summaryrefslogtreecommitdiff
path: root/drivers/media/platform/ti-vpe/vpe.c
blob: c47151495b6f41a52c6331c6729faa07e7c464ad (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
/*
 * TI VPE mem2mem driver, based on the virtual v4l2-mem2mem example driver
 *
 * Copyright (c) 2013 Texas Instruments Inc.
 * David Griego, <dagriego@biglakesoftware.com>
 * Dale Farnsworth, <dale@farnsworth.org>
 * Archit Taneja, <archit@ti.com>
 *
 * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd.
 * Pawel Osciak, <pawel@osciak.com>
 * Marek Szyprowski, <m.szyprowski@samsung.com>
 *
 * Based on the virtual v4l2-mem2mem example device
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published by
 * the Free Software Foundation
 */

#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/ioctl.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/videodev2.h>
#include <linux/log2.h>
#include <linux/sizes.h>

#include <media/v4l2-common.h>
#include <media/v4l2-ctrls.h>
#include <media/v4l2-device.h>
#include <media/v4l2-event.h>
#include <media/v4l2-ioctl.h>
#include <media/v4l2-mem2mem.h>
#include <media/videobuf2-v4l2.h>
#include <media/videobuf2-dma-contig.h>

#include "vpdma.h"
#include "vpdma_priv.h"
#include "vpe_regs.h"
#include "sc.h"
#include "csc.h"

#define VPE_MODULE_NAME "vpe"

/* minimum and maximum frame sizes */
#define MIN_W		32
#define MIN_H		32
#define MAX_W		2048
#define MAX_H		1184

/* required alignments */
#define S_ALIGN		0	/* multiple of 1 */
#define H_ALIGN		1	/* multiple of 2 */

/* flags that indicate a format can be used for capture/output */
#define VPE_FMT_TYPE_CAPTURE	(1 << 0)
#define VPE_FMT_TYPE_OUTPUT	(1 << 1)

/* used as plane indices */
#define VPE_MAX_PLANES	2
#define VPE_LUMA	0
#define VPE_CHROMA	1

/* per m2m context info */
#define VPE_MAX_SRC_BUFS	3	/* need 3 src fields to de-interlace */

#define VPE_DEF_BUFS_PER_JOB	1	/* default one buffer per batch job */

/*
 * each VPE context can need up to 3 config descriptors, 7 input descriptors,
 * 3 output descriptors, and 10 control descriptors
 */
#define VPE_DESC_LIST_SIZE	(10 * VPDMA_DTD_DESC_SIZE +	\
					13 * VPDMA_CFD_CTD_DESC_SIZE)

#define vpe_dbg(vpedev, fmt, arg...)	\
		dev_dbg((vpedev)->v4l2_dev.dev, fmt, ##arg)
#define vpe_err(vpedev, fmt, arg...)	\
		dev_err((vpedev)->v4l2_dev.dev, fmt, ##arg)

struct vpe_us_coeffs {
	unsigned short	anchor_fid0_c0;
	unsigned short	anchor_fid0_c1;
	unsigned short	anchor_fid0_c2;
	unsigned short	anchor_fid0_c3;
	unsigned short	interp_fid0_c0;
	unsigned short	interp_fid0_c1;
	unsigned short	interp_fid0_c2;
	unsigned short	interp_fid0_c3;
	unsigned short	anchor_fid1_c0;
	unsigned short	anchor_fid1_c1;
	unsigned short	anchor_fid1_c2;
	unsigned short	anchor_fid1_c3;
	unsigned short	interp_fid1_c0;
	unsigned short	interp_fid1_c1;
	unsigned short	interp_fid1_c2;
	unsigned short	interp_fid1_c3;
};

/*
 * Default upsampler coefficients
 */
static const struct vpe_us_coeffs us_coeffs[] = {
	{
		/* Coefficients for progressive input */
		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
		0x00C8, 0x0348, 0x0018, 0x3FD8, 0x3FB8, 0x0378, 0x00E8, 0x3FE8,
	},
	{
		/* Coefficients for Top Field Interlaced input */
		0x0051, 0x03D5, 0x3FE3, 0x3FF7, 0x3FB5, 0x02E9, 0x018F, 0x3FD3,
		/* Coefficients for Bottom Field Interlaced input */
		0x016B, 0x0247, 0x00B1, 0x3F9D, 0x3FCF, 0x03DB, 0x005D, 0x3FF9,
	},
};

/*
 * the following registers are for configuring some of the parameters of the
 * motion and edge detection blocks inside DEI, these generally remain the same,
 * these could be passed later via userspace if some one needs to tweak these.
 */
struct vpe_dei_regs {
	unsigned long mdt_spacial_freq_thr_reg;		/* VPE_DEI_REG2 */
	unsigned long edi_config_reg;			/* VPE_DEI_REG3 */
	unsigned long edi_lut_reg0;			/* VPE_DEI_REG4 */
	unsigned long edi_lut_reg1;			/* VPE_DEI_REG5 */
	unsigned long edi_lut_reg2;			/* VPE_DEI_REG6 */
	unsigned long edi_lut_reg3;			/* VPE_DEI_REG7 */
};

/*
 * default expert DEI register values, unlikely to be modified.
 */
static const struct vpe_dei_regs dei_regs = {
	.mdt_spacial_freq_thr_reg = 0x020C0804u,
	.edi_config_reg = 0x0118100Cu,
	.edi_lut_reg0 = 0x08040200u,
	.edi_lut_reg1 = 0x1010100Cu,
	.edi_lut_reg2 = 0x10101010u,
	.edi_lut_reg3 = 0x10101010u,
};

/*
 * The port_data structure contains per-port data.
 */
struct vpe_port_data {
	enum vpdma_channel channel;	/* VPDMA channel */
	u8	vb_index;		/* input frame f, f-1, f-2 index */
	u8	vb_part;		/* plane index for co-panar formats */
};

/*
 * Define indices into the port_data tables
 */
#define VPE_PORT_LUMA1_IN	0
#define VPE_PORT_CHROMA1_IN	1
#define VPE_PORT_LUMA2_IN	2
#define VPE_PORT_CHROMA2_IN	3
#define VPE_PORT_LUMA3_IN	4
#define VPE_PORT_CHROMA3_IN	5
#define VPE_PORT_MV_IN		6
#define VPE_PORT_MV_OUT		7
#define VPE_PORT_LUMA_OUT	8
#define VPE_PORT_CHROMA_OUT	9
#define VPE_PORT_RGB_OUT	10

static const struct vpe_port_data port_data[11] = {
	[VPE_PORT_LUMA1_IN] = {
		.channel	= VPE_CHAN_LUMA1_IN,
		.vb_index	= 0,
		.vb_part	= VPE_LUMA,
	},
	[VPE_PORT_CHROMA1_IN] = {
		.channel	= VPE_CHAN_CHROMA1_IN,
		.vb_index	= 0,
		.vb_part	= VPE_CHROMA,
	},
	[VPE_PORT_LUMA2_IN] = {
		.channel	= VPE_CHAN_LUMA2_IN,
		.vb_index	= 1,
		.vb_part	= VPE_LUMA,
	},
	[VPE_PORT_CHROMA2_IN] = {
		.channel	= VPE_CHAN_CHROMA2_IN,
		.vb_index	= 1,
		.vb_part	= VPE_CHROMA,
	},
	[VPE_PORT_LUMA3_IN] = {
		.channel	= VPE_CHAN_LUMA3_IN,
		.vb_index	= 2,
		.vb_part	= VPE_LUMA,
	},
	[VPE_PORT_CHROMA3_IN] = {
		.channel	= VPE_CHAN_CHROMA3_IN,
		.vb_index	= 2,
		.vb_part	= VPE_CHROMA,
	},
	[VPE_PORT_MV_IN] = {
		.channel	= VPE_CHAN_MV_IN,
	},
	[VPE_PORT_MV_OUT] = {
		.channel	= VPE_CHAN_MV_OUT,
	},
	[VPE_PORT_LUMA_OUT] = {
		.channel	= VPE_CHAN_LUMA_OUT,
		.vb_part	= VPE_LUMA,
	},
	[VPE_PORT_CHROMA_OUT] = {
		.channel	= VPE_CHAN_CHROMA_OUT,
		.vb_part	= VPE_CHROMA,
	},
	[VPE_PORT_RGB_OUT] = {
		.channel	= VPE_CHAN_RGB_OUT,
		.vb_part	= VPE_LUMA,
	},
};


/* driver info for each of the supported video formats */
struct vpe_fmt {
	char	*name;			/* human-readable name */
	u32	fourcc;			/* standard format identifier */
	u8	types;			/* CAPTURE and/or OUTPUT */
	u8	coplanar;		/* set for unpacked Luma and Chroma */
	/* vpdma format info for each plane */
	struct vpdma_data_format const *vpdma_fmt[VPE_MAX_PLANES];
};

static struct vpe_fmt vpe_formats[] = {
	{
		.name		= "NV16 YUV 422 co-planar",
		.fourcc		= V4L2_PIX_FMT_NV16,
		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
		.coplanar	= 1,
		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y444],
				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C444],
				  },
	},
	{
		.name		= "NV12 YUV 420 co-planar",
		.fourcc		= V4L2_PIX_FMT_NV12,
		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
		.coplanar	= 1,
		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_Y420],
				    &vpdma_yuv_fmts[VPDMA_DATA_FMT_C420],
				  },
	},
	{
		.name		= "YUYV 422 packed",
		.fourcc		= V4L2_PIX_FMT_YUYV,
		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_YCB422],
				  },
	},
	{
		.name		= "UYVY 422 packed",
		.fourcc		= V4L2_PIX_FMT_UYVY,
		.types		= VPE_FMT_TYPE_CAPTURE | VPE_FMT_TYPE_OUTPUT,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_yuv_fmts[VPDMA_DATA_FMT_CBY422],
				  },
	},
	{
		.name		= "RGB888 packed",
		.fourcc		= V4L2_PIX_FMT_RGB24,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGB24],
				  },
	},
	{
		.name		= "ARGB32",
		.fourcc		= V4L2_PIX_FMT_RGB32,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ARGB32],
				  },
	},
	{
		.name		= "BGR888 packed",
		.fourcc		= V4L2_PIX_FMT_BGR24,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_BGR24],
				  },
	},
	{
		.name		= "ABGR32",
		.fourcc		= V4L2_PIX_FMT_BGR32,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_ABGR32],
				  },
	},
	{
		.name		= "RGB565",
		.fourcc		= V4L2_PIX_FMT_RGB565,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGB565],
				  },
	},
	{
		.name		= "RGB5551",
		.fourcc		= V4L2_PIX_FMT_RGB555,
		.types		= VPE_FMT_TYPE_CAPTURE,
		.coplanar	= 0,
		.vpdma_fmt	= { &vpdma_rgb_fmts[VPDMA_DATA_FMT_RGBA16_5551],
				  },
	},
};

/*
 * per-queue, driver-specific private data.
 * there is one source queue and one destination queue for each m2m context.
 */
struct vpe_q_data {
	unsigned int		width;				/* frame width */
	unsigned int		height;				/* frame height */
	unsigned int		nplanes;			/* Current number of planes */
	unsigned int		bytesperline[VPE_MAX_PLANES];	/* bytes per line in memory */
	enum v4l2_colorspace	colorspace;
	enum v4l2_field		field;				/* supported field value */
	unsigned int		flags;
	unsigned int		sizeimage[VPE_MAX_PLANES];	/* image size in memory */
	struct v4l2_rect	c_rect;				/* crop/compose rectangle */
	struct vpe_fmt		*fmt;				/* format info */
};

/* vpe_q_data flag bits */
#define	Q_DATA_FRAME_1D			BIT(0)
#define	Q_DATA_MODE_TILED		BIT(1)
#define	Q_DATA_INTERLACED_ALTERNATE	BIT(2)
#define	Q_DATA_INTERLACED_SEQ_TB	BIT(3)

#define Q_IS_INTERLACED		(Q_DATA_INTERLACED_ALTERNATE | \
				Q_DATA_INTERLACED_SEQ_TB)

enum {
	Q_DATA_SRC = 0,
	Q_DATA_DST = 1,
};

/* find our format description corresponding to the passed v4l2_format */
static struct vpe_fmt *find_format(struct v4l2_format *f)
{
	struct vpe_fmt *fmt;
	unsigned int k;

	for (k = 0; k < ARRAY_SIZE(vpe_formats); k++) {
		fmt = &vpe_formats[k];
		if (fmt->fourcc == f->fmt.pix.pixelformat)
			return fmt;
	}

	return NULL;
}

/*
 * there is one vpe_dev structure in the driver, it is shared by
 * all instances.
 */
struct vpe_dev {
	struct v4l2_device	v4l2_dev;
	struct video_device	vfd;
	struct v4l2_m2m_dev	*m2m_dev;

	atomic_t		num_instances;	/* count of driver instances */
	dma_addr_t		loaded_mmrs;	/* shadow mmrs in device */
	struct mutex		dev_mutex;
	spinlock_t		lock;

	int			irq;
	void __iomem		*base;
	struct resource		*res;

	struct vpdma_data	vpdma_data;
	struct vpdma_data	*vpdma;		/* vpdma data handle */
	struct sc_data		*sc;		/* scaler data handle */
	struct csc_data		*csc;		/* csc data handle */
};

/*
 * There is one vpe_ctx structure for each m2m context.
 */
struct vpe_ctx {
	struct v4l2_fh		fh;
	struct vpe_dev		*dev;
	struct v4l2_ctrl_handler hdl;

	unsigned int		field;			/* current field */
	unsigned int		sequence;		/* current frame/field seq */
	unsigned int		aborting;		/* abort after next irq */

	unsigned int		bufs_per_job;		/* input buffers per batch */
	unsigned int		bufs_completed;		/* bufs done in this batch */

	struct vpe_q_data	q_data[2];		/* src & dst queue data */
	struct vb2_v4l2_buffer	*src_vbs[VPE_MAX_SRC_BUFS];
	struct vb2_v4l2_buffer	*dst_vb;

	dma_addr_t		mv_buf_dma[2];		/* dma addrs of motion vector in/out bufs */
	void			*mv_buf[2];		/* virtual addrs of motion vector bufs */
	size_t			mv_buf_size;		/* current motion vector buffer size */
	struct vpdma_buf	mmr_adb;		/* shadow reg addr/data block */
	struct vpdma_buf	sc_coeff_h;		/* h coeff buffer */
	struct vpdma_buf	sc_coeff_v;		/* v coeff buffer */
	struct vpdma_desc_list	desc_list;		/* DMA descriptor list */

	bool			deinterlacing;		/* using de-interlacer */
	bool			load_mmrs;		/* have new shadow reg values */

	unsigned int		src_mv_buf_selector;
};


/*
 * M2M devices get 2 queues.
 * Return the queue given the type.
 */
static struct vpe_q_data *get_q_data(struct vpe_ctx *ctx,
				     enum v4l2_buf_type type)
{
	switch (type) {
	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
		return &ctx->q_data[Q_DATA_SRC];
	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
		return &ctx->q_data[Q_DATA_DST];
	default:
		return NULL;
	}
	return NULL;
}

static u32 read_reg(struct vpe_dev *dev, int offset)
{
	return ioread32(dev->base + offset);
}

static void write_reg(struct vpe_dev *dev, int offset, u32 value)
{
	iowrite32(value, dev->base + offset);
}

/* register field read/write helpers */
static int get_field(u32 value, u32 mask, int shift)
{
	return (value & (mask << shift)) >> shift;
}

static int read_field_reg(struct vpe_dev *dev, int offset, u32 mask, int shift)
{
	return get_field(read_reg(dev, offset), mask, shift);
}

static void write_field(u32 *valp, u32 field, u32 mask, int shift)
{
	u32 val = *valp;

	val &= ~(mask << shift);
	val |= (field & mask) << shift;
	*valp = val;
}

static void write_field_reg(struct vpe_dev *dev, int offset, u32 field,
		u32 mask, int shift)
{
	u32 val = read_reg(dev, offset);

	write_field(&val, field, mask, shift);

	write_reg(dev, offset, val);
}

/*
 * DMA address/data block for the shadow registers
 */
struct vpe_mmr_adb {
	struct vpdma_adb_hdr	out_fmt_hdr;
	u32			out_fmt_reg[1];
	u32			out_fmt_pad[3];
	struct vpdma_adb_hdr	us1_hdr;
	u32			us1_regs[8];
	struct vpdma_adb_hdr	us2_hdr;
	u32			us2_regs[8];
	struct vpdma_adb_hdr	us3_hdr;
	u32			us3_regs[8];
	struct vpdma_adb_hdr	dei_hdr;
	u32			dei_regs[8];
	struct vpdma_adb_hdr	sc_hdr0;
	u32			sc_regs0[7];
	u32			sc_pad0[1];
	struct vpdma_adb_hdr	sc_hdr8;
	u32			sc_regs8[6];
	u32			sc_pad8[2];
	struct vpdma_adb_hdr	sc_hdr17;
	u32			sc_regs17[9];
	u32			sc_pad17[3];
	struct vpdma_adb_hdr	csc_hdr;
	u32			csc_regs[6];
	u32			csc_pad[2];
};

#define GET_OFFSET_TOP(ctx, obj, reg)	\
	((obj)->res->start - ctx->dev->res->start + reg)

#define VPE_SET_MMR_ADB_HDR(ctx, hdr, regs, offset_a)	\
	VPDMA_SET_MMR_ADB_HDR(ctx->mmr_adb, vpe_mmr_adb, hdr, regs, offset_a)
/*
 * Set the headers for all of the address/data block structures.
 */
static void init_adb_hdrs(struct vpe_ctx *ctx)
{
	VPE_SET_MMR_ADB_HDR(ctx, out_fmt_hdr, out_fmt_reg, VPE_CLK_FORMAT_SELECT);
	VPE_SET_MMR_ADB_HDR(ctx, us1_hdr, us1_regs, VPE_US1_R0);
	VPE_SET_MMR_ADB_HDR(ctx, us2_hdr, us2_regs, VPE_US2_R0);
	VPE_SET_MMR_ADB_HDR(ctx, us3_hdr, us3_regs, VPE_US3_R0);
	VPE_SET_MMR_ADB_HDR(ctx, dei_hdr, dei_regs, VPE_DEI_FRAME_SIZE);
	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr0, sc_regs0,
		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC0));
	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr8, sc_regs8,
		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC8));
	VPE_SET_MMR_ADB_HDR(ctx, sc_hdr17, sc_regs17,
		GET_OFFSET_TOP(ctx, ctx->dev->sc, CFG_SC17));
	VPE_SET_MMR_ADB_HDR(ctx, csc_hdr, csc_regs,
		GET_OFFSET_TOP(ctx, ctx->dev->csc, CSC_CSC00));
};

/*
 * Allocate or re-allocate the motion vector DMA buffers
 * There are two buffers, one for input and one for output.
 * However, the roles are reversed after each field is processed.
 * In other words, after each field is processed, the previous
 * output (dst) MV buffer becomes the new input (src) MV buffer.
 */
static int realloc_mv_buffers(struct vpe_ctx *ctx, size_t size)
{
	struct device *dev = ctx->dev->v4l2_dev.dev;

	if (ctx->mv_buf_size == size)
		return 0;

	if (ctx->mv_buf[0])
		dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[0],
			ctx->mv_buf_dma[0]);

	if (ctx->mv_buf[1])
		dma_free_coherent(dev, ctx->mv_buf_size, ctx->mv_buf[1],
			ctx->mv_buf_dma[1]);

	if (size == 0)
		return 0;

	ctx->mv_buf[0] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[0],
				GFP_KERNEL);
	if (!ctx->mv_buf[0]) {
		vpe_err(ctx->dev, "failed to allocate motion vector buffer\n");
		return -ENOMEM;
	}

	ctx->mv_buf[1] = dma_alloc_coherent(dev, size, &ctx->mv_buf_dma[1],
				GFP_KERNEL);
	if (!ctx->mv_buf[1]) {
		vpe_err(ctx->dev, "failed to allocate motion vector buffer\n");
		dma_free_coherent(dev, size, ctx->mv_buf[0],
			ctx->mv_buf_dma[0]);

		return -ENOMEM;
	}

	ctx->mv_buf_size = size;
	ctx->src_mv_buf_selector = 0;

	return 0;
}

static void free_mv_buffers(struct vpe_ctx *ctx)
{
	realloc_mv_buffers(ctx, 0);
}

/*
 * While de-interlacing, we keep the two most recent input buffers
 * around.  This function frees those two buffers when we have
 * finished processing the current stream.
 */
static void free_vbs(struct vpe_ctx *ctx)
{
	struct vpe_dev *dev = ctx->dev;
	unsigned long flags;

	if (ctx->src_vbs[2] == NULL)
		return;

	spin_lock_irqsave(&dev->lock, flags);
	if (ctx->src_vbs[2]) {
		v4l2_m2m_buf_done(ctx->src_vbs[2], VB2_BUF_STATE_DONE);
		if (ctx->src_vbs[1] && (ctx->src_vbs[1] != ctx->src_vbs[2]))
			v4l2_m2m_buf_done(ctx->src_vbs[1], VB2_BUF_STATE_DONE);
		ctx->src_vbs[2] = NULL;
		ctx->src_vbs[1] = NULL;
	}
	spin_unlock_irqrestore(&dev->lock, flags);
}

/*
 * Enable or disable the VPE clocks
 */
static void vpe_set_clock_enable(struct vpe_dev *dev, bool on)
{
	u32 val = 0;

	if (on)
		val = VPE_DATA_PATH_CLK_ENABLE | VPE_VPEDMA_CLK_ENABLE;
	write_reg(dev, VPE_CLK_ENABLE, val);
}

static void vpe_top_reset(struct vpe_dev *dev)
{

	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_DATA_PATH_CLK_RESET_MASK,
		VPE_DATA_PATH_CLK_RESET_SHIFT);

	usleep_range(100, 150);

	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_DATA_PATH_CLK_RESET_MASK,
		VPE_DATA_PATH_CLK_RESET_SHIFT);
}

static void vpe_top_vpdma_reset(struct vpe_dev *dev)
{
	write_field_reg(dev, VPE_CLK_RESET, 1, VPE_VPDMA_CLK_RESET_MASK,
		VPE_VPDMA_CLK_RESET_SHIFT);

	usleep_range(100, 150);

	write_field_reg(dev, VPE_CLK_RESET, 0, VPE_VPDMA_CLK_RESET_MASK,
		VPE_VPDMA_CLK_RESET_SHIFT);
}

/*
 * Load the correct of upsampler coefficients into the shadow MMRs
 */
static void set_us_coefficients(struct vpe_ctx *ctx)
{
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
	u32 *us1_reg = &mmr_adb->us1_regs[0];
	u32 *us2_reg = &mmr_adb->us2_regs[0];
	u32 *us3_reg = &mmr_adb->us3_regs[0];
	const unsigned short *cp, *end_cp;

	cp = &us_coeffs[0].anchor_fid0_c0;

	if (s_q_data->flags & Q_IS_INTERLACED)		/* interlaced */
		cp += sizeof(us_coeffs[0]) / sizeof(*cp);

	end_cp = cp + sizeof(us_coeffs[0]) / sizeof(*cp);

	while (cp < end_cp) {
		write_field(us1_reg, *cp++, VPE_US_C0_MASK, VPE_US_C0_SHIFT);
		write_field(us1_reg, *cp++, VPE_US_C1_MASK, VPE_US_C1_SHIFT);
		*us2_reg++ = *us1_reg;
		*us3_reg++ = *us1_reg++;
	}
	ctx->load_mmrs = true;
}

/*
 * Set the upsampler config mode and the VPDMA line mode in the shadow MMRs.
 */
static void set_cfg_modes(struct vpe_ctx *ctx)
{
	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	u32 *us1_reg0 = &mmr_adb->us1_regs[0];
	u32 *us2_reg0 = &mmr_adb->us2_regs[0];
	u32 *us3_reg0 = &mmr_adb->us3_regs[0];
	int cfg_mode = 1;

	/*
	 * Cfg Mode 0: YUV420 source, enable upsampler, DEI is de-interlacing.
	 * Cfg Mode 1: YUV422 source, disable upsampler, DEI is de-interlacing.
	 */

	if (fmt->fourcc == V4L2_PIX_FMT_NV12)
		cfg_mode = 0;

	write_field(us1_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
	write_field(us2_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);
	write_field(us3_reg0, cfg_mode, VPE_US_MODE_MASK, VPE_US_MODE_SHIFT);

	ctx->load_mmrs = true;
}

static void set_line_modes(struct vpe_ctx *ctx)
{
	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_SRC].fmt;
	int line_mode = 1;

	if (fmt->fourcc == V4L2_PIX_FMT_NV12)
		line_mode = 0;		/* double lines to line buffer */

	/* regs for now */
	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA1_IN);
	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA2_IN);
	vpdma_set_line_mode(ctx->dev->vpdma, line_mode, VPE_CHAN_CHROMA3_IN);

	/* frame start for input luma */
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_LUMA1_IN);
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_LUMA2_IN);
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_LUMA3_IN);

	/* frame start for input chroma */
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_CHROMA1_IN);
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_CHROMA2_IN);
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_CHROMA3_IN);

	/* frame start for MV in client */
	vpdma_set_frame_start_event(ctx->dev->vpdma, VPDMA_FSEVENT_CHANNEL_ACTIVE,
		VPE_CHAN_MV_IN);
}

/*
 * Set the shadow registers that are modified when the source
 * format changes.
 */
static void set_src_registers(struct vpe_ctx *ctx)
{
	set_us_coefficients(ctx);
}

/*
 * Set the shadow registers that are modified when the destination
 * format changes.
 */
static void set_dst_registers(struct vpe_ctx *ctx)
{
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	enum v4l2_colorspace clrspc = ctx->q_data[Q_DATA_DST].colorspace;
	struct vpe_fmt *fmt = ctx->q_data[Q_DATA_DST].fmt;
	u32 val = 0;

	if (clrspc == V4L2_COLORSPACE_SRGB) {
		val |= VPE_RGB_OUT_SELECT;
		vpdma_set_bg_color(ctx->dev->vpdma,
			(struct vpdma_data_format *)fmt->vpdma_fmt[0], 0xff);
	} else if (fmt->fourcc == V4L2_PIX_FMT_NV16)
		val |= VPE_COLOR_SEPARATE_422;

	/*
	 * the source of CHR_DS and CSC is always the scaler, irrespective of
	 * whether it's used or not
	 */
	val |= VPE_DS_SRC_DEI_SCALER | VPE_CSC_SRC_DEI_SCALER;

	if (fmt->fourcc != V4L2_PIX_FMT_NV12)
		val |= VPE_DS_BYPASS;

	mmr_adb->out_fmt_reg[0] = val;

	ctx->load_mmrs = true;
}

/*
 * Set the de-interlacer shadow register values
 */
static void set_dei_regs(struct vpe_ctx *ctx)
{
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];
	unsigned int src_h = s_q_data->c_rect.height;
	unsigned int src_w = s_q_data->c_rect.width;
	u32 *dei_mmr0 = &mmr_adb->dei_regs[0];
	bool deinterlace = true;
	u32 val = 0;

	/*
	 * according to TRM, we should set DEI in progressive bypass mode when
	 * the input content is progressive, however, DEI is bypassed correctly
	 * for both progressive and interlace content in interlace bypass mode.
	 * It has been recommended not to use progressive bypass mode.
	 */
	if (!(s_q_data->flags & Q_IS_INTERLACED) || !ctx->deinterlacing) {
		deinterlace = false;
		val = VPE_DEI_INTERLACE_BYPASS;
	}

	src_h = deinterlace ? src_h * 2 : src_h;

	val |= (src_h << VPE_DEI_HEIGHT_SHIFT) |
		(src_w << VPE_DEI_WIDTH_SHIFT) |
		VPE_DEI_FIELD_FLUSH;

	*dei_mmr0 = val;

	ctx->load_mmrs = true;
}

static void set_dei_shadow_registers(struct vpe_ctx *ctx)
{
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	u32 *dei_mmr = &mmr_adb->dei_regs[0];
	const struct vpe_dei_regs *cur = &dei_regs;

	dei_mmr[2]  = cur->mdt_spacial_freq_thr_reg;
	dei_mmr[3]  = cur->edi_config_reg;
	dei_mmr[4]  = cur->edi_lut_reg0;
	dei_mmr[5]  = cur->edi_lut_reg1;
	dei_mmr[6]  = cur->edi_lut_reg2;
	dei_mmr[7]  = cur->edi_lut_reg3;

	ctx->load_mmrs = true;
}

static void config_edi_input_mode(struct vpe_ctx *ctx, int mode)
{
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	u32 *edi_config_reg = &mmr_adb->dei_regs[3];

	if (mode & 0x2)
		write_field(edi_config_reg, 1, 1, 2);	/* EDI_ENABLE_3D */

	if (mode & 0x3)
		write_field(edi_config_reg, 1, 1, 3);	/* EDI_CHROMA_3D  */

	write_field(edi_config_reg, mode, VPE_EDI_INP_MODE_MASK,
		VPE_EDI_INP_MODE_SHIFT);

	ctx->load_mmrs = true;
}

/*
 * Set the shadow registers whose values are modified when either the
 * source or destination format is changed.
 */
static int set_srcdst_params(struct vpe_ctx *ctx)
{
	struct vpe_q_data *s_q_data =  &ctx->q_data[Q_DATA_SRC];
	struct vpe_q_data *d_q_data =  &ctx->q_data[Q_DATA_DST];
	struct vpe_mmr_adb *mmr_adb = ctx->mmr_adb.addr;
	unsigned int src_w = s_q_data->c_rect.width;
	unsigned int src_h = s_q_data->c_rect.height;
	unsigned int dst_w = d_q_data->c_rect.width;
	unsigned int dst_h = d_q_data->c_rect.height;
	size_t mv_buf_size;
	int ret;

	ctx->sequence = 0;
	ctx->field = V4L2_FIELD_TOP;

	if ((s_q_data->flags & Q_IS_INTERLACED) &&
			!(d_q_data->flags & Q_IS_INTERLACED)) {
		int bytes_per_line;
		const struct vpdma_data_format *mv =
			&vpdma_misc_fmts[VPDMA_DATA_FMT_MV];

		/*
		 * we make sure that the source image has a 16 byte aligned
		 * stride, we need to do the same for the motion vector buffer
		 * by aligning it's stride to the next 16 byte boundry. this
		 * extra space will not be used by the de-interlacer, but will
		 * ensure that vpdma operates correctly
		 */
		bytes_per_line = ALIGN((s_q_data->width * mv->depth) >> 3,
					VPDMA_STRIDE_ALIGN);
		mv_buf_size = bytes_per_line * s_q_data->height;

		ctx->deinterlacing = true;
		src_h <<= 1;
	} else {
		ctx->deinterlacing = false;
		mv_buf_size = 0;
	}

	free_vbs(ctx);
	ctx->src_vbs[2] = ctx->src_vbs[1] = ctx->src_vbs[0] = NULL;

	ret = realloc_mv_buffers(ctx, mv_buf_size);
	if (ret)
		return ret;

	set_cfg_modes(ctx);
	set_dei_regs(ctx);

	csc_set_coeff(ctx->dev->csc, &mmr_adb->csc_regs[0],
		s_q_data->colorspace, d_q_data->colorspace);

	sc_set_hs_coeffs(ctx->dev->sc, ctx->sc_coeff_h.addr, src_w, dst_w);
	sc_set_vs_coeffs(ctx->dev->sc, ctx->sc_coeff_v.addr, src_h, dst_h);

	sc_config_scaler(ctx->dev->sc, &mmr_adb->sc_regs0[0],
		&mmr_adb->sc_regs8[0], &mmr_adb->sc_regs17[0],
		src_w, src_h, dst_w, dst_h);

	return 0;
}

/*
 * Return the vpe_ctx structure for a given struct file
 */
static struct vpe_ctx *file2ctx(struct file *file)
{
	return container_of(file->private_data, struct vpe_ctx, fh);
}

/*
 * mem2mem callbacks
 */

/**
 * job_ready() - check whether an instance is ready to be scheduled to run
 */
static int job_ready(void *priv)
{
	struct vpe_ctx *ctx = priv;

	/*
	 * This check is needed as this might be called directly from driver
	 * When called by m2m framework, this will always satisfy, but when
	 * called from vpe_irq, this might fail. (src stream with zero buffers)
	 */
	if (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) <= 0 ||
		v4l2_m2m_num_dst_bufs_ready(ctx->fh.m2m_ctx) <= 0)
		return 0;

	return 1;
}

static void job_abort(void *priv)
{
	struct vpe_ctx *ctx = priv;

	/* Will cancel the transaction in the next interrupt handler */
	ctx->aborting = 1;
}

/*
 * Lock access to the device
 */
static void vpe_lock(void *priv)
{
	struct vpe_ctx *ctx = priv;
	struct vpe_dev *dev = ctx->dev;
	mutex_lock(&dev->dev_mutex);
}

static void vpe_unlock(void *priv)
{
	struct vpe_ctx *ctx = priv;
	struct vpe_dev *dev = ctx->dev;
	mutex_unlock(&dev->dev_mutex);
}

static void vpe_dump_regs(struct vpe_dev *dev)
{
#define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))

	vpe_dbg(dev, "VPE Registers:\n");

	DUMPREG(PID);
	DUMPREG(SYSCONFIG);
	DUMPREG(INT0_STATUS0_RAW);
	DUMPREG(INT0_STATUS0);
	DUMPREG(INT0_ENABLE0);
	DUMPREG(INT0_STATUS1_RAW);
	DUMPREG(INT0_STATUS1);
	DUMPREG(INT0_ENABLE1);
	DUMPREG(CLK_ENABLE);
	DUMPREG(CLK_RESET);
	DUMPREG(CLK_FORMAT_SELECT);
	DUMPREG(CLK_RANGE_MAP);
	DUMPREG(US1_R0);
	DUMPREG(US1_R1);
	DUMPREG(US1_R2);
	DUMPREG(US1_R3);
	DUMPREG(US1_R4);
	DUMPREG(US1_R5);
	DUMPREG(US1_R6);
	DUMPREG(US1_R7);
	DUMPREG(US2_R0);
	DUMPREG(US2_R1);
	DUMPREG(US2_R2);
	DUMPREG(US2_R3);
	DUMPREG(US2_R4);
	DUMPREG(US2_R5);
	DUMPREG(US2_R6);
	DUMPREG(US2_R7);
	DUMPREG(US3_R0);
	DUMPREG(US3_R1);
	DUMPREG(US3_R2);
	DUMPREG(US3_R3);
	DUMPREG(US3_R4);
	DUMPREG(US3_R5);
	DUMPREG(US3_R6);
	DUMPREG(US3_R7);
	DUMPREG(DEI_FRAME_SIZE);
	DUMPREG(MDT_BYPASS);
	DUMPREG(MDT_SF_THRESHOLD);
	DUMPREG(EDI_CONFIG);
	DUMPREG(DEI_EDI_LUT_R0);
	DUMPREG(DEI_EDI_LUT_R1);
	DUMPREG(DEI_EDI_LUT_R2);
	DUMPREG(DEI_EDI_LUT_R3);
	DUMPREG(DEI_FMD_WINDOW_R0);
	DUMPREG(DEI_FMD_WINDOW_R1);
	DUMPREG(DEI_FMD_CONTROL_R0);
	DUMPREG(DEI_FMD_CONTROL_R1);
	DUMPREG(DEI_FMD_STATUS_R0);
	DUMPREG(DEI_FMD_STATUS_R1);
	DUMPREG(DEI_FMD_STATUS_R2);
#undef DUMPREG

	sc_dump_regs(dev->sc);
	csc_dump_regs(dev->csc);
}

static void add_out_dtd(struct vpe_ctx *ctx, int port)
{
	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_DST];
	const struct vpe_port_data *p_data = &port_data[port];
	struct vb2_buffer *vb = &ctx->dst_vb->vb2_buf;
	struct vpe_fmt *fmt = q_data->fmt;
	const struct vpdma_data_format *vpdma_fmt;
	int mv_buf_selector = !ctx->src_mv_buf_selector;
	dma_addr_t dma_addr;
	u32 flags = 0;
	u32 offset = 0;

	if (port == VPE_PORT_MV_OUT) {
		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
		q_data = &ctx->q_data[Q_DATA_SRC];
	} else {
		/* to incorporate interleaved formats */
		int plane = fmt->coplanar ? p_data->vb_part : 0;

		vpdma_fmt = fmt->vpdma_fmt[plane];
		/*
		 * If we are using a single plane buffer and
		 * we need to set a separate vpdma chroma channel.
		 */
		if (q_data->nplanes == 1 && plane) {
			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
			/* Compute required offset */
			offset = q_data->bytesperline[0] * q_data->height;
		} else {
			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
			/* Use address as is, no offset */
			offset = 0;
		}
		if (!dma_addr) {
			vpe_err(ctx->dev,
				"acquiring output buffer(%d) dma_addr failed\n",
				port);
			return;
		}
		/* Apply the offset */
		dma_addr += offset;
	}

	if (q_data->flags & Q_DATA_FRAME_1D)
		flags |= VPDMA_DATA_FRAME_1D;
	if (q_data->flags & Q_DATA_MODE_TILED)
		flags |= VPDMA_DATA_MODE_TILED;

	vpdma_set_max_size(ctx->dev->vpdma, VPDMA_MAX_SIZE1,
			   MAX_W, MAX_H);

	vpdma_add_out_dtd(&ctx->desc_list, q_data->width,
			  q_data->bytesperline[VPE_LUMA], &q_data->c_rect,
			  vpdma_fmt, dma_addr, MAX_OUT_WIDTH_REG1,
			  MAX_OUT_HEIGHT_REG1, p_data->channel, flags);
}

static void add_in_dtd(struct vpe_ctx *ctx, int port)
{
	struct vpe_q_data *q_data = &ctx->q_data[Q_DATA_SRC];
	const struct vpe_port_data *p_data = &port_data[port];
	struct vb2_buffer *vb = &ctx->src_vbs[p_data->vb_index]->vb2_buf;
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpe_fmt *fmt = q_data->fmt;
	const struct vpdma_data_format *vpdma_fmt;
	int mv_buf_selector = ctx->src_mv_buf_selector;
	int field = vbuf->field == V4L2_FIELD_BOTTOM;
	int frame_width, frame_height;
	dma_addr_t dma_addr;
	u32 flags = 0;
	u32 offset = 0;

	if (port == VPE_PORT_MV_IN) {
		vpdma_fmt = &vpdma_misc_fmts[VPDMA_DATA_FMT_MV];
		dma_addr = ctx->mv_buf_dma[mv_buf_selector];
	} else {
		/* to incorporate interleaved formats */
		int plane = fmt->coplanar ? p_data->vb_part : 0;

		vpdma_fmt = fmt->vpdma_fmt[plane];
		/*
		 * If we are using a single plane buffer and
		 * we need to set a separate vpdma chroma channel.
		 */
		if (q_data->nplanes == 1 && plane) {
			dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
			/* Compute required offset */
			offset = q_data->bytesperline[0] * q_data->height;
		} else {
			dma_addr = vb2_dma_contig_plane_dma_addr(vb, plane);
			/* Use address as is, no offset */
			offset = 0;
		}
		if (!dma_addr) {
			vpe_err(ctx->dev,
				"acquiring output buffer(%d) dma_addr failed\n",
				port);
			return;
		}
		/* Apply the offset */
		dma_addr += offset;

		if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB) {
			/*
			 * Use top or bottom field from same vb alternately
			 * f,f-1,f-2 = TBT when seq is even
			 * f,f-1,f-2 = BTB when seq is odd
			 */
			field = (p_data->vb_index + (ctx->sequence % 2)) % 2;

			if (field) {
				/*
				 * bottom field of a SEQ_TB buffer
				 * Skip the top field data by
				 */
				int height = q_data->height / 2;
				int bpp = fmt->fourcc == V4L2_PIX_FMT_NV12 ?
						1 : (vpdma_fmt->depth >> 3);
				if (plane)
					height /= 2;
				dma_addr += q_data->width * height * bpp;
			}
		}
	}

	if (q_data->flags & Q_DATA_FRAME_1D)
		flags |= VPDMA_DATA_FRAME_1D;
	if (q_data->flags & Q_DATA_MODE_TILED)
		flags |= VPDMA_DATA_MODE_TILED;

	frame_width = q_data->c_rect.width;
	frame_height = q_data->c_rect.height;

	if (p_data->vb_part && fmt->fourcc == V4L2_PIX_FMT_NV12)
		frame_height /= 2;

	vpdma_add_in_dtd(&ctx->desc_list, q_data->width,
			 q_data->bytesperline[VPE_LUMA], &q_data->c_rect,
		vpdma_fmt, dma_addr, p_data->channel, field, flags, frame_width,
		frame_height, 0, 0);
}

/*
 * Enable the expected IRQ sources
 */
static void enable_irqs(struct vpe_ctx *ctx)
{
	write_reg(ctx->dev, VPE_INT0_ENABLE0_SET, VPE_INT0_LIST0_COMPLETE);
	write_reg(ctx->dev, VPE_INT0_ENABLE1_SET, VPE_DEI_ERROR_INT |
				VPE_DS1_UV_ERROR_INT);

	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, 0, true);
}

static void disable_irqs(struct vpe_ctx *ctx)
{
	write_reg(ctx->dev, VPE_INT0_ENABLE0_CLR, 0xffffffff);
	write_reg(ctx->dev, VPE_INT0_ENABLE1_CLR, 0xffffffff);

	vpdma_enable_list_complete_irq(ctx->dev->vpdma, 0, 0, false);
}

/* device_run() - prepares and starts the device
 *
 * This function is only called when both the source and destination
 * buffers are in place.
 */
static void device_run(void *priv)
{
	struct vpe_ctx *ctx = priv;
	struct sc_data *sc = ctx->dev->sc;
	struct vpe_q_data *d_q_data = &ctx->q_data[Q_DATA_DST];
	struct vpe_q_data *s_q_data = &ctx->q_data[Q_DATA_SRC];

	if (ctx->deinterlacing && s_q_data->flags & Q_DATA_INTERLACED_SEQ_TB &&
		ctx->sequence % 2 == 0) {
		/* When using SEQ_TB buffers, When using it first time,
		 * No need to remove the buffer as the next field is present
		 * in the same buffer. (so that job_ready won't fail)
		 * It will be removed when using bottom field
		 */
		ctx->src_vbs[0] = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
		WARN_ON(ctx->src_vbs[0] == NULL);
	} else {
		ctx->src_vbs[0] = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
		WARN_ON(ctx->src_vbs[0] == NULL);
	}

	ctx->dst_vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
	WARN_ON(ctx->dst_vb == NULL);

	if (ctx->deinterlacing) {

		if (ctx->src_vbs[2] == NULL) {
			ctx->src_vbs[2] = ctx->src_vbs[0];
			WARN_ON(ctx->src_vbs[2] == NULL);
			ctx->src_vbs[1] = ctx->src_vbs[0];
			WARN_ON(ctx->src_vbs[1] == NULL);
		}

		/*
		 * we have output the first 2 frames through line average, we
		 * now switch to EDI de-interlacer
		 */
		if (ctx->sequence == 2)
			config_edi_input_mode(ctx, 0x3); /* EDI (Y + UV) */
	}

	/* config descriptors */
	if (ctx->dev->loaded_mmrs != ctx->mmr_adb.dma_addr || ctx->load_mmrs) {
		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->mmr_adb);
		vpdma_add_cfd_adb(&ctx->desc_list, CFD_MMR_CLIENT, &ctx->mmr_adb);

		set_line_modes(ctx);

		ctx->dev->loaded_mmrs = ctx->mmr_adb.dma_addr;
		ctx->load_mmrs = false;
	}

	if (sc->loaded_coeff_h != ctx->sc_coeff_h.dma_addr ||
			sc->load_coeff_h) {
		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_h);
		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
			&ctx->sc_coeff_h, 0);

		sc->loaded_coeff_h = ctx->sc_coeff_h.dma_addr;
		sc->load_coeff_h = false;
	}

	if (sc->loaded_coeff_v != ctx->sc_coeff_v.dma_addr ||
			sc->load_coeff_v) {
		vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->sc_coeff_v);
		vpdma_add_cfd_block(&ctx->desc_list, CFD_SC_CLIENT,
			&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE >> 4);

		sc->loaded_coeff_v = ctx->sc_coeff_v.dma_addr;
		sc->load_coeff_v = false;
	}

	/* output data descriptors */
	if (ctx->deinterlacing)
		add_out_dtd(ctx, VPE_PORT_MV_OUT);

	if (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
		add_out_dtd(ctx, VPE_PORT_RGB_OUT);
	} else {
		add_out_dtd(ctx, VPE_PORT_LUMA_OUT);
		if (d_q_data->fmt->coplanar)
			add_out_dtd(ctx, VPE_PORT_CHROMA_OUT);
	}

	/* input data descriptors */
	if (ctx->deinterlacing) {
		add_in_dtd(ctx, VPE_PORT_LUMA3_IN);
		add_in_dtd(ctx, VPE_PORT_CHROMA3_IN);

		add_in_dtd(ctx, VPE_PORT_LUMA2_IN);
		add_in_dtd(ctx, VPE_PORT_CHROMA2_IN);
	}

	add_in_dtd(ctx, VPE_PORT_LUMA1_IN);
	add_in_dtd(ctx, VPE_PORT_CHROMA1_IN);

	if (ctx->deinterlacing)
		add_in_dtd(ctx, VPE_PORT_MV_IN);

	/* sync on channel control descriptors for input ports */
	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_LUMA1_IN);
	vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_CHROMA1_IN);

	if (ctx->deinterlacing) {
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_LUMA2_IN);
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_CHROMA2_IN);

		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_LUMA3_IN);
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_CHROMA3_IN);

		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_IN);
	}

	/* sync on channel control descriptors for output ports */
	if (d_q_data->colorspace == V4L2_COLORSPACE_SRGB) {
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_RGB_OUT);
	} else {
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
			VPE_CHAN_LUMA_OUT);
		if (d_q_data->fmt->coplanar)
			vpdma_add_sync_on_channel_ctd(&ctx->desc_list,
				VPE_CHAN_CHROMA_OUT);
	}

	if (ctx->deinterlacing)
		vpdma_add_sync_on_channel_ctd(&ctx->desc_list, VPE_CHAN_MV_OUT);

	enable_irqs(ctx);

	vpdma_map_desc_buf(ctx->dev->vpdma, &ctx->desc_list.buf);
	vpdma_submit_descs(ctx->dev->vpdma, &ctx->desc_list, 0);
}

static void dei_error(struct vpe_ctx *ctx)
{
	dev_warn(ctx->dev->v4l2_dev.dev,
		"received DEI error interrupt\n");
}

static void ds1_uv_error(struct vpe_ctx *ctx)
{
	dev_warn(ctx->dev->v4l2_dev.dev,
		"received downsampler error interrupt\n");
}

static irqreturn_t vpe_irq(int irq_vpe, void *data)
{
	struct vpe_dev *dev = (struct vpe_dev *)data;
	struct vpe_ctx *ctx;
	struct vpe_q_data *d_q_data;
	struct vb2_v4l2_buffer *s_vb, *d_vb;
	unsigned long flags;
	u32 irqst0, irqst1;
	bool list_complete = false;

	irqst0 = read_reg(dev, VPE_INT0_STATUS0);
	if (irqst0) {
		write_reg(dev, VPE_INT0_STATUS0_CLR, irqst0);
		vpe_dbg(dev, "INT0_STATUS0 = 0x%08x\n", irqst0);
	}

	irqst1 = read_reg(dev, VPE_INT0_STATUS1);
	if (irqst1) {
		write_reg(dev, VPE_INT0_STATUS1_CLR, irqst1);
		vpe_dbg(dev, "INT0_STATUS1 = 0x%08x\n", irqst1);
	}

	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
	if (!ctx) {
		vpe_err(dev, "instance released before end of transaction\n");
		goto handled;
	}

	if (irqst1) {
		if (irqst1 & VPE_DEI_ERROR_INT) {
			irqst1 &= ~VPE_DEI_ERROR_INT;
			dei_error(ctx);
		}
		if (irqst1 & VPE_DS1_UV_ERROR_INT) {
			irqst1 &= ~VPE_DS1_UV_ERROR_INT;
			ds1_uv_error(ctx);
		}
	}

	if (irqst0) {
		if (irqst0 & VPE_INT0_LIST0_COMPLETE)
			vpdma_clear_list_stat(ctx->dev->vpdma, 0, 0);

		irqst0 &= ~(VPE_INT0_LIST0_COMPLETE);
		list_complete = true;
	}

	if (irqst0 | irqst1) {
		dev_warn(dev->v4l2_dev.dev, "Unexpected interrupt: INT0_STATUS0 = 0x%08x, INT0_STATUS1 = 0x%08x\n",
			irqst0, irqst1);
	}

	/*
	 * Setup next operation only when list complete IRQ occurs
	 * otherwise, skip the following code
	 */
	if (!list_complete)
		goto handled;

	disable_irqs(ctx);

	vpdma_unmap_desc_buf(dev->vpdma, &ctx->desc_list.buf);
	vpdma_unmap_desc_buf(dev->vpdma, &ctx->mmr_adb);
	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_h);
	vpdma_unmap_desc_buf(dev->vpdma, &ctx->sc_coeff_v);

	vpdma_reset_desc_list(&ctx->desc_list);

	 /* the previous dst mv buffer becomes the next src mv buffer */
	ctx->src_mv_buf_selector = !ctx->src_mv_buf_selector;

	if (ctx->aborting)
		goto finished;

	s_vb = ctx->src_vbs[0];
	d_vb = ctx->dst_vb;

	d_vb->flags = s_vb->flags;
	d_vb->vb2_buf.timestamp = s_vb->vb2_buf.timestamp;

	if (s_vb->flags & V4L2_BUF_FLAG_TIMECODE)
		d_vb->timecode = s_vb->timecode;

	d_vb->sequence = ctx->sequence;

	d_q_data = &ctx->q_data[Q_DATA_DST];
	if (d_q_data->flags & Q_IS_INTERLACED) {
		d_vb->field = ctx->field;
		if (ctx->field == V4L2_FIELD_BOTTOM) {
			ctx->sequence++;
			ctx->field = V4L2_FIELD_TOP;
		} else {
			WARN_ON(ctx->field != V4L2_FIELD_TOP);
			ctx->field = V4L2_FIELD_BOTTOM;
		}
	} else {
		d_vb->field = V4L2_FIELD_NONE;
		ctx->sequence++;
	}

	if (ctx->deinterlacing) {
		/*
		 * Allow source buffer to be dequeued only if it won't be used
		 * in the next iteration. All vbs are initialized to first
		 * buffer and we are shifting buffers every iteration, for the
		 * first two iterations, no buffer will be dequeued.
		 * This ensures that driver will keep (n-2)th (n-1)th and (n)th
		 * field when deinterlacing is enabled
		 */
		if (ctx->src_vbs[2] != ctx->src_vbs[1])
			s_vb = ctx->src_vbs[2];
		else
			s_vb = NULL;
	}

	spin_lock_irqsave(&dev->lock, flags);

	if (s_vb)
		v4l2_m2m_buf_done(s_vb, VB2_BUF_STATE_DONE);

	v4l2_m2m_buf_done(d_vb, VB2_BUF_STATE_DONE);

	spin_unlock_irqrestore(&dev->lock, flags);

	if (ctx->deinterlacing) {
		ctx->src_vbs[2] = ctx->src_vbs[1];
		ctx->src_vbs[1] = ctx->src_vbs[0];
	}

	/*
	 * Since the vb2_buf_done has already been called fir therse
	 * buffer we can now NULL them out so that we won't try
	 * to clean out stray pointer later on.
	*/
	ctx->src_vbs[0] = NULL;
	ctx->dst_vb = NULL;

	ctx->bufs_completed++;
	if (ctx->bufs_completed < ctx->bufs_per_job && job_ready(ctx)) {
		device_run(ctx);
		goto handled;
	}

finished:
	vpe_dbg(ctx->dev, "finishing transaction\n");
	ctx->bufs_completed = 0;
	v4l2_m2m_job_finish(dev->m2m_dev, ctx->fh.m2m_ctx);
handled:
	return IRQ_HANDLED;
}

/*
 * video ioctls
 */
static int vpe_querycap(struct file *file, void *priv,
			struct v4l2_capability *cap)
{
	strncpy(cap->driver, VPE_MODULE_NAME, sizeof(cap->driver) - 1);
	strncpy(cap->card, VPE_MODULE_NAME, sizeof(cap->card) - 1);
	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
		VPE_MODULE_NAME);
	cap->device_caps  = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING;
	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
	return 0;
}

static int __enum_fmt(struct v4l2_fmtdesc *f, u32 type)
{
	int i, index;
	struct vpe_fmt *fmt = NULL;

	index = 0;
	for (i = 0; i < ARRAY_SIZE(vpe_formats); ++i) {
		if (vpe_formats[i].types & type) {
			if (index == f->index) {
				fmt = &vpe_formats[i];
				break;
			}
			index++;
		}
	}

	if (!fmt)
		return -EINVAL;

	strncpy(f->description, fmt->name, sizeof(f->description) - 1);
	f->pixelformat = fmt->fourcc;
	return 0;
}

static int vpe_enum_fmt(struct file *file, void *priv,
				struct v4l2_fmtdesc *f)
{
	if (V4L2_TYPE_IS_OUTPUT(f->type))
		return __enum_fmt(f, VPE_FMT_TYPE_OUTPUT);

	return __enum_fmt(f, VPE_FMT_TYPE_CAPTURE);
}

static int vpe_g_fmt(struct file *file, void *priv, struct v4l2_format *f)
{
	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
	struct vpe_ctx *ctx = file2ctx(file);
	struct vb2_queue *vq;
	struct vpe_q_data *q_data;
	int i;

	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
	if (!vq)
		return -EINVAL;

	q_data = get_q_data(ctx, f->type);

	pix->width = q_data->width;
	pix->height = q_data->height;
	pix->pixelformat = q_data->fmt->fourcc;
	pix->field = q_data->field;

	if (V4L2_TYPE_IS_OUTPUT(f->type)) {
		pix->colorspace = q_data->colorspace;
	} else {
		struct vpe_q_data *s_q_data;

		/* get colorspace from the source queue */
		s_q_data = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);

		pix->colorspace = s_q_data->colorspace;
	}

	pix->num_planes = q_data->nplanes;

	for (i = 0; i < pix->num_planes; i++) {
		pix->plane_fmt[i].bytesperline = q_data->bytesperline[i];
		pix->plane_fmt[i].sizeimage = q_data->sizeimage[i];
	}

	return 0;
}

static int __vpe_try_fmt(struct vpe_ctx *ctx, struct v4l2_format *f,
		       struct vpe_fmt *fmt, int type)
{
	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
	struct v4l2_plane_pix_format *plane_fmt;
	unsigned int w_align;
	int i, depth, depth_bytes, height;
	unsigned int stride = 0;

	if (!fmt || !(fmt->types & type)) {
		vpe_err(ctx->dev, "Fourcc format (0x%08x) invalid.\n",
			pix->pixelformat);
		return -EINVAL;
	}

	if (pix->field != V4L2_FIELD_NONE && pix->field != V4L2_FIELD_ALTERNATE
			&& pix->field != V4L2_FIELD_SEQ_TB)
		pix->field = V4L2_FIELD_NONE;

	depth = fmt->vpdma_fmt[VPE_LUMA]->depth;

	/*
	 * the line stride should 16 byte aligned for VPDMA to work, based on
	 * the bytes per pixel, figure out how much the width should be aligned
	 * to make sure line stride is 16 byte aligned
	 */
	depth_bytes = depth >> 3;

	if (depth_bytes == 3) {
		/*
		 * if bpp is 3(as in some RGB formats), the pixel width doesn't
		 * really help in ensuring line stride is 16 byte aligned
		 */
		w_align = 4;
	} else {
		/*
		 * for the remainder bpp(4, 2 and 1), the pixel width alignment
		 * can ensure a line stride alignment of 16 bytes. For example,
		 * if bpp is 2, then the line stride can be 16 byte aligned if
		 * the width is 8 byte aligned
		 */

		/*
		 * HACK: using order_base_2() here causes lots of asm output
		 * errors with smatch, on i386:
		 * ./arch/x86/include/asm/bitops.h:457:22:
		 *		 warning: asm output is not an lvalue
		 * Perhaps some gcc optimization is doing the wrong thing
		 * there.
		 * Let's get rid of them by doing the calculus on two steps
		 */
		w_align = roundup_pow_of_two(VPDMA_DESC_ALIGN / depth_bytes);
		w_align = ilog2(w_align);
	}

	v4l_bound_align_image(&pix->width, MIN_W, MAX_W, w_align,
			      &pix->height, MIN_H, MAX_H, H_ALIGN,
			      S_ALIGN);

	if (!pix->num_planes)
		pix->num_planes = fmt->coplanar ? 2 : 1;
	else if (pix->num_planes > 1 && !fmt->coplanar)
		pix->num_planes = 1;

	pix->pixelformat = fmt->fourcc;

	/*
	 * For the actual image parameters, we need to consider the field
	 * height of the image for SEQ_TB buffers.
	 */
	if (pix->field == V4L2_FIELD_SEQ_TB)
		height = pix->height / 2;
	else
		height = pix->height;

	if (!pix->colorspace) {
		if (fmt->fourcc == V4L2_PIX_FMT_RGB24 ||
				fmt->fourcc == V4L2_PIX_FMT_BGR24 ||
				fmt->fourcc == V4L2_PIX_FMT_RGB32 ||
				fmt->fourcc == V4L2_PIX_FMT_BGR32) {
			pix->colorspace = V4L2_COLORSPACE_SRGB;
		} else {
			if (height > 1280)	/* HD */
				pix->colorspace = V4L2_COLORSPACE_REC709;
			else			/* SD */
				pix->colorspace = V4L2_COLORSPACE_SMPTE170M;
		}
	}

	memset(pix->reserved, 0, sizeof(pix->reserved));
	for (i = 0; i < pix->num_planes; i++) {
		plane_fmt = &pix->plane_fmt[i];
		depth = fmt->vpdma_fmt[i]->depth;

		stride = (pix->width * fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
		if (stride > plane_fmt->bytesperline)
			plane_fmt->bytesperline = stride;

		plane_fmt->bytesperline = ALIGN(plane_fmt->bytesperline,
						VPDMA_STRIDE_ALIGN);

		if (i == VPE_LUMA) {
			plane_fmt->sizeimage = pix->height *
					       plane_fmt->bytesperline;

			if (pix->num_planes == 1 && fmt->coplanar)
				plane_fmt->sizeimage += pix->height *
					plane_fmt->bytesperline *
					fmt->vpdma_fmt[VPE_CHROMA]->depth >> 3;

		} else { /* i == VIP_CHROMA */
			plane_fmt->sizeimage = (pix->height *
					       plane_fmt->bytesperline *
					       depth) >> 3;
		}
		memset(plane_fmt->reserved, 0, sizeof(plane_fmt->reserved));
	}

	return 0;
}

static int vpe_try_fmt(struct file *file, void *priv, struct v4l2_format *f)
{
	struct vpe_ctx *ctx = file2ctx(file);
	struct vpe_fmt *fmt = find_format(f);

	if (V4L2_TYPE_IS_OUTPUT(f->type))
		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_OUTPUT);
	else
		return __vpe_try_fmt(ctx, f, fmt, VPE_FMT_TYPE_CAPTURE);
}

static int __vpe_s_fmt(struct vpe_ctx *ctx, struct v4l2_format *f)
{
	struct v4l2_pix_format_mplane *pix = &f->fmt.pix_mp;
	struct v4l2_plane_pix_format *plane_fmt;
	struct vpe_q_data *q_data;
	struct vb2_queue *vq;
	int i;

	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
	if (!vq)
		return -EINVAL;

	if (vb2_is_busy(vq)) {
		vpe_err(ctx->dev, "queue busy\n");
		return -EBUSY;
	}

	q_data = get_q_data(ctx, f->type);
	if (!q_data)
		return -EINVAL;

	q_data->fmt		= find_format(f);
	q_data->width		= pix->width;
	q_data->height		= pix->height;
	q_data->colorspace	= pix->colorspace;
	q_data->field		= pix->field;
	q_data->nplanes		= pix->num_planes;

	for (i = 0; i < pix->num_planes; i++) {
		plane_fmt = &pix->plane_fmt[i];

		q_data->bytesperline[i]	= plane_fmt->bytesperline;
		q_data->sizeimage[i]	= plane_fmt->sizeimage;
	}

	q_data->c_rect.left	= 0;
	q_data->c_rect.top	= 0;
	q_data->c_rect.width	= q_data->width;
	q_data->c_rect.height	= q_data->height;

	if (q_data->field == V4L2_FIELD_ALTERNATE)
		q_data->flags |= Q_DATA_INTERLACED_ALTERNATE;
	else if (q_data->field == V4L2_FIELD_SEQ_TB)
		q_data->flags |= Q_DATA_INTERLACED_SEQ_TB;
	else
		q_data->flags &= ~Q_IS_INTERLACED;

	/* the crop height is halved for the case of SEQ_TB buffers */
	if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB)
		q_data->c_rect.height /= 2;

	vpe_dbg(ctx->dev, "Setting format for type %d, wxh: %dx%d, fmt: %d bpl_y %d",
		f->type, q_data->width, q_data->height, q_data->fmt->fourcc,
		q_data->bytesperline[VPE_LUMA]);
	if (q_data->nplanes == 2)
		vpe_dbg(ctx->dev, " bpl_uv %d\n",
			q_data->bytesperline[VPE_CHROMA]);

	return 0;
}

static int vpe_s_fmt(struct file *file, void *priv, struct v4l2_format *f)
{
	int ret;
	struct vpe_ctx *ctx = file2ctx(file);

	ret = vpe_try_fmt(file, priv, f);
	if (ret)
		return ret;

	ret = __vpe_s_fmt(ctx, f);
	if (ret)
		return ret;

	if (V4L2_TYPE_IS_OUTPUT(f->type))
		set_src_registers(ctx);
	else
		set_dst_registers(ctx);

	return set_srcdst_params(ctx);
}

static int __vpe_try_selection(struct vpe_ctx *ctx, struct v4l2_selection *s)
{
	struct vpe_q_data *q_data;
	int height;

	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
		return -EINVAL;

	q_data = get_q_data(ctx, s->type);
	if (!q_data)
		return -EINVAL;

	switch (s->target) {
	case V4L2_SEL_TGT_COMPOSE:
		/*
		 * COMPOSE target is only valid for capture buffer type, return
		 * error for output buffer type
		 */
		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
			return -EINVAL;
		break;
	case V4L2_SEL_TGT_CROP:
		/*
		 * CROP target is only valid for output buffer type, return
		 * error for capture buffer type
		 */
		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
			return -EINVAL;
		break;
	/*
	 * bound and default crop/compose targets are invalid targets to
	 * try/set
	 */
	default:
		return -EINVAL;
	}

	/*
	 * For SEQ_TB buffers, crop height should be less than the height of
	 * the field height, not the buffer height
	 */
	if (q_data->flags & Q_DATA_INTERLACED_SEQ_TB)
		height = q_data->height / 2;
	else
		height = q_data->height;

	if (s->r.top < 0 || s->r.left < 0) {
		vpe_err(ctx->dev, "negative values for top and left\n");
		s->r.top = s->r.left = 0;
	}

	v4l_bound_align_image(&s->r.width, MIN_W, q_data->width, 1,
		&s->r.height, MIN_H, height, H_ALIGN, S_ALIGN);

	/* adjust left/top if cropping rectangle is out of bounds */
	if (s->r.left + s->r.width > q_data->width)
		s->r.left = q_data->width - s->r.width;
	if (s->r.top + s->r.height > q_data->height)
		s->r.top = q_data->height - s->r.height;

	return 0;
}

static int vpe_g_selection(struct file *file, void *fh,
		struct v4l2_selection *s)
{
	struct vpe_ctx *ctx = file2ctx(file);
	struct vpe_q_data *q_data;
	bool use_c_rect = false;

	if ((s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) &&
	    (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT))
		return -EINVAL;

	q_data = get_q_data(ctx, s->type);
	if (!q_data)
		return -EINVAL;

	switch (s->target) {
	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
			return -EINVAL;
		break;
	case V4L2_SEL_TGT_CROP_BOUNDS:
	case V4L2_SEL_TGT_CROP_DEFAULT:
		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
			return -EINVAL;
		break;
	case V4L2_SEL_TGT_COMPOSE:
		if (s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
			return -EINVAL;
		use_c_rect = true;
		break;
	case V4L2_SEL_TGT_CROP:
		if (s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
			return -EINVAL;
		use_c_rect = true;
		break;
	default:
		return -EINVAL;
	}

	if (use_c_rect) {
		/*
		 * for CROP/COMPOSE target type, return c_rect params from the
		 * respective buffer type
		 */
		s->r = q_data->c_rect;
	} else {
		/*
		 * for DEFAULT/BOUNDS target type, return width and height from
		 * S_FMT of the respective buffer type
		 */
		s->r.left = 0;
		s->r.top = 0;
		s->r.width = q_data->width;
		s->r.height = q_data->height;
	}

	return 0;
}


static int vpe_s_selection(struct file *file, void *fh,
		struct v4l2_selection *s)
{
	struct vpe_ctx *ctx = file2ctx(file);
	struct vpe_q_data *q_data;
	struct v4l2_selection sel = *s;
	int ret;

	ret = __vpe_try_selection(ctx, &sel);
	if (ret)
		return ret;

	q_data = get_q_data(ctx, sel.type);
	if (!q_data)
		return -EINVAL;

	if ((q_data->c_rect.left == sel.r.left) &&
			(q_data->c_rect.top == sel.r.top) &&
			(q_data->c_rect.width == sel.r.width) &&
			(q_data->c_rect.height == sel.r.height)) {
		vpe_dbg(ctx->dev,
			"requested crop/compose values are already set\n");
		return 0;
	}

	q_data->c_rect = sel.r;

	return set_srcdst_params(ctx);
}

/*
 * defines number of buffers/frames a context can process with VPE before
 * switching to a different context. default value is 1 buffer per context
 */
#define V4L2_CID_VPE_BUFS_PER_JOB		(V4L2_CID_USER_TI_VPE_BASE + 0)

static int vpe_s_ctrl(struct v4l2_ctrl *ctrl)
{
	struct vpe_ctx *ctx =
		container_of(ctrl->handler, struct vpe_ctx, hdl);

	switch (ctrl->id) {
	case V4L2_CID_VPE_BUFS_PER_JOB:
		ctx->bufs_per_job = ctrl->val;
		break;

	default:
		vpe_err(ctx->dev, "Invalid control\n");
		return -EINVAL;
	}

	return 0;
}

static const struct v4l2_ctrl_ops vpe_ctrl_ops = {
	.s_ctrl = vpe_s_ctrl,
};

static const struct v4l2_ioctl_ops vpe_ioctl_ops = {
	.vidioc_querycap		= vpe_querycap,

	.vidioc_enum_fmt_vid_cap_mplane	= vpe_enum_fmt,
	.vidioc_g_fmt_vid_cap_mplane	= vpe_g_fmt,
	.vidioc_try_fmt_vid_cap_mplane	= vpe_try_fmt,
	.vidioc_s_fmt_vid_cap_mplane	= vpe_s_fmt,

	.vidioc_enum_fmt_vid_out_mplane	= vpe_enum_fmt,
	.vidioc_g_fmt_vid_out_mplane	= vpe_g_fmt,
	.vidioc_try_fmt_vid_out_mplane	= vpe_try_fmt,
	.vidioc_s_fmt_vid_out_mplane	= vpe_s_fmt,

	.vidioc_g_selection		= vpe_g_selection,
	.vidioc_s_selection		= vpe_s_selection,

	.vidioc_reqbufs			= v4l2_m2m_ioctl_reqbufs,
	.vidioc_querybuf		= v4l2_m2m_ioctl_querybuf,
	.vidioc_qbuf			= v4l2_m2m_ioctl_qbuf,
	.vidioc_dqbuf			= v4l2_m2m_ioctl_dqbuf,
	.vidioc_expbuf			= v4l2_m2m_ioctl_expbuf,
	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,

	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
};

/*
 * Queue operations
 */
static int vpe_queue_setup(struct vb2_queue *vq,
			   unsigned int *nbuffers, unsigned int *nplanes,
			   unsigned int sizes[], struct device *alloc_devs[])
{
	int i;
	struct vpe_ctx *ctx = vb2_get_drv_priv(vq);
	struct vpe_q_data *q_data;

	q_data = get_q_data(ctx, vq->type);

	*nplanes = q_data->nplanes;

	for (i = 0; i < *nplanes; i++)
		sizes[i] = q_data->sizeimage[i];

	vpe_dbg(ctx->dev, "get %d buffer(s) of size %d", *nbuffers,
		sizes[VPE_LUMA]);
	if (q_data->nplanes == 2)
		vpe_dbg(ctx->dev, " and %d\n", sizes[VPE_CHROMA]);

	return 0;
}

static int vpe_buf_prepare(struct vb2_buffer *vb)
{
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
	struct vpe_q_data *q_data;
	int i, num_planes;

	vpe_dbg(ctx->dev, "type: %d\n", vb->vb2_queue->type);

	q_data = get_q_data(ctx, vb->vb2_queue->type);
	num_planes = q_data->nplanes;

	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
		if (!(q_data->flags & Q_IS_INTERLACED)) {
			vbuf->field = V4L2_FIELD_NONE;
		} else {
			if (vbuf->field != V4L2_FIELD_TOP &&
			    vbuf->field != V4L2_FIELD_BOTTOM &&
			    vbuf->field != V4L2_FIELD_SEQ_TB)
				return -EINVAL;
		}
	}

	for (i = 0; i < num_planes; i++) {
		if (vb2_plane_size(vb, i) < q_data->sizeimage[i]) {
			vpe_err(ctx->dev,
				"data will not fit into plane (%lu < %lu)\n",
				vb2_plane_size(vb, i),
				(long) q_data->sizeimage[i]);
			return -EINVAL;
		}
	}

	for (i = 0; i < num_planes; i++)
		vb2_set_plane_payload(vb, i, q_data->sizeimage[i]);

	return 0;
}

static void vpe_buf_queue(struct vb2_buffer *vb)
{
	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
	struct vpe_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);

	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
}

static int check_srcdst_sizes(struct vpe_ctx *ctx)
{
	struct vpe_q_data *s_q_data =  &ctx->q_data[Q_DATA_SRC];
	struct vpe_q_data *d_q_data =  &ctx->q_data[Q_DATA_DST];
	unsigned int src_w = s_q_data->c_rect.width;
	unsigned int src_h = s_q_data->c_rect.height;
	unsigned int dst_w = d_q_data->c_rect.width;
	unsigned int dst_h = d_q_data->c_rect.height;

	if (src_w == dst_w && src_h == dst_h)
		return 0;

	if (src_h <= SC_MAX_PIXEL_HEIGHT &&
	    src_w <= SC_MAX_PIXEL_WIDTH &&
	    dst_h <= SC_MAX_PIXEL_HEIGHT &&
	    dst_w <= SC_MAX_PIXEL_WIDTH)
		return 0;

	return -1;
}

static void vpe_return_all_buffers(struct vpe_ctx *ctx,  struct vb2_queue *q,
				   enum vb2_buffer_state state)
{
	struct vb2_v4l2_buffer *vb;
	unsigned long flags;

	for (;;) {
		if (V4L2_TYPE_IS_OUTPUT(q->type))
			vb = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
		else
			vb = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
		if (!vb)
			break;
		spin_lock_irqsave(&ctx->dev->lock, flags);
		v4l2_m2m_buf_done(vb, state);
		spin_unlock_irqrestore(&ctx->dev->lock, flags);
	}

	/*
	 * Cleanup the in-transit vb2 buffers that have been
	 * removed from their respective queue already but for
	 * which procecessing has not been completed yet.
	 */
	if (V4L2_TYPE_IS_OUTPUT(q->type)) {
		spin_lock_irqsave(&ctx->dev->lock, flags);

		if (ctx->src_vbs[2])
			v4l2_m2m_buf_done(ctx->src_vbs[2], state);

		if (ctx->src_vbs[1] && (ctx->src_vbs[1] != ctx->src_vbs[2]))
			v4l2_m2m_buf_done(ctx->src_vbs[1], state);

		if (ctx->src_vbs[0] &&
		    (ctx->src_vbs[0] != ctx->src_vbs[1]) &&
		    (ctx->src_vbs[0] != ctx->src_vbs[2]))
			v4l2_m2m_buf_done(ctx->src_vbs[0], state);

		ctx->src_vbs[2] = NULL;
		ctx->src_vbs[1] = NULL;
		ctx->src_vbs[0] = NULL;

		spin_unlock_irqrestore(&ctx->dev->lock, flags);
	} else {
		if (ctx->dst_vb) {
			spin_lock_irqsave(&ctx->dev->lock, flags);

			v4l2_m2m_buf_done(ctx->dst_vb, state);
			ctx->dst_vb = NULL;
			spin_unlock_irqrestore(&ctx->dev->lock, flags);
		}
	}
}

static int vpe_start_streaming(struct vb2_queue *q, unsigned int count)
{
	struct vpe_ctx *ctx = vb2_get_drv_priv(q);

	/* Check any of the size exceed maximum scaling sizes */
	if (check_srcdst_sizes(ctx)) {
		vpe_err(ctx->dev,
			"Conversion setup failed, check source and destination parameters\n"
			);
		vpe_return_all_buffers(ctx, q, VB2_BUF_STATE_QUEUED);
		return -EINVAL;
	}

	if (ctx->deinterlacing)
		config_edi_input_mode(ctx, 0x0);

	if (ctx->sequence != 0)
		set_srcdst_params(ctx);

	return 0;
}

static void vpe_stop_streaming(struct vb2_queue *q)
{
	struct vpe_ctx *ctx = vb2_get_drv_priv(q);

	vpe_dump_regs(ctx->dev);
	vpdma_dump_regs(ctx->dev->vpdma);

	vpe_return_all_buffers(ctx, q, VB2_BUF_STATE_ERROR);
}

static const struct vb2_ops vpe_qops = {
	.queue_setup	 = vpe_queue_setup,
	.buf_prepare	 = vpe_buf_prepare,
	.buf_queue	 = vpe_buf_queue,
	.wait_prepare	 = vb2_ops_wait_prepare,
	.wait_finish	 = vb2_ops_wait_finish,
	.start_streaming = vpe_start_streaming,
	.stop_streaming  = vpe_stop_streaming,
};

static int queue_init(void *priv, struct vb2_queue *src_vq,
		      struct vb2_queue *dst_vq)
{
	struct vpe_ctx *ctx = priv;
	struct vpe_dev *dev = ctx->dev;
	int ret;

	memset(src_vq, 0, sizeof(*src_vq));
	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
	src_vq->drv_priv = ctx;
	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
	src_vq->ops = &vpe_qops;
	src_vq->mem_ops = &vb2_dma_contig_memops;
	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
	src_vq->lock = &dev->dev_mutex;
	src_vq->dev = dev->v4l2_dev.dev;

	ret = vb2_queue_init(src_vq);
	if (ret)
		return ret;

	memset(dst_vq, 0, sizeof(*dst_vq));
	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
	dst_vq->drv_priv = ctx;
	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
	dst_vq->ops = &vpe_qops;
	dst_vq->mem_ops = &vb2_dma_contig_memops;
	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
	dst_vq->lock = &dev->dev_mutex;
	dst_vq->dev = dev->v4l2_dev.dev;

	return vb2_queue_init(dst_vq);
}

static const struct v4l2_ctrl_config vpe_bufs_per_job = {
	.ops = &vpe_ctrl_ops,
	.id = V4L2_CID_VPE_BUFS_PER_JOB,
	.name = "Buffers Per Transaction",
	.type = V4L2_CTRL_TYPE_INTEGER,
	.def = VPE_DEF_BUFS_PER_JOB,
	.min = 1,
	.max = VIDEO_MAX_FRAME,
	.step = 1,
};

/*
 * File operations
 */
static int vpe_open(struct file *file)
{
	struct vpe_dev *dev = video_drvdata(file);
	struct vpe_q_data *s_q_data;
	struct v4l2_ctrl_handler *hdl;
	struct vpe_ctx *ctx;
	int ret;

	vpe_dbg(dev, "vpe_open\n");

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

	ctx->dev = dev;

	if (mutex_lock_interruptible(&dev->dev_mutex)) {
		ret = -ERESTARTSYS;
		goto free_ctx;
	}

	ret = vpdma_create_desc_list(&ctx->desc_list, VPE_DESC_LIST_SIZE,
			VPDMA_LIST_TYPE_NORMAL);
	if (ret != 0)
		goto unlock;

	ret = vpdma_alloc_desc_buf(&ctx->mmr_adb, sizeof(struct vpe_mmr_adb));
	if (ret != 0)
		goto free_desc_list;

	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_h, SC_COEF_SRAM_SIZE);
	if (ret != 0)
		goto free_mmr_adb;

	ret = vpdma_alloc_desc_buf(&ctx->sc_coeff_v, SC_COEF_SRAM_SIZE);
	if (ret != 0)
		goto free_sc_h;

	init_adb_hdrs(ctx);

	v4l2_fh_init(&ctx->fh, video_devdata(file));
	file->private_data = &ctx->fh;

	hdl = &ctx->hdl;
	v4l2_ctrl_handler_init(hdl, 1);
	v4l2_ctrl_new_custom(hdl, &vpe_bufs_per_job, NULL);
	if (hdl->error) {
		ret = hdl->error;
		goto exit_fh;
	}
	ctx->fh.ctrl_handler = hdl;
	v4l2_ctrl_handler_setup(hdl);

	s_q_data = &ctx->q_data[Q_DATA_SRC];
	s_q_data->fmt = &vpe_formats[2];
	s_q_data->width = 1920;
	s_q_data->height = 1080;
	s_q_data->nplanes = 1;
	s_q_data->bytesperline[VPE_LUMA] = (s_q_data->width *
			s_q_data->fmt->vpdma_fmt[VPE_LUMA]->depth) >> 3;
	s_q_data->sizeimage[VPE_LUMA] = (s_q_data->bytesperline[VPE_LUMA] *
			s_q_data->height);
	s_q_data->colorspace = V4L2_COLORSPACE_REC709;
	s_q_data->field = V4L2_FIELD_NONE;
	s_q_data->c_rect.left = 0;
	s_q_data->c_rect.top = 0;
	s_q_data->c_rect.width = s_q_data->width;
	s_q_data->c_rect.height = s_q_data->height;
	s_q_data->flags = 0;

	ctx->q_data[Q_DATA_DST] = *s_q_data;

	set_dei_shadow_registers(ctx);
	set_src_registers(ctx);
	set_dst_registers(ctx);
	ret = set_srcdst_params(ctx);
	if (ret)
		goto exit_fh;

	ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->m2m_dev, ctx, &queue_init);

	if (IS_ERR(ctx->fh.m2m_ctx)) {
		ret = PTR_ERR(ctx->fh.m2m_ctx);
		goto exit_fh;
	}

	v4l2_fh_add(&ctx->fh);

	/*
	 * for now, just report the creation of the first instance, we can later
	 * optimize the driver to enable or disable clocks when the first
	 * instance is created or the last instance released
	 */
	if (atomic_inc_return(&dev->num_instances) == 1)
		vpe_dbg(dev, "first instance created\n");

	ctx->bufs_per_job = VPE_DEF_BUFS_PER_JOB;

	ctx->load_mmrs = true;

	vpe_dbg(dev, "created instance %p, m2m_ctx: %p\n",
		ctx, ctx->fh.m2m_ctx);

	mutex_unlock(&dev->dev_mutex);

	return 0;
exit_fh:
	v4l2_ctrl_handler_free(hdl);
	v4l2_fh_exit(&ctx->fh);
	vpdma_free_desc_buf(&ctx->sc_coeff_v);
free_sc_h:
	vpdma_free_desc_buf(&ctx->sc_coeff_h);
free_mmr_adb:
	vpdma_free_desc_buf(&ctx->mmr_adb);
free_desc_list:
	vpdma_free_desc_list(&ctx->desc_list);
unlock:
	mutex_unlock(&dev->dev_mutex);
free_ctx:
	kfree(ctx);
	return ret;
}

static int vpe_release(struct file *file)
{
	struct vpe_dev *dev = video_drvdata(file);
	struct vpe_ctx *ctx = file2ctx(file);

	vpe_dbg(dev, "releasing instance %p\n", ctx);

	mutex_lock(&dev->dev_mutex);
	free_mv_buffers(ctx);
	vpdma_free_desc_list(&ctx->desc_list);
	vpdma_free_desc_buf(&ctx->mmr_adb);

	vpdma_free_desc_buf(&ctx->sc_coeff_v);
	vpdma_free_desc_buf(&ctx->sc_coeff_h);

	v4l2_fh_del(&ctx->fh);
	v4l2_fh_exit(&ctx->fh);
	v4l2_ctrl_handler_free(&ctx->hdl);
	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);

	kfree(ctx);

	/*
	 * for now, just report the release of the last instance, we can later
	 * optimize the driver to enable or disable clocks when the first
	 * instance is created or the last instance released
	 */
	if (atomic_dec_return(&dev->num_instances) == 0)
		vpe_dbg(dev, "last instance released\n");

	mutex_unlock(&dev->dev_mutex);

	return 0;
}

static const struct v4l2_file_operations vpe_fops = {
	.owner		= THIS_MODULE,
	.open		= vpe_open,
	.release	= vpe_release,
	.poll		= v4l2_m2m_fop_poll,
	.unlocked_ioctl	= video_ioctl2,
	.mmap		= v4l2_m2m_fop_mmap,
};

static struct video_device vpe_videodev = {
	.name		= VPE_MODULE_NAME,
	.fops		= &vpe_fops,
	.ioctl_ops	= &vpe_ioctl_ops,
	.minor		= -1,
	.release	= video_device_release_empty,
	.vfl_dir	= VFL_DIR_M2M,
};

static struct v4l2_m2m_ops m2m_ops = {
	.device_run	= device_run,
	.job_ready	= job_ready,
	.job_abort	= job_abort,
	.lock		= vpe_lock,
	.unlock		= vpe_unlock,
};

static int vpe_runtime_get(struct platform_device *pdev)
{
	int r;

	dev_dbg(&pdev->dev, "vpe_runtime_get\n");

	r = pm_runtime_get_sync(&pdev->dev);
	WARN_ON(r < 0);
	return r < 0 ? r : 0;
}

static void vpe_runtime_put(struct platform_device *pdev)
{

	int r;

	dev_dbg(&pdev->dev, "vpe_runtime_put\n");

	r = pm_runtime_put_sync(&pdev->dev);
	WARN_ON(r < 0 && r != -ENOSYS);
}

static void vpe_fw_cb(struct platform_device *pdev)
{
	struct vpe_dev *dev = platform_get_drvdata(pdev);
	struct video_device *vfd;
	int ret;

	vfd = &dev->vfd;
	*vfd = vpe_videodev;
	vfd->lock = &dev->dev_mutex;
	vfd->v4l2_dev = &dev->v4l2_dev;

	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
	if (ret) {
		vpe_err(dev, "Failed to register video device\n");

		vpe_set_clock_enable(dev, 0);
		vpe_runtime_put(pdev);
		pm_runtime_disable(&pdev->dev);
		v4l2_m2m_release(dev->m2m_dev);
		v4l2_device_unregister(&dev->v4l2_dev);

		return;
	}

	video_set_drvdata(vfd, dev);
	snprintf(vfd->name, sizeof(vfd->name), "%s", vpe_videodev.name);
	dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n",
		vfd->num);
}

static int vpe_probe(struct platform_device *pdev)
{
	struct vpe_dev *dev;
	int ret, irq, func;

	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
	if (!dev)
		return -ENOMEM;

	spin_lock_init(&dev->lock);

	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
	if (ret)
		return ret;

	atomic_set(&dev->num_instances, 0);
	mutex_init(&dev->dev_mutex);

	dev->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
			"vpe_top");
	/*
	 * HACK: we get resource info from device tree in the form of a list of
	 * VPE sub blocks, the driver currently uses only the base of vpe_top
	 * for register access, the driver should be changed later to access
	 * registers based on the sub block base addresses
	 */
	dev->base = devm_ioremap(&pdev->dev, dev->res->start, SZ_32K);
	if (!dev->base) {
		ret = -ENOMEM;
		goto v4l2_dev_unreg;
	}

	irq = platform_get_irq(pdev, 0);
	ret = devm_request_irq(&pdev->dev, irq, vpe_irq, 0, VPE_MODULE_NAME,
			dev);
	if (ret)
		goto v4l2_dev_unreg;

	platform_set_drvdata(pdev, dev);

	dev->m2m_dev = v4l2_m2m_init(&m2m_ops);
	if (IS_ERR(dev->m2m_dev)) {
		vpe_err(dev, "Failed to init mem2mem device\n");
		ret = PTR_ERR(dev->m2m_dev);
		goto v4l2_dev_unreg;
	}

	pm_runtime_enable(&pdev->dev);

	ret = vpe_runtime_get(pdev);
	if (ret)
		goto rel_m2m;

	/* Perform clk enable followed by reset */
	vpe_set_clock_enable(dev, 1);

	vpe_top_reset(dev);

	func = read_field_reg(dev, VPE_PID, VPE_PID_FUNC_MASK,
		VPE_PID_FUNC_SHIFT);
	vpe_dbg(dev, "VPE PID function %x\n", func);

	vpe_top_vpdma_reset(dev);

	dev->sc = sc_create(pdev, "sc");
	if (IS_ERR(dev->sc)) {
		ret = PTR_ERR(dev->sc);
		goto runtime_put;
	}

	dev->csc = csc_create(pdev, "csc");
	if (IS_ERR(dev->csc)) {
		ret = PTR_ERR(dev->csc);
		goto runtime_put;
	}

	dev->vpdma = &dev->vpdma_data;
	ret = vpdma_create(pdev, dev->vpdma, vpe_fw_cb);
	if (ret)
		goto runtime_put;

	return 0;

runtime_put:
	vpe_runtime_put(pdev);
rel_m2m:
	pm_runtime_disable(&pdev->dev);
	v4l2_m2m_release(dev->m2m_dev);
v4l2_dev_unreg:
	v4l2_device_unregister(&dev->v4l2_dev);

	return ret;
}

static int vpe_remove(struct platform_device *pdev)
{
	struct vpe_dev *dev = platform_get_drvdata(pdev);

	v4l2_info(&dev->v4l2_dev, "Removing " VPE_MODULE_NAME);

	v4l2_m2m_release(dev->m2m_dev);
	video_unregister_device(&dev->vfd);
	v4l2_device_unregister(&dev->v4l2_dev);

	vpe_set_clock_enable(dev, 0);
	vpe_runtime_put(pdev);
	pm_runtime_disable(&pdev->dev);

	return 0;
}

#if defined(CONFIG_OF)
static const struct of_device_id vpe_of_match[] = {
	{
		.compatible = "ti,vpe",
	},
	{},
};
MODULE_DEVICE_TABLE(of, vpe_of_match);
#endif

static struct platform_driver vpe_pdrv = {
	.probe		= vpe_probe,
	.remove		= vpe_remove,
	.driver		= {
		.name	= VPE_MODULE_NAME,
		.of_match_table = of_match_ptr(vpe_of_match),
	},
};

module_platform_driver(vpe_pdrv);

MODULE_DESCRIPTION("TI VPE driver");
MODULE_AUTHOR("Dale Farnsworth, <dale@farnsworth.org>");
MODULE_LICENSE("GPL");