd_region->mapping[i].size = mapping->size;
		nd_region->mapping[i].position = mapping->position;
		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
		mutex_init(&nd_region->mapping[i].lock);

		get_device(&nvdimm->dev);
	}
	nd_region->ndr_mappings = ndr_desc->num_mappings;
	nd_region->provider_data = ndr_desc->provider_data;
	nd_region->nd_set = ndr_desc->nd_set;
	nd_region->num_lanes = ndr_desc->num_lanes;
	nd_region->flags = ndr_desc->flags;
	nd_region->ro = ro;
	nd_region->numa_node = ndr_desc->numa_node;
	nd_region->target_node = ndr_desc->target_node;
	ida_init(&nd_region->ns_ida);
	ida_init(&nd_region->btt_ida);
	ida_init(&nd_region->pfn_ida);
	ida_init(&nd_region->dax_ida);
	dev = &nd_region->dev;
	dev_set_name(dev, "region%d", nd_region->id);
	dev->parent = &nvdimm_bus->dev;
	dev->type = dev_type;
	dev->groups = ndr_desc->attr_groups;
	dev->of_node = ndr_desc->of_node;
	nd_region->ndr_size = resource_size(ndr_desc->res);
	nd_region->ndr_start = ndr_desc->res->start;
	nd_region->align = default_align(nd_region);
	if (ndr_desc->flush)
		nd_region->flush = ndr_desc->flush;
	else
		nd_region->flush = NULL;

	device_initialize(dev);
	lockdep_set_class(&dev->mutex, &nvdimm_region_key);
	nd_device_register(dev);

	return nd_region;

err_percpu:
	if (!test_bit(ND_REGION_CXL, &ndr_desc->flags))
		memregion_free(nd_region->id);
err_id:
	kfree(nd_region);
	return NULL;
}

struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc)
{
	ndr_desc->num_lanes = ND_MAX_LANES;
	return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type,
			__func__);
}
EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create);

struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc)
{
	ndr_desc->num_lanes = ND_MAX_LANES;
	return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type,
			__func__);
}
EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);

void nvdimm_region_delete(struct nd_region *nd_region)
{
	if (nd_region)
		nd_device_unregister(&nd_region->dev, ND_SYNC);
}
EXPORT_SYMBOL_GPL(nvdimm_region_delete);

int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
{
	int rc = 0;

	if (!nd_region->flush)
		rc = generic_nvdimm_flush(nd_region);
	else {
		if (nd_region->flush(nd_region, bio))
			rc = -EIO;
	}

	return rc;
}
/**
 * nvdimm_flush - flush any posted write queues between the cpu and pmem media
 * @nd_region: interleaved pmem region
 */
int generic_nvdimm_flush(struct nd_region *nd_region)
{
	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
	int i, idx;

	/*
	 * Try to encourage some diversity in flush hint addresses
	 * across cpus assuming a limited number of flush hints.
	 */
	idx = this_cpu_read(flush_idx);
	idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));

	/*
	 * The pmem_wmb() is needed to 'sfence' all
	 * previous writes such that they are architecturally visible for
	 * the platform buffer flush. Note that we've already arranged for pmem
	 * writes to avoid the cache via memcpy_flushcache().  The final
	 * wmb() ensures ordering for the NVDIMM flush write.
	 */
	pmem_wmb();
	for (i = 0; i < nd_region->ndr_mappings; i++)
		if (ndrd_get_flush_wpq(ndrd, i, 0))
			writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
	wmb();

	return 0;
}
EXPORT_SYMBOL_GPL(nvdimm_flush);

/**
 * nvdimm_has_flush - determine write flushing requirements
 * @nd_region: interleaved pmem region
 *
 * Returns 1 if writes require flushing
 * Returns 0 if writes do not require flushing
 * Returns -ENXIO if flushing capability can not be determined
 */
int nvdimm_has_flush(struct nd_region *nd_region)
{
	int i;

	/* no nvdimm or pmem api == flushing capability unknown */
	if (nd_region->ndr_mappings == 0
			|| !IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
		return -ENXIO;

	/* Test if an explicit flush function is defined */
	if (test_bit(ND_REGION_ASYNC, &nd_region->flags) && nd_region->flush)
		return 1;

	/* Test if any flush hints for the region are available */
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;

		/* flush hints present / available */
		if (nvdimm->num_flush)
			return 1;
	}

	/*
	 * The platform defines dimm devices without hints nor explicit flush,
	 * assume platform persistence mechanism like ADR
	 */
	return 0;
}
EXPORT_SYMBOL_GPL(nvdimm_has_flush);

int nvdimm_has_cache(struct nd_region *nd_region)
{
	return is_nd_pmem(&nd_region->dev) &&
		!test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags);
}
EXPORT_SYMBOL_GPL(nvdimm_has_cache);

bool is_nvdimm_sync(struct nd_region *nd_region)
{
	if (is_nd_volatile(&nd_region->dev))
		return true;

	return is_nd_pmem(&nd_region->dev) &&
		!test_bit(ND_REGION_ASYNC, &nd_region->flags);
}
EXPORT_SYMBOL_GPL(is_nvdimm_sync);

struct conflict_context {
	struct nd_region *nd_region;
	resource_size_t start, size;
};

static int region_conflict(struct device *dev, void *data)
{
	struct nd_region *nd_region;
	struct conflict_context *ctx = data;
	resource_size_t res_end, region_end, region_start;

	if (!is_memory(dev))
		return 0;

	nd_region = to_nd_region(dev);
	if (nd_region == ctx->nd_region)
		return 0;

	res_end = ctx->start + ctx->size;
	region_start = nd_region->ndr_start;
	region_end = region_start + nd_region->ndr_size;
	if (ctx->start >= region_start && ctx->start < region_end)
		return -EBUSY;
	if (res_end > region_start && res_end <= region_end)
		return -EBUSY;
	return 0;
}

int nd_region_conflict(struct nd_region *nd_region, resource_size_t start,
		resource_size_t size)
{
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
	struct conflict_context ctx = {
		.nd_region = nd_region,
		.start = start,
		.size = size,
	};

	return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict);
}