summaryrefslogtreecommitdiff
path: root/drivers/cxl/core/port.c
blob: bffde862de0bfc18833e5aa0f0d3c6eda023f26f (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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/memregion.h>
#include <linux/workqueue.h>
#include <linux/debugfs.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <cxlmem.h>
#include <cxlpci.h>
#include <cxl.h>
#include "core.h"

/**
 * DOC: cxl core
 *
 * The CXL core provides a set of interfaces that can be consumed by CXL aware
 * drivers. The interfaces allow for creation, modification, and destruction of
 * regions, memory devices, ports, and decoders. CXL aware drivers must register
 * with the CXL core via these interfaces in order to be able to participate in
 * cross-device interleave coordination. The CXL core also establishes and
 * maintains the bridge to the nvdimm subsystem.
 *
 * CXL core introduces sysfs hierarchy to control the devices that are
 * instantiated by the core.
 */

static DEFINE_IDA(cxl_port_ida);
static DEFINE_XARRAY(cxl_root_buses);

static ssize_t devtype_show(struct device *dev, struct device_attribute *attr,
			    char *buf)
{
	return sysfs_emit(buf, "%s\n", dev->type->name);
}
static DEVICE_ATTR_RO(devtype);

static int cxl_device_id(struct device *dev)
{
	if (dev->type == &cxl_nvdimm_bridge_type)
		return CXL_DEVICE_NVDIMM_BRIDGE;
	if (dev->type == &cxl_nvdimm_type)
		return CXL_DEVICE_NVDIMM;
	if (dev->type == CXL_PMEM_REGION_TYPE())
		return CXL_DEVICE_PMEM_REGION;
	if (is_cxl_port(dev)) {
		if (is_cxl_root(to_cxl_port(dev)))
			return CXL_DEVICE_ROOT;
		return CXL_DEVICE_PORT;
	}
	if (is_cxl_memdev(dev))
		return CXL_DEVICE_MEMORY_EXPANDER;
	if (dev->type == CXL_REGION_TYPE())
		return CXL_DEVICE_REGION;
	return 0;
}

static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
			     char *buf)
{
	return sysfs_emit(buf, CXL_MODALIAS_FMT "\n", cxl_device_id(dev));
}
static DEVICE_ATTR_RO(modalias);

static struct attribute *cxl_base_attributes[] = {
	&dev_attr_devtype.attr,
	&dev_attr_modalias.attr,
	NULL,
};

struct attribute_group cxl_base_attribute_group = {
	.attrs = cxl_base_attributes,
};

static ssize_t start_show(struct device *dev, struct device_attribute *attr,
			  char *buf)
{
	struct cxl_decoder *cxld = to_cxl_decoder(dev);

	return sysfs_emit(buf, "%#llx\n", cxld->hpa_range.start);
}
static DEVICE_ATTR_ADMIN_RO(start);

static ssize_t size_show(struct device *dev, struct device_attribute *attr,
			char *buf)
{
	struct cxl_decoder *cxld = to_cxl_decoder(dev);

	return sysfs_emit(buf, "%#llx\n", range_len(&cxld->hpa_range));
}
static DEVICE_ATTR_RO(size);

#define CXL_DECODER_FLAG_ATTR(name, flag)                            \
static ssize_t name##_show(struct device *dev,                       \
			   struct device_attribute *attr, char *buf) \
{                                                                    \
	struct cxl_decoder *cxld = to_cxl_decoder(dev);              \
                                                                     \
	return sysfs_emit(buf, "%s\n",                               \
			  (cxld->flags & (flag)) ? "1" : "0");       \
}                                                                    \
static DEVICE_ATTR_RO(name)

CXL_DECODER_FLAG_ATTR(cap_pmem, CXL_DECODER_F_PMEM);
CXL_DECODER_FLAG_ATTR(cap_ram, CXL_DECODER_F_RAM);
CXL_DECODER_FLAG_ATTR(cap_type2, CXL_DECODER_F_TYPE2);
CXL_DECODER_FLAG_ATTR(cap_type3, CXL_DECODER_F_TYPE3);
CXL_DECODER_FLAG_ATTR(locked, CXL_DECODER_F_LOCK);

static ssize_t target_type_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cxl_decoder *cxld = to_cxl_decoder(dev);

	switch (cxld->target_type) {
	case CXL_DECODER_ACCELERATOR:
		return sysfs_emit(buf, "accelerator\n");
	case CXL_DECODER_EXPANDER:
		return sysfs_emit(buf, "expander\n");
	}
	return -ENXIO;
}
static DEVICE_ATTR_RO(target_type);

static ssize_t emit_target_list(struct cxl_switch_decoder *cxlsd, char *buf)
{
	struct cxl_decoder *cxld = &cxlsd->cxld;
	ssize_t offset = 0;
	int i, rc = 0;

	for (i = 0; i < cxld->interleave_ways; i++) {
		struct cxl_dport *dport = cxlsd->target[i];
		struct cxl_dport *next = NULL;

		if (!dport)
			break;

		if (i + 1 < cxld->interleave_ways)
			next = cxlsd->target[i + 1];
		rc = sysfs_emit_at(buf, offset, "%d%s", dport->port_id,
				   next ? "," : "");
		if (rc < 0)
			return rc;
		offset += rc;
	}

	return offset;
}

static ssize_t target_list_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);
	ssize_t offset;
	unsigned int seq;
	int rc;

	do {
		seq = read_seqbegin(&cxlsd->target_lock);
		rc = emit_target_list(cxlsd, buf);
	} while (read_seqretry(&cxlsd->target_lock, seq));

	if (rc < 0)
		return rc;
	offset = rc;

	rc = sysfs_emit_at(buf, offset, "\n");
	if (rc < 0)
		return rc;

	return offset + rc;
}
static DEVICE_ATTR_RO(target_list);

static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
			 char *buf)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);

	switch (cxled->mode) {
	case CXL_DECODER_RAM:
		return sysfs_emit(buf, "ram\n");
	case CXL_DECODER_PMEM:
		return sysfs_emit(buf, "pmem\n");
	case CXL_DECODER_NONE:
		return sysfs_emit(buf, "none\n");
	case CXL_DECODER_MIXED:
	default:
		return sysfs_emit(buf, "mixed\n");
	}
}

static ssize_t mode_store(struct device *dev, struct device_attribute *attr,
			  const char *buf, size_t len)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
	enum cxl_decoder_mode mode;
	ssize_t rc;

	if (sysfs_streq(buf, "pmem"))
		mode = CXL_DECODER_PMEM;
	else if (sysfs_streq(buf, "ram"))
		mode = CXL_DECODER_RAM;
	else
		return -EINVAL;

	rc = cxl_dpa_set_mode(cxled, mode);
	if (rc)
		return rc;

	return len;
}
static DEVICE_ATTR_RW(mode);

static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *attr,
			    char *buf)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
	u64 base = cxl_dpa_resource_start(cxled);

	return sysfs_emit(buf, "%#llx\n", base);
}
static DEVICE_ATTR_RO(dpa_resource);

static ssize_t dpa_size_show(struct device *dev, struct device_attribute *attr,
			     char *buf)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
	resource_size_t size = cxl_dpa_size(cxled);

	return sysfs_emit(buf, "%pa\n", &size);
}

static ssize_t dpa_size_store(struct device *dev, struct device_attribute *attr,
			      const char *buf, size_t len)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
	unsigned long long size;
	ssize_t rc;

	rc = kstrtoull(buf, 0, &size);
	if (rc)
		return rc;

	if (!IS_ALIGNED(size, SZ_256M))
		return -EINVAL;

	rc = cxl_dpa_free(cxled);
	if (rc)
		return rc;

	if (size == 0)
		return len;

	rc = cxl_dpa_alloc(cxled, size);
	if (rc)
		return rc;

	return len;
}
static DEVICE_ATTR_RW(dpa_size);

static ssize_t interleave_granularity_show(struct device *dev,
					   struct device_attribute *attr,
					   char *buf)
{
	struct cxl_decoder *cxld = to_cxl_decoder(dev);

	return sysfs_emit(buf, "%d\n", cxld->interleave_granularity);
}

static DEVICE_ATTR_RO(interleave_granularity);

static ssize_t interleave_ways_show(struct device *dev,
				    struct device_attribute *attr, char *buf)
{
	struct cxl_decoder *cxld = to_cxl_decoder(dev);

	return sysfs_emit(buf, "%d\n", cxld->interleave_ways);
}

static DEVICE_ATTR_RO(interleave_ways);

static struct attribute *cxl_decoder_base_attrs[] = {
	&dev_attr_start.attr,
	&dev_attr_size.attr,
	&dev_attr_locked.attr,
	&dev_attr_interleave_granularity.attr,
	&dev_attr_interleave_ways.attr,
	NULL,
};

static struct attribute_group cxl_decoder_base_attribute_group = {
	.attrs = cxl_decoder_base_attrs,
};

static struct attribute *cxl_decoder_root_attrs[] = {
	&dev_attr_cap_pmem.attr,
	&dev_attr_cap_ram.attr,
	&dev_attr_cap_type2.attr,
	&dev_attr_cap_type3.attr,
	&dev_attr_target_list.attr,
	SET_CXL_REGION_ATTR(create_pmem_region)
	SET_CXL_REGION_ATTR(delete_region)
	NULL,
};

static bool can_create_pmem(struct cxl_root_decoder *cxlrd)
{
	unsigned long flags = CXL_DECODER_F_TYPE3 | CXL_DECODER_F_PMEM;

	return (cxlrd->cxlsd.cxld.flags & flags) == flags;
}

static umode_t cxl_root_decoder_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = kobj_to_dev(kobj);
	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);

	if (a == CXL_REGION_ATTR(create_pmem_region) && !can_create_pmem(cxlrd))
		return 0;

	if (a == CXL_REGION_ATTR(delete_region) && !can_create_pmem(cxlrd))
		return 0;

	return a->mode;
}

static struct attribute_group cxl_decoder_root_attribute_group = {
	.attrs = cxl_decoder_root_attrs,
	.is_visible = cxl_root_decoder_visible,
};

static const struct attribute_group *cxl_decoder_root_attribute_groups[] = {
	&cxl_decoder_root_attribute_group,
	&cxl_decoder_base_attribute_group,
	&cxl_base_attribute_group,
	NULL,
};

static struct attribute *cxl_decoder_switch_attrs[] = {
	&dev_attr_target_type.attr,
	&dev_attr_target_list.attr,
	SET_CXL_REGION_ATTR(region)
	NULL,
};

static struct attribute_group cxl_decoder_switch_attribute_group = {
	.attrs = cxl_decoder_switch_attrs,
};

static const struct attribute_group *cxl_decoder_switch_attribute_groups[] = {
	&cxl_decoder_switch_attribute_group,
	&cxl_decoder_base_attribute_group,
	&cxl_base_attribute_group,
	NULL,
};

static struct attribute *cxl_decoder_endpoint_attrs[] = {
	&dev_attr_target_type.attr,
	&dev_attr_mode.attr,
	&dev_attr_dpa_size.attr,
	&dev_attr_dpa_resource.attr,
	SET_CXL_REGION_ATTR(region)
	NULL,
};

static struct attribute_group cxl_decoder_endpoint_attribute_group = {
	.attrs = cxl_decoder_endpoint_attrs,
};

static const struct attribute_group *cxl_decoder_endpoint_attribute_groups[] = {
	&cxl_decoder_base_attribute_group,
	&cxl_decoder_endpoint_attribute_group,
	&cxl_base_attribute_group,
	NULL,
};

static void __cxl_decoder_release(struct cxl_decoder *cxld)
{
	struct cxl_port *port = to_cxl_port(cxld->dev.parent);

	ida_free(&port->decoder_ida, cxld->id);
	put_device(&port->dev);
}

static void cxl_endpoint_decoder_release(struct device *dev)
{
	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);

	__cxl_decoder_release(&cxled->cxld);
	kfree(cxled);
}

static void cxl_switch_decoder_release(struct device *dev)
{
	struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);

	__cxl_decoder_release(&cxlsd->cxld);
	kfree(cxlsd);
}

struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev)
{
	if (dev_WARN_ONCE(dev, !is_root_decoder(dev),
			  "not a cxl_root_decoder device\n"))
		return NULL;
	return container_of(dev, struct cxl_root_decoder, cxlsd.cxld.dev);
}
EXPORT_SYMBOL_NS_GPL(to_cxl_root_decoder, CXL);

static void cxl_root_decoder_release(struct device *dev)
{
	struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev);

	if (atomic_read(&cxlrd->region_id) >= 0)
		memregion_free(atomic_read(&cxlrd->region_id));
	__cxl_decoder_release(&cxlrd->cxlsd.cxld);
	kfree(cxlrd);
}

static const struct device_type cxl_decoder_endpoint_type = {
	.name = "cxl_decoder_endpoint",
	.release = cxl_endpoint_decoder_release,
	.groups = cxl_decoder_endpoint_attribute_groups,
};

static const struct device_type cxl_decoder_switch_type = {
	.name = "cxl_decoder_switch",
	.release = cxl_switch_decoder_release,
	.groups = cxl_decoder_switch_attribute_groups,
};

static const struct device_type cxl_decoder_root_type = {
	.name = "cxl_decoder_root",
	.release = cxl_root_decoder_release,
	.groups = cxl_decoder_root_attribute_groups,
};

bool is_endpoint_decoder(struct device *dev)
{
	return dev->type == &cxl_decoder_endpoint_type;
}

bool is_root_decoder(struct device *dev)
{
	return dev->type == &cxl_decoder_root_type;
}
EXPORT_SYMBOL_NS_GPL(is_root_decoder, CXL);

bool is_switch_decoder(struct device *dev)
{
	return is_root_decoder(dev) || dev->type == &cxl_decoder_switch_type;
}

struct cxl_decoder *to_cxl_decoder(struct device *dev)
{
	if (dev_WARN_ONCE(dev,
			  !is_switch_decoder(dev) && !is_endpoint_decoder(dev),
			  "not a cxl_decoder device\n"))
		return NULL;
	return container_of(dev, struct cxl_decoder, dev);
}
EXPORT_SYMBOL_NS_GPL(to_cxl_decoder, CXL);

struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev)
{
	if (dev_WARN_ONCE(dev, !is_endpoint_decoder(dev),
			  "not a cxl_endpoint_decoder device\n"))
		return NULL;
	return container_of(dev, struct cxl_endpoint_decoder, cxld.dev);
}
EXPORT_SYMBOL_NS_GPL(to_cxl_endpoint_decoder, CXL);

struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev)
{
	if (dev_WARN_ONCE(dev, !is_switch_decoder(dev),
			  "not a cxl_switch_decoder device\n"))
		return NULL;
	return container_of(dev, struct cxl_switch_decoder, cxld.dev);
}

static void cxl_ep_release(struct cxl_ep *ep)
{
	put_device(ep->ep);
	kfree(ep);
}

static void cxl_ep_remove(struct cxl_port *port, struct cxl_ep *ep)
{
	if (!ep)
		return;
	xa_erase(&port->endpoints, (unsigned long) ep->ep);
	cxl_ep_release(ep);
}

static void cxl_port_release(struct device *dev)
{
	struct cxl_port *port = to_cxl_port(dev);
	unsigned long index;
	struct cxl_ep *ep;

	xa_for_each(&port->endpoints, index, ep)
		cxl_ep_remove(port, ep);
	xa_destroy(&port->endpoints);
	xa_destroy(&port->dports);
	xa_destroy(&port->regions);
	ida_free(&cxl_port_ida, port->id);
	kfree(port);
}

static const struct attribute_group *cxl_port_attribute_groups[] = {
	&cxl_base_attribute_group,
	NULL,
};

static const struct device_type cxl_port_type = {
	.name = "cxl_port",
	.release = cxl_port_release,
	.groups = cxl_port_attribute_groups,
};

bool is_cxl_port(struct device *dev)
{
	return dev->type == &cxl_port_type;
}
EXPORT_SYMBOL_NS_GPL(is_cxl_port, CXL);

struct cxl_port *to_cxl_port(struct device *dev)
{
	if (dev_WARN_ONCE(dev, dev->type != &cxl_port_type,
			  "not a cxl_port device\n"))
		return NULL;
	return container_of(dev, struct cxl_port, dev);
}
EXPORT_SYMBOL_NS_GPL(to_cxl_port, CXL);

static void unregister_port(void *_port)
{
	struct cxl_port *port = _port;
	struct cxl_port *parent;
	struct device *lock_dev;

	if (is_cxl_root(port))
		parent = NULL;
	else
		parent = to_cxl_port(port->dev.parent);

	/*
	 * CXL root port's and the first level of ports are unregistered
	 * under the platform firmware device lock, all other ports are
	 * unregistered while holding their parent port lock.
	 */
	if (!parent)
		lock_dev = port->uport;
	else if (is_cxl_root(parent))
		lock_dev = parent->uport;
	else
		lock_dev = &parent->dev;

	device_lock_assert(lock_dev);
	port->dead = true;
	device_unregister(&port->dev);
}

static void cxl_unlink_uport(void *_port)
{
	struct cxl_port *port = _port;

	sysfs_remove_link(&port->dev.kobj, "uport");
}

static int devm_cxl_link_uport(struct device *host, struct cxl_port *port)
{
	int rc;

	rc = sysfs_create_link(&port->dev.kobj, &port->uport->kobj, "uport");
	if (rc)
		return rc;
	return devm_add_action_or_reset(host, cxl_unlink_uport, port);
}

static struct lock_class_key cxl_port_key;

static struct cxl_port *cxl_port_alloc(struct device *uport,
				       resource_size_t component_reg_phys,
				       struct cxl_dport *parent_dport)
{
	struct cxl_port *port;
	struct device *dev;
	int rc;

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

	rc = ida_alloc(&cxl_port_ida, GFP_KERNEL);
	if (rc < 0)
		goto err;
	port->id = rc;
	port->uport = uport;

	/*
	 * The top-level cxl_port "cxl_root" does not have a cxl_port as
	 * its parent and it does not have any corresponding component
	 * registers as its decode is described by a fixed platform
	 * description.
	 */
	dev = &port->dev;
	if (parent_dport) {
		struct cxl_port *parent_port = parent_dport->port;
		struct cxl_port *iter;

		dev->parent = &parent_port->dev;
		port->depth = parent_port->depth + 1;
		port->parent_dport = parent_dport;

		/*
		 * walk to the host bridge, or the first ancestor that knows
		 * the host bridge
		 */
		iter = port;
		while (!iter->host_bridge &&
		       !is_cxl_root(to_cxl_port(iter->dev.parent)))
			iter = to_cxl_port(iter->dev.parent);
		if (iter->host_bridge)
			port->host_bridge = iter->host_bridge;
		else
			port->host_bridge = iter->uport;
		dev_dbg(uport, "host-bridge: %s\n", dev_name(port->host_bridge));
	} else
		dev->parent = uport;

	port->component_reg_phys = component_reg_phys;
	ida_init(&port->decoder_ida);
	port->hdm_end = -1;
	port->commit_end = -1;
	xa_init(&port->dports);
	xa_init(&port->endpoints);
	xa_init(&port->regions);

	device_initialize(dev);
	lockdep_set_class_and_subclass(&dev->mutex, &cxl_port_key, port->depth);
	device_set_pm_not_required(dev);
	dev->bus = &cxl_bus_type;
	dev->type = &cxl_port_type;

	return port;

err:
	kfree(port);
	return ERR_PTR(rc);
}

/**
 * devm_cxl_add_port - register a cxl_port in CXL memory decode hierarchy
 * @host: host device for devm operations
 * @uport: "physical" device implementing this upstream port
 * @component_reg_phys: (optional) for configurable cxl_port instances
 * @parent_dport: next hop up in the CXL memory decode hierarchy
 */
struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport,
				   resource_size_t component_reg_phys,
				   struct cxl_dport *parent_dport)
{
	struct cxl_port *port;
	struct device *dev;
	int rc;

	port = cxl_port_alloc(uport, component_reg_phys, parent_dport);
	if (IS_ERR(port))
		return port;

	dev = &port->dev;
	if (is_cxl_memdev(uport))
		rc = dev_set_name(dev, "endpoint%d", port->id);
	else if (parent_dport)
		rc = dev_set_name(dev, "port%d", port->id);
	else
		rc = dev_set_name(dev, "root%d", port->id);
	if (rc)
		goto err;

	rc = device_add(dev);
	if (rc)
		goto err;

	rc = devm_add_action_or_reset(host, unregister_port, port);
	if (rc)
		return ERR_PTR(rc);

	rc = devm_cxl_link_uport(host, port);
	if (rc)
		return ERR_PTR(rc);

	return port;

err:
	put_device(dev);
	return ERR_PTR(rc);
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_add_port, CXL);

struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port)
{
	/* There is no pci_bus associated with a CXL platform-root port */
	if (is_cxl_root(port))
		return NULL;

	if (dev_is_pci(port->uport)) {
		struct pci_dev *pdev = to_pci_dev(port->uport);

		return pdev->subordinate;
	}

	return xa_load(&cxl_root_buses, (unsigned long)port->uport);
}
EXPORT_SYMBOL_NS_GPL(cxl_port_to_pci_bus, CXL);

static void unregister_pci_bus(void *uport)
{
	xa_erase(&cxl_root_buses, (unsigned long)uport);
}

int devm_cxl_register_pci_bus(struct device *host, struct device *uport,
			      struct pci_bus *bus)
{
	int rc;

	if (dev_is_pci(uport))
		return -EINVAL;

	rc = xa_insert(&cxl_root_buses, (unsigned long)uport, bus, GFP_KERNEL);
	if (rc)
		return rc;
	return devm_add_action_or_reset(host, unregister_pci_bus, uport);
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_register_pci_bus, CXL);

static bool dev_is_cxl_root_child(struct device *dev)
{
	struct cxl_port *port, *parent;

	if (!is_cxl_port(dev))
		return false;

	port = to_cxl_port(dev);
	if (is_cxl_root(port))
		return false;

	parent = to_cxl_port(port->dev.parent);
	if (is_cxl_root(parent))
		return true;

	return false;
}

/* Find a 2nd level CXL port that has a dport that is an ancestor of @match */
static int match_root_child(struct device *dev, const void *match)
{
	const struct device *iter = NULL;
	struct cxl_dport *dport;
	struct cxl_port *port;

	if (!dev_is_cxl_root_child(dev))
		return 0;

	port = to_cxl_port(dev);
	iter = match;
	while (iter) {
		dport = cxl_find_dport_by_dev(port, iter);
		if (dport)
			break;
		iter = iter->parent;
	}

	return !!iter;
}

struct cxl_port *find_cxl_root(struct device *dev)
{
	struct device *port_dev;
	struct cxl_port *root;

	port_dev = bus_find_device(&cxl_bus_type, NULL, dev, match_root_child);
	if (!port_dev)
		return NULL;

	root = to_cxl_port(port_dev->parent);
	get_device(&root->dev);
	put_device(port_dev);
	return root;
}
EXPORT_SYMBOL_NS_GPL(find_cxl_root, CXL);

static struct cxl_dport *find_dport(struct cxl_port *port, int id)
{
	struct cxl_dport *dport;
	unsigned long index;

	device_lock_assert(&port->dev);
	xa_for_each(&port->dports, index, dport)
		if (dport->port_id == id)
			return dport;
	return NULL;
}

static int add_dport(struct cxl_port *port, struct cxl_dport *new)
{
	struct cxl_dport *dup;

	device_lock_assert(&port->dev);
	dup = find_dport(port, new->port_id);
	if (dup) {
		dev_err(&port->dev,
			"unable to add dport%d-%s non-unique port id (%s)\n",
			new->port_id, dev_name(new->dport),
			dev_name(dup->dport));
		return -EBUSY;
	}
	return xa_insert(&port->dports, (unsigned long)new->dport, new,
			 GFP_KERNEL);
}

/*
 * Since root-level CXL dports cannot be enumerated by PCI they are not
 * enumerated by the common port driver that acquires the port lock over
 * dport add/remove. Instead, root dports are manually added by a
 * platform driver and cond_cxl_root_lock() is used to take the missing
 * port lock in that case.
 */
static void cond_cxl_root_lock(struct cxl_port *port)
{
	if (is_cxl_root(port))
		device_lock(&port->dev);
}

static void cond_cxl_root_unlock(struct cxl_port *port)
{
	if (is_cxl_root(port))
		device_unlock(&port->dev);
}

static void cxl_dport_remove(void *data)
{
	struct cxl_dport *dport = data;
	struct cxl_port *port = dport->port;

	xa_erase(&port->dports, (unsigned long) dport->dport);
	put_device(dport->dport);
}

static void cxl_dport_unlink(void *data)
{
	struct cxl_dport *dport = data;
	struct cxl_port *port = dport->port;
	char link_name[CXL_TARGET_STRLEN];

	sprintf(link_name, "dport%d", dport->port_id);
	sysfs_remove_link(&port->dev.kobj, link_name);
}

/**
 * devm_cxl_add_dport - append downstream port data to a cxl_port
 * @port: the cxl_port that references this dport
 * @dport_dev: firmware or PCI device representing the dport
 * @port_id: identifier for this dport in a decoder's target list
 * @component_reg_phys: optional location of CXL component registers
 *
 * Note that dports are appended to the devm release action's of the
 * either the port's host (for root ports), or the port itself (for
 * switch ports)
 */
struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port,
				     struct device *dport_dev, int port_id,
				     resource_size_t component_reg_phys)
{
	char link_name[CXL_TARGET_STRLEN];
	struct cxl_dport *dport;
	struct device *host;
	int rc;

	if (is_cxl_root(port))
		host = port->uport;
	else
		host = &port->dev;

	if (!host->driver) {
		dev_WARN_ONCE(&port->dev, 1, "dport:%s bad devm context\n",
			      dev_name(dport_dev));
		return ERR_PTR(-ENXIO);
	}

	if (snprintf(link_name, CXL_TARGET_STRLEN, "dport%d", port_id) >=
	    CXL_TARGET_STRLEN)
		return ERR_PTR(-EINVAL);

	dport = devm_kzalloc(host, sizeof(*dport), GFP_KERNEL);
	if (!dport)
		return ERR_PTR(-ENOMEM);

	dport->dport = dport_dev;
	dport->port_id = port_id;
	dport->component_reg_phys = component_reg_phys;
	dport->port = port;

	cond_cxl_root_lock(port);
	rc = add_dport(port, dport);
	cond_cxl_root_unlock(port);
	if (rc)
		return ERR_PTR(rc);

	get_device(dport_dev);
	rc = devm_add_action_or_reset(host, cxl_dport_remove, dport);
	if (rc)
		return ERR_PTR(rc);

	rc = sysfs_create_link(&port->dev.kobj, &dport_dev->kobj, link_name);
	if (rc)
		return ERR_PTR(rc);

	rc = devm_add_action_or_reset(host, cxl_dport_unlink, dport);
	if (rc)
		return ERR_PTR(rc);

	return dport;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_add_dport, CXL);

static int add_ep(struct cxl_ep *new)
{
	struct cxl_port *port = new->dport->port;
	int rc;

	device_lock(&port->dev);
	if (port->dead) {
		device_unlock(&port->dev);
		return -ENXIO;
	}
	rc = xa_insert(&port->endpoints, (unsigned long)new->ep, new,
		       GFP_KERNEL);
	device_unlock(&port->dev);

	return rc;
}

/**
 * cxl_add_ep - register an endpoint's interest in a port
 * @dport: the dport that routes to @ep_dev
 * @ep_dev: device representing the endpoint
 *
 * Intermediate CXL ports are scanned based on the arrival of endpoints.
 * When those endpoints depart the port can be destroyed once all
 * endpoints that care about that port have been removed.
 */
static int cxl_add_ep(struct cxl_dport *dport, struct device *ep_dev)
{
	struct cxl_ep *ep;
	int rc;

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

	ep->ep = get_device(ep_dev);
	ep->dport = dport;

	rc = add_ep(ep);
	if (rc)
		cxl_ep_release(ep);
	return rc;
}

struct cxl_find_port_ctx {
	const struct device *dport_dev;
	const struct cxl_port *parent_port;
	struct cxl_dport **dport;
};

static int match_port_by_dport(struct device *dev, const void *data)
{
	const struct cxl_find_port_ctx *ctx = data;
	struct cxl_dport *dport;
	struct cxl_port *port;

	if (!is_cxl_port(dev))
		return 0;
	if (ctx->parent_port && dev->parent != &ctx->parent_port->dev)
		return 0;

	port = to_cxl_port(dev);
	dport = cxl_find_dport_by_dev(port, ctx->dport_dev);
	if (ctx->dport)
		*ctx->dport = dport;
	return dport != NULL;
}

static struct cxl_port *__find_cxl_port(struct cxl_find_port_ctx *ctx)
{
	struct device *dev;

	if (!ctx->dport_dev)
		return NULL;

	dev = bus_find_device(&cxl_bus_type, NULL, ctx, match_port_by_dport);
	if (dev)
		return to_cxl_port(dev);
	return NULL;
}

static struct cxl_port *find_cxl_port(struct device *dport_dev,
				      struct cxl_dport **dport)
{
	struct cxl_find_port_ctx ctx = {
		.dport_dev = dport_dev,
		.dport = dport,
	};
	struct cxl_port *port;

	port = __find_cxl_port(&ctx);
	return port;
}

static struct cxl_port *find_cxl_port_at(struct cxl_port *parent_port,
					 struct device *dport_dev,
					 struct cxl_dport **dport)
{
	struct cxl_find_port_ctx ctx = {
		.dport_dev = dport_dev,
		.parent_port = parent_port,
		.dport = dport,
	};
	struct cxl_port *port;

	port = __find_cxl_port(&ctx);
	return port;
}

/*
 * All users of grandparent() are using it to walk PCIe-like swich port
 * hierarchy. A PCIe switch is comprised of a bridge device representing the
 * upstream switch port and N bridges representing downstream switch ports. When
 * bridges stack the grand-parent of a downstream switch port is another
 * downstream switch port in the immediate ancestor switch.
 */
static struct device *grandparent(struct device *dev)
{
	if (dev && dev->parent)
		return dev->parent->parent;
	return NULL;
}

static void delete_endpoint(void *data)
{
	struct cxl_memdev *cxlmd = data;
	struct cxl_port *endpoint = dev_get_drvdata(&cxlmd->dev);
	struct cxl_port *parent_port;
	struct device *parent;

	parent_port = cxl_mem_find_port(cxlmd, NULL);
	if (!parent_port)
		goto out;
	parent = &parent_port->dev;

	device_lock(parent);
	if (parent->driver && !endpoint->dead) {
		devm_release_action(parent, cxl_unlink_uport, endpoint);
		devm_release_action(parent, unregister_port, endpoint);
	}
	device_unlock(parent);
	put_device(parent);
out:
	put_device(&endpoint->dev);
}

int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint)
{
	struct device *dev = &cxlmd->dev;

	get_device(&endpoint->dev);
	dev_set_drvdata(dev, endpoint);
	return devm_add_action_or_reset(dev, delete_endpoint, cxlmd);
}
EXPORT_SYMBOL_NS_GPL(cxl_endpoint_autoremove, CXL);

/*
 * The natural end of life of a non-root 'cxl_port' is when its parent port goes
 * through a ->remove() event ("top-down" unregistration). The unnatural trigger
 * for a port to be unregistered is when all memdevs beneath that port have gone
 * through ->remove(). This "bottom-up" removal selectively removes individual
 * child ports manually. This depends on devm_cxl_add_port() to not change is
 * devm action registration order, and for dports to have already been
 * destroyed by reap_dports().
 */
static void delete_switch_port(struct cxl_port *port)
{
	devm_release_action(port->dev.parent, cxl_unlink_uport, port);
	devm_release_action(port->dev.parent, unregister_port, port);
}

static void reap_dports(struct cxl_port *port)
{
	struct cxl_dport *dport;
	unsigned long index;

	device_lock_assert(&port->dev);

	xa_for_each(&port->dports, index, dport) {
		devm_release_action(&port->dev, cxl_dport_unlink, dport);
		devm_release_action(&port->dev, cxl_dport_remove, dport);
		devm_kfree(&port->dev, dport);
	}
}

int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd,
			  struct cxl_dport *parent_dport)
{
	struct cxl_port *parent_port = parent_dport->port;
	struct cxl_dev_state *cxlds = cxlmd->cxlds;
	struct cxl_port *endpoint, *iter, *down;
	int rc;

	/*
	 * Now that the path to the root is established record all the
	 * intervening ports in the chain.
	 */
	for (iter = parent_port, down = NULL; !is_cxl_root(iter);
	     down = iter, iter = to_cxl_port(iter->dev.parent)) {
		struct cxl_ep *ep;

		ep = cxl_ep_load(iter, cxlmd);
		ep->next = down;
	}

	endpoint = devm_cxl_add_port(&parent_port->dev, &cxlmd->dev,
				     cxlds->component_reg_phys, parent_dport);
	if (IS_ERR(endpoint))
		return PTR_ERR(endpoint);

	dev_dbg(&cxlmd->dev, "add: %s\n", dev_name(&endpoint->dev));

	rc = cxl_endpoint_autoremove(cxlmd, endpoint);
	if (rc)
		return rc;

	if (!endpoint->dev.driver) {
		dev_err(&cxlmd->dev, "%s failed probe\n",
			dev_name(&endpoint->dev));
		return -ENXIO;
	}

	return 0;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_add_endpoint, CXL);

static void cxl_detach_ep(void *data)
{
	struct cxl_memdev *cxlmd = data;
	struct device *iter;

	for (iter = &cxlmd->dev; iter; iter = grandparent(iter)) {
		struct device *dport_dev = grandparent(iter);
		struct cxl_port *port, *parent_port;
		struct cxl_ep *ep;
		bool died = false;

		if (!dport_dev)
			break;

		port = find_cxl_port(dport_dev, NULL);
		if (!port)
			continue;

		if (is_cxl_root(port)) {
			put_device(&port->dev);
			continue;
		}

		parent_port = to_cxl_port(port->dev.parent);
		device_lock(&parent_port->dev);
		if (!parent_port->dev.driver) {
			/*
			 * The bottom-up race to delete the port lost to a
			 * top-down port disable, give up here, because the
			 * parent_port ->remove() will have cleaned up all
			 * descendants.
			 */
			device_unlock(&parent_port->dev);
			put_device(&port->dev);
			continue;
		}

		device_lock(&port->dev);
		ep = cxl_ep_load(port, cxlmd);
		dev_dbg(&cxlmd->dev, "disconnect %s from %s\n",
			ep ? dev_name(ep->ep) : "", dev_name(&port->dev));
		cxl_ep_remove(port, ep);
		if (ep && !port->dead && xa_empty(&port->endpoints) &&
		    !is_cxl_root(parent_port)) {
			/*
			 * This was the last ep attached to a dynamically
			 * enumerated port. Block new cxl_add_ep() and garbage
			 * collect the port.
			 */
			died = true;
			port->dead = true;
			reap_dports(port);
		}
		device_unlock(&port->dev);

		if (died) {
			dev_dbg(&cxlmd->dev, "delete %s\n",
				dev_name(&port->dev));
			delete_switch_port(port);
		}
		put_device(&port->dev);
		device_unlock(&parent_port->dev);
	}
}

static resource_size_t find_component_registers(struct device *dev)
{
	struct cxl_register_map map;
	struct pci_dev *pdev;

	/*
	 * Theoretically, CXL component registers can be hosted on a
	 * non-PCI device, in practice, only cxl_test hits this case.
	 */
	if (!dev_is_pci(dev))
		return CXL_RESOURCE_NONE;

	pdev = to_pci_dev(dev);

	cxl_find_regblock(pdev, CXL_REGLOC_RBI_COMPONENT, &map);
	return cxl_regmap_to_base(pdev, &map);
}

static int add_port_attach_ep(struct cxl_memdev *cxlmd,
			      struct device *uport_dev,
			      struct device *dport_dev)
{
	struct device *dparent = grandparent(dport_dev);
	struct cxl_port *port, *parent_port = NULL;
	struct cxl_dport *dport, *parent_dport;
	resource_size_t component_reg_phys;
	int rc;

	if (!dparent) {
		/*
		 * The iteration reached the topology root without finding the
		 * CXL-root 'cxl_port' on a previous iteration, fail for now to
		 * be re-probed after platform driver attaches.
		 */
		dev_dbg(&cxlmd->dev, "%s is a root dport\n",
			dev_name(dport_dev));
		return -ENXIO;
	}

	parent_port = find_cxl_port(dparent, &parent_dport);
	if (!parent_port) {
		/* iterate to create this parent_port */
		return -EAGAIN;
	}

	device_lock(&parent_port->dev);
	if (!parent_port->dev.driver) {
		dev_warn(&cxlmd->dev,
			 "port %s:%s disabled, failed to enumerate CXL.mem\n",
			 dev_name(&parent_port->dev), dev_name(uport_dev));
		port = ERR_PTR(-ENXIO);
		goto out;
	}

	port = find_cxl_port_at(parent_port, dport_dev, &dport);
	if (!port) {
		component_reg_phys = find_component_registers(uport_dev);
		port = devm_cxl_add_port(&parent_port->dev, uport_dev,
					 component_reg_phys, parent_dport);
		/* retry find to pick up the new dport information */
		if (!IS_ERR(port))
			port = find_cxl_port_at(parent_port, dport_dev, &dport);
	}
out:
	device_unlock(&parent_port->dev);

	if (IS_ERR(port))
		rc = PTR_ERR(port);
	else {
		dev_dbg(&cxlmd->dev, "add to new port %s:%s\n",
			dev_name(&port->dev), dev_name(port->uport));
		rc = cxl_add_ep(dport, &cxlmd->dev);
		if (rc == -EBUSY) {
			/*
			 * "can't" happen, but this error code means
			 * something to the caller, so translate it.
			 */
			rc = -ENXIO;
		}
		put_device(&port->dev);
	}

	put_device(&parent_port->dev);
	return rc;
}

int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd)
{
	struct device *dev = &cxlmd->dev;
	struct device *iter;
	int rc;

	rc = devm_add_action_or_reset(&cxlmd->dev, cxl_detach_ep, cxlmd);
	if (rc)
		return rc;

	/*
	 * Scan for and add all cxl_ports in this device's ancestry.
	 * Repeat until no more ports are added. Abort if a port add
	 * attempt fails.
	 */
retry:
	for (iter = dev; iter; iter = grandparent(iter)) {
		struct device *dport_dev = grandparent(iter);
		struct device *uport_dev;
		struct cxl_dport *dport;
		struct cxl_port *port;

		if (!dport_dev)
			return 0;

		uport_dev = dport_dev->parent;
		if (!uport_dev) {
			dev_warn(dev, "at %s no parent for dport: %s\n",
				 dev_name(iter), dev_name(dport_dev));
			return -ENXIO;
		}

		dev_dbg(dev, "scan: iter: %s dport_dev: %s parent: %s\n",
			dev_name(iter), dev_name(dport_dev),
			dev_name(uport_dev));
		port = find_cxl_port(dport_dev, &dport);
		if (port) {
			dev_dbg(&cxlmd->dev,
				"found already registered port %s:%s\n",
				dev_name(&port->dev), dev_name(port->uport));
			rc = cxl_add_ep(dport, &cxlmd->dev);

			/*
			 * If the endpoint already exists in the port's list,
			 * that's ok, it was added on a previous pass.
			 * Otherwise, retry in add_port_attach_ep() after taking
			 * the parent_port lock as the current port may be being
			 * reaped.
			 */
			if (rc && rc != -EBUSY) {
				put_device(&port->dev);
				return rc;
			}

			/* Any more ports to add between this one and the root? */
			if (!dev_is_cxl_root_child(&port->dev)) {
				put_device(&port->dev);
				continue;
			}

			put_device(&port->dev);
			return 0;
		}

		rc = add_port_attach_ep(cxlmd, uport_dev, dport_dev);
		/* port missing, try to add parent */
		if (rc == -EAGAIN)
			continue;
		/* failed to add ep or port */
		if (rc)
			return rc;
		/* port added, new descendants possible, start over */
		goto retry;
	}

	return 0;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_enumerate_ports, CXL);

struct cxl_port *cxl_mem_find_port(struct cxl_memdev *cxlmd,
				   struct cxl_dport **dport)
{
	return find_cxl_port(grandparent(&cxlmd->dev), dport);
}
EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL);

static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
				    struct cxl_port *port, int *target_map)
{
	int i, rc = 0;

	if (!target_map)
		return 0;

	device_lock_assert(&port->dev);

	if (xa_empty(&port->dports))
		return -EINVAL;

	write_seqlock(&cxlsd->target_lock);
	for (i = 0; i < cxlsd->nr_targets; i++) {
		struct cxl_dport *dport = find_dport(port, target_map[i]);

		if (!dport) {
			rc = -ENXIO;
			break;
		}
		cxlsd->target[i] = dport;
	}
	write_sequnlock(&cxlsd->target_lock);

	return rc;
}

static struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos)
{
	struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
	struct cxl_decoder *cxld = &cxlsd->cxld;
	int iw;

	iw = cxld->interleave_ways;
	if (dev_WARN_ONCE(&cxld->dev, iw != cxlsd->nr_targets,
			  "misconfigured root decoder\n"))
		return NULL;

	return cxlrd->cxlsd.target[pos % iw];
}

static struct lock_class_key cxl_decoder_key;

/**
 * cxl_decoder_init - Common decoder setup / initialization
 * @port: owning port of this decoder
 * @cxld: common decoder properties to initialize
 *
 * A port may contain one or more decoders. Each of those decoders
 * enable some address space for CXL.mem utilization. A decoder is
 * expected to be configured by the caller before registering via
 * cxl_decoder_add()
 */
static int cxl_decoder_init(struct cxl_port *port, struct cxl_decoder *cxld)
{
	struct device *dev;
	int rc;

	rc = ida_alloc(&port->decoder_ida, GFP_KERNEL);
	if (rc < 0)
		return rc;

	/* need parent to stick around to release the id */
	get_device(&port->dev);
	cxld->id = rc;

	dev = &cxld->dev;
	device_initialize(dev);
	lockdep_set_class(&dev->mutex, &cxl_decoder_key);
	device_set_pm_not_required(dev);
	dev->parent = &port->dev;
	dev->bus = &cxl_bus_type;

	/* Pre initialize an "empty" decoder */
	cxld->interleave_ways = 1;
	cxld->interleave_granularity = PAGE_SIZE;
	cxld->target_type = CXL_DECODER_EXPANDER;
	cxld->hpa_range = (struct range) {
		.start = 0,
		.end = -1,
	};

	return 0;
}

static int cxl_switch_decoder_init(struct cxl_port *port,
				   struct cxl_switch_decoder *cxlsd,
				   int nr_targets)
{
	if (nr_targets > CXL_DECODER_MAX_INTERLEAVE)
		return -EINVAL;

	cxlsd->nr_targets = nr_targets;
	seqlock_init(&cxlsd->target_lock);
	return cxl_decoder_init(port, &cxlsd->cxld);
}

/**
 * cxl_root_decoder_alloc - Allocate a root level decoder
 * @port: owning CXL root of this decoder
 * @nr_targets: static number of downstream targets
 *
 * Return: A new cxl decoder to be registered by cxl_decoder_add(). A
 * 'CXL root' decoder is one that decodes from a top-level / static platform
 * firmware description of CXL resources into a CXL standard decode
 * topology.
 */
struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
						unsigned int nr_targets)
{
	struct cxl_root_decoder *cxlrd;
	struct cxl_switch_decoder *cxlsd;
	struct cxl_decoder *cxld;
	int rc;

	if (!is_cxl_root(port))
		return ERR_PTR(-EINVAL);

	cxlrd = kzalloc(struct_size(cxlrd, cxlsd.target, nr_targets),
			GFP_KERNEL);
	if (!cxlrd)
		return ERR_PTR(-ENOMEM);

	cxlsd = &cxlrd->cxlsd;
	rc = cxl_switch_decoder_init(port, cxlsd, nr_targets);
	if (rc) {
		kfree(cxlrd);
		return ERR_PTR(rc);
	}

	cxlrd->calc_hb = cxl_hb_modulo;

	cxld = &cxlsd->cxld;
	cxld->dev.type = &cxl_decoder_root_type;
	/*
	 * cxl_root_decoder_release() special cases negative ids to
	 * detect memregion_alloc() failures.
	 */
	atomic_set(&cxlrd->region_id, -1);
	rc = memregion_alloc(GFP_KERNEL);
	if (rc < 0) {
		put_device(&cxld->dev);
		return ERR_PTR(rc);
	}

	atomic_set(&cxlrd->region_id, rc);
	return cxlrd;
}
EXPORT_SYMBOL_NS_GPL(cxl_root_decoder_alloc, CXL);

/**
 * cxl_switch_decoder_alloc - Allocate a switch level decoder
 * @port: owning CXL switch port of this decoder
 * @nr_targets: max number of dynamically addressable downstream targets
 *
 * Return: A new cxl decoder to be registered by cxl_decoder_add(). A
 * 'switch' decoder is any decoder that can be enumerated by PCIe
 * topology and the HDM Decoder Capability. This includes the decoders
 * that sit between Switch Upstream Ports / Switch Downstream Ports and
 * Host Bridges / Root Ports.
 */
struct cxl_switch_decoder *cxl_switch_decoder_alloc(struct cxl_port *port,
						    unsigned int nr_targets)
{
	struct cxl_switch_decoder *cxlsd;
	struct cxl_decoder *cxld;
	int rc;

	if (is_cxl_root(port) || is_cxl_endpoint(port))
		return ERR_PTR(-EINVAL);

	cxlsd = kzalloc(struct_size(cxlsd, target, nr_targets), GFP_KERNEL);
	if (!cxlsd)
		return ERR_PTR(-ENOMEM);

	rc = cxl_switch_decoder_init(port, cxlsd, nr_targets);
	if (rc) {
		kfree(cxlsd);
		return ERR_PTR(rc);
	}

	cxld = &cxlsd->cxld;
	cxld->dev.type = &cxl_decoder_switch_type;
	return cxlsd;
}
EXPORT_SYMBOL_NS_GPL(cxl_switch_decoder_alloc, CXL);

/**
 * cxl_endpoint_decoder_alloc - Allocate an endpoint decoder
 * @port: owning port of this decoder
 *
 * Return: A new cxl decoder to be registered by cxl_decoder_add()
 */
struct cxl_endpoint_decoder *cxl_endpoint_decoder_alloc(struct cxl_port *port)
{
	struct cxl_endpoint_decoder *cxled;
	struct cxl_decoder *cxld;
	int rc;

	if (!is_cxl_endpoint(port))
		return ERR_PTR(-EINVAL);

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

	cxled->pos = -1;
	cxld = &cxled->cxld;
	rc = cxl_decoder_init(port, cxld);
	if (rc)	 {
		kfree(cxled);
		return ERR_PTR(rc);
	}

	cxld->dev.type = &cxl_decoder_endpoint_type;
	return cxled;
}
EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_alloc, CXL);

/**
 * cxl_decoder_add_locked - Add a decoder with targets
 * @cxld: The cxl decoder allocated by cxl_<type>_decoder_alloc()
 * @target_map: A list of downstream ports that this decoder can direct memory
 *              traffic to. These numbers should correspond with the port number
 *              in the PCIe Link Capabilities structure.
 *
 * Certain types of decoders may not have any targets. The main example of this
 * is an endpoint device. A more awkward example is a hostbridge whose root
 * ports get hot added (technically possible, though unlikely).
 *
 * This is the locked variant of cxl_decoder_add().
 *
 * Context: Process context. Expects the device lock of the port that owns the
 *	    @cxld to be held.
 *
 * Return: Negative error code if the decoder wasn't properly configured; else
 *	   returns 0.
 */
int cxl_decoder_add_locked(struct cxl_decoder *cxld, int *target_map)
{
	struct cxl_port *port;
	struct device *dev;
	int rc;

	if (WARN_ON_ONCE(!cxld))
		return -EINVAL;

	if (WARN_ON_ONCE(IS_ERR(cxld)))
		return PTR_ERR(cxld);

	if (cxld->interleave_ways < 1)
		return -EINVAL;

	dev = &cxld->dev;

	port = to_cxl_port(cxld->dev.parent);
	if (!is_endpoint_decoder(dev)) {
		struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);

		rc = decoder_populate_targets(cxlsd, port, target_map);
		if (rc && (cxld->flags & CXL_DECODER_F_ENABLE)) {
			dev_err(&port->dev,
				"Failed to populate active decoder targets\n");
			return rc;
		}
	}

	rc = dev_set_name(dev, "decoder%d.%d", port->id, cxld->id);
	if (rc)
		return rc;

	return device_add(dev);
}
EXPORT_SYMBOL_NS_GPL(cxl_decoder_add_locked, CXL);

/**
 * cxl_decoder_add - Add a decoder with targets
 * @cxld: The cxl decoder allocated by cxl_<type>_decoder_alloc()
 * @target_map: A list of downstream ports that this decoder can direct memory
 *              traffic to. These numbers should correspond with the port number
 *              in the PCIe Link Capabilities structure.
 *
 * This is the unlocked variant of cxl_decoder_add_locked().
 * See cxl_decoder_add_locked().
 *
 * Context: Process context. Takes and releases the device lock of the port that
 *	    owns the @cxld.
 */
int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map)
{
	struct cxl_port *port;
	int rc;

	if (WARN_ON_ONCE(!cxld))
		return -EINVAL;

	if (WARN_ON_ONCE(IS_ERR(cxld)))
		return PTR_ERR(cxld);

	port = to_cxl_port(cxld->dev.parent);

	device_lock(&port->dev);
	rc = cxl_decoder_add_locked(cxld, target_map);
	device_unlock(&port->dev);

	return rc;
}
EXPORT_SYMBOL_NS_GPL(cxl_decoder_add, CXL);

static void cxld_unregister(void *dev)
{
	struct cxl_endpoint_decoder *cxled;

	if (is_endpoint_decoder(dev)) {
		cxled = to_cxl_endpoint_decoder(dev);
		cxl_decoder_kill_region(cxled);
	}

	device_unregister(dev);
}

int cxl_decoder_autoremove(struct device *host, struct cxl_decoder *cxld)
{
	return devm_add_action_or_reset(host, cxld_unregister, &cxld->dev);
}
EXPORT_SYMBOL_NS_GPL(cxl_decoder_autoremove, CXL);

/**
 * __cxl_driver_register - register a driver for the cxl bus
 * @cxl_drv: cxl driver structure to attach
 * @owner: owning module/driver
 * @modname: KBUILD_MODNAME for parent driver
 */
int __cxl_driver_register(struct cxl_driver *cxl_drv, struct module *owner,
			  const char *modname)
{
	if (!cxl_drv->probe) {
		pr_debug("%s ->probe() must be specified\n", modname);
		return -EINVAL;
	}

	if (!cxl_drv->name) {
		pr_debug("%s ->name must be specified\n", modname);
		return -EINVAL;
	}

	if (!cxl_drv->id) {
		pr_debug("%s ->id must be specified\n", modname);
		return -EINVAL;
	}

	cxl_drv->drv.bus = &cxl_bus_type;
	cxl_drv->drv.owner = owner;
	cxl_drv->drv.mod_name = modname;
	cxl_drv->drv.name = cxl_drv->name;

	return driver_register(&cxl_drv->drv);
}
EXPORT_SYMBOL_NS_GPL(__cxl_driver_register, CXL);

void cxl_driver_unregister(struct cxl_driver *cxl_drv)
{
	driver_unregister(&cxl_drv->drv);
}
EXPORT_SYMBOL_NS_GPL(cxl_driver_unregister, CXL);

static int cxl_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
{
	return add_uevent_var(env, "MODALIAS=" CXL_MODALIAS_FMT,
			      cxl_device_id(dev));
}

static int cxl_bus_match(struct device *dev, struct device_driver *drv)
{
	return cxl_device_id(dev) == to_cxl_drv(drv)->id;
}

static int cxl_bus_probe(struct device *dev)
{
	int rc;

	rc = to_cxl_drv(dev->driver)->probe(dev);
	dev_dbg(dev, "probe: %d\n", rc);
	return rc;
}

static void cxl_bus_remove(struct device *dev)
{
	struct cxl_driver *cxl_drv = to_cxl_drv(dev->driver);

	if (cxl_drv->remove)
		cxl_drv->remove(dev);
}

static struct workqueue_struct *cxl_bus_wq;

int cxl_bus_rescan(void)
{
	return bus_rescan_devices(&cxl_bus_type);
}
EXPORT_SYMBOL_NS_GPL(cxl_bus_rescan, CXL);

bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd)
{
	return queue_work(cxl_bus_wq, &cxlmd->detach_work);
}
EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);

/* for user tooling to ensure port disable work has completed */
static ssize_t flush_store(struct bus_type *bus, const char *buf, size_t count)
{
	if (sysfs_streq(buf, "1")) {
		flush_workqueue(cxl_bus_wq);
		return count;
	}

	return -EINVAL;
}

static BUS_ATTR_WO(flush);

static struct attribute *cxl_bus_attributes[] = {
	&bus_attr_flush.attr,
	NULL,
};

static struct attribute_group cxl_bus_attribute_group = {
	.attrs = cxl_bus_attributes,
};

static const struct attribute_group *cxl_bus_attribute_groups[] = {
	&cxl_bus_attribute_group,
	NULL,
};

struct bus_type cxl_bus_type = {
	.name = "cxl",
	.uevent = cxl_bus_uevent,
	.match = cxl_bus_match,
	.probe = cxl_bus_probe,
	.remove = cxl_bus_remove,
	.bus_groups = cxl_bus_attribute_groups,
};
EXPORT_SYMBOL_NS_GPL(cxl_bus_type, CXL);

static struct dentry *cxl_debugfs;

struct dentry *cxl_debugfs_create_dir(const char *dir)
{
	return debugfs_create_dir(dir, cxl_debugfs);
}
EXPORT_SYMBOL_NS_GPL(cxl_debugfs_create_dir, CXL);

static __init int cxl_core_init(void)
{
	int rc;

	cxl_debugfs = debugfs_create_dir("cxl", NULL);

	cxl_mbox_init();

	rc = cxl_memdev_init();
	if (rc)
		return rc;

	cxl_bus_wq = alloc_ordered_workqueue("cxl_port", 0);
	if (!cxl_bus_wq) {
		rc = -ENOMEM;
		goto err_wq;
	}

	rc = bus_register(&cxl_bus_type);
	if (rc)
		goto err_bus;

	rc = cxl_region_init();
	if (rc)
		goto err_region;

	return 0;

err_region:
	bus_unregister(&cxl_bus_type);
err_bus:
	destroy_workqueue(cxl_bus_wq);
err_wq:
	cxl_memdev_exit();
	return rc;
}

static void cxl_core_exit(void)
{
	cxl_region_exit();
	bus_unregister(&cxl_bus_type);
	destroy_workqueue(cxl_bus_wq);
	cxl_memdev_exit();
	debugfs_remove_recursive(cxl_debugfs);
}

module_init(cxl_core_init);
module_exit(cxl_core_exit);
MODULE_LICENSE("GPL v2");