aboutsummaryrefslogtreecommitdiff
path: root/drivers/misc/cxl/pci.c
blob: fa4fe02cfef4154dbbb15e6ca45021b68a45b6ba (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
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
/*
 * Copyright 2014 IBM Corp.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/pci_regs.h>
#include <linux/pci_ids.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/pci.h>
#include <linux/of.h>
#include <linux/delay.h>
#include <asm/opal.h>
#include <asm/msi_bitmap.h>
#include <asm/pnv-pci.h>
#include <asm/io.h>
#include <asm/reg.h>

#include "cxl.h"
#include <misc/cxl.h>


#define CXL_PCI_VSEC_ID	0x1280
#define CXL_VSEC_MIN_SIZE 0x80

#define CXL_READ_VSEC_LENGTH(dev, vsec, dest)			\
	{							\
		pci_read_config_word(dev, vsec + 0x6, dest);	\
		*dest >>= 4;					\
	}
#define CXL_READ_VSEC_NAFUS(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x8, dest)

#define CXL_READ_VSEC_STATUS(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x9, dest)
#define CXL_STATUS_SECOND_PORT  0x80
#define CXL_STATUS_MSI_X_FULL   0x40
#define CXL_STATUS_MSI_X_SINGLE 0x20
#define CXL_STATUS_FLASH_RW     0x08
#define CXL_STATUS_FLASH_RO     0x04
#define CXL_STATUS_LOADABLE_AFU 0x02
#define CXL_STATUS_LOADABLE_PSL 0x01
/* If we see these features we won't try to use the card */
#define CXL_UNSUPPORTED_FEATURES \
	(CXL_STATUS_MSI_X_FULL | CXL_STATUS_MSI_X_SINGLE)

#define CXL_READ_VSEC_MODE_CONTROL(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xa, dest)
#define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \
	pci_write_config_byte(dev, vsec + 0xa, val)
#define CXL_WRITE_VSEC_MODE_CONTROL_BUS(bus, devfn, vsec, val) \
	pci_bus_write_config_byte(bus, devfn, vsec + 0xa, val)
#define CXL_VSEC_PROTOCOL_MASK   0xe0
#define CXL_VSEC_PROTOCOL_1024TB 0x80
#define CXL_VSEC_PROTOCOL_512TB  0x40
#define CXL_VSEC_PROTOCOL_256TB  0x20 /* Power 8 uses this */
#define CXL_VSEC_PROTOCOL_ENABLE 0x01

#define CXL_READ_VSEC_PSL_REVISION(dev, vsec, dest) \
	pci_read_config_word(dev, vsec + 0xc, dest)
#define CXL_READ_VSEC_CAIA_MINOR(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xe, dest)
#define CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0xf, dest)
#define CXL_READ_VSEC_BASE_IMAGE(dev, vsec, dest) \
	pci_read_config_word(dev, vsec + 0x10, dest)

#define CXL_READ_VSEC_IMAGE_STATE(dev, vsec, dest) \
	pci_read_config_byte(dev, vsec + 0x13, dest)
#define CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, val) \
	pci_write_config_byte(dev, vsec + 0x13, val)
#define CXL_VSEC_USER_IMAGE_LOADED 0x80 /* RO */
#define CXL_VSEC_PERST_LOADS_IMAGE 0x20 /* RW */
#define CXL_VSEC_PERST_SELECT_USER 0x10 /* RW */

#define CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x20, dest)
#define CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x24, dest)
#define CXL_READ_VSEC_PS_OFF(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x28, dest)
#define CXL_READ_VSEC_PS_SIZE(dev, vsec, dest) \
	pci_read_config_dword(dev, vsec + 0x2c, dest)


/* This works a little different than the p1/p2 register accesses to make it
 * easier to pull out individual fields */
#define AFUD_READ(afu, off)		in_be64(afu->native->afu_desc_mmio + off)
#define AFUD_READ_LE(afu, off)		in_le64(afu->native->afu_desc_mmio + off)
#define EXTRACT_PPC_BIT(val, bit)	(!!(val & PPC_BIT(bit)))
#define EXTRACT_PPC_BITS(val, bs, be)	((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))

#define AFUD_READ_INFO(afu)		AFUD_READ(afu, 0x0)
#define   AFUD_NUM_INTS_PER_PROC(val)	EXTRACT_PPC_BITS(val,  0, 15)
#define   AFUD_NUM_PROCS(val)		EXTRACT_PPC_BITS(val, 16, 31)
#define   AFUD_NUM_CRS(val)		EXTRACT_PPC_BITS(val, 32, 47)
#define   AFUD_MULTIMODE(val)		EXTRACT_PPC_BIT(val, 48)
#define   AFUD_PUSH_BLOCK_TRANSFER(val)	EXTRACT_PPC_BIT(val, 55)
#define   AFUD_DEDICATED_PROCESS(val)	EXTRACT_PPC_BIT(val, 59)
#define   AFUD_AFU_DIRECTED(val)	EXTRACT_PPC_BIT(val, 61)
#define   AFUD_TIME_SLICED(val)		EXTRACT_PPC_BIT(val, 63)
#define AFUD_READ_CR(afu)		AFUD_READ(afu, 0x20)
#define   AFUD_CR_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_CR_OFF(afu)		AFUD_READ(afu, 0x28)
#define AFUD_READ_PPPSA(afu)		AFUD_READ(afu, 0x30)
#define   AFUD_PPPSA_PP(val)		EXTRACT_PPC_BIT(val, 6)
#define   AFUD_PPPSA_PSA(val)		EXTRACT_PPC_BIT(val, 7)
#define   AFUD_PPPSA_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_PPPSA_OFF(afu)	AFUD_READ(afu, 0x38)
#define AFUD_READ_EB(afu)		AFUD_READ(afu, 0x40)
#define   AFUD_EB_LEN(val)		EXTRACT_PPC_BITS(val, 8, 63)
#define AFUD_READ_EB_OFF(afu)		AFUD_READ(afu, 0x48)

static const struct pci_device_id cxl_pci_tbl[] = {
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0601), },
	{ PCI_DEVICE_CLASS(0x120000, ~0), },

	{ }
};
MODULE_DEVICE_TABLE(pci, cxl_pci_tbl);


/*
 * Mostly using these wrappers to avoid confusion:
 * priv 1 is BAR2, while priv 2 is BAR0
 */
static inline resource_size_t p1_base(struct pci_dev *dev)
{
	return pci_resource_start(dev, 2);
}

static inline resource_size_t p1_size(struct pci_dev *dev)
{
	return pci_resource_len(dev, 2);
}

static inline resource_size_t p2_base(struct pci_dev *dev)
{
	return pci_resource_start(dev, 0);
}

static inline resource_size_t p2_size(struct pci_dev *dev)
{
	return pci_resource_len(dev, 0);
}

static int find_cxl_vsec(struct pci_dev *dev)
{
	int vsec = 0;
	u16 val;

	while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) {
		pci_read_config_word(dev, vsec + 0x4, &val);
		if (val == CXL_PCI_VSEC_ID)
			return vsec;
	}
	return 0;

}

static void dump_cxl_config_space(struct pci_dev *dev)
{
	int vsec;
	u32 val;

	dev_info(&dev->dev, "dump_cxl_config_space\n");

	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0, &val);
	dev_info(&dev->dev, "BAR0: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_1, &val);
	dev_info(&dev->dev, "BAR1: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_2, &val);
	dev_info(&dev->dev, "BAR2: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_3, &val);
	dev_info(&dev->dev, "BAR3: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_4, &val);
	dev_info(&dev->dev, "BAR4: %#.8x\n", val);
	pci_read_config_dword(dev, PCI_BASE_ADDRESS_5, &val);
	dev_info(&dev->dev, "BAR5: %#.8x\n", val);

	dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
		p1_base(dev), p1_size(dev));
	dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
		p2_base(dev), p2_size(dev));
	dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
		pci_resource_start(dev, 4), pci_resource_len(dev, 4));

	if (!(vsec = find_cxl_vsec(dev)))
		return;

#define show_reg(name, what) \
	dev_info(&dev->dev, "cxl vsec: %30s: %#x\n", name, what)

	pci_read_config_dword(dev, vsec + 0x0, &val);
	show_reg("Cap ID", (val >> 0) & 0xffff);
	show_reg("Cap Ver", (val >> 16) & 0xf);
	show_reg("Next Cap Ptr", (val >> 20) & 0xfff);
	pci_read_config_dword(dev, vsec + 0x4, &val);
	show_reg("VSEC ID", (val >> 0) & 0xffff);
	show_reg("VSEC Rev", (val >> 16) & 0xf);
	show_reg("VSEC Length",	(val >> 20) & 0xfff);
	pci_read_config_dword(dev, vsec + 0x8, &val);
	show_reg("Num AFUs", (val >> 0) & 0xff);
	show_reg("Status", (val >> 8) & 0xff);
	show_reg("Mode Control", (val >> 16) & 0xff);
	show_reg("Reserved", (val >> 24) & 0xff);
	pci_read_config_dword(dev, vsec + 0xc, &val);
	show_reg("PSL Rev", (val >> 0) & 0xffff);
	show_reg("CAIA Ver", (val >> 16) & 0xffff);
	pci_read_config_dword(dev, vsec + 0x10, &val);
	show_reg("Base Image Rev", (val >> 0) & 0xffff);
	show_reg("Reserved", (val >> 16) & 0x0fff);
	show_reg("Image Control", (val >> 28) & 0x3);
	show_reg("Reserved", (val >> 30) & 0x1);
	show_reg("Image Loaded", (val >> 31) & 0x1);

	pci_read_config_dword(dev, vsec + 0x14, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x18, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x1c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x20, &val);
	show_reg("AFU Descriptor Offset", val);
	pci_read_config_dword(dev, vsec + 0x24, &val);
	show_reg("AFU Descriptor Size", val);
	pci_read_config_dword(dev, vsec + 0x28, &val);
	show_reg("Problem State Offset", val);
	pci_read_config_dword(dev, vsec + 0x2c, &val);
	show_reg("Problem State Size", val);

	pci_read_config_dword(dev, vsec + 0x30, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x34, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x38, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x3c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x40, &val);
	show_reg("PSL Programming Port", val);
	pci_read_config_dword(dev, vsec + 0x44, &val);
	show_reg("PSL Programming Control", val);

	pci_read_config_dword(dev, vsec + 0x48, &val);
	show_reg("Reserved", val);
	pci_read_config_dword(dev, vsec + 0x4c, &val);
	show_reg("Reserved", val);

	pci_read_config_dword(dev, vsec + 0x50, &val);
	show_reg("Flash Address Register", val);
	pci_read_config_dword(dev, vsec + 0x54, &val);
	show_reg("Flash Size Register", val);
	pci_read_config_dword(dev, vsec + 0x58, &val);
	show_reg("Flash Status/Control Register", val);
	pci_read_config_dword(dev, vsec + 0x58, &val);
	show_reg("Flash Data Port", val);

#undef show_reg
}

static void dump_afu_descriptor(struct cxl_afu *afu)
{
	u64 val, afu_cr_num, afu_cr_off, afu_cr_len;
	int i;

#define show_reg(name, what) \
	dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)

	val = AFUD_READ_INFO(afu);
	show_reg("num_ints_per_process", AFUD_NUM_INTS_PER_PROC(val));
	show_reg("num_of_processes", AFUD_NUM_PROCS(val));
	show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
	show_reg("req_prog_mode", val & 0xffffULL);
	afu_cr_num = AFUD_NUM_CRS(val);

	val = AFUD_READ(afu, 0x8);
	show_reg("Reserved", val);
	val = AFUD_READ(afu, 0x10);
	show_reg("Reserved", val);
	val = AFUD_READ(afu, 0x18);
	show_reg("Reserved", val);

	val = AFUD_READ_CR(afu);
	show_reg("Reserved", (val >> (63-7)) & 0xff);
	show_reg("AFU_CR_len", AFUD_CR_LEN(val));
	afu_cr_len = AFUD_CR_LEN(val) * 256;

	val = AFUD_READ_CR_OFF(afu);
	afu_cr_off = val;
	show_reg("AFU_CR_offset", val);

	val = AFUD_READ_PPPSA(afu);
	show_reg("PerProcessPSA_control", (val >> (63-7)) & 0xff);
	show_reg("PerProcessPSA Length", AFUD_PPPSA_LEN(val));

	val = AFUD_READ_PPPSA_OFF(afu);
	show_reg("PerProcessPSA_offset", val);

	val = AFUD_READ_EB(afu);
	show_reg("Reserved", (val >> (63-7)) & 0xff);
	show_reg("AFU_EB_len", AFUD_EB_LEN(val));

	val = AFUD_READ_EB_OFF(afu);
	show_reg("AFU_EB_offset", val);

	for (i = 0; i < afu_cr_num; i++) {
		val = AFUD_READ_LE(afu, afu_cr_off + i * afu_cr_len);
		show_reg("CR Vendor", val & 0xffff);
		show_reg("CR Device", (val >> 16) & 0xffff);
	}
#undef show_reg
}

#define CAPP_UNIT0_ID 0xBA
#define CAPP_UNIT1_ID 0XBE

static u64 get_capp_unit_id(struct device_node *np)
{
	u32 phb_index;

	/*
	 * For chips other than POWER8NVL, we only have CAPP 0,
	 * irrespective of which PHB is used.
	 */
	if (!pvr_version_is(PVR_POWER8NVL))
		return CAPP_UNIT0_ID;

	/*
	 * For POWER8NVL, assume CAPP 0 is attached to PHB0 and
	 * CAPP 1 is attached to PHB1.
	 */
	if (of_property_read_u32(np, "ibm,phb-index", &phb_index))
		return 0;

	if (phb_index == 0)
		return CAPP_UNIT0_ID;

	if (phb_index == 1)
		return CAPP_UNIT1_ID;

	return 0;
}

static int calc_capp_routing(struct pci_dev *dev, u64 *chipid, u64 *capp_unit_id)
{
	struct device_node *np;
	const __be32 *prop;

	if (!(np = pnv_pci_get_phb_node(dev)))
		return -ENODEV;

	while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL)))
		np = of_get_next_parent(np);
	if (!np)
		return -ENODEV;
	*chipid = be32_to_cpup(prop);
	*capp_unit_id = get_capp_unit_id(np);
	of_node_put(np);
	if (!*capp_unit_id) {
		pr_err("cxl: invalid capp unit id\n");
		return -ENODEV;
	}

	return 0;
}

static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev)
{
	u64 psl_dsnctl, psl_fircntl;
	u64 chipid;
	u64 capp_unit_id;
	int rc;

	rc = calc_capp_routing(dev, &chipid, &capp_unit_id);
	if (rc)
		return rc;

	psl_dsnctl = 0x0000900000000000ULL; /* pteupd ttype, scdone */
	psl_dsnctl |= (0x2ULL << (63-38)); /* MMIO hang pulse: 256 us */
	/* Tell PSL where to route data to */
	psl_dsnctl |= (chipid << (63-5));
	psl_dsnctl |= (capp_unit_id << (63-13));

	cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl);
	cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
	/* snoop write mask */
	cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
	/* set fir_cntl to recommended value for production env */
	psl_fircntl = (0x2ULL << (63-3)); /* ce_report */
	psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */
	psl_fircntl |= 0x1ULL; /* ce_thresh */
	cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl);
	/* for debugging with trace arrays */
	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);

	return 0;
}

static int init_implementation_adapter_xsl_regs(struct cxl *adapter, struct pci_dev *dev)
{
	u64 xsl_dsnctl;
	u64 chipid;
	u64 capp_unit_id;
	int rc;

	rc = calc_capp_routing(dev, &chipid, &capp_unit_id);
	if (rc)
		return rc;

	/* Tell XSL where to route data to */
	xsl_dsnctl = 0x0000600000000000ULL | (chipid << (63-5));
	xsl_dsnctl |= (capp_unit_id << (63-13));
	cxl_p1_write(adapter, CXL_XSL_DSNCTL, xsl_dsnctl);

	return 0;
}

/* PSL & XSL */
#define TBSYNC_CAL(n) (((u64)n & 0x7) << (63-3))
#define TBSYNC_CNT(n) (((u64)n & 0x7) << (63-6))
/* For the PSL this is a multiple for 0 < n <= 7: */
#define PSL_2048_250MHZ_CYCLES 1

static void write_timebase_ctrl_psl(struct cxl *adapter)
{
	cxl_p1_write(adapter, CXL_PSL_TB_CTLSTAT,
		     TBSYNC_CNT(2 * PSL_2048_250MHZ_CYCLES));
}

/* XSL */
#define TBSYNC_ENA (1ULL << 63)
/* For the XSL this is 2**n * 2000 clocks for 0 < n <= 6: */
#define XSL_2000_CLOCKS 1
#define XSL_4000_CLOCKS 2
#define XSL_8000_CLOCKS 3

static void write_timebase_ctrl_xsl(struct cxl *adapter)
{
	cxl_p1_write(adapter, CXL_XSL_TB_CTLSTAT,
		     TBSYNC_ENA |
		     TBSYNC_CAL(3) |
		     TBSYNC_CNT(XSL_4000_CLOCKS));
}

static u64 timebase_read_psl(struct cxl *adapter)
{
	return cxl_p1_read(adapter, CXL_PSL_Timebase);
}

static u64 timebase_read_xsl(struct cxl *adapter)
{
	return cxl_p1_read(adapter, CXL_XSL_Timebase);
}

static void cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
{
	u64 psl_tb;
	int delta;
	unsigned int retry = 0;
	struct device_node *np;

	adapter->psl_timebase_synced = false;

	if (!(np = pnv_pci_get_phb_node(dev)))
		return;

	/* Do not fail when CAPP timebase sync is not supported by OPAL */
	of_node_get(np);
	if (! of_get_property(np, "ibm,capp-timebase-sync", NULL)) {
		of_node_put(np);
		dev_info(&dev->dev, "PSL timebase inactive: OPAL support missing\n");
		return;
	}
	of_node_put(np);

	/*
	 * Setup PSL Timebase Control and Status register
	 * with the recommended Timebase Sync Count value
	 */
	adapter->native->sl_ops->write_timebase_ctrl(adapter);

	/* Enable PSL Timebase */
	cxl_p1_write(adapter, CXL_PSL_Control, 0x0000000000000000);
	cxl_p1_write(adapter, CXL_PSL_Control, CXL_PSL_Control_tb);

	/* Wait until CORE TB and PSL TB difference <= 16usecs */
	do {
		msleep(1);
		if (retry++ > 5) {
			dev_info(&dev->dev, "PSL timebase can't synchronize\n");
			return;
		}
		psl_tb = adapter->native->sl_ops->timebase_read(adapter);
		delta = mftb() - psl_tb;
		if (delta < 0)
			delta = -delta;
	} while (tb_to_ns(delta) > 16000);

	adapter->psl_timebase_synced = true;
	return;
}

static int init_implementation_afu_psl_regs(struct cxl_afu *afu)
{
	/* read/write masks for this slice */
	cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL);
	/* APC read/write masks for this slice */
	cxl_p1n_write(afu, CXL_PSL_COALLOC_A, 0xFF000000FEFEFEFEULL);
	/* for debugging with trace arrays */
	cxl_p1n_write(afu, CXL_PSL_SLICE_TRACE, 0x0000FFFF00000000ULL);
	cxl_p1n_write(afu, CXL_PSL_RXCTL_A, CXL_PSL_RXCTL_AFUHP_4S);

	return 0;
}

int cxl_pci_setup_irq(struct cxl *adapter, unsigned int hwirq,
		unsigned int virq)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_ioda_msi_setup(dev, hwirq, virq);
}

int cxl_update_image_control(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
	int rc;
	int vsec;
	u8 image_state;

	if (!(vsec = find_cxl_vsec(dev))) {
		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
		return -ENODEV;
	}

	if ((rc = CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state))) {
		dev_err(&dev->dev, "failed to read image state: %i\n", rc);
		return rc;
	}

	if (adapter->perst_loads_image)
		image_state |= CXL_VSEC_PERST_LOADS_IMAGE;
	else
		image_state &= ~CXL_VSEC_PERST_LOADS_IMAGE;

	if (adapter->perst_select_user)
		image_state |= CXL_VSEC_PERST_SELECT_USER;
	else
		image_state &= ~CXL_VSEC_PERST_SELECT_USER;

	if ((rc = CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, image_state))) {
		dev_err(&dev->dev, "failed to update image control: %i\n", rc);
		return rc;
	}

	return 0;
}

int cxl_pci_alloc_one_irq(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_alloc_hwirqs(dev, 1);
}

void cxl_pci_release_one_irq(struct cxl *adapter, int hwirq)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_release_hwirqs(dev, hwirq, 1);
}

int cxl_pci_alloc_irq_ranges(struct cxl_irq_ranges *irqs,
			struct cxl *adapter, unsigned int num)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	return pnv_cxl_alloc_hwirq_ranges(irqs, dev, num);
}

void cxl_pci_release_irq_ranges(struct cxl_irq_ranges *irqs,
				struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);

	pnv_cxl_release_hwirq_ranges(irqs, dev);
}

static int setup_cxl_bars(struct pci_dev *dev)
{
	/* Safety check in case we get backported to < 3.17 without M64 */
	if ((p1_base(dev) < 0x100000000ULL) ||
	    (p2_base(dev) < 0x100000000ULL)) {
		dev_err(&dev->dev, "ABORTING: M32 BAR assignment incompatible with CXL\n");
		return -ENODEV;
	}

	/*
	 * BAR 4/5 has a special meaning for CXL and must be programmed with a
	 * special value corresponding to the CXL protocol address range.
	 * For POWER 8 that means bits 48:49 must be set to 10
	 */
	pci_write_config_dword(dev, PCI_BASE_ADDRESS_4, 0x00000000);
	pci_write_config_dword(dev, PCI_BASE_ADDRESS_5, 0x00020000);

	return 0;
}

#ifdef CONFIG_CXL_BIMODAL

struct cxl_switch_work {
	struct pci_dev *dev;
	struct work_struct work;
	int vsec;
	int mode;
};

static void switch_card_to_cxl(struct work_struct *work)
{
	struct cxl_switch_work *switch_work =
		container_of(work, struct cxl_switch_work, work);
	struct pci_dev *dev = switch_work->dev;
	struct pci_bus *bus = dev->bus;
	struct pci_controller *hose = pci_bus_to_host(bus);
	struct pci_dev *bridge;
	struct pnv_php_slot *php_slot;
	unsigned int devfn;
	u8 val;
	int rc;

	dev_info(&bus->dev, "cxl: Preparing for mode switch...\n");
	bridge = list_first_entry_or_null(&hose->bus->devices, struct pci_dev,
					  bus_list);
	if (!bridge) {
		dev_WARN(&bus->dev, "cxl: Couldn't find root port!\n");
		goto err_dev_put;
	}

	php_slot = pnv_php_find_slot(pci_device_to_OF_node(bridge));
	if (!php_slot) {
		dev_err(&bus->dev, "cxl: Failed to find slot hotplug "
			           "information. You may need to upgrade "
			           "skiboot. Aborting.\n");
		goto err_dev_put;
	}

	rc = CXL_READ_VSEC_MODE_CONTROL(dev, switch_work->vsec, &val);
	if (rc) {
		dev_err(&bus->dev, "cxl: Failed to read CAPI mode control: %i\n", rc);
		goto err_dev_put;
	}
	devfn = dev->devfn;

	/* Release the reference obtained in cxl_check_and_switch_mode() */
	pci_dev_put(dev);

	dev_dbg(&bus->dev, "cxl: Removing PCI devices from kernel\n");
	pci_lock_rescan_remove();
	pci_hp_remove_devices(bridge->subordinate);
	pci_unlock_rescan_remove();

	/* Switch the CXL protocol on the card */
	if (switch_work->mode == CXL_BIMODE_CXL) {
		dev_info(&bus->dev, "cxl: Switching card to CXL mode\n");
		val &= ~CXL_VSEC_PROTOCOL_MASK;
		val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE;
		rc = pnv_cxl_enable_phb_kernel_api(hose, true);
		if (rc) {
			dev_err(&bus->dev, "cxl: Failed to enable kernel API"
				           " on real PHB, aborting\n");
			goto err_free_work;
		}
	} else {
		dev_WARN(&bus->dev, "cxl: Switching card to PCI mode not supported!\n");
		goto err_free_work;
	}

	rc = CXL_WRITE_VSEC_MODE_CONTROL_BUS(bus, devfn, switch_work->vsec, val);
	if (rc) {
		dev_err(&bus->dev, "cxl: Failed to configure CXL protocol: %i\n", rc);
		goto err_free_work;
	}

	/*
	 * The CAIA spec (v1.1, Section 10.6 Bi-modal Device Support) states
	 * we must wait 100ms after this mode switch before touching PCIe config
	 * space.
	 */
	msleep(100);

	/*
	 * Hot reset to cause the card to come back in cxl mode. A
	 * OPAL_RESET_PCI_LINK would be sufficient, but currently lacks support
	 * in skiboot, so we use a hot reset instead.
	 *
	 * We call pci_set_pcie_reset_state() on the bridge, as a CAPI card is
	 * guaranteed to sit directly under the root port, and setting the reset
	 * state on a device directly under the root port is equivalent to doing
	 * it on the root port iself.
	 */
	dev_info(&bus->dev, "cxl: Configuration write complete, resetting card\n");
	pci_set_pcie_reset_state(bridge, pcie_hot_reset);
	pci_set_pcie_reset_state(bridge, pcie_deassert_reset);

	dev_dbg(&bus->dev, "cxl: Offlining slot\n");
	rc = pnv_php_set_slot_power_state(&php_slot->slot, OPAL_PCI_SLOT_OFFLINE);
	if (rc) {
		dev_err(&bus->dev, "cxl: OPAL offlining call failed: %i\n", rc);
		goto err_free_work;
	}

	dev_dbg(&bus->dev, "cxl: Onlining and probing slot\n");
	rc = pnv_php_set_slot_power_state(&php_slot->slot, OPAL_PCI_SLOT_ONLINE);
	if (rc) {
		dev_err(&bus->dev, "cxl: OPAL onlining call failed: %i\n", rc);
		goto err_free_work;
	}

	pci_lock_rescan_remove();
	pci_hp_add_devices(bridge->subordinate);
	pci_unlock_rescan_remove();

	dev_info(&bus->dev, "cxl: CAPI mode switch completed\n");
	kfree(switch_work);
	return;

err_dev_put:
	/* Release the reference obtained in cxl_check_and_switch_mode() */
	pci_dev_put(dev);
err_free_work:
	kfree(switch_work);
}

int cxl_check_and_switch_mode(struct pci_dev *dev, int mode, int vsec)
{
	struct cxl_switch_work *work;
	u8 val;
	int rc;

	if (!cpu_has_feature(CPU_FTR_HVMODE))
		return -ENODEV;

	if (!vsec) {
		vsec = find_cxl_vsec(dev);
		if (!vsec) {
			dev_info(&dev->dev, "CXL VSEC not found\n");
			return -ENODEV;
		}
	}

	rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val);
	if (rc) {
		dev_err(&dev->dev, "Failed to read current mode control: %i", rc);
		return rc;
	}

	if (mode == CXL_BIMODE_PCI) {
		if (!(val & CXL_VSEC_PROTOCOL_ENABLE)) {
			dev_info(&dev->dev, "Card is already in PCI mode\n");
			return 0;
		}
		/*
		 * TODO: Before it's safe to switch the card back to PCI mode
		 * we need to disable the CAPP and make sure any cachelines the
		 * card holds have been flushed out. Needs skiboot support.
		 */
		dev_WARN(&dev->dev, "CXL mode switch to PCI unsupported!\n");
		return -EIO;
	}

	if (val & CXL_VSEC_PROTOCOL_ENABLE) {
		dev_info(&dev->dev, "Card is already in CXL mode\n");
		return 0;
	}

	dev_info(&dev->dev, "Card is in PCI mode, scheduling kernel thread "
			    "to switch to CXL mode\n");

	work = kmalloc(sizeof(struct cxl_switch_work), GFP_KERNEL);
	if (!work)
		return -ENOMEM;

	pci_dev_get(dev);
	work->dev = dev;
	work->vsec = vsec;
	work->mode = mode;
	INIT_WORK(&work->work, switch_card_to_cxl);

	schedule_work(&work->work);

	/*
	 * We return a failure now to abort the driver init. Once the
	 * link has been cycled and the card is in cxl mode we will
	 * come back (possibly using the generic cxl driver), but
	 * return success as the card should then be in cxl mode.
	 *
	 * TODO: What if the card comes back in PCI mode even after
	 *       the switch?  Don't want to spin endlessly.
	 */
	return -EBUSY;
}
EXPORT_SYMBOL_GPL(cxl_check_and_switch_mode);

#endif /* CONFIG_CXL_BIMODAL */

static int setup_cxl_protocol_area(struct pci_dev *dev)
{
	u8 val;
	int rc;
	int vsec = find_cxl_vsec(dev);

	if (!vsec) {
		dev_info(&dev->dev, "CXL VSEC not found\n");
		return -ENODEV;
	}

	rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val);
	if (rc) {
		dev_err(&dev->dev, "Failed to read current mode control: %i\n", rc);
		return rc;
	}

	if (!(val & CXL_VSEC_PROTOCOL_ENABLE)) {
		dev_err(&dev->dev, "Card not in CAPI mode!\n");
		return -EIO;
	}

	if ((val & CXL_VSEC_PROTOCOL_MASK) != CXL_VSEC_PROTOCOL_256TB) {
		val &= ~CXL_VSEC_PROTOCOL_MASK;
		val |= CXL_VSEC_PROTOCOL_256TB;
		rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val);
		if (rc) {
			dev_err(&dev->dev, "Failed to set CXL protocol area: %i\n", rc);
			return rc;
		}
	}

	return 0;
}

static int pci_map_slice_regs(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
{
	u64 p1n_base, p2n_base, afu_desc;
	const u64 p1n_size = 0x100;
	const u64 p2n_size = 0x1000;

	p1n_base = p1_base(dev) + 0x10000 + (afu->slice * p1n_size);
	p2n_base = p2_base(dev) + (afu->slice * p2n_size);
	afu->psn_phys = p2_base(dev) + (adapter->native->ps_off + (afu->slice * adapter->ps_size));
	afu_desc = p2_base(dev) + adapter->native->afu_desc_off + (afu->slice * adapter->native->afu_desc_size);

	if (!(afu->native->p1n_mmio = ioremap(p1n_base, p1n_size)))
		goto err;
	if (!(afu->p2n_mmio = ioremap(p2n_base, p2n_size)))
		goto err1;
	if (afu_desc) {
		if (!(afu->native->afu_desc_mmio = ioremap(afu_desc, adapter->native->afu_desc_size)))
			goto err2;
	}

	return 0;
err2:
	iounmap(afu->p2n_mmio);
err1:
	iounmap(afu->native->p1n_mmio);
err:
	dev_err(&afu->dev, "Error mapping AFU MMIO regions\n");
	return -ENOMEM;
}

static void pci_unmap_slice_regs(struct cxl_afu *afu)
{
	if (afu->p2n_mmio) {
		iounmap(afu->p2n_mmio);
		afu->p2n_mmio = NULL;
	}
	if (afu->native->p1n_mmio) {
		iounmap(afu->native->p1n_mmio);
		afu->native->p1n_mmio = NULL;
	}
	if (afu->native->afu_desc_mmio) {
		iounmap(afu->native->afu_desc_mmio);
		afu->native->afu_desc_mmio = NULL;
	}
}

void cxl_pci_release_afu(struct device *dev)
{
	struct cxl_afu *afu = to_cxl_afu(dev);

	pr_devel("%s\n", __func__);

	idr_destroy(&afu->contexts_idr);
	cxl_release_spa(afu);

	kfree(afu->native);
	kfree(afu);
}

/* Expects AFU struct to have recently been zeroed out */
static int cxl_read_afu_descriptor(struct cxl_afu *afu)
{
	u64 val;

	val = AFUD_READ_INFO(afu);
	afu->pp_irqs = AFUD_NUM_INTS_PER_PROC(val);
	afu->max_procs_virtualised = AFUD_NUM_PROCS(val);
	afu->crs_num = AFUD_NUM_CRS(val);

	if (AFUD_AFU_DIRECTED(val))
		afu->modes_supported |= CXL_MODE_DIRECTED;
	if (AFUD_DEDICATED_PROCESS(val))
		afu->modes_supported |= CXL_MODE_DEDICATED;
	if (AFUD_TIME_SLICED(val))
		afu->modes_supported |= CXL_MODE_TIME_SLICED;

	val = AFUD_READ_PPPSA(afu);
	afu->pp_size = AFUD_PPPSA_LEN(val) * 4096;
	afu->psa = AFUD_PPPSA_PSA(val);
	if ((afu->pp_psa = AFUD_PPPSA_PP(val)))
		afu->native->pp_offset = AFUD_READ_PPPSA_OFF(afu);

	val = AFUD_READ_CR(afu);
	afu->crs_len = AFUD_CR_LEN(val) * 256;
	afu->crs_offset = AFUD_READ_CR_OFF(afu);


	/* eb_len is in multiple of 4K */
	afu->eb_len = AFUD_EB_LEN(AFUD_READ_EB(afu)) * 4096;
	afu->eb_offset = AFUD_READ_EB_OFF(afu);

	/* eb_off is 4K aligned so lower 12 bits are always zero */
	if (EXTRACT_PPC_BITS(afu->eb_offset, 0, 11) != 0) {
		dev_warn(&afu->dev,
			 "Invalid AFU error buffer offset %Lx\n",
			 afu->eb_offset);
		dev_info(&afu->dev,
			 "Ignoring AFU error buffer in the descriptor\n");
		/* indicate that no afu buffer exists */
		afu->eb_len = 0;
	}

	return 0;
}

static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu)
{
	int i, rc;
	u32 val;

	if (afu->psa && afu->adapter->ps_size <
			(afu->native->pp_offset + afu->pp_size*afu->max_procs_virtualised)) {
		dev_err(&afu->dev, "per-process PSA can't fit inside the PSA!\n");
		return -ENODEV;
	}

	if (afu->pp_psa && (afu->pp_size < PAGE_SIZE))
		dev_warn(&afu->dev, "AFU uses < PAGE_SIZE per-process PSA!");

	for (i = 0; i < afu->crs_num; i++) {
		rc = cxl_ops->afu_cr_read32(afu, i, 0, &val);
		if (rc || val == 0) {
			dev_err(&afu->dev, "ABORTING: AFU configuration record %i is invalid\n", i);
			return -EINVAL;
		}
	}

	if ((afu->modes_supported & ~CXL_MODE_DEDICATED) && afu->max_procs_virtualised == 0) {
		/*
		 * We could also check this for the dedicated process model
		 * since the architecture indicates it should be set to 1, but
		 * in that case we ignore the value and I'd rather not risk
		 * breaking any existing dedicated process AFUs that left it as
		 * 0 (not that I'm aware of any). It is clearly an error for an
		 * AFU directed AFU to set this to 0, and would have previously
		 * triggered a bug resulting in the maximum not being enforced
		 * at all since idr_alloc treats 0 as no maximum.
		 */
		dev_err(&afu->dev, "AFU does not support any processes\n");
		return -EINVAL;
	}

	return 0;
}

static int sanitise_afu_regs(struct cxl_afu *afu)
{
	u64 reg;

	/*
	 * Clear out any regs that contain either an IVTE or address or may be
	 * waiting on an acknowledgement to try to be a bit safer as we bring
	 * it online
	 */
	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#016llx\n", reg);
		if (cxl_ops->afu_reset(afu))
			return -EIO;
		if (cxl_afu_disable(afu))
			return -EIO;
		if (cxl_psl_purge(afu))
			return -EIO;
	}
	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_AMBAR_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_PSL_SPOffset_An, 0x0000000000000000);
	cxl_p1n_write(afu, CXL_HAURP_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_CSRP_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_AURP1_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_AURP0_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_SSTP1_An, 0x0000000000000000);
	cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000);
	reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
	if (reg) {
		dev_warn(&afu->dev, "AFU had pending DSISR: %#016llx\n", reg);
		if (reg & CXL_PSL_DSISR_TRANS)
			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
		else
			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
	}
	if (afu->adapter->native->sl_ops->register_serr_irq) {
		reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
		if (reg) {
			if (reg & ~0xffff)
				dev_warn(&afu->dev, "AFU had pending SERR: %#016llx\n", reg);
			cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
		}
	}
	reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
	if (reg) {
		dev_warn(&afu->dev, "AFU had pending error status: %#016llx\n", reg);
		cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg);
	}

	return 0;
}

#define ERR_BUFF_MAX_COPY_SIZE PAGE_SIZE
/*
 * afu_eb_read:
 * Called from sysfs and reads the afu error info buffer. The h/w only supports
 * 4/8 bytes aligned access. So in case the requested offset/count arent 8 byte
 * aligned the function uses a bounce buffer which can be max PAGE_SIZE.
 */
ssize_t cxl_pci_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
				loff_t off, size_t count)
{
	loff_t aligned_start, aligned_end;
	size_t aligned_length;
	void *tbuf;
	const void __iomem *ebuf = afu->native->afu_desc_mmio + afu->eb_offset;

	if (count == 0 || off < 0 || (size_t)off >= afu->eb_len)
		return 0;

	/* calculate aligned read window */
	count = min((size_t)(afu->eb_len - off), count);
	aligned_start = round_down(off, 8);
	aligned_end = round_up(off + count, 8);
	aligned_length = aligned_end - aligned_start;

	/* max we can copy in one read is PAGE_SIZE */
	if (aligned_length > ERR_BUFF_MAX_COPY_SIZE) {
		aligned_length = ERR_BUFF_MAX_COPY_SIZE;
		count = ERR_BUFF_MAX_COPY_SIZE - (off & 0x7);
	}

	/* use bounce buffer for copy */
	tbuf = (void *)__get_free_page(GFP_TEMPORARY);
	if (!tbuf)
		return -ENOMEM;

	/* perform aligned read from the mmio region */
	memcpy_fromio(tbuf, ebuf + aligned_start, aligned_length);
	memcpy(buf, tbuf + (off & 0x7), count);

	free_page((unsigned long)tbuf);

	return count;
}

static int pci_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
{
	int rc;

	if ((rc = pci_map_slice_regs(afu, adapter, dev)))
		return rc;

	if ((rc = sanitise_afu_regs(afu)))
		goto err1;

	/* We need to reset the AFU before we can read the AFU descriptor */
	if ((rc = cxl_ops->afu_reset(afu)))
		goto err1;

	if (cxl_verbose)
		dump_afu_descriptor(afu);

	if ((rc = cxl_read_afu_descriptor(afu)))
		goto err1;

	if ((rc = cxl_afu_descriptor_looks_ok(afu)))
		goto err1;

	if (adapter->native->sl_ops->afu_regs_init)
		if ((rc = adapter->native->sl_ops->afu_regs_init(afu)))
			goto err1;

	if (adapter->native->sl_ops->register_serr_irq)
		if ((rc = adapter->native->sl_ops->register_serr_irq(afu)))
			goto err1;

	if ((rc = cxl_native_register_psl_irq(afu)))
		goto err2;

	atomic_set(&afu->configured_state, 0);
	return 0;

err2:
	if (adapter->native->sl_ops->release_serr_irq)
		adapter->native->sl_ops->release_serr_irq(afu);
err1:
	pci_unmap_slice_regs(afu);
	return rc;
}

static void pci_deconfigure_afu(struct cxl_afu *afu)
{
	/*
	 * It's okay to deconfigure when AFU is already locked, otherwise wait
	 * until there are no readers
	 */
	if (atomic_read(&afu->configured_state) != -1) {
		while (atomic_cmpxchg(&afu->configured_state, 0, -1) != -1)
			schedule();
	}
	cxl_native_release_psl_irq(afu);
	if (afu->adapter->native->sl_ops->release_serr_irq)
		afu->adapter->native->sl_ops->release_serr_irq(afu);
	pci_unmap_slice_regs(afu);
}

static int pci_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
{
	struct cxl_afu *afu;
	int rc = -ENOMEM;

	afu = cxl_alloc_afu(adapter, slice);
	if (!afu)
		return -ENOMEM;

	afu->native = kzalloc(sizeof(struct cxl_afu_native), GFP_KERNEL);
	if (!afu->native)
		goto err_free_afu;

	mutex_init(&afu->native->spa_mutex);

	rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice);
	if (rc)
		goto err_free_native;

	rc = pci_configure_afu(afu, adapter, dev);
	if (rc)
		goto err_free_native;

	/* Don't care if this fails */
	cxl_debugfs_afu_add(afu);

	/*
	 * After we call this function we must not free the afu directly, even
	 * if it returns an error!
	 */
	if ((rc = cxl_register_afu(afu)))
		goto err_put1;

	if ((rc = cxl_sysfs_afu_add(afu)))
		goto err_put1;

	adapter->afu[afu->slice] = afu;

	if ((rc = cxl_pci_vphb_add(afu)))
		dev_info(&afu->dev, "Can't register vPHB\n");

	return 0;

err_put1:
	pci_deconfigure_afu(afu);
	cxl_debugfs_afu_remove(afu);
	device_unregister(&afu->dev);
	return rc;

err_free_native:
	kfree(afu->native);
err_free_afu:
	kfree(afu);
	return rc;

}

static void cxl_pci_remove_afu(struct cxl_afu *afu)
{
	pr_devel("%s\n", __func__);

	if (!afu)
		return;

	cxl_pci_vphb_remove(afu);
	cxl_sysfs_afu_remove(afu);
	cxl_debugfs_afu_remove(afu);

	spin_lock(&afu->adapter->afu_list_lock);
	afu->adapter->afu[afu->slice] = NULL;
	spin_unlock(&afu->adapter->afu_list_lock);

	cxl_context_detach_all(afu);
	cxl_ops->afu_deactivate_mode(afu, afu->current_mode);

	pci_deconfigure_afu(afu);
	device_unregister(&afu->dev);
}

int cxl_pci_reset(struct cxl *adapter)
{
	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
	int rc;

	if (adapter->perst_same_image) {
		dev_warn(&dev->dev,
			 "cxl: refusing to reset/reflash when perst_reloads_same_image is set.\n");
		return -EINVAL;
	}

	dev_info(&dev->dev, "CXL reset\n");

	/* the adapter is about to be reset, so ignore errors */
	cxl_data_cache_flush(adapter);

	/* pcie_warm_reset requests a fundamental pci reset which includes a
	 * PERST assert/deassert.  PERST triggers a loading of the image
	 * if "user" or "factory" is selected in sysfs */
	if ((rc = pci_set_pcie_reset_state(dev, pcie_warm_reset))) {
		dev_err(&dev->dev, "cxl: pcie_warm_reset failed\n");
		return rc;
	}

	return rc;
}

static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
{
	if (pci_request_region(dev, 2, "priv 2 regs"))
		goto err1;
	if (pci_request_region(dev, 0, "priv 1 regs"))
		goto err2;

	pr_devel("cxl_map_adapter_regs: p1: %#016llx %#llx, p2: %#016llx %#llx",
			p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev));

	if (!(adapter->native->p1_mmio = ioremap(p1_base(dev), p1_size(dev))))
		goto err3;

	if (!(adapter->native->p2_mmio = ioremap(p2_base(dev), p2_size(dev))))
		goto err4;

	return 0;

err4:
	iounmap(adapter->native->p1_mmio);
	adapter->native->p1_mmio = NULL;
err3:
	pci_release_region(dev, 0);
err2:
	pci_release_region(dev, 2);
err1:
	return -ENOMEM;
}

static void cxl_unmap_adapter_regs(struct cxl *adapter)
{
	if (adapter->native->p1_mmio) {
		iounmap(adapter->native->p1_mmio);
		adapter->native->p1_mmio = NULL;
		pci_release_region(to_pci_dev(adapter->dev.parent), 2);
	}
	if (adapter->native->p2_mmio) {
		iounmap(adapter->native->p2_mmio);
		adapter->native->p2_mmio = NULL;
		pci_release_region(to_pci_dev(adapter->dev.parent), 0);
	}
}

static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
{
	int vsec;
	u32 afu_desc_off, afu_desc_size;
	u32 ps_off, ps_size;
	u16 vseclen;
	u8 image_state;

	if (!(vsec = find_cxl_vsec(dev))) {
		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
		return -ENODEV;
	}

	CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
	if (vseclen < CXL_VSEC_MIN_SIZE) {
		dev_err(&dev->dev, "ABORTING: CXL VSEC too short\n");
		return -EINVAL;
	}

	CXL_READ_VSEC_STATUS(dev, vsec, &adapter->vsec_status);
	CXL_READ_VSEC_PSL_REVISION(dev, vsec, &adapter->psl_rev);
	CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, &adapter->caia_major);
	CXL_READ_VSEC_CAIA_MINOR(dev, vsec, &adapter->caia_minor);
	CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
	CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
	adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
	adapter->perst_select_user = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);

	CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
	CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off);
	CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, &afu_desc_size);
	CXL_READ_VSEC_PS_OFF(dev, vsec, &ps_off);
	CXL_READ_VSEC_PS_SIZE(dev, vsec, &ps_size);

	/* Convert everything to bytes, because there is NO WAY I'd look at the
	 * code a month later and forget what units these are in ;-) */
	adapter->native->ps_off = ps_off * 64 * 1024;
	adapter->ps_size = ps_size * 64 * 1024;
	adapter->native->afu_desc_off = afu_desc_off * 64 * 1024;
	adapter->native->afu_desc_size = afu_desc_size * 64 * 1024;

	/* Total IRQs - 1 PSL ERROR - #AFU*(1 slice error + 1 DSI) */
	adapter->user_irqs = pnv_cxl_get_irq_count(dev) - 1 - 2*adapter->slices;

	return 0;
}

/*
 * Workaround a PCIe Host Bridge defect on some cards, that can cause
 * malformed Transaction Layer Packet (TLP) errors to be erroneously
 * reported. Mask this error in the Uncorrectable Error Mask Register.
 *
 * The upper nibble of the PSL revision is used to distinguish between
 * different cards. The affected ones have it set to 0.
 */
static void cxl_fixup_malformed_tlp(struct cxl *adapter, struct pci_dev *dev)
{
	int aer;
	u32 data;

	if (adapter->psl_rev & 0xf000)
		return;
	if (!(aer = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)))
		return;
	pci_read_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, &data);
	if (data & PCI_ERR_UNC_MALF_TLP)
		if (data & PCI_ERR_UNC_INTN)
			return;
	data |= PCI_ERR_UNC_MALF_TLP;
	data |= PCI_ERR_UNC_INTN;
	pci_write_config_dword(dev, aer + PCI_ERR_UNCOR_MASK, data);
}

static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
{
	if (adapter->vsec_status & CXL_STATUS_SECOND_PORT)
		return -EBUSY;

	if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
		dev_err(&dev->dev, "ABORTING: CXL requires unsupported features\n");
		return -EINVAL;
	}

	if (!adapter->slices) {
		/* Once we support dynamic reprogramming we can use the card if
		 * it supports loadable AFUs */
		dev_err(&dev->dev, "ABORTING: Device has no AFUs\n");
		return -EINVAL;
	}

	if (!adapter->native->afu_desc_off || !adapter->native->afu_desc_size) {
		dev_err(&dev->dev, "ABORTING: VSEC shows no AFU descriptors\n");
		return -EINVAL;
	}

	if (adapter->ps_size > p2_size(dev) - adapter->native->ps_off) {
		dev_err(&dev->dev, "ABORTING: Problem state size larger than "
				   "available in BAR2: 0x%llx > 0x%llx\n",
			 adapter->ps_size, p2_size(dev) - adapter->native->ps_off);
		return -EINVAL;
	}

	return 0;
}

ssize_t cxl_pci_read_adapter_vpd(struct cxl *adapter, void *buf, size_t len)
{
	return pci_read_vpd(to_pci_dev(adapter->dev.parent), 0, len, buf);
}

static void cxl_release_adapter(struct device *dev)
{
	struct cxl *adapter = to_cxl_adapter(dev);

	pr_devel("cxl_release_adapter\n");

	cxl_remove_adapter_nr(adapter);

	kfree(adapter->native);
	kfree(adapter);
}

#define CXL_PSL_ErrIVTE_tberror (0x1ull << (63-31))

static int sanitise_adapter_regs(struct cxl *adapter)
{
	/* Clear PSL tberror bit by writing 1 to it */
	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, CXL_PSL_ErrIVTE_tberror);
	return cxl_tlb_slb_invalidate(adapter);
}

/* This should contain *only* operations that can safely be done in
 * both creation and recovery.
 */
static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
{
	int rc;

	adapter->dev.parent = &dev->dev;
	adapter->dev.release = cxl_release_adapter;
	pci_set_drvdata(dev, adapter);

	rc = pci_enable_device(dev);
	if (rc) {
		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
		return rc;
	}

	if ((rc = cxl_read_vsec(adapter, dev)))
		return rc;

	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
	        return rc;

	cxl_fixup_malformed_tlp(adapter, dev);

	if ((rc = setup_cxl_bars(dev)))
		return rc;

	if ((rc = setup_cxl_protocol_area(dev)))
		return rc;

	if ((rc = cxl_update_image_control(adapter)))
		return rc;

	if ((rc = cxl_map_adapter_regs(adapter, dev)))
		return rc;

	if ((rc = sanitise_adapter_regs(adapter)))
		goto err;

	if ((rc = adapter->native->sl_ops->adapter_regs_init(adapter, dev)))
		goto err;

	/* Required for devices using CAPP DMA mode, harmless for others */
	pci_set_master(dev);

	if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode)))
		goto err;

	/* If recovery happened, the last step is to turn on snooping.
	 * In the non-recovery case this has no effect */
	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON)))
		goto err;

	/* Ignore error, adapter init is not dependant on timebase sync */
	cxl_setup_psl_timebase(adapter, dev);

	if ((rc = cxl_native_register_psl_err_irq(adapter)))
		goto err;

	return 0;

err:
	cxl_unmap_adapter_regs(adapter);
	return rc;

}

static void cxl_deconfigure_adapter(struct cxl *adapter)
{
	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);

	cxl_native_release_psl_err_irq(adapter);
	cxl_unmap_adapter_regs(adapter);

	pci_disable_device(pdev);
}

static const struct cxl_service_layer_ops psl_ops = {
	.adapter_regs_init = init_implementation_adapter_psl_regs,
	.afu_regs_init = init_implementation_afu_psl_regs,
	.register_serr_irq = cxl_native_register_serr_irq,
	.release_serr_irq = cxl_native_release_serr_irq,
	.debugfs_add_adapter_sl_regs = cxl_debugfs_add_adapter_psl_regs,
	.debugfs_add_afu_sl_regs = cxl_debugfs_add_afu_psl_regs,
	.psl_irq_dump_registers = cxl_native_psl_irq_dump_regs,
	.err_irq_dump_registers = cxl_native_err_irq_dump_regs,
	.debugfs_stop_trace = cxl_stop_trace,
	.write_timebase_ctrl = write_timebase_ctrl_psl,
	.timebase_read = timebase_read_psl,
	.capi_mode = OPAL_PHB_CAPI_MODE_CAPI,
	.needs_reset_before_disable = true,
};

static const struct cxl_service_layer_ops xsl_ops = {
	.adapter_regs_init = init_implementation_adapter_xsl_regs,
	.debugfs_add_adapter_sl_regs = cxl_debugfs_add_adapter_xsl_regs,
	.write_timebase_ctrl = write_timebase_ctrl_xsl,
	.timebase_read = timebase_read_xsl,
	.capi_mode = OPAL_PHB_CAPI_MODE_DMA,
};

static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev)
{
	if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) {
		/* Mellanox CX-4 */
		dev_info(&dev->dev, "Device uses an XSL\n");
		adapter->native->sl_ops = &xsl_ops;
		adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */
	} else {
		dev_info(&dev->dev, "Device uses a PSL\n");
		adapter->native->sl_ops = &psl_ops;
	}
}


static struct cxl *cxl_pci_init_adapter(struct pci_dev *dev)
{
	struct cxl *adapter;
	int rc;

	adapter = cxl_alloc_adapter();
	if (!adapter)
		return ERR_PTR(-ENOMEM);

	adapter->native = kzalloc(sizeof(struct cxl_native), GFP_KERNEL);
	if (!adapter->native) {
		rc = -ENOMEM;
		goto err_release;
	}

	set_sl_ops(adapter, dev);

	/* Set defaults for parameters which need to persist over
	 * configure/reconfigure
	 */
	adapter->perst_loads_image = true;
	adapter->perst_same_image = false;

	rc = cxl_configure_adapter(adapter, dev);
	if (rc) {
		pci_disable_device(dev);
		goto err_release;
	}

	/* Don't care if this one fails: */
	cxl_debugfs_adapter_add(adapter);

	/*
	 * After we call this function we must not free the adapter directly,
	 * even if it returns an error!
	 */
	if ((rc = cxl_register_adapter(adapter)))
		goto err_put1;

	if ((rc = cxl_sysfs_adapter_add(adapter)))
		goto err_put1;

	/* Release the context lock as adapter is configured */
	cxl_adapter_context_unlock(adapter);

	return adapter;

err_put1:
	/* This should mirror cxl_remove_adapter, except without the
	 * sysfs parts
	 */
	cxl_debugfs_adapter_remove(adapter);
	cxl_deconfigure_adapter(adapter);
	device_unregister(&adapter->dev);
	return ERR_PTR(rc);

err_release:
	cxl_release_adapter(&adapter->dev);
	return ERR_PTR(rc);
}

static void cxl_pci_remove_adapter(struct cxl *adapter)
{
	pr_devel("cxl_remove_adapter\n");

	cxl_sysfs_adapter_remove(adapter);
	cxl_debugfs_adapter_remove(adapter);

	cxl_deconfigure_adapter(adapter);

	device_unregister(&adapter->dev);
}

#define CXL_MAX_PCIEX_PARENT 2

static int cxl_slot_is_switched(struct pci_dev *dev)
{
	struct device_node *np;
	int depth = 0;
	const __be32 *prop;

	if (!(np = pci_device_to_OF_node(dev))) {
		pr_err("cxl: np = NULL\n");
		return -ENODEV;
	}
	of_node_get(np);
	while (np) {
		np = of_get_next_parent(np);
		prop = of_get_property(np, "device_type", NULL);
		if (!prop || strcmp((char *)prop, "pciex"))
			break;
		depth++;
	}
	of_node_put(np);
	return (depth > CXL_MAX_PCIEX_PARENT);
}

bool cxl_slot_is_supported(struct pci_dev *dev, int flags)
{
	if (!cpu_has_feature(CPU_FTR_HVMODE))
		return false;

	if ((flags & CXL_SLOT_FLAG_DMA) && (!pvr_version_is(PVR_POWER8NVL))) {
		/*
		 * CAPP DMA mode is technically supported on regular P8, but
		 * will EEH if the card attempts to access memory < 4GB, which
		 * we cannot realistically avoid. We might be able to work
		 * around the issue, but until then return unsupported:
		 */
		return false;
	}

	if (cxl_slot_is_switched(dev))
		return false;

	/*
	 * XXX: This gets a little tricky on regular P8 (not POWER8NVL) since
	 * the CAPP can be connected to PHB 0, 1 or 2 on a first come first
	 * served basis, which is racy to check from here. If we need to
	 * support this in future we might need to consider having this
	 * function effectively reserve it ahead of time.
	 *
	 * Currently, the only user of this API is the Mellanox CX4, which is
	 * only supported on P8NVL due to the above mentioned limitation of
	 * CAPP DMA mode and therefore does not need to worry about this. If the
	 * issue with CAPP DMA mode is later worked around on P8 we might need
	 * to revisit this.
	 */

	return true;
}
EXPORT_SYMBOL_GPL(cxl_slot_is_supported);


static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
	struct cxl *adapter;
	int slice;
	int rc;

	if (cxl_pci_is_vphb_device(dev)) {
		dev_dbg(&dev->dev, "cxl_init_adapter: Ignoring cxl vphb device\n");
		return -ENODEV;
	}

	if (cxl_slot_is_switched(dev)) {
		dev_info(&dev->dev, "Ignoring card on incompatible PCI slot\n");
		return -ENODEV;
	}

	if (cxl_verbose)
		dump_cxl_config_space(dev);

	adapter = cxl_pci_init_adapter(dev);
	if (IS_ERR(adapter)) {
		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
		return PTR_ERR(adapter);
	}

	for (slice = 0; slice < adapter->slices; slice++) {
		if ((rc = pci_init_afu(adapter, slice, dev))) {
			dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc);
			continue;
		}

		rc = cxl_afu_select_best_mode(adapter->afu[slice]);
		if (rc)
			dev_err(&dev->dev, "AFU %i failed to start: %i\n", slice, rc);
	}

	if (pnv_pci_on_cxl_phb(dev) && adapter->slices >= 1)
		pnv_cxl_phb_set_peer_afu(dev, adapter->afu[0]);

	return 0;
}

static void cxl_remove(struct pci_dev *dev)
{
	struct cxl *adapter = pci_get_drvdata(dev);
	struct cxl_afu *afu;
	int i;

	/*
	 * Lock to prevent someone grabbing a ref through the adapter list as
	 * we are removing it
	 */
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];
		cxl_pci_remove_afu(afu);
	}
	cxl_pci_remove_adapter(adapter);
}

static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,
						pci_channel_state_t state)
{
	struct pci_dev *afu_dev;
	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
	pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET;

	/* There should only be one entry, but go through the list
	 * anyway
	 */
	list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
		if (!afu_dev->driver)
			continue;

		afu_dev->error_state = state;

		if (afu_dev->driver->err_handler)
			afu_result = afu_dev->driver->err_handler->error_detected(afu_dev,
										  state);
		/* Disconnect trumps all, NONE trumps NEED_RESET */
		if (afu_result == PCI_ERS_RESULT_DISCONNECT)
			result = PCI_ERS_RESULT_DISCONNECT;
		else if ((afu_result == PCI_ERS_RESULT_NONE) &&
			 (result == PCI_ERS_RESULT_NEED_RESET))
			result = PCI_ERS_RESULT_NONE;
	}
	return result;
}

static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
					       pci_channel_state_t state)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET, afu_result;
	int i;

	/* At this point, we could still have an interrupt pending.
	 * Let's try to get them out of the way before they do
	 * anything we don't like.
	 */
	schedule();

	/* If we're permanently dead, give up. */
	if (state == pci_channel_io_perm_failure) {
		/* Tell the AFU drivers; but we don't care what they
		 * say, we're going away.
		 */
		for (i = 0; i < adapter->slices; i++) {
			afu = adapter->afu[i];
			/* Only participate in EEH if we are on a virtual PHB */
			if (afu->phb == NULL)
				return PCI_ERS_RESULT_NONE;
			cxl_vphb_error_detected(afu, state);
		}
		return PCI_ERS_RESULT_DISCONNECT;
	}

	/* Are we reflashing?
	 *
	 * If we reflash, we could come back as something entirely
	 * different, including a non-CAPI card. As such, by default
	 * we don't participate in the process. We'll be unbound and
	 * the slot re-probed. (TODO: check EEH doesn't blindly rebind
	 * us!)
	 *
	 * However, this isn't the entire story: for reliablity
	 * reasons, we usually want to reflash the FPGA on PERST in
	 * order to get back to a more reliable known-good state.
	 *
	 * This causes us a bit of a problem: if we reflash we can't
	 * trust that we'll come back the same - we could have a new
	 * image and been PERSTed in order to load that
	 * image. However, most of the time we actually *will* come
	 * back the same - for example a regular EEH event.
	 *
	 * Therefore, we allow the user to assert that the image is
	 * indeed the same and that we should continue on into EEH
	 * anyway.
	 */
	if (adapter->perst_loads_image && !adapter->perst_same_image) {
		/* TODO take the PHB out of CXL mode */
		dev_info(&pdev->dev, "reflashing, so opting out of EEH!\n");
		return PCI_ERS_RESULT_NONE;
	}

	/*
	 * At this point, we want to try to recover.  We'll always
	 * need a complete slot reset: we don't trust any other reset.
	 *
	 * Now, we go through each AFU:
	 *  - We send the driver, if bound, an error_detected callback.
	 *    We expect it to clean up, but it can also tell us to give
	 *    up and permanently detach the card. To simplify things, if
	 *    any bound AFU driver doesn't support EEH, we give up on EEH.
	 *
	 *  - We detach all contexts associated with the AFU. This
	 *    does not free them, but puts them into a CLOSED state
	 *    which causes any the associated files to return useful
	 *    errors to userland. It also unmaps, but does not free,
	 *    any IRQs.
	 *
	 *  - We clean up our side: releasing and unmapping resources we hold
	 *    so we can wire them up again when the hardware comes back up.
	 *
	 * Driver authors should note:
	 *
	 *  - Any contexts you create in your kernel driver (except
	 *    those associated with anonymous file descriptors) are
	 *    your responsibility to free and recreate. Likewise with
	 *    any attached resources.
	 *
	 *  - We will take responsibility for re-initialising the
	 *    device context (the one set up for you in
	 *    cxl_pci_enable_device_hook and accessed through
	 *    cxl_get_context). If you've attached IRQs or other
	 *    resources to it, they remains yours to free.
	 *
	 * You can call the same functions to release resources as you
	 * normally would: we make sure that these functions continue
	 * to work when the hardware is down.
	 *
	 * Two examples:
	 *
	 * 1) If you normally free all your resources at the end of
	 *    each request, or if you use anonymous FDs, your
	 *    error_detected callback can simply set a flag to tell
	 *    your driver not to start any new calls. You can then
	 *    clear the flag in the resume callback.
	 *
	 * 2) If you normally allocate your resources on startup:
	 *     * Set a flag in error_detected as above.
	 *     * Let CXL detach your contexts.
	 *     * In slot_reset, free the old resources and allocate new ones.
	 *     * In resume, clear the flag to allow things to start.
	 */
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		afu_result = cxl_vphb_error_detected(afu, state);

		cxl_context_detach_all(afu);
		cxl_ops->afu_deactivate_mode(afu, afu->current_mode);
		pci_deconfigure_afu(afu);

		/* Disconnect trumps all, NONE trumps NEED_RESET */
		if (afu_result == PCI_ERS_RESULT_DISCONNECT)
			result = PCI_ERS_RESULT_DISCONNECT;
		else if ((afu_result == PCI_ERS_RESULT_NONE) &&
			 (result == PCI_ERS_RESULT_NEED_RESET))
			result = PCI_ERS_RESULT_NONE;
	}

	/* should take the context lock here */
	if (cxl_adapter_context_lock(adapter) != 0)
		dev_warn(&adapter->dev,
			 "Couldn't take context lock with %d active-contexts\n",
			 atomic_read(&adapter->contexts_num));

	cxl_deconfigure_adapter(adapter);

	return result;
}

static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	struct cxl_context *ctx;
	struct pci_dev *afu_dev;
	pci_ers_result_t afu_result = PCI_ERS_RESULT_RECOVERED;
	pci_ers_result_t result = PCI_ERS_RESULT_RECOVERED;
	int i;

	if (cxl_configure_adapter(adapter, pdev))
		goto err;

	/*
	 * Unlock context activation for the adapter. Ideally this should be
	 * done in cxl_pci_resume but cxlflash module tries to activate the
	 * master context as part of slot_reset callback.
	 */
	cxl_adapter_context_unlock(adapter);

	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		if (pci_configure_afu(afu, adapter, pdev))
			goto err;

		if (cxl_afu_select_best_mode(afu))
			goto err;

		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
			/* Reset the device context.
			 * TODO: make this less disruptive
			 */
			ctx = cxl_get_context(afu_dev);

			if (ctx && cxl_release_context(ctx))
				goto err;

			ctx = cxl_dev_context_init(afu_dev);
			if (!ctx)
				goto err;

			afu_dev->dev.archdata.cxl_ctx = ctx;

			if (cxl_ops->afu_check_and_enable(afu))
				goto err;

			afu_dev->error_state = pci_channel_io_normal;

			/* If there's a driver attached, allow it to
			 * chime in on recovery. Drivers should check
			 * if everything has come back OK, but
			 * shouldn't start new work until we call
			 * their resume function.
			 */
			if (!afu_dev->driver)
				continue;

			if (afu_dev->driver->err_handler &&
			    afu_dev->driver->err_handler->slot_reset)
				afu_result = afu_dev->driver->err_handler->slot_reset(afu_dev);

			if (afu_result == PCI_ERS_RESULT_DISCONNECT)
				result = PCI_ERS_RESULT_DISCONNECT;
		}
	}
	return result;

err:
	/* All the bits that happen in both error_detected and cxl_remove
	 * should be idempotent, so we don't need to worry about leaving a mix
	 * of unconfigured and reconfigured resources.
	 */
	dev_err(&pdev->dev, "EEH recovery failed. Asking to be disconnected.\n");
	return PCI_ERS_RESULT_DISCONNECT;
}

static void cxl_pci_resume(struct pci_dev *pdev)
{
	struct cxl *adapter = pci_get_drvdata(pdev);
	struct cxl_afu *afu;
	struct pci_dev *afu_dev;
	int i;

	/* Everything is back now. Drivers should restart work now.
	 * This is not the place to be checking if everything came back up
	 * properly, because there's no return value: do that in slot_reset.
	 */
	for (i = 0; i < adapter->slices; i++) {
		afu = adapter->afu[i];

		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
			if (afu_dev->driver && afu_dev->driver->err_handler &&
			    afu_dev->driver->err_handler->resume)
				afu_dev->driver->err_handler->resume(afu_dev);
		}
	}
}

static const struct pci_error_handlers cxl_err_handler = {
	.error_detected = cxl_pci_error_detected,
	.slot_reset = cxl_pci_slot_reset,
	.resume = cxl_pci_resume,
};

struct pci_driver cxl_pci_driver = {
	.name = "cxl-pci",
	.id_table = cxl_pci_tbl,
	.probe = cxl_probe,
	.remove = cxl_remove,
	.shutdown = cxl_remove,
	.err_handler = &cxl_err_handler,
};