Free Electrons

Embedded Linux Experts

   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
/*
 * Copyright 2012 Marvell International Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/interrupt.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
#include <linux/dmaengine.h>
#include <linux/platform_device.h>
#include <linux/device.h>
#include <linux/platform_data/mmp_dma.h>
#include <linux/dmapool.h>
#include <linux/of_device.h>
#include <linux/of_dma.h>
#include <linux/of.h>
#include <linux/dma/mmp-pdma.h>

#include "dmaengine.h"

#define DCSR		0x0000
#define DALGN		0x00a0
#define DINT		0x00f0
#define DDADR		0x0200
#define DSADR(n)	(0x0204 + ((n) << 4))
#define DTADR(n)	(0x0208 + ((n) << 4))
#define DCMD		0x020c

#define DCSR_RUN	BIT(31)	/* Run Bit (read / write) */
#define DCSR_NODESC	BIT(30)	/* No-Descriptor Fetch (read / write) */
#define DCSR_STOPIRQEN	BIT(29)	/* Stop Interrupt Enable (read / write) */
#define DCSR_REQPEND	BIT(8)	/* Request Pending (read-only) */
#define DCSR_STOPSTATE	BIT(3)	/* Stop State (read-only) */
#define DCSR_ENDINTR	BIT(2)	/* End Interrupt (read / write) */
#define DCSR_STARTINTR	BIT(1)	/* Start Interrupt (read / write) */
#define DCSR_BUSERR	BIT(0)	/* Bus Error Interrupt (read / write) */

#define DCSR_EORIRQEN	BIT(28)	/* End of Receive Interrupt Enable (R/W) */
#define DCSR_EORJMPEN	BIT(27)	/* Jump to next descriptor on EOR */
#define DCSR_EORSTOPEN	BIT(26)	/* STOP on an EOR */
#define DCSR_SETCMPST	BIT(25)	/* Set Descriptor Compare Status */
#define DCSR_CLRCMPST	BIT(24)	/* Clear Descriptor Compare Status */
#define DCSR_CMPST	BIT(10)	/* The Descriptor Compare Status */
#define DCSR_EORINTR	BIT(9)	/* The end of Receive */

#define DRCMR(n)	((((n) < 64) ? 0x0100 : 0x1100) + (((n) & 0x3f) << 2))
#define DRCMR_MAPVLD	BIT(7)	/* Map Valid (read / write) */
#define DRCMR_CHLNUM	0x1f	/* mask for Channel Number (read / write) */

#define DDADR_DESCADDR	0xfffffff0	/* Address of next descriptor (mask) */
#define DDADR_STOP	BIT(0)	/* Stop (read / write) */

#define DCMD_INCSRCADDR	BIT(31)	/* Source Address Increment Setting. */
#define DCMD_INCTRGADDR	BIT(30)	/* Target Address Increment Setting. */
#define DCMD_FLOWSRC	BIT(29)	/* Flow Control by the source. */
#define DCMD_FLOWTRG	BIT(28)	/* Flow Control by the target. */
#define DCMD_STARTIRQEN	BIT(22)	/* Start Interrupt Enable */
#define DCMD_ENDIRQEN	BIT(21)	/* End Interrupt Enable */
#define DCMD_ENDIAN	BIT(18)	/* Device Endian-ness. */
#define DCMD_BURST8	(1 << 16)	/* 8 byte burst */
#define DCMD_BURST16	(2 << 16)	/* 16 byte burst */
#define DCMD_BURST32	(3 << 16)	/* 32 byte burst */
#define DCMD_WIDTH1	(1 << 14)	/* 1 byte width */
#define DCMD_WIDTH2	(2 << 14)	/* 2 byte width (HalfWord) */
#define DCMD_WIDTH4	(3 << 14)	/* 4 byte width (Word) */
#define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */

#define PDMA_MAX_DESC_BYTES	DCMD_LENGTH

struct mmp_pdma_desc_hw {
	u32 ddadr;	/* Points to the next descriptor + flags */
	u32 dsadr;	/* DSADR value for the current transfer */
	u32 dtadr;	/* DTADR value for the current transfer */
	u32 dcmd;	/* DCMD value for the current transfer */
} __aligned(32);

struct mmp_pdma_desc_sw {
	struct mmp_pdma_desc_hw desc;
	struct list_head node;
	struct list_head tx_list;
	struct dma_async_tx_descriptor async_tx;
};

struct mmp_pdma_phy;

struct mmp_pdma_chan {
	struct device *dev;
	struct dma_chan chan;
	struct dma_async_tx_descriptor desc;
	struct mmp_pdma_phy *phy;
	enum dma_transfer_direction dir;

	struct mmp_pdma_desc_sw *cyclic_first;	/* first desc_sw if channel
						 * is in cyclic mode */

	/* channel's basic info */
	struct tasklet_struct tasklet;
	u32 dcmd;
	u32 drcmr;
	u32 dev_addr;

	/* list for desc */
	spinlock_t desc_lock;		/* Descriptor list lock */
	struct list_head chain_pending;	/* Link descriptors queue for pending */
	struct list_head chain_running;	/* Link descriptors queue for running */
	bool idle;			/* channel statue machine */
	bool byte_align;

	struct dma_pool *desc_pool;	/* Descriptors pool */
};

struct mmp_pdma_phy {
	int idx;
	void __iomem *base;
	struct mmp_pdma_chan *vchan;
};

struct mmp_pdma_device {
	int				dma_channels;
	void __iomem			*base;
	struct device			*dev;
	struct dma_device		device;
	struct mmp_pdma_phy		*phy;
	spinlock_t phy_lock; /* protect alloc/free phy channels */
};

#define tx_to_mmp_pdma_desc(tx)					\
	container_of(tx, struct mmp_pdma_desc_sw, async_tx)
#define to_mmp_pdma_desc(lh)					\
	container_of(lh, struct mmp_pdma_desc_sw, node)
#define to_mmp_pdma_chan(dchan)					\
	container_of(dchan, struct mmp_pdma_chan, chan)
#define to_mmp_pdma_dev(dmadev)					\
	container_of(dmadev, struct mmp_pdma_device, device)

static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
{
	u32 reg = (phy->idx << 4) + DDADR;

	writel(addr, phy->base + reg);
}

static void enable_chan(struct mmp_pdma_phy *phy)
{
	u32 reg, dalgn;

	if (!phy->vchan)
		return;

	reg = DRCMR(phy->vchan->drcmr);
	writel(DRCMR_MAPVLD | phy->idx, phy->base + reg);

	dalgn = readl(phy->base + DALGN);
	if (phy->vchan->byte_align)
		dalgn |= 1 << phy->idx;
	else
		dalgn &= ~(1 << phy->idx);
	writel(dalgn, phy->base + DALGN);

	reg = (phy->idx << 2) + DCSR;
	writel(readl(phy->base + reg) | DCSR_RUN, phy->base + reg);
}

static void disable_chan(struct mmp_pdma_phy *phy)
{
	u32 reg;

	if (!phy)
		return;

	reg = (phy->idx << 2) + DCSR;
	writel(readl(phy->base + reg) & ~DCSR_RUN, phy->base + reg);
}

static int clear_chan_irq(struct mmp_pdma_phy *phy)
{
	u32 dcsr;
	u32 dint = readl(phy->base + DINT);
	u32 reg = (phy->idx << 2) + DCSR;

	if (!(dint & BIT(phy->idx)))
		return -EAGAIN;

	/* clear irq */
	dcsr = readl(phy->base + reg);
	writel(dcsr, phy->base + reg);
	if ((dcsr & DCSR_BUSERR) && (phy->vchan))
		dev_warn(phy->vchan->dev, "DCSR_BUSERR\n");

	return 0;
}

static irqreturn_t mmp_pdma_chan_handler(int irq, void *dev_id)
{
	struct mmp_pdma_phy *phy = dev_id;

	if (clear_chan_irq(phy) != 0)
		return IRQ_NONE;

	tasklet_schedule(&phy->vchan->tasklet);
	return IRQ_HANDLED;
}

static irqreturn_t mmp_pdma_int_handler(int irq, void *dev_id)
{
	struct mmp_pdma_device *pdev = dev_id;
	struct mmp_pdma_phy *phy;
	u32 dint = readl(pdev->base + DINT);
	int i, ret;
	int irq_num = 0;

	while (dint) {
		i = __ffs(dint);
		/* only handle interrupts belonging to pdma driver*/
		if (i >= pdev->dma_channels)
			break;
		dint &= (dint - 1);
		phy = &pdev->phy[i];
		ret = mmp_pdma_chan_handler(irq, phy);
		if (ret == IRQ_HANDLED)
			irq_num++;
	}

	if (irq_num)
		return IRQ_HANDLED;

	return IRQ_NONE;
}

/* lookup free phy channel as descending priority */
static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
{
	int prio, i;
	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(pchan->chan.device);
	struct mmp_pdma_phy *phy, *found = NULL;
	unsigned long flags;

	/*
	 * dma channel priorities
	 * ch 0 - 3,  16 - 19  <--> (0)
	 * ch 4 - 7,  20 - 23  <--> (1)
	 * ch 8 - 11, 24 - 27  <--> (2)
	 * ch 12 - 15, 28 - 31  <--> (3)
	 */

	spin_lock_irqsave(&pdev->phy_lock, flags);
	for (prio = 0; prio <= ((pdev->dma_channels - 1) & 0xf) >> 2; prio++) {
		for (i = 0; i < pdev->dma_channels; i++) {
			if (prio != (i & 0xf) >> 2)
				continue;
			phy = &pdev->phy[i];
			if (!phy->vchan) {
				phy->vchan = pchan;
				found = phy;
				goto out_unlock;
			}
		}
	}

out_unlock:
	spin_unlock_irqrestore(&pdev->phy_lock, flags);
	return found;
}

static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan)
{
	struct mmp_pdma_device *pdev = to_mmp_pdma_dev(pchan->chan.device);
	unsigned long flags;
	u32 reg;

	if (!pchan->phy)
		return;

	/* clear the channel mapping in DRCMR */
	reg = DRCMR(pchan->drcmr);
	writel(0, pchan->phy->base + reg);

	spin_lock_irqsave(&pdev->phy_lock, flags);
	pchan->phy->vchan = NULL;
	pchan->phy = NULL;
	spin_unlock_irqrestore(&pdev->phy_lock, flags);
}

/**
 * start_pending_queue - transfer any pending transactions
 * pending list ==> running list
 */
static void start_pending_queue(struct mmp_pdma_chan *chan)
{
	struct mmp_pdma_desc_sw *desc;

	/* still in running, irq will start the pending list */
	if (!chan->idle) {
		dev_dbg(chan->dev, "DMA controller still busy\n");
		return;
	}

	if (list_empty(&chan->chain_pending)) {
		/* chance to re-fetch phy channel with higher prio */
		mmp_pdma_free_phy(chan);
		dev_dbg(chan->dev, "no pending list\n");
		return;
	}

	if (!chan->phy) {
		chan->phy = lookup_phy(chan);
		if (!chan->phy) {
			dev_dbg(chan->dev, "no free dma channel\n");
			return;
		}
	}

	/*
	 * pending -> running
	 * reintilize pending list
	 */
	desc = list_first_entry(&chan->chain_pending,
				struct mmp_pdma_desc_sw, node);
	list_splice_tail_init(&chan->chain_pending, &chan->chain_running);

	/*
	 * Program the descriptor's address into the DMA controller,
	 * then start the DMA transaction
	 */
	set_desc(chan->phy, desc->async_tx.phys);
	enable_chan(chan->phy);
	chan->idle = false;
}


/* desc->tx_list ==> pending list */
static dma_cookie_t mmp_pdma_tx_submit(struct dma_async_tx_descriptor *tx)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(tx->chan);
	struct mmp_pdma_desc_sw *desc = tx_to_mmp_pdma_desc(tx);
	struct mmp_pdma_desc_sw *child;
	unsigned long flags;
	dma_cookie_t cookie = -EBUSY;

	spin_lock_irqsave(&chan->desc_lock, flags);

	list_for_each_entry(child, &desc->tx_list, node) {
		cookie = dma_cookie_assign(&child->async_tx);
	}

	/* softly link to pending list - desc->tx_list ==> pending list */
	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);

	spin_unlock_irqrestore(&chan->desc_lock, flags);

	return cookie;
}

static struct mmp_pdma_desc_sw *
mmp_pdma_alloc_descriptor(struct mmp_pdma_chan *chan)
{
	struct mmp_pdma_desc_sw *desc;
	dma_addr_t pdesc;

	desc = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
	if (!desc) {
		dev_err(chan->dev, "out of memory for link descriptor\n");
		return NULL;
	}

	INIT_LIST_HEAD(&desc->tx_list);
	dma_async_tx_descriptor_init(&desc->async_tx, &chan->chan);
	/* each desc has submit */
	desc->async_tx.tx_submit = mmp_pdma_tx_submit;
	desc->async_tx.phys = pdesc;

	return desc;
}

/**
 * mmp_pdma_alloc_chan_resources - Allocate resources for DMA channel.
 *
 * This function will create a dma pool for descriptor allocation.
 * Request irq only when channel is requested
 * Return - The number of allocated descriptors.
 */

static int mmp_pdma_alloc_chan_resources(struct dma_chan *dchan)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);

	if (chan->desc_pool)
		return 1;

	chan->desc_pool = dma_pool_create(dev_name(&dchan->dev->device),
					  chan->dev,
					  sizeof(struct mmp_pdma_desc_sw),
					  __alignof__(struct mmp_pdma_desc_sw),
					  0);
	if (!chan->desc_pool) {
		dev_err(chan->dev, "unable to allocate descriptor pool\n");
		return -ENOMEM;
	}

	mmp_pdma_free_phy(chan);
	chan->idle = true;
	chan->dev_addr = 0;
	return 1;
}

static void mmp_pdma_free_desc_list(struct mmp_pdma_chan *chan,
				    struct list_head *list)
{
	struct mmp_pdma_desc_sw *desc, *_desc;

	list_for_each_entry_safe(desc, _desc, list, node) {
		list_del(&desc->node);
		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
	}
}

static void mmp_pdma_free_chan_resources(struct dma_chan *dchan)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	unsigned long flags;

	spin_lock_irqsave(&chan->desc_lock, flags);
	mmp_pdma_free_desc_list(chan, &chan->chain_pending);
	mmp_pdma_free_desc_list(chan, &chan->chain_running);
	spin_unlock_irqrestore(&chan->desc_lock, flags);

	dma_pool_destroy(chan->desc_pool);
	chan->desc_pool = NULL;
	chan->idle = true;
	chan->dev_addr = 0;
	mmp_pdma_free_phy(chan);
	return;
}

static struct dma_async_tx_descriptor *
mmp_pdma_prep_memcpy(struct dma_chan *dchan,
		     dma_addr_t dma_dst, dma_addr_t dma_src,
		     size_t len, unsigned long flags)
{
	struct mmp_pdma_chan *chan;
	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
	size_t copy = 0;

	if (!dchan)
		return NULL;

	if (!len)
		return NULL;

	chan = to_mmp_pdma_chan(dchan);
	chan->byte_align = false;

	if (!chan->dir) {
		chan->dir = DMA_MEM_TO_MEM;
		chan->dcmd = DCMD_INCTRGADDR | DCMD_INCSRCADDR;
		chan->dcmd |= DCMD_BURST32;
	}

	do {
		/* Allocate the link descriptor from DMA pool */
		new = mmp_pdma_alloc_descriptor(chan);
		if (!new) {
			dev_err(chan->dev, "no memory for desc\n");
			goto fail;
		}

		copy = min_t(size_t, len, PDMA_MAX_DESC_BYTES);
		if (dma_src & 0x7 || dma_dst & 0x7)
			chan->byte_align = true;

		new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & copy);
		new->desc.dsadr = dma_src;
		new->desc.dtadr = dma_dst;

		if (!first)
			first = new;
		else
			prev->desc.ddadr = new->async_tx.phys;

		new->async_tx.cookie = 0;
		async_tx_ack(&new->async_tx);

		prev = new;
		len -= copy;

		if (chan->dir == DMA_MEM_TO_DEV) {
			dma_src += copy;
		} else if (chan->dir == DMA_DEV_TO_MEM) {
			dma_dst += copy;
		} else if (chan->dir == DMA_MEM_TO_MEM) {
			dma_src += copy;
			dma_dst += copy;
		}

		/* Insert the link descriptor to the LD ring */
		list_add_tail(&new->node, &first->tx_list);
	} while (len);

	first->async_tx.flags = flags; /* client is in control of this ack */
	first->async_tx.cookie = -EBUSY;

	/* last desc and fire IRQ */
	new->desc.ddadr = DDADR_STOP;
	new->desc.dcmd |= DCMD_ENDIRQEN;

	chan->cyclic_first = NULL;

	return &first->async_tx;

fail:
	if (first)
		mmp_pdma_free_desc_list(chan, &first->tx_list);
	return NULL;
}

static struct dma_async_tx_descriptor *
mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
		       unsigned int sg_len, enum dma_transfer_direction dir,
		       unsigned long flags, void *context)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new = NULL;
	size_t len, avail;
	struct scatterlist *sg;
	dma_addr_t addr;
	int i;

	if ((sgl == NULL) || (sg_len == 0))
		return NULL;

	chan->byte_align = false;

	for_each_sg(sgl, sg, sg_len, i) {
		addr = sg_dma_address(sg);
		avail = sg_dma_len(sgl);

		do {
			len = min_t(size_t, avail, PDMA_MAX_DESC_BYTES);
			if (addr & 0x7)
				chan->byte_align = true;

			/* allocate and populate the descriptor */
			new = mmp_pdma_alloc_descriptor(chan);
			if (!new) {
				dev_err(chan->dev, "no memory for desc\n");
				goto fail;
			}

			new->desc.dcmd = chan->dcmd | (DCMD_LENGTH & len);
			if (dir == DMA_MEM_TO_DEV) {
				new->desc.dsadr = addr;
				new->desc.dtadr = chan->dev_addr;
			} else {
				new->desc.dsadr = chan->dev_addr;
				new->desc.dtadr = addr;
			}

			if (!first)
				first = new;
			else
				prev->desc.ddadr = new->async_tx.phys;

			new->async_tx.cookie = 0;
			async_tx_ack(&new->async_tx);
			prev = new;

			/* Insert the link descriptor to the LD ring */
			list_add_tail(&new->node, &first->tx_list);

			/* update metadata */
			addr += len;
			avail -= len;
		} while (avail);
	}

	first->async_tx.cookie = -EBUSY;
	first->async_tx.flags = flags;

	/* last desc and fire IRQ */
	new->desc.ddadr = DDADR_STOP;
	new->desc.dcmd |= DCMD_ENDIRQEN;

	chan->dir = dir;
	chan->cyclic_first = NULL;

	return &first->async_tx;

fail:
	if (first)
		mmp_pdma_free_desc_list(chan, &first->tx_list);
	return NULL;
}

static struct dma_async_tx_descriptor *
mmp_pdma_prep_dma_cyclic(struct dma_chan *dchan,
			 dma_addr_t buf_addr, size_t len, size_t period_len,
			 enum dma_transfer_direction direction,
			 unsigned long flags)
{
	struct mmp_pdma_chan *chan;
	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
	dma_addr_t dma_src, dma_dst;

	if (!dchan || !len || !period_len)
		return NULL;

	/* the buffer length must be a multiple of period_len */
	if (len % period_len != 0)
		return NULL;

	if (period_len > PDMA_MAX_DESC_BYTES)
		return NULL;

	chan = to_mmp_pdma_chan(dchan);

	switch (direction) {
	case DMA_MEM_TO_DEV:
		dma_src = buf_addr;
		dma_dst = chan->dev_addr;
		break;
	case DMA_DEV_TO_MEM:
		dma_dst = buf_addr;
		dma_src = chan->dev_addr;
		break;
	default:
		dev_err(chan->dev, "Unsupported direction for cyclic DMA\n");
		return NULL;
	}

	chan->dir = direction;

	do {
		/* Allocate the link descriptor from DMA pool */
		new = mmp_pdma_alloc_descriptor(chan);
		if (!new) {
			dev_err(chan->dev, "no memory for desc\n");
			goto fail;
		}

		new->desc.dcmd = (chan->dcmd | DCMD_ENDIRQEN |
				  (DCMD_LENGTH & period_len));
		new->desc.dsadr = dma_src;
		new->desc.dtadr = dma_dst;

		if (!first)
			first = new;
		else
			prev->desc.ddadr = new->async_tx.phys;

		new->async_tx.cookie = 0;
		async_tx_ack(&new->async_tx);

		prev = new;
		len -= period_len;

		if (chan->dir == DMA_MEM_TO_DEV)
			dma_src += period_len;
		else
			dma_dst += period_len;

		/* Insert the link descriptor to the LD ring */
		list_add_tail(&new->node, &first->tx_list);
	} while (len);

	first->async_tx.flags = flags; /* client is in control of this ack */
	first->async_tx.cookie = -EBUSY;

	/* make the cyclic link */
	new->desc.ddadr = first->async_tx.phys;
	chan->cyclic_first = first;

	return &first->async_tx;

fail:
	if (first)
		mmp_pdma_free_desc_list(chan, &first->tx_list);
	return NULL;
}

static int mmp_pdma_config(struct dma_chan *dchan,
			   struct dma_slave_config *cfg)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	u32 maxburst = 0, addr = 0;
	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;

	if (!dchan)
		return -EINVAL;

	if (cfg->direction == DMA_DEV_TO_MEM) {
		chan->dcmd = DCMD_INCTRGADDR | DCMD_FLOWSRC;
		maxburst = cfg->src_maxburst;
		width = cfg->src_addr_width;
		addr = cfg->src_addr;
	} else if (cfg->direction == DMA_MEM_TO_DEV) {
		chan->dcmd = DCMD_INCSRCADDR | DCMD_FLOWTRG;
		maxburst = cfg->dst_maxburst;
		width = cfg->dst_addr_width;
		addr = cfg->dst_addr;
	}

	if (width == DMA_SLAVE_BUSWIDTH_1_BYTE)
		chan->dcmd |= DCMD_WIDTH1;
	else if (width == DMA_SLAVE_BUSWIDTH_2_BYTES)
		chan->dcmd |= DCMD_WIDTH2;
	else if (width == DMA_SLAVE_BUSWIDTH_4_BYTES)
		chan->dcmd |= DCMD_WIDTH4;

	if (maxburst == 8)
		chan->dcmd |= DCMD_BURST8;
	else if (maxburst == 16)
		chan->dcmd |= DCMD_BURST16;
	else if (maxburst == 32)
		chan->dcmd |= DCMD_BURST32;

	chan->dir = cfg->direction;
	chan->dev_addr = addr;
	/* FIXME: drivers should be ported over to use the filter
	 * function. Once that's done, the following two lines can
	 * be removed.
	 */
	if (cfg->slave_id)
		chan->drcmr = cfg->slave_id;

	return 0;
}

static int mmp_pdma_terminate_all(struct dma_chan *dchan)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	unsigned long flags;

	if (!dchan)
		return -EINVAL;

	disable_chan(chan->phy);
	mmp_pdma_free_phy(chan);
	spin_lock_irqsave(&chan->desc_lock, flags);
	mmp_pdma_free_desc_list(chan, &chan->chain_pending);
	mmp_pdma_free_desc_list(chan, &chan->chain_running);
	spin_unlock_irqrestore(&chan->desc_lock, flags);
	chan->idle = true;

	return 0;
}

static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan,
				     dma_cookie_t cookie)
{
	struct mmp_pdma_desc_sw *sw;
	u32 curr, residue = 0;
	bool passed = false;
	bool cyclic = chan->cyclic_first != NULL;

	/*
	 * If the channel does not have a phy pointer anymore, it has already
	 * been completed. Therefore, its residue is 0.
	 */
	if (!chan->phy)
		return 0;

	if (chan->dir == DMA_DEV_TO_MEM)
		curr = readl(chan->phy->base + DTADR(chan->phy->idx));
	else
		curr = readl(chan->phy->base + DSADR(chan->phy->idx));

	list_for_each_entry(sw, &chan->chain_running, node) {
		u32 start, end, len;

		if (chan->dir == DMA_DEV_TO_MEM)
			start = sw->desc.dtadr;
		else
			start = sw->desc.dsadr;

		len = sw->desc.dcmd & DCMD_LENGTH;
		end = start + len;

		/*
		 * 'passed' will be latched once we found the descriptor which
		 * lies inside the boundaries of the curr pointer. All
		 * descriptors that occur in the list _after_ we found that
		 * partially handled descriptor are still to be processed and
		 * are hence added to the residual bytes counter.
		 */

		if (passed) {
			residue += len;
		} else if (curr >= start && curr <= end) {
			residue += end - curr;
			passed = true;
		}

		/*
		 * Descriptors that have the ENDIRQEN bit set mark the end of a
		 * transaction chain, and the cookie assigned with it has been
		 * returned previously from mmp_pdma_tx_submit().
		 *
		 * In case we have multiple transactions in the running chain,
		 * and the cookie does not match the one the user asked us
		 * about, reset the state variables and start over.
		 *
		 * This logic does not apply to cyclic transactions, where all
		 * descriptors have the ENDIRQEN bit set, and for which we
		 * can't have multiple transactions on one channel anyway.
		 */
		if (cyclic || !(sw->desc.dcmd & DCMD_ENDIRQEN))
			continue;

		if (sw->async_tx.cookie == cookie) {
			return residue;
		} else {
			residue = 0;
			passed = false;
		}
	}

	/* We should only get here in case of cyclic transactions */
	return residue;
}

static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
					  dma_cookie_t cookie,
					  struct dma_tx_state *txstate)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	enum dma_status ret;

	ret = dma_cookie_status(dchan, cookie, txstate);
	if (likely(ret != DMA_ERROR))
		dma_set_residue(txstate, mmp_pdma_residue(chan, cookie));

	return ret;
}

/**
 * mmp_pdma_issue_pending - Issue the DMA start command
 * pending list ==> running list
 */
static void mmp_pdma_issue_pending(struct dma_chan *dchan)
{
	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
	unsigned long flags;

	spin_lock_irqsave(&chan->desc_lock, flags);
	start_pending_queue(chan);
	spin_unlock_irqrestore(&chan->desc_lock, flags);
}

/*
 * dma_do_tasklet
 * Do call back
 * Start pending list
 */
static void dma_do_tasklet(unsigned long data)
{
	struct mmp_pdma_chan *chan = (struct mmp_pdma_chan *)data;
	struct mmp_pdma_desc_sw *desc, *_desc;
	LIST_HEAD(chain_cleanup);
	unsigned long flags;
	struct dmaengine_desc_callback cb;

	if (chan->cyclic_first) {
		spin_lock_irqsave(&chan->desc_lock, flags);
		desc = chan->cyclic_first;
		dmaengine_desc_get_callback(&desc->async_tx, &cb);
		spin_unlock_irqrestore(&chan->desc_lock, flags);

		dmaengine_desc_callback_invoke(&cb, NULL);

		return;
	}

	/* submit pending list; callback for each desc; free desc */
	spin_lock_irqsave(&chan->desc_lock, flags);

	list_for_each_entry_safe(desc, _desc, &chan->chain_running, node) {
		/*
		 * move the descriptors to a temporary list so we can drop
		 * the lock during the entire cleanup operation
		 */
		list_move(&desc->node, &chain_cleanup);

		/*
		 * Look for the first list entry which has the ENDIRQEN flag
		 * set. That is the descriptor we got an interrupt for, so
		 * complete that transaction and its cookie.
		 */
		if (desc->desc.dcmd & DCMD_ENDIRQEN) {
			dma_cookie_t cookie = desc->async_tx.cookie;
			dma_cookie_complete(&desc->async_tx);
			dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
			break;
		}
	}

	/*
	 * The hardware is idle and ready for more when the
	 * chain_running list is empty.
	 */
	chan->idle = list_empty(&chan->chain_running);

	/* Start any pending transactions automatically */
	start_pending_queue(chan);
	spin_unlock_irqrestore(&chan->desc_lock, flags);

	/* Run the callback for each descriptor, in order */
	list_for_each_entry_safe(desc, _desc, &chain_cleanup, node) {
		struct dma_async_tx_descriptor *txd = &desc->async_tx;

		/* Remove from the list of transactions */
		list_del(&desc->node);
		/* Run the link descriptor callback function */
		dmaengine_desc_get_callback(txd, &cb);
		dmaengine_desc_callback_invoke(&cb, NULL);

		dma_pool_free(chan->desc_pool, desc, txd->phys);
	}
}

static int mmp_pdma_remove(struct platform_device *op)
{
	struct mmp_pdma_device *pdev = platform_get_drvdata(op);
	struct mmp_pdma_phy *phy;
	int i, irq = 0, irq_num = 0;


	for (i = 0; i < pdev->dma_channels; i++) {
		if (platform_get_irq(op, i) > 0)
			irq_num++;
	}

	if (irq_num != pdev->dma_channels) {
		irq = platform_get_irq(op, 0);
		devm_free_irq(&op->dev, irq, pdev);
	} else {
		for (i = 0; i < pdev->dma_channels; i++) {
			phy = &pdev->phy[i];
			irq = platform_get_irq(op, i);
			devm_free_irq(&op->dev, irq, phy);
		}
	}

	dma_async_device_unregister(&pdev->device);
	return 0;
}

static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq)
{
	struct mmp_pdma_phy *phy  = &pdev->phy[idx];
	struct mmp_pdma_chan *chan;
	int ret;

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

	phy->idx = idx;
	phy->base = pdev->base;

	if (irq) {
		ret = devm_request_irq(pdev->dev, irq, mmp_pdma_chan_handler,
				       IRQF_SHARED, "pdma", phy);
		if (ret) {
			dev_err(pdev->dev, "channel request irq fail!\n");
			return ret;
		}
	}

	spin_lock_init(&chan->desc_lock);
	chan->dev = pdev->dev;
	chan->chan.device = &pdev->device;
	tasklet_init(&chan->tasklet, dma_do_tasklet, (unsigned long)chan);
	INIT_LIST_HEAD(&chan->chain_pending);
	INIT_LIST_HEAD(&chan->chain_running);

	/* register virt channel to dma engine */
	list_add_tail(&chan->chan.device_node, &pdev->device.channels);

	return 0;
}

static const struct of_device_id mmp_pdma_dt_ids[] = {
	{ .compatible = "marvell,pdma-1.0", },
	{}
};
MODULE_DEVICE_TABLE(of, mmp_pdma_dt_ids);

static struct dma_chan *mmp_pdma_dma_xlate(struct of_phandle_args *dma_spec,
					   struct of_dma *ofdma)
{
	struct mmp_pdma_device *d = ofdma->of_dma_data;
	struct dma_chan *chan;

	chan = dma_get_any_slave_channel(&d->device);
	if (!chan)
		return NULL;

	to_mmp_pdma_chan(chan)->drcmr = dma_spec->args[0];

	return chan;
}

static int mmp_pdma_probe(struct platform_device *op)
{
	struct mmp_pdma_device *pdev;
	const struct of_device_id *of_id;
	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
	struct resource *iores;
	int i, ret, irq = 0;
	int dma_channels = 0, irq_num = 0;
	const enum dma_slave_buswidth widths =
		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
		DMA_SLAVE_BUSWIDTH_4_BYTES;

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

	pdev->dev = &op->dev;

	spin_lock_init(&pdev->phy_lock);

	iores = platform_get_resource(op, IORESOURCE_MEM, 0);
	pdev->base = devm_ioremap_resource(pdev->dev, iores);
	if (IS_ERR(pdev->base))
		return PTR_ERR(pdev->base);

	of_id = of_match_device(mmp_pdma_dt_ids, pdev->dev);
	if (of_id)
		of_property_read_u32(pdev->dev->of_node, "#dma-channels",
				     &dma_channels);
	else if (pdata && pdata->dma_channels)
		dma_channels = pdata->dma_channels;
	else
		dma_channels = 32;	/* default 32 channel */
	pdev->dma_channels = dma_channels;

	for (i = 0; i < dma_channels; i++) {
		if (platform_get_irq(op, i) > 0)
			irq_num++;
	}

	pdev->phy = devm_kcalloc(pdev->dev, dma_channels, sizeof(*pdev->phy),
				 GFP_KERNEL);
	if (pdev->phy == NULL)
		return -ENOMEM;

	INIT_LIST_HEAD(&pdev->device.channels);

	if (irq_num != dma_channels) {
		/* all chan share one irq, demux inside */
		irq = platform_get_irq(op, 0);
		ret = devm_request_irq(pdev->dev, irq, mmp_pdma_int_handler,
				       IRQF_SHARED, "pdma", pdev);
		if (ret)
			return ret;
	}

	for (i = 0; i < dma_channels; i++) {
		irq = (irq_num != dma_channels) ? 0 : platform_get_irq(op, i);
		ret = mmp_pdma_chan_init(pdev, i, irq);
		if (ret)
			return ret;
	}

	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
	dma_cap_set(DMA_MEMCPY, pdev->device.cap_mask);
	dma_cap_set(DMA_CYCLIC, pdev->device.cap_mask);
	dma_cap_set(DMA_PRIVATE, pdev->device.cap_mask);
	pdev->device.dev = &op->dev;
	pdev->device.device_alloc_chan_resources = mmp_pdma_alloc_chan_resources;
	pdev->device.device_free_chan_resources = mmp_pdma_free_chan_resources;
	pdev->device.device_tx_status = mmp_pdma_tx_status;
	pdev->device.device_prep_dma_memcpy = mmp_pdma_prep_memcpy;
	pdev->device.device_prep_slave_sg = mmp_pdma_prep_slave_sg;
	pdev->device.device_prep_dma_cyclic = mmp_pdma_prep_dma_cyclic;
	pdev->device.device_issue_pending = mmp_pdma_issue_pending;
	pdev->device.device_config = mmp_pdma_config;
	pdev->device.device_terminate_all = mmp_pdma_terminate_all;
	pdev->device.copy_align = DMAENGINE_ALIGN_8_BYTES;
	pdev->device.src_addr_widths = widths;
	pdev->device.dst_addr_widths = widths;
	pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
	pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;

	if (pdev->dev->coherent_dma_mask)
		dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask);
	else
		dma_set_mask(pdev->dev, DMA_BIT_MASK(64));

	ret = dma_async_device_register(&pdev->device);
	if (ret) {
		dev_err(pdev->device.dev, "unable to register\n");
		return ret;
	}

	if (op->dev.of_node) {
		/* Device-tree DMA controller registration */
		ret = of_dma_controller_register(op->dev.of_node,
						 mmp_pdma_dma_xlate, pdev);
		if (ret < 0) {
			dev_err(&op->dev, "of_dma_controller_register failed\n");
			return ret;
		}
	}

	platform_set_drvdata(op, pdev);
	dev_info(pdev->device.dev, "initialized %d channels\n", dma_channels);
	return 0;
}

static const struct platform_device_id mmp_pdma_id_table[] = {
	{ "mmp-pdma", },
	{ },
};

static struct platform_driver mmp_pdma_driver = {
	.driver		= {
		.name	= "mmp-pdma",
		.of_match_table = mmp_pdma_dt_ids,
	},
	.id_table	= mmp_pdma_id_table,
	.probe		= mmp_pdma_probe,
	.remove		= mmp_pdma_remove,
};

bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param)
{
	struct mmp_pdma_chan *c = to_mmp_pdma_chan(chan);

	if (chan->device->dev->driver != &mmp_pdma_driver.driver)
		return false;

	c->drcmr = *(unsigned int *)param;

	return true;
}
EXPORT_SYMBOL_GPL(mmp_pdma_filter_fn);

module_platform_driver(mmp_pdma_driver);

MODULE_DESCRIPTION("MARVELL MMP Peripheral DMA Driver");
MODULE_AUTHOR("Marvell International Ltd.");
MODULE_LICENSE("GPL v2");