summaryrefslogtreecommitdiff
path: root/drivers/scsi/cxlflash/superpipe.c
blob: ce1507023132369d073c89577bedf5e8d36138e3 (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
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
/*
 * CXL Flash Device Driver
 *
 * Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
 *             Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
 *
 * Copyright (C) 2015 IBM Corporation
 *
 * 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/delay.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <misc/cxl.h>
#include <asm/unaligned.h>

#include <scsi/scsi.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_eh.h>
#include <uapi/scsi/cxlflash_ioctl.h>

#include "sislite.h"
#include "common.h"
#include "vlun.h"
#include "superpipe.h"

struct cxlflash_global global;

/**
 * marshal_rele_to_resize() - translate release to resize structure
 * @rele:	Source structure from which to translate/copy.
 * @resize:	Destination structure for the translate/copy.
 */
static void marshal_rele_to_resize(struct dk_cxlflash_release *release,
				   struct dk_cxlflash_resize *resize)
{
	resize->hdr = release->hdr;
	resize->context_id = release->context_id;
	resize->rsrc_handle = release->rsrc_handle;
}

/**
 * marshal_det_to_rele() - translate detach to release structure
 * @detach:	Destination structure for the translate/copy.
 * @rele:	Source structure from which to translate/copy.
 */
static void marshal_det_to_rele(struct dk_cxlflash_detach *detach,
				struct dk_cxlflash_release *release)
{
	release->hdr = detach->hdr;
	release->context_id = detach->context_id;
}

/**
 * cxlflash_free_errpage() - frees resources associated with global error page
 */
void cxlflash_free_errpage(void)
{

	mutex_lock(&global.mutex);
	if (global.err_page) {
		__free_page(global.err_page);
		global.err_page = NULL;
	}
	mutex_unlock(&global.mutex);
}

/**
 * cxlflash_stop_term_user_contexts() - stops/terminates known user contexts
 * @cfg:	Internal structure associated with the host.
 *
 * When the host needs to go down, all users must be quiesced and their
 * memory freed. This is accomplished by putting the contexts in error
 * state which will notify the user and let them 'drive' the tear down.
 * Meanwhile, this routine camps until all user contexts have been removed.
 */
void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg)
{
	struct device *dev = &cfg->dev->dev;
	int i, found;

	cxlflash_mark_contexts_error(cfg);

	while (true) {
		found = false;

		for (i = 0; i < MAX_CONTEXT; i++)
			if (cfg->ctx_tbl[i]) {
				found = true;
				break;
			}

		if (!found && list_empty(&cfg->ctx_err_recovery))
			return;

		dev_dbg(dev, "%s: Wait for user contexts to quiesce...\n",
			__func__);
		wake_up_all(&cfg->reset_waitq);
		ssleep(1);
	}
}

/**
 * find_error_context() - locates a context by cookie on the error recovery list
 * @cfg:	Internal structure associated with the host.
 * @rctxid:	Desired context by id.
 * @file:	Desired context by file.
 *
 * Return: Found context on success, NULL on failure
 */
static struct ctx_info *find_error_context(struct cxlflash_cfg *cfg, u64 rctxid,
					   struct file *file)
{
	struct ctx_info *ctxi;

	list_for_each_entry(ctxi, &cfg->ctx_err_recovery, list)
		if ((ctxi->ctxid == rctxid) || (ctxi->file == file))
			return ctxi;

	return NULL;
}

/**
 * get_context() - obtains a validated and locked context reference
 * @cfg:	Internal structure associated with the host.
 * @rctxid:	Desired context (raw, un-decoded format).
 * @arg:	LUN information or file associated with request.
 * @ctx_ctrl:	Control information to 'steer' desired lookup.
 *
 * NOTE: despite the name pid, in linux, current->pid actually refers
 * to the lightweight process id (tid) and can change if the process is
 * multi threaded. The tgid remains constant for the process and only changes
 * when the process of fork. For all intents and purposes, think of tgid
 * as a pid in the traditional sense.
 *
 * Return: Validated context on success, NULL on failure
 */
struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid,
			     void *arg, enum ctx_ctrl ctx_ctrl)
{
	struct device *dev = &cfg->dev->dev;
	struct ctx_info *ctxi = NULL;
	struct lun_access *lun_access = NULL;
	struct file *file = NULL;
	struct llun_info *lli = arg;
	u64 ctxid = DECODE_CTXID(rctxid);
	int rc;
	pid_t pid = current->tgid, ctxpid = 0;

	if (ctx_ctrl & CTX_CTRL_FILE) {
		lli = NULL;
		file = (struct file *)arg;
	}

	if (ctx_ctrl & CTX_CTRL_CLONE)
		pid = current->parent->tgid;

	if (likely(ctxid < MAX_CONTEXT)) {
		while (true) {
			mutex_lock(&cfg->ctx_tbl_list_mutex);
			ctxi = cfg->ctx_tbl[ctxid];
			if (ctxi)
				if ((file && (ctxi->file != file)) ||
				    (!file && (ctxi->ctxid != rctxid)))
					ctxi = NULL;

			if ((ctx_ctrl & CTX_CTRL_ERR) ||
			    (!ctxi && (ctx_ctrl & CTX_CTRL_ERR_FALLBACK)))
				ctxi = find_error_context(cfg, rctxid, file);
			if (!ctxi) {
				mutex_unlock(&cfg->ctx_tbl_list_mutex);
				goto out;
			}

			/*
			 * Need to acquire ownership of the context while still
			 * under the table/list lock to serialize with a remove
			 * thread. Use the 'try' to avoid stalling the
			 * table/list lock for a single context.
			 *
			 * Note that the lock order is:
			 *
			 *	cfg->ctx_tbl_list_mutex -> ctxi->mutex
			 *
			 * Therefore release ctx_tbl_list_mutex before retrying.
			 */
			rc = mutex_trylock(&ctxi->mutex);
			mutex_unlock(&cfg->ctx_tbl_list_mutex);
			if (rc)
				break; /* got the context's lock! */
		}

		if (ctxi->unavail)
			goto denied;

		ctxpid = ctxi->pid;
		if (likely(!(ctx_ctrl & CTX_CTRL_NOPID)))
			if (pid != ctxpid)
				goto denied;

		if (lli) {
			list_for_each_entry(lun_access, &ctxi->luns, list)
				if (lun_access->lli == lli)
					goto out;
			goto denied;
		}
	}

out:
	dev_dbg(dev, "%s: rctxid=%016llX ctxinfo=%p ctxpid=%u pid=%u "
		"ctx_ctrl=%u\n", __func__, rctxid, ctxi, ctxpid, pid,
		ctx_ctrl);

	return ctxi;

denied:
	mutex_unlock(&ctxi->mutex);
	ctxi = NULL;
	goto out;
}

/**
 * put_context() - release a context that was retrieved from get_context()
 * @ctxi:	Context to release.
 *
 * For now, releasing the context equates to unlocking it's mutex.
 */
void put_context(struct ctx_info *ctxi)
{
	mutex_unlock(&ctxi->mutex);
}

/**
 * afu_attach() - attach a context to the AFU
 * @cfg:	Internal structure associated with the host.
 * @ctxi:	Context to attach.
 *
 * Upon setting the context capabilities, they must be confirmed with
 * a read back operation as the context might have been closed since
 * the mailbox was unlocked. When this occurs, registration is failed.
 *
 * Return: 0 on success, -errno on failure
 */
static int afu_attach(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
{
	struct device *dev = &cfg->dev->dev;
	struct afu *afu = cfg->afu;
	struct sisl_ctrl_map __iomem *ctrl_map = ctxi->ctrl_map;
	int rc = 0;
	u64 val;

	/* Unlock cap and restrict user to read/write cmds in translated mode */
	readq_be(&ctrl_map->mbox_r);
	val = (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD);
	writeq_be(val, &ctrl_map->ctx_cap);
	val = readq_be(&ctrl_map->ctx_cap);
	if (val != (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD)) {
		dev_err(dev, "%s: ctx may be closed val=%016llX\n",
			__func__, val);
		rc = -EAGAIN;
		goto out;
	}

	/* Set up MMIO registers pointing to the RHT */
	writeq_be((u64)ctxi->rht_start, &ctrl_map->rht_start);
	val = SISL_RHT_CNT_ID((u64)MAX_RHT_PER_CONTEXT, (u64)(afu->ctx_hndl));
	writeq_be(val, &ctrl_map->rht_cnt_id);
out:
	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
	return rc;
}

/**
 * read_cap16() - issues a SCSI READ_CAP16 command
 * @sdev:	SCSI device associated with LUN.
 * @lli:	LUN destined for capacity request.
 *
 * The READ_CAP16 can take quite a while to complete. Should an EEH occur while
 * in scsi_execute(), the EEH handler will attempt to recover. As part of the
 * recovery, the handler drains all currently running ioctls, waiting until they
 * have completed before proceeding with a reset. As this routine is used on the
 * ioctl path, this can create a condition where the EEH handler becomes stuck,
 * infinitely waiting for this ioctl thread. To avoid this behavior, temporarily
 * unmark this thread as an ioctl thread by releasing the ioctl read semaphore.
 * This will allow the EEH handler to proceed with a recovery while this thread
 * is still running. Once the scsi_execute() returns, reacquire the ioctl read
 * semaphore and check the adapter state in case it changed while inside of
 * scsi_execute(). The state check will wait if the adapter is still being
 * recovered or return a failure if the recovery failed. In the event that the
 * adapter reset failed, simply return the failure as the ioctl would be unable
 * to continue.
 *
 * Note that the above puts a requirement on this routine to only be called on
 * an ioctl thread.
 *
 * Return: 0 on success, -errno on failure
 */
static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct glun_info *gli = lli->parent;
	u8 *cmd_buf = NULL;
	u8 *scsi_cmd = NULL;
	u8 *sense_buf = NULL;
	int rc = 0;
	int result = 0;
	int retry_cnt = 0;
	u32 to = CMD_TIMEOUT * HZ;

retry:
	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
		rc = -ENOMEM;
		goto out;
	}

	scsi_cmd[0] = SERVICE_ACTION_IN_16;	/* read cap(16) */
	scsi_cmd[1] = SAI_READ_CAPACITY_16;	/* service action */
	put_unaligned_be32(CMD_BUFSIZE, &scsi_cmd[10]);

	dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
		retry_cnt ? "re" : "", scsi_cmd[0]);

	/* Drop the ioctl read semahpore across lengthy call */
	up_read(&cfg->ioctl_rwsem);
	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
			      CMD_BUFSIZE, sense_buf, to, CMD_RETRIES, 0, NULL);
	down_read(&cfg->ioctl_rwsem);
	rc = check_state(cfg);
	if (rc) {
		dev_err(dev, "%s: Failed state! result=0x08%X\n",
			__func__, result);
		rc = -ENODEV;
		goto out;
	}

	if (driver_byte(result) == DRIVER_SENSE) {
		result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
		if (result & SAM_STAT_CHECK_CONDITION) {
			struct scsi_sense_hdr sshdr;

			scsi_normalize_sense(sense_buf, SCSI_SENSE_BUFFERSIZE,
					    &sshdr);
			switch (sshdr.sense_key) {
			case NO_SENSE:
			case RECOVERED_ERROR:
				/* fall through */
			case NOT_READY:
				result &= ~SAM_STAT_CHECK_CONDITION;
				break;
			case UNIT_ATTENTION:
				switch (sshdr.asc) {
				case 0x29: /* Power on Reset or Device Reset */
					/* fall through */
				case 0x2A: /* Device capacity changed */
				case 0x3F: /* Report LUNs changed */
					/* Retry the command once more */
					if (retry_cnt++ < 1) {
						kfree(cmd_buf);
						kfree(scsi_cmd);
						kfree(sense_buf);
						goto retry;
					}
				}
				break;
			default:
				break;
			}
		}
	}

	if (result) {
		dev_err(dev, "%s: command failed, result=0x%x\n",
			__func__, result);
		rc = -EIO;
		goto out;
	}

	/*
	 * Read cap was successful, grab values from the buffer;
	 * note that we don't need to worry about unaligned access
	 * as the buffer is allocated on an aligned boundary.
	 */
	mutex_lock(&gli->mutex);
	gli->max_lba = be64_to_cpu(*((__be64 *)&cmd_buf[0]));
	gli->blk_len = be32_to_cpu(*((__be32 *)&cmd_buf[8]));
	mutex_unlock(&gli->mutex);

out:
	kfree(cmd_buf);
	kfree(scsi_cmd);
	kfree(sense_buf);

	dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
		__func__, gli->max_lba, gli->blk_len, rc);
	return rc;
}

/**
 * get_rhte() - obtains validated resource handle table entry reference
 * @ctxi:	Context owning the resource handle.
 * @rhndl:	Resource handle associated with entry.
 * @lli:	LUN associated with request.
 *
 * Return: Validated RHTE on success, NULL on failure
 */
struct sisl_rht_entry *get_rhte(struct ctx_info *ctxi, res_hndl_t rhndl,
				struct llun_info *lli)
{
	struct sisl_rht_entry *rhte = NULL;

	if (unlikely(!ctxi->rht_start)) {
		pr_debug("%s: Context does not have allocated RHT!\n",
			 __func__);
		goto out;
	}

	if (unlikely(rhndl >= MAX_RHT_PER_CONTEXT)) {
		pr_debug("%s: Bad resource handle! (%d)\n", __func__, rhndl);
		goto out;
	}

	if (unlikely(ctxi->rht_lun[rhndl] != lli)) {
		pr_debug("%s: Bad resource handle LUN! (%d)\n",
			 __func__, rhndl);
		goto out;
	}

	rhte = &ctxi->rht_start[rhndl];
	if (unlikely(rhte->nmask == 0)) {
		pr_debug("%s: Unopened resource handle! (%d)\n",
			 __func__, rhndl);
		rhte = NULL;
		goto out;
	}

out:
	return rhte;
}

/**
 * rhte_checkout() - obtains free/empty resource handle table entry
 * @ctxi:	Context owning the resource handle.
 * @lli:	LUN associated with request.
 *
 * Return: Free RHTE on success, NULL on failure
 */
struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
				     struct llun_info *lli)
{
	struct sisl_rht_entry *rhte = NULL;
	int i;

	/* Find a free RHT entry */
	for (i = 0; i < MAX_RHT_PER_CONTEXT; i++)
		if (ctxi->rht_start[i].nmask == 0) {
			rhte = &ctxi->rht_start[i];
			ctxi->rht_out++;
			break;
		}

	if (likely(rhte))
		ctxi->rht_lun[i] = lli;

	pr_debug("%s: returning rhte=%p (%d)\n", __func__, rhte, i);
	return rhte;
}

/**
 * rhte_checkin() - releases a resource handle table entry
 * @ctxi:	Context owning the resource handle.
 * @rhte:	RHTE to release.
 */
void rhte_checkin(struct ctx_info *ctxi,
		  struct sisl_rht_entry *rhte)
{
	u32 rsrc_handle = rhte - ctxi->rht_start;

	rhte->nmask = 0;
	rhte->fp = 0;
	ctxi->rht_out--;
	ctxi->rht_lun[rsrc_handle] = NULL;
	ctxi->rht_needs_ws[rsrc_handle] = false;
}

/**
 * rhte_format1() - populates a RHTE for format 1
 * @rhte:	RHTE to populate.
 * @lun_id:	LUN ID of LUN associated with RHTE.
 * @perm:	Desired permissions for RHTE.
 * @port_sel:	Port selection mask
 */
static void rht_format1(struct sisl_rht_entry *rhte, u64 lun_id, u32 perm,
			u32 port_sel)
{
	/*
	 * Populate the Format 1 RHT entry for direct access (physical
	 * LUN) using the synchronization sequence defined in the
	 * SISLite specification.
	 */
	struct sisl_rht_entry_f1 dummy = { 0 };
	struct sisl_rht_entry_f1 *rhte_f1 = (struct sisl_rht_entry_f1 *)rhte;

	memset(rhte_f1, 0, sizeof(*rhte_f1));
	rhte_f1->fp = SISL_RHT_FP(1U, 0);
	dma_wmb(); /* Make setting of format bit visible */

	rhte_f1->lun_id = lun_id;
	dma_wmb(); /* Make setting of LUN id visible */

	/*
	 * Use a dummy RHT Format 1 entry to build the second dword
	 * of the entry that must be populated in a single write when
	 * enabled (valid bit set to TRUE).
	 */
	dummy.valid = 0x80;
	dummy.fp = SISL_RHT_FP(1U, perm);
	dummy.port_sel = port_sel;
	rhte_f1->dw = dummy.dw;

	dma_wmb(); /* Make remaining RHT entry fields visible */
}

/**
 * cxlflash_lun_attach() - attaches a user to a LUN and manages the LUN's mode
 * @gli:	LUN to attach.
 * @mode:	Desired mode of the LUN.
 * @locked:	Mutex status on current thread.
 *
 * Return: 0 on success, -errno on failure
 */
int cxlflash_lun_attach(struct glun_info *gli, enum lun_mode mode, bool locked)
{
	int rc = 0;

	if (!locked)
		mutex_lock(&gli->mutex);

	if (gli->mode == MODE_NONE)
		gli->mode = mode;
	else if (gli->mode != mode) {
		pr_debug("%s: LUN operating in mode %d, requested mode %d\n",
			 __func__, gli->mode, mode);
		rc = -EINVAL;
		goto out;
	}

	gli->users++;
	WARN_ON(gli->users <= 0);
out:
	pr_debug("%s: Returning rc=%d gli->mode=%u gli->users=%u\n",
		 __func__, rc, gli->mode, gli->users);
	if (!locked)
		mutex_unlock(&gli->mutex);
	return rc;
}

/**
 * cxlflash_lun_detach() - detaches a user from a LUN and resets the LUN's mode
 * @gli:	LUN to detach.
 *
 * When resetting the mode, terminate block allocation resources as they
 * are no longer required (service is safe to call even when block allocation
 * resources were not present - such as when transitioning from physical mode).
 * These resources will be reallocated when needed (subsequent transition to
 * virtual mode).
 */
void cxlflash_lun_detach(struct glun_info *gli)
{
	mutex_lock(&gli->mutex);
	WARN_ON(gli->mode == MODE_NONE);
	if (--gli->users == 0) {
		gli->mode = MODE_NONE;
		cxlflash_ba_terminate(&gli->blka.ba_lun);
	}
	pr_debug("%s: gli->users=%u\n", __func__, gli->users);
	WARN_ON(gli->users < 0);
	mutex_unlock(&gli->mutex);
}

/**
 * _cxlflash_disk_release() - releases the specified resource entry
 * @sdev:	SCSI device associated with LUN.
 * @ctxi:	Context owning resources.
 * @release:	Release ioctl data structure.
 *
 * For LUNs in virtual mode, the virtual LUN associated with the specified
 * resource handle is resized to 0 prior to releasing the RHTE. Note that the
 * AFU sync should _not_ be performed when the context is sitting on the error
 * recovery list. A context on the error recovery list is not known to the AFU
 * due to reset. When the context is recovered, it will be reattached and made
 * known again to the AFU.
 *
 * Return: 0 on success, -errno on failure
 */
int _cxlflash_disk_release(struct scsi_device *sdev,
			   struct ctx_info *ctxi,
			   struct dk_cxlflash_release *release)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	struct glun_info *gli = lli->parent;
	struct afu *afu = cfg->afu;
	bool put_ctx = false;

	struct dk_cxlflash_resize size;
	res_hndl_t rhndl = release->rsrc_handle;

	int rc = 0;
	u64 ctxid = DECODE_CTXID(release->context_id),
	    rctxid = release->context_id;

	struct sisl_rht_entry *rhte;
	struct sisl_rht_entry_f1 *rhte_f1;

	dev_dbg(dev, "%s: ctxid=%llu rhndl=0x%llx gli->mode=%u gli->users=%u\n",
		__func__, ctxid, release->rsrc_handle, gli->mode, gli->users);

	if (!ctxi) {
		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
		if (unlikely(!ctxi)) {
			dev_dbg(dev, "%s: Bad context! (%llu)\n",
				__func__, ctxid);
			rc = -EINVAL;
			goto out;
		}

		put_ctx = true;
	}

	rhte = get_rhte(ctxi, rhndl, lli);
	if (unlikely(!rhte)) {
		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
			__func__, rhndl);
		rc = -EINVAL;
		goto out;
	}

	/*
	 * Resize to 0 for virtual LUNS by setting the size
	 * to 0. This will clear LXT_START and LXT_CNT fields
	 * in the RHT entry and properly sync with the AFU.
	 *
	 * Afterwards we clear the remaining fields.
	 */
	switch (gli->mode) {
	case MODE_VIRTUAL:
		marshal_rele_to_resize(release, &size);
		size.req_size = 0;
		rc = _cxlflash_vlun_resize(sdev, ctxi, &size);
		if (rc) {
			dev_dbg(dev, "%s: resize failed rc %d\n", __func__, rc);
			goto out;
		}

		break;
	case MODE_PHYSICAL:
		/*
		 * Clear the Format 1 RHT entry for direct access
		 * (physical LUN) using the synchronization sequence
		 * defined in the SISLite specification.
		 */
		rhte_f1 = (struct sisl_rht_entry_f1 *)rhte;

		rhte_f1->valid = 0;
		dma_wmb(); /* Make revocation of RHT entry visible */

		rhte_f1->lun_id = 0;
		dma_wmb(); /* Make clearing of LUN id visible */

		rhte_f1->dw = 0;
		dma_wmb(); /* Make RHT entry bottom-half clearing visible */

		if (!ctxi->err_recovery_active)
			cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC);
		break;
	default:
		WARN(1, "Unsupported LUN mode!");
		goto out;
	}

	rhte_checkin(ctxi, rhte);
	cxlflash_lun_detach(gli);

out:
	if (put_ctx)
		put_context(ctxi);
	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
	return rc;
}

int cxlflash_disk_release(struct scsi_device *sdev,
			  struct dk_cxlflash_release *release)
{
	return _cxlflash_disk_release(sdev, NULL, release);
}

/**
 * destroy_context() - releases a context
 * @cfg:	Internal structure associated with the host.
 * @ctxi:	Context to release.
 *
 * This routine is safe to be called with a a non-initialized context
 * and is tolerant of being called with the context's mutex held (it
 * will be unlocked if necessary before freeing). Also note that the
 * routine conditionally checks for the existence of the context control
 * map before clearing the RHT registers and context capabilities because
 * it is possible to destroy a context while the context is in the error
 * state (previous mapping was removed [so there is no need to worry about
 * clearing] and context is waiting for a new mapping).
 */
static void destroy_context(struct cxlflash_cfg *cfg,
			    struct ctx_info *ctxi)
{
	struct afu *afu = cfg->afu;

	if (ctxi->initialized) {
		WARN_ON(!list_empty(&ctxi->luns));

		/* Clear RHT registers and drop all capabilities for context */
		if (afu->afu_map && ctxi->ctrl_map) {
			writeq_be(0, &ctxi->ctrl_map->rht_start);
			writeq_be(0, &ctxi->ctrl_map->rht_cnt_id);
			writeq_be(0, &ctxi->ctrl_map->ctx_cap);
		}

		if (mutex_is_locked(&ctxi->mutex))
			mutex_unlock(&ctxi->mutex);
	}

	/* Free memory associated with context */
	free_page((ulong)ctxi->rht_start);
	kfree(ctxi->rht_needs_ws);
	kfree(ctxi->rht_lun);
	kfree(ctxi);
}

/**
 * create_context() - allocates and initializes a context
 * @cfg:	Internal structure associated with the host.
 *
 * Return: Allocated context on success, NULL on failure
 */
static struct ctx_info *create_context(struct cxlflash_cfg *cfg)
{
	struct device *dev = &cfg->dev->dev;
	struct ctx_info *ctxi = NULL;
	struct llun_info **lli = NULL;
	u8 *ws = NULL;
	struct sisl_rht_entry *rhte;

	ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL);
	lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL);
	ws = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*ws)), GFP_KERNEL);
	if (unlikely(!ctxi || !lli || !ws)) {
		dev_err(dev, "%s: Unable to allocate context!\n", __func__);
		goto err;
	}

	rhte = (struct sisl_rht_entry *)get_zeroed_page(GFP_KERNEL);
	if (unlikely(!rhte)) {
		dev_err(dev, "%s: Unable to allocate RHT!\n", __func__);
		goto err;
	}

	ctxi->rht_lun = lli;
	ctxi->rht_needs_ws = ws;
	ctxi->rht_start = rhte;
out:
	return ctxi;

err:
	kfree(ws);
	kfree(lli);
	kfree(ctxi);
	ctxi = NULL;
	goto out;
}

/**
 * init_context() - initializes a previously allocated context
 * @ctxi:	Previously allocated context
 * @cfg:	Internal structure associated with the host.
 * @ctx:	Previously obtained CXL context reference.
 * @ctxid:	Previously obtained process element associated with CXL context.
 * @adap_fd:	Previously obtained adapter fd associated with CXL context.
 * @file:	Previously obtained file associated with CXL context.
 * @perms:	User-specified permissions.
 *
 * Upon return, the context is marked as initialized and the context's mutex
 * is locked.
 */
static void init_context(struct ctx_info *ctxi, struct cxlflash_cfg *cfg,
			 struct cxl_context *ctx, int ctxid, int adap_fd,
			 struct file *file, u32 perms)
{
	struct afu *afu = cfg->afu;

	ctxi->rht_perms = perms;
	ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl;
	ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid);
	ctxi->lfd = adap_fd;
	ctxi->pid = current->tgid; /* tgid = pid */
	ctxi->ctx = ctx;
	ctxi->file = file;
	ctxi->initialized = true;
	mutex_init(&ctxi->mutex);
	INIT_LIST_HEAD(&ctxi->luns);
	INIT_LIST_HEAD(&ctxi->list); /* initialize for list_empty() */

	mutex_lock(&ctxi->mutex);
}

/**
 * _cxlflash_disk_detach() - detaches a LUN from a context
 * @sdev:	SCSI device associated with LUN.
 * @ctxi:	Context owning resources.
 * @detach:	Detach ioctl data structure.
 *
 * As part of the detach, all per-context resources associated with the LUN
 * are cleaned up. When detaching the last LUN for a context, the context
 * itself is cleaned up and released.
 *
 * Return: 0 on success, -errno on failure
 */
static int _cxlflash_disk_detach(struct scsi_device *sdev,
				 struct ctx_info *ctxi,
				 struct dk_cxlflash_detach *detach)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	struct lun_access *lun_access, *t;
	struct dk_cxlflash_release rel;
	bool put_ctx = false;

	int i;
	int rc = 0;
	int lfd;
	u64 ctxid = DECODE_CTXID(detach->context_id),
	    rctxid = detach->context_id;

	dev_dbg(dev, "%s: ctxid=%llu\n", __func__, ctxid);

	if (!ctxi) {
		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
		if (unlikely(!ctxi)) {
			dev_dbg(dev, "%s: Bad context! (%llu)\n",
				__func__, ctxid);
			rc = -EINVAL;
			goto out;
		}

		put_ctx = true;
	}

	/* Cleanup outstanding resources tied to this LUN */
	if (ctxi->rht_out) {
		marshal_det_to_rele(detach, &rel);
		for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) {
			if (ctxi->rht_lun[i] == lli) {
				rel.rsrc_handle = i;
				_cxlflash_disk_release(sdev, ctxi, &rel);
			}

			/* No need to loop further if we're done */
			if (ctxi->rht_out == 0)
				break;
		}
	}

	/* Take our LUN out of context, free the node */
	list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
		if (lun_access->lli == lli) {
			list_del(&lun_access->list);
			kfree(lun_access);
			lun_access = NULL;
			break;
		}

	/* Tear down context following last LUN cleanup */
	if (list_empty(&ctxi->luns)) {
		ctxi->unavail = true;
		mutex_unlock(&ctxi->mutex);
		mutex_lock(&cfg->ctx_tbl_list_mutex);
		mutex_lock(&ctxi->mutex);

		/* Might not have been in error list so conditionally remove */
		if (!list_empty(&ctxi->list))
			list_del(&ctxi->list);
		cfg->ctx_tbl[ctxid] = NULL;
		mutex_unlock(&cfg->ctx_tbl_list_mutex);
		mutex_unlock(&ctxi->mutex);

		lfd = ctxi->lfd;
		destroy_context(cfg, ctxi);
		ctxi = NULL;
		put_ctx = false;

		/*
		 * As a last step, clean up external resources when not
		 * already on an external cleanup thread, i.e.: close(adap_fd).
		 *
		 * NOTE: this will free up the context from the CXL services,
		 * allowing it to dole out the same context_id on a future
		 * (or even currently in-flight) disk_attach operation.
		 */
		if (lfd != -1)
			sys_close(lfd);
	}

	/* Release the sdev reference that bound this LUN to the context */
	scsi_device_put(sdev);

out:
	if (put_ctx)
		put_context(ctxi);
	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
	return rc;
}

static int cxlflash_disk_detach(struct scsi_device *sdev,
				struct dk_cxlflash_detach *detach)
{
	return _cxlflash_disk_detach(sdev, NULL, detach);
}

/**
 * cxlflash_cxl_release() - release handler for adapter file descriptor
 * @inode:	File-system inode associated with fd.
 * @file:	File installed with adapter file descriptor.
 *
 * This routine is the release handler for the fops registered with
 * the CXL services on an initial attach for a context. It is called
 * when a close is performed on the adapter file descriptor returned
 * to the user. Programmatically, the user is not required to perform
 * the close, as it is handled internally via the detach ioctl when
 * a context is being removed. Note that nothing prevents the user
 * from performing a close, but the user should be aware that doing
 * so is considered catastrophic and subsequent usage of the superpipe
 * API with previously saved off tokens will fail.
 *
 * When initiated from an external close (either by the user or via
 * a process tear down), the routine derives the context reference
 * and calls detach for each LUN associated with the context. The
 * final detach operation will cause the context itself to be freed.
 * Note that the saved off lfd is reset prior to calling detach to
 * signify that the final detach should not perform a close.
 *
 * When initiated from a detach operation as part of the tear down
 * of a context, the context is first completely freed and then the
 * close is performed. This routine will fail to derive the context
 * reference (due to the context having already been freed) and then
 * call into the CXL release entry point.
 *
 * Thus, with exception to when the CXL process element (context id)
 * lookup fails (a case that should theoretically never occur), every
 * call into this routine results in a complete freeing of a context.
 *
 * As part of the detach, all per-context resources associated with the LUN
 * are cleaned up. When detaching the last LUN for a context, the context
 * itself is cleaned up and released.
 *
 * Return: 0 on success
 */
static int cxlflash_cxl_release(struct inode *inode, struct file *file)
{
	struct cxl_context *ctx = cxl_fops_get_context(file);
	struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
						cxl_fops);
	struct device *dev = &cfg->dev->dev;
	struct ctx_info *ctxi = NULL;
	struct dk_cxlflash_detach detach = { { 0 }, 0 };
	struct lun_access *lun_access, *t;
	enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
	int ctxid;

	ctxid = cxl_process_element(ctx);
	if (unlikely(ctxid < 0)) {
		dev_err(dev, "%s: Context %p was closed! (%d)\n",
			__func__, ctx, ctxid);
		goto out;
	}

	ctxi = get_context(cfg, ctxid, file, ctrl);
	if (unlikely(!ctxi)) {
		ctxi = get_context(cfg, ctxid, file, ctrl | CTX_CTRL_CLONE);
		if (!ctxi) {
			dev_dbg(dev, "%s: Context %d already free!\n",
				__func__, ctxid);
			goto out_release;
		}

		dev_dbg(dev, "%s: Another process owns context %d!\n",
			__func__, ctxid);
		put_context(ctxi);
		goto out;
	}

	dev_dbg(dev, "%s: close(%d) for context %d\n",
		__func__, ctxi->lfd, ctxid);

	/* Reset the file descriptor to indicate we're on a close() thread */
	ctxi->lfd = -1;
	detach.context_id = ctxi->ctxid;
	list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
		_cxlflash_disk_detach(lun_access->sdev, ctxi, &detach);
out_release:
	cxl_fd_release(inode, file);
out:
	dev_dbg(dev, "%s: returning\n", __func__);
	return 0;
}

/**
 * unmap_context() - clears a previously established mapping
 * @ctxi:	Context owning the mapping.
 *
 * This routine is used to switch between the error notification page
 * (dummy page of all 1's) and the real mapping (established by the CXL
 * fault handler).
 */
static void unmap_context(struct ctx_info *ctxi)
{
	unmap_mapping_range(ctxi->file->f_mapping, 0, 0, 1);
}

/**
 * get_err_page() - obtains and allocates the error notification page
 *
 * Return: error notification page on success, NULL on failure
 */
static struct page *get_err_page(void)
{
	struct page *err_page = global.err_page;

	if (unlikely(!err_page)) {
		err_page = alloc_page(GFP_KERNEL);
		if (unlikely(!err_page)) {
			pr_err("%s: Unable to allocate err_page!\n", __func__);
			goto out;
		}

		memset(page_address(err_page), -1, PAGE_SIZE);

		/* Serialize update w/ other threads to avoid a leak */
		mutex_lock(&global.mutex);
		if (likely(!global.err_page))
			global.err_page = err_page;
		else {
			__free_page(err_page);
			err_page = global.err_page;
		}
		mutex_unlock(&global.mutex);
	}

out:
	pr_debug("%s: returning err_page=%p\n", __func__, err_page);
	return err_page;
}

/**
 * cxlflash_mmap_fault() - mmap fault handler for adapter file descriptor
 * @vma:	VM area associated with mapping.
 * @vmf:	VM fault associated with current fault.
 *
 * To support error notification via MMIO, faults are 'caught' by this routine
 * that was inserted before passing back the adapter file descriptor on attach.
 * When a fault occurs, this routine evaluates if error recovery is active and
 * if so, installs the error page to 'notify' the user about the error state.
 * During normal operation, the fault is simply handled by the original fault
 * handler that was installed by CXL services as part of initializing the
 * adapter file descriptor. The VMA's page protection bits are toggled to
 * indicate cached/not-cached depending on the memory backing the fault.
 *
 * Return: 0 on success, VM_FAULT_SIGBUS on failure
 */
static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct file *file = vma->vm_file;
	struct cxl_context *ctx = cxl_fops_get_context(file);
	struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
						cxl_fops);
	struct device *dev = &cfg->dev->dev;
	struct ctx_info *ctxi = NULL;
	struct page *err_page = NULL;
	enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
	int rc = 0;
	int ctxid;

	ctxid = cxl_process_element(ctx);
	if (unlikely(ctxid < 0)) {
		dev_err(dev, "%s: Context %p was closed! (%d)\n",
			__func__, ctx, ctxid);
		goto err;
	}

	ctxi = get_context(cfg, ctxid, file, ctrl);
	if (unlikely(!ctxi)) {
		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
		goto err;
	}

	dev_dbg(dev, "%s: fault(%d) for context %d\n",
		__func__, ctxi->lfd, ctxid);

	if (likely(!ctxi->err_recovery_active)) {
		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
		rc = ctxi->cxl_mmap_vmops->fault(vma, vmf);
	} else {
		dev_dbg(dev, "%s: err recovery active, use err_page!\n",
			__func__);

		err_page = get_err_page();
		if (unlikely(!err_page)) {
			dev_err(dev, "%s: Could not obtain error page!\n",
				__func__);
			rc = VM_FAULT_RETRY;
			goto out;
		}

		get_page(err_page);
		vmf->page = err_page;
		vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
	}

out:
	if (likely(ctxi))
		put_context(ctxi);
	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
	return rc;

err:
	rc = VM_FAULT_SIGBUS;
	goto out;
}

/*
 * Local MMAP vmops to 'catch' faults
 */
static const struct vm_operations_struct cxlflash_mmap_vmops = {
	.fault = cxlflash_mmap_fault,
};

/**
 * cxlflash_cxl_mmap() - mmap handler for adapter file descriptor
 * @file:	File installed with adapter file descriptor.
 * @vma:	VM area associated with mapping.
 *
 * Installs local mmap vmops to 'catch' faults for error notification support.
 *
 * Return: 0 on success, -errno on failure
 */
static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct cxl_context *ctx = cxl_fops_get_context(file);
	struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg,
						cxl_fops);
	struct device *dev = &cfg->dev->dev;
	struct ctx_info *ctxi = NULL;
	enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
	int ctxid;
	int rc = 0;

	ctxid = cxl_process_element(ctx);
	if (unlikely(ctxid < 0)) {
		dev_err(dev, "%s: Context %p was closed! (%d)\n",
			__func__, ctx, ctxid);
		rc = -EIO;
		goto out;
	}

	ctxi = get_context(cfg, ctxid, file, ctrl);
	if (unlikely(!ctxi)) {
		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
		rc = -EIO;
		goto out;
	}

	dev_dbg(dev, "%s: mmap(%d) for context %d\n",
		__func__, ctxi->lfd, ctxid);

	rc = cxl_fd_mmap(file, vma);
	if (likely(!rc)) {
		/* Insert ourself in the mmap fault handler path */
		ctxi->cxl_mmap_vmops = vma->vm_ops;
		vma->vm_ops = &cxlflash_mmap_vmops;
	}

out:
	if (likely(ctxi))
		put_context(ctxi);
	return rc;
}

const struct file_operations cxlflash_cxl_fops = {
	.owner = THIS_MODULE,
	.mmap = cxlflash_cxl_mmap,
	.release = cxlflash_cxl_release,
};

/**
 * cxlflash_mark_contexts_error() - move contexts to error state and list
 * @cfg:	Internal structure associated with the host.
 *
 * A context is only moved over to the error list when there are no outstanding
 * references to it. This ensures that a running operation has completed.
 *
 * Return: 0 on success, -errno on failure
 */
int cxlflash_mark_contexts_error(struct cxlflash_cfg *cfg)
{
	int i, rc = 0;
	struct ctx_info *ctxi = NULL;

	mutex_lock(&cfg->ctx_tbl_list_mutex);

	for (i = 0; i < MAX_CONTEXT; i++) {
		ctxi = cfg->ctx_tbl[i];
		if (ctxi) {
			mutex_lock(&ctxi->mutex);
			cfg->ctx_tbl[i] = NULL;
			list_add(&ctxi->list, &cfg->ctx_err_recovery);
			ctxi->err_recovery_active = true;
			ctxi->ctrl_map = NULL;
			unmap_context(ctxi);
			mutex_unlock(&ctxi->mutex);
		}
	}

	mutex_unlock(&cfg->ctx_tbl_list_mutex);
	return rc;
}

/*
 * Dummy NULL fops
 */
static const struct file_operations null_fops = {
	.owner = THIS_MODULE,
};

/**
 * check_state() - checks and responds to the current adapter state
 * @cfg:	Internal structure associated with the host.
 *
 * This routine can block and should only be used on process context.
 * It assumes that the caller is an ioctl thread and holding the ioctl
 * read semaphore. This is temporarily let up across the wait to allow
 * for draining actively running ioctls. Also note that when waking up
 * from waiting in reset, the state is unknown and must be checked again
 * before proceeding.
 *
 * Return: 0 on success, -errno on failure
 */
int check_state(struct cxlflash_cfg *cfg)
{
	struct device *dev = &cfg->dev->dev;
	int rc = 0;

retry:
	switch (cfg->state) {
	case STATE_RESET:
		dev_dbg(dev, "%s: Reset state, going to wait...\n", __func__);
		up_read(&cfg->ioctl_rwsem);
		rc = wait_event_interruptible(cfg->reset_waitq,
					      cfg->state != STATE_RESET);
		down_read(&cfg->ioctl_rwsem);
		if (unlikely(rc))
			break;
		goto retry;
	case STATE_FAILTERM:
		dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
		rc = -ENODEV;
		break;
	default:
		break;
	}

	return rc;
}

/**
 * cxlflash_disk_attach() - attach a LUN to a context
 * @sdev:	SCSI device associated with LUN.
 * @attach:	Attach ioctl data structure.
 *
 * Creates a context and attaches LUN to it. A LUN can only be attached
 * one time to a context (subsequent attaches for the same context/LUN pair
 * are not supported). Additional LUNs can be attached to a context by
 * specifying the 'reuse' flag defined in the cxlflash_ioctl.h header.
 *
 * Return: 0 on success, -errno on failure
 */
static int cxlflash_disk_attach(struct scsi_device *sdev,
				struct dk_cxlflash_attach *attach)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct afu *afu = cfg->afu;
	struct llun_info *lli = sdev->hostdata;
	struct glun_info *gli = lli->parent;
	struct cxl_ioctl_start_work *work;
	struct ctx_info *ctxi = NULL;
	struct lun_access *lun_access = NULL;
	int rc = 0;
	u32 perms;
	int ctxid = -1;
	u64 rctxid = 0UL;
	struct file *file = NULL;

	struct cxl_context *ctx = NULL;

	int fd = -1;

	if (attach->num_interrupts > 4) {
		dev_dbg(dev, "%s: Cannot support this many interrupts %llu\n",
			__func__, attach->num_interrupts);
		rc = -EINVAL;
		goto out;
	}

	if (gli->max_lba == 0) {
		dev_dbg(dev, "%s: No capacity info for this LUN (%016llX)\n",
			__func__, lli->lun_id[sdev->channel]);
		rc = read_cap16(sdev, lli);
		if (rc) {
			dev_err(dev, "%s: Invalid device! (%d)\n",
				__func__, rc);
			rc = -ENODEV;
			goto out;
		}
		dev_dbg(dev, "%s: LBA = %016llX\n", __func__, gli->max_lba);
		dev_dbg(dev, "%s: BLK_LEN = %08X\n", __func__, gli->blk_len);
	}

	if (attach->hdr.flags & DK_CXLFLASH_ATTACH_REUSE_CONTEXT) {
		rctxid = attach->context_id;
		ctxi = get_context(cfg, rctxid, NULL, 0);
		if (!ctxi) {
			dev_dbg(dev, "%s: Bad context! (%016llX)\n",
				__func__, rctxid);
			rc = -EINVAL;
			goto out;
		}

		list_for_each_entry(lun_access, &ctxi->luns, list)
			if (lun_access->lli == lli) {
				dev_dbg(dev, "%s: Already attached!\n",
					__func__);
				rc = -EINVAL;
				goto out;
			}
	}

	rc = scsi_device_get(sdev);
	if (unlikely(rc)) {
		dev_err(dev, "%s: Unable to get sdev reference!\n", __func__);
		goto out;
	}

	lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL);
	if (unlikely(!lun_access)) {
		dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
		rc = -ENOMEM;
		goto err;
	}

	lun_access->lli = lli;
	lun_access->sdev = sdev;

	/* Non-NULL context indicates reuse */
	if (ctxi) {
		dev_dbg(dev, "%s: Reusing context for LUN! (%016llX)\n",
			__func__, rctxid);
		list_add(&lun_access->list, &ctxi->luns);
		fd = ctxi->lfd;
		goto out_attach;
	}

	ctxi = create_context(cfg);
	if (unlikely(!ctxi)) {
		dev_err(dev, "%s: Failed to create context! (%d)\n",
			__func__, ctxid);
		goto err;
	}

	ctx = cxl_dev_context_init(cfg->dev);
	if (IS_ERR_OR_NULL(ctx)) {
		dev_err(dev, "%s: Could not initialize context %p\n",
			__func__, ctx);
		rc = -ENODEV;
		goto err;
	}

	work = &ctxi->work;
	work->num_interrupts = attach->num_interrupts;
	work->flags = CXL_START_WORK_NUM_IRQS;

	rc = cxl_start_work(ctx, work);
	if (unlikely(rc)) {
		dev_dbg(dev, "%s: Could not start context rc=%d\n",
			__func__, rc);
		goto err;
	}

	ctxid = cxl_process_element(ctx);
	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
		rc = -EPERM;
		goto err;
	}

	file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
	if (unlikely(fd < 0)) {
		rc = -ENODEV;
		dev_err(dev, "%s: Could not get file descriptor\n", __func__);
		goto err;
	}

	/* Translate read/write O_* flags from fcntl.h to AFU permission bits */
	perms = SISL_RHT_PERM(attach->hdr.flags + 1);

	/* Context mutex is locked upon return */
	init_context(ctxi, cfg, ctx, ctxid, fd, file, perms);

	rc = afu_attach(cfg, ctxi);
	if (unlikely(rc)) {
		dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
		goto err;
	}

	/*
	 * No error paths after this point. Once the fd is installed it's
	 * visible to user space and can't be undone safely on this thread.
	 * There is no need to worry about a deadlock here because no one
	 * knows about us yet; we can be the only one holding our mutex.
	 */
	list_add(&lun_access->list, &ctxi->luns);
	mutex_unlock(&ctxi->mutex);
	mutex_lock(&cfg->ctx_tbl_list_mutex);
	mutex_lock(&ctxi->mutex);
	cfg->ctx_tbl[ctxid] = ctxi;
	mutex_unlock(&cfg->ctx_tbl_list_mutex);
	fd_install(fd, file);

out_attach:
	attach->hdr.return_flags = 0;
	attach->context_id = ctxi->ctxid;
	attach->block_size = gli->blk_len;
	attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
	attach->last_lba = gli->max_lba;
	attach->max_xfer = sdev->host->max_sectors * MAX_SECTOR_UNIT;
	attach->max_xfer /= gli->blk_len;

out:
	attach->adap_fd = fd;

	if (ctxi)
		put_context(ctxi);

	dev_dbg(dev, "%s: returning ctxid=%d fd=%d bs=%lld rc=%d llba=%lld\n",
		__func__, ctxid, fd, attach->block_size, rc, attach->last_lba);
	return rc;

err:
	/* Cleanup CXL context; okay to 'stop' even if it was not started */
	if (!IS_ERR_OR_NULL(ctx)) {
		cxl_stop_context(ctx);
		cxl_release_context(ctx);
		ctx = NULL;
	}

	/*
	 * Here, we're overriding the fops with a dummy all-NULL fops because
	 * fput() calls the release fop, which will cause us to mistakenly
	 * call into the CXL code. Rather than try to add yet more complexity
	 * to that routine (cxlflash_cxl_release) we should try to fix the
	 * issue here.
	 */
	if (fd > 0) {
		file->f_op = &null_fops;
		fput(file);
		put_unused_fd(fd);
		fd = -1;
		file = NULL;
	}

	/* Cleanup our context; safe to call even with mutex locked */
	if (ctxi) {
		destroy_context(cfg, ctxi);
		ctxi = NULL;
	}

	kfree(lun_access);
	scsi_device_put(sdev);
	goto out;
}

/**
 * recover_context() - recovers a context in error
 * @cfg:	Internal structure associated with the host.
 * @ctxi:	Context to release.
 *
 * Restablishes the state for a context-in-error.
 *
 * Return: 0 on success, -errno on failure
 */
static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
{
	struct device *dev = &cfg->dev->dev;
	int rc = 0;
	int old_fd, fd = -1;
	int ctxid = -1;
	struct file *file;
	struct cxl_context *ctx;
	struct afu *afu = cfg->afu;

	ctx = cxl_dev_context_init(cfg->dev);
	if (IS_ERR_OR_NULL(ctx)) {
		dev_err(dev, "%s: Could not initialize context %p\n",
			__func__, ctx);
		rc = -ENODEV;
		goto out;
	}

	rc = cxl_start_work(ctx, &ctxi->work);
	if (unlikely(rc)) {
		dev_dbg(dev, "%s: Could not start context rc=%d\n",
			__func__, rc);
		goto err1;
	}

	ctxid = cxl_process_element(ctx);
	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
		rc = -EPERM;
		goto err2;
	}

	file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd);
	if (unlikely(fd < 0)) {
		rc = -ENODEV;
		dev_err(dev, "%s: Could not get file descriptor\n", __func__);
		goto err2;
	}

	/* Update with new MMIO area based on updated context id */
	ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl;

	rc = afu_attach(cfg, ctxi);
	if (rc) {
		dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc);
		goto err3;
	}

	/*
	 * No error paths after this point. Once the fd is installed it's
	 * visible to user space and can't be undone safely on this thread.
	 */
	old_fd = ctxi->lfd;
	ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid);
	ctxi->lfd = fd;
	ctxi->ctx = ctx;
	ctxi->file = file;

	/*
	 * Put context back in table (note the reinit of the context list);
	 * we must first drop the context's mutex and then acquire it in
	 * order with the table/list mutex to avoid a deadlock - safe to do
	 * here because no one can find us at this moment in time.
	 */
	mutex_unlock(&ctxi->mutex);
	mutex_lock(&cfg->ctx_tbl_list_mutex);
	mutex_lock(&ctxi->mutex);
	list_del_init(&ctxi->list);
	cfg->ctx_tbl[ctxid] = ctxi;
	mutex_unlock(&cfg->ctx_tbl_list_mutex);
	fd_install(fd, file);

	/* Release the original adapter fd and associated CXL resources */
	sys_close(old_fd);
out:
	dev_dbg(dev, "%s: returning ctxid=%d fd=%d rc=%d\n",
		__func__, ctxid, fd, rc);
	return rc;

err3:
	fput(file);
	put_unused_fd(fd);
err2:
	cxl_stop_context(ctx);
err1:
	cxl_release_context(ctx);
	goto out;
}

/**
 * cxlflash_afu_recover() - initiates AFU recovery
 * @sdev:	SCSI device associated with LUN.
 * @recover:	Recover ioctl data structure.
 *
 * Only a single recovery is allowed at a time to avoid exhausting CXL
 * resources (leading to recovery failure) in the event that we're up
 * against the maximum number of contexts limit. For similar reasons,
 * a context recovery is retried if there are multiple recoveries taking
 * place at the same time and the failure was due to CXL services being
 * unable to keep up.
 *
 * As this routine is called on ioctl context, it holds the ioctl r/w
 * semaphore that is used to drain ioctls in recovery scenarios. The
 * implementation to achieve the pacing described above (a local mutex)
 * requires that the ioctl r/w semaphore be dropped and reacquired to
 * avoid a 3-way deadlock when multiple process recoveries operate in
 * parallel.
 *
 * Because a user can detect an error condition before the kernel, it is
 * quite possible for this routine to act as the kernel's EEH detection
 * source (MMIO read of mbox_r). Because of this, there is a window of
 * time where an EEH might have been detected but not yet 'serviced'
 * (callback invoked, causing the device to enter reset state). To avoid
 * looping in this routine during that window, a 1 second sleep is in place
 * between the time the MMIO failure is detected and the time a wait on the
 * reset wait queue is attempted via check_state().
 *
 * Return: 0 on success, -errno on failure
 */
static int cxlflash_afu_recover(struct scsi_device *sdev,
				struct dk_cxlflash_recover_afu *recover)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	struct afu *afu = cfg->afu;
	struct ctx_info *ctxi = NULL;
	struct mutex *mutex = &cfg->ctx_recovery_mutex;
	u64 ctxid = DECODE_CTXID(recover->context_id),
	    rctxid = recover->context_id;
	long reg;
	int lretry = 20; /* up to 2 seconds */
	int rc = 0;

	atomic_inc(&cfg->recovery_threads);
	up_read(&cfg->ioctl_rwsem);
	rc = mutex_lock_interruptible(mutex);
	down_read(&cfg->ioctl_rwsem);
	if (rc)
		goto out;
	rc = check_state(cfg);
	if (rc) {
		dev_err(dev, "%s: Failed state! rc=%d\n", __func__, rc);
		rc = -ENODEV;
		goto out;
	}

	dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
		__func__, recover->reason, rctxid);

retry:
	/* Ensure that this process is attached to the context */
	ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
	if (unlikely(!ctxi)) {
		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
		rc = -EINVAL;
		goto out;
	}

	if (ctxi->err_recovery_active) {
retry_recover:
		rc = recover_context(cfg, ctxi);
		if (unlikely(rc)) {
			dev_err(dev, "%s: Recovery failed for context %llu (rc=%d)\n",
				__func__, ctxid, rc);
			if ((rc == -ENODEV) &&
			    ((atomic_read(&cfg->recovery_threads) > 1) ||
			     (lretry--))) {
				dev_dbg(dev, "%s: Going to try again!\n",
					__func__);
				mutex_unlock(mutex);
				msleep(100);
				rc = mutex_lock_interruptible(mutex);
				if (rc)
					goto out;
				goto retry_recover;
			}

			goto out;
		}

		ctxi->err_recovery_active = false;
		recover->context_id = ctxi->ctxid;
		recover->adap_fd = ctxi->lfd;
		recover->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
		recover->hdr.return_flags |=
			DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
		goto out;
	}

	/* Test if in error state */
	reg = readq_be(&afu->ctrl_map->mbox_r);
	if (reg == -1) {
		dev_dbg(dev, "%s: MMIO fail, wait for recovery.\n", __func__);

		/*
		 * Before checking the state, put back the context obtained with
		 * get_context() as it is no longer needed and sleep for a short
		 * period of time (see prolog notes).
		 */
		put_context(ctxi);
		ctxi = NULL;
		ssleep(1);
		rc = check_state(cfg);
		if (unlikely(rc))
			goto out;
		goto retry;
	}

	dev_dbg(dev, "%s: MMIO working, no recovery required!\n", __func__);
out:
	if (likely(ctxi))
		put_context(ctxi);
	mutex_unlock(mutex);
	atomic_dec_if_positive(&cfg->recovery_threads);
	return rc;
}

/**
 * process_sense() - evaluates and processes sense data
 * @sdev:	SCSI device associated with LUN.
 * @verify:	Verify ioctl data structure.
 *
 * Return: 0 on success, -errno on failure
 */
static int process_sense(struct scsi_device *sdev,
			 struct dk_cxlflash_verify *verify)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	struct glun_info *gli = lli->parent;
	u64 prev_lba = gli->max_lba;
	struct scsi_sense_hdr sshdr = { 0 };
	int rc = 0;

	rc = scsi_normalize_sense((const u8 *)&verify->sense_data,
				  DK_CXLFLASH_VERIFY_SENSE_LEN, &sshdr);
	if (!rc) {
		dev_err(dev, "%s: Failed to normalize sense data!\n", __func__);
		rc = -EINVAL;
		goto out;
	}

	switch (sshdr.sense_key) {
	case NO_SENSE:
	case RECOVERED_ERROR:
		/* fall through */
	case NOT_READY:
		break;
	case UNIT_ATTENTION:
		switch (sshdr.asc) {
		case 0x29: /* Power on Reset or Device Reset */
			/* fall through */
		case 0x2A: /* Device settings/capacity changed */
			rc = read_cap16(sdev, lli);
			if (rc) {
				rc = -ENODEV;
				break;
			}
			if (prev_lba != gli->max_lba)
				dev_dbg(dev, "%s: Capacity changed old=%lld "
					"new=%lld\n", __func__, prev_lba,
					gli->max_lba);
			break;
		case 0x3F: /* Report LUNs changed, Rescan. */
			scsi_scan_host(cfg->host);
			break;
		default:
			rc = -EIO;
			break;
		}
		break;
	default:
		rc = -EIO;
		break;
	}
out:
	dev_dbg(dev, "%s: sense_key %x asc %x ascq %x rc %d\n", __func__,
		sshdr.sense_key, sshdr.asc, sshdr.ascq, rc);
	return rc;
}

/**
 * cxlflash_disk_verify() - verifies a LUN is the same and handle size changes
 * @sdev:	SCSI device associated with LUN.
 * @verify:	Verify ioctl data structure.
 *
 * Return: 0 on success, -errno on failure
 */
static int cxlflash_disk_verify(struct scsi_device *sdev,
				struct dk_cxlflash_verify *verify)
{
	int rc = 0;
	struct ctx_info *ctxi = NULL;
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	struct glun_info *gli = lli->parent;
	struct sisl_rht_entry *rhte = NULL;
	res_hndl_t rhndl = verify->rsrc_handle;
	u64 ctxid = DECODE_CTXID(verify->context_id),
	    rctxid = verify->context_id;
	u64 last_lba = 0;

	dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llX, hint=%016llX, "
		"flags=%016llX\n", __func__, ctxid, verify->rsrc_handle,
		verify->hint, verify->hdr.flags);

	ctxi = get_context(cfg, rctxid, lli, 0);
	if (unlikely(!ctxi)) {
		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
		rc = -EINVAL;
		goto out;
	}

	rhte = get_rhte(ctxi, rhndl, lli);
	if (unlikely(!rhte)) {
		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
			__func__, rhndl);
		rc = -EINVAL;
		goto out;
	}

	/*
	 * Look at the hint/sense to see if it requires us to redrive
	 * inquiry (i.e. the Unit attention is due to the WWN changing).
	 */
	if (verify->hint & DK_CXLFLASH_VERIFY_HINT_SENSE) {
		/* Can't hold mutex across process_sense/read_cap16,
		 * since we could have an intervening EEH event.
		 */
		ctxi->unavail = true;
		mutex_unlock(&ctxi->mutex);
		rc = process_sense(sdev, verify);
		if (unlikely(rc)) {
			dev_err(dev, "%s: Failed to validate sense data (%d)\n",
				__func__, rc);
			mutex_lock(&ctxi->mutex);
			ctxi->unavail = false;
			goto out;
		}
		mutex_lock(&ctxi->mutex);
		ctxi->unavail = false;
	}

	switch (gli->mode) {
	case MODE_PHYSICAL:
		last_lba = gli->max_lba;
		break;
	case MODE_VIRTUAL:
		/* Cast lxt_cnt to u64 for multiply to be treated as 64bit op */
		last_lba = ((u64)rhte->lxt_cnt * MC_CHUNK_SIZE * gli->blk_len);
		last_lba /= CXLFLASH_BLOCK_SIZE;
		last_lba--;
		break;
	default:
		WARN(1, "Unsupported LUN mode!");
	}

	verify->last_lba = last_lba;

out:
	if (likely(ctxi))
		put_context(ctxi);
	dev_dbg(dev, "%s: returning rc=%d llba=%llX\n",
		__func__, rc, verify->last_lba);
	return rc;
}

/**
 * decode_ioctl() - translates an encoded ioctl to an easily identifiable string
 * @cmd:	The ioctl command to decode.
 *
 * Return: A string identifying the decoded ioctl.
 */
static char *decode_ioctl(int cmd)
{
	switch (cmd) {
	case DK_CXLFLASH_ATTACH:
		return __stringify_1(DK_CXLFLASH_ATTACH);
	case DK_CXLFLASH_USER_DIRECT:
		return __stringify_1(DK_CXLFLASH_USER_DIRECT);
	case DK_CXLFLASH_USER_VIRTUAL:
		return __stringify_1(DK_CXLFLASH_USER_VIRTUAL);
	case DK_CXLFLASH_VLUN_RESIZE:
		return __stringify_1(DK_CXLFLASH_VLUN_RESIZE);
	case DK_CXLFLASH_RELEASE:
		return __stringify_1(DK_CXLFLASH_RELEASE);
	case DK_CXLFLASH_DETACH:
		return __stringify_1(DK_CXLFLASH_DETACH);
	case DK_CXLFLASH_VERIFY:
		return __stringify_1(DK_CXLFLASH_VERIFY);
	case DK_CXLFLASH_VLUN_CLONE:
		return __stringify_1(DK_CXLFLASH_VLUN_CLONE);
	case DK_CXLFLASH_RECOVER_AFU:
		return __stringify_1(DK_CXLFLASH_RECOVER_AFU);
	case DK_CXLFLASH_MANAGE_LUN:
		return __stringify_1(DK_CXLFLASH_MANAGE_LUN);
	}

	return "UNKNOWN";
}

/**
 * cxlflash_disk_direct_open() - opens a direct (physical) disk
 * @sdev:	SCSI device associated with LUN.
 * @arg:	UDirect ioctl data structure.
 *
 * On successful return, the user is informed of the resource handle
 * to be used to identify the direct lun and the size (in blocks) of
 * the direct lun in last LBA format.
 *
 * Return: 0 on success, -errno on failure
 */
static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct afu *afu = cfg->afu;
	struct llun_info *lli = sdev->hostdata;
	struct glun_info *gli = lli->parent;

	struct dk_cxlflash_udirect *pphys = (struct dk_cxlflash_udirect *)arg;

	u64 ctxid = DECODE_CTXID(pphys->context_id),
	    rctxid = pphys->context_id;
	u64 lun_size = 0;
	u64 last_lba = 0;
	u64 rsrc_handle = -1;
	u32 port = CHAN2PORT(sdev->channel);

	int rc = 0;

	struct ctx_info *ctxi = NULL;
	struct sisl_rht_entry *rhte = NULL;

	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);

	rc = cxlflash_lun_attach(gli, MODE_PHYSICAL, false);
	if (unlikely(rc)) {
		dev_dbg(dev, "%s: Failed to attach to LUN! (PHYSICAL)\n",
			__func__);
		goto out;
	}

	ctxi = get_context(cfg, rctxid, lli, 0);
	if (unlikely(!ctxi)) {
		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
		rc = -EINVAL;
		goto err1;
	}

	rhte = rhte_checkout(ctxi, lli);
	if (unlikely(!rhte)) {
		dev_dbg(dev, "%s: too many opens for this context\n", __func__);
		rc = -EMFILE;	/* too many opens  */
		goto err1;
	}

	rsrc_handle = (rhte - ctxi->rht_start);

	rht_format1(rhte, lli->lun_id[sdev->channel], ctxi->rht_perms, port);
	cxlflash_afu_sync(afu, ctxid, rsrc_handle, AFU_LW_SYNC);

	last_lba = gli->max_lba;
	pphys->hdr.return_flags = 0;
	pphys->last_lba = last_lba;
	pphys->rsrc_handle = rsrc_handle;

out:
	if (likely(ctxi))
		put_context(ctxi);
	dev_dbg(dev, "%s: returning handle 0x%llx rc=%d llba %lld\n",
		__func__, rsrc_handle, rc, last_lba);
	return rc;

err1:
	cxlflash_lun_detach(gli);
	goto out;
}

/**
 * ioctl_common() - common IOCTL handler for driver
 * @sdev:	SCSI device associated with LUN.
 * @cmd:	IOCTL command.
 *
 * Handles common fencing operations that are valid for multiple ioctls. Always
 * allow through ioctls that are cleanup oriented in nature, even when operating
 * in a failed/terminating state.
 *
 * Return: 0 on success, -errno on failure
 */
static int ioctl_common(struct scsi_device *sdev, int cmd)
{
	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct llun_info *lli = sdev->hostdata;
	int rc = 0;

	if (unlikely(!lli)) {
		dev_dbg(dev, "%s: Unknown LUN\n", __func__);
		rc = -EINVAL;
		goto out;
	}

	rc = check_state(cfg);
	if (unlikely(rc) && (cfg->state == STATE_FAILTERM)) {
		switch (cmd) {
		case DK_CXLFLASH_VLUN_RESIZE:
		case DK_CXLFLASH_RELEASE:
		case DK_CXLFLASH_DETACH:
			dev_dbg(dev, "%s: Command override! (%d)\n",
				__func__, rc);
			rc = 0;
			break;
		}
	}
out:
	return rc;
}

/**
 * cxlflash_ioctl() - IOCTL handler for driver
 * @sdev:	SCSI device associated with LUN.
 * @cmd:	IOCTL command.
 * @arg:	Userspace ioctl data structure.
 *
 * A read/write semaphore is used to implement a 'drain' of currently
 * running ioctls. The read semaphore is taken at the beginning of each
 * ioctl thread and released upon concluding execution. Additionally the
 * semaphore should be released and then reacquired in any ioctl execution
 * path which will wait for an event to occur that is outside the scope of
 * the ioctl (i.e. an adapter reset). To drain the ioctls currently running,
 * a thread simply needs to acquire the write semaphore.
 *
 * Return: 0 on success, -errno on failure
 */
int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
{
	typedef int (*sioctl) (struct scsi_device *, void *);

	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
	struct device *dev = &cfg->dev->dev;
	struct afu *afu = cfg->afu;
	struct dk_cxlflash_hdr *hdr;
	char buf[sizeof(union cxlflash_ioctls)];
	size_t size = 0;
	bool known_ioctl = false;
	int idx;
	int rc = 0;
	struct Scsi_Host *shost = sdev->host;
	sioctl do_ioctl = NULL;

	static const struct {
		size_t size;
		sioctl ioctl;
	} ioctl_tbl[] = {	/* NOTE: order matters here */
	{sizeof(struct dk_cxlflash_attach), (sioctl)cxlflash_disk_attach},
	{sizeof(struct dk_cxlflash_udirect), cxlflash_disk_direct_open},
	{sizeof(struct dk_cxlflash_release), (sioctl)cxlflash_disk_release},
	{sizeof(struct dk_cxlflash_detach), (sioctl)cxlflash_disk_detach},
	{sizeof(struct dk_cxlflash_verify), (sioctl)cxlflash_disk_verify},
	{sizeof(struct dk_cxlflash_recover_afu), (sioctl)cxlflash_afu_recover},
	{sizeof(struct dk_cxlflash_manage_lun), (sioctl)cxlflash_manage_lun},
	{sizeof(struct dk_cxlflash_uvirtual), cxlflash_disk_virtual_open},
	{sizeof(struct dk_cxlflash_resize), (sioctl)cxlflash_vlun_resize},
	{sizeof(struct dk_cxlflash_clone), (sioctl)cxlflash_disk_clone},
	};

	/* Hold read semaphore so we can drain if needed */
	down_read(&cfg->ioctl_rwsem);

	/* Restrict command set to physical support only for internal LUN */
	if (afu->internal_lun)
		switch (cmd) {
		case DK_CXLFLASH_RELEASE:
		case DK_CXLFLASH_USER_VIRTUAL:
		case DK_CXLFLASH_VLUN_RESIZE:
		case DK_CXLFLASH_VLUN_CLONE:
			dev_dbg(dev, "%s: %s not supported for lun_mode=%d\n",
				__func__, decode_ioctl(cmd), afu->internal_lun);
			rc = -EINVAL;
			goto cxlflash_ioctl_exit;
		}

	switch (cmd) {
	case DK_CXLFLASH_ATTACH:
	case DK_CXLFLASH_USER_DIRECT:
	case DK_CXLFLASH_RELEASE:
	case DK_CXLFLASH_DETACH:
	case DK_CXLFLASH_VERIFY:
	case DK_CXLFLASH_RECOVER_AFU:
	case DK_CXLFLASH_USER_VIRTUAL:
	case DK_CXLFLASH_VLUN_RESIZE:
	case DK_CXLFLASH_VLUN_CLONE:
		dev_dbg(dev, "%s: %s (%08X) on dev(%d/%d/%d/%llu)\n",
			__func__, decode_ioctl(cmd), cmd, shost->host_no,
			sdev->channel, sdev->id, sdev->lun);
		rc = ioctl_common(sdev, cmd);
		if (unlikely(rc))
			goto cxlflash_ioctl_exit;

		/* fall through */

	case DK_CXLFLASH_MANAGE_LUN:
		known_ioctl = true;
		idx = _IOC_NR(cmd) - _IOC_NR(DK_CXLFLASH_ATTACH);
		size = ioctl_tbl[idx].size;
		do_ioctl = ioctl_tbl[idx].ioctl;

		if (likely(do_ioctl))
			break;

		/* fall through */
	default:
		rc = -EINVAL;
		goto cxlflash_ioctl_exit;
	}

	if (unlikely(copy_from_user(&buf, arg, size))) {
		dev_err(dev, "%s: copy_from_user() fail! "
			"size=%lu cmd=%d (%s) arg=%p\n",
			__func__, size, cmd, decode_ioctl(cmd), arg);
		rc = -EFAULT;
		goto cxlflash_ioctl_exit;
	}

	hdr = (struct dk_cxlflash_hdr *)&buf;
	if (hdr->version != DK_CXLFLASH_VERSION_0) {
		dev_dbg(dev, "%s: Version %u not supported for %s\n",
			__func__, hdr->version, decode_ioctl(cmd));
		rc = -EINVAL;
		goto cxlflash_ioctl_exit;
	}

	if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->rsvd[2] || hdr->return_flags) {
		dev_dbg(dev, "%s: Reserved/rflags populated!\n", __func__);
		rc = -EINVAL;
		goto cxlflash_ioctl_exit;
	}

	rc = do_ioctl(sdev, (void *)&buf);
	if (likely(!rc))
		if (unlikely(copy_to_user(arg, &buf, size))) {
			dev_err(dev, "%s: copy_to_user() fail! "
				"size=%lu cmd=%d (%s) arg=%p\n",
				__func__, size, cmd, decode_ioctl(cmd), arg);
			rc = -EFAULT;
		}

	/* fall through to exit */

cxlflash_ioctl_exit:
	up_read(&cfg->ioctl_rwsem);
	if (unlikely(rc && known_ioctl))
		dev_err(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
			"returned rc %d\n", __func__,
			decode_ioctl(cmd), cmd, shost->host_no,
			sdev->channel, sdev->id, sdev->lun, rc);
	else
		dev_dbg(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) "
			"returned rc %d\n", __func__, decode_ioctl(cmd),
			cmd, shost->host_no, sdev->channel, sdev->id,
			sdev->lun, rc);
	return rc;
}