summaryrefslogtreecommitdiff
path: root/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
blob: ef227af72348ac6617128c8455a536269ae759fe (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
// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/*
 * Wave5 series multi-standard codec IP - decoder interface
 *
 * Copyright (C) 2021-2023 CHIPS&MEDIA INC
 */

#include "wave5-helper.h"

#define VPU_DEC_DEV_NAME "C&M Wave5 VPU decoder"
#define VPU_DEC_DRV_NAME "wave5-dec"

#define DEFAULT_SRC_SIZE(width, height) ({			\
	(width) * (height) / 8 * 3;					\
})

static const struct vpu_format dec_fmt_list[FMT_TYPES][MAX_FMTS] = {
	[VPU_FMT_TYPE_CODEC] = {
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_HEVC,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_H264,
			.max_width = 8192,
			.min_width = 32,
			.max_height = 4320,
			.min_height = 32,
		},
	},
	[VPU_FMT_TYPE_RAW] = {
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_YUV420,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV12,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV21,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_YUV422P,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV16,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV61,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_YUV420M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV12M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV21M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_YUV422M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV16M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
		{
			.v4l2_pix_fmt = V4L2_PIX_FMT_NV61M,
			.max_width = 8192,
			.min_width = 8,
			.max_height = 4320,
			.min_height = 8,
		},
	}
};

/*
 * Make sure that the state switch is allowed and add logging for debugging
 * purposes
 */
static int switch_state(struct vpu_instance *inst, enum vpu_instance_state state)
{
	switch (state) {
	case VPU_INST_STATE_NONE:
		break;
	case VPU_INST_STATE_OPEN:
		if (inst->state != VPU_INST_STATE_NONE)
			goto invalid_state_switch;
		goto valid_state_switch;
	case VPU_INST_STATE_INIT_SEQ:
		if (inst->state != VPU_INST_STATE_OPEN && inst->state != VPU_INST_STATE_STOP)
			goto invalid_state_switch;
		goto valid_state_switch;
	case VPU_INST_STATE_PIC_RUN:
		if (inst->state != VPU_INST_STATE_INIT_SEQ)
			goto invalid_state_switch;
		goto valid_state_switch;
	case VPU_INST_STATE_STOP:
		goto valid_state_switch;
	}
invalid_state_switch:
	WARN(1, "Invalid state switch from %s to %s.\n",
	     state_to_str(inst->state), state_to_str(state));
	return -EINVAL;
valid_state_switch:
	dev_dbg(inst->dev->dev, "Switch state from %s to %s.\n",
		state_to_str(inst->state), state_to_str(state));
	inst->state = state;
	return 0;
}

static int wave5_vpu_dec_set_eos_on_firmware(struct vpu_instance *inst)
{
	int ret;

	ret = wave5_vpu_dec_update_bitstream_buffer(inst, 0);
	if (ret) {
		/*
		 * To set the EOS flag, a command is sent to the firmware.
		 * That command may never return (timeout) or may report an error.
		 */
		dev_err(inst->dev->dev,
			"Setting EOS for the bitstream, fail: %d\n", ret);
		return ret;
	}
	return 0;
}

static bool wave5_last_src_buffer_consumed(struct v4l2_m2m_ctx *m2m_ctx)
{
	struct vpu_src_buffer *vpu_buf;

	if (!m2m_ctx->last_src_buf)
		return false;

	vpu_buf = wave5_to_vpu_src_buf(m2m_ctx->last_src_buf);
	return vpu_buf->consumed;
}

static void wave5_handle_src_buffer(struct vpu_instance *inst, dma_addr_t rd_ptr)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct v4l2_m2m_buffer *buf, *n;
	size_t consumed_bytes = 0;

	if (rd_ptr >= inst->last_rd_ptr) {
		consumed_bytes = rd_ptr - inst->last_rd_ptr;
	} else {
		size_t rd_offs = rd_ptr - inst->bitstream_vbuf.daddr;
		size_t last_rd_offs = inst->last_rd_ptr - inst->bitstream_vbuf.daddr;

		consumed_bytes = rd_offs + (inst->bitstream_vbuf.size - last_rd_offs);
	}

	inst->last_rd_ptr = rd_ptr;
	consumed_bytes += inst->remaining_consumed_bytes;

	dev_dbg(inst->dev->dev, "%s: %zu bytes of bitstream was consumed", __func__,
		consumed_bytes);

	v4l2_m2m_for_each_src_buf_safe(m2m_ctx, buf, n) {
		struct vb2_v4l2_buffer *src_buf = &buf->vb;
		size_t src_size = vb2_get_plane_payload(&src_buf->vb2_buf, 0);

		if (src_size > consumed_bytes)
			break;

		dev_dbg(inst->dev->dev, "%s: removing src buffer %i",
			__func__, src_buf->vb2_buf.index);
		src_buf = v4l2_m2m_src_buf_remove(m2m_ctx);
		inst->timestamp = src_buf->vb2_buf.timestamp;
		v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
		consumed_bytes -= src_size;

		/* Handle the case the last bitstream buffer has been picked */
		if (src_buf == m2m_ctx->last_src_buf) {
			int ret;

			m2m_ctx->last_src_buf = NULL;
			ret = wave5_vpu_dec_set_eos_on_firmware(inst);
			if (ret)
				dev_warn(inst->dev->dev,
					 "Setting EOS for the bitstream, fail: %d\n", ret);
			break;
		}
	}

	inst->remaining_consumed_bytes = consumed_bytes;
}

static void wave5_update_pix_fmt(struct v4l2_pix_format_mplane *pix_mp, unsigned int width,
				 unsigned int height)
{
	switch (pix_mp->pixelformat) {
	case V4L2_PIX_FMT_YUV420:
	case V4L2_PIX_FMT_NV12:
	case V4L2_PIX_FMT_NV21:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height * 3 / 2;
		break;
	case V4L2_PIX_FMT_YUV422P:
	case V4L2_PIX_FMT_NV16:
	case V4L2_PIX_FMT_NV61:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height * 2;
		break;
	case V4L2_PIX_FMT_YUV420M:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height;
		pix_mp->plane_fmt[1].bytesperline = round_up(width, 32) / 2;
		pix_mp->plane_fmt[1].sizeimage = width * height / 4;
		pix_mp->plane_fmt[2].bytesperline = round_up(width, 32) / 2;
		pix_mp->plane_fmt[2].sizeimage = width * height / 4;
		break;
	case V4L2_PIX_FMT_NV12M:
	case V4L2_PIX_FMT_NV21M:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height;
		pix_mp->plane_fmt[1].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[1].sizeimage = width * height / 2;
		break;
	case V4L2_PIX_FMT_YUV422M:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height;
		pix_mp->plane_fmt[1].bytesperline = round_up(width, 32) / 2;
		pix_mp->plane_fmt[1].sizeimage = width * height / 2;
		pix_mp->plane_fmt[2].bytesperline = round_up(width, 32) / 2;
		pix_mp->plane_fmt[2].sizeimage = width * height / 2;
		break;
	case V4L2_PIX_FMT_NV16M:
	case V4L2_PIX_FMT_NV61M:
		pix_mp->width = round_up(width, 32);
		pix_mp->height = round_up(height, 16);
		pix_mp->plane_fmt[0].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[0].sizeimage = width * height;
		pix_mp->plane_fmt[1].bytesperline = round_up(width, 32);
		pix_mp->plane_fmt[1].sizeimage = width * height;
		break;
	default:
		pix_mp->width = width;
		pix_mp->height = height;
		pix_mp->plane_fmt[0].bytesperline = 0;
		pix_mp->plane_fmt[0].sizeimage = max(DEFAULT_SRC_SIZE(width, height),
						     pix_mp->plane_fmt[0].sizeimage);
		break;
	}
}

static int start_decode(struct vpu_instance *inst, u32 *fail_res)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	int ret = 0;

	ret = wave5_vpu_dec_start_one_frame(inst, fail_res);
	if (ret) {
		struct vb2_v4l2_buffer *src_buf;

		src_buf = v4l2_m2m_src_buf_remove(m2m_ctx);
		if (src_buf)
			v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_ERROR);
		switch_state(inst, VPU_INST_STATE_STOP);

		dev_dbg(inst->dev->dev, "%s: pic run failed / finish job", __func__);
		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
	}

	return ret;
}

static void flag_last_buffer_done(struct vpu_instance *inst)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct vb2_v4l2_buffer *vb;
	int i;

	lockdep_assert_held(&inst->state_spinlock);

	vb = v4l2_m2m_dst_buf_remove(m2m_ctx);
	if (!vb) {
		m2m_ctx->is_draining = true;
		m2m_ctx->next_buf_last = true;
		return;
	}

	for (i = 0; i < vb->vb2_buf.num_planes; i++)
		vb2_set_plane_payload(&vb->vb2_buf, i, 0);
	vb->field = V4L2_FIELD_NONE;

	v4l2_m2m_last_buffer_done(m2m_ctx, vb);
}

static void send_eos_event(struct vpu_instance *inst)
{
	static const struct v4l2_event vpu_event_eos = {
		.type = V4L2_EVENT_EOS
	};

	lockdep_assert_held(&inst->state_spinlock);

	v4l2_event_queue_fh(&inst->v4l2_fh, &vpu_event_eos);
	inst->eos = false;
}

static int handle_dynamic_resolution_change(struct vpu_instance *inst)
{
	struct v4l2_fh *fh = &inst->v4l2_fh;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;

	static const struct v4l2_event vpu_event_src_ch = {
		.type = V4L2_EVENT_SOURCE_CHANGE,
		.u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION,
	};
	struct dec_info *p_dec_info = &inst->codec_info->dec_info;
	struct dec_initial_info *initial_info = &inst->codec_info->dec_info.initial_info;

	lockdep_assert_held(&inst->state_spinlock);

	dev_dbg(inst->dev->dev, "%s: rd_ptr %pad", __func__, &initial_info->rd_ptr);

	dev_dbg(inst->dev->dev, "%s: width: %u height: %u profile: %u | minbuffer: %u\n",
		__func__, initial_info->pic_width, initial_info->pic_height,
		initial_info->profile, initial_info->min_frame_buffer_count);

	inst->needs_reallocation = true;
	inst->fbc_buf_count = initial_info->min_frame_buffer_count + 1;
	if (inst->fbc_buf_count != v4l2_m2m_num_dst_bufs_ready(m2m_ctx)) {
		struct v4l2_ctrl *ctrl;

		ctrl = v4l2_ctrl_find(&inst->v4l2_ctrl_hdl,
				      V4L2_CID_MIN_BUFFERS_FOR_CAPTURE);
		if (ctrl)
			v4l2_ctrl_s_ctrl(ctrl, inst->fbc_buf_count);
	}

	if (p_dec_info->initial_info_obtained) {
		inst->conf_win.left = initial_info->pic_crop_rect.left;
		inst->conf_win.top = initial_info->pic_crop_rect.top;
		inst->conf_win.width = initial_info->pic_width -
			initial_info->pic_crop_rect.left - initial_info->pic_crop_rect.right;
		inst->conf_win.height = initial_info->pic_height -
			initial_info->pic_crop_rect.top - initial_info->pic_crop_rect.bottom;

		wave5_update_pix_fmt(&inst->src_fmt, initial_info->pic_width,
				     initial_info->pic_height);
		wave5_update_pix_fmt(&inst->dst_fmt, initial_info->pic_width,
				     initial_info->pic_height);
	}

	v4l2_event_queue_fh(fh, &vpu_event_src_ch);

	return 0;
}

static void wave5_vpu_dec_finish_decode(struct vpu_instance *inst)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct dec_output_info dec_info;
	int ret;
	struct vb2_v4l2_buffer *dec_buf = NULL;
	struct vb2_v4l2_buffer *disp_buf = NULL;
	struct vb2_queue *dst_vq = v4l2_m2m_get_dst_vq(m2m_ctx);
	struct queue_status_info q_status;

	dev_dbg(inst->dev->dev, "%s: Fetch output info from firmware.", __func__);

	ret = wave5_vpu_dec_get_output_info(inst, &dec_info);
	if (ret) {
		dev_warn(inst->dev->dev, "%s: could not get output info.", __func__);
		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
		return;
	}

	dev_dbg(inst->dev->dev, "%s: rd_ptr %pad wr_ptr %pad", __func__, &dec_info.rd_ptr,
		&dec_info.wr_ptr);
	wave5_handle_src_buffer(inst, dec_info.rd_ptr);

	dev_dbg(inst->dev->dev, "%s: dec_info dec_idx %i disp_idx %i", __func__,
		dec_info.index_frame_decoded, dec_info.index_frame_display);

	if (!vb2_is_streaming(dst_vq)) {
		dev_dbg(inst->dev->dev, "%s: capture is not streaming..", __func__);
		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
		return;
	}

	/* Remove decoded buffer from the ready queue now that it has been
	 * decoded.
	 */
	if (dec_info.index_frame_decoded >= 0) {
		struct vb2_buffer *vb = vb2_get_buffer(dst_vq,
						       dec_info.index_frame_decoded);
		if (vb) {
			dec_buf = to_vb2_v4l2_buffer(vb);
			dec_buf->vb2_buf.timestamp = inst->timestamp;
		} else {
			dev_warn(inst->dev->dev, "%s: invalid decoded frame index %i",
				 __func__, dec_info.index_frame_decoded);
		}
	}

	if (dec_info.index_frame_display >= 0) {
		disp_buf = v4l2_m2m_dst_buf_remove_by_idx(m2m_ctx, dec_info.index_frame_display);
		if (!disp_buf)
			dev_warn(inst->dev->dev, "%s: invalid display frame index %i",
				 __func__, dec_info.index_frame_display);
	}

	/* If there is anything to display, do that now */
	if (disp_buf) {
		struct vpu_dst_buffer *dst_vpu_buf = wave5_to_vpu_dst_buf(disp_buf);

		if (inst->dst_fmt.num_planes == 1) {
			vb2_set_plane_payload(&disp_buf->vb2_buf, 0,
					      inst->dst_fmt.plane_fmt[0].sizeimage);
		} else if (inst->dst_fmt.num_planes == 2) {
			vb2_set_plane_payload(&disp_buf->vb2_buf, 0,
					      inst->dst_fmt.plane_fmt[0].sizeimage);
			vb2_set_plane_payload(&disp_buf->vb2_buf, 1,
					      inst->dst_fmt.plane_fmt[1].sizeimage);
		} else if (inst->dst_fmt.num_planes == 3) {
			vb2_set_plane_payload(&disp_buf->vb2_buf, 0,
					      inst->dst_fmt.plane_fmt[0].sizeimage);
			vb2_set_plane_payload(&disp_buf->vb2_buf, 1,
					      inst->dst_fmt.plane_fmt[1].sizeimage);
			vb2_set_plane_payload(&disp_buf->vb2_buf, 2,
					      inst->dst_fmt.plane_fmt[2].sizeimage);
		}

		/* TODO implement interlace support */
		disp_buf->field = V4L2_FIELD_NONE;
		dst_vpu_buf->display = true;
		v4l2_m2m_buf_done(disp_buf, VB2_BUF_STATE_DONE);

		dev_dbg(inst->dev->dev, "%s: frame_cycle %8u (payload %lu)\n",
			__func__, dec_info.frame_cycle,
			vb2_get_plane_payload(&disp_buf->vb2_buf, 0));
	}

	if ((dec_info.index_frame_display == DISPLAY_IDX_FLAG_SEQ_END ||
	     dec_info.sequence_changed)) {
		unsigned long flags;

		spin_lock_irqsave(&inst->state_spinlock, flags);
		if (!v4l2_m2m_has_stopped(m2m_ctx)) {
			switch_state(inst, VPU_INST_STATE_STOP);

			if (dec_info.sequence_changed)
				handle_dynamic_resolution_change(inst);
			else
				send_eos_event(inst);

			flag_last_buffer_done(inst);
		}
		spin_unlock_irqrestore(&inst->state_spinlock, flags);
	}

	/*
	 * During a resolution change and while draining, the firmware may flush
	 * the reorder queue regardless of having a matching decoding operation
	 * pending. Only terminate the job if there are no more IRQ coming.
	 */
	wave5_vpu_dec_give_command(inst, DEC_GET_QUEUE_STATUS, &q_status);
	if (q_status.report_queue_count == 0 &&
	    (q_status.instance_queue_count == 0 || dec_info.sequence_changed)) {
		dev_dbg(inst->dev->dev, "%s: finishing job.\n", __func__);
		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
	}
}

static int wave5_vpu_dec_querycap(struct file *file, void *fh, struct v4l2_capability *cap)
{
	strscpy(cap->driver, VPU_DEC_DRV_NAME, sizeof(cap->driver));
	strscpy(cap->card, VPU_DEC_DRV_NAME, sizeof(cap->card));

	return 0;
}

static int wave5_vpu_dec_enum_framesizes(struct file *f, void *fh, struct v4l2_frmsizeenum *fsize)
{
	const struct vpu_format *vpu_fmt;

	if (fsize->index)
		return -EINVAL;

	vpu_fmt = wave5_find_vpu_fmt(fsize->pixel_format, dec_fmt_list[VPU_FMT_TYPE_CODEC]);
	if (!vpu_fmt) {
		vpu_fmt = wave5_find_vpu_fmt(fsize->pixel_format, dec_fmt_list[VPU_FMT_TYPE_RAW]);
		if (!vpu_fmt)
			return -EINVAL;
	}

	fsize->type = V4L2_FRMSIZE_TYPE_CONTINUOUS;
	fsize->stepwise.min_width = vpu_fmt->min_width;
	fsize->stepwise.max_width = vpu_fmt->max_width;
	fsize->stepwise.step_width = 1;
	fsize->stepwise.min_height = vpu_fmt->min_height;
	fsize->stepwise.max_height = vpu_fmt->max_height;
	fsize->stepwise.step_height = 1;

	return 0;
}

static int wave5_vpu_dec_enum_fmt_cap(struct file *file, void *fh, struct v4l2_fmtdesc *f)
{
	const struct vpu_format *vpu_fmt;

	vpu_fmt = wave5_find_vpu_fmt_by_idx(f->index, dec_fmt_list[VPU_FMT_TYPE_RAW]);
	if (!vpu_fmt)
		return -EINVAL;

	f->pixelformat = vpu_fmt->v4l2_pix_fmt;
	f->flags = 0;

	return 0;
}

static int wave5_vpu_dec_try_fmt_cap(struct file *file, void *fh, struct v4l2_format *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	struct dec_info *p_dec_info = &inst->codec_info->dec_info;
	const struct vpu_format *vpu_fmt;
	int width, height;

	dev_dbg(inst->dev->dev,
		"%s: fourcc: %u width: %u height: %u nm planes: %u colorspace: %u field: %u\n",
		__func__, f->fmt.pix_mp.pixelformat, f->fmt.pix_mp.width, f->fmt.pix_mp.height,
		f->fmt.pix_mp.num_planes, f->fmt.pix_mp.colorspace, f->fmt.pix_mp.field);

	vpu_fmt = wave5_find_vpu_fmt(f->fmt.pix_mp.pixelformat, dec_fmt_list[VPU_FMT_TYPE_RAW]);
	if (!vpu_fmt) {
		width = inst->dst_fmt.width;
		height = inst->dst_fmt.height;
		f->fmt.pix_mp.pixelformat = inst->dst_fmt.pixelformat;
		f->fmt.pix_mp.num_planes = inst->dst_fmt.num_planes;
	} else {
		const struct v4l2_format_info *info = v4l2_format_info(vpu_fmt->v4l2_pix_fmt);

		width = clamp(f->fmt.pix_mp.width, vpu_fmt->min_width, vpu_fmt->max_width);
		height = clamp(f->fmt.pix_mp.height, vpu_fmt->min_height, vpu_fmt->max_height);
		f->fmt.pix_mp.pixelformat = vpu_fmt->v4l2_pix_fmt;
		f->fmt.pix_mp.num_planes = info->mem_planes;
	}

	if (p_dec_info->initial_info_obtained) {
		width = inst->dst_fmt.width;
		height = inst->dst_fmt.height;
	}

	wave5_update_pix_fmt(&f->fmt.pix_mp, width, height);
	f->fmt.pix_mp.flags = 0;
	f->fmt.pix_mp.field = V4L2_FIELD_NONE;
	f->fmt.pix_mp.colorspace = inst->colorspace;
	f->fmt.pix_mp.ycbcr_enc = inst->ycbcr_enc;
	f->fmt.pix_mp.quantization = inst->quantization;
	f->fmt.pix_mp.xfer_func = inst->xfer_func;

	return 0;
}

static int wave5_vpu_dec_s_fmt_cap(struct file *file, void *fh, struct v4l2_format *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	int i, ret;

	dev_dbg(inst->dev->dev,
		"%s: fourcc: %u width: %u height: %u num_planes: %u colorspace: %u field: %u\n",
		__func__, f->fmt.pix_mp.pixelformat, f->fmt.pix_mp.width, f->fmt.pix_mp.height,
		f->fmt.pix_mp.num_planes, f->fmt.pix_mp.colorspace, f->fmt.pix_mp.field);

	ret = wave5_vpu_dec_try_fmt_cap(file, fh, f);
	if (ret)
		return ret;

	inst->dst_fmt.width = f->fmt.pix_mp.width;
	inst->dst_fmt.height = f->fmt.pix_mp.height;
	inst->dst_fmt.pixelformat = f->fmt.pix_mp.pixelformat;
	inst->dst_fmt.field = f->fmt.pix_mp.field;
	inst->dst_fmt.flags = f->fmt.pix_mp.flags;
	inst->dst_fmt.num_planes = f->fmt.pix_mp.num_planes;
	for (i = 0; i < inst->dst_fmt.num_planes; i++) {
		inst->dst_fmt.plane_fmt[i].bytesperline = f->fmt.pix_mp.plane_fmt[i].bytesperline;
		inst->dst_fmt.plane_fmt[i].sizeimage = f->fmt.pix_mp.plane_fmt[i].sizeimage;
	}

	if (inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV12 ||
	    inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV12M) {
		inst->cbcr_interleave = true;
		inst->nv21 = false;
		inst->output_format = FORMAT_420;
	} else if (inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV21 ||
		   inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV21M) {
		inst->cbcr_interleave = true;
		inst->nv21 = true;
		inst->output_format = FORMAT_420;
	} else if (inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV16 ||
		   inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV16M) {
		inst->cbcr_interleave = true;
		inst->nv21 = false;
		inst->output_format = FORMAT_422;
	} else if (inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV61 ||
		   inst->dst_fmt.pixelformat == V4L2_PIX_FMT_NV61M) {
		inst->cbcr_interleave = true;
		inst->nv21 = true;
		inst->output_format = FORMAT_422;
	} else if (inst->dst_fmt.pixelformat == V4L2_PIX_FMT_YUV422P ||
		   inst->dst_fmt.pixelformat == V4L2_PIX_FMT_YUV422M) {
		inst->cbcr_interleave = false;
		inst->nv21 = false;
		inst->output_format = FORMAT_422;
	} else {
		inst->cbcr_interleave = false;
		inst->nv21 = false;
		inst->output_format = FORMAT_420;
	}

	return 0;
}

static int wave5_vpu_dec_g_fmt_cap(struct file *file, void *fh, struct v4l2_format *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	int i;

	f->fmt.pix_mp.width = inst->dst_fmt.width;
	f->fmt.pix_mp.height = inst->dst_fmt.height;
	f->fmt.pix_mp.pixelformat = inst->dst_fmt.pixelformat;
	f->fmt.pix_mp.field = inst->dst_fmt.field;
	f->fmt.pix_mp.flags = inst->dst_fmt.flags;
	f->fmt.pix_mp.num_planes = inst->dst_fmt.num_planes;
	for (i = 0; i < f->fmt.pix_mp.num_planes; i++) {
		f->fmt.pix_mp.plane_fmt[i].bytesperline = inst->dst_fmt.plane_fmt[i].bytesperline;
		f->fmt.pix_mp.plane_fmt[i].sizeimage = inst->dst_fmt.plane_fmt[i].sizeimage;
	}

	f->fmt.pix_mp.colorspace = inst->colorspace;
	f->fmt.pix_mp.ycbcr_enc = inst->ycbcr_enc;
	f->fmt.pix_mp.quantization = inst->quantization;
	f->fmt.pix_mp.xfer_func = inst->xfer_func;

	return 0;
}

static int wave5_vpu_dec_enum_fmt_out(struct file *file, void *fh, struct v4l2_fmtdesc *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	const struct vpu_format *vpu_fmt;

	dev_dbg(inst->dev->dev, "%s: index: %u\n", __func__, f->index);

	vpu_fmt = wave5_find_vpu_fmt_by_idx(f->index, dec_fmt_list[VPU_FMT_TYPE_CODEC]);
	if (!vpu_fmt)
		return -EINVAL;

	f->pixelformat = vpu_fmt->v4l2_pix_fmt;
	f->flags = V4L2_FMT_FLAG_DYN_RESOLUTION | V4L2_FMT_FLAG_COMPRESSED;

	return 0;
}

static int wave5_vpu_dec_try_fmt_out(struct file *file, void *fh, struct v4l2_format *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	const struct vpu_format *vpu_fmt;

	dev_dbg(inst->dev->dev,
		"%s: fourcc: %u width: %u height: %u num_planes: %u colorspace: %u field: %u\n",
		__func__, f->fmt.pix_mp.pixelformat, f->fmt.pix_mp.width, f->fmt.pix_mp.height,
		f->fmt.pix_mp.num_planes, f->fmt.pix_mp.colorspace, f->fmt.pix_mp.field);

	vpu_fmt = wave5_find_vpu_fmt(f->fmt.pix_mp.pixelformat, dec_fmt_list[VPU_FMT_TYPE_CODEC]);
	if (!vpu_fmt) {
		f->fmt.pix_mp.pixelformat = inst->src_fmt.pixelformat;
		f->fmt.pix_mp.num_planes = inst->src_fmt.num_planes;
		wave5_update_pix_fmt(&f->fmt.pix_mp, inst->src_fmt.width, inst->src_fmt.height);
	} else {
		int width = clamp(f->fmt.pix_mp.width, vpu_fmt->min_width, vpu_fmt->max_width);
		int height = clamp(f->fmt.pix_mp.height, vpu_fmt->min_height, vpu_fmt->max_height);

		f->fmt.pix_mp.pixelformat = vpu_fmt->v4l2_pix_fmt;
		f->fmt.pix_mp.num_planes = 1;
		wave5_update_pix_fmt(&f->fmt.pix_mp, width, height);
	}

	f->fmt.pix_mp.flags = 0;
	f->fmt.pix_mp.field = V4L2_FIELD_NONE;

	return 0;
}

static int wave5_vpu_dec_s_fmt_out(struct file *file, void *fh, struct v4l2_format *f)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	int i, ret;

	dev_dbg(inst->dev->dev,
		"%s: fourcc: %u width: %u height: %u num_planes: %u field: %u\n",
		__func__, f->fmt.pix_mp.pixelformat, f->fmt.pix_mp.width, f->fmt.pix_mp.height,
		f->fmt.pix_mp.num_planes, f->fmt.pix_mp.field);

	ret = wave5_vpu_dec_try_fmt_out(file, fh, f);
	if (ret)
		return ret;

	inst->std = wave5_to_vpu_std(f->fmt.pix_mp.pixelformat, inst->type);
	if (inst->std == STD_UNKNOWN) {
		dev_warn(inst->dev->dev, "unsupported pixelformat: %.4s\n",
			 (char *)&f->fmt.pix_mp.pixelformat);
		return -EINVAL;
	}

	inst->src_fmt.width = f->fmt.pix_mp.width;
	inst->src_fmt.height = f->fmt.pix_mp.height;
	inst->src_fmt.pixelformat = f->fmt.pix_mp.pixelformat;
	inst->src_fmt.field = f->fmt.pix_mp.field;
	inst->src_fmt.flags = f->fmt.pix_mp.flags;
	inst->src_fmt.num_planes = f->fmt.pix_mp.num_planes;
	for (i = 0; i < inst->src_fmt.num_planes; i++) {
		inst->src_fmt.plane_fmt[i].bytesperline = f->fmt.pix_mp.plane_fmt[i].bytesperline;
		inst->src_fmt.plane_fmt[i].sizeimage = f->fmt.pix_mp.plane_fmt[i].sizeimage;
	}

	inst->colorspace = f->fmt.pix_mp.colorspace;
	inst->ycbcr_enc = f->fmt.pix_mp.ycbcr_enc;
	inst->quantization = f->fmt.pix_mp.quantization;
	inst->xfer_func = f->fmt.pix_mp.xfer_func;

	wave5_update_pix_fmt(&inst->dst_fmt, f->fmt.pix_mp.width, f->fmt.pix_mp.height);

	return 0;
}

static int wave5_vpu_dec_g_selection(struct file *file, void *fh, struct v4l2_selection *s)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);

	dev_dbg(inst->dev->dev, "%s: type: %u | target: %u\n", __func__, s->type, s->target);

	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
		return -EINVAL;
	switch (s->target) {
	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
	case V4L2_SEL_TGT_COMPOSE_PADDED:
		s->r.left = 0;
		s->r.top = 0;
		s->r.width = inst->dst_fmt.width;
		s->r.height = inst->dst_fmt.height;
		break;
	case V4L2_SEL_TGT_COMPOSE:
	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
		s->r.left = 0;
		s->r.top = 0;
		if (inst->state > VPU_INST_STATE_OPEN) {
			s->r = inst->conf_win;
		} else {
			s->r.width = inst->src_fmt.width;
			s->r.height = inst->src_fmt.height;
		}
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int wave5_vpu_dec_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);

	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
		return -EINVAL;

	if (s->target != V4L2_SEL_TGT_COMPOSE)
		return -EINVAL;

	dev_dbg(inst->dev->dev, "V4L2_SEL_TGT_COMPOSE w: %u h: %u\n",
		s->r.width, s->r.height);

	s->r.left = 0;
	s->r.top = 0;
	s->r.width = inst->dst_fmt.width;
	s->r.height = inst->dst_fmt.height;

	return 0;
}

static int wave5_vpu_dec_stop(struct vpu_instance *inst)
{
	int ret = 0;
	unsigned long flags;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;

	spin_lock_irqsave(&inst->state_spinlock, flags);

	if (m2m_ctx->is_draining) {
		ret = -EBUSY;
		goto unlock_and_return;
	}

	if (inst->state != VPU_INST_STATE_NONE) {
		/*
		 * Temporarily release the state_spinlock so that subsequent
		 * calls do not block on a mutex while inside this spinlock.
		 */
		spin_unlock_irqrestore(&inst->state_spinlock, flags);
		ret = wave5_vpu_dec_set_eos_on_firmware(inst);
		if (ret)
			return ret;

		spin_lock_irqsave(&inst->state_spinlock, flags);
		/*
		 * TODO eliminate this check by using a separate check for
		 * draining triggered by a resolution change.
		 */
		if (m2m_ctx->is_draining) {
			ret = -EBUSY;
			goto unlock_and_return;
		}
	}

	/*
	 * Used to remember the EOS state after the streamoff/on transition on
	 * the capture queue.
	 */
	inst->eos = true;

	if (m2m_ctx->has_stopped)
		goto unlock_and_return;

	m2m_ctx->last_src_buf = v4l2_m2m_last_src_buf(m2m_ctx);
	m2m_ctx->is_draining = true;

	/*
	 * Deferred to device run in case it wasn't in the ring buffer
	 * yet. In other case, we have to send the EOS signal to the
	 * firmware so that any pending PIC_RUN ends without new
	 * bitstream buffer.
	 */
	if (m2m_ctx->last_src_buf)
		goto unlock_and_return;

	if (inst->state == VPU_INST_STATE_NONE) {
		send_eos_event(inst);
		flag_last_buffer_done(inst);
	}

unlock_and_return:
	spin_unlock_irqrestore(&inst->state_spinlock, flags);
	return ret;
}

static int wave5_vpu_dec_start(struct vpu_instance *inst)
{
	int ret = 0;
	unsigned long flags;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct vb2_queue *dst_vq = v4l2_m2m_get_dst_vq(m2m_ctx);

	spin_lock_irqsave(&inst->state_spinlock, flags);

	if (m2m_ctx->is_draining) {
		ret = -EBUSY;
		goto unlock_and_return;
	}

	if (m2m_ctx->has_stopped)
		m2m_ctx->has_stopped = false;

	vb2_clear_last_buffer_dequeued(dst_vq);
	inst->eos = false;

unlock_and_return:
	spin_unlock_irqrestore(&inst->state_spinlock, flags);
	return ret;
}

static int wave5_vpu_dec_decoder_cmd(struct file *file, void *fh, struct v4l2_decoder_cmd *dc)
{
	struct vpu_instance *inst = wave5_to_vpu_inst(fh);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	int ret;

	dev_dbg(inst->dev->dev, "decoder command: %u\n", dc->cmd);

	ret = v4l2_m2m_ioctl_try_decoder_cmd(file, fh, dc);
	if (ret)
		return ret;

	switch (dc->cmd) {
	case V4L2_DEC_CMD_STOP:
		ret = wave5_vpu_dec_stop(inst);
		/* Just in case we don't have anything to decode anymore */
		v4l2_m2m_try_schedule(m2m_ctx);
		break;
	case V4L2_DEC_CMD_START:
		ret = wave5_vpu_dec_start(inst);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}

static const struct v4l2_ioctl_ops wave5_vpu_dec_ioctl_ops = {
	.vidioc_querycap = wave5_vpu_dec_querycap,
	.vidioc_enum_framesizes = wave5_vpu_dec_enum_framesizes,

	.vidioc_enum_fmt_vid_cap	= wave5_vpu_dec_enum_fmt_cap,
	.vidioc_s_fmt_vid_cap_mplane = wave5_vpu_dec_s_fmt_cap,
	.vidioc_g_fmt_vid_cap_mplane = wave5_vpu_dec_g_fmt_cap,
	.vidioc_try_fmt_vid_cap_mplane = wave5_vpu_dec_try_fmt_cap,

	.vidioc_enum_fmt_vid_out	= wave5_vpu_dec_enum_fmt_out,
	.vidioc_s_fmt_vid_out_mplane = wave5_vpu_dec_s_fmt_out,
	.vidioc_g_fmt_vid_out_mplane = wave5_vpu_g_fmt_out,
	.vidioc_try_fmt_vid_out_mplane = wave5_vpu_dec_try_fmt_out,

	.vidioc_g_selection = wave5_vpu_dec_g_selection,
	.vidioc_s_selection = wave5_vpu_dec_s_selection,

	.vidioc_reqbufs = v4l2_m2m_ioctl_reqbufs,
	/*
	 * Firmware does not support CREATE_BUFS for CAPTURE queue. Since
	 * there is no immediate use-case for supporting CREATE_BUFS on
	 * just the OUTPUT queue, disable CREATE_BUFS altogether.
	 */
	.vidioc_querybuf = v4l2_m2m_ioctl_querybuf,
	.vidioc_prepare_buf = v4l2_m2m_ioctl_prepare_buf,
	.vidioc_qbuf = v4l2_m2m_ioctl_qbuf,
	.vidioc_expbuf = v4l2_m2m_ioctl_expbuf,
	.vidioc_dqbuf = v4l2_m2m_ioctl_dqbuf,
	.vidioc_streamon = v4l2_m2m_ioctl_streamon,
	.vidioc_streamoff = v4l2_m2m_ioctl_streamoff,

	.vidioc_try_decoder_cmd = v4l2_m2m_ioctl_try_decoder_cmd,
	.vidioc_decoder_cmd = wave5_vpu_dec_decoder_cmd,

	.vidioc_subscribe_event = wave5_vpu_subscribe_event,
	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
};

static int wave5_vpu_dec_queue_setup(struct vb2_queue *q, unsigned int *num_buffers,
				     unsigned int *num_planes, unsigned int sizes[],
				     struct device *alloc_devs[])
{
	struct vpu_instance *inst = vb2_get_drv_priv(q);
	struct v4l2_pix_format_mplane inst_format =
		(q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) ? inst->src_fmt : inst->dst_fmt;

	dev_dbg(inst->dev->dev, "%s: num_buffers: %u | num_planes: %u | type: %u\n", __func__,
		*num_buffers, *num_planes, q->type);

	*num_planes = inst_format.num_planes;

	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
		sizes[0] = inst_format.plane_fmt[0].sizeimage;
		dev_dbg(inst->dev->dev, "%s: size[0]: %u\n", __func__, sizes[0]);
	} else if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
		if (*num_buffers < inst->fbc_buf_count)
			*num_buffers = inst->fbc_buf_count;

		if (*num_planes == 1) {
			if (inst->output_format == FORMAT_422)
				sizes[0] = inst_format.width * inst_format.height * 2;
			else
				sizes[0] = inst_format.width * inst_format.height * 3 / 2;
			dev_dbg(inst->dev->dev, "%s: size[0]: %u\n", __func__, sizes[0]);
		} else if (*num_planes == 2) {
			sizes[0] = inst_format.width * inst_format.height;
			if (inst->output_format == FORMAT_422)
				sizes[1] = inst_format.width * inst_format.height;
			else
				sizes[1] = inst_format.width * inst_format.height / 2;
			dev_dbg(inst->dev->dev, "%s: size[0]: %u | size[1]: %u\n",
				__func__, sizes[0], sizes[1]);
		} else if (*num_planes == 3) {
			sizes[0] = inst_format.width * inst_format.height;
			if (inst->output_format == FORMAT_422) {
				sizes[1] = inst_format.width * inst_format.height / 2;
				sizes[2] = inst_format.width * inst_format.height / 2;
			} else {
				sizes[1] = inst_format.width * inst_format.height / 4;
				sizes[2] = inst_format.width * inst_format.height / 4;
			}
			dev_dbg(inst->dev->dev, "%s: size[0]: %u | size[1]: %u | size[2]: %u\n",
				__func__, sizes[0], sizes[1], sizes[2]);
		}
	}

	return 0;
}

static int wave5_prepare_fb(struct vpu_instance *inst)
{
	int linear_num;
	int non_linear_num;
	int fb_stride = 0, fb_height = 0;
	int luma_size, chroma_size;
	int ret, i;
	struct v4l2_m2m_buffer *buf, *n;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;

	linear_num = v4l2_m2m_num_dst_bufs_ready(m2m_ctx);
	non_linear_num = inst->fbc_buf_count;

	for (i = 0; i < non_linear_num; i++) {
		struct frame_buffer *frame = &inst->frame_buf[i];
		struct vpu_buf *vframe = &inst->frame_vbuf[i];

		fb_stride = inst->dst_fmt.width;
		fb_height = ALIGN(inst->dst_fmt.height, 32);
		luma_size = fb_stride * fb_height;

		chroma_size = ALIGN(fb_stride / 2, 16) * fb_height;

		if (vframe->size == (luma_size + chroma_size))
			continue;

		if (vframe->size)
			wave5_vpu_dec_reset_framebuffer(inst, i);

		vframe->size = luma_size + chroma_size;
		ret = wave5_vdi_allocate_dma_memory(inst->dev, vframe);
		if (ret) {
			dev_dbg(inst->dev->dev,
				"%s: Allocating FBC buf of size %zu, fail: %d\n",
				__func__, vframe->size, ret);
			return ret;
		}

		frame->buf_y = vframe->daddr;
		frame->buf_cb = vframe->daddr + luma_size;
		frame->buf_cr = (dma_addr_t)-1;
		frame->size = vframe->size;
		frame->width = inst->src_fmt.width;
		frame->stride = fb_stride;
		frame->map_type = COMPRESSED_FRAME_MAP;
		frame->update_fb_info = true;
	}
	/* In case the count has reduced, clean up leftover framebuffer memory */
	for (i = non_linear_num; i < MAX_REG_FRAME; i++) {
		ret = wave5_vpu_dec_reset_framebuffer(inst, i);
		if (ret)
			break;
	}

	for (i = 0; i < linear_num; i++) {
		struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
		struct vb2_queue *dst_vq = v4l2_m2m_get_dst_vq(m2m_ctx);
		struct vb2_buffer *vb = vb2_get_buffer(dst_vq, i);
		struct frame_buffer *frame = &inst->frame_buf[non_linear_num + i];
		dma_addr_t buf_addr_y = 0, buf_addr_cb = 0, buf_addr_cr = 0;
		u32 buf_size = 0;
		u32 fb_stride = inst->dst_fmt.width;
		u32 luma_size = fb_stride * inst->dst_fmt.height;
		u32 chroma_size;

		if (inst->output_format == FORMAT_422)
			chroma_size = fb_stride * inst->dst_fmt.height / 2;
		else
			chroma_size = fb_stride * inst->dst_fmt.height / 4;

		if (inst->dst_fmt.num_planes == 1) {
			buf_size = vb2_plane_size(vb, 0);
			buf_addr_y = vb2_dma_contig_plane_dma_addr(vb, 0);
			buf_addr_cb = buf_addr_y + luma_size;
			buf_addr_cr = buf_addr_cb + chroma_size;
		} else if (inst->dst_fmt.num_planes == 2) {
			buf_size = vb2_plane_size(vb, 0) +
				vb2_plane_size(vb, 1);
			buf_addr_y = vb2_dma_contig_plane_dma_addr(vb, 0);
			buf_addr_cb = vb2_dma_contig_plane_dma_addr(vb, 1);
			buf_addr_cr = buf_addr_cb + chroma_size;
		} else if (inst->dst_fmt.num_planes == 3) {
			buf_size = vb2_plane_size(vb, 0) +
				vb2_plane_size(vb, 1) +
				vb2_plane_size(vb, 2);
			buf_addr_y = vb2_dma_contig_plane_dma_addr(vb, 0);
			buf_addr_cb = vb2_dma_contig_plane_dma_addr(vb, 1);
			buf_addr_cr = vb2_dma_contig_plane_dma_addr(vb, 2);
		}

		frame->buf_y = buf_addr_y;
		frame->buf_cb = buf_addr_cb;
		frame->buf_cr = buf_addr_cr;
		frame->size = buf_size;
		frame->width = inst->src_fmt.width;
		frame->stride = fb_stride;
		frame->map_type = LINEAR_FRAME_MAP;
		frame->update_fb_info = true;
	}

	ret = wave5_vpu_dec_register_frame_buffer_ex(inst, non_linear_num, linear_num,
						     fb_stride, inst->dst_fmt.height);
	if (ret) {
		dev_dbg(inst->dev->dev, "%s: vpu_dec_register_frame_buffer_ex fail: %d",
			__func__, ret);
		return ret;
	}

	/*
	 * Mark all frame buffers as out of display, to avoid using them before
	 * the application have them queued.
	 */
	for (i = 0; i < v4l2_m2m_num_dst_bufs_ready(m2m_ctx); i++) {
		ret = wave5_vpu_dec_set_disp_flag(inst, i);
		if (ret) {
			dev_dbg(inst->dev->dev,
				"%s: Setting display flag of buf index: %u, fail: %d\n",
				__func__, i, ret);
		}
	}

	v4l2_m2m_for_each_dst_buf_safe(m2m_ctx, buf, n) {
		struct vb2_v4l2_buffer *vbuf = &buf->vb;

		ret = wave5_vpu_dec_clr_disp_flag(inst, vbuf->vb2_buf.index);
		if (ret)
			dev_dbg(inst->dev->dev,
				"%s: Clearing display flag of buf index: %u, fail: %d\n",
				__func__, i, ret);
	}

	return 0;
}

static int write_to_ringbuffer(struct vpu_instance *inst, void *buffer, size_t buffer_size,
			       struct vpu_buf *ring_buffer, dma_addr_t wr_ptr)
{
	size_t size;
	size_t offset = wr_ptr - ring_buffer->daddr;
	int ret;

	if (wr_ptr + buffer_size > ring_buffer->daddr + ring_buffer->size) {
		size = ring_buffer->daddr + ring_buffer->size - wr_ptr;
		ret = wave5_vdi_write_memory(inst->dev, ring_buffer, offset, (u8 *)buffer, size);
		if (ret < 0)
			return ret;

		ret = wave5_vdi_write_memory(inst->dev, ring_buffer, 0, (u8 *)buffer + size,
					     buffer_size - size);
		if (ret < 0)
			return ret;
	} else {
		ret = wave5_vdi_write_memory(inst->dev, ring_buffer, offset, (u8 *)buffer,
					     buffer_size);
		if (ret < 0)
			return ret;
	}

	return 0;
}

static int fill_ringbuffer(struct vpu_instance *inst)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct v4l2_m2m_buffer *buf, *n;
	int ret;

	if (m2m_ctx->last_src_buf)  {
		struct vpu_src_buffer *vpu_buf = wave5_to_vpu_src_buf(m2m_ctx->last_src_buf);

		if (vpu_buf->consumed) {
			dev_dbg(inst->dev->dev, "last src buffer already written\n");
			return 0;
		}
	}

	v4l2_m2m_for_each_src_buf_safe(m2m_ctx, buf, n) {
		struct vb2_v4l2_buffer *vbuf = &buf->vb;
		struct vpu_src_buffer *vpu_buf = wave5_to_vpu_src_buf(vbuf);
		struct vpu_buf *ring_buffer = &inst->bitstream_vbuf;
		size_t src_size = vb2_get_plane_payload(&vbuf->vb2_buf, 0);
		void *src_buf = vb2_plane_vaddr(&vbuf->vb2_buf, 0);
		dma_addr_t rd_ptr = 0;
		dma_addr_t wr_ptr = 0;
		size_t remain_size = 0;

		if (vpu_buf->consumed) {
			dev_dbg(inst->dev->dev, "already copied src buf (%u) to the ring buffer\n",
				vbuf->vb2_buf.index);
			continue;
		}

		if (!src_buf) {
			dev_dbg(inst->dev->dev,
				"%s: Acquiring kernel pointer to src buf (%u), fail\n",
				__func__, vbuf->vb2_buf.index);
			break;
		}

		ret = wave5_vpu_dec_get_bitstream_buffer(inst, &rd_ptr, &wr_ptr, &remain_size);
		if (ret) {
			/* Unable to acquire the mutex */
			dev_err(inst->dev->dev, "Getting the bitstream buffer, fail: %d\n",
				ret);
			return ret;
		}

		dev_dbg(inst->dev->dev, "%s: rd_ptr %pad wr_ptr %pad", __func__, &rd_ptr, &wr_ptr);

		if (remain_size < src_size) {
			dev_dbg(inst->dev->dev,
				"%s: remaining size: %zu < source size: %zu for src buf (%u)\n",
				__func__, remain_size, src_size, vbuf->vb2_buf.index);
			break;
		}

		ret = write_to_ringbuffer(inst, src_buf, src_size, ring_buffer, wr_ptr);
		if (ret) {
			dev_err(inst->dev->dev, "Write src buf (%u) to ring buffer, fail: %d\n",
				vbuf->vb2_buf.index, ret);
			return ret;
		}

		ret = wave5_vpu_dec_update_bitstream_buffer(inst, src_size);
		if (ret) {
			dev_dbg(inst->dev->dev,
				"update_bitstream_buffer fail: %d for src buf (%u)\n",
				ret, vbuf->vb2_buf.index);
			break;
		}

		vpu_buf->consumed = true;

		/* Don't write buffers passed the last one while draining. */
		if (v4l2_m2m_is_last_draining_src_buf(m2m_ctx, vbuf)) {
			dev_dbg(inst->dev->dev, "last src buffer written to the ring buffer\n");
			break;
		}
	}

	return 0;
}

static void wave5_vpu_dec_buf_queue_src(struct vb2_buffer *vb)
{
	struct vpu_instance *inst = vb2_get_drv_priv(vb->vb2_queue);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpu_src_buffer *vpu_buf = wave5_to_vpu_src_buf(vbuf);

	vpu_buf->consumed = false;
	vbuf->sequence = inst->queued_src_buf_num++;

	v4l2_m2m_buf_queue(m2m_ctx, vbuf);
}

static void wave5_vpu_dec_buf_queue_dst(struct vb2_buffer *vb)
{
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpu_instance *inst = vb2_get_drv_priv(vb->vb2_queue);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;

	vbuf->sequence = inst->queued_dst_buf_num++;

	if (inst->state == VPU_INST_STATE_PIC_RUN) {
		struct vpu_dst_buffer *vpu_buf = wave5_to_vpu_dst_buf(vbuf);
		int ret;

		/*
		 * The buffer is already registered just clear the display flag
		 * to let the firmware know it can be used.
		 */
		vpu_buf->display = false;
		ret = wave5_vpu_dec_clr_disp_flag(inst, vb->index);
		if (ret) {
			dev_dbg(inst->dev->dev,
				"%s: Clearing the display flag of buffer index: %u, fail: %d\n",
				__func__, vb->index, ret);
		}
	}

	if (vb2_is_streaming(vb->vb2_queue) && v4l2_m2m_dst_buf_is_last(m2m_ctx)) {
		unsigned int i;

		for (i = 0; i < vb->num_planes; i++)
			vb2_set_plane_payload(vb, i, 0);

		vbuf->field = V4L2_FIELD_NONE;

		send_eos_event(inst);
		v4l2_m2m_last_buffer_done(m2m_ctx, vbuf);
	} else {
		v4l2_m2m_buf_queue(m2m_ctx, vbuf);
	}
}

static void wave5_vpu_dec_buf_queue(struct vb2_buffer *vb)
{
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpu_instance *inst = vb2_get_drv_priv(vb->vb2_queue);

	dev_dbg(inst->dev->dev, "%s: type: %4u index: %4u size: ([0]=%4lu, [1]=%4lu, [2]=%4lu)\n",
		__func__, vb->type, vb->index, vb2_plane_size(&vbuf->vb2_buf, 0),
		vb2_plane_size(&vbuf->vb2_buf, 1), vb2_plane_size(&vbuf->vb2_buf, 2));

	if (vb->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
		wave5_vpu_dec_buf_queue_src(vb);
	else if (vb->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
		wave5_vpu_dec_buf_queue_dst(vb);
}

static int wave5_vpu_dec_allocate_ring_buffer(struct vpu_instance *inst)
{
	int ret;
	struct vpu_buf *ring_buffer = &inst->bitstream_vbuf;

	ring_buffer->size = ALIGN(inst->src_fmt.plane_fmt[0].sizeimage, 1024) * 4;
	ret = wave5_vdi_allocate_dma_memory(inst->dev, ring_buffer);
	if (ret) {
		dev_dbg(inst->dev->dev, "%s: allocate ring buffer of size %zu fail: %d\n",
			__func__, ring_buffer->size, ret);
		return ret;
	}

	inst->last_rd_ptr = ring_buffer->daddr;

	return 0;
}

static int wave5_vpu_dec_start_streaming(struct vb2_queue *q, unsigned int count)
{
	struct vpu_instance *inst = vb2_get_drv_priv(q);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	int ret = 0;

	dev_dbg(inst->dev->dev, "%s: type: %u\n", __func__, q->type);

	v4l2_m2m_update_start_streaming_state(m2m_ctx, q);

	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE && inst->state == VPU_INST_STATE_NONE) {
		struct dec_open_param open_param;

		memset(&open_param, 0, sizeof(struct dec_open_param));

		ret = wave5_vpu_dec_allocate_ring_buffer(inst);
		if (ret)
			goto return_buffers;

		open_param.bitstream_buffer = inst->bitstream_vbuf.daddr;
		open_param.bitstream_buffer_size = inst->bitstream_vbuf.size;

		ret = wave5_vpu_dec_open(inst, &open_param);
		if (ret) {
			dev_dbg(inst->dev->dev, "%s: decoder opening, fail: %d\n",
				__func__, ret);
			goto free_bitstream_vbuf;
		}

		ret = switch_state(inst, VPU_INST_STATE_OPEN);
		if (ret)
			goto free_bitstream_vbuf;
	} else if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
		struct dec_initial_info *initial_info =
			&inst->codec_info->dec_info.initial_info;

		if (inst->state == VPU_INST_STATE_STOP)
			ret = switch_state(inst, VPU_INST_STATE_INIT_SEQ);
		if (ret)
			goto return_buffers;

		if (inst->state == VPU_INST_STATE_INIT_SEQ) {
			if (initial_info->luma_bitdepth != 8) {
				dev_info(inst->dev->dev, "%s: no support for %d bit depth",
					 __func__, initial_info->luma_bitdepth);
				ret = -EINVAL;
				goto return_buffers;
			}
		}
	}

	return ret;

free_bitstream_vbuf:
	wave5_vdi_free_dma_memory(inst->dev, &inst->bitstream_vbuf);
return_buffers:
	wave5_return_bufs(q, VB2_BUF_STATE_QUEUED);
	return ret;
}

static int streamoff_output(struct vb2_queue *q)
{
	struct vpu_instance *inst = vb2_get_drv_priv(q);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct vb2_v4l2_buffer *buf;
	int ret;
	dma_addr_t new_rd_ptr;

	while ((buf = v4l2_m2m_src_buf_remove(m2m_ctx))) {
		dev_dbg(inst->dev->dev, "%s: (Multiplanar) buf type %4u | index %4u\n",
			__func__, buf->vb2_buf.type, buf->vb2_buf.index);
		v4l2_m2m_buf_done(buf, VB2_BUF_STATE_ERROR);
	}

	ret = wave5_vpu_flush_instance(inst);
	if (ret)
		return ret;

	/* Reset the ring buffer information */
	new_rd_ptr = wave5_vpu_dec_get_rd_ptr(inst);
	inst->last_rd_ptr = new_rd_ptr;
	inst->codec_info->dec_info.stream_rd_ptr = new_rd_ptr;
	inst->codec_info->dec_info.stream_wr_ptr = new_rd_ptr;

	if (v4l2_m2m_has_stopped(m2m_ctx))
		send_eos_event(inst);

	/* streamoff on output cancels any draining operation */
	inst->eos = false;

	return 0;
}

static int streamoff_capture(struct vb2_queue *q)
{
	struct vpu_instance *inst = vb2_get_drv_priv(q);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct vb2_v4l2_buffer *buf;
	unsigned int i;
	int ret = 0;

	for (i = 0; i < v4l2_m2m_num_dst_bufs_ready(m2m_ctx); i++) {
		ret = wave5_vpu_dec_set_disp_flag(inst, i);
		if (ret)
			dev_dbg(inst->dev->dev,
				"%s: Setting display flag of buf index: %u, fail: %d\n",
				__func__, i, ret);
	}

	while ((buf = v4l2_m2m_dst_buf_remove(m2m_ctx))) {
		u32 plane;

		dev_dbg(inst->dev->dev, "%s: buf type %4u | index %4u\n",
			__func__, buf->vb2_buf.type, buf->vb2_buf.index);

		for (plane = 0; plane < inst->dst_fmt.num_planes; plane++)
			vb2_set_plane_payload(&buf->vb2_buf, plane, 0);

		v4l2_m2m_buf_done(buf, VB2_BUF_STATE_ERROR);
	}

	if (inst->needs_reallocation) {
		wave5_vpu_dec_give_command(inst, DEC_RESET_FRAMEBUF_INFO, NULL);
		inst->needs_reallocation = false;
	}

	if (v4l2_m2m_has_stopped(m2m_ctx)) {
		ret = switch_state(inst, VPU_INST_STATE_INIT_SEQ);
		if (ret)
			return ret;
	}

	return 0;
}

static void wave5_vpu_dec_stop_streaming(struct vb2_queue *q)
{
	struct vpu_instance *inst = vb2_get_drv_priv(q);
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	bool check_cmd = TRUE;

	dev_dbg(inst->dev->dev, "%s: type: %u\n", __func__, q->type);

	while (check_cmd) {
		struct queue_status_info q_status;
		struct dec_output_info dec_output_info;

		wave5_vpu_dec_give_command(inst, DEC_GET_QUEUE_STATUS, &q_status);

		if (q_status.report_queue_count == 0)
			break;

		if (wave5_vpu_wait_interrupt(inst, VPU_DEC_TIMEOUT) < 0)
			break;

		if (wave5_vpu_dec_get_output_info(inst, &dec_output_info))
			dev_dbg(inst->dev->dev, "Getting decoding results from fw, fail\n");
	}

	v4l2_m2m_update_stop_streaming_state(m2m_ctx, q);

	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
		streamoff_output(q);
	else
		streamoff_capture(q);
}

static const struct vb2_ops wave5_vpu_dec_vb2_ops = {
	.queue_setup = wave5_vpu_dec_queue_setup,
	.wait_prepare = vb2_ops_wait_prepare,
	.wait_finish = vb2_ops_wait_finish,
	.buf_queue = wave5_vpu_dec_buf_queue,
	.start_streaming = wave5_vpu_dec_start_streaming,
	.stop_streaming = wave5_vpu_dec_stop_streaming,
};

static void wave5_set_default_format(struct v4l2_pix_format_mplane *src_fmt,
				     struct v4l2_pix_format_mplane *dst_fmt)
{
	unsigned int dst_pix_fmt = dec_fmt_list[VPU_FMT_TYPE_RAW][0].v4l2_pix_fmt;
	const struct v4l2_format_info *dst_fmt_info = v4l2_format_info(dst_pix_fmt);

	src_fmt->pixelformat = dec_fmt_list[VPU_FMT_TYPE_CODEC][0].v4l2_pix_fmt;
	src_fmt->field = V4L2_FIELD_NONE;
	src_fmt->flags = 0;
	src_fmt->num_planes = 1;
	wave5_update_pix_fmt(src_fmt, 720, 480);

	dst_fmt->pixelformat = dst_pix_fmt;
	dst_fmt->field = V4L2_FIELD_NONE;
	dst_fmt->flags = 0;
	dst_fmt->num_planes = dst_fmt_info->mem_planes;
	wave5_update_pix_fmt(dst_fmt, 736, 480);
}

static int wave5_vpu_dec_queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)
{
	return wave5_vpu_queue_init(priv, src_vq, dst_vq, &wave5_vpu_dec_vb2_ops);
}

static const struct vpu_instance_ops wave5_vpu_dec_inst_ops = {
	.finish_process = wave5_vpu_dec_finish_decode,
};

static int initialize_sequence(struct vpu_instance *inst)
{
	struct dec_initial_info initial_info;
	int ret = 0;

	memset(&initial_info, 0, sizeof(struct dec_initial_info));

	ret = wave5_vpu_dec_issue_seq_init(inst);
	if (ret) {
		dev_dbg(inst->dev->dev, "%s: wave5_vpu_dec_issue_seq_init, fail: %d\n",
			__func__, ret);
		return ret;
	}

	if (wave5_vpu_wait_interrupt(inst, VPU_DEC_TIMEOUT) < 0)
		dev_dbg(inst->dev->dev, "%s: failed to call vpu_wait_interrupt()\n", __func__);

	ret = wave5_vpu_dec_complete_seq_init(inst, &initial_info);
	if (ret) {
		dev_dbg(inst->dev->dev, "%s: vpu_dec_complete_seq_init, fail: %d, reason: %u\n",
			__func__, ret, initial_info.seq_init_err_reason);
		wave5_handle_src_buffer(inst, initial_info.rd_ptr);
		return ret;
	}

	handle_dynamic_resolution_change(inst);

	return 0;
}

static bool wave5_is_draining_or_eos(struct vpu_instance *inst)
{
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;

	lockdep_assert_held(&inst->state_spinlock);
	return m2m_ctx->is_draining || inst->eos;
}

static void wave5_vpu_dec_device_run(void *priv)
{
	struct vpu_instance *inst = priv;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	struct queue_status_info q_status;
	u32 fail_res = 0;
	int ret = 0;

	dev_dbg(inst->dev->dev, "%s: Fill the ring buffer with new bitstream data", __func__);

	ret = fill_ringbuffer(inst);
	if (ret) {
		dev_warn(inst->dev->dev, "Filling ring buffer failed\n");
		goto finish_job_and_return;
	}

	switch (inst->state) {
	case VPU_INST_STATE_OPEN:
		ret = initialize_sequence(inst);
		if (ret) {
			unsigned long flags;

			spin_lock_irqsave(&inst->state_spinlock, flags);
			if (wave5_is_draining_or_eos(inst) &&
			    wave5_last_src_buffer_consumed(m2m_ctx)) {
				struct vb2_queue *dst_vq = v4l2_m2m_get_dst_vq(m2m_ctx);

				switch_state(inst, VPU_INST_STATE_STOP);

				if (vb2_is_streaming(dst_vq))
					send_eos_event(inst);
				else
					handle_dynamic_resolution_change(inst);

				flag_last_buffer_done(inst);
			}
			spin_unlock_irqrestore(&inst->state_spinlock, flags);
		} else {
			switch_state(inst, VPU_INST_STATE_INIT_SEQ);
		}

		break;

	case VPU_INST_STATE_INIT_SEQ:
		/*
		 * Do this early, preparing the fb can trigger an IRQ before
		 * we had a chance to switch, which leads to an invalid state
		 * change.
		 */
		switch_state(inst, VPU_INST_STATE_PIC_RUN);

		/*
		 * During DRC, the picture decoding remains pending, so just leave the job
		 * active until this decode operation completes.
		 */
		wave5_vpu_dec_give_command(inst, DEC_GET_QUEUE_STATUS, &q_status);

		/*
		 * The sequence must be analyzed first to calculate the proper
		 * size of the auxiliary buffers.
		 */
		ret = wave5_prepare_fb(inst);
		if (ret) {
			dev_warn(inst->dev->dev, "Framebuffer preparation, fail: %d\n", ret);
			switch_state(inst, VPU_INST_STATE_STOP);
			break;
		}

		if (q_status.instance_queue_count) {
			dev_dbg(inst->dev->dev, "%s: leave with active job", __func__);
			return;
		}

		fallthrough;
	case VPU_INST_STATE_PIC_RUN:
		ret = start_decode(inst, &fail_res);
		if (ret) {
			dev_err(inst->dev->dev,
				"Frame decoding on m2m context (%p), fail: %d (result: %d)\n",
				m2m_ctx, ret, fail_res);
			break;
		}
		/* Return so that we leave this job active */
		dev_dbg(inst->dev->dev, "%s: leave with active job", __func__);
		return;
	default:
		WARN(1, "Execution of a job in state %s illegal.\n", state_to_str(inst->state));
		break;
	}

finish_job_and_return:
	dev_dbg(inst->dev->dev, "%s: leave and finish job", __func__);
	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
}

static void wave5_vpu_dec_job_abort(void *priv)
{
	struct vpu_instance *inst = priv;
	int ret;

	ret = switch_state(inst, VPU_INST_STATE_STOP);
	if (ret)
		return;

	ret = wave5_vpu_dec_set_eos_on_firmware(inst);
	if (ret)
		dev_warn(inst->dev->dev,
			 "Setting EOS for the bitstream, fail: %d\n", ret);
}

static int wave5_vpu_dec_job_ready(void *priv)
{
	struct vpu_instance *inst = priv;
	struct v4l2_m2m_ctx *m2m_ctx = inst->v4l2_fh.m2m_ctx;
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&inst->state_spinlock, flags);

	switch (inst->state) {
	case VPU_INST_STATE_NONE:
		dev_dbg(inst->dev->dev, "Decoder must be open to start queueing M2M jobs!\n");
		break;
	case VPU_INST_STATE_OPEN:
		if (wave5_is_draining_or_eos(inst) || !v4l2_m2m_has_stopped(m2m_ctx) ||
		    v4l2_m2m_num_src_bufs_ready(m2m_ctx) > 0) {
			ret = 1;
			break;
		}

		dev_dbg(inst->dev->dev,
			"Decoder must be draining or >= 1 OUTPUT queue buffer must be queued!\n");
		break;
	case VPU_INST_STATE_INIT_SEQ:
	case VPU_INST_STATE_PIC_RUN:
		if (!m2m_ctx->cap_q_ctx.q.streaming) {
			dev_dbg(inst->dev->dev, "CAPTURE queue must be streaming to queue jobs!\n");
			break;
		} else if (v4l2_m2m_num_dst_bufs_ready(m2m_ctx) < (inst->fbc_buf_count - 1)) {
			dev_dbg(inst->dev->dev,
				"No capture buffer ready to decode!\n");
			break;
		} else if (!wave5_is_draining_or_eos(inst) &&
			   !v4l2_m2m_num_src_bufs_ready(m2m_ctx)) {
			dev_dbg(inst->dev->dev,
				"No bitstream data to decode!\n");
			break;
		}
		ret = 1;
		break;
	case VPU_INST_STATE_STOP:
		dev_dbg(inst->dev->dev, "Decoder is stopped, not running.\n");
		break;
	}

	spin_unlock_irqrestore(&inst->state_spinlock, flags);

	return ret;
}

static const struct v4l2_m2m_ops wave5_vpu_dec_m2m_ops = {
	.device_run = wave5_vpu_dec_device_run,
	.job_abort = wave5_vpu_dec_job_abort,
	.job_ready = wave5_vpu_dec_job_ready,
};

static int wave5_vpu_open_dec(struct file *filp)
{
	struct video_device *vdev = video_devdata(filp);
	struct vpu_device *dev = video_drvdata(filp);
	struct vpu_instance *inst = NULL;
	struct v4l2_m2m_ctx *m2m_ctx;
	int ret = 0;

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

	inst->dev = dev;
	inst->type = VPU_INST_TYPE_DEC;
	inst->ops = &wave5_vpu_dec_inst_ops;

	spin_lock_init(&inst->state_spinlock);

	inst->codec_info = kzalloc(sizeof(*inst->codec_info), GFP_KERNEL);
	if (!inst->codec_info)
		return -ENOMEM;

	v4l2_fh_init(&inst->v4l2_fh, vdev);
	filp->private_data = &inst->v4l2_fh;
	v4l2_fh_add(&inst->v4l2_fh);

	INIT_LIST_HEAD(&inst->list);
	list_add_tail(&inst->list, &dev->instances);

	inst->v4l2_m2m_dev = inst->dev->v4l2_m2m_dec_dev;
	inst->v4l2_fh.m2m_ctx =
		v4l2_m2m_ctx_init(inst->v4l2_m2m_dev, inst, wave5_vpu_dec_queue_init);
	if (IS_ERR(inst->v4l2_fh.m2m_ctx)) {
		ret = PTR_ERR(inst->v4l2_fh.m2m_ctx);
		goto cleanup_inst;
	}
	m2m_ctx = inst->v4l2_fh.m2m_ctx;

	v4l2_m2m_set_src_buffered(m2m_ctx, true);
	v4l2_m2m_set_dst_buffered(m2m_ctx, true);
	/*
	 * We use the M2M job queue to ensure synchronization of steps where
	 * needed, as IOCTLs can occur at anytime and we need to run commands on
	 * the firmware in a specified order.
	 * In order to initialize the sequence on the firmware within an M2M
	 * job, the M2M framework needs to be able to queue jobs before
	 * the CAPTURE queue has been started, because we need the results of the
	 * initialization to properly prepare the CAPTURE queue with the correct
	 * amount of buffers.
	 * By setting ignore_cap_streaming to true the m2m framework will call
	 * job_ready as soon as the OUTPUT queue is streaming, instead of
	 * waiting until both the CAPTURE and OUTPUT queues are streaming.
	 */
	m2m_ctx->ignore_cap_streaming = true;

	v4l2_ctrl_handler_init(&inst->v4l2_ctrl_hdl, 10);
	v4l2_ctrl_new_std(&inst->v4l2_ctrl_hdl, NULL,
			  V4L2_CID_MIN_BUFFERS_FOR_CAPTURE, 1, 32, 1, 1);

	if (inst->v4l2_ctrl_hdl.error) {
		ret = -ENODEV;
		goto cleanup_inst;
	}

	inst->v4l2_fh.ctrl_handler = &inst->v4l2_ctrl_hdl;
	v4l2_ctrl_handler_setup(&inst->v4l2_ctrl_hdl);

	wave5_set_default_format(&inst->src_fmt, &inst->dst_fmt);
	inst->colorspace = V4L2_COLORSPACE_REC709;
	inst->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
	inst->quantization = V4L2_QUANTIZATION_DEFAULT;
	inst->xfer_func = V4L2_XFER_FUNC_DEFAULT;

	init_completion(&inst->irq_done);

	inst->id = ida_alloc(&inst->dev->inst_ida, GFP_KERNEL);
	if (inst->id < 0) {
		dev_warn(inst->dev->dev, "Allocating instance ID, fail: %d\n", inst->id);
		ret = inst->id;
		goto cleanup_inst;
	}

	wave5_vdi_allocate_sram(inst->dev);

	return 0;

cleanup_inst:
	wave5_cleanup_instance(inst);
	return ret;
}

static int wave5_vpu_dec_release(struct file *filp)
{
	return wave5_vpu_release_device(filp, wave5_vpu_dec_close, "decoder");
}

static const struct v4l2_file_operations wave5_vpu_dec_fops = {
	.owner = THIS_MODULE,
	.open = wave5_vpu_open_dec,
	.release = wave5_vpu_dec_release,
	.unlocked_ioctl = video_ioctl2,
	.poll = v4l2_m2m_fop_poll,
	.mmap = v4l2_m2m_fop_mmap,
};

int wave5_vpu_dec_register_device(struct vpu_device *dev)
{
	struct video_device *vdev_dec;
	int ret;

	vdev_dec = devm_kzalloc(dev->v4l2_dev.dev, sizeof(*vdev_dec), GFP_KERNEL);
	if (!vdev_dec)
		return -ENOMEM;

	dev->v4l2_m2m_dec_dev = v4l2_m2m_init(&wave5_vpu_dec_m2m_ops);
	if (IS_ERR(dev->v4l2_m2m_dec_dev)) {
		ret = PTR_ERR(dev->v4l2_m2m_dec_dev);
		dev_err(dev->dev, "v4l2_m2m_init, fail: %d\n", ret);
		return -EINVAL;
	}

	dev->video_dev_dec = vdev_dec;

	strscpy(vdev_dec->name, VPU_DEC_DEV_NAME, sizeof(vdev_dec->name));
	vdev_dec->fops = &wave5_vpu_dec_fops;
	vdev_dec->ioctl_ops = &wave5_vpu_dec_ioctl_ops;
	vdev_dec->release = video_device_release_empty;
	vdev_dec->v4l2_dev = &dev->v4l2_dev;
	vdev_dec->vfl_dir = VFL_DIR_M2M;
	vdev_dec->device_caps = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING;
	vdev_dec->lock = &dev->dev_lock;

	ret = video_register_device(vdev_dec, VFL_TYPE_VIDEO, -1);
	if (ret)
		return ret;

	video_set_drvdata(vdev_dec, dev);

	return 0;
}

void wave5_vpu_dec_unregister_device(struct vpu_device *dev)
{
	video_unregister_device(dev->video_dev_dec);
	if (dev->v4l2_m2m_dec_dev)
		v4l2_m2m_release(dev->v4l2_m2m_dec_dev);
}