summaryrefslogtreecommitdiff
path: root/drivers/dma/bcm-sba-raid.c
blob: 15c558508345a30a1168af55bebda470e3af2678 (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
/*
 * Copyright (C) 2017 Broadcom
 *
 * 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.
 */

/*
 * Broadcom SBA RAID Driver
 *
 * The Broadcom stream buffer accelerator (SBA) provides offloading
 * capabilities for RAID operations. The SBA offload engine is accessible
 * via Broadcom SoC specific ring manager. Two or more offload engines
 * can share same Broadcom SoC specific ring manager due to this Broadcom
 * SoC specific ring manager driver is implemented as a mailbox controller
 * driver and offload engine drivers are implemented as mallbox clients.
 *
 * Typically, Broadcom SoC specific ring manager will implement larger
 * number of hardware rings over one or more SBA hardware devices. By
 * design, the internal buffer size of SBA hardware device is limited
 * but all offload operations supported by SBA can be broken down into
 * multiple small size requests and executed parallely on multiple SBA
 * hardware devices for achieving high through-put.
 *
 * The Broadcom SBA RAID driver does not require any register programming
 * except submitting request to SBA hardware device via mailbox channels.
 * This driver implements a DMA device with one DMA channel using a set
 * of mailbox channels provided by Broadcom SoC specific ring manager
 * driver. To exploit parallelism (as described above), all DMA request
 * coming to SBA RAID DMA channel are broken down to smaller requests
 * and submitted to multiple mailbox channels in round-robin fashion.
 * For having more SBA DMA channels, we can create more SBA device nodes
 * in Broadcom SoC specific DTS based on number of hardware rings supported
 * by Broadcom SoC ring manager.
 */

#include <linux/bitops.h>
#include <linux/debugfs.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
#include <linux/list.h>
#include <linux/mailbox_client.h>
#include <linux/mailbox/brcm-message.h>
#include <linux/module.h>
#include <linux/of_device.h>
#include <linux/slab.h>
#include <linux/raid/pq.h>

#include "dmaengine.h"

/* ====== Driver macros and defines ===== */

#define SBA_TYPE_SHIFT					48
#define SBA_TYPE_MASK					GENMASK(1, 0)
#define SBA_TYPE_A					0x0
#define SBA_TYPE_B					0x2
#define SBA_TYPE_C					0x3
#define SBA_USER_DEF_SHIFT				32
#define SBA_USER_DEF_MASK				GENMASK(15, 0)
#define SBA_R_MDATA_SHIFT				24
#define SBA_R_MDATA_MASK				GENMASK(7, 0)
#define SBA_C_MDATA_MS_SHIFT				18
#define SBA_C_MDATA_MS_MASK				GENMASK(1, 0)
#define SBA_INT_SHIFT					17
#define SBA_INT_MASK					BIT(0)
#define SBA_RESP_SHIFT					16
#define SBA_RESP_MASK					BIT(0)
#define SBA_C_MDATA_SHIFT				8
#define SBA_C_MDATA_MASK				GENMASK(7, 0)
#define SBA_C_MDATA_BNUMx_SHIFT(__bnum)			(2 * (__bnum))
#define SBA_C_MDATA_BNUMx_MASK				GENMASK(1, 0)
#define SBA_C_MDATA_DNUM_SHIFT				5
#define SBA_C_MDATA_DNUM_MASK				GENMASK(4, 0)
#define SBA_C_MDATA_LS(__v)				((__v) & 0xff)
#define SBA_C_MDATA_MS(__v)				(((__v) >> 8) & 0x3)
#define SBA_CMD_SHIFT					0
#define SBA_CMD_MASK					GENMASK(3, 0)
#define SBA_CMD_ZERO_BUFFER				0x4
#define SBA_CMD_ZERO_ALL_BUFFERS			0x8
#define SBA_CMD_LOAD_BUFFER				0x9
#define SBA_CMD_XOR					0xa
#define SBA_CMD_GALOIS_XOR				0xb
#define SBA_CMD_WRITE_BUFFER				0xc
#define SBA_CMD_GALOIS					0xe

#define SBA_MAX_REQ_PER_MBOX_CHANNEL			8192

/* Driver helper macros */
#define to_sba_request(tx)		\
	container_of(tx, struct sba_request, tx)
#define to_sba_device(dchan)		\
	container_of(dchan, struct sba_device, dma_chan)

/* ===== Driver data structures ===== */

enum sba_request_flags {
	SBA_REQUEST_STATE_FREE		= 0x001,
	SBA_REQUEST_STATE_ALLOCED	= 0x002,
	SBA_REQUEST_STATE_PENDING	= 0x004,
	SBA_REQUEST_STATE_ACTIVE	= 0x008,
	SBA_REQUEST_STATE_ABORTED	= 0x010,
	SBA_REQUEST_STATE_MASK		= 0x0ff,
	SBA_REQUEST_FENCE		= 0x100,
};

struct sba_request {
	/* Global state */
	struct list_head node;
	struct sba_device *sba;
	u32 flags;
	/* Chained requests management */
	struct sba_request *first;
	struct list_head next;
	atomic_t next_pending_count;
	/* BRCM message data */
	struct brcm_message msg;
	struct dma_async_tx_descriptor tx;
	/* SBA commands */
	struct brcm_sba_command cmds[0];
};

enum sba_version {
	SBA_VER_1 = 0,
	SBA_VER_2
};

struct sba_device {
	/* Underlying device */
	struct device *dev;
	/* DT configuration parameters */
	enum sba_version ver;
	/* Derived configuration parameters */
	u32 max_req;
	u32 hw_buf_size;
	u32 hw_resp_size;
	u32 max_pq_coefs;
	u32 max_pq_srcs;
	u32 max_cmd_per_req;
	u32 max_xor_srcs;
	u32 max_resp_pool_size;
	u32 max_cmds_pool_size;
	/* Maibox client and Mailbox channels */
	struct mbox_client client;
	int mchans_count;
	atomic_t mchans_current;
	struct mbox_chan **mchans;
	struct device *mbox_dev;
	/* DMA device and DMA channel */
	struct dma_device dma_dev;
	struct dma_chan dma_chan;
	/* DMA channel resources */
	void *resp_base;
	dma_addr_t resp_dma_base;
	void *cmds_base;
	dma_addr_t cmds_dma_base;
	spinlock_t reqs_lock;
	bool reqs_fence;
	struct list_head reqs_alloc_list;
	struct list_head reqs_pending_list;
	struct list_head reqs_active_list;
	struct list_head reqs_aborted_list;
	struct list_head reqs_free_list;
	/* DebugFS directory entries */
	struct dentry *root;
	struct dentry *stats;
};

/* ====== Command helper routines ===== */

static inline u64 __pure sba_cmd_enc(u64 cmd, u32 val, u32 shift, u32 mask)
{
	cmd &= ~((u64)mask << shift);
	cmd |= ((u64)(val & mask) << shift);
	return cmd;
}

static inline u32 __pure sba_cmd_load_c_mdata(u32 b0)
{
	return b0 & SBA_C_MDATA_BNUMx_MASK;
}

static inline u32 __pure sba_cmd_write_c_mdata(u32 b0)
{
	return b0 & SBA_C_MDATA_BNUMx_MASK;
}

static inline u32 __pure sba_cmd_xor_c_mdata(u32 b1, u32 b0)
{
	return (b0 & SBA_C_MDATA_BNUMx_MASK) |
	       ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1));
}

static inline u32 __pure sba_cmd_pq_c_mdata(u32 d, u32 b1, u32 b0)
{
	return (b0 & SBA_C_MDATA_BNUMx_MASK) |
	       ((b1 & SBA_C_MDATA_BNUMx_MASK) << SBA_C_MDATA_BNUMx_SHIFT(1)) |
	       ((d & SBA_C_MDATA_DNUM_MASK) << SBA_C_MDATA_DNUM_SHIFT);
}

/* ====== General helper routines ===== */

static void sba_peek_mchans(struct sba_device *sba)
{
	int mchan_idx;

	for (mchan_idx = 0; mchan_idx < sba->mchans_count; mchan_idx++)
		mbox_client_peek_data(sba->mchans[mchan_idx]);
}

static struct sba_request *sba_alloc_request(struct sba_device *sba)
{
	bool found = false;
	unsigned long flags;
	struct sba_request *req = NULL;

	spin_lock_irqsave(&sba->reqs_lock, flags);
	list_for_each_entry(req, &sba->reqs_free_list, node) {
		if (async_tx_test_ack(&req->tx)) {
			list_move_tail(&req->node, &sba->reqs_alloc_list);
			found = true;
			break;
		}
	}
	spin_unlock_irqrestore(&sba->reqs_lock, flags);

	if (!found) {
		/*
		 * We have no more free requests so, we peek
		 * mailbox channels hoping few active requests
		 * would have completed which will create more
		 * room for new requests.
		 */
		sba_peek_mchans(sba);
		return NULL;
	}

	req->flags = SBA_REQUEST_STATE_ALLOCED;
	req->first = req;
	INIT_LIST_HEAD(&req->next);
	atomic_set(&req->next_pending_count, 1);

	dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan);
	async_tx_ack(&req->tx);

	return req;
}

/* Note: Must be called with sba->reqs_lock held */
static void _sba_pending_request(struct sba_device *sba,
				 struct sba_request *req)
{
	lockdep_assert_held(&sba->reqs_lock);
	req->flags &= ~SBA_REQUEST_STATE_MASK;
	req->flags |= SBA_REQUEST_STATE_PENDING;
	list_move_tail(&req->node, &sba->reqs_pending_list);
	if (list_empty(&sba->reqs_active_list))
		sba->reqs_fence = false;
}

/* Note: Must be called with sba->reqs_lock held */
static bool _sba_active_request(struct sba_device *sba,
				struct sba_request *req)
{
	lockdep_assert_held(&sba->reqs_lock);
	if (list_empty(&sba->reqs_active_list))
		sba->reqs_fence = false;
	if (sba->reqs_fence)
		return false;
	req->flags &= ~SBA_REQUEST_STATE_MASK;
	req->flags |= SBA_REQUEST_STATE_ACTIVE;
	list_move_tail(&req->node, &sba->reqs_active_list);
	if (req->flags & SBA_REQUEST_FENCE)
		sba->reqs_fence = true;
	return true;
}

/* Note: Must be called with sba->reqs_lock held */
static void _sba_abort_request(struct sba_device *sba,
			       struct sba_request *req)
{
	lockdep_assert_held(&sba->reqs_lock);
	req->flags &= ~SBA_REQUEST_STATE_MASK;
	req->flags |= SBA_REQUEST_STATE_ABORTED;
	list_move_tail(&req->node, &sba->reqs_aborted_list);
	if (list_empty(&sba->reqs_active_list))
		sba->reqs_fence = false;
}

/* Note: Must be called with sba->reqs_lock held */
static void _sba_free_request(struct sba_device *sba,
			      struct sba_request *req)
{
	lockdep_assert_held(&sba->reqs_lock);
	req->flags &= ~SBA_REQUEST_STATE_MASK;
	req->flags |= SBA_REQUEST_STATE_FREE;
	list_move_tail(&req->node, &sba->reqs_free_list);
	if (list_empty(&sba->reqs_active_list))
		sba->reqs_fence = false;
}

static void sba_free_chained_requests(struct sba_request *req)
{
	unsigned long flags;
	struct sba_request *nreq;
	struct sba_device *sba = req->sba;

	spin_lock_irqsave(&sba->reqs_lock, flags);

	_sba_free_request(sba, req);
	list_for_each_entry(nreq, &req->next, next)
		_sba_free_request(sba, nreq);

	spin_unlock_irqrestore(&sba->reqs_lock, flags);
}

static void sba_chain_request(struct sba_request *first,
			      struct sba_request *req)
{
	unsigned long flags;
	struct sba_device *sba = req->sba;

	spin_lock_irqsave(&sba->reqs_lock, flags);

	list_add_tail(&req->next, &first->next);
	req->first = first;
	atomic_inc(&first->next_pending_count);

	spin_unlock_irqrestore(&sba->reqs_lock, flags);
}

static void sba_cleanup_nonpending_requests(struct sba_device *sba)
{
	unsigned long flags;
	struct sba_request *req, *req1;

	spin_lock_irqsave(&sba->reqs_lock, flags);

	/* Freeup all alloced request */
	list_for_each_entry_safe(req, req1, &sba->reqs_alloc_list, node)
		_sba_free_request(sba, req);

	/* Set all active requests as aborted */
	list_for_each_entry_safe(req, req1, &sba->reqs_active_list, node)
		_sba_abort_request(sba, req);

	/*
	 * Note: We expect that aborted request will be eventually
	 * freed by sba_receive_message()
	 */

	spin_unlock_irqrestore(&sba->reqs_lock, flags);
}

static void sba_cleanup_pending_requests(struct sba_device *sba)
{
	unsigned long flags;
	struct sba_request *req, *req1;

	spin_lock_irqsave(&sba->reqs_lock, flags);

	/* Freeup all pending request */
	list_for_each_entry_safe(req, req1, &sba->reqs_pending_list, node)
		_sba_free_request(sba, req);

	spin_unlock_irqrestore(&sba->reqs_lock, flags);
}

static int sba_send_mbox_request(struct sba_device *sba,
				 struct sba_request *req)
{
	int mchans_idx, ret = 0;

	/* Select mailbox channel in round-robin fashion */
	mchans_idx = atomic_inc_return(&sba->mchans_current);
	mchans_idx = mchans_idx % sba->mchans_count;

	/* Send message for the request */
	req->msg.error = 0;
	ret = mbox_send_message(sba->mchans[mchans_idx], &req->msg);
	if (ret < 0) {
		dev_err(sba->dev, "send message failed with error %d", ret);
		return ret;
	}

	/* Check error returned by mailbox controller */
	ret = req->msg.error;
	if (ret < 0) {
		dev_err(sba->dev, "message error %d", ret);
	}

	/* Signal txdone for mailbox channel */
	mbox_client_txdone(sba->mchans[mchans_idx], ret);

	return ret;
}

/* Note: Must be called with sba->reqs_lock held */
static void _sba_process_pending_requests(struct sba_device *sba)
{
	int ret;
	u32 count;
	struct sba_request *req;

	/*
	 * Process few pending requests
	 *
	 * For now, we process (<number_of_mailbox_channels> * 8)
	 * number of requests at a time.
	 */
	count = sba->mchans_count * 8;
	while (!list_empty(&sba->reqs_pending_list) && count) {
		/* Get the first pending request */
		req = list_first_entry(&sba->reqs_pending_list,
				       struct sba_request, node);

		/* Try to make request active */
		if (!_sba_active_request(sba, req))
			break;

		/* Send request to mailbox channel */
		ret = sba_send_mbox_request(sba, req);
		if (ret < 0) {
			_sba_pending_request(sba, req);
			break;
		}

		count--;
	}
}

static void sba_process_received_request(struct sba_device *sba,
					 struct sba_request *req)
{
	unsigned long flags;
	struct dma_async_tx_descriptor *tx;
	struct sba_request *nreq, *first = req->first;

	/* Process only after all chained requests are received */
	if (!atomic_dec_return(&first->next_pending_count)) {
		tx = &first->tx;

		WARN_ON(tx->cookie < 0);
		if (tx->cookie > 0) {
			spin_lock_irqsave(&sba->reqs_lock, flags);
			dma_cookie_complete(tx);
			spin_unlock_irqrestore(&sba->reqs_lock, flags);
			dmaengine_desc_get_callback_invoke(tx, NULL);
			dma_descriptor_unmap(tx);
			tx->callback = NULL;
			tx->callback_result = NULL;
		}

		dma_run_dependencies(tx);

		spin_lock_irqsave(&sba->reqs_lock, flags);

		/* Free all requests chained to first request */
		list_for_each_entry(nreq, &first->next, next)
			_sba_free_request(sba, nreq);
		INIT_LIST_HEAD(&first->next);

		/* Free the first request */
		_sba_free_request(sba, first);

		/* Process pending requests */
		_sba_process_pending_requests(sba);

		spin_unlock_irqrestore(&sba->reqs_lock, flags);
	}
}

static void sba_write_stats_in_seqfile(struct sba_device *sba,
				       struct seq_file *file)
{
	unsigned long flags;
	struct sba_request *req;
	u32 free_count = 0, alloced_count = 0;
	u32 pending_count = 0, active_count = 0, aborted_count = 0;

	spin_lock_irqsave(&sba->reqs_lock, flags);

	list_for_each_entry(req, &sba->reqs_free_list, node)
		if (async_tx_test_ack(&req->tx))
			free_count++;

	list_for_each_entry(req, &sba->reqs_alloc_list, node)
		alloced_count++;

	list_for_each_entry(req, &sba->reqs_pending_list, node)
		pending_count++;

	list_for_each_entry(req, &sba->reqs_active_list, node)
		active_count++;

	list_for_each_entry(req, &sba->reqs_aborted_list, node)
		aborted_count++;

	spin_unlock_irqrestore(&sba->reqs_lock, flags);

	seq_printf(file, "maximum requests   = %d\n", sba->max_req);
	seq_printf(file, "free requests      = %d\n", free_count);
	seq_printf(file, "alloced requests   = %d\n", alloced_count);
	seq_printf(file, "pending requests   = %d\n", pending_count);
	seq_printf(file, "active requests    = %d\n", active_count);
	seq_printf(file, "aborted requests   = %d\n", aborted_count);
}

/* ====== DMAENGINE callbacks ===== */

static void sba_free_chan_resources(struct dma_chan *dchan)
{
	/*
	 * Channel resources are pre-alloced so we just free-up
	 * whatever we can so that we can re-use pre-alloced
	 * channel resources next time.
	 */
	sba_cleanup_nonpending_requests(to_sba_device(dchan));
}

static int sba_device_terminate_all(struct dma_chan *dchan)
{
	/* Cleanup all pending requests */
	sba_cleanup_pending_requests(to_sba_device(dchan));

	return 0;
}

static void sba_issue_pending(struct dma_chan *dchan)
{
	unsigned long flags;
	struct sba_device *sba = to_sba_device(dchan);

	/* Process pending requests */
	spin_lock_irqsave(&sba->reqs_lock, flags);
	_sba_process_pending_requests(sba);
	spin_unlock_irqrestore(&sba->reqs_lock, flags);
}

static dma_cookie_t sba_tx_submit(struct dma_async_tx_descriptor *tx)
{
	unsigned long flags;
	dma_cookie_t cookie;
	struct sba_device *sba;
	struct sba_request *req, *nreq;

	if (unlikely(!tx))
		return -EINVAL;

	sba = to_sba_device(tx->chan);
	req = to_sba_request(tx);

	/* Assign cookie and mark all chained requests pending */
	spin_lock_irqsave(&sba->reqs_lock, flags);
	cookie = dma_cookie_assign(tx);
	_sba_pending_request(sba, req);
	list_for_each_entry(nreq, &req->next, next)
		_sba_pending_request(sba, nreq);
	spin_unlock_irqrestore(&sba->reqs_lock, flags);

	return cookie;
}

static enum dma_status sba_tx_status(struct dma_chan *dchan,
				     dma_cookie_t cookie,
				     struct dma_tx_state *txstate)
{
	enum dma_status ret;
	struct sba_device *sba = to_sba_device(dchan);

	ret = dma_cookie_status(dchan, cookie, txstate);
	if (ret == DMA_COMPLETE)
		return ret;

	sba_peek_mchans(sba);

	return dma_cookie_status(dchan, cookie, txstate);
}

static void sba_fillup_interrupt_msg(struct sba_request *req,
				     struct brcm_sba_command *cmds,
				     struct brcm_message *msg)
{
	u64 cmd;
	u32 c_mdata;
	dma_addr_t resp_dma = req->tx.phys;
	struct brcm_sba_command *cmdsp = cmds;

	/* Type-B command to load dummy data into buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	c_mdata = sba_cmd_load_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
	cmdsp->data = resp_dma;
	cmdsp->data_len = req->sba->hw_resp_size;
	cmdsp++;

	/* Type-A command to write buf0 to dummy location */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, req->sba->hw_resp_size,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, 0x1,
			  SBA_RESP_SHIFT, SBA_RESP_MASK);
	c_mdata = sba_cmd_write_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	if (req->sba->hw_resp_size) {
		cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
		cmdsp->resp = resp_dma;
		cmdsp->resp_len = req->sba->hw_resp_size;
	}
	cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
	cmdsp->data = resp_dma;
	cmdsp->data_len = req->sba->hw_resp_size;
	cmdsp++;

	/* Fillup brcm_message */
	msg->type = BRCM_MESSAGE_SBA;
	msg->sba.cmds = cmds;
	msg->sba.cmds_count = cmdsp - cmds;
	msg->ctx = req;
	msg->error = 0;
}

static struct dma_async_tx_descriptor *
sba_prep_dma_interrupt(struct dma_chan *dchan, unsigned long flags)
{
	struct sba_request *req = NULL;
	struct sba_device *sba = to_sba_device(dchan);

	/* Alloc new request */
	req = sba_alloc_request(sba);
	if (!req)
		return NULL;

	/*
	 * Force fence so that no requests are submitted
	 * until DMA callback for this request is invoked.
	 */
	req->flags |= SBA_REQUEST_FENCE;

	/* Fillup request message */
	sba_fillup_interrupt_msg(req, req->cmds, &req->msg);

	/* Init async_tx descriptor */
	req->tx.flags = flags;
	req->tx.cookie = -EBUSY;

	return &req->tx;
}

static void sba_fillup_memcpy_msg(struct sba_request *req,
				  struct brcm_sba_command *cmds,
				  struct brcm_message *msg,
				  dma_addr_t msg_offset, size_t msg_len,
				  dma_addr_t dst, dma_addr_t src)
{
	u64 cmd;
	u32 c_mdata;
	dma_addr_t resp_dma = req->tx.phys;
	struct brcm_sba_command *cmdsp = cmds;

	/* Type-B command to load data into buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	c_mdata = sba_cmd_load_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
	cmdsp->data = src + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

	/* Type-A command to write buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, 0x1,
			  SBA_RESP_SHIFT, SBA_RESP_MASK);
	c_mdata = sba_cmd_write_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	if (req->sba->hw_resp_size) {
		cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
		cmdsp->resp = resp_dma;
		cmdsp->resp_len = req->sba->hw_resp_size;
	}
	cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
	cmdsp->data = dst + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

	/* Fillup brcm_message */
	msg->type = BRCM_MESSAGE_SBA;
	msg->sba.cmds = cmds;
	msg->sba.cmds_count = cmdsp - cmds;
	msg->ctx = req;
	msg->error = 0;
}

static struct sba_request *
sba_prep_dma_memcpy_req(struct sba_device *sba,
			dma_addr_t off, dma_addr_t dst, dma_addr_t src,
			size_t len, unsigned long flags)
{
	struct sba_request *req = NULL;

	/* Alloc new request */
	req = sba_alloc_request(sba);
	if (!req)
		return NULL;
	if (flags & DMA_PREP_FENCE)
		req->flags |= SBA_REQUEST_FENCE;

	/* Fillup request message */
	sba_fillup_memcpy_msg(req, req->cmds, &req->msg,
			      off, len, dst, src);

	/* Init async_tx descriptor */
	req->tx.flags = flags;
	req->tx.cookie = -EBUSY;

	return req;
}

static struct dma_async_tx_descriptor *
sba_prep_dma_memcpy(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t src,
		    size_t len, unsigned long flags)
{
	size_t req_len;
	dma_addr_t off = 0;
	struct sba_device *sba = to_sba_device(dchan);
	struct sba_request *first = NULL, *req;

	/* Create chained requests where each request is upto hw_buf_size */
	while (len) {
		req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size;

		req = sba_prep_dma_memcpy_req(sba, off, dst, src,
					      req_len, flags);
		if (!req) {
			if (first)
				sba_free_chained_requests(first);
			return NULL;
		}

		if (first)
			sba_chain_request(first, req);
		else
			first = req;

		off += req_len;
		len -= req_len;
	}

	return (first) ? &first->tx : NULL;
}

static void sba_fillup_xor_msg(struct sba_request *req,
				struct brcm_sba_command *cmds,
				struct brcm_message *msg,
				dma_addr_t msg_offset, size_t msg_len,
				dma_addr_t dst, dma_addr_t *src, u32 src_cnt)
{
	u64 cmd;
	u32 c_mdata;
	unsigned int i;
	dma_addr_t resp_dma = req->tx.phys;
	struct brcm_sba_command *cmdsp = cmds;

	/* Type-B command to load data into buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	c_mdata = sba_cmd_load_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
	cmdsp->data = src[0] + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

	/* Type-B commands to xor data with buf0 and put it back in buf0 */
	for (i = 1; i < src_cnt; i++) {
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_xor_c_mdata(0, 0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_XOR,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = src[i] + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Type-A command to write buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, 0x1,
			  SBA_RESP_SHIFT, SBA_RESP_MASK);
	c_mdata = sba_cmd_write_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	if (req->sba->hw_resp_size) {
		cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
		cmdsp->resp = resp_dma;
		cmdsp->resp_len = req->sba->hw_resp_size;
	}
	cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
	cmdsp->data = dst + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

	/* Fillup brcm_message */
	msg->type = BRCM_MESSAGE_SBA;
	msg->sba.cmds = cmds;
	msg->sba.cmds_count = cmdsp - cmds;
	msg->ctx = req;
	msg->error = 0;
}

static struct sba_request *
sba_prep_dma_xor_req(struct sba_device *sba,
		     dma_addr_t off, dma_addr_t dst, dma_addr_t *src,
		     u32 src_cnt, size_t len, unsigned long flags)
{
	struct sba_request *req = NULL;

	/* Alloc new request */
	req = sba_alloc_request(sba);
	if (!req)
		return NULL;
	if (flags & DMA_PREP_FENCE)
		req->flags |= SBA_REQUEST_FENCE;

	/* Fillup request message */
	sba_fillup_xor_msg(req, req->cmds, &req->msg,
			   off, len, dst, src, src_cnt);

	/* Init async_tx descriptor */
	req->tx.flags = flags;
	req->tx.cookie = -EBUSY;

	return req;
}

static struct dma_async_tx_descriptor *
sba_prep_dma_xor(struct dma_chan *dchan, dma_addr_t dst, dma_addr_t *src,
		 u32 src_cnt, size_t len, unsigned long flags)
{
	size_t req_len;
	dma_addr_t off = 0;
	struct sba_device *sba = to_sba_device(dchan);
	struct sba_request *first = NULL, *req;

	/* Sanity checks */
	if (unlikely(src_cnt > sba->max_xor_srcs))
		return NULL;

	/* Create chained requests where each request is upto hw_buf_size */
	while (len) {
		req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size;

		req = sba_prep_dma_xor_req(sba, off, dst, src, src_cnt,
					   req_len, flags);
		if (!req) {
			if (first)
				sba_free_chained_requests(first);
			return NULL;
		}

		if (first)
			sba_chain_request(first, req);
		else
			first = req;

		off += req_len;
		len -= req_len;
	}

	return (first) ? &first->tx : NULL;
}

static void sba_fillup_pq_msg(struct sba_request *req,
				bool pq_continue,
				struct brcm_sba_command *cmds,
				struct brcm_message *msg,
				dma_addr_t msg_offset, size_t msg_len,
				dma_addr_t *dst_p, dma_addr_t *dst_q,
				const u8 *scf, dma_addr_t *src, u32 src_cnt)
{
	u64 cmd;
	u32 c_mdata;
	unsigned int i;
	dma_addr_t resp_dma = req->tx.phys;
	struct brcm_sba_command *cmdsp = cmds;

	if (pq_continue) {
		/* Type-B command to load old P into buf0 */
		if (dst_p) {
			cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				SBA_TYPE_SHIFT, SBA_TYPE_MASK);
			cmd = sba_cmd_enc(cmd, msg_len,
				SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
			c_mdata = sba_cmd_load_c_mdata(0);
			cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
			cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
				SBA_CMD_SHIFT, SBA_CMD_MASK);
			cmdsp->cmd = cmd;
			*cmdsp->cmd_dma = cpu_to_le64(cmd);
			cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
			cmdsp->data = *dst_p + msg_offset;
			cmdsp->data_len = msg_len;
			cmdsp++;
		}

		/* Type-B command to load old Q into buf1 */
		if (dst_q) {
			cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				SBA_TYPE_SHIFT, SBA_TYPE_MASK);
			cmd = sba_cmd_enc(cmd, msg_len,
				SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
			c_mdata = sba_cmd_load_c_mdata(1);
			cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
			cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
				SBA_CMD_SHIFT, SBA_CMD_MASK);
			cmdsp->cmd = cmd;
			*cmdsp->cmd_dma = cpu_to_le64(cmd);
			cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
			cmdsp->data = *dst_q + msg_offset;
			cmdsp->data_len = msg_len;
			cmdsp++;
		}
	} else {
		/* Type-A command to zero all buffers */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
		cmdsp++;
	}

	/* Type-B commands for generate P onto buf0 and Q onto buf1 */
	for (i = 0; i < src_cnt; i++) {
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_pq_c_mdata(raid6_gflog[scf[i]], 1, 0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata),
				  SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS_XOR,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = src[i] + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Type-A command to write buf0 */
	if (dst_p) {
		cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		cmd = sba_cmd_enc(cmd, 0x1,
				  SBA_RESP_SHIFT, SBA_RESP_MASK);
		c_mdata = sba_cmd_write_c_mdata(0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
		if (req->sba->hw_resp_size) {
			cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
			cmdsp->resp = resp_dma;
			cmdsp->resp_len = req->sba->hw_resp_size;
		}
		cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
		cmdsp->data = *dst_p + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Type-A command to write buf1 */
	if (dst_q) {
		cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		cmd = sba_cmd_enc(cmd, 0x1,
				  SBA_RESP_SHIFT, SBA_RESP_MASK);
		c_mdata = sba_cmd_write_c_mdata(1);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
		if (req->sba->hw_resp_size) {
			cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
			cmdsp->resp = resp_dma;
			cmdsp->resp_len = req->sba->hw_resp_size;
		}
		cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
		cmdsp->data = *dst_q + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Fillup brcm_message */
	msg->type = BRCM_MESSAGE_SBA;
	msg->sba.cmds = cmds;
	msg->sba.cmds_count = cmdsp - cmds;
	msg->ctx = req;
	msg->error = 0;
}

static struct sba_request *
sba_prep_dma_pq_req(struct sba_device *sba, dma_addr_t off,
		    dma_addr_t *dst_p, dma_addr_t *dst_q, dma_addr_t *src,
		    u32 src_cnt, const u8 *scf, size_t len, unsigned long flags)
{
	struct sba_request *req = NULL;

	/* Alloc new request */
	req = sba_alloc_request(sba);
	if (!req)
		return NULL;
	if (flags & DMA_PREP_FENCE)
		req->flags |= SBA_REQUEST_FENCE;

	/* Fillup request messages */
	sba_fillup_pq_msg(req, dmaf_continue(flags),
			  req->cmds, &req->msg,
			  off, len, dst_p, dst_q, scf, src, src_cnt);

	/* Init async_tx descriptor */
	req->tx.flags = flags;
	req->tx.cookie = -EBUSY;

	return req;
}

static void sba_fillup_pq_single_msg(struct sba_request *req,
				bool pq_continue,
				struct brcm_sba_command *cmds,
				struct brcm_message *msg,
				dma_addr_t msg_offset, size_t msg_len,
				dma_addr_t *dst_p, dma_addr_t *dst_q,
				dma_addr_t src, u8 scf)
{
	u64 cmd;
	u32 c_mdata;
	u8 pos, dpos = raid6_gflog[scf];
	dma_addr_t resp_dma = req->tx.phys;
	struct brcm_sba_command *cmdsp = cmds;

	if (!dst_p)
		goto skip_p;

	if (pq_continue) {
		/* Type-B command to load old P into buf0 */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_load_c_mdata(0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = *dst_p + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;

		/*
		 * Type-B commands to xor data with buf0 and put it
		 * back in buf0
		 */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_xor_c_mdata(0, 0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_XOR,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = src + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	} else {
		/* Type-B command to load old P into buf0 */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_load_c_mdata(0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_LOAD_BUFFER,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = src + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Type-A command to write buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, 0x1,
			  SBA_RESP_SHIFT, SBA_RESP_MASK);
	c_mdata = sba_cmd_write_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	if (req->sba->hw_resp_size) {
		cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
		cmdsp->resp = resp_dma;
		cmdsp->resp_len = req->sba->hw_resp_size;
	}
	cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
	cmdsp->data = *dst_p + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

skip_p:
	if (!dst_q)
		goto skip_q;

	/* Type-A command to zero all buffers */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_ZERO_ALL_BUFFERS,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	cmdsp++;

	if (dpos == 255)
		goto skip_q_computation;
	pos = (dpos < req->sba->max_pq_coefs) ?
		dpos : (req->sba->max_pq_coefs - 1);

	/*
	 * Type-B command to generate initial Q from data
	 * and store output into buf0
	 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	c_mdata = sba_cmd_pq_c_mdata(pos, 0, 0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata),
			  SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
	cmdsp->data = src + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

	dpos -= pos;

	/* Multiple Type-A command to generate final Q */
	while (dpos) {
		pos = (dpos < req->sba->max_pq_coefs) ?
			dpos : (req->sba->max_pq_coefs - 1);

		/*
		 * Type-A command to generate Q with buf0 and
		 * buf1 store result in buf0
		 */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_pq_c_mdata(pos, 0, 1);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_MS(c_mdata),
				  SBA_C_MDATA_MS_SHIFT, SBA_C_MDATA_MS_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_GALOIS,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
		cmdsp++;

		dpos -= pos;
	}

skip_q_computation:
	if (pq_continue) {
		/*
		 * Type-B command to XOR previous output with
		 * buf0 and write it into buf0
		 */
		cmd = sba_cmd_enc(0x0, SBA_TYPE_B,
				  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
		cmd = sba_cmd_enc(cmd, msg_len,
				  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
		c_mdata = sba_cmd_xor_c_mdata(0, 0);
		cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
				  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
		cmd = sba_cmd_enc(cmd, SBA_CMD_XOR,
				  SBA_CMD_SHIFT, SBA_CMD_MASK);
		cmdsp->cmd = cmd;
		*cmdsp->cmd_dma = cpu_to_le64(cmd);
		cmdsp->flags = BRCM_SBA_CMD_TYPE_B;
		cmdsp->data = *dst_q + msg_offset;
		cmdsp->data_len = msg_len;
		cmdsp++;
	}

	/* Type-A command to write buf0 */
	cmd = sba_cmd_enc(0x0, SBA_TYPE_A,
			  SBA_TYPE_SHIFT, SBA_TYPE_MASK);
	cmd = sba_cmd_enc(cmd, msg_len,
			  SBA_USER_DEF_SHIFT, SBA_USER_DEF_MASK);
	cmd = sba_cmd_enc(cmd, 0x1,
			  SBA_RESP_SHIFT, SBA_RESP_MASK);
	c_mdata = sba_cmd_write_c_mdata(0);
	cmd = sba_cmd_enc(cmd, SBA_C_MDATA_LS(c_mdata),
			  SBA_C_MDATA_SHIFT, SBA_C_MDATA_MASK);
	cmd = sba_cmd_enc(cmd, SBA_CMD_WRITE_BUFFER,
			  SBA_CMD_SHIFT, SBA_CMD_MASK);
	cmdsp->cmd = cmd;
	*cmdsp->cmd_dma = cpu_to_le64(cmd);
	cmdsp->flags = BRCM_SBA_CMD_TYPE_A;
	if (req->sba->hw_resp_size) {
		cmdsp->flags |= BRCM_SBA_CMD_HAS_RESP;
		cmdsp->resp = resp_dma;
		cmdsp->resp_len = req->sba->hw_resp_size;
	}
	cmdsp->flags |= BRCM_SBA_CMD_HAS_OUTPUT;
	cmdsp->data = *dst_q + msg_offset;
	cmdsp->data_len = msg_len;
	cmdsp++;

skip_q:
	/* Fillup brcm_message */
	msg->type = BRCM_MESSAGE_SBA;
	msg->sba.cmds = cmds;
	msg->sba.cmds_count = cmdsp - cmds;
	msg->ctx = req;
	msg->error = 0;
}

static struct sba_request *
sba_prep_dma_pq_single_req(struct sba_device *sba, dma_addr_t off,
			   dma_addr_t *dst_p, dma_addr_t *dst_q,
			   dma_addr_t src, u8 scf, size_t len,
			   unsigned long flags)
{
	struct sba_request *req = NULL;

	/* Alloc new request */
	req = sba_alloc_request(sba);
	if (!req)
		return NULL;
	if (flags & DMA_PREP_FENCE)
		req->flags |= SBA_REQUEST_FENCE;

	/* Fillup request messages */
	sba_fillup_pq_single_msg(req,  dmaf_continue(flags),
				 req->cmds, &req->msg, off, len,
				 dst_p, dst_q, src, scf);

	/* Init async_tx descriptor */
	req->tx.flags = flags;
	req->tx.cookie = -EBUSY;

	return req;
}

static struct dma_async_tx_descriptor *
sba_prep_dma_pq(struct dma_chan *dchan, dma_addr_t *dst, dma_addr_t *src,
		u32 src_cnt, const u8 *scf, size_t len, unsigned long flags)
{
	u32 i, dst_q_index;
	size_t req_len;
	bool slow = false;
	dma_addr_t off = 0;
	dma_addr_t *dst_p = NULL, *dst_q = NULL;
	struct sba_device *sba = to_sba_device(dchan);
	struct sba_request *first = NULL, *req;

	/* Sanity checks */
	if (unlikely(src_cnt > sba->max_pq_srcs))
		return NULL;
	for (i = 0; i < src_cnt; i++)
		if (sba->max_pq_coefs <= raid6_gflog[scf[i]])
			slow = true;

	/* Figure-out P and Q destination addresses */
	if (!(flags & DMA_PREP_PQ_DISABLE_P))
		dst_p = &dst[0];
	if (!(flags & DMA_PREP_PQ_DISABLE_Q))
		dst_q = &dst[1];

	/* Create chained requests where each request is upto hw_buf_size */
	while (len) {
		req_len = (len < sba->hw_buf_size) ? len : sba->hw_buf_size;

		if (slow) {
			dst_q_index = src_cnt;

			if (dst_q) {
				for (i = 0; i < src_cnt; i++) {
					if (*dst_q == src[i]) {
						dst_q_index = i;
						break;
					}
				}
			}

			if (dst_q_index < src_cnt) {
				i = dst_q_index;
				req = sba_prep_dma_pq_single_req(sba,
					off, dst_p, dst_q, src[i], scf[i],
					req_len, flags | DMA_PREP_FENCE);
				if (!req)
					goto fail;

				if (first)
					sba_chain_request(first, req);
				else
					first = req;

				flags |= DMA_PREP_CONTINUE;
			}

			for (i = 0; i < src_cnt; i++) {
				if (dst_q_index == i)
					continue;

				req = sba_prep_dma_pq_single_req(sba,
					off, dst_p, dst_q, src[i], scf[i],
					req_len, flags | DMA_PREP_FENCE);
				if (!req)
					goto fail;

				if (first)
					sba_chain_request(first, req);
				else
					first = req;

				flags |= DMA_PREP_CONTINUE;
			}
		} else {
			req = sba_prep_dma_pq_req(sba, off,
						  dst_p, dst_q, src, src_cnt,
						  scf, req_len, flags);
			if (!req)
				goto fail;

			if (first)
				sba_chain_request(first, req);
			else
				first = req;
		}

		off += req_len;
		len -= req_len;
	}

	return (first) ? &first->tx : NULL;

fail:
	if (first)
		sba_free_chained_requests(first);
	return NULL;
}

/* ====== Mailbox callbacks ===== */

static void sba_receive_message(struct mbox_client *cl, void *msg)
{
	struct brcm_message *m = msg;
	struct sba_request *req = m->ctx;
	struct sba_device *sba = req->sba;

	/* Error count if message has error */
	if (m->error < 0)
		dev_err(sba->dev, "%s got message with error %d",
			dma_chan_name(&sba->dma_chan), m->error);

	/* Process received request */
	sba_process_received_request(sba, req);
}

/* ====== Debugfs callbacks ====== */

static int sba_debugfs_stats_show(struct seq_file *file, void *offset)
{
	struct platform_device *pdev = to_platform_device(file->private);
	struct sba_device *sba = platform_get_drvdata(pdev);

	/* Write stats in file */
	sba_write_stats_in_seqfile(sba, file);

	return 0;
}

/* ====== Platform driver routines ===== */

static int sba_prealloc_channel_resources(struct sba_device *sba)
{
	int i, j, ret = 0;
	struct sba_request *req = NULL;

	sba->resp_base = dma_alloc_coherent(sba->mbox_dev,
					    sba->max_resp_pool_size,
					    &sba->resp_dma_base, GFP_KERNEL);
	if (!sba->resp_base)
		return -ENOMEM;

	sba->cmds_base = dma_alloc_coherent(sba->mbox_dev,
					    sba->max_cmds_pool_size,
					    &sba->cmds_dma_base, GFP_KERNEL);
	if (!sba->cmds_base) {
		ret = -ENOMEM;
		goto fail_free_resp_pool;
	}

	spin_lock_init(&sba->reqs_lock);
	sba->reqs_fence = false;
	INIT_LIST_HEAD(&sba->reqs_alloc_list);
	INIT_LIST_HEAD(&sba->reqs_pending_list);
	INIT_LIST_HEAD(&sba->reqs_active_list);
	INIT_LIST_HEAD(&sba->reqs_aborted_list);
	INIT_LIST_HEAD(&sba->reqs_free_list);

	for (i = 0; i < sba->max_req; i++) {
		req = devm_kzalloc(sba->dev,
				sizeof(*req) +
				sba->max_cmd_per_req * sizeof(req->cmds[0]),
				GFP_KERNEL);
		if (!req) {
			ret = -ENOMEM;
			goto fail_free_cmds_pool;
		}
		INIT_LIST_HEAD(&req->node);
		req->sba = sba;
		req->flags = SBA_REQUEST_STATE_FREE;
		INIT_LIST_HEAD(&req->next);
		atomic_set(&req->next_pending_count, 0);
		for (j = 0; j < sba->max_cmd_per_req; j++) {
			req->cmds[j].cmd = 0;
			req->cmds[j].cmd_dma = sba->cmds_base +
				(i * sba->max_cmd_per_req + j) * sizeof(u64);
			req->cmds[j].cmd_dma_addr = sba->cmds_dma_base +
				(i * sba->max_cmd_per_req + j) * sizeof(u64);
			req->cmds[j].flags = 0;
		}
		memset(&req->msg, 0, sizeof(req->msg));
		dma_async_tx_descriptor_init(&req->tx, &sba->dma_chan);
		async_tx_ack(&req->tx);
		req->tx.tx_submit = sba_tx_submit;
		req->tx.phys = sba->resp_dma_base + i * sba->hw_resp_size;
		list_add_tail(&req->node, &sba->reqs_free_list);
	}

	return 0;

fail_free_cmds_pool:
	dma_free_coherent(sba->mbox_dev,
			  sba->max_cmds_pool_size,
			  sba->cmds_base, sba->cmds_dma_base);
fail_free_resp_pool:
	dma_free_coherent(sba->mbox_dev,
			  sba->max_resp_pool_size,
			  sba->resp_base, sba->resp_dma_base);
	return ret;
}

static void sba_freeup_channel_resources(struct sba_device *sba)
{
	dmaengine_terminate_all(&sba->dma_chan);
	dma_free_coherent(sba->mbox_dev, sba->max_cmds_pool_size,
			  sba->cmds_base, sba->cmds_dma_base);
	dma_free_coherent(sba->mbox_dev, sba->max_resp_pool_size,
			  sba->resp_base, sba->resp_dma_base);
	sba->resp_base = NULL;
	sba->resp_dma_base = 0;
}

static int sba_async_register(struct sba_device *sba)
{
	int ret;
	struct dma_device *dma_dev = &sba->dma_dev;

	/* Initialize DMA channel cookie */
	sba->dma_chan.device = dma_dev;
	dma_cookie_init(&sba->dma_chan);

	/* Initialize DMA device capability mask */
	dma_cap_zero(dma_dev->cap_mask);
	dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask);
	dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
	dma_cap_set(DMA_XOR, dma_dev->cap_mask);
	dma_cap_set(DMA_PQ, dma_dev->cap_mask);

	/*
	 * Set mailbox channel device as the base device of
	 * our dma_device because the actual memory accesses
	 * will be done by mailbox controller
	 */
	dma_dev->dev = sba->mbox_dev;

	/* Set base prep routines */
	dma_dev->device_free_chan_resources = sba_free_chan_resources;
	dma_dev->device_terminate_all = sba_device_terminate_all;
	dma_dev->device_issue_pending = sba_issue_pending;
	dma_dev->device_tx_status = sba_tx_status;

	/* Set interrupt routine */
	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
		dma_dev->device_prep_dma_interrupt = sba_prep_dma_interrupt;

	/* Set memcpy routine */
	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask))
		dma_dev->device_prep_dma_memcpy = sba_prep_dma_memcpy;

	/* Set xor routine and capability */
	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
		dma_dev->device_prep_dma_xor = sba_prep_dma_xor;
		dma_dev->max_xor = sba->max_xor_srcs;
	}

	/* Set pq routine and capability */
	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
		dma_dev->device_prep_dma_pq = sba_prep_dma_pq;
		dma_set_maxpq(dma_dev, sba->max_pq_srcs, 0);
	}

	/* Initialize DMA device channel list */
	INIT_LIST_HEAD(&dma_dev->channels);
	list_add_tail(&sba->dma_chan.device_node, &dma_dev->channels);

	/* Register with Linux async DMA framework*/
	ret = dma_async_device_register(dma_dev);
	if (ret) {
		dev_err(sba->dev, "async device register error %d", ret);
		return ret;
	}

	dev_info(sba->dev, "%s capabilities: %s%s%s%s\n",
	dma_chan_name(&sba->dma_chan),
	dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "interrupt " : "",
	dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "memcpy " : "",
	dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
	dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "");

	return 0;
}

static int sba_probe(struct platform_device *pdev)
{
	int i, ret = 0, mchans_count;
	struct sba_device *sba;
	struct platform_device *mbox_pdev;
	struct of_phandle_args args;

	/* Allocate main SBA struct */
	sba = devm_kzalloc(&pdev->dev, sizeof(*sba), GFP_KERNEL);
	if (!sba)
		return -ENOMEM;

	sba->dev = &pdev->dev;
	platform_set_drvdata(pdev, sba);

	/* Number of channels equals number of mailbox channels */
	ret = of_count_phandle_with_args(pdev->dev.of_node,
					 "mboxes", "#mbox-cells");
	if (ret <= 0)
		return -ENODEV;
	mchans_count = ret;

	/* Determine SBA version from DT compatible string */
	if (of_device_is_compatible(sba->dev->of_node, "brcm,iproc-sba"))
		sba->ver = SBA_VER_1;
	else if (of_device_is_compatible(sba->dev->of_node,
					 "brcm,iproc-sba-v2"))
		sba->ver = SBA_VER_2;
	else
		return -ENODEV;

	/* Derived Configuration parameters */
	switch (sba->ver) {
	case SBA_VER_1:
		sba->hw_buf_size = 4096;
		sba->hw_resp_size = 8;
		sba->max_pq_coefs = 6;
		sba->max_pq_srcs = 6;
		break;
	case SBA_VER_2:
		sba->hw_buf_size = 4096;
		sba->hw_resp_size = 8;
		sba->max_pq_coefs = 30;
		/*
		 * We can support max_pq_srcs == max_pq_coefs because
		 * we are limited by number of SBA commands that we can
		 * fit in one message for underlying ring manager HW.
		 */
		sba->max_pq_srcs = 12;
		break;
	default:
		return -EINVAL;
	}
	sba->max_req = SBA_MAX_REQ_PER_MBOX_CHANNEL * mchans_count;
	sba->max_cmd_per_req = sba->max_pq_srcs + 3;
	sba->max_xor_srcs = sba->max_cmd_per_req - 1;
	sba->max_resp_pool_size = sba->max_req * sba->hw_resp_size;
	sba->max_cmds_pool_size = sba->max_req *
				  sba->max_cmd_per_req * sizeof(u64);

	/* Setup mailbox client */
	sba->client.dev			= &pdev->dev;
	sba->client.rx_callback		= sba_receive_message;
	sba->client.tx_block		= false;
	sba->client.knows_txdone	= true;
	sba->client.tx_tout		= 0;

	/* Allocate mailbox channel array */
	sba->mchans = devm_kcalloc(&pdev->dev, mchans_count,
				   sizeof(*sba->mchans), GFP_KERNEL);
	if (!sba->mchans)
		return -ENOMEM;

	/* Request mailbox channels */
	sba->mchans_count = 0;
	for (i = 0; i < mchans_count; i++) {
		sba->mchans[i] = mbox_request_channel(&sba->client, i);
		if (IS_ERR(sba->mchans[i])) {
			ret = PTR_ERR(sba->mchans[i]);
			goto fail_free_mchans;
		}
		sba->mchans_count++;
	}
	atomic_set(&sba->mchans_current, 0);

	/* Find-out underlying mailbox device */
	ret = of_parse_phandle_with_args(pdev->dev.of_node,
					 "mboxes", "#mbox-cells", 0, &args);
	if (ret)
		goto fail_free_mchans;
	mbox_pdev = of_find_device_by_node(args.np);
	of_node_put(args.np);
	if (!mbox_pdev) {
		ret = -ENODEV;
		goto fail_free_mchans;
	}
	sba->mbox_dev = &mbox_pdev->dev;

	/* All mailbox channels should be of same ring manager device */
	for (i = 1; i < mchans_count; i++) {
		ret = of_parse_phandle_with_args(pdev->dev.of_node,
					 "mboxes", "#mbox-cells", i, &args);
		if (ret)
			goto fail_free_mchans;
		mbox_pdev = of_find_device_by_node(args.np);
		of_node_put(args.np);
		if (sba->mbox_dev != &mbox_pdev->dev) {
			ret = -EINVAL;
			goto fail_free_mchans;
		}
	}

	/* Prealloc channel resource */
	ret = sba_prealloc_channel_resources(sba);
	if (ret)
		goto fail_free_mchans;

	/* Check availability of debugfs */
	if (!debugfs_initialized())
		goto skip_debugfs;

	/* Create debugfs root entry */
	sba->root = debugfs_create_dir(dev_name(sba->dev), NULL);
	if (IS_ERR_OR_NULL(sba->root)) {
		dev_err(sba->dev, "failed to create debugfs root entry\n");
		sba->root = NULL;
		goto skip_debugfs;
	}

	/* Create debugfs stats entry */
	sba->stats = debugfs_create_devm_seqfile(sba->dev, "stats", sba->root,
						 sba_debugfs_stats_show);
	if (IS_ERR_OR_NULL(sba->stats))
		dev_err(sba->dev, "failed to create debugfs stats file\n");
skip_debugfs:

	/* Register DMA device with Linux async framework */
	ret = sba_async_register(sba);
	if (ret)
		goto fail_free_resources;

	/* Print device info */
	dev_info(sba->dev, "%s using SBAv%d and %d mailbox channels",
		 dma_chan_name(&sba->dma_chan), sba->ver+1,
		 sba->mchans_count);

	return 0;

fail_free_resources:
	debugfs_remove_recursive(sba->root);
	sba_freeup_channel_resources(sba);
fail_free_mchans:
	for (i = 0; i < sba->mchans_count; i++)
		mbox_free_channel(sba->mchans[i]);
	return ret;
}

static int sba_remove(struct platform_device *pdev)
{
	int i;
	struct sba_device *sba = platform_get_drvdata(pdev);

	dma_async_device_unregister(&sba->dma_dev);

	debugfs_remove_recursive(sba->root);

	sba_freeup_channel_resources(sba);

	for (i = 0; i < sba->mchans_count; i++)
		mbox_free_channel(sba->mchans[i]);

	return 0;
}

static const struct of_device_id sba_of_match[] = {
	{ .compatible = "brcm,iproc-sba", },
	{ .compatible = "brcm,iproc-sba-v2", },
	{},
};
MODULE_DEVICE_TABLE(of, sba_of_match);

static struct platform_driver sba_driver = {
	.probe = sba_probe,
	.remove = sba_remove,
	.driver = {
		.name = "bcm-sba-raid",
		.of_match_table = sba_of_match,
	},
};
module_platform_driver(sba_driver);

MODULE_DESCRIPTION("Broadcom SBA RAID driver");
MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>");
MODULE_LICENSE("GPL v2");