summaryrefslogtreecommitdiffstats
path: root/sound/firewire/amdtp-stream.c
blob: d35d0a420ee088ade28cbe3212c0e9d6d3199594 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Audio and Music Data Transmission Protocol (IEC 61883-6) streams
 * with Common Isochronous Packet (IEC 61883-1) headers
 *
 * Copyright (c) Clemens Ladisch <clemens@ladisch.de>
 */

#include <linux/device.h>
#include <linux/err.h>
#include <linux/firewire.h>
#include <linux/firewire-constants.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <sound/pcm.h>
#include <sound/pcm_params.h>
#include "amdtp-stream.h"

#define TICKS_PER_CYCLE		3072
#define CYCLES_PER_SECOND	8000
#define TICKS_PER_SECOND	(TICKS_PER_CYCLE * CYCLES_PER_SECOND)

#define OHCI_SECOND_MODULUS		8

/* Always support Linux tracing subsystem. */
#define CREATE_TRACE_POINTS
#include "amdtp-stream-trace.h"

#define TRANSFER_DELAY_TICKS	0x2e00 /* 479.17 microseconds */

/* isochronous header parameters */
#define ISO_DATA_LENGTH_SHIFT	16
#define TAG_NO_CIP_HEADER	0
#define TAG_CIP			1

// Common Isochronous Packet (CIP) header parameters. Use two quadlets CIP header when supported.
#define CIP_HEADER_QUADLETS	2
#define CIP_EOH_SHIFT		31
#define CIP_EOH			(1u << CIP_EOH_SHIFT)
#define CIP_EOH_MASK		0x80000000
#define CIP_SID_SHIFT		24
#define CIP_SID_MASK		0x3f000000
#define CIP_DBS_MASK		0x00ff0000
#define CIP_DBS_SHIFT		16
#define CIP_SPH_MASK		0x00000400
#define CIP_SPH_SHIFT		10
#define CIP_DBC_MASK		0x000000ff
#define CIP_FMT_SHIFT		24
#define CIP_FMT_MASK		0x3f000000
#define CIP_FDF_MASK		0x00ff0000
#define CIP_FDF_SHIFT		16
#define CIP_FDF_NO_DATA		0xff
#define CIP_SYT_MASK		0x0000ffff
#define CIP_SYT_NO_INFO		0xffff
#define CIP_SYT_CYCLE_MODULUS	16
#define CIP_NO_DATA		((CIP_FDF_NO_DATA << CIP_FDF_SHIFT) | CIP_SYT_NO_INFO)

#define CIP_HEADER_SIZE		(sizeof(__be32) * CIP_HEADER_QUADLETS)

/* Audio and Music transfer protocol specific parameters */
#define CIP_FMT_AM		0x10
#define AMDTP_FDF_NO_DATA	0xff

// For iso header and tstamp.
#define IR_CTX_HEADER_DEFAULT_QUADLETS	2
// Add nothing.
#define IR_CTX_HEADER_SIZE_NO_CIP	(sizeof(__be32) * IR_CTX_HEADER_DEFAULT_QUADLETS)
// Add two quadlets CIP header.
#define IR_CTX_HEADER_SIZE_CIP		(IR_CTX_HEADER_SIZE_NO_CIP + CIP_HEADER_SIZE)
#define HEADER_TSTAMP_MASK	0x0000ffff

#define IT_PKT_HEADER_SIZE_CIP		CIP_HEADER_SIZE
#define IT_PKT_HEADER_SIZE_NO_CIP	0 // Nothing.

// The initial firmware of OXFW970 can postpone transmission of packet during finishing
// asynchronous transaction. This module accepts 5 cycles to skip as maximum to avoid buffer
// overrun. Actual device can skip more, then this module stops the packet streaming.
#define IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES	5

/**
 * amdtp_stream_init - initialize an AMDTP stream structure
 * @s: the AMDTP stream to initialize
 * @unit: the target of the stream
 * @dir: the direction of stream
 * @flags: the details of the streaming protocol consist of cip_flags enumeration-constants.
 * @fmt: the value of fmt field in CIP header
 * @process_ctx_payloads: callback handler to process payloads of isoc context
 * @protocol_size: the size to allocate newly for protocol
 */
int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
		      enum amdtp_stream_direction dir, unsigned int flags,
		      unsigned int fmt,
		      amdtp_stream_process_ctx_payloads_t process_ctx_payloads,
		      unsigned int protocol_size)
{
	if (process_ctx_payloads == NULL)
		return -EINVAL;

	s->protocol = kzalloc(protocol_size, GFP_KERNEL);
	if (!s->protocol)
		return -ENOMEM;

	s->unit = unit;
	s->direction = dir;
	s->flags = flags;
	s->context = ERR_PTR(-1);
	mutex_init(&s->mutex);
	s->packet_index = 0;

	init_waitqueue_head(&s->ready_wait);

	s->fmt = fmt;
	s->process_ctx_payloads = process_ctx_payloads;

	return 0;
}
EXPORT_SYMBOL(amdtp_stream_init);

/**
 * amdtp_stream_destroy - free stream resources
 * @s: the AMDTP stream to destroy
 */
void amdtp_stream_destroy(struct amdtp_stream *s)
{
	/* Not initialized. */
	if (s->protocol == NULL)
		return;

	WARN_ON(amdtp_stream_running(s));
	kfree(s->protocol);
	mutex_destroy(&s->mutex);
}
EXPORT_SYMBOL(amdtp_stream_destroy);

const unsigned int amdtp_syt_intervals[CIP_SFC_COUNT] = {
	[CIP_SFC_32000]  =  8,
	[CIP_SFC_44100]  =  8,
	[CIP_SFC_48000]  =  8,
	[CIP_SFC_88200]  = 16,
	[CIP_SFC_96000]  = 16,
	[CIP_SFC_176400] = 32,
	[CIP_SFC_192000] = 32,
};
EXPORT_SYMBOL(amdtp_syt_intervals);

const unsigned int amdtp_rate_table[CIP_SFC_COUNT] = {
	[CIP_SFC_32000]  =  32000,
	[CIP_SFC_44100]  =  44100,
	[CIP_SFC_48000]  =  48000,
	[CIP_SFC_88200]  =  88200,
	[CIP_SFC_96000]  =  96000,
	[CIP_SFC_176400] = 176400,
	[CIP_SFC_192000] = 192000,
};
EXPORT_SYMBOL(amdtp_rate_table);

static int apply_constraint_to_size(struct snd_pcm_hw_params *params,
				    struct snd_pcm_hw_rule *rule)
{
	struct snd_interval *s = hw_param_interval(params, rule->var);
	const struct snd_interval *r =
		hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_RATE);
	struct snd_interval t = {0};
	unsigned int step = 0;
	int i;

	for (i = 0; i < CIP_SFC_COUNT; ++i) {
		if (snd_interval_test(r, amdtp_rate_table[i]))
			step = max(step, amdtp_syt_intervals[i]);
	}

	t.min = roundup(s->min, step);
	t.max = rounddown(s->max, step);
	t.integer = 1;

	return snd_interval_refine(s, &t);
}

/**
 * amdtp_stream_add_pcm_hw_constraints - add hw constraints for PCM substream
 * @s:		the AMDTP stream, which must be initialized.
 * @runtime:	the PCM substream runtime
 */
int amdtp_stream_add_pcm_hw_constraints(struct amdtp_stream *s,
					struct snd_pcm_runtime *runtime)
{
	struct snd_pcm_hardware *hw = &runtime->hw;
	unsigned int ctx_header_size;
	unsigned int maximum_usec_per_period;
	int err;

	hw->info = SNDRV_PCM_INFO_BLOCK_TRANSFER |
		   SNDRV_PCM_INFO_INTERLEAVED |
		   SNDRV_PCM_INFO_JOINT_DUPLEX |
		   SNDRV_PCM_INFO_MMAP |
		   SNDRV_PCM_INFO_MMAP_VALID |
		   SNDRV_PCM_INFO_NO_PERIOD_WAKEUP;

	hw->periods_min = 2;
	hw->periods_max = UINT_MAX;

	/* bytes for a frame */
	hw->period_bytes_min = 4 * hw->channels_max;

	/* Just to prevent from allocating much pages. */
	hw->period_bytes_max = hw->period_bytes_min * 2048;
	hw->buffer_bytes_max = hw->period_bytes_max * hw->periods_min;

	// Linux driver for 1394 OHCI controller voluntarily flushes isoc
	// context when total size of accumulated context header reaches
	// PAGE_SIZE. This kicks work for the isoc context and brings
	// callback in the middle of scheduled interrupts.
	// Although AMDTP streams in the same domain use the same events per
	// IRQ, use the largest size of context header between IT/IR contexts.
	// Here, use the value of context header in IR context is for both
	// contexts.
	if (!(s->flags & CIP_NO_HEADER))
		ctx_header_size = IR_CTX_HEADER_SIZE_CIP;
	else
		ctx_header_size = IR_CTX_HEADER_SIZE_NO_CIP;
	maximum_usec_per_period = USEC_PER_SEC * PAGE_SIZE /
				  CYCLES_PER_SECOND / ctx_header_size;

	// In IEC 61883-6, one isoc packet can transfer events up to the value
	// of syt interval. This comes from the interval of isoc cycle. As 1394
	// OHCI controller can generate hardware IRQ per isoc packet, the
	// interval is 125 usec.
	// However, there are two ways of transmission in IEC 61883-6; blocking
	// and non-blocking modes. In blocking mode, the sequence of isoc packet
	// includes 'empty' or 'NODATA' packets which include no event. In
	// non-blocking mode, the number of events per packet is variable up to
	// the syt interval.
	// Due to the above protocol design, the minimum PCM frames per
	// interrupt should be double of the value of syt interval, thus it is
	// 250 usec.
	err = snd_pcm_hw_constraint_minmax(runtime,
					   SNDRV_PCM_HW_PARAM_PERIOD_TIME,
					   250, maximum_usec_per_period);
	if (err < 0)
		goto end;

	/* Non-Blocking stream has no more constraints */
	if (!(s->flags & CIP_BLOCKING))
		goto end;

	/*
	 * One AMDTP packet can include some frames. In blocking mode, the
	 * number equals to SYT_INTERVAL. So the number is 8, 16 or 32,
	 * depending on its sampling rate. For accurate period interrupt, it's
	 * preferrable to align period/buffer sizes to current SYT_INTERVAL.
	 */
	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
				  apply_constraint_to_size, NULL,
				  SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
				  SNDRV_PCM_HW_PARAM_RATE, -1);
	if (err < 0)
		goto end;
	err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
				  apply_constraint_to_size, NULL,
				  SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
				  SNDRV_PCM_HW_PARAM_RATE, -1);
	if (err < 0)
		goto end;
end:
	return err;
}
EXPORT_SYMBOL(amdtp_stream_add_pcm_hw_constraints);

/**
 * amdtp_stream_set_parameters - set stream parameters
 * @s: the AMDTP stream to configure
 * @rate: the sample rate
 * @data_block_quadlets: the size of a data block in quadlet unit
 * @pcm_frame_multiplier: the multiplier to compute the number of PCM frames by the number of AMDTP
 *			  events.
 *
 * The parameters must be set before the stream is started, and must not be
 * changed while the stream is running.
 */
int amdtp_stream_set_parameters(struct amdtp_stream *s, unsigned int rate,
				unsigned int data_block_quadlets, unsigned int pcm_frame_multiplier)
{
	unsigned int sfc;

	for (sfc = 0; sfc < ARRAY_SIZE(amdtp_rate_table); ++sfc) {
		if (amdtp_rate_table[sfc] == rate)
			break;
	}
	if (sfc == ARRAY_SIZE(amdtp_rate_table))
		return -EINVAL;

	s->sfc = sfc;
	s->data_block_quadlets = data_block_quadlets;
	s->syt_interval = amdtp_syt_intervals[sfc];

	// default buffering in the device.
	s->transfer_delay = TRANSFER_DELAY_TICKS - TICKS_PER_CYCLE;

	// additional buffering needed to adjust for no-data packets.
	if (s->flags & CIP_BLOCKING)
		s->transfer_delay += TICKS_PER_SECOND * s->syt_interval / rate;

	s->pcm_frame_multiplier = pcm_frame_multiplier;

	return 0;
}
EXPORT_SYMBOL(amdtp_stream_set_parameters);

// The CIP header is processed in context header apart from context payload.
static int amdtp_stream_get_max_ctx_payload_size(struct amdtp_stream *s)
{
	unsigned int multiplier;

	if (s->flags & CIP_JUMBO_PAYLOAD)
		multiplier = IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES;
	else
		multiplier = 1;

	return s->syt_interval * s->data_block_quadlets * sizeof(__be32) * multiplier;
}

/**
 * amdtp_stream_get_max_payload - get the stream's packet size
 * @s: the AMDTP stream
 *
 * This function must not be called before the stream has been configured
 * with amdtp_stream_set_parameters().
 */
unsigned int amdtp_stream_get_max_payload(struct amdtp_stream *s)
{
	unsigned int cip_header_size;

	if (!(s->flags & CIP_NO_HEADER))
		cip_header_size = CIP_HEADER_SIZE;
	else
		cip_header_size = 0;

	return cip_header_size + amdtp_stream_get_max_ctx_payload_size(s);
}
EXPORT_SYMBOL(amdtp_stream_get_max_payload);

/**
 * amdtp_stream_pcm_prepare - prepare PCM device for running
 * @s: the AMDTP stream
 *
 * This function should be called from the PCM device's .prepare callback.
 */
void amdtp_stream_pcm_prepare(struct amdtp_stream *s)
{
	s->pcm_buffer_pointer = 0;
	s->pcm_period_pointer = 0;
}
EXPORT_SYMBOL(amdtp_stream_pcm_prepare);

#define prev_packet_desc(s, desc) \
	list_prev_entry_circular(desc, &s->packet_descs_list, link)

static void pool_blocking_data_blocks(struct amdtp_stream *s, struct seq_desc *descs,
				      unsigned int size, unsigned int pos, unsigned int count)
{
	const unsigned int syt_interval = s->syt_interval;
	int i;

	for (i = 0; i < count; ++i) {
		struct seq_desc *desc = descs + pos;

		if (desc->syt_offset != CIP_SYT_NO_INFO)
			desc->data_blocks = syt_interval;
		else
			desc->data_blocks = 0;

		pos = (pos + 1) % size;
	}
}

static void pool_ideal_nonblocking_data_blocks(struct amdtp_stream *s, struct seq_desc *descs,
					       unsigned int size, unsigned int pos,
					       unsigned int count)
{
	const enum cip_sfc sfc = s->sfc;
	unsigned int state = s->ctx_data.rx.data_block_state;
	int i;

	for (i = 0; i < count; ++i) {
		struct seq_desc *desc = descs + pos;

		if (!cip_sfc_is_base_44100(sfc)) {
			// Sample_rate / 8000 is an integer, and precomputed.
			desc->data_blocks = state;
		} else {
			unsigned int phase = state;

		/*
		 * This calculates the number of data blocks per packet so that
		 * 1) the overall rate is correct and exactly synchronized to
		 *    the bus clock, and
		 * 2) packets with a rounded-up number of blocks occur as early
		 *    as possible in the sequence (to prevent underruns of the
		 *    device's buffer).
		 */
			if (sfc == CIP_SFC_44100)
				/* 6 6 5 6 5 6 5 ... */
				desc->data_blocks = 5 + ((phase & 1) ^ (phase == 0 || phase >= 40));
			else
				/* 12 11 11 11 11 ... or 23 22 22 22 22 ... */
				desc->data_blocks = 11 * (sfc >> 1) + (phase == 0);
			if (++phase >= (80 >> (sfc >> 1)))
				phase = 0;
			state = phase;
		}

		pos = (pos + 1) % size;
	}

	s->ctx_data.rx.data_block_state = state;
}

static unsigned int calculate_syt_offset(unsigned int *last_syt_offset,
			unsigned int *syt_offset_state, enum cip_sfc sfc)
{
	unsigned int syt_offset;

	if (*last_syt_offset < TICKS_PER_CYCLE) {
		if (!cip_sfc_is_base_44100(sfc))
			syt_offset = *last_syt_offset + *syt_offset_state;
		else {
		/*
		 * The time, in ticks, of the n'th SYT_INTERVAL sample is:
		 *   n * SYT_INTERVAL * 24576000 / sample_rate
		 * Modulo TICKS_PER_CYCLE, the difference between successive
		 * elements is about 1386.23.  Rounding the results of this
		 * formula to the SYT precision results in a sequence of
		 * differences that begins with:
		 *   1386 1386 1387 1386 1386 1386 1387 1386 1386 1386 1387 ...
		 * This code generates _exactly_ the same sequence.
		 */
			unsigned int phase = *syt_offset_state;
			unsigned int index = phase % 13;

			syt_offset = *last_syt_offset;
			syt_offset += 1386 + ((index && !(index & 3)) ||
					      phase == 146);
			if (++phase >= 147)
				phase = 0;
			*syt_offset_state = phase;
		}
	} else
		syt_offset = *last_syt_offset - TICKS_PER_CYCLE;
	*last_syt_offset = syt_offset;

	if (syt_offset >= TICKS_PER_CYCLE)
		syt_offset = CIP_SYT_NO_INFO;

	return syt_offset;
}

static void pool_ideal_syt_offsets(struct amdtp_stream *s, struct seq_desc *descs,
				   unsigned int size, unsigned int pos, unsigned int count)
{
	const enum cip_sfc sfc = s->sfc;
	unsigned int last = s->ctx_data.rx.last_syt_offset;
	unsigned int state = s->ctx_data.rx.syt_offset_state;
	int i;

	for (i = 0; i < count; ++i) {
		struct seq_desc *desc = descs + pos;

		desc->syt_offset = calculate_syt_offset(&last, &state, sfc);

		pos = (pos + 1) % size;
	}

	s->ctx_data.rx.last_syt_offset = last;
	s->ctx_data.rx.syt_offset_state = state;
}

static unsigned int compute_syt_offset(unsigned int syt, unsigned int cycle,
				       unsigned int transfer_delay)
{
	unsigned int cycle_lo = (cycle % CYCLES_PER_SECOND) & 0x0f;
	unsigned int syt_cycle_lo = (syt & 0xf000) >> 12;
	unsigned int syt_offset;

	// Round up.
	if (syt_cycle_lo < cycle_lo)
		syt_cycle_lo += CIP_SYT_CYCLE_MODULUS;
	syt_cycle_lo -= cycle_lo;

	// Subtract transfer delay so that the synchronization offset is not so large
	// at transmission.
	syt_offset = syt_cycle_lo * TICKS_PER_CYCLE + (syt & 0x0fff);
	if (syt_offset < transfer_delay)
		syt_offset += CIP_SYT_CYCLE_MODULUS * TICKS_PER_CYCLE;

	return syt_offset - transfer_delay;
}

// Both of the producer and consumer of the queue runs in the same clock of IEEE 1394 bus.
// Additionally, the sequence of tx packets is severely checked against any discontinuity
// before filling entries in the queue. The calculation is safe even if it looks fragile by
// overrun.
static unsigned int calculate_cached_cycle_count(struct amdtp_stream *s, unsigned int head)
{
	const unsigned int cache_size = s->ctx_data.tx.cache.size;
	unsigned int cycles = s->ctx_data.tx.cache.pos;

	if (cycles < head)
		cycles += cache_size;
	cycles -= head;

	return cycles;
}

static void cache_seq(struct amdtp_stream *s, const struct pkt_desc *src, unsigned int desc_count)
{
	const unsigned int transfer_delay = s->transfer_delay;
	const unsigned int cache_size = s->ctx_data.tx.cache.size;
	struct seq_desc *cache = s->ctx_data.tx.cache.descs;
	unsigned int cache_pos = s->ctx_data.tx.cache.pos;
	bool aware_syt = !(s->flags & CIP_UNAWARE_SYT);
	int i;

	for (i = 0; i < desc_count; ++i) {
		struct seq_desc *dst = cache + cache_pos;

		if (aware_syt && src->syt != CIP_SYT_NO_INFO)
			dst->syt_offset = compute_syt_offset(src->syt, src->cycle, transfer_delay);
		else
			dst->syt_offset = CIP_SYT_NO_INFO;
		dst->data_blocks = src->data_blocks;

		cache_pos = (cache_pos + 1) % cache_size;
		src = amdtp_stream_next_packet_desc(s, src);
	}

	s->ctx_data.tx.cache.pos = cache_pos;
}

static void pool_ideal_seq_descs(struct amdtp_stream *s, struct seq_desc *descs, unsigned int size,
				 unsigned int pos, unsigned int count)
{
	pool_ideal_syt_offsets(s, descs, size, pos, count);

	if (s->flags & CIP_BLOCKING)
		pool_blocking_data_blocks(s, descs, size, pos, count);
	else
		pool_ideal_nonblocking_data_blocks(s, descs, size, pos, count);
}

static void pool_replayed_seq(struct amdtp_stream *s, struct seq_desc *descs, unsigned int size,
			      unsigned int pos, unsigned int count)
{
	struct amdtp_stream *target = s->ctx_data.rx.replay_target;
	const struct seq_desc *cache = target->ctx_data.tx.cache.descs;
	const unsigned int cache_size = target->ctx_data.tx.cache.size;
	unsigned int cache_pos = s->ctx_data.rx.cache_pos;
	int i;

	for (i = 0; i < count; ++i) {
		descs[pos] = cache[cache_pos];
		cache_pos = (cache_pos + 1) % cache_size;
		pos = (pos + 1) % size;
	}

	s->ctx_data.rx.cache_pos = cache_pos;
}

static void pool_seq_descs(struct amdtp_stream *s, struct seq_desc *descs, unsigned int size,
			   unsigned int pos, unsigned int count)
{
	struct amdtp_domain *d = s->domain;
	void (*pool_seq_descs)(struct amdtp_stream *s, struct seq_desc *descs, unsigned int size,
			       unsigned int pos, unsigned int count);

	if (!d->replay.enable || !s->ctx_data.rx.replay_target) {
		pool_seq_descs = pool_ideal_seq_descs;
	} else {
		if (!d->replay.on_the_fly) {
			pool_seq_descs = pool_replayed_seq;
		} else {
			struct amdtp_stream *tx = s->ctx_data.rx.replay_target;
			const unsigned int cache_size = tx->ctx_data.tx.cache.size;
			const unsigned int cache_pos = s->ctx_data.rx.cache_pos;
			unsigned int cached_cycles = calculate_cached_cycle_count(tx, cache_pos);

			if (cached_cycles > count && cached_cycles > cache_size / 2)
				pool_seq_descs = pool_replayed_seq;
			else
				pool_seq_descs = pool_ideal_seq_descs;
		}
	}

	pool_seq_descs(s, descs, size, pos, count);
}

static void update_pcm_pointers(struct amdtp_stream *s,
				struct snd_pcm_substream *pcm,
				unsigned int frames)
{
	unsigned int ptr;

	ptr = s->pcm_buffer_pointer + frames;
	if (ptr >= pcm->runtime->buffer_size)
		ptr -= pcm->runtime->buffer_size;
	WRITE_ONCE(s->pcm_buffer_pointer, ptr);

	s->pcm_period_pointer += frames;
	if (s->pcm_period_pointer >= pcm->runtime->period_size) {
		s->pcm_period_pointer -= pcm->runtime->period_size;

		// The program in user process should periodically check the status of intermediate
		// buffer associated to PCM substream to process PCM frames in the buffer, instead
		// of receiving notification of period elapsed by poll wait.
		if (!pcm->runtime->no_period_wakeup) {
			if (in_softirq()) {
				// In software IRQ context for 1394 OHCI.
				snd_pcm_period_elapsed(pcm);
			} else {
				// In process context of ALSA PCM application under acquired lock of
				// PCM substream.
				snd_pcm_period_elapsed_under_stream_lock(pcm);
			}
		}
	}
}

static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params,
			bool sched_irq)
{
	int err;

	params->interrupt = sched_irq;
	params->tag = s->tag;
	params->sy = 0;

	err = fw_iso_context_queue(s->context, params, &s->buffer.iso_buffer,
				   s->buffer.packets[s->packet_index].offset);
	if (err < 0) {
		dev_err(&s->unit->device, "queueing error: %d\n", err);
		goto end;
	}

	if (++s->packet_index >= s->queue_size)
		s->packet_index = 0;
end:
	return err;
}

static inline int queue_out_packet(struct amdtp_stream *s,
				   struct fw_iso_packet *params, bool sched_irq)
{
	params->skip =
		!!(params->header_length == 0 && params->payload_length == 0);
	return queue_packet(s, params, sched_irq);
}

static inline int queue_in_packet(struct amdtp_stream *s,
				  struct fw_iso_packet *params)
{
	// Queue one packet for IR context.
	params->header_length = s->ctx_data.tx.ctx_header_size;
	params->payload_length = s->ctx_data.tx.max_ctx_payload_length;
	params->skip = false;
	return queue_packet(s, params, false);
}

static void generate_cip_header(struct amdtp_stream *s, __be32 cip_header[2],
			unsigned int data_block_counter, unsigned int syt)
{
	cip_header[0] = cpu_to_be32(READ_ONCE(s->source_node_id_field) |
				(s->data_block_quadlets << CIP_DBS_SHIFT) |
				((s->sph << CIP_SPH_SHIFT) & CIP_SPH_MASK) |
				data_block_counter);
	cip_header[1] = cpu_to_be32(CIP_EOH |
			((s->fmt << CIP_FMT_SHIFT) & CIP_FMT_MASK) |
			((s->ctx_data.rx.fdf << CIP_FDF_SHIFT) & CIP_FDF_MASK) |
			(syt & CIP_SYT_MASK));
}

static void build_it_pkt_header(struct amdtp_stream *s, unsigned int cycle,
				struct fw_iso_packet *params, unsigned int header_length,
				unsigned int data_blocks,
				unsigned int data_block_counter,
				unsigned int syt, unsigned int index, u32 curr_cycle_time)
{
	unsigned int payload_length;
	__be32 *cip_header;

	payload_length = data_blocks * sizeof(__be32) * s->data_block_quadlets;
	params->payload_length = payload_length;

	if (header_length > 0) {
		cip_header = (__be32 *)params->header;
		generate_cip_header(s, cip_header, data_block_counter, syt);
		params->header_length = header_length;
	} else {
		cip_header = NULL;
	}

	trace_amdtp_packet(s, cycle, cip_header, payload_length + header_length, data_blocks,
			   data_block_counter, s->packet_index, index, curr_cycle_time);
}

static int check_cip_header(struct amdtp_stream *s, const __be32 *buf,
			    unsigned int payload_length,
			    unsigned int *data_blocks,
			    unsigned int *data_block_counter, unsigned int *syt)
{
	u32 cip_header[2];
	unsigned int sph;
	unsigned int fmt;
	unsigned int fdf;
	unsigned int dbc;
	bool lost;

	cip_header[0] = be32_to_cpu(buf[0]);
	cip_header[1] = be32_to_cpu(buf[1]);

	/*
	 * This module supports 'Two-quadlet CIP header with SYT field'.
	 * For convenience, also check FMT field is AM824 or not.
	 */
	if ((((cip_header[0] & CIP_EOH_MASK) == CIP_EOH) ||
	     ((cip_header[1] & CIP_EOH_MASK) != CIP_EOH)) &&
	    (!(s->flags & CIP_HEADER_WITHOUT_EOH))) {
		dev_info_ratelimited(&s->unit->device,
				"Invalid CIP header for AMDTP: %08X:%08X\n",
				cip_header[0], cip_header[1]);
		return -EAGAIN;
	}

	/* Check valid protocol or not. */
	sph = (cip_header[0] & CIP_SPH_MASK) >> CIP_SPH_SHIFT;
	fmt = (cip_header[1] & CIP_FMT_MASK) >> CIP_FMT_SHIFT;
	if (sph != s->sph || fmt != s->fmt) {
		dev_info_ratelimited(&s->unit->device,
				     "Detect unexpected protocol: %08x %08x\n",
				     cip_header[0], cip_header[1]);
		return -EAGAIN;
	}

	/* Calculate data blocks */
	fdf = (cip_header[1] & CIP_FDF_MASK) >> CIP_FDF_SHIFT;
	if (payload_length == 0 || (fmt == CIP_FMT_AM && fdf == AMDTP_FDF_NO_DATA)) {
		*data_blocks = 0;
	} else {
		unsigned int data_block_quadlets =
				(cip_header[0] & CIP_DBS_MASK) >> CIP_DBS_SHIFT;
		/* avoid division by zero */
		if (data_block_quadlets == 0) {
			dev_err(&s->unit->device,
				"Detect invalid value in dbs field: %08X\n",
				cip_header[0]);
			return -EPROTO;
		}
		if (s->flags & CIP_WRONG_DBS)
			data_block_quadlets = s->data_block_quadlets;

		*data_blocks = payload_length / sizeof(__be32) / data_block_quadlets;
	}

	/* Check data block counter continuity */
	dbc = cip_header[0] & CIP_DBC_MASK;
	if (*data_blocks == 0 && (s->flags & CIP_EMPTY_HAS_WRONG_DBC) &&
	    *data_block_counter != UINT_MAX)
		dbc = *data_block_counter;

	if ((dbc == 0x00 && (s->flags & CIP_SKIP_DBC_ZERO_CHECK)) ||
	    *data_block_counter == UINT_MAX) {
		lost = false;
	} else if (!(s->flags & CIP_DBC_IS_END_EVENT)) {
		lost = dbc != *data_block_counter;
	} else {
		unsigned int dbc_interval;

		if (!(s->flags & CIP_DBC_IS_PAYLOAD_QUADLETS)) {
			if (*data_blocks > 0 && s->ctx_data.tx.dbc_interval > 0)
				dbc_interval = s->ctx_data.tx.dbc_interval;
			else
				dbc_interval = *data_blocks;
		} else {
			dbc_interval = payload_length / sizeof(__be32);
		}

		lost = dbc != ((*data_block_counter + dbc_interval) & 0xff);
	}

	if (lost) {
		dev_err(&s->unit->device,
			"Detect discontinuity of CIP: %02X %02X\n",
			*data_block_counter, dbc);
		return -EIO;
	}

	*data_block_counter = dbc;

	if (!(s->flags & CIP_UNAWARE_SYT))
		*syt = cip_header[1] & CIP_SYT_MASK;

	return 0;
}

static int parse_ir_ctx_header(struct amdtp_stream *s, unsigned int cycle,
			       const __be32 *ctx_header,
			       unsigned int *data_blocks,
			       unsigned int *data_block_counter,
			       unsigned int *syt, unsigned int packet_index, unsigned int index,
			       u32 curr_cycle_time)
{
	unsigned int payload_length;
	const __be32 *cip_header;
	unsigned int cip_header_size;

	payload_length = be32_to_cpu(ctx_header[0]) >> ISO_DATA_LENGTH_SHIFT;

	if (!(s->flags & CIP_NO_HEADER))
		cip_header_size = CIP_HEADER_SIZE;
	else
		cip_header_size = 0;

	if (payload_length > cip_header_size + s->ctx_data.tx.max_ctx_payload_length) {
		dev_err(&s->unit->device,
			"Detect jumbo payload: %04x %04x\n",
			payload_length, cip_header_size + s->ctx_data.tx.max_ctx_payload_length);
		return -EIO;
	}

	if (cip_header_size > 0) {
		if (payload_length >= cip_header_size) {
			int err;

			cip_header = ctx_header + IR_CTX_HEADER_DEFAULT_QUADLETS;
			err = check_cip_header(s, cip_header, payload_length - cip_header_size,
					       data_blocks, data_block_counter, syt);
			if (err < 0)
				return err;
		} else {
			// Handle the cycle so that empty packet arrives.
			cip_header = NULL;
			*data_blocks = 0;
			*syt = 0;
		}
	} else {
		cip_header = NULL;
		*data_blocks = payload_length / sizeof(__be32) / s->data_block_quadlets;
		*syt = 0;

		if (*data_block_counter == UINT_MAX)
			*data_block_counter = 0;
	}

	trace_amdtp_packet(s, cycle, cip_header, payload_length, *data_blocks,
			   *data_block_counter, packet_index, index, curr_cycle_time);

	return 0;
}

// In CYCLE_TIMER register of IEEE 1394, 7 bits are used to represent second. On
// the other hand, in DMA descriptors of 1394 OHCI, 3 bits are used to represent
// it. Thus, via Linux firewire subsystem, we can get the 3 bits for second.
static inline u32 compute_ohci_iso_ctx_cycle_count(u32 tstamp)
{
	return (((tstamp >> 13) & 0x07) * CYCLES_PER_SECOND) + (tstamp & 0x1fff);
}

static inline u32 compute_ohci_cycle_count(__be32 ctx_header_tstamp)
{
	u32 tstamp = be32_to_cpu(ctx_header_tstamp) & HEADER_TSTAMP_MASK;
	return compute_ohci_iso_ctx_cycle_count(tstamp);
}

static inline u32 increment_ohci_cycle_count(u32 cycle, unsigned int addend)
{
	cycle += addend;
	if (cycle >= OHCI_SECOND_MODULUS * CYCLES_PER_SECOND)
		cycle -= OHCI_SECOND_MODULUS * CYCLES_PER_SECOND;
	return cycle;
}

static inline u32 decrement_ohci_cycle_count(u32 minuend, u32 subtrahend)
{
	if (minuend < subtrahend)
		minuend += OHCI_SECOND_MODULUS * CYCLES_PER_SECOND;

	return minuend - subtrahend;
}

static int compare_ohci_cycle_count(u32 lval, u32 rval)
{
	if (lval == rval)
		return 0;
	else if (lval < rval && rval - lval < OHCI_SECOND_MODULUS * CYCLES_PER_SECOND / 2)
		return -1;
	else
		return 1;
}

// Align to actual cycle count for the packet which is going to be scheduled.
// This module queued the same number of isochronous cycle as the size of queue
// to kip isochronous cycle, therefore it's OK to just increment the cycle by
// the size of queue for scheduled cycle.
static inline u32 compute_ohci_it_cycle(const __be32 ctx_header_tstamp,
					unsigned int queue_size)
{
	u32 cycle = compute_ohci_cycle_count(ctx_header_tstamp);
	return increment_ohci_cycle_count(cycle, queue_size);
}

static int generate_tx_packet_descs(struct amdtp_stream *s, struct pkt_desc *desc,
				    const __be32 *ctx_header, unsigned int packet_count,
				    unsigned int *desc_count)
{
	unsigned int next_cycle = s->next_cycle;
	unsigned int dbc = s->data_block_counter;
	unsigned int packet_index = s->packet_index;
	unsigned int queue_size = s->queue_size;
	u32 curr_cycle_time = 0;
	int i;
	int err;

	if (trace_amdtp_packet_enabled())
		(void)fw_card_read_cycle_time(fw_parent_device(s->unit)->card, &curr_cycle_time);

	*desc_count = 0;
	for (i = 0; i < packet_count; ++i) {
		unsigned int cycle;
		bool lost;
		unsigned int data_blocks;
		unsigned int syt;

		cycle = compute_ohci_cycle_count(ctx_header[1]);
		lost = (next_cycle != cycle);
		if (lost) {
			if (s->flags & CIP_NO_HEADER) {
				// Fireface skips transmission just for an isoc cycle corresponding
				// to empty packet.
				unsigned int prev_cycle = next_cycle;

				next_cycle = increment_ohci_cycle_count(next_cycle, 1);
				lost = (next_cycle != cycle);
				if (!lost) {
					// Prepare a description for the skipped cycle for
					// sequence replay.
					desc->cycle = prev_cycle;
					desc->syt = 0;
					desc->data_blocks = 0;
					desc->data_block_counter = dbc;
					desc->ctx_payload = NULL;
					desc = amdtp_stream_next_packet_desc(s, desc);
					++(*desc_count);
				}
			} else if (s->flags & CIP_JUMBO_PAYLOAD) {
				// OXFW970 skips transmission for several isoc cycles during
				// asynchronous transaction. The sequence replay is impossible due
				// to the reason.
				unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle,
								IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES);
				lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0);
			}
			if (lost) {
				dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n",
					next_cycle, cycle);
				return -EIO;
			}
		}

		err = parse_ir_ctx_header(s, cycle, ctx_header, &data_blocks, &dbc, &syt,
					  packet_index, i, curr_cycle_time);
		if (err < 0)
			return err;

		desc->cycle = cycle;
		desc->syt = syt;
		desc->data_blocks = data_blocks;
		desc->data_block_counter = dbc;
		desc->ctx_payload = s->buffer.packets[packet_index].buffer;

		if (!(s->flags & CIP_DBC_IS_END_EVENT))
			dbc = (dbc + desc->data_blocks) & 0xff;

		next_cycle = increment_ohci_cycle_count(next_cycle, 1);
		desc = amdtp_stream_next_packet_desc(s, desc);
		++(*desc_count);
		ctx_header += s->ctx_data.tx.ctx_header_size / sizeof(*ctx_header);
		packet_index = (packet_index + 1) % queue_size;
	}

	s->next_cycle = next_cycle;
	s->data_block_counter = dbc;

	return 0;
}

static unsigned int compute_syt(unsigned int syt_offset, unsigned int cycle,
				unsigned int transfer_delay)
{
	unsigned int syt;

	syt_offset += transfer_delay;
	syt = ((cycle + syt_offset / TICKS_PER_CYCLE) << 12) |
	      (syt_offset % TICKS_PER_CYCLE);
	return syt & CIP_SYT_MASK;
}

static void generate_rx_packet_descs(struct amdtp_stream *s, struct pkt_desc *desc,
				     const __be32 *ctx_header, unsigned int packet_count)
{
	struct seq_desc *seq_descs = s->ctx_data.rx.seq.descs;
	unsigned int seq_size = s->ctx_data.rx.seq.size;
	unsigned int seq_pos = s->ctx_data.rx.seq.pos;
	unsigned int dbc = s->data_block_counter;
	bool aware_syt = !(s->flags & CIP_UNAWARE_SYT);
	int i;

	pool_seq_descs(s, seq_descs, seq_size, seq_pos, packet_count);

	for (i = 0; i < packet_count; ++i) {
		unsigned int index = (s->packet_index + i) % s->queue_size;
		const struct seq_desc *seq = seq_descs + seq_pos;

		desc->cycle = compute_ohci_it_cycle(*ctx_header, s->queue_size);

		if (aware_syt && seq->syt_offset != CIP_SYT_NO_INFO)
			desc->syt = compute_syt(seq->syt_offset, desc->cycle, s->transfer_delay);
		else
			desc->syt = CIP_SYT_NO_INFO;

		desc->data_blocks = seq->data_blocks;

		if (s->flags & CIP_DBC_IS_END_EVENT)
			dbc = (dbc + desc->data_blocks) & 0xff;

		desc->data_block_counter = dbc;

		if (!(s->flags & CIP_DBC_IS_END_EVENT))
			dbc = (dbc + desc->data_blocks) & 0xff;

		desc->ctx_payload = s->buffer.packets[index].buffer;

		seq_pos = (seq_pos + 1) % seq_size;
		desc = amdtp_stream_next_packet_desc(s, desc);

		++ctx_header;
	}

	s->data_block_counter = dbc;
	s->ctx_data.rx.seq.pos = seq_pos;
}

static inline void cancel_stream(struct amdtp_stream *s)
{
	s->packet_index = -1;
	if (in_softirq())
		amdtp_stream_pcm_abort(s);
	WRITE_ONCE(s->pcm_buffer_pointer, SNDRV_PCM_POS_XRUN);
}

static snd_pcm_sframes_t compute_pcm_extra_delay(struct amdtp_stream *s,
						 const struct pkt_desc *desc, unsigned int count)
{
	unsigned int data_block_count = 0;
	u32 latest_cycle;
	u32 cycle_time;
	u32 curr_cycle;
	u32 cycle_gap;
	int i, err;

	if (count == 0)
		goto end;

	// Forward to the latest record.
	for (i = 0; i < count - 1; ++i)
		desc = amdtp_stream_next_packet_desc(s, desc);
	latest_cycle = desc->cycle;

	err = fw_card_read_cycle_time(fw_parent_device(s->unit)->card, &cycle_time);
	if (err < 0)
		goto end;

	// Compute cycle count with lower 3 bits of second field and cycle field like timestamp
	// format of 1394 OHCI isochronous context.
	curr_cycle = compute_ohci_iso_ctx_cycle_count((cycle_time >> 12) & 0x0000ffff);

	if (s->direction == AMDTP_IN_STREAM) {
		// NOTE: The AMDTP packet descriptor should be for the past isochronous cycle since
		// it corresponds to arrived isochronous packet.
		if (compare_ohci_cycle_count(latest_cycle, curr_cycle) > 0)
			goto end;
		cycle_gap = decrement_ohci_cycle_count(curr_cycle, latest_cycle);

		// NOTE: estimate delay by recent history of arrived AMDTP packets. The estimated
		// value expectedly corresponds to a few packets (0-2) since the packet arrived at
		// the most recent isochronous cycle has been already processed.
		for (i = 0; i < cycle_gap; ++i) {
			desc = amdtp_stream_next_packet_desc(s, desc);
			data_block_count += desc->data_blocks;
		}
	} else {
		// NOTE: The AMDTP packet descriptor should be for the future isochronous cycle
		// since it was already scheduled.
		if (compare_ohci_cycle_count(latest_cycle, curr_cycle) < 0)
			goto end;
		cycle_gap = decrement_ohci_cycle_count(latest_cycle, curr_cycle);

		// NOTE: use history of scheduled packets.
		for (i = 0; i < cycle_gap; ++i) {
			data_block_count += desc->data_blocks;
			desc = prev_packet_desc(s, desc);
		}
	}
end:
	return data_block_count * s->pcm_frame_multiplier;
}

static void process_ctx_payloads(struct amdtp_stream *s,
				 const struct pkt_desc *desc,
				 unsigned int count)
{
	struct snd_pcm_substream *pcm;
	int i;

	pcm = READ_ONCE(s->pcm);
	s->process_ctx_payloads(s, desc, count, pcm);

	if (pcm) {
		unsigned int data_block_count = 0;

		pcm->runtime->delay = compute_pcm_extra_delay(s, desc, count);

		for (i = 0; i < count; ++i) {
			data_block_count += desc->data_blocks;
			desc = amdtp_stream_next_packet_desc(s, desc);
		}

		update_pcm_pointers(s, pcm, data_block_count * s->pcm_frame_multiplier);
	}
}

static void process_rx_packets(struct fw_iso_context *context, u32 tstamp, size_t header_length,
			       void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	const struct amdtp_domain *d = s->domain;
	const __be32 *ctx_header = header;
	const unsigned int events_per_period = d->events_per_period;
	unsigned int event_count = s->ctx_data.rx.event_count;
	struct pkt_desc *desc = s->packet_descs_cursor;
	unsigned int pkt_header_length;
	unsigned int packets;
	u32 curr_cycle_time;
	bool need_hw_irq;
	int i;

	if (s->packet_index < 0)
		return;

	// Calculate the number of packets in buffer and check XRUN.
	packets = header_length / sizeof(*ctx_header);

	generate_rx_packet_descs(s, desc, ctx_header, packets);

	process_ctx_payloads(s, desc, packets);

	if (!(s->flags & CIP_NO_HEADER))
		pkt_header_length = IT_PKT_HEADER_SIZE_CIP;
	else
		pkt_header_length = 0;

	if (s == d->irq_target) {
		// At NO_PERIOD_WAKEUP mode, the packets for all IT/IR contexts are processed by
		// the tasks of user process operating ALSA PCM character device by calling ioctl(2)
		// with some requests, instead of scheduled hardware IRQ of an IT context.
		struct snd_pcm_substream *pcm = READ_ONCE(s->pcm);
		need_hw_irq = !pcm || !pcm->runtime->no_period_wakeup;
	} else {
		need_hw_irq = false;
	}

	if (trace_amdtp_packet_enabled())
		(void)fw_card_read_cycle_time(fw_parent_device(s->unit)->card, &curr_cycle_time);

	for (i = 0; i < packets; ++i) {
		DEFINE_FLEX(struct fw_iso_packet, template, header,
			    header_length, CIP_HEADER_QUADLETS);
		bool sched_irq = false;

		build_it_pkt_header(s, desc->cycle, template, pkt_header_length,
				    desc->data_blocks, desc->data_block_counter,
				    desc->syt, i, curr_cycle_time);

		if (s == s->domain->irq_target) {
			event_count += desc->data_blocks;
			if (event_count >= events_per_period) {
				event_count -= events_per_period;
				sched_irq = need_hw_irq;
			}
		}

		if (queue_out_packet(s, template, sched_irq) < 0) {
			cancel_stream(s);
			return;
		}

		desc = amdtp_stream_next_packet_desc(s, desc);
	}

	s->ctx_data.rx.event_count = event_count;
	s->packet_descs_cursor = desc;
}

static void skip_rx_packets(struct fw_iso_context *context, u32 tstamp, size_t header_length,
			    void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;
	const __be32 *ctx_header = header;
	unsigned int packets;
	unsigned int cycle;
	int i;

	if (s->packet_index < 0)
		return;

	packets = header_length / sizeof(*ctx_header);

	cycle = compute_ohci_it_cycle(ctx_header[packets - 1], s->queue_size);
	s->next_cycle = increment_ohci_cycle_count(cycle, 1);

	for (i = 0; i < packets; ++i) {
		struct fw_iso_packet params = {
			.header_length = 0,
			.payload_length = 0,
		};
		bool sched_irq = (s == d->irq_target && i == packets - 1);

		if (queue_out_packet(s, &params, sched_irq) < 0) {
			cancel_stream(s);
			return;
		}
	}
}

static void irq_target_callback(struct fw_iso_context *context, u32 tstamp, size_t header_length,
				void *header, void *private_data);

static void process_rx_packets_intermediately(struct fw_iso_context *context, u32 tstamp,
					size_t header_length, void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;
	__be32 *ctx_header = header;
	const unsigned int queue_size = s->queue_size;
	unsigned int packets;
	unsigned int offset;

	if (s->packet_index < 0)
		return;

	packets = header_length / sizeof(*ctx_header);

	offset = 0;
	while (offset < packets) {
		unsigned int cycle = compute_ohci_it_cycle(ctx_header[offset], queue_size);

		if (compare_ohci_cycle_count(cycle, d->processing_cycle.rx_start) >= 0)
			break;

		++offset;
	}

	if (offset > 0) {
		unsigned int length = sizeof(*ctx_header) * offset;

		skip_rx_packets(context, tstamp, length, ctx_header, private_data);
		if (amdtp_streaming_error(s))
			return;

		ctx_header += offset;
		header_length -= length;
	}

	if (offset < packets) {
		s->ready_processing = true;
		wake_up(&s->ready_wait);

		if (d->replay.enable)
			s->ctx_data.rx.cache_pos = 0;

		process_rx_packets(context, tstamp, header_length, ctx_header, private_data);
		if (amdtp_streaming_error(s))
			return;

		if (s == d->irq_target)
			s->context->callback.sc = irq_target_callback;
		else
			s->context->callback.sc = process_rx_packets;
	}
}

static void process_tx_packets(struct fw_iso_context *context, u32 tstamp, size_t header_length,
			       void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	__be32 *ctx_header = header;
	struct pkt_desc *desc = s->packet_descs_cursor;
	unsigned int packet_count;
	unsigned int desc_count;
	int i;
	int err;

	if (s->packet_index < 0)
		return;

	// Calculate the number of packets in buffer and check XRUN.
	packet_count = header_length / s->ctx_data.tx.ctx_header_size;

	desc_count = 0;
	err = generate_tx_packet_descs(s, desc, ctx_header, packet_count, &desc_count);
	if (err < 0) {
		if (err != -EAGAIN) {
			cancel_stream(s);
			return;
		}
	} else {
		struct amdtp_domain *d = s->domain;

		process_ctx_payloads(s, desc, desc_count);

		if (d->replay.enable)
			cache_seq(s, desc, desc_count);

		for (i = 0; i < desc_count; ++i)
			desc = amdtp_stream_next_packet_desc(s, desc);
		s->packet_descs_cursor = desc;
	}

	for (i = 0; i < packet_count; ++i) {
		struct fw_iso_packet params = {0};

		if (queue_in_packet(s, &params) < 0) {
			cancel_stream(s);
			return;
		}
	}
}

static void drop_tx_packets(struct fw_iso_context *context, u32 tstamp, size_t header_length,
			    void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	const __be32 *ctx_header = header;
	unsigned int packets;
	unsigned int cycle;
	int i;

	if (s->packet_index < 0)
		return;

	packets = header_length / s->ctx_data.tx.ctx_header_size;

	ctx_header += (packets - 1) * s->ctx_data.tx.ctx_header_size / sizeof(*ctx_header);
	cycle = compute_ohci_cycle_count(ctx_header[1]);
	s->next_cycle = increment_ohci_cycle_count(cycle, 1);

	for (i = 0; i < packets; ++i) {
		struct fw_iso_packet params = {0};

		if (queue_in_packet(s, &params) < 0) {
			cancel_stream(s);
			return;
		}
	}
}

static void process_tx_packets_intermediately(struct fw_iso_context *context, u32 tstamp,
					size_t header_length, void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;
	__be32 *ctx_header;
	unsigned int packets;
	unsigned int offset;

	if (s->packet_index < 0)
		return;

	packets = header_length / s->ctx_data.tx.ctx_header_size;

	offset = 0;
	ctx_header = header;
	while (offset < packets) {
		unsigned int cycle = compute_ohci_cycle_count(ctx_header[1]);

		if (compare_ohci_cycle_count(cycle, d->processing_cycle.tx_start) >= 0)
			break;

		ctx_header += s->ctx_data.tx.ctx_header_size / sizeof(__be32);
		++offset;
	}

	ctx_header = header;

	if (offset > 0) {
		size_t length = s->ctx_data.tx.ctx_header_size * offset;

		drop_tx_packets(context, tstamp, length, ctx_header, s);
		if (amdtp_streaming_error(s))
			return;

		ctx_header += length / sizeof(*ctx_header);
		header_length -= length;
	}

	if (offset < packets) {
		s->ready_processing = true;
		wake_up(&s->ready_wait);

		process_tx_packets(context, tstamp, header_length, ctx_header, s);
		if (amdtp_streaming_error(s))
			return;

		context->callback.sc = process_tx_packets;
	}
}

static void drop_tx_packets_initially(struct fw_iso_context *context, u32 tstamp,
				      size_t header_length, void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;
	__be32 *ctx_header;
	unsigned int count;
	unsigned int events;
	int i;

	if (s->packet_index < 0)
		return;

	count = header_length / s->ctx_data.tx.ctx_header_size;

	// Attempt to detect any event in the batch of packets.
	events = 0;
	ctx_header = header;
	for (i = 0; i < count; ++i) {
		unsigned int payload_quads =
			(be32_to_cpu(*ctx_header) >> ISO_DATA_LENGTH_SHIFT) / sizeof(__be32);
		unsigned int data_blocks;

		if (s->flags & CIP_NO_HEADER) {
			data_blocks = payload_quads / s->data_block_quadlets;
		} else {
			__be32 *cip_headers = ctx_header + IR_CTX_HEADER_DEFAULT_QUADLETS;

			if (payload_quads < CIP_HEADER_QUADLETS) {
				data_blocks = 0;
			} else {
				payload_quads -= CIP_HEADER_QUADLETS;

				if (s->flags & CIP_UNAWARE_SYT) {
					data_blocks = payload_quads / s->data_block_quadlets;
				} else {
					u32 cip1 = be32_to_cpu(cip_headers[1]);

					// NODATA packet can includes any data blocks but they are
					// not available as event.
					if ((cip1 & CIP_NO_DATA) == CIP_NO_DATA)
						data_blocks = 0;
					else
						data_blocks = payload_quads / s->data_block_quadlets;
				}
			}
		}

		events += data_blocks;

		ctx_header += s->ctx_data.tx.ctx_header_size / sizeof(__be32);
	}

	drop_tx_packets(context, tstamp, header_length, header, s);

	if (events > 0)
		s->ctx_data.tx.event_starts = true;

	// Decide the cycle count to begin processing content of packet in IR contexts.
	{
		unsigned int stream_count = 0;
		unsigned int event_starts_count = 0;
		unsigned int cycle = UINT_MAX;

		list_for_each_entry(s, &d->streams, list) {
			if (s->direction == AMDTP_IN_STREAM) {
				++stream_count;
				if (s->ctx_data.tx.event_starts)
					++event_starts_count;
			}
		}

		if (stream_count == event_starts_count) {
			unsigned int next_cycle;

			list_for_each_entry(s, &d->streams, list) {
				if (s->direction != AMDTP_IN_STREAM)
					continue;

				next_cycle = increment_ohci_cycle_count(s->next_cycle,
								d->processing_cycle.tx_init_skip);
				if (cycle == UINT_MAX ||
				    compare_ohci_cycle_count(next_cycle, cycle) > 0)
					cycle = next_cycle;

				s->context->callback.sc = process_tx_packets_intermediately;
			}

			d->processing_cycle.tx_start = cycle;
		}
	}
}

static void process_ctxs_in_domain(struct amdtp_domain *d)
{
	struct amdtp_stream *s;

	list_for_each_entry(s, &d->streams, list) {
		if (s != d->irq_target && amdtp_stream_running(s))
			fw_iso_context_flush_completions(s->context);

		if (amdtp_streaming_error(s))
			goto error;
	}

	return;
error:
	if (amdtp_stream_running(d->irq_target))
		cancel_stream(d->irq_target);

	list_for_each_entry(s, &d->streams, list) {
		if (amdtp_stream_running(s))
			cancel_stream(s);
	}
}

static void irq_target_callback(struct fw_iso_context *context, u32 tstamp, size_t header_length,
				void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;

	process_rx_packets(context, tstamp, header_length, header, private_data);
	process_ctxs_in_domain(d);
}

static void irq_target_callback_intermediately(struct fw_iso_context *context, u32 tstamp,
					size_t header_length, void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;

	process_rx_packets_intermediately(context, tstamp, header_length, header, private_data);
	process_ctxs_in_domain(d);
}

static void irq_target_callback_skip(struct fw_iso_context *context, u32 tstamp,
				     size_t header_length, void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;
	bool ready_to_start;

	skip_rx_packets(context, tstamp, header_length, header, private_data);
	process_ctxs_in_domain(d);

	if (d->replay.enable && !d->replay.on_the_fly) {
		unsigned int rx_count = 0;
		unsigned int rx_ready_count = 0;
		struct amdtp_stream *rx;

		list_for_each_entry(rx, &d->streams, list) {
			struct amdtp_stream *tx;
			unsigned int cached_cycles;

			if (rx->direction != AMDTP_OUT_STREAM)
				continue;
			++rx_count;

			tx = rx->ctx_data.rx.replay_target;
			cached_cycles = calculate_cached_cycle_count(tx, 0);
			if (cached_cycles > tx->ctx_data.tx.cache.size / 2)
				++rx_ready_count;
		}

		ready_to_start = (rx_count == rx_ready_count);
	} else {
		ready_to_start = true;
	}

	// Decide the cycle count to begin processing content of packet in IT contexts. All of IT
	// contexts are expected to start and get callback when reaching here.
	if (ready_to_start) {
		unsigned int cycle = s->next_cycle;
		list_for_each_entry(s, &d->streams, list) {
			if (s->direction != AMDTP_OUT_STREAM)
				continue;

			if (compare_ohci_cycle_count(s->next_cycle, cycle) > 0)
				cycle = s->next_cycle;

			if (s == d->irq_target)
				s->context->callback.sc = irq_target_callback_intermediately;
			else
				s->context->callback.sc = process_rx_packets_intermediately;
		}

		d->processing_cycle.rx_start = cycle;
	}
}

// This is executed one time. For in-stream, first packet has come. For out-stream, prepared to
// transmit first packet.
static void amdtp_stream_first_callback(struct fw_iso_context *context,
					u32 tstamp, size_t header_length,
					void *header, void *private_data)
{
	struct amdtp_stream *s = private_data;
	struct amdtp_domain *d = s->domain;

	if (s->direction == AMDTP_IN_STREAM) {
		context->callback.sc = drop_tx_packets_initially;
	} else {
		if (s == d->irq_target)
			context->callback.sc = irq_target_callback_skip;
		else
			context->callback.sc = skip_rx_packets;
	}

	context->callback.sc(context, tstamp, header_length, header, s);
}

/**
 * amdtp_stream_start - start transferring packets
 * @s: the AMDTP stream to start
 * @channel: the isochronous channel on the bus
 * @speed: firewire speed code
 * @queue_size: The number of packets in the queue.
 * @idle_irq_interval: the interval to queue packet during initial state.
 *
 * The stream cannot be started until it has been configured with
 * amdtp_stream_set_parameters() and it must be started before any PCM or MIDI
 * device can be started.
 */
static int amdtp_stream_start(struct amdtp_stream *s, int channel, int speed,
			      unsigned int queue_size, unsigned int idle_irq_interval)
{
	bool is_irq_target = (s == s->domain->irq_target);
	unsigned int ctx_header_size;
	unsigned int max_ctx_payload_size;
	enum dma_data_direction dir;
	struct pkt_desc *descs;
	int i, type, tag, err;

	mutex_lock(&s->mutex);

	if (WARN_ON(amdtp_stream_running(s) ||
		    (s->data_block_quadlets < 1))) {
		err = -EBADFD;
		goto err_unlock;
	}

	if (s->direction == AMDTP_IN_STREAM) {
		// NOTE: IT context should be used for constant IRQ.
		if (is_irq_target) {
			err = -EINVAL;
			goto err_unlock;
		}

		s->data_block_counter = UINT_MAX;
	} else {
		s->data_block_counter = 0;
	}

	// initialize packet buffer.
	if (s->direction == AMDTP_IN_STREAM) {
		dir = DMA_FROM_DEVICE;
		type = FW_ISO_CONTEXT_RECEIVE;
		if (!(s->flags & CIP_NO_HEADER))
			ctx_header_size = IR_CTX_HEADER_SIZE_CIP;
		else
			ctx_header_size = IR_CTX_HEADER_SIZE_NO_CIP;
	} else {
		dir = DMA_TO_DEVICE;
		type = FW_ISO_CONTEXT_TRANSMIT;
		ctx_header_size = 0;	// No effect for IT context.
	}
	max_ctx_payload_size = amdtp_stream_get_max_ctx_payload_size(s);

	err = iso_packets_buffer_init(&s->buffer, s->unit, queue_size, max_ctx_payload_size, dir);
	if (err < 0)
		goto err_unlock;
	s->queue_size = queue_size;

	s->context = fw_iso_context_create(fw_parent_device(s->unit)->card,
					  type, channel, speed, ctx_header_size,
					  amdtp_stream_first_callback, s);
	if (IS_ERR(s->context)) {
		err = PTR_ERR(s->context);
		if (err == -EBUSY)
			dev_err(&s->unit->device,
				"no free stream on this controller\n");
		goto err_buffer;
	}

	amdtp_stream_update(s);

	if (s->direction == AMDTP_IN_STREAM) {
		s->ctx_data.tx.max_ctx_payload_length = max_ctx_payload_size;
		s->ctx_data.tx.ctx_header_size = ctx_header_size;
		s->ctx_data.tx.event_starts = false;

		if (s->domain->replay.enable) {
			// struct fw_iso_context.drop_overflow_headers is false therefore it's
			// possible to cache much unexpectedly.
			s->ctx_data.tx.cache.size = max_t(unsigned int, s->syt_interval * 2,
							  queue_size * 3 / 2);
			s->ctx_data.tx.cache.pos = 0;
			s->ctx_data.tx.cache.descs = kcalloc(s->ctx_data.tx.cache.size,
						sizeof(*s->ctx_data.tx.cache.descs), GFP_KERNEL);
			if (!s->ctx_data.tx.cache.descs) {
				err = -ENOMEM;
				goto err_context;
			}
		}
	} else {
		static const struct {
			unsigned int data_block;
			unsigned int syt_offset;
		} *entry, initial_state[] = {
			[CIP_SFC_32000]  = {  4, 3072 },
			[CIP_SFC_48000]  = {  6, 1024 },
			[CIP_SFC_96000]  = { 12, 1024 },
			[CIP_SFC_192000] = { 24, 1024 },
			[CIP_SFC_44100]  = {  0,   67 },
			[CIP_SFC_88200]  = {  0,   67 },
			[CIP_SFC_176400] = {  0,   67 },
		};

		s->ctx_data.rx.seq.descs = kcalloc(queue_size, sizeof(*s->ctx_data.rx.seq.descs), GFP_KERNEL);
		if (!s->ctx_data.rx.seq.descs) {
			err = -ENOMEM;
			goto err_context;
		}
		s->ctx_data.rx.seq.size = queue_size;
		s->ctx_data.rx.seq.pos = 0;

		entry = &initial_state[s->sfc];
		s->ctx_data.rx.data_block_state = entry->data_block;
		s->ctx_data.rx.syt_offset_state = entry->syt_offset;
		s->ctx_data.rx.last_syt_offset = TICKS_PER_CYCLE;

		s->ctx_data.rx.event_count = 0;
	}

	if (s->flags & CIP_NO_HEADER)
		s->tag = TAG_NO_CIP_HEADER;
	else
		s->tag = TAG_CIP;

	// NOTE: When operating without hardIRQ/softIRQ, applications tends to call ioctl request
	// for runtime of PCM substream in the interval equivalent to the size of PCM buffer. It
	// could take a round over queue of AMDTP packet descriptors and small loss of history. For
	// safe, keep more 8 elements for the queue, equivalent to 1 ms.
	descs = kcalloc(s->queue_size + 8, sizeof(*descs), GFP_KERNEL);
	if (!descs) {
		err = -ENOMEM;
		goto err_context;
	}
	s->packet_descs = descs;

	INIT_LIST_HEAD(&s->packet_descs_list);
	for (i = 0; i < s->queue_size; ++i) {
		INIT_LIST_HEAD(&descs->link);
		list_add_tail(&descs->link, &s->packet_descs_list);
		++descs;
	}
	s->packet_descs_cursor = list_first_entry(&s->packet_descs_list, struct pkt_desc, link);

	s->packet_index = 0;
	do {
		struct fw_iso_packet params;

		if (s->direction == AMDTP_IN_STREAM) {
			err = queue_in_packet(s, &params);
		} else {
			bool sched_irq = false;

			params.header_length = 0;
			params.payload_length = 0;

			if (is_irq_target) {
				sched_irq = !((s->packet_index + 1) %
					      idle_irq_interval);
			}

			err = queue_out_packet(s, &params, sched_irq);
		}
		if (err < 0)
			goto err_pkt_descs;
	} while (s->packet_index > 0);

	/* NOTE: TAG1 matches CIP. This just affects in stream. */
	tag = FW_ISO_CONTEXT_MATCH_TAG1;
	if ((s->flags & CIP_EMPTY_WITH_TAG0) || (s->flags & CIP_NO_HEADER))
		tag |= FW_ISO_CONTEXT_MATCH_TAG0;

	s->ready_processing = false;
	err = fw_iso_context_start(s->context, -1, 0, tag);
	if (err < 0)
		goto err_pkt_descs;

	mutex_unlock(&s->mutex);

	return 0;
err_pkt_descs:
	kfree(s->packet_descs);
	s->packet_descs = NULL;
err_context:
	if (s->direction == AMDTP_OUT_STREAM) {
		kfree(s->ctx_data.rx.seq.descs);
	} else {
		if (s->domain->replay.enable)
			kfree(s->ctx_data.tx.cache.descs);
	}
	fw_iso_context_destroy(s->context);
	s->context = ERR_PTR(-1);
err_buffer:
	iso_packets_buffer_destroy(&s->buffer, s->unit);
err_unlock:
	mutex_unlock(&s->mutex);

	return err;
}

/**
 * amdtp_domain_stream_pcm_pointer - get the PCM buffer position
 * @d: the AMDTP domain.
 * @s: the AMDTP stream that transports the PCM data
 *
 * Returns the current buffer position, in frames.
 */
unsigned long amdtp_domain_stream_pcm_pointer(struct amdtp_domain *d,
					      struct amdtp_stream *s)
{
	struct amdtp_stream *irq_target = d->irq_target;

	// Process isochronous packets queued till recent isochronous cycle to handle PCM frames.
	if (irq_target && amdtp_stream_running(irq_target)) {
		// In software IRQ context, the call causes dead-lock to disable the tasklet
		// synchronously.
		if (!in_softirq())
			fw_iso_context_flush_completions(irq_target->context);
	}

	return READ_ONCE(s->pcm_buffer_pointer);
}
EXPORT_SYMBOL_GPL(amdtp_domain_stream_pcm_pointer);

/**
 * amdtp_domain_stream_pcm_ack - acknowledge queued PCM frames
 * @d: the AMDTP domain.
 * @s: the AMDTP stream that transfers the PCM frames
 *
 * Returns zero always.
 */
int amdtp_domain_stream_pcm_ack(struct amdtp_domain *d, struct amdtp_stream *s)
{
	struct amdtp_stream *irq_target = d->irq_target;

	// Process isochronous packets for recent isochronous cycle to handle
	// queued PCM frames.
	if (irq_target && amdtp_stream_running(irq_target))
		fw_iso_context_flush_completions(irq_target->context);

	return 0;
}
EXPORT_SYMBOL_GPL(amdtp_domain_stream_pcm_ack);

/**
 * amdtp_stream_update - update the stream after a bus reset
 * @s: the AMDTP stream
 */
void amdtp_stream_update(struct amdtp_stream *s)
{
	/* Precomputing. */
	WRITE_ONCE(s->source_node_id_field,
                   (fw_parent_device(s->unit)->card->node_id << CIP_SID_SHIFT) & CIP_SID_MASK);
}
EXPORT_SYMBOL(amdtp_stream_update);

/**
 * amdtp_stream_stop - stop sending packets
 * @s: the AMDTP stream to stop
 *
 * All PCM and MIDI devices of the stream must be stopped before the stream
 * itself can be stopped.
 */
static void amdtp_stream_stop(struct amdtp_stream *s)
{
	mutex_lock(&s->mutex);

	if (!amdtp_stream_running(s)) {
		mutex_unlock(&s->mutex);
		return;
	}

	fw_iso_context_stop(s->context);
	fw_iso_context_destroy(s->context);
	s->context = ERR_PTR(-1);
	iso_packets_buffer_destroy(&s->buffer, s->unit);
	kfree(s->packet_descs);
	s->packet_descs = NULL;

	if (s->direction == AMDTP_OUT_STREAM) {
		kfree(s->ctx_data.rx.seq.descs);
	} else {
		if (s->domain->replay.enable)
			kfree(s->ctx_data.tx.cache.descs);
	}

	mutex_unlock(&s->mutex);
}

/**
 * amdtp_stream_pcm_abort - abort the running PCM device
 * @s: the AMDTP stream about to be stopped
 *
 * If the isochronous stream needs to be stopped asynchronously, call this
 * function first to stop the PCM device.
 */
void amdtp_stream_pcm_abort(struct amdtp_stream *s)
{
	struct snd_pcm_substream *pcm;

	pcm = READ_ONCE(s->pcm);
	if (pcm)
		snd_pcm_stop_xrun(pcm);
}
EXPORT_SYMBOL(amdtp_stream_pcm_abort);

/**
 * amdtp_domain_init - initialize an AMDTP domain structure
 * @d: the AMDTP domain to initialize.
 */
int amdtp_domain_init(struct amdtp_domain *d)
{
	INIT_LIST_HEAD(&d->streams);

	d->events_per_period = 0;

	return 0;
}
EXPORT_SYMBOL_GPL(amdtp_domain_init);

/**
 * amdtp_domain_destroy - destroy an AMDTP domain structure
 * @d: the AMDTP domain to destroy.
 */
void amdtp_domain_destroy(struct amdtp_domain *d)
{
	// At present nothing to do.
	return;
}
EXPORT_SYMBOL_GPL(amdtp_domain_destroy);

/**
 * amdtp_domain_add_stream - register isoc context into the domain.
 * @d: the AMDTP domain.
 * @s: the AMDTP stream.
 * @channel: the isochronous channel on the bus.
 * @speed: firewire speed code.
 */
int amdtp_domain_add_stream(struct amdtp_domain *d, struct amdtp_stream *s,
			    int channel, int speed)
{
	struct amdtp_stream *tmp;

	list_for_each_entry(tmp, &d->streams, list) {
		if (s == tmp)
			return -EBUSY;
	}

	list_add(&s->list, &d->streams);

	s->channel = channel;
	s->speed = speed;
	s->domain = d;

	return 0;
}
EXPORT_SYMBOL_GPL(amdtp_domain_add_stream);

// Make the reference from rx stream to tx stream for sequence replay. When the number of tx streams
// is less than the number of rx streams, the first tx stream is selected.
static int make_association(struct amdtp_domain *d)
{
	unsigned int dst_index = 0;
	struct amdtp_stream *rx;

	// Make association to replay target.
	list_for_each_entry(rx, &d->streams, list) {
		if (rx->direction == AMDTP_OUT_STREAM) {
			unsigned int src_index = 0;
			struct amdtp_stream *tx = NULL;
			struct amdtp_stream *s;

			list_for_each_entry(s, &d->streams, list) {
				if (s->direction == AMDTP_IN_STREAM) {
					if (dst_index == src_index) {
						tx = s;
						break;
					}

					++src_index;
				}
			}
			if (!tx) {
				// Select the first entry.
				list_for_each_entry(s, &d->streams, list) {
					if (s->direction == AMDTP_IN_STREAM) {
						tx = s;
						break;
					}
				}
				// No target is available to replay sequence.
				if (!tx)
					return -EINVAL;
			}

			rx->ctx_data.rx.replay_target = tx;

			++dst_index;
		}
	}

	return 0;
}

/**
 * amdtp_domain_start - start sending packets for isoc context in the domain.
 * @d: the AMDTP domain.
 * @tx_init_skip_cycles: the number of cycles to skip processing packets at initial stage of IR
 *			 contexts.
 * @replay_seq: whether to replay the sequence of packet in IR context for the sequence of packet in
 *		IT context.
 * @replay_on_the_fly: transfer rx packets according to nominal frequency, then begin to replay
 *		       according to arrival of events in tx packets.
 */
int amdtp_domain_start(struct amdtp_domain *d, unsigned int tx_init_skip_cycles, bool replay_seq,
		       bool replay_on_the_fly)
{
	unsigned int events_per_buffer = d->events_per_buffer;
	unsigned int events_per_period = d->events_per_period;
	unsigned int queue_size;
	struct amdtp_stream *s;
	bool found = false;
	int err;

	if (replay_seq) {
		err = make_association(d);
		if (err < 0)
			return err;
	}
	d->replay.enable = replay_seq;
	d->replay.on_the_fly = replay_on_the_fly;

	// Select an IT context as IRQ target.
	list_for_each_entry(s, &d->streams, list) {
		if (s->direction == AMDTP_OUT_STREAM) {
			found = true;
			break;
		}
	}
	if (!found)
		return -ENXIO;
	d->irq_target = s;

	d->processing_cycle.tx_init_skip = tx_init_skip_cycles;

	// This is a case that AMDTP streams in domain run just for MIDI
	// substream. Use the number of events equivalent to 10 msec as
	// interval of hardware IRQ.
	if (events_per_period == 0)
		events_per_period = amdtp_rate_table[d->irq_target->sfc] / 100;
	if (events_per_buffer == 0)
		events_per_buffer = events_per_period * 3;

	queue_size = DIV_ROUND_UP(CYCLES_PER_SECOND * events_per_buffer,
				  amdtp_rate_table[d->irq_target->sfc]);

	list_for_each_entry(s, &d->streams, list) {
		unsigned int idle_irq_interval = 0;

		if (s->direction == AMDTP_OUT_STREAM && s == d->irq_target) {
			idle_irq_interval = DIV_ROUND_UP(CYCLES_PER_SECOND * events_per_period,
							 amdtp_rate_table[d->irq_target->sfc]);
		}

		// Starts immediately but actually DMA context starts several hundred cycles later.
		err = amdtp_stream_start(s, s->channel, s->speed, queue_size, idle_irq_interval);
		if (err < 0)
			goto error;
	}

	return 0;
error:
	list_for_each_entry(s, &d->streams, list)
		amdtp_stream_stop(s);
	return err;
}
EXPORT_SYMBOL_GPL(amdtp_domain_start);

/**
 * amdtp_domain_stop - stop sending packets for isoc context in the same domain.
 * @d: the AMDTP domain to which the isoc contexts belong.
 */
void amdtp_domain_stop(struct amdtp_domain *d)
{
	struct amdtp_stream *s, *next;

	if (d->irq_target)
		amdtp_stream_stop(d->irq_target);

	list_for_each_entry_safe(s, next, &d->streams, list) {
		list_del(&s->list);

		if (s != d->irq_target)
			amdtp_stream_stop(s);
	}

	d->events_per_period = 0;
	d->irq_target = NULL;
}
EXPORT_SYMBOL_GPL(amdtp_domain_stop);