summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/powernv/eeh-powernv.c
blob: 89e22c460ebf982c3de6dc76ba2fe04019d10f06 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * PowerNV Platform dependent EEH operations
 *
 * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
 */

#include <linux/atomic.h>
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>

#include <asm/eeh.h>
#include <asm/eeh_event.h>
#include <asm/firmware.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/machdep.h>
#include <asm/msi_bitmap.h>
#include <asm/opal.h>
#include <asm/ppc-pci.h>
#include <asm/pnv-pci.h>

#include "powernv.h"
#include "pci.h"
#include "../../../../drivers/pci/pci.h"

static int eeh_event_irq = -EINVAL;

static void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
{
	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
	eeh_probe_device(pdev);
}

static irqreturn_t pnv_eeh_event(int irq, void *data)
{
	/*
	 * We simply send a special EEH event if EEH has been
	 * enabled. We don't care about EEH events until we've
	 * finished processing the outstanding ones. Event processing
	 * gets unmasked in next_error() if EEH is enabled.
	 */
	disable_irq_nosync(irq);

	if (eeh_enabled())
		eeh_send_failure_event(NULL);

	return IRQ_HANDLED;
}

#ifdef CONFIG_DEBUG_FS
static ssize_t pnv_eeh_ei_write(struct file *filp,
				const char __user *user_buf,
				size_t count, loff_t *ppos)
{
	struct pci_controller *hose = filp->private_data;
	struct eeh_pe *pe;
	int pe_no, type, func;
	unsigned long addr, mask;
	char buf[50];
	int ret;

	if (!eeh_ops || !eeh_ops->err_inject)
		return -ENXIO;

	/* Copy over argument buffer */
	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
	if (!ret)
		return -EFAULT;

	/* Retrieve parameters */
	ret = sscanf(buf, "%x:%x:%x:%lx:%lx",
		     &pe_no, &type, &func, &addr, &mask);
	if (ret != 5)
		return -EINVAL;

	/* Retrieve PE */
	pe = eeh_pe_get(hose, pe_no);
	if (!pe)
		return -ENODEV;

	/* Do error injection */
	ret = eeh_ops->err_inject(pe, type, func, addr, mask);
	return ret < 0 ? ret : count;
}

static const struct file_operations pnv_eeh_ei_fops = {
	.open	= simple_open,
	.llseek	= no_llseek,
	.write	= pnv_eeh_ei_write,
};

static int pnv_eeh_dbgfs_set(void *data, int offset, u64 val)
{
	struct pci_controller *hose = data;
	struct pnv_phb *phb = hose->private_data;

	out_be64(phb->regs + offset, val);
	return 0;
}

static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val)
{
	struct pci_controller *hose = data;
	struct pnv_phb *phb = hose->private_data;

	*val = in_be64(phb->regs + offset);
	return 0;
}

#define PNV_EEH_DBGFS_ENTRY(name, reg)				\
static int pnv_eeh_dbgfs_set_##name(void *data, u64 val)	\
{								\
	return pnv_eeh_dbgfs_set(data, reg, val);		\
}								\
								\
static int pnv_eeh_dbgfs_get_##name(void *data, u64 *val)	\
{								\
	return pnv_eeh_dbgfs_get(data, reg, val);		\
}								\
								\
DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_dbgfs_ops_##name,		\
			pnv_eeh_dbgfs_get_##name,		\
                        pnv_eeh_dbgfs_set_##name,		\
			"0x%llx\n")

PNV_EEH_DBGFS_ENTRY(outb, 0xD10);
PNV_EEH_DBGFS_ENTRY(inbA, 0xD90);
PNV_EEH_DBGFS_ENTRY(inbB, 0xE10);

#endif /* CONFIG_DEBUG_FS */

static void pnv_eeh_enable_phbs(void)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;

	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;
		/*
		 * If EEH is enabled, we're going to rely on that.
		 * Otherwise, we restore to conventional mechanism
		 * to clear frozen PE during PCI config access.
		 */
		if (eeh_enabled())
			phb->flags |= PNV_PHB_FLAG_EEH;
		else
			phb->flags &= ~PNV_PHB_FLAG_EEH;
	}
}

/**
 * pnv_eeh_post_init - EEH platform dependent post initialization
 *
 * EEH platform dependent post initialization on powernv. When
 * the function is called, the EEH PEs and devices should have
 * been built. If the I/O cache staff has been built, EEH is
 * ready to supply service.
 */
int pnv_eeh_post_init(void)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;
	int ret = 0;

	eeh_show_enabled();

	/* Register OPAL event notifier */
	eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR));
	if (eeh_event_irq < 0) {
		pr_err("%s: Can't register OPAL event interrupt (%d)\n",
		       __func__, eeh_event_irq);
		return eeh_event_irq;
	}

	ret = request_irq(eeh_event_irq, pnv_eeh_event,
			  IRQ_TYPE_LEVEL_HIGH, "opal-eeh", NULL);
	if (ret < 0) {
		irq_dispose_mapping(eeh_event_irq);
		pr_err("%s: Can't request OPAL event interrupt (%d)\n",
		       __func__, eeh_event_irq);
		return ret;
	}

	if (!eeh_enabled())
		disable_irq(eeh_event_irq);

	pnv_eeh_enable_phbs();

	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;

		/* Create debugfs entries */
#ifdef CONFIG_DEBUG_FS
		if (phb->has_dbgfs || !phb->dbgfs)
			continue;

		phb->has_dbgfs = 1;
		debugfs_create_file("err_injct", 0200,
				    phb->dbgfs, hose,
				    &pnv_eeh_ei_fops);

		debugfs_create_file("err_injct_outbound", 0600,
				    phb->dbgfs, hose,
				    &pnv_eeh_dbgfs_ops_outb);
		debugfs_create_file("err_injct_inboundA", 0600,
				    phb->dbgfs, hose,
				    &pnv_eeh_dbgfs_ops_inbA);
		debugfs_create_file("err_injct_inboundB", 0600,
				    phb->dbgfs, hose,
				    &pnv_eeh_dbgfs_ops_inbB);
#endif /* CONFIG_DEBUG_FS */
	}

	return ret;
}

static int pnv_eeh_find_cap(struct pci_dn *pdn, int cap)
{
	int pos = PCI_CAPABILITY_LIST;
	int cnt = 48;   /* Maximal number of capabilities */
	u32 status, id;

	if (!pdn)
		return 0;

	/* Check if the device supports capabilities */
	pnv_pci_cfg_read(pdn, PCI_STATUS, 2, &status);
	if (!(status & PCI_STATUS_CAP_LIST))
		return 0;

	while (cnt--) {
		pnv_pci_cfg_read(pdn, pos, 1, &pos);
		if (pos < 0x40)
			break;

		pos &= ~3;
		pnv_pci_cfg_read(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
		if (id == 0xff)
			break;

		/* Found */
		if (id == cap)
			return pos;

		/* Next one */
		pos += PCI_CAP_LIST_NEXT;
	}

	return 0;
}

static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap)
{
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
	u32 header;
	int pos = 256, ttl = (4096 - 256) / 8;

	if (!edev || !edev->pcie_cap)
		return 0;
	if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
		return 0;
	else if (!header)
		return 0;

	while (ttl-- > 0) {
		if (PCI_EXT_CAP_ID(header) == cap && pos)
			return pos;

		pos = PCI_EXT_CAP_NEXT(header);
		if (pos < 256)
			break;

		if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
			break;
	}

	return 0;
}

static struct eeh_pe *pnv_eeh_get_upstream_pe(struct pci_dev *pdev)
{
	struct pci_controller *hose = pdev->bus->sysdata;
	struct pnv_phb *phb = hose->private_data;
	struct pci_dev *parent = pdev->bus->self;

#ifdef CONFIG_PCI_IOV
	/* for VFs we use the PF's PE as the upstream PE */
	if (pdev->is_virtfn)
		parent = pdev->physfn;
#endif

	/* otherwise use the PE of our parent bridge */
	if (parent) {
		struct pnv_ioda_pe *ioda_pe = pnv_ioda_get_pe(parent);

		return eeh_pe_get(phb->hose, ioda_pe->pe_number);
	}

	return NULL;
}

/**
 * pnv_eeh_probe - Do probe on PCI device
 * @pdev: pci_dev to probe
 *
 * Create, or find the existing, eeh_dev for this pci_dev.
 */
static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev)
{
	struct pci_dn *pdn = pci_get_pdn(pdev);
	struct pci_controller *hose = pdn->phb;
	struct pnv_phb *phb = hose->private_data;
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
	struct eeh_pe *upstream_pe;
	uint32_t pcie_flags;
	int ret;
	int config_addr = (pdn->busno << 8) | (pdn->devfn);

	/*
	 * When probing the root bridge, which doesn't have any
	 * subordinate PCI devices. We don't have OF node for
	 * the root bridge. So it's not reasonable to continue
	 * the probing.
	 */
	if (!edev || edev->pe)
		return NULL;

	/* already configured? */
	if (edev->pdev) {
		pr_debug("%s: found existing edev for %04x:%02x:%02x.%01x\n",
			__func__, hose->global_number, config_addr >> 8,
			PCI_SLOT(config_addr), PCI_FUNC(config_addr));
		return edev;
	}

	/* Skip for PCI-ISA bridge */
	if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
		return NULL;

	eeh_edev_dbg(edev, "Probing device\n");

	/* Initialize eeh device */
	edev->mode	&= 0xFFFFFF00;
	edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX);
	edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP);
	edev->af_cap   = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF);
	edev->aer_cap  = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
	if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
		edev->mode |= EEH_DEV_BRIDGE;
		if (edev->pcie_cap) {
			pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
					 2, &pcie_flags);
			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
				edev->mode |= EEH_DEV_ROOT_PORT;
			else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM)
				edev->mode |= EEH_DEV_DS_PORT;
		}
	}

	edev->pe_config_addr = phb->ioda.pe_rmap[config_addr];

	upstream_pe = pnv_eeh_get_upstream_pe(pdev);

	/* Create PE */
	ret = eeh_pe_tree_insert(edev, upstream_pe);
	if (ret) {
		eeh_edev_warn(edev, "Failed to add device to PE (code %d)\n", ret);
		return NULL;
	}

	/*
	 * If the PE contains any one of following adapters, the
	 * PCI config space can't be accessed when dumping EEH log.
	 * Otherwise, we will run into fenced PHB caused by shortage
	 * of outbound credits in the adapter. The PCI config access
	 * should be blocked until PE reset. MMIO access is dropped
	 * by hardware certainly. In order to drop PCI config requests,
	 * one more flag (EEH_PE_CFG_RESTRICTED) is introduced, which
	 * will be checked in the backend for PE state retrival. If
	 * the PE becomes frozen for the first time and the flag has
	 * been set for the PE, we will set EEH_PE_CFG_BLOCKED for
	 * that PE to block its config space.
	 *
	 * Broadcom BCM5718 2-ports NICs (14e4:1656)
	 * Broadcom Austin 4-ports NICs (14e4:1657)
	 * Broadcom Shiner 4-ports 1G NICs (14e4:168a)
	 * Broadcom Shiner 2-ports 10G NICs (14e4:168e)
	 */
	if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
	     pdn->device_id == 0x1656) ||
	    (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
	     pdn->device_id == 0x1657) ||
	    (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
	     pdn->device_id == 0x168a) ||
	    (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
	     pdn->device_id == 0x168e))
		edev->pe->state |= EEH_PE_CFG_RESTRICTED;

	/*
	 * Cache the PE primary bus, which can't be fetched when
	 * full hotplug is in progress. In that case, all child
	 * PCI devices of the PE are expected to be removed prior
	 * to PE reset.
	 */
	if (!(edev->pe->state & EEH_PE_PRI_BUS)) {
		edev->pe->bus = pci_find_bus(hose->global_number,
					     pdn->busno);
		if (edev->pe->bus)
			edev->pe->state |= EEH_PE_PRI_BUS;
	}

	/*
	 * Enable EEH explicitly so that we will do EEH check
	 * while accessing I/O stuff
	 */
	if (!eeh_has_flag(EEH_ENABLED)) {
		enable_irq(eeh_event_irq);
		pnv_eeh_enable_phbs();
		eeh_add_flag(EEH_ENABLED);
	}

	/* Save memory bars */
	eeh_save_bars(edev);

	eeh_edev_dbg(edev, "EEH enabled on device\n");

	return edev;
}

/**
 * pnv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
 * @pe: EEH PE
 * @option: operation to be issued
 *
 * The function is used to control the EEH functionality globally.
 * Currently, following options are support according to PAPR:
 * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
 */
static int pnv_eeh_set_option(struct eeh_pe *pe, int option)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	bool freeze_pe = false;
	int opt;
	s64 rc;

	switch (option) {
	case EEH_OPT_DISABLE:
		return -EPERM;
	case EEH_OPT_ENABLE:
		return 0;
	case EEH_OPT_THAW_MMIO:
		opt = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO;
		break;
	case EEH_OPT_THAW_DMA:
		opt = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
		break;
	case EEH_OPT_FREEZE_PE:
		freeze_pe = true;
		opt = OPAL_EEH_ACTION_SET_FREEZE_ALL;
		break;
	default:
		pr_warn("%s: Invalid option %d\n", __func__, option);
		return -EINVAL;
	}

	/* Freeze master and slave PEs if PHB supports compound PEs */
	if (freeze_pe) {
		if (phb->freeze_pe) {
			phb->freeze_pe(phb, pe->addr);
			return 0;
		}

		rc = opal_pci_eeh_freeze_set(phb->opal_id, pe->addr, opt);
		if (rc != OPAL_SUCCESS) {
			pr_warn("%s: Failure %lld freezing PHB#%x-PE#%x\n",
				__func__, rc, phb->hose->global_number,
				pe->addr);
			return -EIO;
		}

		return 0;
	}

	/* Unfreeze master and slave PEs if PHB supports */
	if (phb->unfreeze_pe)
		return phb->unfreeze_pe(phb, pe->addr, opt);

	rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe->addr, opt);
	if (rc != OPAL_SUCCESS) {
		pr_warn("%s: Failure %lld enable %d for PHB#%x-PE#%x\n",
			__func__, rc, option, phb->hose->global_number,
			pe->addr);
		return -EIO;
	}

	return 0;
}

static void pnv_eeh_get_phb_diag(struct eeh_pe *pe)
{
	struct pnv_phb *phb = pe->phb->private_data;
	s64 rc;

	rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data,
					 phb->diag_data_size);
	if (rc != OPAL_SUCCESS)
		pr_warn("%s: Failure %lld getting PHB#%x diag-data\n",
			__func__, rc, pe->phb->global_number);
}

static int pnv_eeh_get_phb_state(struct eeh_pe *pe)
{
	struct pnv_phb *phb = pe->phb->private_data;
	u8 fstate = 0;
	__be16 pcierr = 0;
	s64 rc;
	int result = 0;

	rc = opal_pci_eeh_freeze_status(phb->opal_id,
					pe->addr,
					&fstate,
					&pcierr,
					NULL);
	if (rc != OPAL_SUCCESS) {
		pr_warn("%s: Failure %lld getting PHB#%x state\n",
			__func__, rc, phb->hose->global_number);
		return EEH_STATE_NOT_SUPPORT;
	}

	/*
	 * Check PHB state. If the PHB is frozen for the
	 * first time, to dump the PHB diag-data.
	 */
	if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) {
		result = (EEH_STATE_MMIO_ACTIVE  |
			  EEH_STATE_DMA_ACTIVE   |
			  EEH_STATE_MMIO_ENABLED |
			  EEH_STATE_DMA_ENABLED);
	} else if (!(pe->state & EEH_PE_ISOLATED)) {
		eeh_pe_mark_isolated(pe);
		pnv_eeh_get_phb_diag(pe);

		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
	}

	return result;
}

static int pnv_eeh_get_pe_state(struct eeh_pe *pe)
{
	struct pnv_phb *phb = pe->phb->private_data;
	u8 fstate = 0;
	__be16 pcierr = 0;
	s64 rc;
	int result;

	/*
	 * We don't clobber hardware frozen state until PE
	 * reset is completed. In order to keep EEH core
	 * moving forward, we have to return operational
	 * state during PE reset.
	 */
	if (pe->state & EEH_PE_RESET) {
		result = (EEH_STATE_MMIO_ACTIVE  |
			  EEH_STATE_DMA_ACTIVE   |
			  EEH_STATE_MMIO_ENABLED |
			  EEH_STATE_DMA_ENABLED);
		return result;
	}

	/*
	 * Fetch PE state from hardware. If the PHB
	 * supports compound PE, let it handle that.
	 */
	if (phb->get_pe_state) {
		fstate = phb->get_pe_state(phb, pe->addr);
	} else {
		rc = opal_pci_eeh_freeze_status(phb->opal_id,
						pe->addr,
						&fstate,
						&pcierr,
						NULL);
		if (rc != OPAL_SUCCESS) {
			pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n",
				__func__, rc, phb->hose->global_number,
				pe->addr);
			return EEH_STATE_NOT_SUPPORT;
		}
	}

	/* Figure out state */
	switch (fstate) {
	case OPAL_EEH_STOPPED_NOT_FROZEN:
		result = (EEH_STATE_MMIO_ACTIVE  |
			  EEH_STATE_DMA_ACTIVE   |
			  EEH_STATE_MMIO_ENABLED |
			  EEH_STATE_DMA_ENABLED);
		break;
	case OPAL_EEH_STOPPED_MMIO_FREEZE:
		result = (EEH_STATE_DMA_ACTIVE |
			  EEH_STATE_DMA_ENABLED);
		break;
	case OPAL_EEH_STOPPED_DMA_FREEZE:
		result = (EEH_STATE_MMIO_ACTIVE |
			  EEH_STATE_MMIO_ENABLED);
		break;
	case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE:
		result = 0;
		break;
	case OPAL_EEH_STOPPED_RESET:
		result = EEH_STATE_RESET_ACTIVE;
		break;
	case OPAL_EEH_STOPPED_TEMP_UNAVAIL:
		result = EEH_STATE_UNAVAILABLE;
		break;
	case OPAL_EEH_STOPPED_PERM_UNAVAIL:
		result = EEH_STATE_NOT_SUPPORT;
		break;
	default:
		result = EEH_STATE_NOT_SUPPORT;
		pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n",
			__func__, phb->hose->global_number,
			pe->addr, fstate);
	}

	/*
	 * If PHB supports compound PE, to freeze all
	 * slave PEs for consistency.
	 *
	 * If the PE is switching to frozen state for the
	 * first time, to dump the PHB diag-data.
	 */
	if (!(result & EEH_STATE_NOT_SUPPORT) &&
	    !(result & EEH_STATE_UNAVAILABLE) &&
	    !(result & EEH_STATE_MMIO_ACTIVE) &&
	    !(result & EEH_STATE_DMA_ACTIVE)  &&
	    !(pe->state & EEH_PE_ISOLATED)) {
		if (phb->freeze_pe)
			phb->freeze_pe(phb, pe->addr);

		eeh_pe_mark_isolated(pe);
		pnv_eeh_get_phb_diag(pe);

		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
	}

	return result;
}

/**
 * pnv_eeh_get_state - Retrieve PE state
 * @pe: EEH PE
 * @delay: delay while PE state is temporarily unavailable
 *
 * Retrieve the state of the specified PE. For IODA-compitable
 * platform, it should be retrieved from IODA table. Therefore,
 * we prefer passing down to hardware implementation to handle
 * it.
 */
static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay)
{
	int ret;

	if (pe->type & EEH_PE_PHB)
		ret = pnv_eeh_get_phb_state(pe);
	else
		ret = pnv_eeh_get_pe_state(pe);

	if (!delay)
		return ret;

	/*
	 * If the PE state is temporarily unavailable,
	 * to inform the EEH core delay for default
	 * period (1 second)
	 */
	*delay = 0;
	if (ret & EEH_STATE_UNAVAILABLE)
		*delay = 1000;

	return ret;
}

static s64 pnv_eeh_poll(unsigned long id)
{
	s64 rc = OPAL_HARDWARE;

	while (1) {
		rc = opal_pci_poll(id);
		if (rc <= 0)
			break;

		if (system_state < SYSTEM_RUNNING)
			udelay(1000 * rc);
		else
			msleep(rc);
	}

	return rc;
}

int pnv_eeh_phb_reset(struct pci_controller *hose, int option)
{
	struct pnv_phb *phb = hose->private_data;
	s64 rc = OPAL_HARDWARE;

	pr_debug("%s: Reset PHB#%x, option=%d\n",
		 __func__, hose->global_number, option);

	/* Issue PHB complete reset request */
	if (option == EEH_RESET_FUNDAMENTAL ||
	    option == EEH_RESET_HOT)
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PHB_COMPLETE,
				    OPAL_ASSERT_RESET);
	else if (option == EEH_RESET_DEACTIVATE)
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PHB_COMPLETE,
				    OPAL_DEASSERT_RESET);
	if (rc < 0)
		goto out;

	/*
	 * Poll state of the PHB until the request is done
	 * successfully. The PHB reset is usually PHB complete
	 * reset followed by hot reset on root bus. So we also
	 * need the PCI bus settlement delay.
	 */
	if (rc > 0)
		rc = pnv_eeh_poll(phb->opal_id);
	if (option == EEH_RESET_DEACTIVATE) {
		if (system_state < SYSTEM_RUNNING)
			udelay(1000 * EEH_PE_RST_SETTLE_TIME);
		else
			msleep(EEH_PE_RST_SETTLE_TIME);
	}
out:
	if (rc != OPAL_SUCCESS)
		return -EIO;

	return 0;
}

static int pnv_eeh_root_reset(struct pci_controller *hose, int option)
{
	struct pnv_phb *phb = hose->private_data;
	s64 rc = OPAL_HARDWARE;

	pr_debug("%s: Reset PHB#%x, option=%d\n",
		 __func__, hose->global_number, option);

	/*
	 * During the reset deassert time, we needn't care
	 * the reset scope because the firmware does nothing
	 * for fundamental or hot reset during deassert phase.
	 */
	if (option == EEH_RESET_FUNDAMENTAL)
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PCI_FUNDAMENTAL,
				    OPAL_ASSERT_RESET);
	else if (option == EEH_RESET_HOT)
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PCI_HOT,
				    OPAL_ASSERT_RESET);
	else if (option == EEH_RESET_DEACTIVATE)
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PCI_HOT,
				    OPAL_DEASSERT_RESET);
	if (rc < 0)
		goto out;

	/* Poll state of the PHB until the request is done */
	if (rc > 0)
		rc = pnv_eeh_poll(phb->opal_id);
	if (option == EEH_RESET_DEACTIVATE)
		msleep(EEH_PE_RST_SETTLE_TIME);
out:
	if (rc != OPAL_SUCCESS)
		return -EIO;

	return 0;
}

static int __pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
{
	struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
	int aer = edev ? edev->aer_cap : 0;
	u32 ctrl;

	pr_debug("%s: Secondary Reset PCI bus %04x:%02x with option %d\n",
		 __func__, pci_domain_nr(dev->bus),
		 dev->bus->number, option);

	switch (option) {
	case EEH_RESET_FUNDAMENTAL:
	case EEH_RESET_HOT:
		/* Don't report linkDown event */
		if (aer) {
			eeh_ops->read_config(edev, aer + PCI_ERR_UNCOR_MASK,
					     4, &ctrl);
			ctrl |= PCI_ERR_UNC_SURPDN;
			eeh_ops->write_config(edev, aer + PCI_ERR_UNCOR_MASK,
					      4, ctrl);
		}

		eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &ctrl);
		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
		eeh_ops->write_config(edev, PCI_BRIDGE_CONTROL, 2, ctrl);

		msleep(EEH_PE_RST_HOLD_TIME);
		break;
	case EEH_RESET_DEACTIVATE:
		eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &ctrl);
		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
		eeh_ops->write_config(edev, PCI_BRIDGE_CONTROL, 2, ctrl);

		msleep(EEH_PE_RST_SETTLE_TIME);

		/* Continue reporting linkDown event */
		if (aer) {
			eeh_ops->read_config(edev, aer + PCI_ERR_UNCOR_MASK,
					     4, &ctrl);
			ctrl &= ~PCI_ERR_UNC_SURPDN;
			eeh_ops->write_config(edev, aer + PCI_ERR_UNCOR_MASK,
					      4, ctrl);
		}

		break;
	}

	return 0;
}

static int pnv_eeh_bridge_reset(struct pci_dev *pdev, int option)
{
	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
	struct pnv_phb *phb = hose->private_data;
	struct device_node *dn = pci_device_to_OF_node(pdev);
	uint64_t id = PCI_SLOT_ID(phb->opal_id,
				  (pdev->bus->number << 8) | pdev->devfn);
	uint8_t scope;
	int64_t rc;

	/* Hot reset to the bus if firmware cannot handle */
	if (!dn || !of_get_property(dn, "ibm,reset-by-firmware", NULL))
		return __pnv_eeh_bridge_reset(pdev, option);

	pr_debug("%s: FW reset PCI bus %04x:%02x with option %d\n",
		 __func__, pci_domain_nr(pdev->bus),
		 pdev->bus->number, option);

	switch (option) {
	case EEH_RESET_FUNDAMENTAL:
		scope = OPAL_RESET_PCI_FUNDAMENTAL;
		break;
	case EEH_RESET_HOT:
		scope = OPAL_RESET_PCI_HOT;
		break;
	case EEH_RESET_DEACTIVATE:
		return 0;
	default:
		dev_dbg(&pdev->dev, "%s: Unsupported reset %d\n",
			__func__, option);
		return -EINVAL;
	}

	rc = opal_pci_reset(id, scope, OPAL_ASSERT_RESET);
	if (rc <= OPAL_SUCCESS)
		goto out;

	rc = pnv_eeh_poll(id);
out:
	return (rc == OPAL_SUCCESS) ? 0 : -EIO;
}

void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
{
	struct pci_controller *hose;

	if (pci_is_root_bus(dev->bus)) {
		hose = pci_bus_to_host(dev->bus);
		pnv_eeh_root_reset(hose, EEH_RESET_HOT);
		pnv_eeh_root_reset(hose, EEH_RESET_DEACTIVATE);
	} else {
		pnv_eeh_bridge_reset(dev, EEH_RESET_HOT);
		pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE);
	}
}

static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type,
				     int pos, u16 mask)
{
	struct eeh_dev *edev = pdn->edev;
	int i, status = 0;

	/* Wait for Transaction Pending bit to be cleared */
	for (i = 0; i < 4; i++) {
		eeh_ops->read_config(edev, pos, 2, &status);
		if (!(status & mask))
			return;

		msleep((1 << i) * 100);
	}

	pr_warn("%s: Pending transaction while issuing %sFLR to %04x:%02x:%02x.%01x\n",
		__func__, type,
		pdn->phb->global_number, pdn->busno,
		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
}

static int pnv_eeh_do_flr(struct pci_dn *pdn, int option)
{
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
	u32 reg = 0;

	if (WARN_ON(!edev->pcie_cap))
		return -ENOTTY;

	eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCAP, 4, &reg);
	if (!(reg & PCI_EXP_DEVCAP_FLR))
		return -ENOTTY;

	switch (option) {
	case EEH_RESET_HOT:
	case EEH_RESET_FUNDAMENTAL:
		pnv_eeh_wait_for_pending(pdn, "",
					 edev->pcie_cap + PCI_EXP_DEVSTA,
					 PCI_EXP_DEVSTA_TRPND);
		eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL,
				     4, &reg);
		reg |= PCI_EXP_DEVCTL_BCR_FLR;
		eeh_ops->write_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL,
				      4, reg);
		msleep(EEH_PE_RST_HOLD_TIME);
		break;
	case EEH_RESET_DEACTIVATE:
		eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL,
				     4, &reg);
		reg &= ~PCI_EXP_DEVCTL_BCR_FLR;
		eeh_ops->write_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL,
				      4, reg);
		msleep(EEH_PE_RST_SETTLE_TIME);
		break;
	}

	return 0;
}

static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option)
{
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
	u32 cap = 0;

	if (WARN_ON(!edev->af_cap))
		return -ENOTTY;

	eeh_ops->read_config(edev, edev->af_cap + PCI_AF_CAP, 1, &cap);
	if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR))
		return -ENOTTY;

	switch (option) {
	case EEH_RESET_HOT:
	case EEH_RESET_FUNDAMENTAL:
		/*
		 * Wait for Transaction Pending bit to clear. A word-aligned
		 * test is used, so we use the conrol offset rather than status
		 * and shift the test bit to match.
		 */
		pnv_eeh_wait_for_pending(pdn, "AF",
					 edev->af_cap + PCI_AF_CTRL,
					 PCI_AF_STATUS_TP << 8);
		eeh_ops->write_config(edev, edev->af_cap + PCI_AF_CTRL,
				      1, PCI_AF_CTRL_FLR);
		msleep(EEH_PE_RST_HOLD_TIME);
		break;
	case EEH_RESET_DEACTIVATE:
		eeh_ops->write_config(edev, edev->af_cap + PCI_AF_CTRL, 1, 0);
		msleep(EEH_PE_RST_SETTLE_TIME);
		break;
	}

	return 0;
}

static int pnv_eeh_reset_vf_pe(struct eeh_pe *pe, int option)
{
	struct eeh_dev *edev;
	struct pci_dn *pdn;
	int ret;

	/* The VF PE should have only one child device */
	edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry);
	pdn = eeh_dev_to_pdn(edev);
	if (!pdn)
		return -ENXIO;

	ret = pnv_eeh_do_flr(pdn, option);
	if (!ret)
		return ret;

	return pnv_eeh_do_af_flr(pdn, option);
}

/**
 * pnv_eeh_reset - Reset the specified PE
 * @pe: EEH PE
 * @option: reset option
 *
 * Do reset on the indicated PE. For PCI bus sensitive PE,
 * we need to reset the parent p2p bridge. The PHB has to
 * be reinitialized if the p2p bridge is root bridge. For
 * PCI device sensitive PE, we will try to reset the device
 * through FLR. For now, we don't have OPAL APIs to do HARD
 * reset yet, so all reset would be SOFT (HOT) reset.
 */
static int pnv_eeh_reset(struct eeh_pe *pe, int option)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb;
	struct pci_bus *bus;
	int64_t rc;

	/*
	 * For PHB reset, we always have complete reset. For those PEs whose
	 * primary bus derived from root complex (root bus) or root port
	 * (usually bus#1), we apply hot or fundamental reset on the root port.
	 * For other PEs, we always have hot reset on the PE primary bus.
	 *
	 * Here, we have different design to pHyp, which always clear the
	 * frozen state during PE reset. However, the good idea here from
	 * benh is to keep frozen state before we get PE reset done completely
	 * (until BAR restore). With the frozen state, HW drops illegal IO
	 * or MMIO access, which can incur recrusive frozen PE during PE
	 * reset. The side effect is that EEH core has to clear the frozen
	 * state explicitly after BAR restore.
	 */
	if (pe->type & EEH_PE_PHB)
		return pnv_eeh_phb_reset(hose, option);

	/*
	 * The frozen PE might be caused by PAPR error injection
	 * registers, which are expected to be cleared after hitting
	 * frozen PE as stated in the hardware spec. Unfortunately,
	 * that's not true on P7IOC. So we have to clear it manually
	 * to avoid recursive EEH errors during recovery.
	 */
	phb = hose->private_data;
	if (phb->model == PNV_PHB_MODEL_P7IOC &&
	    (option == EEH_RESET_HOT ||
	     option == EEH_RESET_FUNDAMENTAL)) {
		rc = opal_pci_reset(phb->opal_id,
				    OPAL_RESET_PHB_ERROR,
				    OPAL_ASSERT_RESET);
		if (rc != OPAL_SUCCESS) {
			pr_warn("%s: Failure %lld clearing error injection registers\n",
				__func__, rc);
			return -EIO;
		}
	}

	if (pe->type & EEH_PE_VF)
		return pnv_eeh_reset_vf_pe(pe, option);

	bus = eeh_pe_bus_get(pe);
	if (!bus) {
		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
			__func__, pe->phb->global_number, pe->addr);
		return -EIO;
	}

	if (pci_is_root_bus(bus))
		return pnv_eeh_root_reset(hose, option);

	/*
	 * For hot resets try use the generic PCI error recovery reset
	 * functions. These correctly handles the case where the secondary
	 * bus is behind a hotplug slot and it will use the slot provided
	 * reset methods to prevent spurious hotplug events during the reset.
	 *
	 * Fundemental resets need to be handled internally to EEH since the
	 * PCI core doesn't really have a concept of a fundemental reset,
	 * mainly because there's no standard way to generate one. Only a
	 * few devices require an FRESET so it should be fine.
	 */
	if (option != EEH_RESET_FUNDAMENTAL) {
		/*
		 * NB: Skiboot and pnv_eeh_bridge_reset() also no-op the
		 *     de-assert step. It's like the OPAL reset API was
		 *     poorly designed or something...
		 */
		if (option == EEH_RESET_DEACTIVATE)
			return 0;

		rc = pci_bus_error_reset(bus->self);
		if (!rc)
			return 0;
	}

	/* otherwise, use the generic bridge reset. this might call into FW */
	if (pci_is_root_bus(bus->parent))
		return pnv_eeh_root_reset(hose, option);
	return pnv_eeh_bridge_reset(bus->self, option);
}

/**
 * pnv_eeh_get_log - Retrieve error log
 * @pe: EEH PE
 * @severity: temporary or permanent error log
 * @drv_log: driver log to be combined with retrieved error log
 * @len: length of driver log
 *
 * Retrieve the temporary or permanent error from the PE.
 */
static int pnv_eeh_get_log(struct eeh_pe *pe, int severity,
			   char *drv_log, unsigned long len)
{
	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);

	return 0;
}

/**
 * pnv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
 * @pe: EEH PE
 *
 * The function will be called to reconfigure the bridges included
 * in the specified PE so that the mulfunctional PE would be recovered
 * again.
 */
static int pnv_eeh_configure_bridge(struct eeh_pe *pe)
{
	return 0;
}

/**
 * pnv_pe_err_inject - Inject specified error to the indicated PE
 * @pe: the indicated PE
 * @type: error type
 * @func: specific error type
 * @addr: address
 * @mask: address mask
 *
 * The routine is called to inject specified error, which is
 * determined by @type and @func, to the indicated PE for
 * testing purpose.
 */
static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
			      unsigned long addr, unsigned long mask)
{
	struct pci_controller *hose = pe->phb;
	struct pnv_phb *phb = hose->private_data;
	s64 rc;

	if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR &&
	    type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) {
		pr_warn("%s: Invalid error type %d\n",
			__func__, type);
		return -ERANGE;
	}

	if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR ||
	    func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) {
		pr_warn("%s: Invalid error function %d\n",
			__func__, func);
		return -ERANGE;
	}

	/* Firmware supports error injection ? */
	if (!opal_check_token(OPAL_PCI_ERR_INJECT)) {
		pr_warn("%s: Firmware doesn't support error injection\n",
			__func__);
		return -ENXIO;
	}

	/* Do error injection */
	rc = opal_pci_err_inject(phb->opal_id, pe->addr,
				 type, func, addr, mask);
	if (rc != OPAL_SUCCESS) {
		pr_warn("%s: Failure %lld injecting error "
			"%d-%d to PHB#%x-PE#%x\n",
			__func__, rc, type, func,
			hose->global_number, pe->addr);
		return -EIO;
	}

	return 0;
}

static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn)
{
	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);

	if (!edev || !edev->pe)
		return false;

	/*
	 * We will issue FLR or AF FLR to all VFs, which are contained
	 * in VF PE. It relies on the EEH PCI config accessors. So we
	 * can't block them during the window.
	 */
	if (edev->physfn && (edev->pe->state & EEH_PE_RESET))
		return false;

	if (edev->pe->state & EEH_PE_CFG_BLOCKED)
		return true;

	return false;
}

static int pnv_eeh_read_config(struct eeh_dev *edev,
			       int where, int size, u32 *val)
{
	struct pci_dn *pdn = eeh_dev_to_pdn(edev);

	if (!pdn)
		return PCIBIOS_DEVICE_NOT_FOUND;

	if (pnv_eeh_cfg_blocked(pdn)) {
		*val = 0xFFFFFFFF;
		return PCIBIOS_SET_FAILED;
	}

	return pnv_pci_cfg_read(pdn, where, size, val);
}

static int pnv_eeh_write_config(struct eeh_dev *edev,
				int where, int size, u32 val)
{
	struct pci_dn *pdn = eeh_dev_to_pdn(edev);

	if (!pdn)
		return PCIBIOS_DEVICE_NOT_FOUND;

	if (pnv_eeh_cfg_blocked(pdn))
		return PCIBIOS_SET_FAILED;

	return pnv_pci_cfg_write(pdn, where, size, val);
}

static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data)
{
	/* GEM */
	if (data->gemXfir || data->gemRfir ||
	    data->gemRirqfir || data->gemMask || data->gemRwof)
		pr_info("  GEM: %016llx %016llx %016llx %016llx %016llx\n",
			be64_to_cpu(data->gemXfir),
			be64_to_cpu(data->gemRfir),
			be64_to_cpu(data->gemRirqfir),
			be64_to_cpu(data->gemMask),
			be64_to_cpu(data->gemRwof));

	/* LEM */
	if (data->lemFir || data->lemErrMask ||
	    data->lemAction0 || data->lemAction1 || data->lemWof)
		pr_info("  LEM: %016llx %016llx %016llx %016llx %016llx\n",
			be64_to_cpu(data->lemFir),
			be64_to_cpu(data->lemErrMask),
			be64_to_cpu(data->lemAction0),
			be64_to_cpu(data->lemAction1),
			be64_to_cpu(data->lemWof));
}

static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose)
{
	struct pnv_phb *phb = hose->private_data;
	struct OpalIoP7IOCErrorData *data =
		(struct OpalIoP7IOCErrorData*)phb->diag_data;
	long rc;

	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
	if (rc != OPAL_SUCCESS) {
		pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n",
			__func__, phb->hub_id, rc);
		return;
	}

	switch (be16_to_cpu(data->type)) {
	case OPAL_P7IOC_DIAG_TYPE_RGC:
		pr_info("P7IOC diag-data for RGC\n\n");
		pnv_eeh_dump_hub_diag_common(data);
		if (data->rgc.rgcStatus || data->rgc.rgcLdcp)
			pr_info("  RGC: %016llx %016llx\n",
				be64_to_cpu(data->rgc.rgcStatus),
				be64_to_cpu(data->rgc.rgcLdcp));
		break;
	case OPAL_P7IOC_DIAG_TYPE_BI:
		pr_info("P7IOC diag-data for BI %s\n\n",
			data->bi.biDownbound ? "Downbound" : "Upbound");
		pnv_eeh_dump_hub_diag_common(data);
		if (data->bi.biLdcp0 || data->bi.biLdcp1 ||
		    data->bi.biLdcp2 || data->bi.biFenceStatus)
			pr_info("  BI:  %016llx %016llx %016llx %016llx\n",
				be64_to_cpu(data->bi.biLdcp0),
				be64_to_cpu(data->bi.biLdcp1),
				be64_to_cpu(data->bi.biLdcp2),
				be64_to_cpu(data->bi.biFenceStatus));
		break;
	case OPAL_P7IOC_DIAG_TYPE_CI:
		pr_info("P7IOC diag-data for CI Port %d\n\n",
			data->ci.ciPort);
		pnv_eeh_dump_hub_diag_common(data);
		if (data->ci.ciPortStatus || data->ci.ciPortLdcp)
			pr_info("  CI:  %016llx %016llx\n",
				be64_to_cpu(data->ci.ciPortStatus),
				be64_to_cpu(data->ci.ciPortLdcp));
		break;
	case OPAL_P7IOC_DIAG_TYPE_MISC:
		pr_info("P7IOC diag-data for MISC\n\n");
		pnv_eeh_dump_hub_diag_common(data);
		break;
	case OPAL_P7IOC_DIAG_TYPE_I2C:
		pr_info("P7IOC diag-data for I2C\n\n");
		pnv_eeh_dump_hub_diag_common(data);
		break;
	default:
		pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n",
			__func__, phb->hub_id, data->type);
	}
}

static int pnv_eeh_get_pe(struct pci_controller *hose,
			  u16 pe_no, struct eeh_pe **pe)
{
	struct pnv_phb *phb = hose->private_data;
	struct pnv_ioda_pe *pnv_pe;
	struct eeh_pe *dev_pe;

	/*
	 * If PHB supports compound PE, to fetch
	 * the master PE because slave PE is invisible
	 * to EEH core.
	 */
	pnv_pe = &phb->ioda.pe_array[pe_no];
	if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
		pnv_pe = pnv_pe->master;
		WARN_ON(!pnv_pe ||
			!(pnv_pe->flags & PNV_IODA_PE_MASTER));
		pe_no = pnv_pe->pe_number;
	}

	/* Find the PE according to PE# */
	dev_pe = eeh_pe_get(hose, pe_no);
	if (!dev_pe)
		return -EEXIST;

	/* Freeze the (compound) PE */
	*pe = dev_pe;
	if (!(dev_pe->state & EEH_PE_ISOLATED))
		phb->freeze_pe(phb, pe_no);

	/*
	 * At this point, we're sure the (compound) PE should
	 * have been frozen. However, we still need poke until
	 * hitting the frozen PE on top level.
	 */
	dev_pe = dev_pe->parent;
	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
		int ret;
		ret = eeh_ops->get_state(dev_pe, NULL);
		if (ret <= 0 || eeh_state_active(ret)) {
			dev_pe = dev_pe->parent;
			continue;
		}

		/* Frozen parent PE */
		*pe = dev_pe;
		if (!(dev_pe->state & EEH_PE_ISOLATED))
			phb->freeze_pe(phb, dev_pe->addr);

		/* Next one */
		dev_pe = dev_pe->parent;
	}

	return 0;
}

/**
 * pnv_eeh_next_error - Retrieve next EEH error to handle
 * @pe: Affected PE
 *
 * The function is expected to be called by EEH core while it gets
 * special EEH event (without binding PE). The function calls to
 * OPAL APIs for next error to handle. The informational error is
 * handled internally by platform. However, the dead IOC, dead PHB,
 * fenced PHB and frozen PE should be handled by EEH core eventually.
 */
static int pnv_eeh_next_error(struct eeh_pe **pe)
{
	struct pci_controller *hose;
	struct pnv_phb *phb;
	struct eeh_pe *phb_pe, *parent_pe;
	__be64 frozen_pe_no;
	__be16 err_type, severity;
	long rc;
	int state, ret = EEH_NEXT_ERR_NONE;

	/*
	 * While running here, it's safe to purge the event queue. The
	 * event should still be masked.
	 */
	eeh_remove_event(NULL, false);

	list_for_each_entry(hose, &hose_list, list_node) {
		/*
		 * If the subordinate PCI buses of the PHB has been
		 * removed or is exactly under error recovery, we
		 * needn't take care of it any more.
		 */
		phb = hose->private_data;
		phb_pe = eeh_phb_pe_get(hose);
		if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED))
			continue;

		rc = opal_pci_next_error(phb->opal_id,
					 &frozen_pe_no, &err_type, &severity);
		if (rc != OPAL_SUCCESS) {
			pr_devel("%s: Invalid return value on "
				 "PHB#%x (0x%lx) from opal_pci_next_error",
				 __func__, hose->global_number, rc);
			continue;
		}

		/* If the PHB doesn't have error, stop processing */
		if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR ||
		    be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) {
			pr_devel("%s: No error found on PHB#%x\n",
				 __func__, hose->global_number);
			continue;
		}

		/*
		 * Processing the error. We're expecting the error with
		 * highest priority reported upon multiple errors on the
		 * specific PHB.
		 */
		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
			__func__, be16_to_cpu(err_type),
			be16_to_cpu(severity), be64_to_cpu(frozen_pe_no),
			hose->global_number);
		switch (be16_to_cpu(err_type)) {
		case OPAL_EEH_IOC_ERROR:
			if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) {
				pr_err("EEH: dead IOC detected\n");
				ret = EEH_NEXT_ERR_DEAD_IOC;
			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
				pr_info("EEH: IOC informative error "
					"detected\n");
				pnv_eeh_get_and_dump_hub_diag(hose);
				ret = EEH_NEXT_ERR_NONE;
			}

			break;
		case OPAL_EEH_PHB_ERROR:
			if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
				*pe = phb_pe;
				pr_err("EEH: dead PHB#%x detected, "
				       "location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_DEAD_PHB;
			} else if (be16_to_cpu(severity) ==
				   OPAL_EEH_SEV_PHB_FENCED) {
				*pe = phb_pe;
				pr_err("EEH: Fenced PHB#%x detected, "
				       "location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_FENCED_PHB;
			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
				pr_info("EEH: PHB#%x informative error "
					"detected, location: %s\n",
					hose->global_number,
					eeh_pe_loc_get(phb_pe));
				pnv_eeh_get_phb_diag(phb_pe);
				pnv_pci_dump_phb_diag_data(hose, phb_pe->data);
				ret = EEH_NEXT_ERR_NONE;
			}

			break;
		case OPAL_EEH_PE_ERROR:
			/*
			 * If we can't find the corresponding PE, we
			 * just try to unfreeze.
			 */
			if (pnv_eeh_get_pe(hose,
				be64_to_cpu(frozen_pe_no), pe)) {
				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
					hose->global_number, be64_to_cpu(frozen_pe_no));
				pr_info("EEH: PHB location: %s\n",
					eeh_pe_loc_get(phb_pe));

				/* Dump PHB diag-data */
				rc = opal_pci_get_phb_diag_data2(phb->opal_id,
					phb->diag_data, phb->diag_data_size);
				if (rc == OPAL_SUCCESS)
					pnv_pci_dump_phb_diag_data(hose,
							phb->diag_data);

				/* Try best to clear it */
				opal_pci_eeh_freeze_clear(phb->opal_id,
					be64_to_cpu(frozen_pe_no),
					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
				ret = EEH_NEXT_ERR_NONE;
			} else if ((*pe)->state & EEH_PE_ISOLATED ||
				   eeh_pe_passed(*pe)) {
				ret = EEH_NEXT_ERR_NONE;
			} else {
				pr_err("EEH: Frozen PE#%x "
				       "on PHB#%x detected\n",
				       (*pe)->addr,
					(*pe)->phb->global_number);
				pr_err("EEH: PE location: %s, "
				       "PHB location: %s\n",
				       eeh_pe_loc_get(*pe),
				       eeh_pe_loc_get(phb_pe));
				ret = EEH_NEXT_ERR_FROZEN_PE;
			}

			break;
		default:
			pr_warn("%s: Unexpected error type %d\n",
				__func__, be16_to_cpu(err_type));
		}

		/*
		 * EEH core will try recover from fenced PHB or
		 * frozen PE. In the time for frozen PE, EEH core
		 * enable IO path for that before collecting logs,
		 * but it ruins the site. So we have to dump the
		 * log in advance here.
		 */
		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
		    !((*pe)->state & EEH_PE_ISOLATED)) {
			eeh_pe_mark_isolated(*pe);
			pnv_eeh_get_phb_diag(*pe);

			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
				pnv_pci_dump_phb_diag_data((*pe)->phb,
							   (*pe)->data);
		}

		/*
		 * We probably have the frozen parent PE out there and
		 * we need have to handle frozen parent PE firstly.
		 */
		if (ret == EEH_NEXT_ERR_FROZEN_PE) {
			parent_pe = (*pe)->parent;
			while (parent_pe) {
				/* Hit the ceiling ? */
				if (parent_pe->type & EEH_PE_PHB)
					break;

				/* Frozen parent PE ? */
				state = eeh_ops->get_state(parent_pe, NULL);
				if (state > 0 && !eeh_state_active(state))
					*pe = parent_pe;

				/* Next parent level */
				parent_pe = parent_pe->parent;
			}

			/* We possibly migrate to another PE */
			eeh_pe_mark_isolated(*pe);
		}

		/*
		 * If we have no errors on the specific PHB or only
		 * informative error there, we continue poking it.
		 * Otherwise, we need actions to be taken by upper
		 * layer.
		 */
		if (ret > EEH_NEXT_ERR_INF)
			break;
	}

	/* Unmask the event */
	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
		enable_irq(eeh_event_irq);

	return ret;
}

static int pnv_eeh_restore_config(struct eeh_dev *edev)
{
	struct pnv_phb *phb;
	s64 ret = 0;

	if (!edev)
		return -EEXIST;

	if (edev->physfn)
		return 0;

	phb = edev->controller->private_data;
	ret = opal_pci_reinit(phb->opal_id,
			      OPAL_REINIT_PCI_DEV, edev->bdfn);

	if (ret) {
		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
			__func__, edev->bdfn, ret);
		return -EIO;
	}

	return ret;
}

static struct eeh_ops pnv_eeh_ops = {
	.name                   = "powernv",
	.probe			= pnv_eeh_probe,
	.set_option             = pnv_eeh_set_option,
	.get_state              = pnv_eeh_get_state,
	.reset                  = pnv_eeh_reset,
	.get_log                = pnv_eeh_get_log,
	.configure_bridge       = pnv_eeh_configure_bridge,
	.err_inject		= pnv_eeh_err_inject,
	.read_config            = pnv_eeh_read_config,
	.write_config           = pnv_eeh_write_config,
	.next_error		= pnv_eeh_next_error,
	.restore_config		= pnv_eeh_restore_config,
	.notify_resume		= NULL
};

#ifdef CONFIG_PCI_IOV
static void pnv_pci_fixup_vf_mps(struct pci_dev *pdev)
{
	struct pci_dn *pdn = pci_get_pdn(pdev);
	int parent_mps;

	if (!pdev->is_virtfn)
		return;

	/* Synchronize MPS for VF and PF */
	parent_mps = pcie_get_mps(pdev->physfn);
	if ((128 << pdev->pcie_mpss) >= parent_mps)
		pcie_set_mps(pdev, parent_mps);
	pdn->mps = pcie_get_mps(pdev);
}
DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_mps);
#endif /* CONFIG_PCI_IOV */

/**
 * eeh_powernv_init - Register platform dependent EEH operations
 *
 * EEH initialization on powernv platform. This function should be
 * called before any EEH related functions.
 */
static int __init eeh_powernv_init(void)
{
	int max_diag_size = PNV_PCI_DIAG_BUF_SIZE;
	struct pci_controller *hose;
	struct pnv_phb *phb;
	int ret = -EINVAL;

	if (!firmware_has_feature(FW_FEATURE_OPAL)) {
		pr_warn("%s: OPAL is required !\n", __func__);
		return -EINVAL;
	}

	/* Set probe mode */
	eeh_add_flag(EEH_PROBE_MODE_DEV);

	/*
	 * P7IOC blocks PCI config access to frozen PE, but PHB3
	 * doesn't do that. So we have to selectively enable I/O
	 * prior to collecting error log.
	 */
	list_for_each_entry(hose, &hose_list, list_node) {
		phb = hose->private_data;

		if (phb->model == PNV_PHB_MODEL_P7IOC)
			eeh_add_flag(EEH_ENABLE_IO_FOR_LOG);

		if (phb->diag_data_size > max_diag_size)
			max_diag_size = phb->diag_data_size;

		break;
	}

	/*
	 * eeh_init() allocates the eeh_pe and its aux data buf so the
	 * size needs to be set before calling eeh_init().
	 */
	eeh_set_pe_aux_size(max_diag_size);
	ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device;

	ret = eeh_init(&pnv_eeh_ops);
	if (!ret)
		pr_info("EEH: PowerNV platform initialized\n");
	else
		pr_info("EEH: Failed to initialize PowerNV platform (%d)\n", ret);

	return ret;
}
machine_arch_initcall(powernv, eeh_powernv_init);