summaryrefslogtreecommitdiffstats
path: root/drivers/char/xillybus/xillybus_core.c
blob: a11af94e2e6507480ae17d7ec1ebc96458701073 (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
/*
 * linux/drivers/misc/xillybus_core.c
 *
 * Copyright 2011 Xillybus Ltd, http://xillybus.com
 *
 * Driver for the Xillybus FPGA/host framework.
 *
 * This driver interfaces with a special IP core in an FPGA, setting up
 * a pipe between a hardware FIFO in the programmable logic and a device
 * file in the host. The number of such pipes and their attributes are
 * set up on the logic. This driver detects these automatically and
 * creates the device files accordingly.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the smems of the GNU General Public License as published by
 * the Free Software Foundation; version 2 of the License.
 */

#include <linux/list.h>
#include <linux/device.h>
#include <linux/module.h>
#include <linux/io.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/crc32.h>
#include <linux/poll.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include "xillybus.h"

MODULE_DESCRIPTION("Xillybus core functions");
MODULE_AUTHOR("Eli Billauer, Xillybus Ltd.");
MODULE_VERSION("1.07");
MODULE_ALIAS("xillybus_core");
MODULE_LICENSE("GPL v2");

/* General timeout is 100 ms, rx timeout is 10 ms */
#define XILLY_RX_TIMEOUT (10*HZ/1000)
#define XILLY_TIMEOUT (100*HZ/1000)

#define fpga_msg_ctrl_reg              0x0008
#define fpga_dma_control_reg           0x0020
#define fpga_dma_bufno_reg             0x0024
#define fpga_dma_bufaddr_lowaddr_reg   0x0028
#define fpga_dma_bufaddr_highaddr_reg  0x002c
#define fpga_buf_ctrl_reg              0x0030
#define fpga_buf_offset_reg            0x0034
#define fpga_endian_reg                0x0040

#define XILLYMSG_OPCODE_RELEASEBUF 1
#define XILLYMSG_OPCODE_QUIESCEACK 2
#define XILLYMSG_OPCODE_FIFOEOF 3
#define XILLYMSG_OPCODE_FATAL_ERROR 4
#define XILLYMSG_OPCODE_NONEMPTY 5

static const char xillyname[] = "xillybus";

static struct class *xillybus_class;

/*
 * ep_list_lock is the last lock to be taken; No other lock requests are
 * allowed while holding it. It merely protects list_of_endpoints, and not
 * the endpoints listed in it.
 */

static LIST_HEAD(list_of_endpoints);
static struct mutex ep_list_lock;
static struct workqueue_struct *xillybus_wq;

/*
 * Locking scheme: Mutexes protect invocations of character device methods.
 * If both locks are taken, wr_mutex is taken first, rd_mutex second.
 *
 * wr_spinlock protects wr_*_buf_idx, wr_empty, wr_sleepy, wr_ready and the
 * buffers' end_offset fields against changes made by IRQ handler (and in
 * theory, other file request handlers, but the mutex handles that). Nothing
 * else.
 * They are held for short direct memory manipulations. Needless to say,
 * no mutex locking is allowed when a spinlock is held.
 *
 * rd_spinlock does the same with rd_*_buf_idx, rd_empty and end_offset.
 *
 * register_mutex is endpoint-specific, and is held when non-atomic
 * register operations are performed. wr_mutex and rd_mutex may be
 * held when register_mutex is taken, but none of the spinlocks. Note that
 * register_mutex doesn't protect against sporadic buf_ctrl_reg writes
 * which are unrelated to buf_offset_reg, since they are harmless.
 *
 * Blocking on the wait queues is allowed with mutexes held, but not with
 * spinlocks.
 *
 * Only interruptible blocking is allowed on mutexes and wait queues.
 *
 * All in all, the locking order goes (with skips allowed, of course):
 * wr_mutex -> rd_mutex -> register_mutex -> wr_spinlock -> rd_spinlock
 */

static void malformed_message(struct xilly_endpoint *endpoint, u32 *buf)
{
	int opcode;
	int msg_channel, msg_bufno, msg_data, msg_dir;

	opcode = (buf[0] >> 24) & 0xff;
	msg_dir = buf[0] & 1;
	msg_channel = (buf[0] >> 1) & 0x7ff;
	msg_bufno = (buf[0] >> 12) & 0x3ff;
	msg_data = buf[1] & 0xfffffff;

	dev_warn(endpoint->dev,
		 "Malformed message (skipping): opcode=%d, channel=%03x, dir=%d, bufno=%03x, data=%07x\n",
		 opcode, msg_channel, msg_dir, msg_bufno, msg_data);
}

/*
 * xillybus_isr assumes the interrupt is allocated exclusively to it,
 * which is the natural case MSI and several other hardware-oriented
 * interrupts. Sharing is not allowed.
 */

irqreturn_t xillybus_isr(int irq, void *data)
{
	struct xilly_endpoint *ep = data;
	u32 *buf;
	unsigned int buf_size;
	int i;
	int opcode;
	unsigned int msg_channel, msg_bufno, msg_data, msg_dir;
	struct xilly_channel *channel;

	buf = ep->msgbuf_addr;
	buf_size = ep->msg_buf_size/sizeof(u32);

	ep->ephw->hw_sync_sgl_for_cpu(ep,
				      ep->msgbuf_dma_addr,
				      ep->msg_buf_size,
				      DMA_FROM_DEVICE);

	for (i = 0; i < buf_size; i += 2) {
		if (((buf[i+1] >> 28) & 0xf) != ep->msg_counter) {
			malformed_message(ep, &buf[i]);
			dev_warn(ep->dev,
				 "Sending a NACK on counter %x (instead of %x) on entry %d\n",
				 ((buf[i+1] >> 28) & 0xf),
				 ep->msg_counter,
				 i/2);

			if (++ep->failed_messages > 10) {
				dev_err(ep->dev,
					"Lost sync with interrupt messages. Stopping.\n");
			} else {
				ep->ephw->hw_sync_sgl_for_device(
					ep,
					ep->msgbuf_dma_addr,
					ep->msg_buf_size,
					DMA_FROM_DEVICE);

				iowrite32(0x01,  /* Message NACK */
					  ep->registers + fpga_msg_ctrl_reg);
			}
			return IRQ_HANDLED;
		} else if (buf[i] & (1 << 22)) /* Last message */
			break;
	}

	if (i >= buf_size) {
		dev_err(ep->dev, "Bad interrupt message. Stopping.\n");
		return IRQ_HANDLED;
	}

	buf_size = i + 2;

	for (i = 0; i < buf_size; i += 2) { /* Scan through messages */
		opcode = (buf[i] >> 24) & 0xff;

		msg_dir = buf[i] & 1;
		msg_channel = (buf[i] >> 1) & 0x7ff;
		msg_bufno = (buf[i] >> 12) & 0x3ff;
		msg_data = buf[i+1] & 0xfffffff;

		switch (opcode) {
		case XILLYMSG_OPCODE_RELEASEBUF:
			if ((msg_channel > ep->num_channels) ||
			    (msg_channel == 0)) {
				malformed_message(ep, &buf[i]);
				break;
			}

			channel = ep->channels[msg_channel];

			if (msg_dir) { /* Write channel */
				if (msg_bufno >= channel->num_wr_buffers) {
					malformed_message(ep, &buf[i]);
					break;
				}
				spin_lock(&channel->wr_spinlock);
				channel->wr_buffers[msg_bufno]->end_offset =
					msg_data;
				channel->wr_fpga_buf_idx = msg_bufno;
				channel->wr_empty = 0;
				channel->wr_sleepy = 0;
				spin_unlock(&channel->wr_spinlock);

				wake_up_interruptible(&channel->wr_wait);

			} else {
				/* Read channel */

				if (msg_bufno >= channel->num_rd_buffers) {
					malformed_message(ep, &buf[i]);
					break;
				}

				spin_lock(&channel->rd_spinlock);
				channel->rd_fpga_buf_idx = msg_bufno;
				channel->rd_full = 0;
				spin_unlock(&channel->rd_spinlock);

				wake_up_interruptible(&channel->rd_wait);
				if (!channel->rd_synchronous)
					queue_delayed_work(
						xillybus_wq,
						&channel->rd_workitem,
						XILLY_RX_TIMEOUT);
			}

			break;
		case XILLYMSG_OPCODE_NONEMPTY:
			if ((msg_channel > ep->num_channels) ||
			    (msg_channel == 0) || (!msg_dir) ||
			    !ep->channels[msg_channel]->wr_supports_nonempty) {
				malformed_message(ep, &buf[i]);
				break;
			}

			channel = ep->channels[msg_channel];

			if (msg_bufno >= channel->num_wr_buffers) {
				malformed_message(ep, &buf[i]);
				break;
			}
			spin_lock(&channel->wr_spinlock);
			if (msg_bufno == channel->wr_host_buf_idx)
				channel->wr_ready = 1;
			spin_unlock(&channel->wr_spinlock);

			wake_up_interruptible(&channel->wr_ready_wait);

			break;
		case XILLYMSG_OPCODE_QUIESCEACK:
			ep->idtlen = msg_data;
			wake_up_interruptible(&ep->ep_wait);

			break;
		case XILLYMSG_OPCODE_FIFOEOF:
			if ((msg_channel > ep->num_channels) ||
			    (msg_channel == 0) || (!msg_dir) ||
			    !ep->channels[msg_channel]->num_wr_buffers) {
				malformed_message(ep, &buf[i]);
				break;
			}
			channel = ep->channels[msg_channel];
			spin_lock(&channel->wr_spinlock);
			channel->wr_eof = msg_bufno;
			channel->wr_sleepy = 0;

			channel->wr_hangup = channel->wr_empty &&
				(channel->wr_host_buf_idx == msg_bufno);

			spin_unlock(&channel->wr_spinlock);

			wake_up_interruptible(&channel->wr_wait);

			break;
		case XILLYMSG_OPCODE_FATAL_ERROR:
			ep->fatal_error = 1;
			wake_up_interruptible(&ep->ep_wait); /* For select() */
			dev_err(ep->dev,
				"FPGA reported a fatal error. This means that the low-level communication with the device has failed. This hardware problem is most likely unrelated to Xillybus (neither kernel module nor FPGA core), but reports are still welcome. All I/O is aborted.\n");
			break;
		default:
			malformed_message(ep, &buf[i]);
			break;
		}
	}

	ep->ephw->hw_sync_sgl_for_device(ep,
					 ep->msgbuf_dma_addr,
					 ep->msg_buf_size,
					 DMA_FROM_DEVICE);

	ep->msg_counter = (ep->msg_counter + 1) & 0xf;
	ep->failed_messages = 0;
	iowrite32(0x03, ep->registers + fpga_msg_ctrl_reg); /* Message ACK */

	return IRQ_HANDLED;
}
EXPORT_SYMBOL(xillybus_isr);

/*
 * A few trivial memory management functions.
 * NOTE: These functions are used only on probe and remove, and therefore
 * no locks are applied!
 */

static void xillybus_autoflush(struct work_struct *work);

struct xilly_alloc_state {
	void *salami;
	int left_of_salami;
	int nbuffer;
	enum dma_data_direction direction;
	u32 regdirection;
};

static int xilly_get_dma_buffers(struct xilly_endpoint *ep,
				 struct xilly_alloc_state *s,
				 struct xilly_buffer **buffers,
				 int bufnum, int bytebufsize)
{
	int i, rc;
	dma_addr_t dma_addr;
	struct device *dev = ep->dev;
	struct xilly_buffer *this_buffer = NULL; /* Init to silence warning */

	if (buffers) { /* Not the message buffer */
		this_buffer = devm_kcalloc(dev, bufnum,
					   sizeof(struct xilly_buffer),
					   GFP_KERNEL);
		if (!this_buffer)
			return -ENOMEM;
	}

	for (i = 0; i < bufnum; i++) {
		/*
		 * Buffers are expected in descending size order, so there
		 * is either enough space for this buffer or none at all.
		 */

		if ((s->left_of_salami < bytebufsize) &&
		    (s->left_of_salami > 0)) {
			dev_err(ep->dev,
				"Corrupt buffer allocation in IDT. Aborting.\n");
			return -ENODEV;
		}

		if (s->left_of_salami == 0) {
			int allocorder, allocsize;

			allocsize = PAGE_SIZE;
			allocorder = 0;
			while (bytebufsize > allocsize) {
				allocsize *= 2;
				allocorder++;
			}

			s->salami = (void *) devm_get_free_pages(
				dev,
				GFP_KERNEL | __GFP_DMA32 | __GFP_ZERO,
				allocorder);
			if (!s->salami)
				return -ENOMEM;

			s->left_of_salami = allocsize;
		}

		rc = ep->ephw->map_single(ep, s->salami,
					  bytebufsize, s->direction,
					  &dma_addr);
		if (rc)
			return rc;

		iowrite32((u32) (dma_addr & 0xffffffff),
			  ep->registers + fpga_dma_bufaddr_lowaddr_reg);
		iowrite32(((u32) ((((u64) dma_addr) >> 32) & 0xffffffff)),
			  ep->registers + fpga_dma_bufaddr_highaddr_reg);

		if (buffers) { /* Not the message buffer */
			this_buffer->addr = s->salami;
			this_buffer->dma_addr = dma_addr;
			buffers[i] = this_buffer++;

			iowrite32(s->regdirection | s->nbuffer++,
				  ep->registers + fpga_dma_bufno_reg);
		} else {
			ep->msgbuf_addr = s->salami;
			ep->msgbuf_dma_addr = dma_addr;
			ep->msg_buf_size = bytebufsize;

			iowrite32(s->regdirection,
				  ep->registers + fpga_dma_bufno_reg);
		}

		s->left_of_salami -= bytebufsize;
		s->salami += bytebufsize;
	}
	return 0;
}

static int xilly_setupchannels(struct xilly_endpoint *ep,
			       unsigned char *chandesc,
			       int entries)
{
	struct device *dev = ep->dev;
	int i, entry, rc;
	struct xilly_channel *channel;
	int channelnum, bufnum, bufsize, format, is_writebuf;
	int bytebufsize;
	int synchronous, allowpartial, exclusive_open, seekable;
	int supports_nonempty;
	int msg_buf_done = 0;

	struct xilly_alloc_state rd_alloc = {
		.salami = NULL,
		.left_of_salami = 0,
		.nbuffer = 1,
		.direction = DMA_TO_DEVICE,
		.regdirection = 0,
	};

	struct xilly_alloc_state wr_alloc = {
		.salami = NULL,
		.left_of_salami = 0,
		.nbuffer = 1,
		.direction = DMA_FROM_DEVICE,
		.regdirection = 0x80000000,
	};

	channel = devm_kcalloc(dev, ep->num_channels,
			       sizeof(struct xilly_channel), GFP_KERNEL);
	if (!channel)
		return -ENOMEM;

	ep->channels = devm_kcalloc(dev, ep->num_channels + 1,
				    sizeof(struct xilly_channel *),
				    GFP_KERNEL);
	if (!ep->channels)
		return -ENOMEM;

	ep->channels[0] = NULL; /* Channel 0 is message buf. */

	/* Initialize all channels with defaults */

	for (i = 1; i <= ep->num_channels; i++) {
		channel->wr_buffers = NULL;
		channel->rd_buffers = NULL;
		channel->num_wr_buffers = 0;
		channel->num_rd_buffers = 0;
		channel->wr_fpga_buf_idx = -1;
		channel->wr_host_buf_idx = 0;
		channel->wr_host_buf_pos = 0;
		channel->wr_empty = 1;
		channel->wr_ready = 0;
		channel->wr_sleepy = 1;
		channel->rd_fpga_buf_idx = 0;
		channel->rd_host_buf_idx = 0;
		channel->rd_host_buf_pos = 0;
		channel->rd_full = 0;
		channel->wr_ref_count = 0;
		channel->rd_ref_count = 0;

		spin_lock_init(&channel->wr_spinlock);
		spin_lock_init(&channel->rd_spinlock);
		mutex_init(&channel->wr_mutex);
		mutex_init(&channel->rd_mutex);
		init_waitqueue_head(&channel->rd_wait);
		init_waitqueue_head(&channel->wr_wait);
		init_waitqueue_head(&channel->wr_ready_wait);

		INIT_DELAYED_WORK(&channel->rd_workitem, xillybus_autoflush);

		channel->endpoint = ep;
		channel->chan_num = i;

		channel->log2_element_size = 0;

		ep->channels[i] = channel++;
	}

	for (entry = 0; entry < entries; entry++, chandesc += 4) {
		struct xilly_buffer **buffers = NULL;

		is_writebuf = chandesc[0] & 0x01;
		channelnum = (chandesc[0] >> 1) | ((chandesc[1] & 0x0f) << 7);
		format = (chandesc[1] >> 4) & 0x03;
		allowpartial = (chandesc[1] >> 6) & 0x01;
		synchronous = (chandesc[1] >> 7) & 0x01;
		bufsize = 1 << (chandesc[2] & 0x1f);
		bufnum = 1 << (chandesc[3] & 0x0f);
		exclusive_open = (chandesc[2] >> 7) & 0x01;
		seekable = (chandesc[2] >> 6) & 0x01;
		supports_nonempty = (chandesc[2] >> 5) & 0x01;

		if ((channelnum > ep->num_channels) ||
		    ((channelnum == 0) && !is_writebuf)) {
			dev_err(ep->dev,
				"IDT requests channel out of range. Aborting.\n");
			return -ENODEV;
		}

		channel = ep->channels[channelnum]; /* NULL for msg channel */

		if (!is_writebuf || channelnum > 0) {
			channel->log2_element_size = ((format > 2) ?
						      2 : format);

			bytebufsize = bufsize *
				(1 << channel->log2_element_size);

			buffers = devm_kcalloc(dev, bufnum,
					       sizeof(struct xilly_buffer *),
					       GFP_KERNEL);
			if (!buffers)
				return -ENOMEM;
		} else {
			bytebufsize = bufsize << 2;
		}

		if (!is_writebuf) {
			channel->num_rd_buffers = bufnum;
			channel->rd_buf_size = bytebufsize;
			channel->rd_allow_partial = allowpartial;
			channel->rd_synchronous = synchronous;
			channel->rd_exclusive_open = exclusive_open;
			channel->seekable = seekable;

			channel->rd_buffers = buffers;
			rc = xilly_get_dma_buffers(ep, &rd_alloc, buffers,
						   bufnum, bytebufsize);
		} else if (channelnum > 0) {
			channel->num_wr_buffers = bufnum;
			channel->wr_buf_size = bytebufsize;

			channel->seekable = seekable;
			channel->wr_supports_nonempty = supports_nonempty;

			channel->wr_allow_partial = allowpartial;
			channel->wr_synchronous = synchronous;
			channel->wr_exclusive_open = exclusive_open;

			channel->wr_buffers = buffers;
			rc = xilly_get_dma_buffers(ep, &wr_alloc, buffers,
						   bufnum, bytebufsize);
		} else {
			rc = xilly_get_dma_buffers(ep, &wr_alloc, NULL,
						   bufnum, bytebufsize);
			msg_buf_done++;
		}

		if (rc)
			return -ENOMEM;
	}

	if (!msg_buf_done) {
		dev_err(ep->dev,
			"Corrupt IDT: No message buffer. Aborting.\n");
		return -ENODEV;
	}
	return 0;
}

static int xilly_scan_idt(struct xilly_endpoint *endpoint,
			  struct xilly_idt_handle *idt_handle)
{
	int count = 0;
	unsigned char *idt = endpoint->channels[1]->wr_buffers[0]->addr;
	unsigned char *end_of_idt = idt + endpoint->idtlen - 4;
	unsigned char *scan;
	int len;

	scan = idt;
	idt_handle->idt = idt;

	scan++; /* Skip version number */

	while ((scan <= end_of_idt) && *scan) {
		while ((scan <= end_of_idt) && *scan++)
			/* Do nothing, just scan thru string */;
		count++;
	}

	scan++;

	if (scan > end_of_idt) {
		dev_err(endpoint->dev,
			"IDT device name list overflow. Aborting.\n");
		return -ENODEV;
	}
	idt_handle->chandesc = scan;

	len = endpoint->idtlen - (3 + ((int) (scan - idt)));

	if (len & 0x03) {
		dev_err(endpoint->dev,
			"Corrupt IDT device name list. Aborting.\n");
		return -ENODEV;
	}

	idt_handle->entries = len >> 2;
	endpoint->num_channels = count;

	return 0;
}

static int xilly_obtain_idt(struct xilly_endpoint *endpoint)
{
	struct xilly_channel *channel;
	unsigned char *version;
	long t;

	channel = endpoint->channels[1]; /* This should be generated ad-hoc */

	channel->wr_sleepy = 1;

	iowrite32(1 |
		  (3 << 24), /* Opcode 3 for channel 0 = Send IDT */
		  endpoint->registers + fpga_buf_ctrl_reg);

	t = wait_event_interruptible_timeout(channel->wr_wait,
					     (!channel->wr_sleepy),
					     XILLY_TIMEOUT);

	if (t <= 0) {
		dev_err(endpoint->dev, "Failed to obtain IDT. Aborting.\n");

		if (endpoint->fatal_error)
			return -EIO;

		return -ENODEV;
	}

	endpoint->ephw->hw_sync_sgl_for_cpu(
		channel->endpoint,
		channel->wr_buffers[0]->dma_addr,
		channel->wr_buf_size,
		DMA_FROM_DEVICE);

	if (channel->wr_buffers[0]->end_offset != endpoint->idtlen) {
		dev_err(endpoint->dev,
			"IDT length mismatch (%d != %d). Aborting.\n",
			channel->wr_buffers[0]->end_offset, endpoint->idtlen);
		return -ENODEV;
	}

	if (crc32_le(~0, channel->wr_buffers[0]->addr,
		     endpoint->idtlen+1) != 0) {
		dev_err(endpoint->dev, "IDT failed CRC check. Aborting.\n");
		return -ENODEV;
	}

	version = channel->wr_buffers[0]->addr;

	/* Check version number. Reject anything above 0x82. */
	if (*version > 0x82) {
		dev_err(endpoint->dev,
			"No support for IDT version 0x%02x. Maybe the xillybus driver needs an upgrade. Aborting.\n",
			*version);
		return -ENODEV;
	}

	return 0;
}

static ssize_t xillybus_read(struct file *filp, char __user *userbuf,
			     size_t count, loff_t *f_pos)
{
	ssize_t rc;
	unsigned long flags;
	int bytes_done = 0;
	int no_time_left = 0;
	long deadline, left_to_sleep;
	struct xilly_channel *channel = filp->private_data;

	int empty, reached_eof, exhausted, ready;
	/* Initializations are there only to silence warnings */

	int howmany = 0, bufpos = 0, bufidx = 0, bufferdone = 0;
	int waiting_bufidx;

	if (channel->endpoint->fatal_error)
		return -EIO;

	deadline = jiffies + 1 + XILLY_RX_TIMEOUT;

	rc = mutex_lock_interruptible(&channel->wr_mutex);
	if (rc)
		return rc;

	while (1) { /* Note that we may drop mutex within this loop */
		int bytes_to_do = count - bytes_done;

		spin_lock_irqsave(&channel->wr_spinlock, flags);

		empty = channel->wr_empty;
		ready = !empty || channel->wr_ready;

		if (!empty) {
			bufidx = channel->wr_host_buf_idx;
			bufpos = channel->wr_host_buf_pos;
			howmany = ((channel->wr_buffers[bufidx]->end_offset
				    + 1) << channel->log2_element_size)
				- bufpos;

			/* Update wr_host_* to its post-operation state */
			if (howmany > bytes_to_do) {
				bufferdone = 0;

				howmany = bytes_to_do;
				channel->wr_host_buf_pos += howmany;
			} else {
				bufferdone = 1;

				channel->wr_host_buf_pos = 0;

				if (bufidx == channel->wr_fpga_buf_idx) {
					channel->wr_empty = 1;
					channel->wr_sleepy = 1;
					channel->wr_ready = 0;
				}

				if (bufidx >= (channel->num_wr_buffers - 1))
					channel->wr_host_buf_idx = 0;
				else
					channel->wr_host_buf_idx++;
			}
		}

		/*
		 * Marking our situation after the possible changes above,
		 * for use after releasing the spinlock.
		 *
		 * empty = empty before change
		 * exhasted = empty after possible change
		 */

		reached_eof = channel->wr_empty &&
			(channel->wr_host_buf_idx == channel->wr_eof);
		channel->wr_hangup = reached_eof;
		exhausted = channel->wr_empty;
		waiting_bufidx = channel->wr_host_buf_idx;

		spin_unlock_irqrestore(&channel->wr_spinlock, flags);

		if (!empty) { /* Go on, now without the spinlock */

			if (bufpos == 0) /* Position zero means it's virgin */
				channel->endpoint->ephw->hw_sync_sgl_for_cpu(
					channel->endpoint,
					channel->wr_buffers[bufidx]->dma_addr,
					channel->wr_buf_size,
					DMA_FROM_DEVICE);

			if (copy_to_user(
				    userbuf,
				    channel->wr_buffers[bufidx]->addr
				    + bufpos, howmany))
				rc = -EFAULT;

			userbuf += howmany;
			bytes_done += howmany;

			if (bufferdone) {
				channel->endpoint->ephw->hw_sync_sgl_for_device(
					channel->endpoint,
					channel->wr_buffers[bufidx]->dma_addr,
					channel->wr_buf_size,
					DMA_FROM_DEVICE);

				/*
				 * Tell FPGA the buffer is done with. It's an
				 * atomic operation to the FPGA, so what
				 * happens with other channels doesn't matter,
				 * and the certain channel is protected with
				 * the channel-specific mutex.
				 */

				iowrite32(1 | (channel->chan_num << 1) |
					  (bufidx << 12),
					  channel->endpoint->registers +
					  fpga_buf_ctrl_reg);
			}

			if (rc) {
				mutex_unlock(&channel->wr_mutex);
				return rc;
			}
		}

		/* This includes a zero-count return = EOF */
		if ((bytes_done >= count) || reached_eof)
			break;

		if (!exhausted)
			continue; /* More in RAM buffer(s)? Just go on. */

		if ((bytes_done > 0) &&
		    (no_time_left ||
		     (channel->wr_synchronous && channel->wr_allow_partial)))
			break;

		/*
		 * Nonblocking read: The "ready" flag tells us that the FPGA
		 * has data to send. In non-blocking mode, if it isn't on,
		 * just return. But if there is, we jump directly to the point
		 * where we ask for the FPGA to send all it has, and wait
		 * until that data arrives. So in a sense, we *do* block in
		 * nonblocking mode, but only for a very short time.
		 */

		if (!no_time_left && (filp->f_flags & O_NONBLOCK)) {
			if (bytes_done > 0)
				break;

			if (ready)
				goto desperate;

			rc = -EAGAIN;
			break;
		}

		if (!no_time_left || (bytes_done > 0)) {
			/*
			 * Note that in case of an element-misaligned read
			 * request, offsetlimit will include the last element,
			 * which will be partially read from.
			 */
			int offsetlimit = ((count - bytes_done) - 1) >>
				channel->log2_element_size;
			int buf_elements = channel->wr_buf_size >>
				channel->log2_element_size;

			/*
			 * In synchronous mode, always send an offset limit.
			 * Just don't send a value too big.
			 */

			if (channel->wr_synchronous) {
				/* Don't request more than one buffer */
				if (channel->wr_allow_partial &&
				    (offsetlimit >= buf_elements))
					offsetlimit = buf_elements - 1;

				/* Don't request more than all buffers */
				if (!channel->wr_allow_partial &&
				    (offsetlimit >=
				     (buf_elements * channel->num_wr_buffers)))
					offsetlimit = buf_elements *
						channel->num_wr_buffers - 1;
			}

			/*
			 * In asynchronous mode, force early flush of a buffer
			 * only if that will allow returning a full count. The
			 * "offsetlimit < ( ... )" rather than "<=" excludes
			 * requesting a full buffer, which would obviously
			 * cause a buffer transmission anyhow
			 */

			if (channel->wr_synchronous ||
			    (offsetlimit < (buf_elements - 1))) {
				mutex_lock(&channel->endpoint->register_mutex);

				iowrite32(offsetlimit,
					  channel->endpoint->registers +
					  fpga_buf_offset_reg);

				iowrite32(1 | (channel->chan_num << 1) |
					  (2 << 24) |  /* 2 = offset limit */
					  (waiting_bufidx << 12),
					  channel->endpoint->registers +
					  fpga_buf_ctrl_reg);

				mutex_unlock(&channel->endpoint->
					     register_mutex);
			}
		}

		/*
		 * If partial completion is disallowed, there is no point in
		 * timeout sleeping. Neither if no_time_left is set and
		 * there's no data.
		 */

		if (!channel->wr_allow_partial ||
		    (no_time_left && (bytes_done == 0))) {
			/*
			 * This do-loop will run more than once if another
			 * thread reasserted wr_sleepy before we got the mutex
			 * back, so we try again.
			 */

			do {
				mutex_unlock(&channel->wr_mutex);

				if (wait_event_interruptible(
					    channel->wr_wait,
					    (!channel->wr_sleepy)))
					goto interrupted;

				if (mutex_lock_interruptible(
					    &channel->wr_mutex))
					goto interrupted;
			} while (channel->wr_sleepy);

			continue;

interrupted: /* Mutex is not held if got here */
			if (channel->endpoint->fatal_error)
				return -EIO;
			if (bytes_done)
				return bytes_done;
			if (filp->f_flags & O_NONBLOCK)
				return -EAGAIN; /* Don't admit snoozing */
			return -EINTR;
		}

		left_to_sleep = deadline - ((long) jiffies);

		/*
		 * If our time is out, skip the waiting. We may miss wr_sleepy
		 * being deasserted but hey, almost missing the train is like
		 * missing it.
		 */

		if (left_to_sleep > 0) {
			left_to_sleep =
				wait_event_interruptible_timeout(
					channel->wr_wait,
					(!channel->wr_sleepy),
					left_to_sleep);

			if (left_to_sleep > 0) /* wr_sleepy deasserted */
				continue;

			if (left_to_sleep < 0) { /* Interrupt */
				mutex_unlock(&channel->wr_mutex);
				if (channel->endpoint->fatal_error)
					return -EIO;
				if (bytes_done)
					return bytes_done;
				return -EINTR;
			}
		}

desperate:
		no_time_left = 1; /* We're out of sleeping time. Desperate! */

		if (bytes_done == 0) {
			/*
			 * Reaching here means that we allow partial return,
			 * that we've run out of time, and that we have
			 * nothing to return.
			 * So tell the FPGA to send anything it has or gets.
			 */

			iowrite32(1 | (channel->chan_num << 1) |
				  (3 << 24) |  /* Opcode 3, flush it all! */
				  (waiting_bufidx << 12),
				  channel->endpoint->registers +
				  fpga_buf_ctrl_reg);
		}

		/*
		 * Reaching here means that we *do* have data in the buffer,
		 * but the "partial" flag disallows returning less than
		 * required. And we don't have as much. So loop again,
		 * which is likely to end up blocking indefinitely until
		 * enough data has arrived.
		 */
	}

	mutex_unlock(&channel->wr_mutex);

	if (channel->endpoint->fatal_error)
		return -EIO;

	if (rc)
		return rc;

	return bytes_done;
}

/*
 * The timeout argument takes values as follows:
 *  >0 : Flush with timeout
 * ==0 : Flush, and wait idefinitely for the flush to complete
 *  <0 : Autoflush: Flush only if there's a single buffer occupied
 */

static int xillybus_myflush(struct xilly_channel *channel, long timeout)
{
	int rc;
	unsigned long flags;

	int end_offset_plus1;
	int bufidx, bufidx_minus1;
	int i;
	int empty;
	int new_rd_host_buf_pos;

	if (channel->endpoint->fatal_error)
		return -EIO;
	rc = mutex_lock_interruptible(&channel->rd_mutex);
	if (rc)
		return rc;

	/*
	 * Don't flush a closed channel. This can happen when the work queued
	 * autoflush thread fires off after the file has closed. This is not
	 * an error, just something to dismiss.
	 */

	if (!channel->rd_ref_count)
		goto done;

	bufidx = channel->rd_host_buf_idx;

	bufidx_minus1 = (bufidx == 0) ?
		channel->num_rd_buffers - 1 :
		bufidx - 1;

	end_offset_plus1 = channel->rd_host_buf_pos >>
		channel->log2_element_size;

	new_rd_host_buf_pos = channel->rd_host_buf_pos -
		(end_offset_plus1 << channel->log2_element_size);

	/* Submit the current buffer if it's nonempty */
	if (end_offset_plus1) {
		unsigned char *tail = channel->rd_buffers[bufidx]->addr +
			(end_offset_plus1 << channel->log2_element_size);

		/* Copy  unflushed data, so we can put it in next buffer */
		for (i = 0; i < new_rd_host_buf_pos; i++)
			channel->rd_leftovers[i] = *tail++;

		spin_lock_irqsave(&channel->rd_spinlock, flags);

		/* Autoflush only if a single buffer is occupied */

		if ((timeout < 0) &&
		    (channel->rd_full ||
		     (bufidx_minus1 != channel->rd_fpga_buf_idx))) {
			spin_unlock_irqrestore(&channel->rd_spinlock, flags);
			/*
			 * A new work item may be queued by the ISR exactly
			 * now, since the execution of a work item allows the
			 * queuing of a new one while it's running.
			 */
			goto done;
		}

		/* The 4th element is never needed for data, so it's a flag */
		channel->rd_leftovers[3] = (new_rd_host_buf_pos != 0);

		/* Set up rd_full to reflect a certain moment's state */

		if (bufidx == channel->rd_fpga_buf_idx)
			channel->rd_full = 1;
		spin_unlock_irqrestore(&channel->rd_spinlock, flags);

		if (bufidx >= (channel->num_rd_buffers - 1))
			channel->rd_host_buf_idx = 0;
		else
			channel->rd_host_buf_idx++;

		channel->endpoint->ephw->hw_sync_sgl_for_device(
			channel->endpoint,
			channel->rd_buffers[bufidx]->dma_addr,
			channel->rd_buf_size,
			DMA_TO_DEVICE);

		mutex_lock(&channel->endpoint->register_mutex);

		iowrite32(end_offset_plus1 - 1,
			  channel->endpoint->registers + fpga_buf_offset_reg);

		iowrite32((channel->chan_num << 1) | /* Channel ID */
			  (2 << 24) |  /* Opcode 2, submit buffer */
			  (bufidx << 12),
			  channel->endpoint->registers + fpga_buf_ctrl_reg);

		mutex_unlock(&channel->endpoint->register_mutex);
	} else if (bufidx == 0) {
		bufidx = channel->num_rd_buffers - 1;
	} else {
		bufidx--;
	}

	channel->rd_host_buf_pos = new_rd_host_buf_pos;

	if (timeout < 0)
		goto done; /* Autoflush */

	/*
	 * bufidx is now the last buffer written to (or equal to
	 * rd_fpga_buf_idx if buffer was never written to), and
	 * channel->rd_host_buf_idx the one after it.
	 *
	 * If bufidx == channel->rd_fpga_buf_idx we're either empty or full.
	 */

	while (1) { /* Loop waiting for draining of buffers */
		spin_lock_irqsave(&channel->rd_spinlock, flags);

		if (bufidx != channel->rd_fpga_buf_idx)
			channel->rd_full = 1; /*
					       * Not really full,
					       * but needs waiting.
					       */

		empty = !channel->rd_full;

		spin_unlock_irqrestore(&channel->rd_spinlock, flags);

		if (empty)
			break;

		/*
		 * Indefinite sleep with mutex taken. With data waiting for
		 * flushing user should not be surprised if open() for write
		 * sleeps.
		 */
		if (timeout == 0)
			wait_event_interruptible(channel->rd_wait,
						 (!channel->rd_full));

		else if (wait_event_interruptible_timeout(
				 channel->rd_wait,
				 (!channel->rd_full),
				 timeout) == 0) {
			dev_warn(channel->endpoint->dev,
				 "Timed out while flushing. Output data may be lost.\n");

			rc = -ETIMEDOUT;
			break;
		}

		if (channel->rd_full) {
			rc = -EINTR;
			break;
		}
	}

done:
	mutex_unlock(&channel->rd_mutex);

	if (channel->endpoint->fatal_error)
		return -EIO;

	return rc;
}

static int xillybus_flush(struct file *filp, fl_owner_t id)
{
	if (!(filp->f_mode & FMODE_WRITE))
		return 0;

	return xillybus_myflush(filp->private_data, HZ); /* 1 second timeout */
}

static void xillybus_autoflush(struct work_struct *work)
{
	struct delayed_work *workitem = container_of(
		work, struct delayed_work, work);
	struct xilly_channel *channel = container_of(
		workitem, struct xilly_channel, rd_workitem);
	int rc;

	rc = xillybus_myflush(channel, -1);
	if (rc == -EINTR)
		dev_warn(channel->endpoint->dev,
			 "Autoflush failed because work queue thread got a signal.\n");
	else if (rc)
		dev_err(channel->endpoint->dev,
			"Autoflush failed under weird circumstances.\n");
}

static ssize_t xillybus_write(struct file *filp, const char __user *userbuf,
			      size_t count, loff_t *f_pos)
{
	ssize_t rc;
	unsigned long flags;
	int bytes_done = 0;
	struct xilly_channel *channel = filp->private_data;

	int full, exhausted;
	/* Initializations are there only to silence warnings */

	int howmany = 0, bufpos = 0, bufidx = 0, bufferdone = 0;
	int end_offset_plus1 = 0;

	if (channel->endpoint->fatal_error)
		return -EIO;

	rc = mutex_lock_interruptible(&channel->rd_mutex);
	if (rc)
		return rc;

	while (1) {
		int bytes_to_do = count - bytes_done;

		spin_lock_irqsave(&channel->rd_spinlock, flags);

		full = channel->rd_full;

		if (!full) {
			bufidx = channel->rd_host_buf_idx;
			bufpos = channel->rd_host_buf_pos;
			howmany = channel->rd_buf_size - bufpos;

			/*
			 * Update rd_host_* to its state after this operation.
			 * count=0 means committing the buffer immediately,
			 * which is like flushing, but not necessarily block.
			 */

			if ((howmany > bytes_to_do) &&
			    (count ||
			     ((bufpos >> channel->log2_element_size) == 0))) {
				bufferdone = 0;

				howmany = bytes_to_do;
				channel->rd_host_buf_pos += howmany;
			} else {
				bufferdone = 1;

				if (count) {
					end_offset_plus1 =
						channel->rd_buf_size >>
						channel->log2_element_size;
					channel->rd_host_buf_pos = 0;
				} else {
					unsigned char *tail;
					int i;

					howmany = 0;

					end_offset_plus1 = bufpos >>
						channel->log2_element_size;

					channel->rd_host_buf_pos -=
						end_offset_plus1 <<
						channel->log2_element_size;

					tail = channel->
						rd_buffers[bufidx]->addr +
						(end_offset_plus1 <<
						 channel->log2_element_size);

					for (i = 0;
					     i < channel->rd_host_buf_pos;
					     i++)
						channel->rd_leftovers[i] =
							*tail++;
				}

				if (bufidx == channel->rd_fpga_buf_idx)
					channel->rd_full = 1;

				if (bufidx >= (channel->num_rd_buffers - 1))
					channel->rd_host_buf_idx = 0;
				else
					channel->rd_host_buf_idx++;
			}
		}

		/*
		 * Marking our situation after the possible changes above,
		 * for use  after releasing the spinlock.
		 *
		 * full = full before change
		 * exhasted = full after possible change
		 */

		exhausted = channel->rd_full;

		spin_unlock_irqrestore(&channel->rd_spinlock, flags);

		if (!full) { /* Go on, now without the spinlock */
			unsigned char *head =
				channel->rd_buffers[bufidx]->addr;
			int i;

			if ((bufpos == 0) || /* Zero means it's virgin */
			    (channel->rd_leftovers[3] != 0)) {
				channel->endpoint->ephw->hw_sync_sgl_for_cpu(
					channel->endpoint,
					channel->rd_buffers[bufidx]->dma_addr,
					channel->rd_buf_size,
					DMA_TO_DEVICE);

				/* Virgin, but leftovers are due */
				for (i = 0; i < bufpos; i++)
					*head++ = channel->rd_leftovers[i];

				channel->rd_leftovers[3] = 0; /* Clear flag */
			}

			if (copy_from_user(
				    channel->rd_buffers[bufidx]->addr + bufpos,
				    userbuf, howmany))
				rc = -EFAULT;

			userbuf += howmany;
			bytes_done += howmany;

			if (bufferdone) {
				channel->endpoint->ephw->hw_sync_sgl_for_device(
					channel->endpoint,
					channel->rd_buffers[bufidx]->dma_addr,
					channel->rd_buf_size,
					DMA_TO_DEVICE);

				mutex_lock(&channel->endpoint->register_mutex);

				iowrite32(end_offset_plus1 - 1,
					  channel->endpoint->registers +
					  fpga_buf_offset_reg);

				iowrite32((channel->chan_num << 1) |
					  (2 << 24) |  /* 2 = submit buffer */
					  (bufidx << 12),
					  channel->endpoint->registers +
					  fpga_buf_ctrl_reg);

				mutex_unlock(&channel->endpoint->
					     register_mutex);

				channel->rd_leftovers[3] =
					(channel->rd_host_buf_pos != 0);
			}

			if (rc) {
				mutex_unlock(&channel->rd_mutex);

				if (channel->endpoint->fatal_error)
					return -EIO;

				if (!channel->rd_synchronous)
					queue_delayed_work(
						xillybus_wq,
						&channel->rd_workitem,
						XILLY_RX_TIMEOUT);

				return rc;
			}
		}

		if (bytes_done >= count)
			break;

		if (!exhausted)
			continue; /* If there's more space, just go on */

		if ((bytes_done > 0) && channel->rd_allow_partial)
			break;

		/*
		 * Indefinite sleep with mutex taken. With data waiting for
		 * flushing, user should not be surprised if open() for write
		 * sleeps.
		 */

		if (filp->f_flags & O_NONBLOCK) {
			rc = -EAGAIN;
			break;
		}

		if (wait_event_interruptible(channel->rd_wait,
					     (!channel->rd_full))) {
			mutex_unlock(&channel->rd_mutex);

			if (channel->endpoint->fatal_error)
				return -EIO;

			if (bytes_done)
				return bytes_done;
			return -EINTR;
		}
	}

	mutex_unlock(&channel->rd_mutex);

	if (!channel->rd_synchronous)
		queue_delayed_work(xillybus_wq,
				   &channel->rd_workitem,
				   XILLY_RX_TIMEOUT);

	if (channel->endpoint->fatal_error)
		return -EIO;

	if (rc)
		return rc;

	if ((channel->rd_synchronous) && (bytes_done > 0)) {
		rc = xillybus_myflush(filp->private_data, 0); /* No timeout */

		if (rc && (rc != -EINTR))
			return rc;
	}

	return bytes_done;
}

static int xillybus_open(struct inode *inode, struct file *filp)
{
	int rc = 0;
	unsigned long flags;
	int minor = iminor(inode);
	int major = imajor(inode);
	struct xilly_endpoint *ep_iter, *endpoint = NULL;
	struct xilly_channel *channel;

	mutex_lock(&ep_list_lock);

	list_for_each_entry(ep_iter, &list_of_endpoints, ep_list) {
		if ((ep_iter->major == major) &&
		    (minor >= ep_iter->lowest_minor) &&
		    (minor < (ep_iter->lowest_minor +
			      ep_iter->num_channels))) {
			endpoint = ep_iter;
			break;
		}
	}
	mutex_unlock(&ep_list_lock);

	if (!endpoint) {
		pr_err("xillybus: open() failed to find a device for major=%d and minor=%d\n",
		       major, minor);
		return -ENODEV;
	}

	if (endpoint->fatal_error)
		return -EIO;

	channel = endpoint->channels[1 + minor - endpoint->lowest_minor];
	filp->private_data = channel;

	/*
	 * It gets complicated because:
	 * 1. We don't want to take a mutex we don't have to
	 * 2. We don't want to open one direction if the other will fail.
	 */

	if ((filp->f_mode & FMODE_READ) && (!channel->num_wr_buffers))
		return -ENODEV;

	if ((filp->f_mode & FMODE_WRITE) && (!channel->num_rd_buffers))
		return -ENODEV;

	if ((filp->f_mode & FMODE_READ) && (filp->f_flags & O_NONBLOCK) &&
	    (channel->wr_synchronous || !channel->wr_allow_partial ||
	     !channel->wr_supports_nonempty)) {
		dev_err(endpoint->dev,
			"open() failed: O_NONBLOCK not allowed for read on this device\n");
		return -ENODEV;
	}

	if ((filp->f_mode & FMODE_WRITE) && (filp->f_flags & O_NONBLOCK) &&
	    (channel->rd_synchronous || !channel->rd_allow_partial)) {
		dev_err(endpoint->dev,
			"open() failed: O_NONBLOCK not allowed for write on this device\n");
		return -ENODEV;
	}

	/*
	 * Note: open() may block on getting mutexes despite O_NONBLOCK.
	 * This shouldn't occur normally, since multiple open of the same
	 * file descriptor is almost always prohibited anyhow
	 * (*_exclusive_open is normally set in real-life systems).
	 */

	if (filp->f_mode & FMODE_READ) {
		rc = mutex_lock_interruptible(&channel->wr_mutex);
		if (rc)
			return rc;
	}

	if (filp->f_mode & FMODE_WRITE) {
		rc = mutex_lock_interruptible(&channel->rd_mutex);
		if (rc)
			goto unlock_wr;
	}

	if ((filp->f_mode & FMODE_READ) &&
	    (channel->wr_ref_count != 0) &&
	    (channel->wr_exclusive_open)) {
		rc = -EBUSY;
		goto unlock;
	}

	if ((filp->f_mode & FMODE_WRITE) &&
	    (channel->rd_ref_count != 0) &&
	    (channel->rd_exclusive_open)) {
		rc = -EBUSY;
		goto unlock;
	}

	if (filp->f_mode & FMODE_READ) {
		if (channel->wr_ref_count == 0) { /* First open of file */
			/* Move the host to first buffer */
			spin_lock_irqsave(&channel->wr_spinlock, flags);
			channel->wr_host_buf_idx = 0;
			channel->wr_host_buf_pos = 0;
			channel->wr_fpga_buf_idx = -1;
			channel->wr_empty = 1;
			channel->wr_ready = 0;
			channel->wr_sleepy = 1;
			channel->wr_eof = -1;
			channel->wr_hangup = 0;

			spin_unlock_irqrestore(&channel->wr_spinlock, flags);

			iowrite32(1 | (channel->chan_num << 1) |
				  (4 << 24) |  /* Opcode 4, open channel */
				  ((channel->wr_synchronous & 1) << 23),
				  channel->endpoint->registers +
				  fpga_buf_ctrl_reg);
		}

		channel->wr_ref_count++;
	}

	if (filp->f_mode & FMODE_WRITE) {
		if (channel->rd_ref_count == 0) { /* First open of file */
			/* Move the host to first buffer */
			spin_lock_irqsave(&channel->rd_spinlock, flags);
			channel->rd_host_buf_idx = 0;
			channel->rd_host_buf_pos = 0;
			channel->rd_leftovers[3] = 0; /* No leftovers. */
			channel->rd_fpga_buf_idx = channel->num_rd_buffers - 1;
			channel->rd_full = 0;

			spin_unlock_irqrestore(&channel->rd_spinlock, flags);

			iowrite32((channel->chan_num << 1) |
				  (4 << 24),   /* Opcode 4, open channel */
				  channel->endpoint->registers +
				  fpga_buf_ctrl_reg);
		}

		channel->rd_ref_count++;
	}

unlock:
	if (filp->f_mode & FMODE_WRITE)
		mutex_unlock(&channel->rd_mutex);
unlock_wr:
	if (filp->f_mode & FMODE_READ)
		mutex_unlock(&channel->wr_mutex);

	if (!rc && (!channel->seekable))
		return nonseekable_open(inode, filp);

	return rc;
}

static int xillybus_release(struct inode *inode, struct file *filp)
{
	unsigned long flags;
	struct xilly_channel *channel = filp->private_data;

	int buf_idx;
	int eof;

	if (channel->endpoint->fatal_error)
		return -EIO;

	if (filp->f_mode & FMODE_WRITE) {
		mutex_lock(&channel->rd_mutex);

		channel->rd_ref_count--;

		if (channel->rd_ref_count == 0) {
			/*
			 * We rely on the kernel calling flush()
			 * before we get here.
			 */

			iowrite32((channel->chan_num << 1) | /* Channel ID */
				  (5 << 24),  /* Opcode 5, close channel */
				  channel->endpoint->registers +
				  fpga_buf_ctrl_reg);
		}
		mutex_unlock(&channel->rd_mutex);
	}

	if (filp->f_mode & FMODE_READ) {
		mutex_lock(&channel->wr_mutex);

		channel->wr_ref_count--;

		if (channel->wr_ref_count == 0) {
			iowrite32(1 | (channel->chan_num << 1) |
				  (5 << 24),  /* Opcode 5, close channel */
				  channel->endpoint->registers +
				  fpga_buf_ctrl_reg);

			/*
			 * This is crazily cautious: We make sure that not
			 * only that we got an EOF (be it because we closed
			 * the channel or because of a user's EOF), but verify
			 * that it's one beyond the last buffer arrived, so
			 * we have no leftover buffers pending before wrapping
			 * up (which can only happen in asynchronous channels,
			 * BTW)
			 */

			while (1) {
				spin_lock_irqsave(&channel->wr_spinlock,
						  flags);
				buf_idx = channel->wr_fpga_buf_idx;
				eof = channel->wr_eof;
				channel->wr_sleepy = 1;
				spin_unlock_irqrestore(&channel->wr_spinlock,
						       flags);

				/*
				 * Check if eof points at the buffer after
				 * the last one the FPGA submitted. Note that
				 * no EOF is marked by negative eof.
				 */

				buf_idx++;
				if (buf_idx == channel->num_wr_buffers)
					buf_idx = 0;

				if (buf_idx == eof)
					break;

				/*
				 * Steal extra 100 ms if awaken by interrupt.
				 * This is a simple workaround for an
				 * interrupt pending when entering, which would
				 * otherwise result in declaring the hardware
				 * non-responsive.
				 */

				if (wait_event_interruptible(
					    channel->wr_wait,
					    (!channel->wr_sleepy)))
					msleep(100);

				if (channel->wr_sleepy) {
					mutex_unlock(&channel->wr_mutex);
					dev_warn(channel->endpoint->dev,
						 "Hardware failed to respond to close command, therefore left in messy state.\n");
					return -EINTR;
				}
			}
		}

		mutex_unlock(&channel->wr_mutex);
	}

	return 0;
}

static loff_t xillybus_llseek(struct file *filp, loff_t offset, int whence)
{
	struct xilly_channel *channel = filp->private_data;
	loff_t pos = filp->f_pos;
	int rc = 0;

	/*
	 * Take both mutexes not allowing interrupts, since it seems like
	 * common applications don't expect an -EINTR here. Besides, multiple
	 * access to a single file descriptor on seekable devices is a mess
	 * anyhow.
	 */

	if (channel->endpoint->fatal_error)
		return -EIO;

	mutex_lock(&channel->wr_mutex);
	mutex_lock(&channel->rd_mutex);

	switch (whence) {
	case SEEK_SET:
		pos = offset;
		break;
	case SEEK_CUR:
		pos += offset;
		break;
	case SEEK_END:
		pos = offset; /* Going to the end => to the beginning */
		break;
	default:
		rc = -EINVAL;
		goto end;
	}

	/* In any case, we must finish on an element boundary */
	if (pos & ((1 << channel->log2_element_size) - 1)) {
		rc = -EINVAL;
		goto end;
	}

	mutex_lock(&channel->endpoint->register_mutex);

	iowrite32(pos >> channel->log2_element_size,
		  channel->endpoint->registers + fpga_buf_offset_reg);

	iowrite32((channel->chan_num << 1) |
		  (6 << 24),  /* Opcode 6, set address */
		  channel->endpoint->registers + fpga_buf_ctrl_reg);

	mutex_unlock(&channel->endpoint->register_mutex);

end:
	mutex_unlock(&channel->rd_mutex);
	mutex_unlock(&channel->wr_mutex);

	if (rc) /* Return error after releasing mutexes */
		return rc;

	filp->f_pos = pos;

	/*
	 * Since seekable devices are allowed only when the channel is
	 * synchronous, we assume that there is no data pending in either
	 * direction (which holds true as long as no concurrent access on the
	 * file descriptor takes place).
	 * The only thing we may need to throw away is leftovers from partial
	 * write() flush.
	 */

	channel->rd_leftovers[3] = 0;

	return pos;
}

static __poll_t xillybus_poll(struct file *filp, poll_table *wait)
{
	struct xilly_channel *channel = filp->private_data;
	__poll_t mask = 0;
	unsigned long flags;

	poll_wait(filp, &channel->endpoint->ep_wait, wait);

	/*
	 * poll() won't play ball regarding read() channels which
	 * aren't asynchronous and support the nonempty message. Allowing
	 * that will create situations where data has been delivered at
	 * the FPGA, and users expecting select() to wake up, which it may
	 * not.
	 */

	if (!channel->wr_synchronous && channel->wr_supports_nonempty) {
		poll_wait(filp, &channel->wr_wait, wait);
		poll_wait(filp, &channel->wr_ready_wait, wait);

		spin_lock_irqsave(&channel->wr_spinlock, flags);
		if (!channel->wr_empty || channel->wr_ready)
			mask |= EPOLLIN | EPOLLRDNORM;

		if (channel->wr_hangup)
			/*
			 * Not EPOLLHUP, because its behavior is in the
			 * mist, and EPOLLIN does what we want: Wake up
			 * the read file descriptor so it sees EOF.
			 */
			mask |=  EPOLLIN | EPOLLRDNORM;
		spin_unlock_irqrestore(&channel->wr_spinlock, flags);
	}

	/*
	 * If partial data write is disallowed on a write() channel,
	 * it's pointless to ever signal OK to write, because is could
	 * block despite some space being available.
	 */

	if (channel->rd_allow_partial) {
		poll_wait(filp, &channel->rd_wait, wait);

		spin_lock_irqsave(&channel->rd_spinlock, flags);
		if (!channel->rd_full)
			mask |= EPOLLOUT | EPOLLWRNORM;
		spin_unlock_irqrestore(&channel->rd_spinlock, flags);
	}

	if (channel->endpoint->fatal_error)
		mask |= EPOLLERR;

	return mask;
}

static const struct file_operations xillybus_fops = {
	.owner      = THIS_MODULE,
	.read       = xillybus_read,
	.write      = xillybus_write,
	.open       = xillybus_open,
	.flush      = xillybus_flush,
	.release    = xillybus_release,
	.llseek     = xillybus_llseek,
	.poll       = xillybus_poll,
};

static int xillybus_init_chrdev(struct xilly_endpoint *endpoint,
				const unsigned char *idt)
{
	int rc;
	dev_t dev;
	int devnum, i, minor, major;
	char devname[48];
	struct device *device;

	rc = alloc_chrdev_region(&dev, 0, /* minor start */
				 endpoint->num_channels,
				 xillyname);
	if (rc) {
		dev_warn(endpoint->dev, "Failed to obtain major/minors");
		return rc;
	}

	endpoint->major = major = MAJOR(dev);
	endpoint->lowest_minor = minor = MINOR(dev);

	cdev_init(&endpoint->cdev, &xillybus_fops);
	endpoint->cdev.owner = endpoint->ephw->owner;
	rc = cdev_add(&endpoint->cdev, MKDEV(major, minor),
		      endpoint->num_channels);
	if (rc) {
		dev_warn(endpoint->dev, "Failed to add cdev. Aborting.\n");
		goto unregister_chrdev;
	}

	idt++;

	for (i = minor, devnum = 0;
	     devnum < endpoint->num_channels;
	     devnum++, i++) {
		snprintf(devname, sizeof(devname)-1, "xillybus_%s", idt);

		devname[sizeof(devname)-1] = 0; /* Should never matter */

		while (*idt++)
			/* Skip to next */;

		device = device_create(xillybus_class,
				       NULL,
				       MKDEV(major, i),
				       NULL,
				       "%s", devname);

		if (IS_ERR(device)) {
			dev_warn(endpoint->dev,
				 "Failed to create %s device. Aborting.\n",
				 devname);
			rc = -ENODEV;
			goto unroll_device_create;
		}
	}

	dev_info(endpoint->dev, "Created %d device files.\n",
		 endpoint->num_channels);
	return 0; /* succeed */

unroll_device_create:
	devnum--; i--;
	for (; devnum >= 0; devnum--, i--)
		device_destroy(xillybus_class, MKDEV(major, i));

	cdev_del(&endpoint->cdev);
unregister_chrdev:
	unregister_chrdev_region(MKDEV(major, minor), endpoint->num_channels);

	return rc;
}

static void xillybus_cleanup_chrdev(struct xilly_endpoint *endpoint)
{
	int minor;

	for (minor = endpoint->lowest_minor;
	     minor < (endpoint->lowest_minor + endpoint->num_channels);
	     minor++)
		device_destroy(xillybus_class, MKDEV(endpoint->major, minor));
	cdev_del(&endpoint->cdev);
	unregister_chrdev_region(MKDEV(endpoint->major,
				       endpoint->lowest_minor),
				 endpoint->num_channels);

	dev_info(endpoint->dev, "Removed %d device files.\n",
		 endpoint->num_channels);
}

struct xilly_endpoint *xillybus_init_endpoint(struct pci_dev *pdev,
					      struct device *dev,
					      struct xilly_endpoint_hardware
					      *ephw)
{
	struct xilly_endpoint *endpoint;

	endpoint = devm_kzalloc(dev, sizeof(*endpoint), GFP_KERNEL);
	if (!endpoint)
		return NULL;

	endpoint->pdev = pdev;
	endpoint->dev = dev;
	endpoint->ephw = ephw;
	endpoint->msg_counter = 0x0b;
	endpoint->failed_messages = 0;
	endpoint->fatal_error = 0;

	init_waitqueue_head(&endpoint->ep_wait);
	mutex_init(&endpoint->register_mutex);

	return endpoint;
}
EXPORT_SYMBOL(xillybus_init_endpoint);

static int xilly_quiesce(struct xilly_endpoint *endpoint)
{
	long t;

	endpoint->idtlen = -1;

	iowrite32((u32) (endpoint->dma_using_dac & 0x0001),
		  endpoint->registers + fpga_dma_control_reg);

	t = wait_event_interruptible_timeout(endpoint->ep_wait,
					     (endpoint->idtlen >= 0),
					     XILLY_TIMEOUT);
	if (t <= 0) {
		dev_err(endpoint->dev,
			"Failed to quiesce the device on exit.\n");
		return -ENODEV;
	}
	return 0;
}

int xillybus_endpoint_discovery(struct xilly_endpoint *endpoint)
{
	int rc;
	long t;

	void *bootstrap_resources;
	int idtbuffersize = (1 << PAGE_SHIFT);
	struct device *dev = endpoint->dev;

	/*
	 * The bogus IDT is used during bootstrap for allocating the initial
	 * message buffer, and then the message buffer and space for the IDT
	 * itself. The initial message buffer is of a single page's size, but
	 * it's soon replaced with a more modest one (and memory is freed).
	 */

	unsigned char bogus_idt[8] = { 1, 224, (PAGE_SHIFT)-2, 0,
				       3, 192, PAGE_SHIFT, 0 };
	struct xilly_idt_handle idt_handle;

	/*
	 * Writing the value 0x00000001 to Endianness register signals which
	 * endianness this processor is using, so the FPGA can swap words as
	 * necessary.
	 */

	iowrite32(1, endpoint->registers + fpga_endian_reg);

	/* Bootstrap phase I: Allocate temporary message buffer */

	bootstrap_resources = devres_open_group(dev, NULL, GFP_KERNEL);
	if (!bootstrap_resources)
		return -ENOMEM;

	endpoint->num_channels = 0;

	rc = xilly_setupchannels(endpoint, bogus_idt, 1);
	if (rc)
		return rc;

	/* Clear the message subsystem (and counter in particular) */
	iowrite32(0x04, endpoint->registers + fpga_msg_ctrl_reg);

	endpoint->idtlen = -1;

	/*
	 * Set DMA 32/64 bit mode, quiesce the device (?!) and get IDT
	 * buffer size.
	 */
	iowrite32((u32) (endpoint->dma_using_dac & 0x0001),
		  endpoint->registers + fpga_dma_control_reg);

	t = wait_event_interruptible_timeout(endpoint->ep_wait,
					     (endpoint->idtlen >= 0),
					     XILLY_TIMEOUT);
	if (t <= 0) {
		dev_err(endpoint->dev, "No response from FPGA. Aborting.\n");
		return -ENODEV;
	}

	/* Enable DMA */
	iowrite32((u32) (0x0002 | (endpoint->dma_using_dac & 0x0001)),
		  endpoint->registers + fpga_dma_control_reg);

	/* Bootstrap phase II: Allocate buffer for IDT and obtain it */
	while (endpoint->idtlen >= idtbuffersize) {
		idtbuffersize *= 2;
		bogus_idt[6]++;
	}

	endpoint->num_channels = 1;

	rc = xilly_setupchannels(endpoint, bogus_idt, 2);
	if (rc)
		goto failed_idt;

	rc = xilly_obtain_idt(endpoint);
	if (rc)
		goto failed_idt;

	rc = xilly_scan_idt(endpoint, &idt_handle);
	if (rc)
		goto failed_idt;

	devres_close_group(dev, bootstrap_resources);

	/* Bootstrap phase III: Allocate buffers according to IDT */

	rc = xilly_setupchannels(endpoint,
				 idt_handle.chandesc,
				 idt_handle.entries);
	if (rc)
		goto failed_idt;

	/*
	 * endpoint is now completely configured. We put it on the list
	 * available to open() before registering the char device(s)
	 */

	mutex_lock(&ep_list_lock);
	list_add_tail(&endpoint->ep_list, &list_of_endpoints);
	mutex_unlock(&ep_list_lock);

	rc = xillybus_init_chrdev(endpoint, idt_handle.idt);
	if (rc)
		goto failed_chrdevs;

	devres_release_group(dev, bootstrap_resources);

	return 0;

failed_chrdevs:
	mutex_lock(&ep_list_lock);
	list_del(&endpoint->ep_list);
	mutex_unlock(&ep_list_lock);

failed_idt:
	xilly_quiesce(endpoint);
	flush_workqueue(xillybus_wq);

	return rc;
}
EXPORT_SYMBOL(xillybus_endpoint_discovery);

void xillybus_endpoint_remove(struct xilly_endpoint *endpoint)
{
	xillybus_cleanup_chrdev(endpoint);

	mutex_lock(&ep_list_lock);
	list_del(&endpoint->ep_list);
	mutex_unlock(&ep_list_lock);

	xilly_quiesce(endpoint);

	/*
	 * Flushing is done upon endpoint release to prevent access to memory
	 * just about to be released. This makes the quiesce complete.
	 */
	flush_workqueue(xillybus_wq);
}
EXPORT_SYMBOL(xillybus_endpoint_remove);

static int __init xillybus_init(void)
{
	mutex_init(&ep_list_lock);

	xillybus_class = class_create(THIS_MODULE, xillyname);
	if (IS_ERR(xillybus_class))
		return PTR_ERR(xillybus_class);

	xillybus_wq = alloc_workqueue(xillyname, 0, 0);
	if (!xillybus_wq) {
		class_destroy(xillybus_class);
		return -ENOMEM;
	}

	return 0;
}

static void __exit xillybus_exit(void)
{
	/* flush_workqueue() was called for each endpoint released */
	destroy_workqueue(xillybus_wq);

	class_destroy(xillybus_class);
}

module_init(xillybus_init);
module_exit(xillybus_exit);