summaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms/pseries/papr_scm.c
blob: 9b6420eb3567dfe7a07b3a6920a7a53061e2e92d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
// SPDX-License-Identifier: GPL-2.0

#define pr_fmt(fmt)	"papr-scm: " fmt

#include <linux/of.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/ndctl.h>
#include <linux/sched.h>
#include <linux/libnvdimm.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/seq_buf.h>
#include <linux/nd.h>

#include <asm/plpar_wrappers.h>
#include <uapi/linux/papr_pdsm.h>
#include <linux/papr_scm.h>
#include <asm/mce.h>
#include <asm/unaligned.h>
#include <linux/perf_event.h>

#define BIND_ANY_ADDR (~0ul)

#define PAPR_SCM_DIMM_CMD_MASK \
	((1ul << ND_CMD_GET_CONFIG_SIZE) | \
	 (1ul << ND_CMD_GET_CONFIG_DATA) | \
	 (1ul << ND_CMD_SET_CONFIG_DATA) | \
	 (1ul << ND_CMD_CALL))

/* Struct holding a single performance metric */
struct papr_scm_perf_stat {
	u8 stat_id[8];
	__be64 stat_val;
} __packed;

/* Struct exchanged between kernel and PHYP for fetching drc perf stats */
struct papr_scm_perf_stats {
	u8 eye_catcher[8];
	/* Should be PAPR_SCM_PERF_STATS_VERSION */
	__be32 stats_version;
	/* Number of stats following */
	__be32 num_statistics;
	/* zero or more performance matrics */
	struct papr_scm_perf_stat scm_statistic[];
} __packed;

/* private struct associated with each region */
struct papr_scm_priv {
	struct platform_device *pdev;
	struct device_node *dn;
	uint32_t drc_index;
	uint64_t blocks;
	uint64_t block_size;
	int metadata_size;
	bool is_volatile;
	bool hcall_flush_required;

	uint64_t bound_addr;

	struct nvdimm_bus_descriptor bus_desc;
	struct nvdimm_bus *bus;
	struct nvdimm *nvdimm;
	struct resource res;
	struct nd_region *region;
	struct nd_interleave_set nd_set;
	struct list_head region_list;

	/* Protect dimm health data from concurrent read/writes */
	struct mutex health_mutex;

	/* Last time the health information of the dimm was updated */
	unsigned long lasthealth_jiffies;

	/* Health information for the dimm */
	u64 health_bitmap;

	/* Holds the last known dirty shutdown counter value */
	u64 dirty_shutdown_counter;

	/* length of the stat buffer as expected by phyp */
	size_t stat_buffer_len;

	/* The bits which needs to be overridden */
	u64 health_bitmap_inject_mask;
};

static int papr_scm_pmem_flush(struct nd_region *nd_region,
			       struct bio *bio __maybe_unused)
{
	struct papr_scm_priv *p = nd_region_provider_data(nd_region);
	unsigned long ret_buf[PLPAR_HCALL_BUFSIZE], token = 0;
	long rc;

	dev_dbg(&p->pdev->dev, "flush drc 0x%x", p->drc_index);

	do {
		rc = plpar_hcall(H_SCM_FLUSH, ret_buf, p->drc_index, token);
		token = ret_buf[0];

		/* Check if we are stalled for some time */
		if (H_IS_LONG_BUSY(rc)) {
			msleep(get_longbusy_msecs(rc));
			rc = H_BUSY;
		} else if (rc == H_BUSY) {
			cond_resched();
		}
	} while (rc == H_BUSY);

	if (rc) {
		dev_err(&p->pdev->dev, "flush error: %ld", rc);
		rc = -EIO;
	} else {
		dev_dbg(&p->pdev->dev, "flush drc 0x%x complete", p->drc_index);
	}

	return rc;
}

static LIST_HEAD(papr_nd_regions);
static DEFINE_MUTEX(papr_ndr_lock);

static int drc_pmem_bind(struct papr_scm_priv *p)
{
	unsigned long ret[PLPAR_HCALL_BUFSIZE];
	uint64_t saved = 0;
	uint64_t token;
	int64_t rc;

	/*
	 * When the hypervisor cannot map all the requested memory in a single
	 * hcall it returns H_BUSY and we call again with the token until
	 * we get H_SUCCESS. Aborting the retry loop before getting H_SUCCESS
	 * leave the system in an undefined state, so we wait.
	 */
	token = 0;

	do {
		rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0,
				p->blocks, BIND_ANY_ADDR, token);
		token = ret[0];
		if (!saved)
			saved = ret[1];
		cond_resched();
	} while (rc == H_BUSY);

	if (rc)
		return rc;

	p->bound_addr = saved;
	dev_dbg(&p->pdev->dev, "bound drc 0x%x to 0x%lx\n",
		p->drc_index, (unsigned long)saved);
	return rc;
}

static void drc_pmem_unbind(struct papr_scm_priv *p)
{
	unsigned long ret[PLPAR_HCALL_BUFSIZE];
	uint64_t token = 0;
	int64_t rc;

	dev_dbg(&p->pdev->dev, "unbind drc 0x%x\n", p->drc_index);

	/* NB: unbind has the same retry requirements as drc_pmem_bind() */
	do {

		/* Unbind of all SCM resources associated with drcIndex */
		rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC,
				 p->drc_index, token);
		token = ret[0];

		/* Check if we are stalled for some time */
		if (H_IS_LONG_BUSY(rc)) {
			msleep(get_longbusy_msecs(rc));
			rc = H_BUSY;
		} else if (rc == H_BUSY) {
			cond_resched();
		}

	} while (rc == H_BUSY);

	if (rc)
		dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
	else
		dev_dbg(&p->pdev->dev, "unbind drc 0x%x complete\n",
			p->drc_index);

	return;
}

static int drc_pmem_query_n_bind(struct papr_scm_priv *p)
{
	unsigned long start_addr;
	unsigned long end_addr;
	unsigned long ret[PLPAR_HCALL_BUFSIZE];
	int64_t rc;


	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
			 p->drc_index, 0);
	if (rc)
		goto err_out;
	start_addr = ret[0];

	/* Make sure the full region is bound. */
	rc = plpar_hcall(H_SCM_QUERY_BLOCK_MEM_BINDING, ret,
			 p->drc_index, p->blocks - 1);
	if (rc)
		goto err_out;
	end_addr = ret[0];

	if ((end_addr - start_addr) != ((p->blocks - 1) * p->block_size))
		goto err_out;

	p->bound_addr = start_addr;
	dev_dbg(&p->pdev->dev, "bound drc 0x%x to 0x%lx\n", p->drc_index, start_addr);
	return rc;

err_out:
	dev_info(&p->pdev->dev,
		 "Failed to query, trying an unbind followed by bind");
	drc_pmem_unbind(p);
	return drc_pmem_bind(p);
}

/*
 * Query the Dimm performance stats from PHYP and copy them (if returned) to
 * provided struct papr_scm_perf_stats instance 'stats' that can hold atleast
 * (num_stats + header) bytes.
 * - If buff_stats == NULL the return value is the size in bytes of the buffer
 * needed to hold all supported performance-statistics.
 * - If buff_stats != NULL and num_stats == 0 then we copy all known
 * performance-statistics to 'buff_stat' and expect to be large enough to
 * hold them.
 * - if buff_stats != NULL and num_stats > 0 then copy the requested
 * performance-statistics to buff_stats.
 */
static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p,
				    struct papr_scm_perf_stats *buff_stats,
				    unsigned int num_stats)
{
	unsigned long ret[PLPAR_HCALL_BUFSIZE];
	size_t size;
	s64 rc;

	/* Setup the out buffer */
	if (buff_stats) {
		memcpy(buff_stats->eye_catcher,
		       PAPR_SCM_PERF_STATS_EYECATCHER, 8);
		buff_stats->stats_version =
			cpu_to_be32(PAPR_SCM_PERF_STATS_VERSION);
		buff_stats->num_statistics =
			cpu_to_be32(num_stats);

		/*
		 * Calculate the buffer size based on num-stats provided
		 * or use the prefetched max buffer length
		 */
		if (num_stats)
			/* Calculate size from the num_stats */
			size = sizeof(struct papr_scm_perf_stats) +
				num_stats * sizeof(struct papr_scm_perf_stat);
		else
			size = p->stat_buffer_len;
	} else {
		/* In case of no out buffer ignore the size */
		size = 0;
	}

	/* Do the HCALL asking PHYP for info */
	rc = plpar_hcall(H_SCM_PERFORMANCE_STATS, ret, p->drc_index,
			 buff_stats ? virt_to_phys(buff_stats) : 0,
			 size);

	/* Check if the error was due to an unknown stat-id */
	if (rc == H_PARTIAL) {
		dev_err(&p->pdev->dev,
			"Unknown performance stats, Err:0x%016lX\n", ret[0]);
		return -ENOENT;
	} else if (rc == H_AUTHORITY) {
		dev_info(&p->pdev->dev,
			 "Permission denied while accessing performance stats");
		return -EPERM;
	} else if (rc == H_UNSUPPORTED) {
		dev_dbg(&p->pdev->dev, "Performance stats unsupported\n");
		return -EOPNOTSUPP;
	} else if (rc != H_SUCCESS) {
		dev_err(&p->pdev->dev,
			"Failed to query performance stats, Err:%lld\n", rc);
		return -EIO;

	} else if (!size) {
		/* Handle case where stat buffer size was requested */
		dev_dbg(&p->pdev->dev,
			"Performance stats size %ld\n", ret[0]);
		return ret[0];
	}

	/* Successfully fetched the requested stats from phyp */
	dev_dbg(&p->pdev->dev,
		"Performance stats returned %d stats\n",
		be32_to_cpu(buff_stats->num_statistics));
	return 0;
}

#ifdef CONFIG_PERF_EVENTS
#define to_nvdimm_pmu(_pmu)	container_of(_pmu, struct nvdimm_pmu, pmu)

static const char * const nvdimm_events_map[] = {
	[1] = "CtlResCt",
	[2] = "CtlResTm",
	[3] = "PonSecs ",
	[4] = "MemLife ",
	[5] = "CritRscU",
	[6] = "HostLCnt",
	[7] = "HostSCnt",
	[8] = "HostSDur",
	[9] = "HostLDur",
	[10] = "MedRCnt ",
	[11] = "MedWCnt ",
	[12] = "MedRDur ",
	[13] = "MedWDur ",
	[14] = "CchRHCnt",
	[15] = "CchWHCnt",
	[16] = "FastWCnt",
};

static int papr_scm_pmu_get_value(struct perf_event *event, struct device *dev, u64 *count)
{
	struct papr_scm_perf_stat *stat;
	struct papr_scm_perf_stats *stats;
	struct papr_scm_priv *p = dev_get_drvdata(dev);
	int rc, size;

	/* Invalid eventcode */
	if (event->attr.config == 0 || event->attr.config >= ARRAY_SIZE(nvdimm_events_map))
		return -EINVAL;

	/* Allocate request buffer enough to hold single performance stat */
	size = sizeof(struct papr_scm_perf_stats) +
		sizeof(struct papr_scm_perf_stat);

	if (!p)
		return -EINVAL;

	stats = kzalloc(size, GFP_KERNEL);
	if (!stats)
		return -ENOMEM;

	stat = &stats->scm_statistic[0];
	memcpy(&stat->stat_id,
	       nvdimm_events_map[event->attr.config],
		sizeof(stat->stat_id));
	stat->stat_val = 0;

	rc = drc_pmem_query_stats(p, stats, 1);
	if (rc < 0) {
		kfree(stats);
		return rc;
	}

	*count = be64_to_cpu(stat->stat_val);
	kfree(stats);
	return 0;
}

static int papr_scm_pmu_event_init(struct perf_event *event)
{
	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);
	struct papr_scm_priv *p;

	if (!nd_pmu)
		return -EINVAL;

	/* test the event attr type for PMU enumeration */
	if (event->attr.type != event->pmu->type)
		return -ENOENT;

	/* it does not support event sampling mode */
	if (is_sampling_event(event))
		return -EOPNOTSUPP;

	/* no branch sampling */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	p = (struct papr_scm_priv *)nd_pmu->dev->driver_data;
	if (!p)
		return -EINVAL;

	/* Invalid eventcode */
	if (event->attr.config == 0 || event->attr.config > 16)
		return -EINVAL;

	return 0;
}

static int papr_scm_pmu_add(struct perf_event *event, int flags)
{
	u64 count;
	int rc;
	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);

	if (!nd_pmu)
		return -EINVAL;

	if (flags & PERF_EF_START) {
		rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &count);
		if (rc)
			return rc;

		local64_set(&event->hw.prev_count, count);
	}

	return 0;
}

static void papr_scm_pmu_read(struct perf_event *event)
{
	u64 prev, now;
	int rc;
	struct nvdimm_pmu *nd_pmu = to_nvdimm_pmu(event->pmu);

	if (!nd_pmu)
		return;

	rc = papr_scm_pmu_get_value(event, nd_pmu->dev, &now);
	if (rc)
		return;

	prev = local64_xchg(&event->hw.prev_count, now);
	local64_add(now - prev, &event->count);
}

static void papr_scm_pmu_del(struct perf_event *event, int flags)
{
	papr_scm_pmu_read(event);
}

static void papr_scm_pmu_register(struct papr_scm_priv *p)
{
	struct nvdimm_pmu *nd_pmu;
	int rc, nodeid;

	nd_pmu = kzalloc(sizeof(*nd_pmu), GFP_KERNEL);
	if (!nd_pmu) {
		rc = -ENOMEM;
		goto pmu_err_print;
	}

	if (!p->stat_buffer_len) {
		rc = -ENOENT;
		goto pmu_check_events_err;
	}

	nd_pmu->pmu.task_ctx_nr = perf_invalid_context;
	nd_pmu->pmu.name = nvdimm_name(p->nvdimm);
	nd_pmu->pmu.event_init = papr_scm_pmu_event_init;
	nd_pmu->pmu.read = papr_scm_pmu_read;
	nd_pmu->pmu.add = papr_scm_pmu_add;
	nd_pmu->pmu.del = papr_scm_pmu_del;

	nd_pmu->pmu.capabilities = PERF_PMU_CAP_NO_INTERRUPT |
				PERF_PMU_CAP_NO_EXCLUDE;

	/*updating the cpumask variable */
	nodeid = numa_map_to_online_node(dev_to_node(&p->pdev->dev));
	nd_pmu->arch_cpumask = *cpumask_of_node(nodeid);

	rc = register_nvdimm_pmu(nd_pmu, p->pdev);
	if (rc)
		goto pmu_check_events_err;

	/*
	 * Set archdata.priv value to nvdimm_pmu structure, to handle the
	 * unregistering of pmu device.
	 */
	p->pdev->archdata.priv = nd_pmu;
	return;

pmu_check_events_err:
	kfree(nd_pmu);
pmu_err_print:
	dev_info(&p->pdev->dev, "nvdimm pmu didn't register rc=%d\n", rc);
}

#else
static void papr_scm_pmu_register(struct papr_scm_priv *p) { }
#endif

/*
 * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the
 * health information.
 */
static int __drc_pmem_query_health(struct papr_scm_priv *p)
{
	unsigned long ret[PLPAR_HCALL_BUFSIZE];
	u64 bitmap = 0;
	long rc;

	/* issue the hcall */
	rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index);
	if (rc == H_SUCCESS)
		bitmap = ret[0] & ret[1];
	else if (rc == H_FUNCTION)
		dev_info_once(&p->pdev->dev,
			      "Hcall H_SCM_HEALTH not implemented, assuming empty health bitmap");
	else {

		dev_err(&p->pdev->dev,
			"Failed to query health information, Err:%ld\n", rc);
		return -ENXIO;
	}

	p->lasthealth_jiffies = jiffies;
	/* Allow injecting specific health bits via inject mask. */
	if (p->health_bitmap_inject_mask)
		bitmap = (bitmap & ~p->health_bitmap_inject_mask) |
			p->health_bitmap_inject_mask;
	WRITE_ONCE(p->health_bitmap, bitmap);
	dev_dbg(&p->pdev->dev,
		"Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n",
		ret[0], ret[1]);

	return 0;
}

/* Min interval in seconds for assuming stable dimm health */
#define MIN_HEALTH_QUERY_INTERVAL 60

/* Query cached health info and if needed call drc_pmem_query_health */
static int drc_pmem_query_health(struct papr_scm_priv *p)
{
	unsigned long cache_timeout;
	int rc;

	/* Protect concurrent modifications to papr_scm_priv */
	rc = mutex_lock_interruptible(&p->health_mutex);
	if (rc)
		return rc;

	/* Jiffies offset for which the health data is assumed to be same */
	cache_timeout = p->lasthealth_jiffies +
		msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);

	/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
	if (time_after(jiffies, cache_timeout))
		rc = __drc_pmem_query_health(p);
	else
		/* Assume cached health data is valid */
		rc = 0;

	mutex_unlock(&p->health_mutex);
	return rc;
}

static int papr_scm_meta_get(struct papr_scm_priv *p,
			     struct nd_cmd_get_config_data_hdr *hdr)
{
	unsigned long data[PLPAR_HCALL_BUFSIZE];
	unsigned long offset, data_offset;
	int len, read;
	int64_t ret;

	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
		return -EINVAL;

	for (len = hdr->in_length; len; len -= read) {

		data_offset = hdr->in_length - len;
		offset = hdr->in_offset + data_offset;

		if (len >= 8)
			read = 8;
		else if (len >= 4)
			read = 4;
		else if (len >= 2)
			read = 2;
		else
			read = 1;

		ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
				  offset, read);

		if (ret == H_PARAMETER) /* bad DRC index */
			return -ENODEV;
		if (ret)
			return -EINVAL; /* other invalid parameter */

		switch (read) {
		case 8:
			*(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
			break;
		case 4:
			*(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
			break;

		case 2:
			*(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
			break;

		case 1:
			*(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
			break;
		}
	}
	return 0;
}

static int papr_scm_meta_set(struct papr_scm_priv *p,
			     struct nd_cmd_set_config_hdr *hdr)
{
	unsigned long offset, data_offset;
	int len, wrote;
	unsigned long data;
	__be64 data_be;
	int64_t ret;

	if ((hdr->in_offset + hdr->in_length) > p->metadata_size)
		return -EINVAL;

	for (len = hdr->in_length; len; len -= wrote) {

		data_offset = hdr->in_length - len;
		offset = hdr->in_offset + data_offset;

		if (len >= 8) {
			data = *(uint64_t *)(hdr->in_buf + data_offset);
			data_be = cpu_to_be64(data);
			wrote = 8;
		} else if (len >= 4) {
			data = *(uint32_t *)(hdr->in_buf + data_offset);
			data &= 0xffffffff;
			data_be = cpu_to_be32(data);
			wrote = 4;
		} else if (len >= 2) {
			data = *(uint16_t *)(hdr->in_buf + data_offset);
			data &= 0xffff;
			data_be = cpu_to_be16(data);
			wrote = 2;
		} else {
			data_be = *(uint8_t *)(hdr->in_buf + data_offset);
			data_be &= 0xff;
			wrote = 1;
		}

		ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
					 offset, data_be, wrote);
		if (ret == H_PARAMETER) /* bad DRC index */
			return -ENODEV;
		if (ret)
			return -EINVAL; /* other invalid parameter */
	}

	return 0;
}

/*
 * Do a sanity checks on the inputs args to dimm-control function and return
 * '0' if valid. Validation of PDSM payloads happens later in
 * papr_scm_service_pdsm.
 */
static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf,
			unsigned int buf_len)
{
	unsigned long cmd_mask = PAPR_SCM_DIMM_CMD_MASK;
	struct nd_cmd_pkg *nd_cmd;
	struct papr_scm_priv *p;
	enum papr_pdsm pdsm;

	/* Only dimm-specific calls are supported atm */
	if (!nvdimm)
		return -EINVAL;

	/* get the provider data from struct nvdimm */
	p = nvdimm_provider_data(nvdimm);

	if (!test_bit(cmd, &cmd_mask)) {
		dev_dbg(&p->pdev->dev, "Unsupported cmd=%u\n", cmd);
		return -EINVAL;
	}

	/* For CMD_CALL verify pdsm request */
	if (cmd == ND_CMD_CALL) {
		/* Verify the envelope and envelop size */
		if (!buf ||
		    buf_len < (sizeof(struct nd_cmd_pkg) + ND_PDSM_HDR_SIZE)) {
			dev_dbg(&p->pdev->dev, "Invalid pkg size=%u\n",
				buf_len);
			return -EINVAL;
		}

		/* Verify that the nd_cmd_pkg.nd_family is correct */
		nd_cmd = (struct nd_cmd_pkg *)buf;

		if (nd_cmd->nd_family != NVDIMM_FAMILY_PAPR) {
			dev_dbg(&p->pdev->dev, "Invalid pkg family=0x%llx\n",
				nd_cmd->nd_family);
			return -EINVAL;
		}

		pdsm = (enum papr_pdsm)nd_cmd->nd_command;

		/* Verify if the pdsm command is valid */
		if (pdsm <= PAPR_PDSM_MIN || pdsm >= PAPR_PDSM_MAX) {
			dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid PDSM\n",
				pdsm);
			return -EINVAL;
		}

		/* Have enough space to hold returned 'nd_pkg_pdsm' header */
		if (nd_cmd->nd_size_out < ND_PDSM_HDR_SIZE) {
			dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid payload\n",
				pdsm);
			return -EINVAL;
		}
	}

	/* Let the command be further processed */
	return 0;
}

static int papr_pdsm_fuel_gauge(struct papr_scm_priv *p,
				union nd_pdsm_payload *payload)
{
	int rc, size;
	u64 statval;
	struct papr_scm_perf_stat *stat;
	struct papr_scm_perf_stats *stats;

	/* Silently fail if fetching performance metrics isn't  supported */
	if (!p->stat_buffer_len)
		return 0;

	/* Allocate request buffer enough to hold single performance stat */
	size = sizeof(struct papr_scm_perf_stats) +
		sizeof(struct papr_scm_perf_stat);

	stats = kzalloc(size, GFP_KERNEL);
	if (!stats)
		return -ENOMEM;

	stat = &stats->scm_statistic[0];
	memcpy(&stat->stat_id, "MemLife ", sizeof(stat->stat_id));
	stat->stat_val = 0;

	/* Fetch the fuel gauge and populate it in payload */
	rc = drc_pmem_query_stats(p, stats, 1);
	if (rc < 0) {
		dev_dbg(&p->pdev->dev, "Err(%d) fetching fuel gauge\n", rc);
		goto free_stats;
	}

	statval = be64_to_cpu(stat->stat_val);
	dev_dbg(&p->pdev->dev,
		"Fetched fuel-gauge %llu", statval);
	payload->health.extension_flags |=
		PDSM_DIMM_HEALTH_RUN_GAUGE_VALID;
	payload->health.dimm_fuel_gauge = statval;

	rc = sizeof(struct nd_papr_pdsm_health);

free_stats:
	kfree(stats);
	return rc;
}

/* Add the dirty-shutdown-counter value to the pdsm */
static int papr_pdsm_dsc(struct papr_scm_priv *p,
			 union nd_pdsm_payload *payload)
{
	payload->health.extension_flags |= PDSM_DIMM_DSC_VALID;
	payload->health.dimm_dsc = p->dirty_shutdown_counter;

	return sizeof(struct nd_papr_pdsm_health);
}

/* Fetch the DIMM health info and populate it in provided package. */
static int papr_pdsm_health(struct papr_scm_priv *p,
			    union nd_pdsm_payload *payload)
{
	int rc;

	/* Ensure dimm health mutex is taken preventing concurrent access */
	rc = mutex_lock_interruptible(&p->health_mutex);
	if (rc)
		goto out;

	/* Always fetch upto date dimm health data ignoring cached values */
	rc = __drc_pmem_query_health(p);
	if (rc) {
		mutex_unlock(&p->health_mutex);
		goto out;
	}

	/* update health struct with various flags derived from health bitmap */
	payload->health = (struct nd_papr_pdsm_health) {
		.extension_flags = 0,
		.dimm_unarmed = !!(p->health_bitmap & PAPR_PMEM_UNARMED_MASK),
		.dimm_bad_shutdown = !!(p->health_bitmap & PAPR_PMEM_BAD_SHUTDOWN_MASK),
		.dimm_bad_restore = !!(p->health_bitmap & PAPR_PMEM_BAD_RESTORE_MASK),
		.dimm_scrubbed = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED),
		.dimm_locked = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED),
		.dimm_encrypted = !!(p->health_bitmap & PAPR_PMEM_ENCRYPTED),
		.dimm_health = PAPR_PDSM_DIMM_HEALTHY,
	};

	/* Update field dimm_health based on health_bitmap flags */
	if (p->health_bitmap & PAPR_PMEM_HEALTH_FATAL)
		payload->health.dimm_health = PAPR_PDSM_DIMM_FATAL;
	else if (p->health_bitmap & PAPR_PMEM_HEALTH_CRITICAL)
		payload->health.dimm_health = PAPR_PDSM_DIMM_CRITICAL;
	else if (p->health_bitmap & PAPR_PMEM_HEALTH_UNHEALTHY)
		payload->health.dimm_health = PAPR_PDSM_DIMM_UNHEALTHY;

	/* struct populated hence can release the mutex now */
	mutex_unlock(&p->health_mutex);

	/* Populate the fuel gauge meter in the payload */
	papr_pdsm_fuel_gauge(p, payload);
	/* Populate the dirty-shutdown-counter field */
	papr_pdsm_dsc(p, payload);

	rc = sizeof(struct nd_papr_pdsm_health);

out:
	return rc;
}

/* Inject a smart error Add the dirty-shutdown-counter value to the pdsm */
static int papr_pdsm_smart_inject(struct papr_scm_priv *p,
				  union nd_pdsm_payload *payload)
{
	int rc;
	u32 supported_flags = 0;
	u64 inject_mask = 0, clear_mask = 0;
	u64 mask;

	/* Check for individual smart error flags and update inject/clear masks */
	if (payload->smart_inject.flags & PDSM_SMART_INJECT_HEALTH_FATAL) {
		supported_flags |= PDSM_SMART_INJECT_HEALTH_FATAL;
		if (payload->smart_inject.fatal_enable)
			inject_mask |= PAPR_PMEM_HEALTH_FATAL;
		else
			clear_mask |= PAPR_PMEM_HEALTH_FATAL;
	}

	if (payload->smart_inject.flags & PDSM_SMART_INJECT_BAD_SHUTDOWN) {
		supported_flags |= PDSM_SMART_INJECT_BAD_SHUTDOWN;
		if (payload->smart_inject.unsafe_shutdown_enable)
			inject_mask |= PAPR_PMEM_SHUTDOWN_DIRTY;
		else
			clear_mask |= PAPR_PMEM_SHUTDOWN_DIRTY;
	}

	dev_dbg(&p->pdev->dev, "[Smart-inject] inject_mask=%#llx clear_mask=%#llx\n",
		inject_mask, clear_mask);

	/* Prevent concurrent access to dimm health bitmap related members */
	rc = mutex_lock_interruptible(&p->health_mutex);
	if (rc)
		return rc;

	/* Use inject/clear masks to set health_bitmap_inject_mask */
	mask = READ_ONCE(p->health_bitmap_inject_mask);
	mask = (mask & ~clear_mask) | inject_mask;
	WRITE_ONCE(p->health_bitmap_inject_mask, mask);

	/* Invalidate cached health bitmap */
	p->lasthealth_jiffies = 0;

	mutex_unlock(&p->health_mutex);

	/* Return the supported flags back to userspace */
	payload->smart_inject.flags = supported_flags;

	return sizeof(struct nd_papr_pdsm_health);
}

/*
 * 'struct pdsm_cmd_desc'
 * Identifies supported PDSMs' expected length of in/out payloads
 * and pdsm service function.
 *
 * size_in	: Size of input payload if any in the PDSM request.
 * size_out	: Size of output payload if any in the PDSM request.
 * service	: Service function for the PDSM request. Return semantics:
 *		  rc < 0 : Error servicing PDSM and rc indicates the error.
 *		  rc >=0 : Serviced successfully and 'rc' indicate number of
 *			bytes written to payload.
 */
struct pdsm_cmd_desc {
	u32 size_in;
	u32 size_out;
	int (*service)(struct papr_scm_priv *dimm,
		       union nd_pdsm_payload *payload);
};

/* Holds all supported PDSMs' command descriptors */
static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = {
	[PAPR_PDSM_MIN] = {
		.size_in = 0,
		.size_out = 0,
		.service = NULL,
	},
	/* New PDSM command descriptors to be added below */

	[PAPR_PDSM_HEALTH] = {
		.size_in = 0,
		.size_out = sizeof(struct nd_papr_pdsm_health),
		.service = papr_pdsm_health,
	},

	[PAPR_PDSM_SMART_INJECT] = {
		.size_in = sizeof(struct nd_papr_pdsm_smart_inject),
		.size_out = sizeof(struct nd_papr_pdsm_smart_inject),
		.service = papr_pdsm_smart_inject,
	},
	/* Empty */
	[PAPR_PDSM_MAX] = {
		.size_in = 0,
		.size_out = 0,
		.service = NULL,
	},
};

/* Given a valid pdsm cmd return its command descriptor else return NULL */
static inline const struct pdsm_cmd_desc *pdsm_cmd_desc(enum papr_pdsm cmd)
{
	if (cmd >= 0 || cmd < ARRAY_SIZE(__pdsm_cmd_descriptors))
		return &__pdsm_cmd_descriptors[cmd];

	return NULL;
}

/*
 * For a given pdsm request call an appropriate service function.
 * Returns errors if any while handling the pdsm command package.
 */
static int papr_scm_service_pdsm(struct papr_scm_priv *p,
				 struct nd_cmd_pkg *pkg)
{
	/* Get the PDSM header and PDSM command */
	struct nd_pkg_pdsm *pdsm_pkg = (struct nd_pkg_pdsm *)pkg->nd_payload;
	enum papr_pdsm pdsm = (enum papr_pdsm)pkg->nd_command;
	const struct pdsm_cmd_desc *pdsc;
	int rc;

	/* Fetch corresponding pdsm descriptor for validation and servicing */
	pdsc = pdsm_cmd_desc(pdsm);

	/* Validate pdsm descriptor */
	/* Ensure that reserved fields are 0 */
	if (pdsm_pkg->reserved[0] || pdsm_pkg->reserved[1]) {
		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid reserved field\n",
			pdsm);
		return -EINVAL;
	}

	/* If pdsm expects some input, then ensure that the size_in matches */
	if (pdsc->size_in &&
	    pkg->nd_size_in != (pdsc->size_in + ND_PDSM_HDR_SIZE)) {
		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_in=%d\n",
			pdsm, pkg->nd_size_in);
		return -EINVAL;
	}

	/* If pdsm wants to return data, then ensure that  size_out matches */
	if (pdsc->size_out &&
	    pkg->nd_size_out != (pdsc->size_out + ND_PDSM_HDR_SIZE)) {
		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_out=%d\n",
			pdsm, pkg->nd_size_out);
		return -EINVAL;
	}

	/* Service the pdsm */
	if (pdsc->service) {
		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Servicing..\n", pdsm);

		rc = pdsc->service(p, &pdsm_pkg->payload);

		if (rc < 0) {
			/* error encountered while servicing pdsm */
			pdsm_pkg->cmd_status = rc;
			pkg->nd_fw_size = ND_PDSM_HDR_SIZE;
		} else {
			/* pdsm serviced and 'rc' bytes written to payload */
			pdsm_pkg->cmd_status = 0;
			pkg->nd_fw_size = ND_PDSM_HDR_SIZE + rc;
		}
	} else {
		dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Unsupported PDSM request\n",
			pdsm);
		pdsm_pkg->cmd_status = -ENOENT;
		pkg->nd_fw_size = ND_PDSM_HDR_SIZE;
	}

	return pdsm_pkg->cmd_status;
}

static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
			  struct nvdimm *nvdimm, unsigned int cmd, void *buf,
			  unsigned int buf_len, int *cmd_rc)
{
	struct nd_cmd_get_config_size *get_size_hdr;
	struct nd_cmd_pkg *call_pkg = NULL;
	struct papr_scm_priv *p;
	int rc;

	rc = is_cmd_valid(nvdimm, cmd, buf, buf_len);
	if (rc) {
		pr_debug("Invalid cmd=0x%x. Err=%d\n", cmd, rc);
		return rc;
	}

	/* Use a local variable in case cmd_rc pointer is NULL */
	if (!cmd_rc)
		cmd_rc = &rc;

	p = nvdimm_provider_data(nvdimm);

	switch (cmd) {
	case ND_CMD_GET_CONFIG_SIZE:
		get_size_hdr = buf;

		get_size_hdr->status = 0;
		get_size_hdr->max_xfer = 8;
		get_size_hdr->config_size = p->metadata_size;
		*cmd_rc = 0;
		break;

	case ND_CMD_GET_CONFIG_DATA:
		*cmd_rc = papr_scm_meta_get(p, buf);
		break;

	case ND_CMD_SET_CONFIG_DATA:
		*cmd_rc = papr_scm_meta_set(p, buf);
		break;

	case ND_CMD_CALL:
		call_pkg = (struct nd_cmd_pkg *)buf;
		*cmd_rc = papr_scm_service_pdsm(p, call_pkg);
		break;

	default:
		dev_dbg(&p->pdev->dev, "Unknown command = %d\n", cmd);
		return -EINVAL;
	}

	dev_dbg(&p->pdev->dev, "returned with cmd_rc = %d\n", *cmd_rc);

	return 0;
}

static ssize_t health_bitmap_inject_show(struct device *dev,
					 struct device_attribute *attr,
					 char *buf)
{
	struct nvdimm *dimm = to_nvdimm(dev);
	struct papr_scm_priv *p = nvdimm_provider_data(dimm);

	return sprintf(buf, "%#llx\n",
		       READ_ONCE(p->health_bitmap_inject_mask));
}

static DEVICE_ATTR_ADMIN_RO(health_bitmap_inject);

static ssize_t perf_stats_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	int index;
	ssize_t rc;
	struct seq_buf s;
	struct papr_scm_perf_stat *stat;
	struct papr_scm_perf_stats *stats;
	struct nvdimm *dimm = to_nvdimm(dev);
	struct papr_scm_priv *p = nvdimm_provider_data(dimm);

	if (!p->stat_buffer_len)
		return -ENOENT;

	/* Allocate the buffer for phyp where stats are written */
	stats = kzalloc(p->stat_buffer_len, GFP_KERNEL);
	if (!stats)
		return -ENOMEM;

	/* Ask phyp to return all dimm perf stats */
	rc = drc_pmem_query_stats(p, stats, 0);
	if (rc)
		goto free_stats;
	/*
	 * Go through the returned output buffer and print stats and
	 * values. Since stat_id is essentially a char string of
	 * 8 bytes, simply use the string format specifier to print it.
	 */
	seq_buf_init(&s, buf, PAGE_SIZE);
	for (index = 0, stat = stats->scm_statistic;
	     index < be32_to_cpu(stats->num_statistics);
	     ++index, ++stat) {
		seq_buf_printf(&s, "%.8s = 0x%016llX\n",
			       stat->stat_id,
			       be64_to_cpu(stat->stat_val));
	}

free_stats:
	kfree(stats);
	return rc ? rc : (ssize_t)seq_buf_used(&s);
}
static DEVICE_ATTR_ADMIN_RO(perf_stats);

static ssize_t flags_show(struct device *dev,
			  struct device_attribute *attr, char *buf)
{
	struct nvdimm *dimm = to_nvdimm(dev);
	struct papr_scm_priv *p = nvdimm_provider_data(dimm);
	struct seq_buf s;
	u64 health;
	int rc;

	rc = drc_pmem_query_health(p);
	if (rc)
		return rc;

	/* Copy health_bitmap locally, check masks & update out buffer */
	health = READ_ONCE(p->health_bitmap);

	seq_buf_init(&s, buf, PAGE_SIZE);
	if (health & PAPR_PMEM_UNARMED_MASK)
		seq_buf_printf(&s, "not_armed ");

	if (health & PAPR_PMEM_BAD_SHUTDOWN_MASK)
		seq_buf_printf(&s, "flush_fail ");

	if (health & PAPR_PMEM_BAD_RESTORE_MASK)
		seq_buf_printf(&s, "restore_fail ");

	if (health & PAPR_PMEM_ENCRYPTED)
		seq_buf_printf(&s, "encrypted ");

	if (health & PAPR_PMEM_SMART_EVENT_MASK)
		seq_buf_printf(&s, "smart_notify ");

	if (health & PAPR_PMEM_SCRUBBED_AND_LOCKED)
		seq_buf_printf(&s, "scrubbed locked ");

	if (seq_buf_used(&s))
		seq_buf_printf(&s, "\n");

	return seq_buf_used(&s);
}
DEVICE_ATTR_RO(flags);

static ssize_t dirty_shutdown_show(struct device *dev,
			  struct device_attribute *attr, char *buf)
{
	struct nvdimm *dimm = to_nvdimm(dev);
	struct papr_scm_priv *p = nvdimm_provider_data(dimm);

	return sysfs_emit(buf, "%llu\n", p->dirty_shutdown_counter);
}
DEVICE_ATTR_RO(dirty_shutdown);

static umode_t papr_nd_attribute_visible(struct kobject *kobj,
					 struct attribute *attr, int n)
{
	struct device *dev = kobj_to_dev(kobj);
	struct nvdimm *nvdimm = to_nvdimm(dev);
	struct papr_scm_priv *p = nvdimm_provider_data(nvdimm);

	/* For if perf-stats not available remove perf_stats sysfs */
	if (attr == &dev_attr_perf_stats.attr && p->stat_buffer_len == 0)
		return 0;

	return attr->mode;
}

/* papr_scm specific dimm attributes */
static struct attribute *papr_nd_attributes[] = {
	&dev_attr_flags.attr,
	&dev_attr_perf_stats.attr,
	&dev_attr_dirty_shutdown.attr,
	&dev_attr_health_bitmap_inject.attr,
	NULL,
};

static const struct attribute_group papr_nd_attribute_group = {
	.name = "papr",
	.is_visible = papr_nd_attribute_visible,
	.attrs = papr_nd_attributes,
};

static const struct attribute_group *papr_nd_attr_groups[] = {
	&papr_nd_attribute_group,
	NULL,
};

static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
{
	struct device *dev = &p->pdev->dev;
	struct nd_mapping_desc mapping;
	struct nd_region_desc ndr_desc;
	unsigned long dimm_flags;
	int target_nid, online_nid;

	p->bus_desc.ndctl = papr_scm_ndctl;
	p->bus_desc.module = THIS_MODULE;
	p->bus_desc.of_node = p->pdev->dev.of_node;
	p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL);

	/* Set the dimm command family mask to accept PDSMs */
	set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask);

	if (!p->bus_desc.provider_name)
		return -ENOMEM;

	p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
	if (!p->bus) {
		dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
		kfree(p->bus_desc.provider_name);
		return -ENXIO;
	}

	dimm_flags = 0;
	set_bit(NDD_LABELING, &dimm_flags);

	/*
	 * Check if the nvdimm is unarmed. No locking needed as we are still
	 * initializing. Ignore error encountered if any.
	 */
	__drc_pmem_query_health(p);

	if (p->health_bitmap & PAPR_PMEM_UNARMED_MASK)
		set_bit(NDD_UNARMED, &dimm_flags);

	p->nvdimm = nvdimm_create(p->bus, p, papr_nd_attr_groups,
				  dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL);
	if (!p->nvdimm) {
		dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn);
		goto err;
	}

	if (nvdimm_bus_check_dimm_count(p->bus, 1))
		goto err;

	/* now add the region */

	memset(&mapping, 0, sizeof(mapping));
	mapping.nvdimm = p->nvdimm;
	mapping.start = 0;
	mapping.size = p->blocks * p->block_size; // XXX: potential overflow?

	memset(&ndr_desc, 0, sizeof(ndr_desc));
	target_nid = dev_to_node(&p->pdev->dev);
	online_nid = numa_map_to_online_node(target_nid);
	ndr_desc.numa_node = online_nid;
	ndr_desc.target_node = target_nid;
	ndr_desc.res = &p->res;
	ndr_desc.of_node = p->dn;
	ndr_desc.provider_data = p;
	ndr_desc.mapping = &mapping;
	ndr_desc.num_mappings = 1;
	ndr_desc.nd_set = &p->nd_set;

	if (p->hcall_flush_required) {
		set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
		ndr_desc.flush = papr_scm_pmem_flush;
	}

	if (p->is_volatile)
		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
	else {
		set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
		p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
	}
	if (!p->region) {
		dev_err(dev, "Error registering region %pR from %pOF\n",
				ndr_desc.res, p->dn);
		goto err;
	}
	if (target_nid != online_nid)
		dev_info(dev, "Region registered with target node %d and online node %d",
			 target_nid, online_nid);

	mutex_lock(&papr_ndr_lock);
	list_add_tail(&p->region_list, &papr_nd_regions);
	mutex_unlock(&papr_ndr_lock);

	return 0;

err:	nvdimm_bus_unregister(p->bus);
	kfree(p->bus_desc.provider_name);
	return -ENXIO;
}

static void papr_scm_add_badblock(struct nd_region *region,
				  struct nvdimm_bus *bus, u64 phys_addr)
{
	u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);

	if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) {
		pr_err("Bad block registration for 0x%llx failed\n", phys_addr);
		return;
	}

	pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n",
		 aligned_addr, aligned_addr + L1_CACHE_BYTES);

	nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON);
}

static int handle_mce_ue(struct notifier_block *nb, unsigned long val,
			 void *data)
{
	struct machine_check_event *evt = data;
	struct papr_scm_priv *p;
	u64 phys_addr;
	bool found = false;

	if (evt->error_type != MCE_ERROR_TYPE_UE)
		return NOTIFY_DONE;

	if (list_empty(&papr_nd_regions))
		return NOTIFY_DONE;

	/*
	 * The physical address obtained here is PAGE_SIZE aligned, so get the
	 * exact address from the effective address
	 */
	phys_addr = evt->u.ue_error.physical_address +
			(evt->u.ue_error.effective_address & ~PAGE_MASK);

	if (!evt->u.ue_error.physical_address_provided ||
	    !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT)))
		return NOTIFY_DONE;

	/* mce notifier is called from a process context, so mutex is safe */
	mutex_lock(&papr_ndr_lock);
	list_for_each_entry(p, &papr_nd_regions, region_list) {
		if (phys_addr >= p->res.start && phys_addr <= p->res.end) {
			found = true;
			break;
		}
	}

	if (found)
		papr_scm_add_badblock(p->region, p->bus, phys_addr);

	mutex_unlock(&papr_ndr_lock);

	return found ? NOTIFY_OK : NOTIFY_DONE;
}

static struct notifier_block mce_ue_nb = {
	.notifier_call = handle_mce_ue
};

static int papr_scm_probe(struct platform_device *pdev)
{
	struct device_node *dn = pdev->dev.of_node;
	u32 drc_index, metadata_size;
	u64 blocks, block_size;
	struct papr_scm_priv *p;
	u8 uuid_raw[UUID_SIZE];
	const char *uuid_str;
	ssize_t stat_size;
	uuid_t uuid;
	int rc;

	/* check we have all the required DT properties */
	if (of_property_read_u32(dn, "ibm,my-drc-index", &drc_index)) {
		dev_err(&pdev->dev, "%pOF: missing drc-index!\n", dn);
		return -ENODEV;
	}

	if (of_property_read_u64(dn, "ibm,block-size", &block_size)) {
		dev_err(&pdev->dev, "%pOF: missing block-size!\n", dn);
		return -ENODEV;
	}

	if (of_property_read_u64(dn, "ibm,number-of-blocks", &blocks)) {
		dev_err(&pdev->dev, "%pOF: missing number-of-blocks!\n", dn);
		return -ENODEV;
	}

	if (of_property_read_string(dn, "ibm,unit-guid", &uuid_str)) {
		dev_err(&pdev->dev, "%pOF: missing unit-guid!\n", dn);
		return -ENODEV;
	}

	/*
	 * open firmware platform device create won't update the NUMA 
	 * distance table. For PAPR SCM devices we use numa_map_to_online_node()
	 * to find the nearest online NUMA node and that requires correct
	 * distance table information.
	 */
	update_numa_distance(dn);

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

	/* Initialize the dimm mutex */
	mutex_init(&p->health_mutex);

	/* optional DT properties */
	of_property_read_u32(dn, "ibm,metadata-size", &metadata_size);

	p->dn = dn;
	p->drc_index = drc_index;
	p->block_size = block_size;
	p->blocks = blocks;
	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
	p->hcall_flush_required = of_property_read_bool(dn, "ibm,hcall-flush-required");

	if (of_property_read_u64(dn, "ibm,persistence-failed-count",
				 &p->dirty_shutdown_counter))
		p->dirty_shutdown_counter = 0;

	/* We just need to ensure that set cookies are unique across */
	uuid_parse(uuid_str, &uuid);

	/*
	 * The cookie1 and cookie2 are not really little endian.
	 * We store a raw buffer representation of the
	 * uuid string so that we can compare this with the label
	 * area cookie irrespective of the endian configuration
	 * with which the kernel is built.
	 *
	 * Historically we stored the cookie in the below format.
	 * for a uuid string 72511b67-0b3b-42fd-8d1d-5be3cae8bcaa
	 *	cookie1 was 0xfd423b0b671b5172
	 *	cookie2 was 0xaabce8cae35b1d8d
	 */
	export_uuid(uuid_raw, &uuid);
	p->nd_set.cookie1 = get_unaligned_le64(&uuid_raw[0]);
	p->nd_set.cookie2 = get_unaligned_le64(&uuid_raw[8]);

	/* might be zero */
	p->metadata_size = metadata_size;
	p->pdev = pdev;

	/* request the hypervisor to bind this region to somewhere in memory */
	rc = drc_pmem_bind(p);

	/* If phyp says drc memory still bound then force unbound and retry */
	if (rc == H_OVERLAP)
		rc = drc_pmem_query_n_bind(p);

	if (rc != H_SUCCESS) {
		dev_err(&p->pdev->dev, "bind err: %d\n", rc);
		rc = -ENXIO;
		goto err;
	}

	/* setup the resource for the newly bound range */
	p->res.start = p->bound_addr;
	p->res.end   = p->bound_addr + p->blocks * p->block_size - 1;
	p->res.name  = pdev->name;
	p->res.flags = IORESOURCE_MEM;

	/* Try retrieving the stat buffer and see if its supported */
	stat_size = drc_pmem_query_stats(p, NULL, 0);
	if (stat_size > 0) {
		p->stat_buffer_len = stat_size;
		dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n",
			p->stat_buffer_len);
	}

	rc = papr_scm_nvdimm_init(p);
	if (rc)
		goto err2;

	platform_set_drvdata(pdev, p);
	papr_scm_pmu_register(p);

	return 0;

err2:	drc_pmem_unbind(p);
err:	kfree(p);
	return rc;
}

static void papr_scm_remove(struct platform_device *pdev)
{
	struct papr_scm_priv *p = platform_get_drvdata(pdev);

	mutex_lock(&papr_ndr_lock);
	list_del(&p->region_list);
	mutex_unlock(&papr_ndr_lock);

	nvdimm_bus_unregister(p->bus);
	drc_pmem_unbind(p);

	if (pdev->archdata.priv)
		unregister_nvdimm_pmu(pdev->archdata.priv);

	pdev->archdata.priv = NULL;
	kfree(p->bus_desc.provider_name);
	kfree(p);
}

static const struct of_device_id papr_scm_match[] = {
	{ .compatible = "ibm,pmemory" },
	{ .compatible = "ibm,pmemory-v2" },
	{ },
};

static struct platform_driver papr_scm_driver = {
	.probe = papr_scm_probe,
	.remove_new = papr_scm_remove,
	.driver = {
		.name = "papr_scm",
		.of_match_table = papr_scm_match,
	},
};

static int __init papr_scm_init(void)
{
	int ret;

	ret = platform_driver_register(&papr_scm_driver);
	if (!ret)
		mce_register_notifier(&mce_ue_nb);

	return ret;
}
module_init(papr_scm_init);

static void __exit papr_scm_exit(void)
{
	mce_unregister_notifier(&mce_ue_nb);
	platform_driver_unregister(&papr_scm_driver);
}
module_exit(papr_scm_exit);

MODULE_DEVICE_TABLE(of, papr_scm_match);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("IBM Corporation");