summaryrefslogtreecommitdiff
path: root/drivers/usb/host/xhci-mem.c
blob: 4e3abdd0ec3675fcdfe59b1367ff21f62812ac7a (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
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
/*
 * xHCI host controller driver
 *
 * Copyright (C) 2008 Intel Corp.
 *
 * Author: Sarah Sharp
 * Some code borrowed from the Linux EHCI driver.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
 * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software Foundation,
 * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#include <linux/usb.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/dmapool.h>
#include <linux/dma-mapping.h>

#include "xhci.h"
#include "xhci-trace.h"

/*
 * Allocates a generic ring segment from the ring pool, sets the dma address,
 * initializes the segment to zero, and sets the private next pointer to NULL.
 *
 * Section 4.11.1.1:
 * "All components of all Command and Transfer TRBs shall be initialized to '0'"
 */
static struct xhci_segment *xhci_segment_alloc(struct xhci_hcd *xhci,
					unsigned int cycle_state, gfp_t flags)
{
	struct xhci_segment *seg;
	dma_addr_t	dma;
	int		i;

	seg = kzalloc(sizeof *seg, flags);
	if (!seg)
		return NULL;

	seg->trbs = dma_pool_zalloc(xhci->segment_pool, flags, &dma);
	if (!seg->trbs) {
		kfree(seg);
		return NULL;
	}

	/* If the cycle state is 0, set the cycle bit to 1 for all the TRBs */
	if (cycle_state == 0) {
		for (i = 0; i < TRBS_PER_SEGMENT; i++)
			seg->trbs[i].link.control |= cpu_to_le32(TRB_CYCLE);
	}
	seg->dma = dma;
	seg->next = NULL;

	return seg;
}

static void xhci_segment_free(struct xhci_hcd *xhci, struct xhci_segment *seg)
{
	if (seg->trbs) {
		dma_pool_free(xhci->segment_pool, seg->trbs, seg->dma);
		seg->trbs = NULL;
	}
	kfree(seg);
}

static void xhci_free_segments_for_ring(struct xhci_hcd *xhci,
				struct xhci_segment *first)
{
	struct xhci_segment *seg;

	seg = first->next;
	while (seg != first) {
		struct xhci_segment *next = seg->next;
		xhci_segment_free(xhci, seg);
		seg = next;
	}
	xhci_segment_free(xhci, first);
}

/*
 * Make the prev segment point to the next segment.
 *
 * Change the last TRB in the prev segment to be a Link TRB which points to the
 * DMA address of the next segment.  The caller needs to set any Link TRB
 * related flags, such as End TRB, Toggle Cycle, and no snoop.
 */
static void xhci_link_segments(struct xhci_hcd *xhci, struct xhci_segment *prev,
		struct xhci_segment *next, enum xhci_ring_type type)
{
	u32 val;

	if (!prev || !next)
		return;
	prev->next = next;
	if (type != TYPE_EVENT) {
		prev->trbs[TRBS_PER_SEGMENT-1].link.segment_ptr =
			cpu_to_le64(next->dma);

		/* Set the last TRB in the segment to have a TRB type ID of Link TRB */
		val = le32_to_cpu(prev->trbs[TRBS_PER_SEGMENT-1].link.control);
		val &= ~TRB_TYPE_BITMASK;
		val |= TRB_TYPE(TRB_LINK);
		/* Always set the chain bit with 0.95 hardware */
		/* Set chain bit for isoc rings on AMD 0.96 host */
		if (xhci_link_trb_quirk(xhci) ||
				(type == TYPE_ISOC &&
				 (xhci->quirks & XHCI_AMD_0x96_HOST)))
			val |= TRB_CHAIN;
		prev->trbs[TRBS_PER_SEGMENT-1].link.control = cpu_to_le32(val);
	}
}

/*
 * Link the ring to the new segments.
 * Set Toggle Cycle for the new ring if needed.
 */
static void xhci_link_rings(struct xhci_hcd *xhci, struct xhci_ring *ring,
		struct xhci_segment *first, struct xhci_segment *last,
		unsigned int num_segs)
{
	struct xhci_segment *next;

	if (!ring || !first || !last)
		return;

	next = ring->enq_seg->next;
	xhci_link_segments(xhci, ring->enq_seg, first, ring->type);
	xhci_link_segments(xhci, last, next, ring->type);
	ring->num_segs += num_segs;
	ring->num_trbs_free += (TRBS_PER_SEGMENT - 1) * num_segs;

	if (ring->type != TYPE_EVENT && ring->enq_seg == ring->last_seg) {
		ring->last_seg->trbs[TRBS_PER_SEGMENT-1].link.control
			&= ~cpu_to_le32(LINK_TOGGLE);
		last->trbs[TRBS_PER_SEGMENT-1].link.control
			|= cpu_to_le32(LINK_TOGGLE);
		ring->last_seg = last;
	}
}

/*
 * We need a radix tree for mapping physical addresses of TRBs to which stream
 * ID they belong to.  We need to do this because the host controller won't tell
 * us which stream ring the TRB came from.  We could store the stream ID in an
 * event data TRB, but that doesn't help us for the cancellation case, since the
 * endpoint may stop before it reaches that event data TRB.
 *
 * The radix tree maps the upper portion of the TRB DMA address to a ring
 * segment that has the same upper portion of DMA addresses.  For example, say I
 * have segments of size 1KB, that are always 1KB aligned.  A segment may
 * start at 0x10c91000 and end at 0x10c913f0.  If I use the upper 10 bits, the
 * key to the stream ID is 0x43244.  I can use the DMA address of the TRB to
 * pass the radix tree a key to get the right stream ID:
 *
 *	0x10c90fff >> 10 = 0x43243
 *	0x10c912c0 >> 10 = 0x43244
 *	0x10c91400 >> 10 = 0x43245
 *
 * Obviously, only those TRBs with DMA addresses that are within the segment
 * will make the radix tree return the stream ID for that ring.
 *
 * Caveats for the radix tree:
 *
 * The radix tree uses an unsigned long as a key pair.  On 32-bit systems, an
 * unsigned long will be 32-bits; on a 64-bit system an unsigned long will be
 * 64-bits.  Since we only request 32-bit DMA addresses, we can use that as the
 * key on 32-bit or 64-bit systems (it would also be fine if we asked for 64-bit
 * PCI DMA addresses on a 64-bit system).  There might be a problem on 32-bit
 * extended systems (where the DMA address can be bigger than 32-bits),
 * if we allow the PCI dma mask to be bigger than 32-bits.  So don't do that.
 */
static int xhci_insert_segment_mapping(struct radix_tree_root *trb_address_map,
		struct xhci_ring *ring,
		struct xhci_segment *seg,
		gfp_t mem_flags)
{
	unsigned long key;
	int ret;

	key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
	/* Skip any segments that were already added. */
	if (radix_tree_lookup(trb_address_map, key))
		return 0;

	ret = radix_tree_maybe_preload(mem_flags);
	if (ret)
		return ret;
	ret = radix_tree_insert(trb_address_map,
			key, ring);
	radix_tree_preload_end();
	return ret;
}

static void xhci_remove_segment_mapping(struct radix_tree_root *trb_address_map,
		struct xhci_segment *seg)
{
	unsigned long key;

	key = (unsigned long)(seg->dma >> TRB_SEGMENT_SHIFT);
	if (radix_tree_lookup(trb_address_map, key))
		radix_tree_delete(trb_address_map, key);
}

static int xhci_update_stream_segment_mapping(
		struct radix_tree_root *trb_address_map,
		struct xhci_ring *ring,
		struct xhci_segment *first_seg,
		struct xhci_segment *last_seg,
		gfp_t mem_flags)
{
	struct xhci_segment *seg;
	struct xhci_segment *failed_seg;
	int ret;

	if (WARN_ON_ONCE(trb_address_map == NULL))
		return 0;

	seg = first_seg;
	do {
		ret = xhci_insert_segment_mapping(trb_address_map,
				ring, seg, mem_flags);
		if (ret)
			goto remove_streams;
		if (seg == last_seg)
			return 0;
		seg = seg->next;
	} while (seg != first_seg);

	return 0;

remove_streams:
	failed_seg = seg;
	seg = first_seg;
	do {
		xhci_remove_segment_mapping(trb_address_map, seg);
		if (seg == failed_seg)
			return ret;
		seg = seg->next;
	} while (seg != first_seg);

	return ret;
}

static void xhci_remove_stream_mapping(struct xhci_ring *ring)
{
	struct xhci_segment *seg;

	if (WARN_ON_ONCE(ring->trb_address_map == NULL))
		return;

	seg = ring->first_seg;
	do {
		xhci_remove_segment_mapping(ring->trb_address_map, seg);
		seg = seg->next;
	} while (seg != ring->first_seg);
}

static int xhci_update_stream_mapping(struct xhci_ring *ring, gfp_t mem_flags)
{
	return xhci_update_stream_segment_mapping(ring->trb_address_map, ring,
			ring->first_seg, ring->last_seg, mem_flags);
}

/* XXX: Do we need the hcd structure in all these functions? */
void xhci_ring_free(struct xhci_hcd *xhci, struct xhci_ring *ring)
{
	if (!ring)
		return;

	if (ring->first_seg) {
		if (ring->type == TYPE_STREAM)
			xhci_remove_stream_mapping(ring);
		xhci_free_segments_for_ring(xhci, ring->first_seg);
	}

	kfree(ring);
}

static void xhci_initialize_ring_info(struct xhci_ring *ring,
					unsigned int cycle_state)
{
	/* The ring is empty, so the enqueue pointer == dequeue pointer */
	ring->enqueue = ring->first_seg->trbs;
	ring->enq_seg = ring->first_seg;
	ring->dequeue = ring->enqueue;
	ring->deq_seg = ring->first_seg;
	/* The ring is initialized to 0. The producer must write 1 to the cycle
	 * bit to handover ownership of the TRB, so PCS = 1.  The consumer must
	 * compare CCS to the cycle bit to check ownership, so CCS = 1.
	 *
	 * New rings are initialized with cycle state equal to 1; if we are
	 * handling ring expansion, set the cycle state equal to the old ring.
	 */
	ring->cycle_state = cycle_state;
	/* Not necessary for new rings, but needed for re-initialized rings */
	ring->enq_updates = 0;
	ring->deq_updates = 0;

	/*
	 * Each segment has a link TRB, and leave an extra TRB for SW
	 * accounting purpose
	 */
	ring->num_trbs_free = ring->num_segs * (TRBS_PER_SEGMENT - 1) - 1;
}

/* Allocate segments and link them for a ring */
static int xhci_alloc_segments_for_ring(struct xhci_hcd *xhci,
		struct xhci_segment **first, struct xhci_segment **last,
		unsigned int num_segs, unsigned int cycle_state,
		enum xhci_ring_type type, gfp_t flags)
{
	struct xhci_segment *prev;

	prev = xhci_segment_alloc(xhci, cycle_state, flags);
	if (!prev)
		return -ENOMEM;
	num_segs--;

	*first = prev;
	while (num_segs > 0) {
		struct xhci_segment	*next;

		next = xhci_segment_alloc(xhci, cycle_state, flags);
		if (!next) {
			prev = *first;
			while (prev) {
				next = prev->next;
				xhci_segment_free(xhci, prev);
				prev = next;
			}
			return -ENOMEM;
		}
		xhci_link_segments(xhci, prev, next, type);

		prev = next;
		num_segs--;
	}
	xhci_link_segments(xhci, prev, *first, type);
	*last = prev;

	return 0;
}

/**
 * Create a new ring with zero or more segments.
 *
 * Link each segment together into a ring.
 * Set the end flag and the cycle toggle bit on the last segment.
 * See section 4.9.1 and figures 15 and 16.
 */
static struct xhci_ring *xhci_ring_alloc(struct xhci_hcd *xhci,
		unsigned int num_segs, unsigned int cycle_state,
		enum xhci_ring_type type, gfp_t flags)
{
	struct xhci_ring	*ring;
	int ret;

	ring = kzalloc(sizeof *(ring), flags);
	if (!ring)
		return NULL;

	ring->num_segs = num_segs;
	INIT_LIST_HEAD(&ring->td_list);
	ring->type = type;
	if (num_segs == 0)
		return ring;

	ret = xhci_alloc_segments_for_ring(xhci, &ring->first_seg,
			&ring->last_seg, num_segs, cycle_state, type, flags);
	if (ret)
		goto fail;

	/* Only event ring does not use link TRB */
	if (type != TYPE_EVENT) {
		/* See section 4.9.2.1 and 6.4.4.1 */
		ring->last_seg->trbs[TRBS_PER_SEGMENT - 1].link.control |=
			cpu_to_le32(LINK_TOGGLE);
	}
	xhci_initialize_ring_info(ring, cycle_state);
	return ring;

fail:
	kfree(ring);
	return NULL;
}

void xhci_free_or_cache_endpoint_ring(struct xhci_hcd *xhci,
		struct xhci_virt_device *virt_dev,
		unsigned int ep_index)
{
	int rings_cached;

	rings_cached = virt_dev->num_rings_cached;
	if (rings_cached < XHCI_MAX_RINGS_CACHED) {
		virt_dev->ring_cache[rings_cached] =
			virt_dev->eps[ep_index].ring;
		virt_dev->num_rings_cached++;
		xhci_dbg(xhci, "Cached old ring, "
				"%d ring%s cached\n",
				virt_dev->num_rings_cached,
				(virt_dev->num_rings_cached > 1) ? "s" : "");
	} else {
		xhci_ring_free(xhci, virt_dev->eps[ep_index].ring);
		xhci_dbg(xhci, "Ring cache full (%d rings), "
				"freeing ring\n",
				virt_dev->num_rings_cached);
	}
	virt_dev->eps[ep_index].ring = NULL;
}

/* Zero an endpoint ring (except for link TRBs) and move the enqueue and dequeue
 * pointers to the beginning of the ring.
 */
static void xhci_reinit_cached_ring(struct xhci_hcd *xhci,
			struct xhci_ring *ring, unsigned int cycle_state,
			enum xhci_ring_type type)
{
	struct xhci_segment	*seg = ring->first_seg;
	int i;

	do {
		memset(seg->trbs, 0,
				sizeof(union xhci_trb)*TRBS_PER_SEGMENT);
		if (cycle_state == 0) {
			for (i = 0; i < TRBS_PER_SEGMENT; i++)
				seg->trbs[i].link.control |=
					cpu_to_le32(TRB_CYCLE);
		}
		/* All endpoint rings have link TRBs */
		xhci_link_segments(xhci, seg, seg->next, type);
		seg = seg->next;
	} while (seg != ring->first_seg);
	ring->type = type;
	xhci_initialize_ring_info(ring, cycle_state);
	/* td list should be empty since all URBs have been cancelled,
	 * but just in case...
	 */
	INIT_LIST_HEAD(&ring->td_list);
}

/*
 * Expand an existing ring.
 * Look for a cached ring or allocate a new ring which has same segment numbers
 * and link the two rings.
 */
int xhci_ring_expansion(struct xhci_hcd *xhci, struct xhci_ring *ring,
				unsigned int num_trbs, gfp_t flags)
{
	struct xhci_segment	*first;
	struct xhci_segment	*last;
	unsigned int		num_segs;
	unsigned int		num_segs_needed;
	int			ret;

	num_segs_needed = (num_trbs + (TRBS_PER_SEGMENT - 1) - 1) /
				(TRBS_PER_SEGMENT - 1);

	/* Allocate number of segments we needed, or double the ring size */
	num_segs = ring->num_segs > num_segs_needed ?
			ring->num_segs : num_segs_needed;

	ret = xhci_alloc_segments_for_ring(xhci, &first, &last,
			num_segs, ring->cycle_state, ring->type, flags);
	if (ret)
		return -ENOMEM;

	if (ring->type == TYPE_STREAM)
		ret = xhci_update_stream_segment_mapping(ring->trb_address_map,
						ring, first, last, flags);
	if (ret) {
		struct xhci_segment *next;
		do {
			next = first->next;
			xhci_segment_free(xhci, first);
			if (first == last)
				break;
			first = next;
		} while (true);
		return ret;
	}

	xhci_link_rings(xhci, ring, first, last, num_segs);
	xhci_dbg_trace(xhci, trace_xhci_dbg_ring_expansion,
			"ring expansion succeed, now has %d segments",
			ring->num_segs);

	return 0;
}

#define CTX_SIZE(_hcc) (HCC_64BYTE_CONTEXT(_hcc) ? 64 : 32)

static struct xhci_container_ctx *xhci_alloc_container_ctx(struct xhci_hcd *xhci,
						    int type, gfp_t flags)
{
	struct xhci_container_ctx *ctx;

	if ((type != XHCI_CTX_TYPE_DEVICE) && (type != XHCI_CTX_TYPE_INPUT))
		return NULL;

	ctx = kzalloc(sizeof(*ctx), flags);
	if (!ctx)
		return NULL;

	ctx->type = type;
	ctx->size = HCC_64BYTE_CONTEXT(xhci->hcc_params) ? 2048 : 1024;
	if (type == XHCI_CTX_TYPE_INPUT)
		ctx->size += CTX_SIZE(xhci->hcc_params);

	ctx->bytes = dma_pool_zalloc(xhci->device_pool, flags, &ctx->dma);
	if (!ctx->bytes) {
		kfree(ctx);
		return NULL;
	}
	return ctx;
}

static void xhci_free_container_ctx(struct xhci_hcd *xhci,
			     struct xhci_container_ctx *ctx)
{
	if (!ctx)
		return;
	dma_pool_free(xhci->device_pool, ctx->bytes, ctx->dma);
	kfree(ctx);
}

struct xhci_input_control_ctx *xhci_get_input_control_ctx(
					      struct xhci_container_ctx *ctx)
{
	if (ctx->type != XHCI_CTX_TYPE_INPUT)
		return NULL;

	return (struct xhci_input_control_ctx *)ctx->bytes;
}

struct xhci_slot_ctx *xhci_get_slot_ctx(struct xhci_hcd *xhci,
					struct xhci_container_ctx *ctx)
{
	if (ctx->type == XHCI_CTX_TYPE_DEVICE)
		return (struct xhci_slot_ctx *)ctx->bytes;

	return (struct xhci_slot_ctx *)
		(ctx->bytes + CTX_SIZE(xhci->hcc_params));
}

struct xhci_ep_ctx *xhci_get_ep_ctx(struct xhci_hcd *xhci,
				    struct xhci_container_ctx *ctx,
				    unsigned int ep_index)
{
	/* increment ep index by offset of start of ep ctx array */
	ep_index++;
	if (ctx->type == XHCI_CTX_TYPE_INPUT)
		ep_index++;

	return (struct xhci_ep_ctx *)
		(ctx->bytes + (ep_index * CTX_SIZE(xhci->hcc_params)));
}


/***************** Streams structures manipulation *************************/

static void xhci_free_stream_ctx(struct xhci_hcd *xhci,
		unsigned int num_stream_ctxs,
		struct xhci_stream_ctx *stream_ctx, dma_addr_t dma)
{
	struct device *dev = xhci_to_hcd(xhci)->self.controller;
	size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs;

	if (size > MEDIUM_STREAM_ARRAY_SIZE)
		dma_free_coherent(dev, size,
				stream_ctx, dma);
	else if (size <= SMALL_STREAM_ARRAY_SIZE)
		return dma_pool_free(xhci->small_streams_pool,
				stream_ctx, dma);
	else
		return dma_pool_free(xhci->medium_streams_pool,
				stream_ctx, dma);
}

/*
 * The stream context array for each endpoint with bulk streams enabled can
 * vary in size, based on:
 *  - how many streams the endpoint supports,
 *  - the maximum primary stream array size the host controller supports,
 *  - and how many streams the device driver asks for.
 *
 * The stream context array must be a power of 2, and can be as small as
 * 64 bytes or as large as 1MB.
 */
static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci,
		unsigned int num_stream_ctxs, dma_addr_t *dma,
		gfp_t mem_flags)
{
	struct device *dev = xhci_to_hcd(xhci)->self.controller;
	size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs;

	if (size > MEDIUM_STREAM_ARRAY_SIZE)
		return dma_alloc_coherent(dev, size,
				dma, mem_flags);
	else if (size <= SMALL_STREAM_ARRAY_SIZE)
		return dma_pool_alloc(xhci->small_streams_pool,
				mem_flags, dma);
	else
		return dma_pool_alloc(xhci->medium_streams_pool,
				mem_flags, dma);
}

struct xhci_ring *xhci_dma_to_transfer_ring(
		struct xhci_virt_ep *ep,
		u64 address)
{
	if (ep->ep_state & EP_HAS_STREAMS)
		return radix_tree_lookup(&ep->stream_info->trb_address_map,
				address >> TRB_SEGMENT_SHIFT);
	return ep->ring;
}

struct xhci_ring *xhci_stream_id_to_ring(
		struct xhci_virt_device *dev,
		unsigned int ep_index,
		unsigned int stream_id)
{
	struct xhci_virt_ep *ep = &dev->eps[ep_index];

	if (stream_id == 0)
		return ep->ring;
	if (!ep->stream_info)
		return NULL;

	if (stream_id > ep->stream_info->num_streams)
		return NULL;
	return ep->stream_info->stream_rings[stream_id];
}

/*
 * Change an endpoint's internal structure so it supports stream IDs.  The
 * number of requested streams includes stream 0, which cannot be used by device
 * drivers.
 *
 * The number of stream contexts in the stream context array may be bigger than
 * the number of streams the driver wants to use.  This is because the number of
 * stream context array entries must be a power of two.
 */
struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci,
		unsigned int num_stream_ctxs,
		unsigned int num_streams, gfp_t mem_flags)
{
	struct xhci_stream_info *stream_info;
	u32 cur_stream;
	struct xhci_ring *cur_ring;
	u64 addr;
	int ret;

	xhci_dbg(xhci, "Allocating %u streams and %u "
			"stream context array entries.\n",
			num_streams, num_stream_ctxs);
	if (xhci->cmd_ring_reserved_trbs == MAX_RSVD_CMD_TRBS) {
		xhci_dbg(xhci, "Command ring has no reserved TRBs available\n");
		return NULL;
	}
	xhci->cmd_ring_reserved_trbs++;

	stream_info = kzalloc(sizeof(struct xhci_stream_info), mem_flags);
	if (!stream_info)
		goto cleanup_trbs;

	stream_info->num_streams = num_streams;
	stream_info->num_stream_ctxs = num_stream_ctxs;

	/* Initialize the array of virtual pointers to stream rings. */
	stream_info->stream_rings = kzalloc(
			sizeof(struct xhci_ring *)*num_streams,
			mem_flags);
	if (!stream_info->stream_rings)
		goto cleanup_info;

	/* Initialize the array of DMA addresses for stream rings for the HW. */
	stream_info->stream_ctx_array = xhci_alloc_stream_ctx(xhci,
			num_stream_ctxs, &stream_info->ctx_array_dma,
			mem_flags);
	if (!stream_info->stream_ctx_array)
		goto cleanup_ctx;
	memset(stream_info->stream_ctx_array, 0,
			sizeof(struct xhci_stream_ctx)*num_stream_ctxs);

	/* Allocate everything needed to free the stream rings later */
	stream_info->free_streams_command =
		xhci_alloc_command(xhci, true, true, mem_flags);
	if (!stream_info->free_streams_command)
		goto cleanup_ctx;

	INIT_RADIX_TREE(&stream_info->trb_address_map, GFP_ATOMIC);

	/* Allocate rings for all the streams that the driver will use,
	 * and add their segment DMA addresses to the radix tree.
	 * Stream 0 is reserved.
	 */
	for (cur_stream = 1; cur_stream < num_streams; cur_stream++) {
		stream_info->stream_rings[cur_stream] =
			xhci_ring_alloc(xhci, 2, 1, TYPE_STREAM, mem_flags);
		cur_ring = stream_info->stream_rings[cur_stream];
		if (!cur_ring)
			goto cleanup_rings;
		cur_ring->stream_id = cur_stream;
		cur_ring->trb_address_map = &stream_info->trb_address_map;
		/* Set deq ptr, cycle bit, and stream context type */
		addr = cur_ring->first_seg->dma |
			SCT_FOR_CTX(SCT_PRI_TR) |
			cur_ring->cycle_state;
		stream_info->stream_ctx_array[cur_stream].stream_ring =
			cpu_to_le64(addr);
		xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n",
				cur_stream, (unsigned long long) addr);

		ret = xhci_update_stream_mapping(cur_ring, mem_flags);
		if (ret) {
			xhci_ring_free(xhci, cur_ring);
			stream_info->stream_rings[cur_stream] = NULL;
			goto cleanup_rings;
		}
	}
	/* Leave the other unused stream ring pointers in the stream context
	 * array initialized to zero.  This will cause the xHC to give us an
	 * error if the device asks for a stream ID we don't have setup (if it
	 * was any other way, the host controller would assume the ring is
	 * "empty" and wait forever for data to be queued to that stream ID).
	 */

	return stream_info;

cleanup_rings:
	for (cur_stream = 1; cur_stream < num_streams; cur_stream++) {
		cur_ring = stream_info->stream_rings[cur_stream];
		if (cur_ring) {
			xhci_ring_free(xhci, cur_ring);
			stream_info->stream_rings[cur_stream] = NULL;
		}
	}
	xhci_free_command(xhci, stream_info->free_streams_command);
cleanup_ctx:
	kfree(stream_info->stream_rings);
cleanup_info:
	kfree(stream_info);
cleanup_trbs:
	xhci->cmd_ring_reserved_trbs--;
	return NULL;
}
/*
 * Sets the MaxPStreams field and the Linear Stream Array field.
 * Sets the dequeue pointer to the stream context array.
 */
void xhci_setup_streams_ep_input_ctx(struct xhci_hcd *xhci,
		struct xhci_ep_ctx *ep_ctx,
		struct xhci_stream_info *stream_info)
{
	u32 max_primary_streams;
	/* MaxPStreams is the number of stream context array entries, not the
	 * number we're actually using.  Must be in 2^(MaxPstreams + 1) format.
	 * fls(0) = 0, fls(0x1) = 1, fls(0x10) = 2, fls(0x100) = 3, etc.
	 */
	max_primary_streams = fls(stream_info->num_stream_ctxs) - 2;
	xhci_dbg_trace(xhci,  trace_xhci_dbg_context_change,
			"Setting number of stream ctx array entries to %u",
			1 << (max_primary_streams + 1));
	ep_ctx->ep_info &= cpu_to_le32(~EP_MAXPSTREAMS_MASK);
	ep_ctx->ep_info |= cpu_to_le32(EP_MAXPSTREAMS(max_primary_streams)
				       | EP_HAS_LSA);
	ep_ctx->deq  = cpu_to_le64(stream_info->ctx_array_dma);
}

/*
 * Sets the MaxPStreams field and the Linear Stream Array field to 0.
 * Reinstalls the "normal" endpoint ring (at its previous dequeue mark,
 * not at the beginning of the ring).
 */
void xhci_setup_no_streams_ep_input_ctx(struct xhci_ep_ctx *ep_ctx,
		struct xhci_virt_ep *ep)
{
	dma_addr_t addr;
	ep_ctx->ep_info &= cpu_to_le32(~(EP_MAXPSTREAMS_MASK | EP_HAS_LSA));
	addr = xhci_trb_virt_to_dma(ep->ring->deq_seg, ep->ring->dequeue);
	ep_ctx->deq  = cpu_to_le64(addr | ep->ring->cycle_state);
}

/* Frees all stream contexts associated with the endpoint,
 *
 * Caller should fix the endpoint context streams fields.
 */
void xhci_free_stream_info(struct xhci_hcd *xhci,
		struct xhci_stream_info *stream_info)
{
	int cur_stream;
	struct xhci_ring *cur_ring;

	if (!stream_info)
		return;

	for (cur_stream = 1; cur_stream < stream_info->num_streams;
			cur_stream++) {
		cur_ring = stream_info->stream_rings[cur_stream];
		if (cur_ring) {
			xhci_ring_free(xhci, cur_ring);
			stream_info->stream_rings[cur_stream] = NULL;
		}
	}
	xhci_free_command(xhci, stream_info->free_streams_command);
	xhci->cmd_ring_reserved_trbs--;
	if (stream_info->stream_ctx_array)
		xhci_free_stream_ctx(xhci,
				stream_info->num_stream_ctxs,
				stream_info->stream_ctx_array,
				stream_info->ctx_array_dma);

	kfree(stream_info->stream_rings);
	kfree(stream_info);
}


/***************** Device context manipulation *************************/

static void xhci_init_endpoint_timer(struct xhci_hcd *xhci,
		struct xhci_virt_ep *ep)
{
	setup_timer(&ep->stop_cmd_timer, xhci_stop_endpoint_command_watchdog,
		    (unsigned long)ep);
	ep->xhci = xhci;
}

static void xhci_free_tt_info(struct xhci_hcd *xhci,
		struct xhci_virt_device *virt_dev,
		int slot_id)
{
	struct list_head *tt_list_head;
	struct xhci_tt_bw_info *tt_info, *next;
	bool slot_found = false;

	/* If the device never made it past the Set Address stage,
	 * it may not have the real_port set correctly.
	 */
	if (virt_dev->real_port == 0 ||
			virt_dev->real_port > HCS_MAX_PORTS(xhci->hcs_params1)) {
		xhci_dbg(xhci, "Bad real port.\n");
		return;
	}

	tt_list_head = &(xhci->rh_bw[virt_dev->real_port - 1].tts);
	list_for_each_entry_safe(tt_info, next, tt_list_head, tt_list) {
		/* Multi-TT hubs will have more than one entry */
		if (tt_info->slot_id == slot_id) {
			slot_found = true;
			list_del(&tt_info->tt_list);
			kfree(tt_info);
		} else if (slot_found) {
			break;
		}
	}
}

int xhci_alloc_tt_info(struct xhci_hcd *xhci,
		struct xhci_virt_device *virt_dev,
		struct usb_device *hdev,
		struct usb_tt *tt, gfp_t mem_flags)
{
	struct xhci_tt_bw_info		*tt_info;
	unsigned int			num_ports;
	int				i, j;

	if (!tt->multi)
		num_ports = 1;
	else
		num_ports = hdev->maxchild;

	for (i = 0; i < num_ports; i++, tt_info++) {
		struct xhci_interval_bw_table *bw_table;

		tt_info = kzalloc(sizeof(*tt_info), mem_flags);
		if (!tt_info)
			goto free_tts;
		INIT_LIST_HEAD(&tt_info->tt_list);
		list_add(&tt_info->tt_list,
				&xhci->rh_bw[virt_dev->real_port - 1].tts);
		tt_info->slot_id = virt_dev->udev->slot_id;
		if (tt->multi)
			tt_info->ttport = i+1;
		bw_table = &tt_info->bw_table;
		for (j = 0; j < XHCI_MAX_INTERVAL; j++)
			INIT_LIST_HEAD(&bw_table->interval_bw[j].endpoints);
	}
	return 0;

free_tts:
	xhci_free_tt_info(xhci, virt_dev, virt_dev->udev->slot_id);
	return -ENOMEM;
}


/* All the xhci_tds in the ring's TD list should be freed at this point.
 * Should be called with xhci->lock held if there is any chance the TT lists
 * will be manipulated by the configure endpoint, allocate device, or update
 * hub functions while this function is removing the TT entries from the list.
 */
void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
{
	struct xhci_virt_device *dev;
	int i;
	int old_active_eps = 0;

	/* Slot ID 0 is reserved */
	if (slot_id == 0 || !xhci->devs[slot_id])
		return;

	dev = xhci->devs[slot_id];
	xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
	if (!dev)
		return;

	if (dev->tt_info)
		old_active_eps = dev->tt_info->active_eps;

	for (i = 0; i < 31; ++i) {
		if (dev->eps[i].ring)
			xhci_ring_free(xhci, dev->eps[i].ring);
		if (dev->eps[i].stream_info)
			xhci_free_stream_info(xhci,
					dev->eps[i].stream_info);
		/* Endpoints on the TT/root port lists should have been removed
		 * when usb_disable_device() was called for the device.
		 * We can't drop them anyway, because the udev might have gone
		 * away by this point, and we can't tell what speed it was.
		 */
		if (!list_empty(&dev->eps[i].bw_endpoint_list))
			xhci_warn(xhci, "Slot %u endpoint %u "
					"not removed from BW list!\n",
					slot_id, i);
	}
	/* If this is a hub, free the TT(s) from the TT list */
	xhci_free_tt_info(xhci, dev, slot_id);
	/* If necessary, update the number of active TTs on this root port */
	xhci_update_tt_active_eps(xhci, dev, old_active_eps);

	if (dev->ring_cache) {
		for (i = 0; i < dev->num_rings_cached; i++)
			xhci_ring_free(xhci, dev->ring_cache[i]);
		kfree(dev->ring_cache);
	}

	if (dev->in_ctx)
		xhci_free_container_ctx(xhci, dev->in_ctx);
	if (dev->out_ctx)
		xhci_free_container_ctx(xhci, dev->out_ctx);

	kfree(xhci->devs[slot_id]);
	xhci->devs[slot_id] = NULL;
}

int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
		struct usb_device *udev, gfp_t flags)
{
	struct xhci_virt_device *dev;
	int i;

	/* Slot ID 0 is reserved */
	if (slot_id == 0 || xhci->devs[slot_id]) {
		xhci_warn(xhci, "Bad Slot ID %d\n", slot_id);
		return 0;
	}

	xhci->devs[slot_id] = kzalloc(sizeof(*xhci->devs[slot_id]), flags);
	if (!xhci->devs[slot_id])
		return 0;
	dev = xhci->devs[slot_id];

	/* Allocate the (output) device context that will be used in the HC. */
	dev->out_ctx = xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_DEVICE, flags);
	if (!dev->out_ctx)
		goto fail;

	xhci_dbg(xhci, "Slot %d output ctx = 0x%llx (dma)\n", slot_id,
			(unsigned long long)dev->out_ctx->dma);

	/* Allocate the (input) device context for address device command */
	dev->in_ctx = xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_INPUT, flags);
	if (!dev->in_ctx)
		goto fail;

	xhci_dbg(xhci, "Slot %d input ctx = 0x%llx (dma)\n", slot_id,
			(unsigned long long)dev->in_ctx->dma);

	/* Initialize the cancellation list and watchdog timers for each ep */
	for (i = 0; i < 31; i++) {
		xhci_init_endpoint_timer(xhci, &dev->eps[i]);
		INIT_LIST_HEAD(&dev->eps[i].cancelled_td_list);
		INIT_LIST_HEAD(&dev->eps[i].bw_endpoint_list);
	}

	/* Allocate endpoint 0 ring */
	dev->eps[0].ring = xhci_ring_alloc(xhci, 2, 1, TYPE_CTRL, flags);
	if (!dev->eps[0].ring)
		goto fail;

	/* Allocate pointers to the ring cache */
	dev->ring_cache = kzalloc(
			sizeof(struct xhci_ring *)*XHCI_MAX_RINGS_CACHED,
			flags);
	if (!dev->ring_cache)
		goto fail;
	dev->num_rings_cached = 0;

	init_completion(&dev->cmd_completion);
	dev->udev = udev;

	/* Point to output device context in dcbaa. */
	xhci->dcbaa->dev_context_ptrs[slot_id] = cpu_to_le64(dev->out_ctx->dma);
	xhci_dbg(xhci, "Set slot id %d dcbaa entry %p to 0x%llx\n",
		 slot_id,
		 &xhci->dcbaa->dev_context_ptrs[slot_id],
		 le64_to_cpu(xhci->dcbaa->dev_context_ptrs[slot_id]));

	return 1;
fail:
	xhci_free_virt_device(xhci, slot_id);
	return 0;
}

void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci,
		struct usb_device *udev)
{
	struct xhci_virt_device *virt_dev;
	struct xhci_ep_ctx	*ep0_ctx;
	struct xhci_ring	*ep_ring;

	virt_dev = xhci->devs[udev->slot_id];
	ep0_ctx = xhci_get_ep_ctx(xhci, virt_dev->in_ctx, 0);
	ep_ring = virt_dev->eps[0].ring;
	/*
	 * FIXME we don't keep track of the dequeue pointer very well after a
	 * Set TR dequeue pointer, so we're setting the dequeue pointer of the
	 * host to our enqueue pointer.  This should only be called after a
	 * configured device has reset, so all control transfers should have
	 * been completed or cancelled before the reset.
	 */
	ep0_ctx->deq = cpu_to_le64(xhci_trb_virt_to_dma(ep_ring->enq_seg,
							ep_ring->enqueue)
				   | ep_ring->cycle_state);
}

/*
 * The xHCI roothub may have ports of differing speeds in any order in the port
 * status registers.  xhci->port_array provides an array of the port speed for
 * each offset into the port status registers.
 *
 * The xHCI hardware wants to know the roothub port number that the USB device
 * is attached to (or the roothub port its ancestor hub is attached to).  All we
 * know is the index of that port under either the USB 2.0 or the USB 3.0
 * roothub, but that doesn't give us the real index into the HW port status
 * registers. Call xhci_find_raw_port_number() to get real index.
 */
static u32 xhci_find_real_port_number(struct xhci_hcd *xhci,
		struct usb_device *udev)
{
	struct usb_device *top_dev;
	struct usb_hcd *hcd;

	if (udev->speed >= USB_SPEED_SUPER)
		hcd = xhci->shared_hcd;
	else
		hcd = xhci->main_hcd;

	for (top_dev = udev; top_dev->parent && top_dev->parent->parent;
			top_dev = top_dev->parent)
		/* Found device below root hub */;

	return	xhci_find_raw_port_number(hcd, top_dev->portnum);
}

/* Setup an xHCI virtual device for a Set Address command */
int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *udev)
{
	struct xhci_virt_device *dev;
	struct xhci_ep_ctx	*ep0_ctx;
	struct xhci_slot_ctx    *slot_ctx;
	u32			port_num;
	u32			max_packets;
	struct usb_device *top_dev;

	dev = xhci->devs[udev->slot_id];
	/* Slot ID 0 is reserved */
	if (udev->slot_id == 0 || !dev) {
		xhci_warn(xhci, "Slot ID %d is not assigned to this device\n",
				udev->slot_id);
		return -EINVAL;
	}
	ep0_ctx = xhci_get_ep_ctx(xhci, dev->in_ctx, 0);
	slot_ctx = xhci_get_slot_ctx(xhci, dev->in_ctx);

	/* 3) Only the control endpoint is valid - one endpoint context */
	slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | udev->route);
	switch (udev->speed) {
	case USB_SPEED_SUPER_PLUS:
		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_SSP);
		max_packets = MAX_PACKET(512);
		break;
	case USB_SPEED_SUPER:
		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_SS);
		max_packets = MAX_PACKET(512);
		break;
	case USB_SPEED_HIGH:
		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_HS);
		max_packets = MAX_PACKET(64);
		break;
	/* USB core guesses at a 64-byte max packet first for FS devices */
	case USB_SPEED_FULL:
		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_FS);
		max_packets = MAX_PACKET(64);
		break;
	case USB_SPEED_LOW:
		slot_ctx->dev_info |= cpu_to_le32(SLOT_SPEED_LS);
		max_packets = MAX_PACKET(8);
		break;
	case USB_SPEED_WIRELESS:
		xhci_dbg(xhci, "FIXME xHCI doesn't support wireless speeds\n");
		return -EINVAL;
		break;
	default:
		/* Speed was set earlier, this shouldn't happen. */
		return -EINVAL;
	}
	/* Find the root hub port this device is under */
	port_num = xhci_find_real_port_number(xhci, udev);
	if (!port_num)
		return -EINVAL;
	slot_ctx->dev_info2 |= cpu_to_le32(ROOT_HUB_PORT(port_num));
	/* Set the port number in the virtual_device to the faked port number */
	for (top_dev = udev; top_dev->parent && top_dev->parent->parent;
			top_dev = top_dev->parent)
		/* Found device below root hub */;
	dev->fake_port = top_dev->portnum;
	dev->real_port = port_num;
	xhci_dbg(xhci, "Set root hub portnum to %d\n", port_num);
	xhci_dbg(xhci, "Set fake root hub portnum to %d\n", dev->fake_port);

	/* Find the right bandwidth table that this device will be a part of.
	 * If this is a full speed device attached directly to a root port (or a
	 * decendent of one), it counts as a primary bandwidth domain, not a
	 * secondary bandwidth domain under a TT.  An xhci_tt_info structure
	 * will never be created for the HS root hub.
	 */
	if (!udev->tt || !udev->tt->hub->parent) {
		dev->bw_table = &xhci->rh_bw[port_num - 1].bw_table;
	} else {
		struct xhci_root_port_bw_info *rh_bw;
		struct xhci_tt_bw_info *tt_bw;

		rh_bw = &xhci->rh_bw[port_num - 1];
		/* Find the right TT. */
		list_for_each_entry(tt_bw, &rh_bw->tts, tt_list) {
			if (tt_bw->slot_id != udev->tt->hub->slot_id)
				continue;

			if (!dev->udev->tt->multi ||
					(udev->tt->multi &&
					 tt_bw->ttport == dev->udev->ttport)) {
				dev->bw_table = &tt_bw->bw_table;
				dev->tt_info = tt_bw;
				break;
			}
		}
		if (!dev->tt_info)
			xhci_warn(xhci, "WARN: Didn't find a matching TT\n");
	}

	/* Is this a LS/FS device under an external HS hub? */
	if (udev->tt && udev->tt->hub->parent) {
		slot_ctx->tt_info = cpu_to_le32(udev->tt->hub->slot_id |
						(udev->ttport << 8));
		if (udev->tt->multi)
			slot_ctx->dev_info |= cpu_to_le32(DEV_MTT);
	}
	xhci_dbg(xhci, "udev->tt = %p\n", udev->tt);
	xhci_dbg(xhci, "udev->ttport = 0x%x\n", udev->ttport);

	/* Step 4 - ring already allocated */
	/* Step 5 */
	ep0_ctx->ep_info2 = cpu_to_le32(EP_TYPE(CTRL_EP));

	/* EP 0 can handle "burst" sizes of 1, so Max Burst Size field is 0 */
	ep0_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(0) | ERROR_COUNT(3) |
					 max_packets);

	ep0_ctx->deq = cpu_to_le64(dev->eps[0].ring->first_seg->dma |
				   dev->eps[0].ring->cycle_state);

	/* Steps 7 and 8 were done in xhci_alloc_virt_device() */

	return 0;
}

/*
 * Convert interval expressed as 2^(bInterval - 1) == interval into
 * straight exponent value 2^n == interval.
 *
 */
static unsigned int xhci_parse_exponent_interval(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	unsigned int interval;

	interval = clamp_val(ep->desc.bInterval, 1, 16) - 1;
	if (interval != ep->desc.bInterval - 1)
		dev_warn(&udev->dev,
			 "ep %#x - rounding interval to %d %sframes\n",
			 ep->desc.bEndpointAddress,
			 1 << interval,
			 udev->speed == USB_SPEED_FULL ? "" : "micro");

	if (udev->speed == USB_SPEED_FULL) {
		/*
		 * Full speed isoc endpoints specify interval in frames,
		 * not microframes. We are using microframes everywhere,
		 * so adjust accordingly.
		 */
		interval += 3;	/* 1 frame = 2^3 uframes */
	}

	return interval;
}

/*
 * Convert bInterval expressed in microframes (in 1-255 range) to exponent of
 * microframes, rounded down to nearest power of 2.
 */
static unsigned int xhci_microframes_to_exponent(struct usb_device *udev,
		struct usb_host_endpoint *ep, unsigned int desc_interval,
		unsigned int min_exponent, unsigned int max_exponent)
{
	unsigned int interval;

	interval = fls(desc_interval) - 1;
	interval = clamp_val(interval, min_exponent, max_exponent);
	if ((1 << interval) != desc_interval)
		dev_dbg(&udev->dev,
			 "ep %#x - rounding interval to %d microframes, ep desc says %d microframes\n",
			 ep->desc.bEndpointAddress,
			 1 << interval,
			 desc_interval);

	return interval;
}

static unsigned int xhci_parse_microframe_interval(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	if (ep->desc.bInterval == 0)
		return 0;
	return xhci_microframes_to_exponent(udev, ep,
			ep->desc.bInterval, 0, 15);
}


static unsigned int xhci_parse_frame_interval(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	return xhci_microframes_to_exponent(udev, ep,
			ep->desc.bInterval * 8, 3, 10);
}

/* Return the polling or NAK interval.
 *
 * The polling interval is expressed in "microframes".  If xHCI's Interval field
 * is set to N, it will service the endpoint every 2^(Interval)*125us.
 *
 * The NAK interval is one NAK per 1 to 255 microframes, or no NAKs if interval
 * is set to 0.
 */
static unsigned int xhci_get_endpoint_interval(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	unsigned int interval = 0;

	switch (udev->speed) {
	case USB_SPEED_HIGH:
		/* Max NAK rate */
		if (usb_endpoint_xfer_control(&ep->desc) ||
		    usb_endpoint_xfer_bulk(&ep->desc)) {
			interval = xhci_parse_microframe_interval(udev, ep);
			break;
		}
		/* Fall through - SS and HS isoc/int have same decoding */

	case USB_SPEED_SUPER_PLUS:
	case USB_SPEED_SUPER:
		if (usb_endpoint_xfer_int(&ep->desc) ||
		    usb_endpoint_xfer_isoc(&ep->desc)) {
			interval = xhci_parse_exponent_interval(udev, ep);
		}
		break;

	case USB_SPEED_FULL:
		if (usb_endpoint_xfer_isoc(&ep->desc)) {
			interval = xhci_parse_exponent_interval(udev, ep);
			break;
		}
		/*
		 * Fall through for interrupt endpoint interval decoding
		 * since it uses the same rules as low speed interrupt
		 * endpoints.
		 */

	case USB_SPEED_LOW:
		if (usb_endpoint_xfer_int(&ep->desc) ||
		    usb_endpoint_xfer_isoc(&ep->desc)) {

			interval = xhci_parse_frame_interval(udev, ep);
		}
		break;

	default:
		BUG();
	}
	return interval;
}

/* The "Mult" field in the endpoint context is only set for SuperSpeed isoc eps.
 * High speed endpoint descriptors can define "the number of additional
 * transaction opportunities per microframe", but that goes in the Max Burst
 * endpoint context field.
 */
static u32 xhci_get_endpoint_mult(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	if (udev->speed < USB_SPEED_SUPER ||
			!usb_endpoint_xfer_isoc(&ep->desc))
		return 0;
	return ep->ss_ep_comp.bmAttributes;
}

static u32 xhci_get_endpoint_max_burst(struct usb_device *udev,
				       struct usb_host_endpoint *ep)
{
	/* Super speed and Plus have max burst in ep companion desc */
	if (udev->speed >= USB_SPEED_SUPER)
		return ep->ss_ep_comp.bMaxBurst;

	if (udev->speed == USB_SPEED_HIGH &&
	    (usb_endpoint_xfer_isoc(&ep->desc) ||
	     usb_endpoint_xfer_int(&ep->desc)))
		return (usb_endpoint_maxp(&ep->desc) & 0x1800) >> 11;

	return 0;
}

static u32 xhci_get_endpoint_type(struct usb_host_endpoint *ep)
{
	int in;

	in = usb_endpoint_dir_in(&ep->desc);

	if (usb_endpoint_xfer_control(&ep->desc))
		return CTRL_EP;
	if (usb_endpoint_xfer_bulk(&ep->desc))
		return in ? BULK_IN_EP : BULK_OUT_EP;
	if (usb_endpoint_xfer_isoc(&ep->desc))
		return in ? ISOC_IN_EP : ISOC_OUT_EP;
	if (usb_endpoint_xfer_int(&ep->desc))
		return in ? INT_IN_EP : INT_OUT_EP;
	return 0;
}

/* Return the maximum endpoint service interval time (ESIT) payload.
 * Basically, this is the maxpacket size, multiplied by the burst size
 * and mult size.
 */
static u32 xhci_get_max_esit_payload(struct usb_device *udev,
		struct usb_host_endpoint *ep)
{
	int max_burst;
	int max_packet;

	/* Only applies for interrupt or isochronous endpoints */
	if (usb_endpoint_xfer_control(&ep->desc) ||
			usb_endpoint_xfer_bulk(&ep->desc))
		return 0;

	if (udev->speed >= USB_SPEED_SUPER)
		return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval);

	max_packet = GET_MAX_PACKET(usb_endpoint_maxp(&ep->desc));
	max_burst = (usb_endpoint_maxp(&ep->desc) & 0x1800) >> 11;
	/* A 0 in max burst means 1 transfer per ESIT */
	return max_packet * (max_burst + 1);
}

/* Set up an endpoint with one ring segment.  Do not allocate stream rings.
 * Drivers will have to call usb_alloc_streams() to do that.
 */
int xhci_endpoint_init(struct xhci_hcd *xhci,
		struct xhci_virt_device *virt_dev,
		struct usb_device *udev,
		struct usb_host_endpoint *ep,
		gfp_t mem_flags)
{
	unsigned int ep_index;
	struct xhci_ep_ctx *ep_ctx;
	struct xhci_ring *ep_ring;
	unsigned int max_packet;
	enum xhci_ring_type ring_type;
	u32 max_esit_payload;
	u32 endpoint_type;
	unsigned int max_burst;
	unsigned int interval;
	unsigned int mult;
	unsigned int avg_trb_len;
	unsigned int err_count = 0;

	ep_index = xhci_get_endpoint_index(&ep->desc);
	ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->in_ctx, ep_index);

	endpoint_type = xhci_get_endpoint_type(ep);
	if (!endpoint_type)
		return -EINVAL;

	ring_type = usb_endpoint_type(&ep->desc);
	/* Set up the endpoint ring */
	virt_dev->eps[ep_index].new_ring =
		xhci_ring_alloc(xhci, 2, 1, ring_type, mem_flags);
	if (!virt_dev->eps[ep_index].new_ring) {
		/* Attempt to use the ring cache */
		if (virt_dev->num_rings_cached == 0)
			return -ENOMEM;
		virt_dev->num_rings_cached--;
		virt_dev->eps[ep_index].new_ring =
			virt_dev->ring_cache[virt_dev->num_rings_cached];
		virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL;
		xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring,
					1, ring_type);
	}
	virt_dev->eps[ep_index].skip = false;
	ep_ring = virt_dev->eps[ep_index].new_ring;

	/*
	 * Get values to fill the endpoint context, mostly from ep descriptor.
	 * The average TRB buffer lengt for bulk endpoints is unclear as we
	 * have no clue on scatter gather list entry size. For Isoc and Int,
	 * set it to max available. See xHCI 1.1 spec 4.14.1.1 for details.
	 */
	max_esit_payload = xhci_get_max_esit_payload(udev, ep);
	interval = xhci_get_endpoint_interval(udev, ep);
	mult = xhci_get_endpoint_mult(udev, ep);
	max_packet = GET_MAX_PACKET(usb_endpoint_maxp(&ep->desc));
	max_burst = xhci_get_endpoint_max_burst(udev, ep);
	avg_trb_len = max_esit_payload;

	/* FIXME dig Mult and streams info out of ep companion desc */

	/* Allow 3 retries for everything but isoc, set CErr = 3 */
	if (!usb_endpoint_xfer_isoc(&ep->desc))
		err_count = 3;
	/* Some devices get this wrong */
	if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH)
		max_packet = 512;
	/* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */
	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
		avg_trb_len = 8;

	/* Fill the endpoint context */
	ep_ctx->ep_info = cpu_to_le32(EP_INTERVAL(interval) |
				      EP_MULT(mult));
	ep_ctx->ep_info2 = cpu_to_le32(EP_TYPE(endpoint_type) |
				       MAX_PACKET(max_packet) |
				       MAX_BURST(max_burst) |
				       ERROR_COUNT(err_count));
	ep_ctx->deq = cpu_to_le64(ep_ring->first_seg->dma |
				  ep_ring->cycle_state);

	ep_ctx->tx_info = cpu_to_le32(EP_MAX_ESIT_PAYLOAD_LO(max_esit_payload) |
				      EP_AVG_TRB_LENGTH(avg_trb_len));

	/* FIXME Debug endpoint context */
	return 0;
}

void xhci_endpoint_zero(struct xhci_hcd *xhci,
		struct xhci_virt_device *virt_dev,
		struct usb_host_endpoint *ep)
{
	unsigned int ep_index;
	struct xhci_ep_ctx *ep_ctx;

	ep_index = xhci_get_endpoint_index(&ep->desc);
	ep_ctx = xhci_get_ep_ctx(xhci, virt_dev->in_ctx, ep_index);

	ep_ctx->ep_info = 0;
	ep_ctx->ep_info2 = 0;
	ep_ctx->deq = 0;
	ep_ctx->tx_info = 0;
	/* Don't free the endpoint ring until the set interface or configuration
	 * request succeeds.
	 */
}

void xhci_clear_endpoint_bw_info(struct xhci_bw_info *bw_info)
{
	bw_info->ep_interval = 0;
	bw_info->mult = 0;
	bw_info->num_packets = 0;
	bw_info->max_packet_size = 0;
	bw_info->type = 0;
	bw_info->max_esit_payload = 0;
}

void xhci_update_bw_info(struct xhci_hcd *xhci,
		struct xhci_container_ctx *in_ctx,
		struct xhci_input_control_ctx *ctrl_ctx,
		struct xhci_virt_device *virt_dev)
{
	struct xhci_bw_info *bw_info;
	struct xhci_ep_ctx *ep_ctx;
	unsigned int ep_type;
	int i;

	for (i = 1; i < 31; ++i) {
		bw_info = &virt_dev->eps[i].bw_info;

		/* We can't tell what endpoint type is being dropped, but
		 * unconditionally clearing the bandwidth info for non-periodic
		 * endpoints should be harmless because the info will never be
		 * set in the first place.
		 */
		if (!EP_IS_ADDED(ctrl_ctx, i) && EP_IS_DROPPED(ctrl_ctx, i)) {
			/* Dropped endpoint */
			xhci_clear_endpoint_bw_info(bw_info);
			continue;
		}

		if (EP_IS_ADDED(ctrl_ctx, i)) {
			ep_ctx = xhci_get_ep_ctx(xhci, in_ctx, i);
			ep_type = CTX_TO_EP_TYPE(le32_to_cpu(ep_ctx->ep_info2));

			/* Ignore non-periodic endpoints */
			if (ep_type != ISOC_OUT_EP && ep_type != INT_OUT_EP &&
					ep_type != ISOC_IN_EP &&
					ep_type != INT_IN_EP)
				continue;

			/* Added or changed endpoint */
			bw_info->ep_interval = CTX_TO_EP_INTERVAL(
					le32_to_cpu(ep_ctx->ep_info));
			/* Number of packets and mult are zero-based in the
			 * input context, but we want one-based for the
			 * interval table.
			 */
			bw_info->mult = CTX_TO_EP_MULT(
					le32_to_cpu(ep_ctx->ep_info)) + 1;
			bw_info->num_packets = CTX_TO_MAX_BURST(
					le32_to_cpu(ep_ctx->ep_info2)) + 1;
			bw_info->max_packet_size = MAX_PACKET_DECODED(
					le32_to_cpu(ep_ctx->ep_info2));
			bw_info->type = ep_type;
			bw_info->max_esit_payload = CTX_TO_MAX_ESIT_PAYLOAD(
					le32_to_cpu(ep_ctx->tx_info));
		}
	}
}

/* Copy output xhci_ep_ctx to the input xhci_ep_ctx copy.
 * Useful when you want to change one particular aspect of the endpoint and then
 * issue a configure endpoint command.
 */
void xhci_endpoint_copy(struct xhci_hcd *xhci,
		struct xhci_container_ctx *in_ctx,
		struct xhci_container_ctx *out_ctx,
		unsigned int ep_index)
{
	struct xhci_ep_ctx *out_ep_ctx;
	struct xhci_ep_ctx *in_ep_ctx;

	out_ep_ctx = xhci_get_ep_ctx(xhci, out_ctx, ep_index);
	in_ep_ctx = xhci_get_ep_ctx(xhci, in_ctx, ep_index);

	in_ep_ctx->ep_info = out_ep_ctx->ep_info;
	in_ep_ctx->ep_info2 = out_ep_ctx->ep_info2;
	in_ep_ctx->deq = out_ep_ctx->deq;
	in_ep_ctx->tx_info = out_ep_ctx->tx_info;
}

/* Copy output xhci_slot_ctx to the input xhci_slot_ctx.
 * Useful when you want to change one particular aspect of the endpoint and then
 * issue a configure endpoint command.  Only the context entries field matters,
 * but we'll copy the whole thing anyway.
 */
void xhci_slot_copy(struct xhci_hcd *xhci,
		struct xhci_container_ctx *in_ctx,
		struct xhci_container_ctx *out_ctx)
{
	struct xhci_slot_ctx *in_slot_ctx;
	struct xhci_slot_ctx *out_slot_ctx;

	in_slot_ctx = xhci_get_slot_ctx(xhci, in_ctx);
	out_slot_ctx = xhci_get_slot_ctx(xhci, out_ctx);

	in_slot_ctx->dev_info = out_slot_ctx->dev_info;
	in_slot_ctx->dev_info2 = out_slot_ctx->dev_info2;
	in_slot_ctx->tt_info = out_slot_ctx->tt_info;
	in_slot_ctx->dev_state = out_slot_ctx->dev_state;
}

/* Set up the scratchpad buffer array and scratchpad buffers, if needed. */
static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags)
{
	int i;
	struct device *dev = xhci_to_hcd(xhci)->self.controller;
	int num_sp = HCS_MAX_SCRATCHPAD(xhci->hcs_params2);

	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Allocating %d scratchpad buffers", num_sp);

	if (!num_sp)
		return 0;

	xhci->scratchpad = kzalloc(sizeof(*xhci->scratchpad), flags);
	if (!xhci->scratchpad)
		goto fail_sp;

	xhci->scratchpad->sp_array = dma_alloc_coherent(dev,
				     num_sp * sizeof(u64),
				     &xhci->scratchpad->sp_dma, flags);
	if (!xhci->scratchpad->sp_array)
		goto fail_sp2;

	xhci->scratchpad->sp_buffers = kzalloc(sizeof(void *) * num_sp, flags);
	if (!xhci->scratchpad->sp_buffers)
		goto fail_sp3;

	xhci->scratchpad->sp_dma_buffers =
		kzalloc(sizeof(dma_addr_t) * num_sp, flags);

	if (!xhci->scratchpad->sp_dma_buffers)
		goto fail_sp4;

	xhci->dcbaa->dev_context_ptrs[0] = cpu_to_le64(xhci->scratchpad->sp_dma);
	for (i = 0; i < num_sp; i++) {
		dma_addr_t dma;
		void *buf = dma_alloc_coherent(dev, xhci->page_size, &dma,
				flags);
		if (!buf)
			goto fail_sp5;

		xhci->scratchpad->sp_array[i] = dma;
		xhci->scratchpad->sp_buffers[i] = buf;
		xhci->scratchpad->sp_dma_buffers[i] = dma;
	}

	return 0;

 fail_sp5:
	for (i = i - 1; i >= 0; i--) {
		dma_free_coherent(dev, xhci->page_size,
				    xhci->scratchpad->sp_buffers[i],
				    xhci->scratchpad->sp_dma_buffers[i]);
	}
	kfree(xhci->scratchpad->sp_dma_buffers);

 fail_sp4:
	kfree(xhci->scratchpad->sp_buffers);

 fail_sp3:
	dma_free_coherent(dev, num_sp * sizeof(u64),
			    xhci->scratchpad->sp_array,
			    xhci->scratchpad->sp_dma);

 fail_sp2:
	kfree(xhci->scratchpad);
	xhci->scratchpad = NULL;

 fail_sp:
	return -ENOMEM;
}

static void scratchpad_free(struct xhci_hcd *xhci)
{
	int num_sp;
	int i;
	struct device *dev = xhci_to_hcd(xhci)->self.controller;

	if (!xhci->scratchpad)
		return;

	num_sp = HCS_MAX_SCRATCHPAD(xhci->hcs_params2);

	for (i = 0; i < num_sp; i++) {
		dma_free_coherent(dev, xhci->page_size,
				    xhci->scratchpad->sp_buffers[i],
				    xhci->scratchpad->sp_dma_buffers[i]);
	}
	kfree(xhci->scratchpad->sp_dma_buffers);
	kfree(xhci->scratchpad->sp_buffers);
	dma_free_coherent(dev, num_sp * sizeof(u64),
			    xhci->scratchpad->sp_array,
			    xhci->scratchpad->sp_dma);
	kfree(xhci->scratchpad);
	xhci->scratchpad = NULL;
}

struct xhci_command *xhci_alloc_command(struct xhci_hcd *xhci,
		bool allocate_in_ctx, bool allocate_completion,
		gfp_t mem_flags)
{
	struct xhci_command *command;

	command = kzalloc(sizeof(*command), mem_flags);
	if (!command)
		return NULL;

	if (allocate_in_ctx) {
		command->in_ctx =
			xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_INPUT,
					mem_flags);
		if (!command->in_ctx) {
			kfree(command);
			return NULL;
		}
	}

	if (allocate_completion) {
		command->completion =
			kzalloc(sizeof(struct completion), mem_flags);
		if (!command->completion) {
			xhci_free_container_ctx(xhci, command->in_ctx);
			kfree(command);
			return NULL;
		}
		init_completion(command->completion);
	}

	command->status = 0;
	INIT_LIST_HEAD(&command->cmd_list);
	return command;
}

void xhci_urb_free_priv(struct urb_priv *urb_priv)
{
	if (urb_priv) {
		kfree(urb_priv->td[0]);
		kfree(urb_priv);
	}
}

void xhci_free_command(struct xhci_hcd *xhci,
		struct xhci_command *command)
{
	xhci_free_container_ctx(xhci,
			command->in_ctx);
	kfree(command->completion);
	kfree(command);
}

void xhci_mem_cleanup(struct xhci_hcd *xhci)
{
	struct device	*dev = xhci_to_hcd(xhci)->self.controller;
	int size;
	int i, j, num_ports;

	del_timer_sync(&xhci->cmd_timer);

	/* Free the Event Ring Segment Table and the actual Event Ring */
	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
	if (xhci->erst.entries)
		dma_free_coherent(dev, size,
				xhci->erst.entries, xhci->erst.erst_dma_addr);
	xhci->erst.entries = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed ERST");
	if (xhci->event_ring)
		xhci_ring_free(xhci, xhci->event_ring);
	xhci->event_ring = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed event ring");

	if (xhci->lpm_command)
		xhci_free_command(xhci, xhci->lpm_command);
	xhci->lpm_command = NULL;
	if (xhci->cmd_ring)
		xhci_ring_free(xhci, xhci->cmd_ring);
	xhci->cmd_ring = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed command ring");
	xhci_cleanup_command_queue(xhci);

	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
	for (i = 0; i < num_ports && xhci->rh_bw; i++) {
		struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
		for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
			struct list_head *ep = &bwt->interval_bw[j].endpoints;
			while (!list_empty(ep))
				list_del_init(ep->next);
		}
	}

	for (i = 1; i < MAX_HC_SLOTS; ++i)
		xhci_free_virt_device(xhci, i);

	dma_pool_destroy(xhci->segment_pool);
	xhci->segment_pool = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed segment pool");

	dma_pool_destroy(xhci->device_pool);
	xhci->device_pool = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Freed device context pool");

	dma_pool_destroy(xhci->small_streams_pool);
	xhci->small_streams_pool = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Freed small stream array pool");

	dma_pool_destroy(xhci->medium_streams_pool);
	xhci->medium_streams_pool = NULL;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Freed medium stream array pool");

	if (xhci->dcbaa)
		dma_free_coherent(dev, sizeof(*xhci->dcbaa),
				xhci->dcbaa, xhci->dcbaa->dma);
	xhci->dcbaa = NULL;

	scratchpad_free(xhci);

	if (!xhci->rh_bw)
		goto no_bw;

	for (i = 0; i < num_ports; i++) {
		struct xhci_tt_bw_info *tt, *n;
		list_for_each_entry_safe(tt, n, &xhci->rh_bw[i].tts, tt_list) {
			list_del(&tt->tt_list);
			kfree(tt);
		}
	}

no_bw:
	xhci->cmd_ring_reserved_trbs = 0;
	xhci->num_usb2_ports = 0;
	xhci->num_usb3_ports = 0;
	xhci->num_active_eps = 0;
	kfree(xhci->usb2_ports);
	kfree(xhci->usb3_ports);
	kfree(xhci->port_array);
	kfree(xhci->rh_bw);
	kfree(xhci->ext_caps);

	xhci->page_size = 0;
	xhci->page_shift = 0;
	xhci->bus_state[0].bus_suspended = 0;
	xhci->bus_state[1].bus_suspended = 0;
}

static int xhci_test_trb_in_td(struct xhci_hcd *xhci,
		struct xhci_segment *input_seg,
		union xhci_trb *start_trb,
		union xhci_trb *end_trb,
		dma_addr_t input_dma,
		struct xhci_segment *result_seg,
		char *test_name, int test_number)
{
	unsigned long long start_dma;
	unsigned long long end_dma;
	struct xhci_segment *seg;

	start_dma = xhci_trb_virt_to_dma(input_seg, start_trb);
	end_dma = xhci_trb_virt_to_dma(input_seg, end_trb);

	seg = trb_in_td(xhci, input_seg, start_trb, end_trb, input_dma, false);
	if (seg != result_seg) {
		xhci_warn(xhci, "WARN: %s TRB math test %d failed!\n",
				test_name, test_number);
		xhci_warn(xhci, "Tested TRB math w/ seg %p and "
				"input DMA 0x%llx\n",
				input_seg,
				(unsigned long long) input_dma);
		xhci_warn(xhci, "starting TRB %p (0x%llx DMA), "
				"ending TRB %p (0x%llx DMA)\n",
				start_trb, start_dma,
				end_trb, end_dma);
		xhci_warn(xhci, "Expected seg %p, got seg %p\n",
				result_seg, seg);
		trb_in_td(xhci, input_seg, start_trb, end_trb, input_dma,
			  true);
		return -1;
	}
	return 0;
}

/* TRB math checks for xhci_trb_in_td(), using the command and event rings. */
static int xhci_check_trb_in_td_math(struct xhci_hcd *xhci)
{
	struct {
		dma_addr_t		input_dma;
		struct xhci_segment	*result_seg;
	} simple_test_vector [] = {
		/* A zeroed DMA field should fail */
		{ 0, NULL },
		/* One TRB before the ring start should fail */
		{ xhci->event_ring->first_seg->dma - 16, NULL },
		/* One byte before the ring start should fail */
		{ xhci->event_ring->first_seg->dma - 1, NULL },
		/* Starting TRB should succeed */
		{ xhci->event_ring->first_seg->dma, xhci->event_ring->first_seg },
		/* Ending TRB should succeed */
		{ xhci->event_ring->first_seg->dma + (TRBS_PER_SEGMENT - 1)*16,
			xhci->event_ring->first_seg },
		/* One byte after the ring end should fail */
		{ xhci->event_ring->first_seg->dma + (TRBS_PER_SEGMENT - 1)*16 + 1, NULL },
		/* One TRB after the ring end should fail */
		{ xhci->event_ring->first_seg->dma + (TRBS_PER_SEGMENT)*16, NULL },
		/* An address of all ones should fail */
		{ (dma_addr_t) (~0), NULL },
	};
	struct {
		struct xhci_segment	*input_seg;
		union xhci_trb		*start_trb;
		union xhci_trb		*end_trb;
		dma_addr_t		input_dma;
		struct xhci_segment	*result_seg;
	} complex_test_vector [] = {
		/* Test feeding a valid DMA address from a different ring */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = xhci->event_ring->first_seg->trbs,
			.end_trb = &xhci->event_ring->first_seg->trbs[TRBS_PER_SEGMENT - 1],
			.input_dma = xhci->cmd_ring->first_seg->dma,
			.result_seg = NULL,
		},
		/* Test feeding a valid end TRB from a different ring */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = xhci->event_ring->first_seg->trbs,
			.end_trb = &xhci->cmd_ring->first_seg->trbs[TRBS_PER_SEGMENT - 1],
			.input_dma = xhci->cmd_ring->first_seg->dma,
			.result_seg = NULL,
		},
		/* Test feeding a valid start and end TRB from a different ring */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = xhci->cmd_ring->first_seg->trbs,
			.end_trb = &xhci->cmd_ring->first_seg->trbs[TRBS_PER_SEGMENT - 1],
			.input_dma = xhci->cmd_ring->first_seg->dma,
			.result_seg = NULL,
		},
		/* TRB in this ring, but after this TD */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = &xhci->event_ring->first_seg->trbs[0],
			.end_trb = &xhci->event_ring->first_seg->trbs[3],
			.input_dma = xhci->event_ring->first_seg->dma + 4*16,
			.result_seg = NULL,
		},
		/* TRB in this ring, but before this TD */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = &xhci->event_ring->first_seg->trbs[3],
			.end_trb = &xhci->event_ring->first_seg->trbs[6],
			.input_dma = xhci->event_ring->first_seg->dma + 2*16,
			.result_seg = NULL,
		},
		/* TRB in this ring, but after this wrapped TD */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = &xhci->event_ring->first_seg->trbs[TRBS_PER_SEGMENT - 3],
			.end_trb = &xhci->event_ring->first_seg->trbs[1],
			.input_dma = xhci->event_ring->first_seg->dma + 2*16,
			.result_seg = NULL,
		},
		/* TRB in this ring, but before this wrapped TD */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = &xhci->event_ring->first_seg->trbs[TRBS_PER_SEGMENT - 3],
			.end_trb = &xhci->event_ring->first_seg->trbs[1],
			.input_dma = xhci->event_ring->first_seg->dma + (TRBS_PER_SEGMENT - 4)*16,
			.result_seg = NULL,
		},
		/* TRB not in this ring, and we have a wrapped TD */
		{	.input_seg = xhci->event_ring->first_seg,
			.start_trb = &xhci->event_ring->first_seg->trbs[TRBS_PER_SEGMENT - 3],
			.end_trb = &xhci->event_ring->first_seg->trbs[1],
			.input_dma = xhci->cmd_ring->first_seg->dma + 2*16,
			.result_seg = NULL,
		},
	};

	unsigned int num_tests;
	int i, ret;

	num_tests = ARRAY_SIZE(simple_test_vector);
	for (i = 0; i < num_tests; i++) {
		ret = xhci_test_trb_in_td(xhci,
				xhci->event_ring->first_seg,
				xhci->event_ring->first_seg->trbs,
				&xhci->event_ring->first_seg->trbs[TRBS_PER_SEGMENT - 1],
				simple_test_vector[i].input_dma,
				simple_test_vector[i].result_seg,
				"Simple", i);
		if (ret < 0)
			return ret;
	}

	num_tests = ARRAY_SIZE(complex_test_vector);
	for (i = 0; i < num_tests; i++) {
		ret = xhci_test_trb_in_td(xhci,
				complex_test_vector[i].input_seg,
				complex_test_vector[i].start_trb,
				complex_test_vector[i].end_trb,
				complex_test_vector[i].input_dma,
				complex_test_vector[i].result_seg,
				"Complex", i);
		if (ret < 0)
			return ret;
	}
	xhci_dbg(xhci, "TRB math tests passed.\n");
	return 0;
}

static void xhci_set_hc_event_deq(struct xhci_hcd *xhci)
{
	u64 temp;
	dma_addr_t deq;

	deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg,
			xhci->event_ring->dequeue);
	if (deq == 0 && !in_interrupt())
		xhci_warn(xhci, "WARN something wrong with SW event ring "
				"dequeue ptr.\n");
	/* Update HC event ring dequeue pointer */
	temp = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue);
	temp &= ERST_PTR_MASK;
	/* Don't clear the EHB bit (which is RW1C) because
	 * there might be more events to service.
	 */
	temp &= ~ERST_EHB;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Write event ring dequeue pointer, "
			"preserving EHB bit");
	xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp,
			&xhci->ir_set->erst_dequeue);
}

static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
		__le32 __iomem *addr, int max_caps)
{
	u32 temp, port_offset, port_count;
	int i;
	u8 major_revision;
	struct xhci_hub *rhub;

	temp = readl(addr);
	major_revision = XHCI_EXT_PORT_MAJOR(temp);

	if (major_revision == 0x03) {
		rhub = &xhci->usb3_rhub;
	} else if (major_revision <= 0x02) {
		rhub = &xhci->usb2_rhub;
	} else {
		xhci_warn(xhci, "Ignoring unknown port speed, "
				"Ext Cap %p, revision = 0x%x\n",
				addr, major_revision);
		/* Ignoring port protocol we can't understand. FIXME */
		return;
	}
	rhub->maj_rev = XHCI_EXT_PORT_MAJOR(temp);
	rhub->min_rev = XHCI_EXT_PORT_MINOR(temp);

	/* Port offset and count in the third dword, see section 7.2 */
	temp = readl(addr + 2);
	port_offset = XHCI_EXT_PORT_OFF(temp);
	port_count = XHCI_EXT_PORT_COUNT(temp);
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Ext Cap %p, port offset = %u, "
			"count = %u, revision = 0x%x",
			addr, port_offset, port_count, major_revision);
	/* Port count includes the current port offset */
	if (port_offset == 0 || (port_offset + port_count - 1) > num_ports)
		/* WTF? "Valid values are ‘1’ to MaxPorts" */
		return;

	rhub->psi_count = XHCI_EXT_PORT_PSIC(temp);
	if (rhub->psi_count) {
		rhub->psi = kcalloc(rhub->psi_count, sizeof(*rhub->psi),
				    GFP_KERNEL);
		if (!rhub->psi)
			rhub->psi_count = 0;

		rhub->psi_uid_count++;
		for (i = 0; i < rhub->psi_count; i++) {
			rhub->psi[i] = readl(addr + 4 + i);

			/* count unique ID values, two consecutive entries can
			 * have the same ID if link is assymetric
			 */
			if (i && (XHCI_EXT_PORT_PSIV(rhub->psi[i]) !=
				  XHCI_EXT_PORT_PSIV(rhub->psi[i - 1])))
				rhub->psi_uid_count++;

			xhci_dbg(xhci, "PSIV:%d PSIE:%d PLT:%d PFD:%d LP:%d PSIM:%d\n",
				  XHCI_EXT_PORT_PSIV(rhub->psi[i]),
				  XHCI_EXT_PORT_PSIE(rhub->psi[i]),
				  XHCI_EXT_PORT_PLT(rhub->psi[i]),
				  XHCI_EXT_PORT_PFD(rhub->psi[i]),
				  XHCI_EXT_PORT_LP(rhub->psi[i]),
				  XHCI_EXT_PORT_PSIM(rhub->psi[i]));
		}
	}
	/* cache usb2 port capabilities */
	if (major_revision < 0x03 && xhci->num_ext_caps < max_caps)
		xhci->ext_caps[xhci->num_ext_caps++] = temp;

	/* Check the host's USB2 LPM capability */
	if ((xhci->hci_version == 0x96) && (major_revision != 0x03) &&
			(temp & XHCI_L1C)) {
		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
				"xHCI 0.96: support USB2 software lpm");
		xhci->sw_lpm_support = 1;
	}

	if ((xhci->hci_version >= 0x100) && (major_revision != 0x03)) {
		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
				"xHCI 1.0: support USB2 software lpm");
		xhci->sw_lpm_support = 1;
		if (temp & XHCI_HLC) {
			xhci_dbg_trace(xhci, trace_xhci_dbg_init,
					"xHCI 1.0: support USB2 hardware lpm");
			xhci->hw_lpm_support = 1;
		}
	}

	port_offset--;
	for (i = port_offset; i < (port_offset + port_count); i++) {
		/* Duplicate entry.  Ignore the port if the revisions differ. */
		if (xhci->port_array[i] != 0) {
			xhci_warn(xhci, "Duplicate port entry, Ext Cap %p,"
					" port %u\n", addr, i);
			xhci_warn(xhci, "Port was marked as USB %u, "
					"duplicated as USB %u\n",
					xhci->port_array[i], major_revision);
			/* Only adjust the roothub port counts if we haven't
			 * found a similar duplicate.
			 */
			if (xhci->port_array[i] != major_revision &&
				xhci->port_array[i] != DUPLICATE_ENTRY) {
				if (xhci->port_array[i] == 0x03)
					xhci->num_usb3_ports--;
				else
					xhci->num_usb2_ports--;
				xhci->port_array[i] = DUPLICATE_ENTRY;
			}
			/* FIXME: Should we disable the port? */
			continue;
		}
		xhci->port_array[i] = major_revision;
		if (major_revision == 0x03)
			xhci->num_usb3_ports++;
		else
			xhci->num_usb2_ports++;
	}
	/* FIXME: Should we disable ports not in the Extended Capabilities? */
}

/*
 * Scan the Extended Capabilities for the "Supported Protocol Capabilities" that
 * specify what speeds each port is supposed to be.  We can't count on the port
 * speed bits in the PORTSC register being correct until a device is connected,
 * but we need to set up the two fake roothubs with the correct number of USB
 * 3.0 and USB 2.0 ports at host controller initialization time.
 */
static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
{
	void __iomem *base;
	u32 offset;
	unsigned int num_ports;
	int i, j, port_index;
	int cap_count = 0;
	u32 cap_start;

	num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
	xhci->port_array = kzalloc(sizeof(*xhci->port_array)*num_ports, flags);
	if (!xhci->port_array)
		return -ENOMEM;

	xhci->rh_bw = kzalloc(sizeof(*xhci->rh_bw)*num_ports, flags);
	if (!xhci->rh_bw)
		return -ENOMEM;
	for (i = 0; i < num_ports; i++) {
		struct xhci_interval_bw_table *bw_table;

		INIT_LIST_HEAD(&xhci->rh_bw[i].tts);
		bw_table = &xhci->rh_bw[i].bw_table;
		for (j = 0; j < XHCI_MAX_INTERVAL; j++)
			INIT_LIST_HEAD(&bw_table->interval_bw[j].endpoints);
	}
	base = &xhci->cap_regs->hc_capbase;

	cap_start = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_PROTOCOL);
	if (!cap_start) {
		xhci_err(xhci, "No Extended Capability registers, unable to set up roothub\n");
		return -ENODEV;
	}

	offset = cap_start;
	/* count extended protocol capability entries for later caching */
	while (offset) {
		cap_count++;
		offset = xhci_find_next_ext_cap(base, offset,
						      XHCI_EXT_CAPS_PROTOCOL);
	}

	xhci->ext_caps = kzalloc(sizeof(*xhci->ext_caps) * cap_count, flags);
	if (!xhci->ext_caps)
		return -ENOMEM;

	offset = cap_start;

	while (offset) {
		xhci_add_in_port(xhci, num_ports, base + offset, cap_count);
		if (xhci->num_usb2_ports + xhci->num_usb3_ports == num_ports)
			break;
		offset = xhci_find_next_ext_cap(base, offset,
						XHCI_EXT_CAPS_PROTOCOL);
	}

	if (xhci->num_usb2_ports == 0 && xhci->num_usb3_ports == 0) {
		xhci_warn(xhci, "No ports on the roothubs?\n");
		return -ENODEV;
	}
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Found %u USB 2.0 ports and %u USB 3.0 ports.",
			xhci->num_usb2_ports, xhci->num_usb3_ports);

	/* Place limits on the number of roothub ports so that the hub
	 * descriptors aren't longer than the USB core will allocate.
	 */
	if (xhci->num_usb3_ports > 15) {
		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
				"Limiting USB 3.0 roothub ports to 15.");
		xhci->num_usb3_ports = 15;
	}
	if (xhci->num_usb2_ports > USB_MAXCHILDREN) {
		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
				"Limiting USB 2.0 roothub ports to %u.",
				USB_MAXCHILDREN);
		xhci->num_usb2_ports = USB_MAXCHILDREN;
	}

	/*
	 * Note we could have all USB 3.0 ports, or all USB 2.0 ports.
	 * Not sure how the USB core will handle a hub with no ports...
	 */
	if (xhci->num_usb2_ports) {
		xhci->usb2_ports = kmalloc(sizeof(*xhci->usb2_ports)*
				xhci->num_usb2_ports, flags);
		if (!xhci->usb2_ports)
			return -ENOMEM;

		port_index = 0;
		for (i = 0; i < num_ports; i++) {
			if (xhci->port_array[i] == 0x03 ||
					xhci->port_array[i] == 0 ||
					xhci->port_array[i] == DUPLICATE_ENTRY)
				continue;

			xhci->usb2_ports[port_index] =
				&xhci->op_regs->port_status_base +
				NUM_PORT_REGS*i;
			xhci_dbg_trace(xhci, trace_xhci_dbg_init,
					"USB 2.0 port at index %u, "
					"addr = %p", i,
					xhci->usb2_ports[port_index]);
			port_index++;
			if (port_index == xhci->num_usb2_ports)
				break;
		}
	}
	if (xhci->num_usb3_ports) {
		xhci->usb3_ports = kmalloc(sizeof(*xhci->usb3_ports)*
				xhci->num_usb3_ports, flags);
		if (!xhci->usb3_ports)
			return -ENOMEM;

		port_index = 0;
		for (i = 0; i < num_ports; i++)
			if (xhci->port_array[i] == 0x03) {
				xhci->usb3_ports[port_index] =
					&xhci->op_regs->port_status_base +
					NUM_PORT_REGS*i;
				xhci_dbg_trace(xhci, trace_xhci_dbg_init,
						"USB 3.0 port at index %u, "
						"addr = %p", i,
						xhci->usb3_ports[port_index]);
				port_index++;
				if (port_index == xhci->num_usb3_ports)
					break;
			}
	}
	return 0;
}

int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
{
	dma_addr_t	dma;
	struct device	*dev = xhci_to_hcd(xhci)->self.controller;
	unsigned int	val, val2;
	u64		val_64;
	struct xhci_segment	*seg;
	u32 page_size, temp;
	int i;

	INIT_LIST_HEAD(&xhci->cmd_list);

	/* init command timeout timer */
	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
		    (unsigned long)xhci);

	page_size = readl(&xhci->op_regs->page_size);
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Supported page size register = 0x%x", page_size);
	for (i = 0; i < 16; i++) {
		if ((0x1 & page_size) != 0)
			break;
		page_size = page_size >> 1;
	}
	if (i < 16)
		xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Supported page size of %iK", (1 << (i+12)) / 1024);
	else
		xhci_warn(xhci, "WARN: no supported page size\n");
	/* Use 4K pages, since that's common and the minimum the HC supports */
	xhci->page_shift = 12;
	xhci->page_size = 1 << xhci->page_shift;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"HCD page size set to %iK", xhci->page_size / 1024);

	/*
	 * Program the Number of Device Slots Enabled field in the CONFIG
	 * register with the max value of slots the HC can handle.
	 */
	val = HCS_MAX_SLOTS(readl(&xhci->cap_regs->hcs_params1));
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// xHC can handle at most %d device slots.", val);
	val2 = readl(&xhci->op_regs->config_reg);
	val |= (val2 & ~HCS_SLOTS_MASK);
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Setting Max device slots reg = 0x%x.", val);
	writel(val, &xhci->op_regs->config_reg);

	/*
	 * Section 5.4.8 - doorbell array must be
	 * "physically contiguous and 64-byte (cache line) aligned".
	 */
	xhci->dcbaa = dma_alloc_coherent(dev, sizeof(*xhci->dcbaa), &dma,
			GFP_KERNEL);
	if (!xhci->dcbaa)
		goto fail;
	memset(xhci->dcbaa, 0, sizeof *(xhci->dcbaa));
	xhci->dcbaa->dma = dma;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Device context base array address = 0x%llx (DMA), %p (virt)",
			(unsigned long long)xhci->dcbaa->dma, xhci->dcbaa);
	xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr);

	/*
	 * Initialize the ring segment pool.  The ring must be a contiguous
	 * structure comprised of TRBs.  The TRBs must be 16 byte aligned,
	 * however, the command ring segment needs 64-byte aligned segments
	 * and our use of dma addresses in the trb_address_map radix tree needs
	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
	 */
	xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
			TRB_SEGMENT_SIZE, TRB_SEGMENT_SIZE, xhci->page_size);

	/* See Table 46 and Note on Figure 55 */
	xhci->device_pool = dma_pool_create("xHCI input/output contexts", dev,
			2112, 64, xhci->page_size);
	if (!xhci->segment_pool || !xhci->device_pool)
		goto fail;

	/* Linear stream context arrays don't have any boundary restrictions,
	 * and only need to be 16-byte aligned.
	 */
	xhci->small_streams_pool =
		dma_pool_create("xHCI 256 byte stream ctx arrays",
			dev, SMALL_STREAM_ARRAY_SIZE, 16, 0);
	xhci->medium_streams_pool =
		dma_pool_create("xHCI 1KB stream ctx arrays",
			dev, MEDIUM_STREAM_ARRAY_SIZE, 16, 0);
	/* Any stream context array bigger than MEDIUM_STREAM_ARRAY_SIZE
	 * will be allocated with dma_alloc_coherent()
	 */

	if (!xhci->small_streams_pool || !xhci->medium_streams_pool)
		goto fail;

	/* Set up the command ring to have one segments for now. */
	xhci->cmd_ring = xhci_ring_alloc(xhci, 1, 1, TYPE_COMMAND, flags);
	if (!xhci->cmd_ring)
		goto fail;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Allocated command ring at %p", xhci->cmd_ring);
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "First segment DMA is 0x%llx",
			(unsigned long long)xhci->cmd_ring->first_seg->dma);

	/* Set the address in the Command Ring Control register */
	val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring);
	val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) |
		(xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) |
		xhci->cmd_ring->cycle_state;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Setting command ring address to 0x%x", val);
	xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring);
	xhci_dbg_cmd_ptrs(xhci);

	xhci->lpm_command = xhci_alloc_command(xhci, true, true, flags);
	if (!xhci->lpm_command)
		goto fail;

	/* Reserve one command ring TRB for disabling LPM.
	 * Since the USB core grabs the shared usb_bus bandwidth mutex before
	 * disabling LPM, we only need to reserve one TRB for all devices.
	 */
	xhci->cmd_ring_reserved_trbs++;

	val = readl(&xhci->cap_regs->db_off);
	val &= DBOFF_MASK;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Doorbell array is located at offset 0x%x"
			" from cap regs base addr", val);
	xhci->dba = (void __iomem *) xhci->cap_regs + val;
	xhci_dbg_regs(xhci);
	xhci_print_run_regs(xhci);
	/* Set ir_set to interrupt register set 0 */
	xhci->ir_set = &xhci->run_regs->ir_set[0];

	/*
	 * Event ring setup: Allocate a normal ring, but also setup
	 * the event ring segment table (ERST).  Section 4.9.3.
	 */
	xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Allocating event ring");
	xhci->event_ring = xhci_ring_alloc(xhci, ERST_NUM_SEGS, 1, TYPE_EVENT,
						flags);
	if (!xhci->event_ring)
		goto fail;
	if (xhci_check_trb_in_td_math(xhci) < 0)
		goto fail;

	xhci->erst.entries = dma_alloc_coherent(dev,
			sizeof(struct xhci_erst_entry) * ERST_NUM_SEGS, &dma,
			GFP_KERNEL);
	if (!xhci->erst.entries)
		goto fail;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Allocated event ring segment table at 0x%llx",
			(unsigned long long)dma);

	memset(xhci->erst.entries, 0, sizeof(struct xhci_erst_entry)*ERST_NUM_SEGS);
	xhci->erst.num_entries = ERST_NUM_SEGS;
	xhci->erst.erst_dma_addr = dma;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Set ERST to 0; private num segs = %i, virt addr = %p, dma addr = 0x%llx",
			xhci->erst.num_entries,
			xhci->erst.entries,
			(unsigned long long)xhci->erst.erst_dma_addr);

	/* set ring base address and size for each segment table entry */
	for (val = 0, seg = xhci->event_ring->first_seg; val < ERST_NUM_SEGS; val++) {
		struct xhci_erst_entry *entry = &xhci->erst.entries[val];
		entry->seg_addr = cpu_to_le64(seg->dma);
		entry->seg_size = cpu_to_le32(TRBS_PER_SEGMENT);
		entry->rsvd = 0;
		seg = seg->next;
	}

	/* set ERST count with the number of entries in the segment table */
	val = readl(&xhci->ir_set->erst_size);
	val &= ERST_SIZE_MASK;
	val |= ERST_NUM_SEGS;
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Write ERST size = %i to ir_set 0 (some bits preserved)",
			val);
	writel(val, &xhci->ir_set->erst_size);

	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Set ERST entries to point to event ring.");
	/* set the segment table base address */
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"// Set ERST base address for ir_set 0 = 0x%llx",
			(unsigned long long)xhci->erst.erst_dma_addr);
	val_64 = xhci_read_64(xhci, &xhci->ir_set->erst_base);
	val_64 &= ERST_PTR_MASK;
	val_64 |= (xhci->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK);
	xhci_write_64(xhci, val_64, &xhci->ir_set->erst_base);

	/* Set the event ring dequeue address */
	xhci_set_hc_event_deq(xhci);
	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
			"Wrote ERST address to ir_set 0.");
	xhci_print_ir_set(xhci, 0);

	/*
	 * XXX: Might need to set the Interrupter Moderation Register to
	 * something other than the default (~1ms minimum between interrupts).
	 * See section 5.5.1.2.
	 */
	init_completion(&xhci->addr_dev);
	for (i = 0; i < MAX_HC_SLOTS; ++i)
		xhci->devs[i] = NULL;
	for (i = 0; i < USB_MAXCHILDREN; ++i) {
		xhci->bus_state[0].resume_done[i] = 0;
		xhci->bus_state[1].resume_done[i] = 0;
		/* Only the USB 2.0 completions will ever be used. */
		init_completion(&xhci->bus_state[1].rexit_done[i]);
	}

	if (scratchpad_alloc(xhci, flags))
		goto fail;
	if (xhci_setup_port_arrays(xhci, flags))
		goto fail;

	/* Enable USB 3.0 device notifications for function remote wake, which
	 * is necessary for allowing USB 3.0 devices to do remote wakeup from
	 * U3 (device suspend).
	 */
	temp = readl(&xhci->op_regs->dev_notification);
	temp &= ~DEV_NOTE_MASK;
	temp |= DEV_NOTE_FWAKE;
	writel(temp, &xhci->op_regs->dev_notification);

	return 0;

fail:
	xhci_warn(xhci, "Couldn't initialize memory\n");
	xhci_halt(xhci);
	xhci_reset(xhci);
	xhci_mem_cleanup(xhci);
	return -ENOMEM;
}