summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/ipu-v3/ipu-image-convert.c
blob: 2ba7d437a2afc7a0758402690526de5366abb718 (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
/*
 * Copyright (C) 2012-2016 Mentor Graphics Inc.
 *
 * Queued image conversion support, with tiling and rotation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the
 * Free Software Foundation; either version 2 of the License, or (at your
 * option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
 * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * for more details.
 */

#include <linux/interrupt.h>
#include <linux/dma-mapping.h>
#include <video/imx-ipu-image-convert.h>
#include "ipu-prv.h"

/*
 * The IC Resizer has a restriction that the output frame from the
 * resizer must be 1024 or less in both width (pixels) and height
 * (lines).
 *
 * The image converter attempts to split up a conversion when
 * the desired output (converted) frame resolution exceeds the
 * IC resizer limit of 1024 in either dimension.
 *
 * If either dimension of the output frame exceeds the limit, the
 * dimension is split into 1, 2, or 4 equal stripes, for a maximum
 * of 4*4 or 16 tiles. A conversion is then carried out for each
 * tile (but taking care to pass the full frame stride length to
 * the DMA channel's parameter memory!). IDMA double-buffering is used
 * to convert each tile back-to-back when possible (see note below
 * when double_buffering boolean is set).
 *
 * Note that the input frame must be split up into the same number
 * of tiles as the output frame.
 *
 * FIXME: at this point there is no attempt to deal with visible seams
 * at the tile boundaries when upscaling. The seams are caused by a reset
 * of the bilinear upscale interpolation when starting a new tile. The
 * seams are barely visible for small upscale factors, but become
 * increasingly visible as the upscale factor gets larger, since more
 * interpolated pixels get thrown out at the tile boundaries. A possilble
 * fix might be to overlap tiles of different sizes, but this must be done
 * while also maintaining the IDMAC dma buffer address alignment and 8x8 IRT
 * alignment restrictions of each tile.
 */

#define MAX_STRIPES_W    4
#define MAX_STRIPES_H    4
#define MAX_TILES (MAX_STRIPES_W * MAX_STRIPES_H)

#define MIN_W     16
#define MIN_H     8
#define MAX_W     4096
#define MAX_H     4096

enum ipu_image_convert_type {
	IMAGE_CONVERT_IN = 0,
	IMAGE_CONVERT_OUT,
};

struct ipu_image_convert_dma_buf {
	void          *virt;
	dma_addr_t    phys;
	unsigned long len;
};

struct ipu_image_convert_dma_chan {
	int in;
	int out;
	int rot_in;
	int rot_out;
	int vdi_in_p;
	int vdi_in;
	int vdi_in_n;
};

/* dimensions of one tile */
struct ipu_image_tile {
	u32 width;
	u32 height;
	/* size and strides are in bytes */
	u32 size;
	u32 stride;
	u32 rot_stride;
	/* start Y or packed offset of this tile */
	u32 offset;
	/* offset from start to tile in U plane, for planar formats */
	u32 u_off;
	/* offset from start to tile in V plane, for planar formats */
	u32 v_off;
};

struct ipu_image_convert_image {
	struct ipu_image base;
	enum ipu_image_convert_type type;

	const struct ipu_image_pixfmt *fmt;
	unsigned int stride;

	/* # of rows (horizontal stripes) if dest height is > 1024 */
	unsigned int num_rows;
	/* # of columns (vertical stripes) if dest width is > 1024 */
	unsigned int num_cols;

	struct ipu_image_tile tile[MAX_TILES];
};

struct ipu_image_pixfmt {
	u32	fourcc;        /* V4L2 fourcc */
	int     bpp;           /* total bpp */
	int     uv_width_dec;  /* decimation in width for U/V planes */
	int     uv_height_dec; /* decimation in height for U/V planes */
	bool    planar;        /* planar format */
	bool    uv_swapped;    /* U and V planes are swapped */
	bool    uv_packed;     /* partial planar (U and V in same plane) */
};

struct ipu_image_convert_ctx;
struct ipu_image_convert_chan;
struct ipu_image_convert_priv;

struct ipu_image_convert_ctx {
	struct ipu_image_convert_chan *chan;

	ipu_image_convert_cb_t complete;
	void *complete_context;

	/* Source/destination image data and rotation mode */
	struct ipu_image_convert_image in;
	struct ipu_image_convert_image out;
	enum ipu_rotate_mode rot_mode;

	/* intermediate buffer for rotation */
	struct ipu_image_convert_dma_buf rot_intermediate[2];

	/* current buffer number for double buffering */
	int cur_buf_num;

	bool aborting;
	struct completion aborted;

	/* can we use double-buffering for this conversion operation? */
	bool double_buffering;
	/* num_rows * num_cols */
	unsigned int num_tiles;
	/* next tile to process */
	unsigned int next_tile;
	/* where to place converted tile in dest image */
	unsigned int out_tile_map[MAX_TILES];

	struct list_head list;
};

struct ipu_image_convert_chan {
	struct ipu_image_convert_priv *priv;

	enum ipu_ic_task ic_task;
	const struct ipu_image_convert_dma_chan *dma_ch;

	struct ipu_ic *ic;
	struct ipuv3_channel *in_chan;
	struct ipuv3_channel *out_chan;
	struct ipuv3_channel *rotation_in_chan;
	struct ipuv3_channel *rotation_out_chan;

	/* the IPU end-of-frame irqs */
	int out_eof_irq;
	int rot_out_eof_irq;

	spinlock_t irqlock;

	/* list of convert contexts */
	struct list_head ctx_list;
	/* queue of conversion runs */
	struct list_head pending_q;
	/* queue of completed runs */
	struct list_head done_q;

	/* the current conversion run */
	struct ipu_image_convert_run *current_run;
};

struct ipu_image_convert_priv {
	struct ipu_image_convert_chan chan[IC_NUM_TASKS];
	struct ipu_soc *ipu;
};

static const struct ipu_image_convert_dma_chan
image_convert_dma_chan[IC_NUM_TASKS] = {
	[IC_TASK_VIEWFINDER] = {
		.in = IPUV3_CHANNEL_MEM_IC_PRP_VF,
		.out = IPUV3_CHANNEL_IC_PRP_VF_MEM,
		.rot_in = IPUV3_CHANNEL_MEM_ROT_VF,
		.rot_out = IPUV3_CHANNEL_ROT_VF_MEM,
		.vdi_in_p = IPUV3_CHANNEL_MEM_VDI_PREV,
		.vdi_in = IPUV3_CHANNEL_MEM_VDI_CUR,
		.vdi_in_n = IPUV3_CHANNEL_MEM_VDI_NEXT,
	},
	[IC_TASK_POST_PROCESSOR] = {
		.in = IPUV3_CHANNEL_MEM_IC_PP,
		.out = IPUV3_CHANNEL_IC_PP_MEM,
		.rot_in = IPUV3_CHANNEL_MEM_ROT_PP,
		.rot_out = IPUV3_CHANNEL_ROT_PP_MEM,
	},
};

static const struct ipu_image_pixfmt image_convert_formats[] = {
	{
		.fourcc	= V4L2_PIX_FMT_RGB565,
		.bpp    = 16,
	}, {
		.fourcc	= V4L2_PIX_FMT_RGB24,
		.bpp    = 24,
	}, {
		.fourcc	= V4L2_PIX_FMT_BGR24,
		.bpp    = 24,
	}, {
		.fourcc	= V4L2_PIX_FMT_RGB32,
		.bpp    = 32,
	}, {
		.fourcc	= V4L2_PIX_FMT_BGR32,
		.bpp    = 32,
	}, {
		.fourcc	= V4L2_PIX_FMT_YUYV,
		.bpp    = 16,
		.uv_width_dec = 2,
		.uv_height_dec = 1,
	}, {
		.fourcc	= V4L2_PIX_FMT_UYVY,
		.bpp    = 16,
		.uv_width_dec = 2,
		.uv_height_dec = 1,
	}, {
		.fourcc	= V4L2_PIX_FMT_YUV420,
		.bpp    = 12,
		.planar = true,
		.uv_width_dec = 2,
		.uv_height_dec = 2,
	}, {
		.fourcc	= V4L2_PIX_FMT_YVU420,
		.bpp    = 12,
		.planar = true,
		.uv_width_dec = 2,
		.uv_height_dec = 2,
		.uv_swapped = true,
	}, {
		.fourcc = V4L2_PIX_FMT_NV12,
		.bpp    = 12,
		.planar = true,
		.uv_width_dec = 2,
		.uv_height_dec = 2,
		.uv_packed = true,
	}, {
		.fourcc = V4L2_PIX_FMT_YUV422P,
		.bpp    = 16,
		.planar = true,
		.uv_width_dec = 2,
		.uv_height_dec = 1,
	}, {
		.fourcc = V4L2_PIX_FMT_NV16,
		.bpp    = 16,
		.planar = true,
		.uv_width_dec = 2,
		.uv_height_dec = 1,
		.uv_packed = true,
	},
};

static const struct ipu_image_pixfmt *get_format(u32 fourcc)
{
	const struct ipu_image_pixfmt *ret = NULL;
	unsigned int i;

	for (i = 0; i < ARRAY_SIZE(image_convert_formats); i++) {
		if (image_convert_formats[i].fourcc == fourcc) {
			ret = &image_convert_formats[i];
			break;
		}
	}

	return ret;
}

static void dump_format(struct ipu_image_convert_ctx *ctx,
			struct ipu_image_convert_image *ic_image)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;

	dev_dbg(priv->ipu->dev,
		"task %u: ctx %p: %s format: %dx%d (%dx%d tiles of size %dx%d), %c%c%c%c\n",
		chan->ic_task, ctx,
		ic_image->type == IMAGE_CONVERT_OUT ? "Output" : "Input",
		ic_image->base.pix.width, ic_image->base.pix.height,
		ic_image->num_cols, ic_image->num_rows,
		ic_image->tile[0].width, ic_image->tile[0].height,
		ic_image->fmt->fourcc & 0xff,
		(ic_image->fmt->fourcc >> 8) & 0xff,
		(ic_image->fmt->fourcc >> 16) & 0xff,
		(ic_image->fmt->fourcc >> 24) & 0xff);
}

int ipu_image_convert_enum_format(int index, u32 *fourcc)
{
	const struct ipu_image_pixfmt *fmt;

	if (index >= (int)ARRAY_SIZE(image_convert_formats))
		return -EINVAL;

	/* Format found */
	fmt = &image_convert_formats[index];
	*fourcc = fmt->fourcc;
	return 0;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_enum_format);

static void free_dma_buf(struct ipu_image_convert_priv *priv,
			 struct ipu_image_convert_dma_buf *buf)
{
	if (buf->virt)
		dma_free_coherent(priv->ipu->dev,
				  buf->len, buf->virt, buf->phys);
	buf->virt = NULL;
	buf->phys = 0;
}

static int alloc_dma_buf(struct ipu_image_convert_priv *priv,
			 struct ipu_image_convert_dma_buf *buf,
			 int size)
{
	buf->len = PAGE_ALIGN(size);
	buf->virt = dma_alloc_coherent(priv->ipu->dev, buf->len, &buf->phys,
				       GFP_DMA | GFP_KERNEL);
	if (!buf->virt) {
		dev_err(priv->ipu->dev, "failed to alloc dma buffer\n");
		return -ENOMEM;
	}

	return 0;
}

static inline int num_stripes(int dim)
{
	if (dim <= 1024)
		return 1;
	else if (dim <= 2048)
		return 2;
	else
		return 4;
}

static void calc_tile_dimensions(struct ipu_image_convert_ctx *ctx,
				 struct ipu_image_convert_image *image)
{
	int i;

	for (i = 0; i < ctx->num_tiles; i++) {
		struct ipu_image_tile *tile = &image->tile[i];

		tile->height = image->base.pix.height / image->num_rows;
		tile->width = image->base.pix.width / image->num_cols;
		tile->size = ((tile->height * image->fmt->bpp) >> 3) *
			tile->width;

		if (image->fmt->planar) {
			tile->stride = tile->width;
			tile->rot_stride = tile->height;
		} else {
			tile->stride =
				(image->fmt->bpp * tile->width) >> 3;
			tile->rot_stride =
				(image->fmt->bpp * tile->height) >> 3;
		}
	}
}

/*
 * Use the rotation transformation to find the tile coordinates
 * (row, col) of a tile in the destination frame that corresponds
 * to the given tile coordinates of a source frame. The destination
 * coordinate is then converted to a tile index.
 */
static int transform_tile_index(struct ipu_image_convert_ctx *ctx,
				int src_row, int src_col)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_image *s_image = &ctx->in;
	struct ipu_image_convert_image *d_image = &ctx->out;
	int dst_row, dst_col;

	/* with no rotation it's a 1:1 mapping */
	if (ctx->rot_mode == IPU_ROTATE_NONE)
		return src_row * s_image->num_cols + src_col;

	/*
	 * before doing the transform, first we have to translate
	 * source row,col for an origin in the center of s_image
	 */
	src_row = src_row * 2 - (s_image->num_rows - 1);
	src_col = src_col * 2 - (s_image->num_cols - 1);

	/* do the rotation transform */
	if (ctx->rot_mode & IPU_ROT_BIT_90) {
		dst_col = -src_row;
		dst_row = src_col;
	} else {
		dst_col = src_col;
		dst_row = src_row;
	}

	/* apply flip */
	if (ctx->rot_mode & IPU_ROT_BIT_HFLIP)
		dst_col = -dst_col;
	if (ctx->rot_mode & IPU_ROT_BIT_VFLIP)
		dst_row = -dst_row;

	dev_dbg(priv->ipu->dev, "task %u: ctx %p: [%d,%d] --> [%d,%d]\n",
		chan->ic_task, ctx, src_col, src_row, dst_col, dst_row);

	/*
	 * finally translate dest row,col using an origin in upper
	 * left of d_image
	 */
	dst_row += d_image->num_rows - 1;
	dst_col += d_image->num_cols - 1;
	dst_row /= 2;
	dst_col /= 2;

	return dst_row * d_image->num_cols + dst_col;
}

/*
 * Fill the out_tile_map[] with transformed destination tile indeces.
 */
static void calc_out_tile_map(struct ipu_image_convert_ctx *ctx)
{
	struct ipu_image_convert_image *s_image = &ctx->in;
	unsigned int row, col, tile = 0;

	for (row = 0; row < s_image->num_rows; row++) {
		for (col = 0; col < s_image->num_cols; col++) {
			ctx->out_tile_map[tile] =
				transform_tile_index(ctx, row, col);
			tile++;
		}
	}
}

static void calc_tile_offsets_planar(struct ipu_image_convert_ctx *ctx,
				     struct ipu_image_convert_image *image)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	const struct ipu_image_pixfmt *fmt = image->fmt;
	unsigned int row, col, tile = 0;
	u32 H, w, h, y_stride, uv_stride;
	u32 uv_row_off, uv_col_off, uv_off, u_off, v_off, tmp;
	u32 y_row_off, y_col_off, y_off;
	u32 y_size, uv_size;

	/* setup some convenience vars */
	H = image->base.pix.height;

	y_stride = image->stride;
	uv_stride = y_stride / fmt->uv_width_dec;
	if (fmt->uv_packed)
		uv_stride *= 2;

	y_size = H * y_stride;
	uv_size = y_size / (fmt->uv_width_dec * fmt->uv_height_dec);

	for (row = 0; row < image->num_rows; row++) {
		w = image->tile[tile].width;
		h = image->tile[tile].height;
		y_row_off = row * h * y_stride;
		uv_row_off = (row * h * uv_stride) / fmt->uv_height_dec;

		for (col = 0; col < image->num_cols; col++) {
			y_col_off = col * w;
			uv_col_off = y_col_off / fmt->uv_width_dec;
			if (fmt->uv_packed)
				uv_col_off *= 2;

			y_off = y_row_off + y_col_off;
			uv_off = uv_row_off + uv_col_off;

			u_off = y_size - y_off + uv_off;
			v_off = (fmt->uv_packed) ? 0 : u_off + uv_size;
			if (fmt->uv_swapped) {
				tmp = u_off;
				u_off = v_off;
				v_off = tmp;
			}

			image->tile[tile].offset = y_off;
			image->tile[tile].u_off = u_off;
			image->tile[tile++].v_off = v_off;

			dev_dbg(priv->ipu->dev,
				"task %u: ctx %p: %s@[%d,%d]: y_off %08x, u_off %08x, v_off %08x\n",
				chan->ic_task, ctx,
				image->type == IMAGE_CONVERT_IN ?
				"Input" : "Output", row, col,
				y_off, u_off, v_off);
		}
	}
}

static void calc_tile_offsets_packed(struct ipu_image_convert_ctx *ctx,
				     struct ipu_image_convert_image *image)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	const struct ipu_image_pixfmt *fmt = image->fmt;
	unsigned int row, col, tile = 0;
	u32 w, h, bpp, stride;
	u32 row_off, col_off;

	/* setup some convenience vars */
	stride = image->stride;
	bpp = fmt->bpp;

	for (row = 0; row < image->num_rows; row++) {
		w = image->tile[tile].width;
		h = image->tile[tile].height;
		row_off = row * h * stride;

		for (col = 0; col < image->num_cols; col++) {
			col_off = (col * w * bpp) >> 3;

			image->tile[tile].offset = row_off + col_off;
			image->tile[tile].u_off = 0;
			image->tile[tile++].v_off = 0;

			dev_dbg(priv->ipu->dev,
				"task %u: ctx %p: %s@[%d,%d]: phys %08x\n",
				chan->ic_task, ctx,
				image->type == IMAGE_CONVERT_IN ?
				"Input" : "Output", row, col,
				row_off + col_off);
		}
	}
}

static void calc_tile_offsets(struct ipu_image_convert_ctx *ctx,
			      struct ipu_image_convert_image *image)
{
	if (image->fmt->planar)
		calc_tile_offsets_planar(ctx, image);
	else
		calc_tile_offsets_packed(ctx, image);
}

/*
 * return the number of runs in given queue (pending_q or done_q)
 * for this context. hold irqlock when calling.
 */
static int get_run_count(struct ipu_image_convert_ctx *ctx,
			 struct list_head *q)
{
	struct ipu_image_convert_run *run;
	int count = 0;

	lockdep_assert_held(&ctx->chan->irqlock);

	list_for_each_entry(run, q, list) {
		if (run->ctx == ctx)
			count++;
	}

	return count;
}

static void convert_stop(struct ipu_image_convert_run *run)
{
	struct ipu_image_convert_ctx *ctx = run->ctx;
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;

	dev_dbg(priv->ipu->dev, "%s: task %u: stopping ctx %p run %p\n",
		__func__, chan->ic_task, ctx, run);

	/* disable IC tasks and the channels */
	ipu_ic_task_disable(chan->ic);
	ipu_idmac_disable_channel(chan->in_chan);
	ipu_idmac_disable_channel(chan->out_chan);

	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		ipu_idmac_disable_channel(chan->rotation_in_chan);
		ipu_idmac_disable_channel(chan->rotation_out_chan);
		ipu_idmac_unlink(chan->out_chan, chan->rotation_in_chan);
	}

	ipu_ic_disable(chan->ic);
}

static void init_idmac_channel(struct ipu_image_convert_ctx *ctx,
			       struct ipuv3_channel *channel,
			       struct ipu_image_convert_image *image,
			       enum ipu_rotate_mode rot_mode,
			       bool rot_swap_width_height)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	unsigned int burst_size;
	u32 width, height, stride;
	dma_addr_t addr0, addr1 = 0;
	struct ipu_image tile_image;
	unsigned int tile_idx[2];

	if (image->type == IMAGE_CONVERT_OUT) {
		tile_idx[0] = ctx->out_tile_map[0];
		tile_idx[1] = ctx->out_tile_map[1];
	} else {
		tile_idx[0] = 0;
		tile_idx[1] = 1;
	}

	if (rot_swap_width_height) {
		width = image->tile[0].height;
		height = image->tile[0].width;
		stride = image->tile[0].rot_stride;
		addr0 = ctx->rot_intermediate[0].phys;
		if (ctx->double_buffering)
			addr1 = ctx->rot_intermediate[1].phys;
	} else {
		width = image->tile[0].width;
		height = image->tile[0].height;
		stride = image->stride;
		addr0 = image->base.phys0 +
			image->tile[tile_idx[0]].offset;
		if (ctx->double_buffering)
			addr1 = image->base.phys0 +
				image->tile[tile_idx[1]].offset;
	}

	ipu_cpmem_zero(channel);

	memset(&tile_image, 0, sizeof(tile_image));
	tile_image.pix.width = tile_image.rect.width = width;
	tile_image.pix.height = tile_image.rect.height = height;
	tile_image.pix.bytesperline = stride;
	tile_image.pix.pixelformat =  image->fmt->fourcc;
	tile_image.phys0 = addr0;
	tile_image.phys1 = addr1;
	ipu_cpmem_set_image(channel, &tile_image);

	if (image->fmt->planar && !rot_swap_width_height)
		ipu_cpmem_set_uv_offset(channel,
					image->tile[tile_idx[0]].u_off,
					image->tile[tile_idx[0]].v_off);

	if (rot_mode)
		ipu_cpmem_set_rotation(channel, rot_mode);

	if (channel == chan->rotation_in_chan ||
	    channel == chan->rotation_out_chan) {
		burst_size = 8;
		ipu_cpmem_set_block_mode(channel);
	} else
		burst_size = (width % 16) ? 8 : 16;

	ipu_cpmem_set_burstsize(channel, burst_size);

	ipu_ic_task_idma_init(chan->ic, channel, width, height,
			      burst_size, rot_mode);

	ipu_cpmem_set_axi_id(channel, 1);

	ipu_idmac_set_double_buffer(channel, ctx->double_buffering);
}

static int convert_start(struct ipu_image_convert_run *run)
{
	struct ipu_image_convert_ctx *ctx = run->ctx;
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_image *s_image = &ctx->in;
	struct ipu_image_convert_image *d_image = &ctx->out;
	enum ipu_color_space src_cs, dest_cs;
	unsigned int dest_width, dest_height;
	int ret;

	dev_dbg(priv->ipu->dev, "%s: task %u: starting ctx %p run %p\n",
		__func__, chan->ic_task, ctx, run);

	src_cs = ipu_pixelformat_to_colorspace(s_image->fmt->fourcc);
	dest_cs = ipu_pixelformat_to_colorspace(d_image->fmt->fourcc);

	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		/* swap width/height for resizer */
		dest_width = d_image->tile[0].height;
		dest_height = d_image->tile[0].width;
	} else {
		dest_width = d_image->tile[0].width;
		dest_height = d_image->tile[0].height;
	}

	/* setup the IC resizer and CSC */
	ret = ipu_ic_task_init(chan->ic,
			       s_image->tile[0].width,
			       s_image->tile[0].height,
			       dest_width,
			       dest_height,
			       src_cs, dest_cs);
	if (ret) {
		dev_err(priv->ipu->dev, "ipu_ic_task_init failed, %d\n", ret);
		return ret;
	}

	/* init the source MEM-->IC PP IDMAC channel */
	init_idmac_channel(ctx, chan->in_chan, s_image,
			   IPU_ROTATE_NONE, false);

	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		/* init the IC PP-->MEM IDMAC channel */
		init_idmac_channel(ctx, chan->out_chan, d_image,
				   IPU_ROTATE_NONE, true);

		/* init the MEM-->IC PP ROT IDMAC channel */
		init_idmac_channel(ctx, chan->rotation_in_chan, d_image,
				   ctx->rot_mode, true);

		/* init the destination IC PP ROT-->MEM IDMAC channel */
		init_idmac_channel(ctx, chan->rotation_out_chan, d_image,
				   IPU_ROTATE_NONE, false);

		/* now link IC PP-->MEM to MEM-->IC PP ROT */
		ipu_idmac_link(chan->out_chan, chan->rotation_in_chan);
	} else {
		/* init the destination IC PP-->MEM IDMAC channel */
		init_idmac_channel(ctx, chan->out_chan, d_image,
				   ctx->rot_mode, false);
	}

	/* enable the IC */
	ipu_ic_enable(chan->ic);

	/* set buffers ready */
	ipu_idmac_select_buffer(chan->in_chan, 0);
	ipu_idmac_select_buffer(chan->out_chan, 0);
	if (ipu_rot_mode_is_irt(ctx->rot_mode))
		ipu_idmac_select_buffer(chan->rotation_out_chan, 0);
	if (ctx->double_buffering) {
		ipu_idmac_select_buffer(chan->in_chan, 1);
		ipu_idmac_select_buffer(chan->out_chan, 1);
		if (ipu_rot_mode_is_irt(ctx->rot_mode))
			ipu_idmac_select_buffer(chan->rotation_out_chan, 1);
	}

	/* enable the channels! */
	ipu_idmac_enable_channel(chan->in_chan);
	ipu_idmac_enable_channel(chan->out_chan);
	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		ipu_idmac_enable_channel(chan->rotation_in_chan);
		ipu_idmac_enable_channel(chan->rotation_out_chan);
	}

	ipu_ic_task_enable(chan->ic);

	ipu_cpmem_dump(chan->in_chan);
	ipu_cpmem_dump(chan->out_chan);
	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		ipu_cpmem_dump(chan->rotation_in_chan);
		ipu_cpmem_dump(chan->rotation_out_chan);
	}

	ipu_dump(priv->ipu);

	return 0;
}

/* hold irqlock when calling */
static int do_run(struct ipu_image_convert_run *run)
{
	struct ipu_image_convert_ctx *ctx = run->ctx;
	struct ipu_image_convert_chan *chan = ctx->chan;

	lockdep_assert_held(&chan->irqlock);

	ctx->in.base.phys0 = run->in_phys;
	ctx->out.base.phys0 = run->out_phys;

	ctx->cur_buf_num = 0;
	ctx->next_tile = 1;

	/* remove run from pending_q and set as current */
	list_del(&run->list);
	chan->current_run = run;

	return convert_start(run);
}

/* hold irqlock when calling */
static void run_next(struct ipu_image_convert_chan *chan)
{
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_run *run, *tmp;
	int ret;

	lockdep_assert_held(&chan->irqlock);

	list_for_each_entry_safe(run, tmp, &chan->pending_q, list) {
		/* skip contexts that are aborting */
		if (run->ctx->aborting) {
			dev_dbg(priv->ipu->dev,
				"%s: task %u: skipping aborting ctx %p run %p\n",
				__func__, chan->ic_task, run->ctx, run);
			continue;
		}

		ret = do_run(run);
		if (!ret)
			break;

		/*
		 * something went wrong with start, add the run
		 * to done q and continue to the next run in the
		 * pending q.
		 */
		run->status = ret;
		list_add_tail(&run->list, &chan->done_q);
		chan->current_run = NULL;
	}
}

static void empty_done_q(struct ipu_image_convert_chan *chan)
{
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_run *run;
	unsigned long flags;

	spin_lock_irqsave(&chan->irqlock, flags);

	while (!list_empty(&chan->done_q)) {
		run = list_entry(chan->done_q.next,
				 struct ipu_image_convert_run,
				 list);

		list_del(&run->list);

		dev_dbg(priv->ipu->dev,
			"%s: task %u: completing ctx %p run %p with %d\n",
			__func__, chan->ic_task, run->ctx, run, run->status);

		/* call the completion callback and free the run */
		spin_unlock_irqrestore(&chan->irqlock, flags);
		run->ctx->complete(run, run->ctx->complete_context);
		spin_lock_irqsave(&chan->irqlock, flags);
	}

	spin_unlock_irqrestore(&chan->irqlock, flags);
}

/*
 * the bottom half thread clears out the done_q, calling the
 * completion handler for each.
 */
static irqreturn_t do_bh(int irq, void *dev_id)
{
	struct ipu_image_convert_chan *chan = dev_id;
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_ctx *ctx;
	unsigned long flags;

	dev_dbg(priv->ipu->dev, "%s: task %u: enter\n", __func__,
		chan->ic_task);

	empty_done_q(chan);

	spin_lock_irqsave(&chan->irqlock, flags);

	/*
	 * the done_q is cleared out, signal any contexts
	 * that are aborting that abort can complete.
	 */
	list_for_each_entry(ctx, &chan->ctx_list, list) {
		if (ctx->aborting) {
			dev_dbg(priv->ipu->dev,
				"%s: task %u: signaling abort for ctx %p\n",
				__func__, chan->ic_task, ctx);
			complete(&ctx->aborted);
		}
	}

	spin_unlock_irqrestore(&chan->irqlock, flags);

	dev_dbg(priv->ipu->dev, "%s: task %u: exit\n", __func__,
		chan->ic_task);

	return IRQ_HANDLED;
}

/* hold irqlock when calling */
static irqreturn_t do_irq(struct ipu_image_convert_run *run)
{
	struct ipu_image_convert_ctx *ctx = run->ctx;
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_tile *src_tile, *dst_tile;
	struct ipu_image_convert_image *s_image = &ctx->in;
	struct ipu_image_convert_image *d_image = &ctx->out;
	struct ipuv3_channel *outch;
	unsigned int dst_idx;

	lockdep_assert_held(&chan->irqlock);

	outch = ipu_rot_mode_is_irt(ctx->rot_mode) ?
		chan->rotation_out_chan : chan->out_chan;

	/*
	 * It is difficult to stop the channel DMA before the channels
	 * enter the paused state. Without double-buffering the channels
	 * are always in a paused state when the EOF irq occurs, so it
	 * is safe to stop the channels now. For double-buffering we
	 * just ignore the abort until the operation completes, when it
	 * is safe to shut down.
	 */
	if (ctx->aborting && !ctx->double_buffering) {
		convert_stop(run);
		run->status = -EIO;
		goto done;
	}

	if (ctx->next_tile == ctx->num_tiles) {
		/*
		 * the conversion is complete
		 */
		convert_stop(run);
		run->status = 0;
		goto done;
	}

	/*
	 * not done, place the next tile buffers.
	 */
	if (!ctx->double_buffering) {

		src_tile = &s_image->tile[ctx->next_tile];
		dst_idx = ctx->out_tile_map[ctx->next_tile];
		dst_tile = &d_image->tile[dst_idx];

		ipu_cpmem_set_buffer(chan->in_chan, 0,
				     s_image->base.phys0 + src_tile->offset);
		ipu_cpmem_set_buffer(outch, 0,
				     d_image->base.phys0 + dst_tile->offset);
		if (s_image->fmt->planar)
			ipu_cpmem_set_uv_offset(chan->in_chan,
						src_tile->u_off,
						src_tile->v_off);
		if (d_image->fmt->planar)
			ipu_cpmem_set_uv_offset(outch,
						dst_tile->u_off,
						dst_tile->v_off);

		ipu_idmac_select_buffer(chan->in_chan, 0);
		ipu_idmac_select_buffer(outch, 0);

	} else if (ctx->next_tile < ctx->num_tiles - 1) {

		src_tile = &s_image->tile[ctx->next_tile + 1];
		dst_idx = ctx->out_tile_map[ctx->next_tile + 1];
		dst_tile = &d_image->tile[dst_idx];

		ipu_cpmem_set_buffer(chan->in_chan, ctx->cur_buf_num,
				     s_image->base.phys0 + src_tile->offset);
		ipu_cpmem_set_buffer(outch, ctx->cur_buf_num,
				     d_image->base.phys0 + dst_tile->offset);

		ipu_idmac_select_buffer(chan->in_chan, ctx->cur_buf_num);
		ipu_idmac_select_buffer(outch, ctx->cur_buf_num);

		ctx->cur_buf_num ^= 1;
	}

	ctx->next_tile++;
	return IRQ_HANDLED;
done:
	list_add_tail(&run->list, &chan->done_q);
	chan->current_run = NULL;
	run_next(chan);
	return IRQ_WAKE_THREAD;
}

static irqreturn_t norotate_irq(int irq, void *data)
{
	struct ipu_image_convert_chan *chan = data;
	struct ipu_image_convert_ctx *ctx;
	struct ipu_image_convert_run *run;
	unsigned long flags;
	irqreturn_t ret;

	spin_lock_irqsave(&chan->irqlock, flags);

	/* get current run and its context */
	run = chan->current_run;
	if (!run) {
		ret = IRQ_NONE;
		goto out;
	}

	ctx = run->ctx;

	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		/* this is a rotation operation, just ignore */
		spin_unlock_irqrestore(&chan->irqlock, flags);
		return IRQ_HANDLED;
	}

	ret = do_irq(run);
out:
	spin_unlock_irqrestore(&chan->irqlock, flags);
	return ret;
}

static irqreturn_t rotate_irq(int irq, void *data)
{
	struct ipu_image_convert_chan *chan = data;
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_ctx *ctx;
	struct ipu_image_convert_run *run;
	unsigned long flags;
	irqreturn_t ret;

	spin_lock_irqsave(&chan->irqlock, flags);

	/* get current run and its context */
	run = chan->current_run;
	if (!run) {
		ret = IRQ_NONE;
		goto out;
	}

	ctx = run->ctx;

	if (!ipu_rot_mode_is_irt(ctx->rot_mode)) {
		/* this was NOT a rotation operation, shouldn't happen */
		dev_err(priv->ipu->dev, "Unexpected rotation interrupt\n");
		spin_unlock_irqrestore(&chan->irqlock, flags);
		return IRQ_HANDLED;
	}

	ret = do_irq(run);
out:
	spin_unlock_irqrestore(&chan->irqlock, flags);
	return ret;
}

/*
 * try to force the completion of runs for this ctx. Called when
 * abort wait times out in ipu_image_convert_abort().
 */
static void force_abort(struct ipu_image_convert_ctx *ctx)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_run *run;
	unsigned long flags;

	spin_lock_irqsave(&chan->irqlock, flags);

	run = chan->current_run;
	if (run && run->ctx == ctx) {
		convert_stop(run);
		run->status = -EIO;
		list_add_tail(&run->list, &chan->done_q);
		chan->current_run = NULL;
		run_next(chan);
	}

	spin_unlock_irqrestore(&chan->irqlock, flags);

	empty_done_q(chan);
}

static void release_ipu_resources(struct ipu_image_convert_chan *chan)
{
	if (chan->out_eof_irq >= 0)
		free_irq(chan->out_eof_irq, chan);
	if (chan->rot_out_eof_irq >= 0)
		free_irq(chan->rot_out_eof_irq, chan);

	if (!IS_ERR_OR_NULL(chan->in_chan))
		ipu_idmac_put(chan->in_chan);
	if (!IS_ERR_OR_NULL(chan->out_chan))
		ipu_idmac_put(chan->out_chan);
	if (!IS_ERR_OR_NULL(chan->rotation_in_chan))
		ipu_idmac_put(chan->rotation_in_chan);
	if (!IS_ERR_OR_NULL(chan->rotation_out_chan))
		ipu_idmac_put(chan->rotation_out_chan);
	if (!IS_ERR_OR_NULL(chan->ic))
		ipu_ic_put(chan->ic);

	chan->in_chan = chan->out_chan = chan->rotation_in_chan =
		chan->rotation_out_chan = NULL;
	chan->out_eof_irq = chan->rot_out_eof_irq = -1;
}

static int get_ipu_resources(struct ipu_image_convert_chan *chan)
{
	const struct ipu_image_convert_dma_chan *dma = chan->dma_ch;
	struct ipu_image_convert_priv *priv = chan->priv;
	int ret;

	/* get IC */
	chan->ic = ipu_ic_get(priv->ipu, chan->ic_task);
	if (IS_ERR(chan->ic)) {
		dev_err(priv->ipu->dev, "could not acquire IC\n");
		ret = PTR_ERR(chan->ic);
		goto err;
	}

	/* get IDMAC channels */
	chan->in_chan = ipu_idmac_get(priv->ipu, dma->in);
	chan->out_chan = ipu_idmac_get(priv->ipu, dma->out);
	if (IS_ERR(chan->in_chan) || IS_ERR(chan->out_chan)) {
		dev_err(priv->ipu->dev, "could not acquire idmac channels\n");
		ret = -EBUSY;
		goto err;
	}

	chan->rotation_in_chan = ipu_idmac_get(priv->ipu, dma->rot_in);
	chan->rotation_out_chan = ipu_idmac_get(priv->ipu, dma->rot_out);
	if (IS_ERR(chan->rotation_in_chan) || IS_ERR(chan->rotation_out_chan)) {
		dev_err(priv->ipu->dev,
			"could not acquire idmac rotation channels\n");
		ret = -EBUSY;
		goto err;
	}

	/* acquire the EOF interrupts */
	chan->out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
						  chan->out_chan,
						  IPU_IRQ_EOF);

	ret = request_threaded_irq(chan->out_eof_irq, norotate_irq, do_bh,
				   0, "ipu-ic", chan);
	if (ret < 0) {
		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
			 chan->out_eof_irq);
		chan->out_eof_irq = -1;
		goto err;
	}

	chan->rot_out_eof_irq = ipu_idmac_channel_irq(priv->ipu,
						     chan->rotation_out_chan,
						     IPU_IRQ_EOF);

	ret = request_threaded_irq(chan->rot_out_eof_irq, rotate_irq, do_bh,
				   0, "ipu-ic", chan);
	if (ret < 0) {
		dev_err(priv->ipu->dev, "could not acquire irq %d\n",
			chan->rot_out_eof_irq);
		chan->rot_out_eof_irq = -1;
		goto err;
	}

	return 0;
err:
	release_ipu_resources(chan);
	return ret;
}

static int fill_image(struct ipu_image_convert_ctx *ctx,
		      struct ipu_image_convert_image *ic_image,
		      struct ipu_image *image,
		      enum ipu_image_convert_type type)
{
	struct ipu_image_convert_priv *priv = ctx->chan->priv;

	ic_image->base = *image;
	ic_image->type = type;

	ic_image->fmt = get_format(image->pix.pixelformat);
	if (!ic_image->fmt) {
		dev_err(priv->ipu->dev, "pixelformat not supported for %s\n",
			type == IMAGE_CONVERT_OUT ? "Output" : "Input");
		return -EINVAL;
	}

	if (ic_image->fmt->planar)
		ic_image->stride = ic_image->base.pix.width;
	else
		ic_image->stride  = ic_image->base.pix.bytesperline;

	calc_tile_dimensions(ctx, ic_image);
	calc_tile_offsets(ctx, ic_image);

	return 0;
}

/* borrowed from drivers/media/v4l2-core/v4l2-common.c */
static unsigned int clamp_align(unsigned int x, unsigned int min,
				unsigned int max, unsigned int align)
{
	/* Bits that must be zero to be aligned */
	unsigned int mask = ~((1 << align) - 1);

	/* Clamp to aligned min and max */
	x = clamp(x, (min + ~mask) & mask, max & mask);

	/* Round to nearest aligned value */
	if (align)
		x = (x + (1 << (align - 1))) & mask;

	return x;
}

/*
 * We have to adjust the tile width such that the tile physaddrs and
 * U and V plane offsets are multiples of 8 bytes as required by
 * the IPU DMA Controller. For the planar formats, this corresponds
 * to a pixel alignment of 16 (but use a more formal equation since
 * the variables are available). For all the packed formats, 8 is
 * good enough.
 */
static inline u32 tile_width_align(const struct ipu_image_pixfmt *fmt)
{
	return fmt->planar ? 8 * fmt->uv_width_dec : 8;
}

/*
 * For tile height alignment, we have to ensure that the output tile
 * heights are multiples of 8 lines if the IRT is required by the
 * given rotation mode (the IRT performs rotations on 8x8 blocks
 * at a time). If the IRT is not used, or for input image tiles,
 * 2 lines are good enough.
 */
static inline u32 tile_height_align(enum ipu_image_convert_type type,
				    enum ipu_rotate_mode rot_mode)
{
	return (type == IMAGE_CONVERT_OUT &&
		ipu_rot_mode_is_irt(rot_mode)) ? 8 : 2;
}

/* Adjusts input/output images to IPU restrictions */
void ipu_image_convert_adjust(struct ipu_image *in, struct ipu_image *out,
			      enum ipu_rotate_mode rot_mode)
{
	const struct ipu_image_pixfmt *infmt, *outfmt;
	unsigned int num_in_rows, num_in_cols;
	unsigned int num_out_rows, num_out_cols;
	u32 w_align, h_align;

	infmt = get_format(in->pix.pixelformat);
	outfmt = get_format(out->pix.pixelformat);

	/* set some default pixel formats if needed */
	if (!infmt) {
		in->pix.pixelformat = V4L2_PIX_FMT_RGB24;
		infmt = get_format(V4L2_PIX_FMT_RGB24);
	}
	if (!outfmt) {
		out->pix.pixelformat = V4L2_PIX_FMT_RGB24;
		outfmt = get_format(V4L2_PIX_FMT_RGB24);
	}

	/* image converter does not handle fields */
	in->pix.field = out->pix.field = V4L2_FIELD_NONE;

	/* resizer cannot downsize more than 4:1 */
	if (ipu_rot_mode_is_irt(rot_mode)) {
		out->pix.height = max_t(__u32, out->pix.height,
					in->pix.width / 4);
		out->pix.width = max_t(__u32, out->pix.width,
				       in->pix.height / 4);
	} else {
		out->pix.width = max_t(__u32, out->pix.width,
				       in->pix.width / 4);
		out->pix.height = max_t(__u32, out->pix.height,
					in->pix.height / 4);
	}

	/* get tiling rows/cols from output format */
	num_out_rows = num_stripes(out->pix.height);
	num_out_cols = num_stripes(out->pix.width);
	if (ipu_rot_mode_is_irt(rot_mode)) {
		num_in_rows = num_out_cols;
		num_in_cols = num_out_rows;
	} else {
		num_in_rows = num_out_rows;
		num_in_cols = num_out_cols;
	}

	/* align input width/height */
	w_align = ilog2(tile_width_align(infmt) * num_in_cols);
	h_align = ilog2(tile_height_align(IMAGE_CONVERT_IN, rot_mode) *
			num_in_rows);
	in->pix.width = clamp_align(in->pix.width, MIN_W, MAX_W, w_align);
	in->pix.height = clamp_align(in->pix.height, MIN_H, MAX_H, h_align);

	/* align output width/height */
	w_align = ilog2(tile_width_align(outfmt) * num_out_cols);
	h_align = ilog2(tile_height_align(IMAGE_CONVERT_OUT, rot_mode) *
			num_out_rows);
	out->pix.width = clamp_align(out->pix.width, MIN_W, MAX_W, w_align);
	out->pix.height = clamp_align(out->pix.height, MIN_H, MAX_H, h_align);

	/* set input/output strides and image sizes */
	in->pix.bytesperline = (in->pix.width * infmt->bpp) >> 3;
	in->pix.sizeimage = in->pix.height * in->pix.bytesperline;
	out->pix.bytesperline = (out->pix.width * outfmt->bpp) >> 3;
	out->pix.sizeimage = out->pix.height * out->pix.bytesperline;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_adjust);

/*
 * this is used by ipu_image_convert_prepare() to verify set input and
 * output images are valid before starting the conversion. Clients can
 * also call it before calling ipu_image_convert_prepare().
 */
int ipu_image_convert_verify(struct ipu_image *in, struct ipu_image *out,
			     enum ipu_rotate_mode rot_mode)
{
	struct ipu_image testin, testout;

	testin = *in;
	testout = *out;

	ipu_image_convert_adjust(&testin, &testout, rot_mode);

	if (testin.pix.width != in->pix.width ||
	    testin.pix.height != in->pix.height ||
	    testout.pix.width != out->pix.width ||
	    testout.pix.height != out->pix.height)
		return -EINVAL;

	return 0;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_verify);

/*
 * Call ipu_image_convert_prepare() to prepare for the conversion of
 * given images and rotation mode. Returns a new conversion context.
 */
struct ipu_image_convert_ctx *
ipu_image_convert_prepare(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
			  struct ipu_image *in, struct ipu_image *out,
			  enum ipu_rotate_mode rot_mode,
			  ipu_image_convert_cb_t complete,
			  void *complete_context)
{
	struct ipu_image_convert_priv *priv = ipu->image_convert_priv;
	struct ipu_image_convert_image *s_image, *d_image;
	struct ipu_image_convert_chan *chan;
	struct ipu_image_convert_ctx *ctx;
	unsigned long flags;
	bool get_res;
	int ret;

	if (!in || !out || !complete ||
	    (ic_task != IC_TASK_VIEWFINDER &&
	     ic_task != IC_TASK_POST_PROCESSOR))
		return ERR_PTR(-EINVAL);

	/* verify the in/out images before continuing */
	ret = ipu_image_convert_verify(in, out, rot_mode);
	if (ret) {
		dev_err(priv->ipu->dev, "%s: in/out formats invalid\n",
			__func__);
		return ERR_PTR(ret);
	}

	chan = &priv->chan[ic_task];

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

	dev_dbg(priv->ipu->dev, "%s: task %u: ctx %p\n", __func__,
		chan->ic_task, ctx);

	ctx->chan = chan;
	init_completion(&ctx->aborted);

	s_image = &ctx->in;
	d_image = &ctx->out;

	/* set tiling and rotation */
	d_image->num_rows = num_stripes(out->pix.height);
	d_image->num_cols = num_stripes(out->pix.width);
	if (ipu_rot_mode_is_irt(rot_mode)) {
		s_image->num_rows = d_image->num_cols;
		s_image->num_cols = d_image->num_rows;
	} else {
		s_image->num_rows = d_image->num_rows;
		s_image->num_cols = d_image->num_cols;
	}

	ctx->num_tiles = d_image->num_cols * d_image->num_rows;
	ctx->rot_mode = rot_mode;

	ret = fill_image(ctx, s_image, in, IMAGE_CONVERT_IN);
	if (ret)
		goto out_free;
	ret = fill_image(ctx, d_image, out, IMAGE_CONVERT_OUT);
	if (ret)
		goto out_free;

	calc_out_tile_map(ctx);

	dump_format(ctx, s_image);
	dump_format(ctx, d_image);

	ctx->complete = complete;
	ctx->complete_context = complete_context;

	/*
	 * Can we use double-buffering for this operation? If there is
	 * only one tile (the whole image can be converted in a single
	 * operation) there's no point in using double-buffering. Also,
	 * the IPU's IDMAC channels allow only a single U and V plane
	 * offset shared between both buffers, but these offsets change
	 * for every tile, and therefore would have to be updated for
	 * each buffer which is not possible. So double-buffering is
	 * impossible when either the source or destination images are
	 * a planar format (YUV420, YUV422P, etc.).
	 */
	ctx->double_buffering = (ctx->num_tiles > 1 &&
				 !s_image->fmt->planar &&
				 !d_image->fmt->planar);

	if (ipu_rot_mode_is_irt(ctx->rot_mode)) {
		ret = alloc_dma_buf(priv, &ctx->rot_intermediate[0],
				    d_image->tile[0].size);
		if (ret)
			goto out_free;
		if (ctx->double_buffering) {
			ret = alloc_dma_buf(priv,
					    &ctx->rot_intermediate[1],
					    d_image->tile[0].size);
			if (ret)
				goto out_free_dmabuf0;
		}
	}

	spin_lock_irqsave(&chan->irqlock, flags);

	get_res = list_empty(&chan->ctx_list);

	list_add_tail(&ctx->list, &chan->ctx_list);

	spin_unlock_irqrestore(&chan->irqlock, flags);

	if (get_res) {
		ret = get_ipu_resources(chan);
		if (ret)
			goto out_free_dmabuf1;
	}

	return ctx;

out_free_dmabuf1:
	free_dma_buf(priv, &ctx->rot_intermediate[1]);
	spin_lock_irqsave(&chan->irqlock, flags);
	list_del(&ctx->list);
	spin_unlock_irqrestore(&chan->irqlock, flags);
out_free_dmabuf0:
	free_dma_buf(priv, &ctx->rot_intermediate[0]);
out_free:
	kfree(ctx);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(ipu_image_convert_prepare);

/*
 * Carry out a single image conversion run. Only the physaddr's of the input
 * and output image buffers are needed. The conversion context must have
 * been created previously with ipu_image_convert_prepare().
 */
int ipu_image_convert_queue(struct ipu_image_convert_run *run)
{
	struct ipu_image_convert_chan *chan;
	struct ipu_image_convert_priv *priv;
	struct ipu_image_convert_ctx *ctx;
	unsigned long flags;
	int ret = 0;

	if (!run || !run->ctx || !run->in_phys || !run->out_phys)
		return -EINVAL;

	ctx = run->ctx;
	chan = ctx->chan;
	priv = chan->priv;

	dev_dbg(priv->ipu->dev, "%s: task %u: ctx %p run %p\n", __func__,
		chan->ic_task, ctx, run);

	INIT_LIST_HEAD(&run->list);

	spin_lock_irqsave(&chan->irqlock, flags);

	if (ctx->aborting) {
		ret = -EIO;
		goto unlock;
	}

	list_add_tail(&run->list, &chan->pending_q);

	if (!chan->current_run) {
		ret = do_run(run);
		if (ret)
			chan->current_run = NULL;
	}
unlock:
	spin_unlock_irqrestore(&chan->irqlock, flags);
	return ret;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_queue);

/* Abort any active or pending conversions for this context */
void ipu_image_convert_abort(struct ipu_image_convert_ctx *ctx)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	struct ipu_image_convert_run *run, *active_run, *tmp;
	unsigned long flags;
	int run_count, ret;
	bool need_abort;

	reinit_completion(&ctx->aborted);

	spin_lock_irqsave(&chan->irqlock, flags);

	/* move all remaining pending runs in this context to done_q */
	list_for_each_entry_safe(run, tmp, &chan->pending_q, list) {
		if (run->ctx != ctx)
			continue;
		run->status = -EIO;
		list_move_tail(&run->list, &chan->done_q);
	}

	run_count = get_run_count(ctx, &chan->done_q);
	active_run = (chan->current_run && chan->current_run->ctx == ctx) ?
		chan->current_run : NULL;

	need_abort = (run_count || active_run);

	ctx->aborting = need_abort;

	spin_unlock_irqrestore(&chan->irqlock, flags);

	if (!need_abort) {
		dev_dbg(priv->ipu->dev,
			"%s: task %u: no abort needed for ctx %p\n",
			__func__, chan->ic_task, ctx);
		return;
	}

	dev_dbg(priv->ipu->dev,
		"%s: task %u: wait for completion: %d runs, active run %p\n",
		__func__, chan->ic_task, run_count, active_run);

	ret = wait_for_completion_timeout(&ctx->aborted,
					  msecs_to_jiffies(10000));
	if (ret == 0) {
		dev_warn(priv->ipu->dev, "%s: timeout\n", __func__);
		force_abort(ctx);
	}

	ctx->aborting = false;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_abort);

/* Unprepare image conversion context */
void ipu_image_convert_unprepare(struct ipu_image_convert_ctx *ctx)
{
	struct ipu_image_convert_chan *chan = ctx->chan;
	struct ipu_image_convert_priv *priv = chan->priv;
	unsigned long flags;
	bool put_res;

	/* make sure no runs are hanging around */
	ipu_image_convert_abort(ctx);

	dev_dbg(priv->ipu->dev, "%s: task %u: removing ctx %p\n", __func__,
		chan->ic_task, ctx);

	spin_lock_irqsave(&chan->irqlock, flags);

	list_del(&ctx->list);

	put_res = list_empty(&chan->ctx_list);

	spin_unlock_irqrestore(&chan->irqlock, flags);

	if (put_res)
		release_ipu_resources(chan);

	free_dma_buf(priv, &ctx->rot_intermediate[1]);
	free_dma_buf(priv, &ctx->rot_intermediate[0]);

	kfree(ctx);
}
EXPORT_SYMBOL_GPL(ipu_image_convert_unprepare);

/*
 * "Canned" asynchronous single image conversion. Allocates and returns
 * a new conversion run.  On successful return the caller must free the
 * run and call ipu_image_convert_unprepare() after conversion completes.
 */
struct ipu_image_convert_run *
ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
		  struct ipu_image *in, struct ipu_image *out,
		  enum ipu_rotate_mode rot_mode,
		  ipu_image_convert_cb_t complete,
		  void *complete_context)
{
	struct ipu_image_convert_ctx *ctx;
	struct ipu_image_convert_run *run;
	int ret;

	ctx = ipu_image_convert_prepare(ipu, ic_task, in, out, rot_mode,
					complete, complete_context);
	if (IS_ERR(ctx))
		return ERR_PTR(PTR_ERR(ctx));

	run = kzalloc(sizeof(*run), GFP_KERNEL);
	if (!run) {
		ipu_image_convert_unprepare(ctx);
		return ERR_PTR(-ENOMEM);
	}

	run->ctx = ctx;
	run->in_phys = in->phys0;
	run->out_phys = out->phys0;

	ret = ipu_image_convert_queue(run);
	if (ret) {
		ipu_image_convert_unprepare(ctx);
		kfree(run);
		return ERR_PTR(ret);
	}

	return run;
}
EXPORT_SYMBOL_GPL(ipu_image_convert);

/* "Canned" synchronous single image conversion */
static void image_convert_sync_complete(struct ipu_image_convert_run *run,
					void *data)
{
	struct completion *comp = data;

	complete(comp);
}

int ipu_image_convert_sync(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
			   struct ipu_image *in, struct ipu_image *out,
			   enum ipu_rotate_mode rot_mode)
{
	struct ipu_image_convert_run *run;
	struct completion comp;
	int ret;

	init_completion(&comp);

	run = ipu_image_convert(ipu, ic_task, in, out, rot_mode,
				image_convert_sync_complete, &comp);
	if (IS_ERR(run))
		return PTR_ERR(run);

	ret = wait_for_completion_timeout(&comp, msecs_to_jiffies(10000));
	ret = (ret == 0) ? -ETIMEDOUT : 0;

	ipu_image_convert_unprepare(run->ctx);
	kfree(run);

	return ret;
}
EXPORT_SYMBOL_GPL(ipu_image_convert_sync);

int ipu_image_convert_init(struct ipu_soc *ipu, struct device *dev)
{
	struct ipu_image_convert_priv *priv;
	int i;

	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
	if (!priv)
		return -ENOMEM;

	ipu->image_convert_priv = priv;
	priv->ipu = ipu;

	for (i = 0; i < IC_NUM_TASKS; i++) {
		struct ipu_image_convert_chan *chan = &priv->chan[i];

		chan->ic_task = i;
		chan->priv = priv;
		chan->dma_ch = &image_convert_dma_chan[i];
		chan->out_eof_irq = -1;
		chan->rot_out_eof_irq = -1;

		spin_lock_init(&chan->irqlock);
		INIT_LIST_HEAD(&chan->ctx_list);
		INIT_LIST_HEAD(&chan->pending_q);
		INIT_LIST_HEAD(&chan->done_q);
	}

	return 0;
}

void ipu_image_convert_exit(struct ipu_soc *ipu)
{
}
OpenPOWER on IntegriCloud