aboutsummaryrefslogtreecommitdiff
path: root/drivers/dma/ioat/prep.c
blob: 033d9f2b3e2a9155ea54b96ab1c2713d4dd3cd26 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Intel I/OAT DMA Linux driver
 * Copyright(c) 2004 - 2015 Intel Corporation.
 */
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/gfp.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/prefetch.h>
#include "../dmaengine.h"
#include "registers.h"
#include "hw.h"
#include "dma.h"

#define MAX_SCF	256

/* provide a lookup table for setting the source address in the base or
 * extended descriptor of an xor or pq descriptor
 */
static const u8 xor_idx_to_desc = 0xe0;
static const u8 xor_idx_to_field[] = { 1, 4, 5, 6, 7, 0, 1, 2 };
static const u8 pq_idx_to_desc = 0xf8;
static const u8 pq16_idx_to_desc[] = { 0, 0, 1, 1, 1, 1, 1, 1, 1,
				       2, 2, 2, 2, 2, 2, 2 };
static const u8 pq_idx_to_field[] = { 1, 4, 5, 0, 1, 2, 4, 5 };
static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
					0, 1, 2, 3, 4, 5, 6 };

static void xor_set_src(struct ioat_raw_descriptor *descs[2],
			dma_addr_t addr, u32 offset, int idx)
{
	struct ioat_raw_descriptor *raw = descs[xor_idx_to_desc >> idx & 1];

	raw->field[xor_idx_to_field[idx]] = addr + offset;
}

static dma_addr_t pq_get_src(struct ioat_raw_descriptor *descs[2], int idx)
{
	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];

	return raw->field[pq_idx_to_field[idx]];
}

static dma_addr_t pq16_get_src(struct ioat_raw_descriptor *desc[3], int idx)
{
	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];

	return raw->field[pq16_idx_to_field[idx]];
}

static void pq_set_src(struct ioat_raw_descriptor *descs[2],
		       dma_addr_t addr, u32 offset, u8 coef, int idx)
{
	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *) descs[0];
	struct ioat_raw_descriptor *raw = descs[pq_idx_to_desc >> idx & 1];

	raw->field[pq_idx_to_field[idx]] = addr + offset;
	pq->coef[idx] = coef;
}

static void pq16_set_src(struct ioat_raw_descriptor *desc[3],
			dma_addr_t addr, u32 offset, u8 coef, unsigned idx)
{
	struct ioat_pq_descriptor *pq = (struct ioat_pq_descriptor *)desc[0];
	struct ioat_pq16a_descriptor *pq16 =
		(struct ioat_pq16a_descriptor *)desc[1];
	struct ioat_raw_descriptor *raw = desc[pq16_idx_to_desc[idx]];

	raw->field[pq16_idx_to_field[idx]] = addr + offset;

	if (idx < 8)
		pq->coef[idx] = coef;
	else
		pq16->coef[idx - 8] = coef;
}

static struct ioat_sed_ent *
ioat3_alloc_sed(struct ioatdma_device *ioat_dma, unsigned int hw_pool)
{
	struct ioat_sed_ent *sed;
	gfp_t flags = __GFP_ZERO | GFP_ATOMIC;

	sed = kmem_cache_alloc(ioat_sed_cache, flags);
	if (!sed)
		return NULL;

	sed->hw_pool = hw_pool;
	sed->hw = dma_pool_alloc(ioat_dma->sed_hw_pool[hw_pool],
				 flags, &sed->dma);
	if (!sed->hw) {
		kmem_cache_free(ioat_sed_cache, sed);
		return NULL;
	}

	return sed;
}

struct dma_async_tx_descriptor *
ioat_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
			   dma_addr_t dma_src, size_t len, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
	struct ioat_dma_descriptor *hw;
	struct ioat_ring_ent *desc;
	dma_addr_t dst = dma_dest;
	dma_addr_t src = dma_src;
	size_t total_len = len;
	int num_descs, idx, i;

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
	if (likely(num_descs) &&
	    ioat_check_space_lock(ioat_chan, num_descs) == 0)
		idx = ioat_chan->head;
	else
		return NULL;
	i = 0;
	do {
		size_t copy = min_t(size_t, len, 1 << ioat_chan->xfercap_log);

		desc = ioat_get_ring_ent(ioat_chan, idx + i);
		hw = desc->hw;

		hw->size = copy;
		hw->ctl = 0;
		hw->src_addr = src;
		hw->dst_addr = dst;

		len -= copy;
		dst += copy;
		src += copy;
		dump_desc_dbg(ioat_chan, desc);
	} while (++i < num_descs);

	desc->txd.flags = flags;
	desc->len = total_len;
	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
	hw->ctl_f.compl_write = 1;
	dump_desc_dbg(ioat_chan, desc);
	/* we leave the channel locked to ensure in order submission */

	return &desc->txd;
}


static struct dma_async_tx_descriptor *
__ioat_prep_xor_lock(struct dma_chan *c, enum sum_check_flags *result,
		      dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt,
		      size_t len, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
	struct ioat_ring_ent *compl_desc;
	struct ioat_ring_ent *desc;
	struct ioat_ring_ent *ext;
	size_t total_len = len;
	struct ioat_xor_descriptor *xor;
	struct ioat_xor_ext_descriptor *xor_ex = NULL;
	struct ioat_dma_descriptor *hw;
	int num_descs, with_ext, idx, i;
	u32 offset = 0;
	u8 op = result ? IOAT_OP_XOR_VAL : IOAT_OP_XOR;

	BUG_ON(src_cnt < 2);

	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
	/* we need 2x the number of descriptors to cover greater than 5
	 * sources
	 */
	if (src_cnt > 5) {
		with_ext = 1;
		num_descs *= 2;
	} else
		with_ext = 0;

	/* completion writes from the raid engine may pass completion
	 * writes from the legacy engine, so we need one extra null
	 * (legacy) descriptor to ensure all completion writes arrive in
	 * order.
	 */
	if (likely(num_descs) &&
	    ioat_check_space_lock(ioat_chan, num_descs+1) == 0)
		idx = ioat_chan->head;
	else
		return NULL;
	i = 0;
	do {
		struct ioat_raw_descriptor *descs[2];
		size_t xfer_size = min_t(size_t,
					 len, 1 << ioat_chan->xfercap_log);
		int s;

		desc = ioat_get_ring_ent(ioat_chan, idx + i);
		xor = desc->xor;

		/* save a branch by unconditionally retrieving the
		 * extended descriptor xor_set_src() knows to not write
		 * to it in the single descriptor case
		 */
		ext = ioat_get_ring_ent(ioat_chan, idx + i + 1);
		xor_ex = ext->xor_ex;

		descs[0] = (struct ioat_raw_descriptor *) xor;
		descs[1] = (struct ioat_raw_descriptor *) xor_ex;
		for (s = 0; s < src_cnt; s++)
			xor_set_src(descs, src[s], offset, s);
		xor->size = xfer_size;
		xor->dst_addr = dest + offset;
		xor->ctl = 0;
		xor->ctl_f.op = op;
		xor->ctl_f.src_cnt = src_cnt_to_hw(src_cnt);

		len -= xfer_size;
		offset += xfer_size;
		dump_desc_dbg(ioat_chan, desc);
	} while ((i += 1 + with_ext) < num_descs);

	/* last xor descriptor carries the unmap parameters and fence bit */
	desc->txd.flags = flags;
	desc->len = total_len;
	if (result)
		desc->result = result;
	xor->ctl_f.fence = !!(flags & DMA_PREP_FENCE);

	/* completion descriptor carries interrupt bit */
	compl_desc = ioat_get_ring_ent(ioat_chan, idx + i);
	compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
	hw = compl_desc->hw;
	hw->ctl = 0;
	hw->ctl_f.null = 1;
	hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
	hw->ctl_f.compl_write = 1;
	hw->size = NULL_DESC_BUFFER_SIZE;
	dump_desc_dbg(ioat_chan, compl_desc);

	/* we leave the channel locked to ensure in order submission */
	return &compl_desc->txd;
}

struct dma_async_tx_descriptor *
ioat_prep_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
	       unsigned int src_cnt, size_t len, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	return __ioat_prep_xor_lock(chan, NULL, dest, src, src_cnt, len, flags);
}

struct dma_async_tx_descriptor *
ioat_prep_xor_val(struct dma_chan *chan, dma_addr_t *src,
		    unsigned int src_cnt, size_t len,
		    enum sum_check_flags *result, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	/* the cleanup routine only sets bits on validate failure, it
	 * does not clear bits on validate success... so clear it here
	 */
	*result = 0;

	return __ioat_prep_xor_lock(chan, result, src[0], &src[1],
				     src_cnt - 1, len, flags);
}

static void
dump_pq_desc_dbg(struct ioatdma_chan *ioat_chan, struct ioat_ring_ent *desc,
		 struct ioat_ring_ent *ext)
{
	struct device *dev = to_dev(ioat_chan);
	struct ioat_pq_descriptor *pq = desc->pq;
	struct ioat_pq_ext_descriptor *pq_ex = ext ? ext->pq_ex : NULL;
	struct ioat_raw_descriptor *descs[] = { (void *) pq, (void *) pq_ex };
	int src_cnt = src_cnt_to_sw(pq->ctl_f.src_cnt);
	int i;

	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
		" sz: %#10.8x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
		" src_cnt: %d)\n",
		desc_id(desc), (unsigned long long) desc->txd.phys,
		(unsigned long long) (pq_ex ? pq_ex->next : pq->next),
		desc->txd.flags, pq->size, pq->ctl, pq->ctl_f.op,
		pq->ctl_f.int_en, pq->ctl_f.compl_write,
		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
		pq->ctl_f.src_cnt);
	for (i = 0; i < src_cnt; i++)
		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
			(unsigned long long) pq_get_src(descs, i), pq->coef[i]);
	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
	dev_dbg(dev, "\tNEXT: %#llx\n", pq->next);
}

static void dump_pq16_desc_dbg(struct ioatdma_chan *ioat_chan,
			       struct ioat_ring_ent *desc)
{
	struct device *dev = to_dev(ioat_chan);
	struct ioat_pq_descriptor *pq = desc->pq;
	struct ioat_raw_descriptor *descs[] = { (void *)pq,
						(void *)pq,
						(void *)pq };
	int src_cnt = src16_cnt_to_sw(pq->ctl_f.src_cnt);
	int i;

	if (desc->sed) {
		descs[1] = (void *)desc->sed->hw;
		descs[2] = (void *)desc->sed->hw + 64;
	}

	dev_dbg(dev, "desc[%d]: (%#llx->%#llx) flags: %#x"
		" sz: %#x ctl: %#x (op: %#x int: %d compl: %d pq: '%s%s'"
		" src_cnt: %d)\n",
		desc_id(desc), (unsigned long long) desc->txd.phys,
		(unsigned long long) pq->next,
		desc->txd.flags, pq->size, pq->ctl,
		pq->ctl_f.op, pq->ctl_f.int_en,
		pq->ctl_f.compl_write,
		pq->ctl_f.p_disable ? "" : "p", pq->ctl_f.q_disable ? "" : "q",
		pq->ctl_f.src_cnt);
	for (i = 0; i < src_cnt; i++) {
		dev_dbg(dev, "\tsrc[%d]: %#llx coef: %#x\n", i,
			(unsigned long long) pq16_get_src(descs, i),
			pq->coef[i]);
	}
	dev_dbg(dev, "\tP: %#llx\n", pq->p_addr);
	dev_dbg(dev, "\tQ: %#llx\n", pq->q_addr);
}

static struct dma_async_tx_descriptor *
__ioat_prep_pq_lock(struct dma_chan *c, enum sum_check_flags *result,
		     const dma_addr_t *dst, const dma_addr_t *src,
		     unsigned int src_cnt, const unsigned char *scf,
		     size_t len, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
	struct ioat_ring_ent *compl_desc;
	struct ioat_ring_ent *desc;
	struct ioat_ring_ent *ext;
	size_t total_len = len;
	struct ioat_pq_descriptor *pq;
	struct ioat_pq_ext_descriptor *pq_ex = NULL;
	struct ioat_dma_descriptor *hw;
	u32 offset = 0;
	u8 op = result ? IOAT_OP_PQ_VAL : IOAT_OP_PQ;
	int i, s, idx, with_ext, num_descs;
	int cb32 = (ioat_dma->version < IOAT_VER_3_3) ? 1 : 0;

	dev_dbg(to_dev(ioat_chan), "%s\n", __func__);
	/* the engine requires at least two sources (we provide
	 * at least 1 implied source in the DMA_PREP_CONTINUE case)
	 */
	BUG_ON(src_cnt + dmaf_continue(flags) < 2);

	num_descs = ioat_xferlen_to_descs(ioat_chan, len);
	/* we need 2x the number of descriptors to cover greater than 3
	 * sources (we need 1 extra source in the q-only continuation
	 * case and 3 extra sources in the p+q continuation case.
	 */
	if (src_cnt + dmaf_p_disabled_continue(flags) > 3 ||
	    (dmaf_continue(flags) && !dmaf_p_disabled_continue(flags))) {
		with_ext = 1;
		num_descs *= 2;
	} else
		with_ext = 0;

	/* completion writes from the raid engine may pass completion
	 * writes from the legacy engine, so we need one extra null
	 * (legacy) descriptor to ensure all completion writes arrive in
	 * order.
	 */
	if (likely(num_descs) &&
	    ioat_check_space_lock(ioat_chan, num_descs + cb32) == 0)
		idx = ioat_chan->head;
	else
		return NULL;
	i = 0;
	do {
		struct ioat_raw_descriptor *descs[2];
		size_t xfer_size = min_t(size_t, len,
					 1 << ioat_chan->xfercap_log);

		desc = ioat_get_ring_ent(ioat_chan, idx + i);
		pq = desc->pq;

		/* save a branch by unconditionally retrieving the
		 * extended descriptor pq_set_src() knows to not write
		 * to it in the single descriptor case
		 */
		ext = ioat_get_ring_ent(ioat_chan, idx + i + with_ext);
		pq_ex = ext->pq_ex;

		descs[0] = (struct ioat_raw_descriptor *) pq;
		descs[1] = (struct ioat_raw_descriptor *) pq_ex;

		for (s = 0; s < src_cnt; s++)
			pq_set_src(descs, src[s], offset, scf[s], s);

		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
		if (dmaf_p_disabled_continue(flags))
			pq_set_src(descs, dst[1], offset, 1, s++);
		else if (dmaf_continue(flags)) {
			pq_set_src(descs, dst[0], offset, 0, s++);
			pq_set_src(descs, dst[1], offset, 1, s++);
			pq_set_src(descs, dst[1], offset, 0, s++);
		}
		pq->size = xfer_size;
		pq->p_addr = dst[0] + offset;
		pq->q_addr = dst[1] + offset;
		pq->ctl = 0;
		pq->ctl_f.op = op;
		/* we turn on descriptor write back error status */
		if (ioat_dma->cap & IOAT_CAP_DWBES)
			pq->ctl_f.wb_en = result ? 1 : 0;
		pq->ctl_f.src_cnt = src_cnt_to_hw(s);
		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);

		len -= xfer_size;
		offset += xfer_size;
	} while ((i += 1 + with_ext) < num_descs);

	/* last pq descriptor carries the unmap parameters and fence bit */
	desc->txd.flags = flags;
	desc->len = total_len;
	if (result)
		desc->result = result;
	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
	dump_pq_desc_dbg(ioat_chan, desc, ext);

	if (!cb32) {
		pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
		pq->ctl_f.compl_write = 1;
		compl_desc = desc;
	} else {
		/* completion descriptor carries interrupt bit */
		compl_desc = ioat_get_ring_ent(ioat_chan, idx + i);
		compl_desc->txd.flags = flags & DMA_PREP_INTERRUPT;
		hw = compl_desc->hw;
		hw->ctl = 0;
		hw->ctl_f.null = 1;
		hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
		hw->ctl_f.compl_write = 1;
		hw->size = NULL_DESC_BUFFER_SIZE;
		dump_desc_dbg(ioat_chan, compl_desc);
	}


	/* we leave the channel locked to ensure in order submission */
	return &compl_desc->txd;
}

static struct dma_async_tx_descriptor *
__ioat_prep_pq16_lock(struct dma_chan *c, enum sum_check_flags *result,
		       const dma_addr_t *dst, const dma_addr_t *src,
		       unsigned int src_cnt, const unsigned char *scf,
		       size_t len, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
	struct ioat_ring_ent *desc;
	size_t total_len = len;
	struct ioat_pq_descriptor *pq;
	u32 offset = 0;
	u8 op;
	int i, s, idx, num_descs;

	/* this function is only called with 9-16 sources */
	op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;

	dev_dbg(to_dev(ioat_chan), "%s\n", __func__);

	num_descs = ioat_xferlen_to_descs(ioat_chan, len);

	/*
	 * 16 source pq is only available on cb3.3 and has no completion
	 * write hw bug.
	 */
	if (num_descs && ioat_check_space_lock(ioat_chan, num_descs) == 0)
		idx = ioat_chan->head;
	else
		return NULL;

	i = 0;

	do {
		struct ioat_raw_descriptor *descs[4];
		size_t xfer_size = min_t(size_t, len,
					 1 << ioat_chan->xfercap_log);

		desc = ioat_get_ring_ent(ioat_chan, idx + i);
		pq = desc->pq;

		descs[0] = (struct ioat_raw_descriptor *) pq;

		desc->sed = ioat3_alloc_sed(ioat_dma, (src_cnt-2) >> 3);
		if (!desc->sed) {
			dev_err(to_dev(ioat_chan),
				"%s: no free sed entries\n", __func__);
			return NULL;
		}

		pq->sed_addr = desc->sed->dma;
		desc->sed->parent = desc;

		descs[1] = (struct ioat_raw_descriptor *)desc->sed->hw;
		descs[2] = (void *)descs[1] + 64;

		for (s = 0; s < src_cnt; s++)
			pq16_set_src(descs, src[s], offset, scf[s], s);

		/* see the comment for dma_maxpq in include/linux/dmaengine.h */
		if (dmaf_p_disabled_continue(flags))
			pq16_set_src(descs, dst[1], offset, 1, s++);
		else if (dmaf_continue(flags)) {
			pq16_set_src(descs, dst[0], offset, 0, s++);
			pq16_set_src(descs, dst[1], offset, 1, s++);
			pq16_set_src(descs, dst[1], offset, 0, s++);
		}

		pq->size = xfer_size;
		pq->p_addr = dst[0] + offset;
		pq->q_addr = dst[1] + offset;
		pq->ctl = 0;
		pq->ctl_f.op = op;
		pq->ctl_f.src_cnt = src16_cnt_to_hw(s);
		/* we turn on descriptor write back error status */
		if (ioat_dma->cap & IOAT_CAP_DWBES)
			pq->ctl_f.wb_en = result ? 1 : 0;
		pq->ctl_f.p_disable = !!(flags & DMA_PREP_PQ_DISABLE_P);
		pq->ctl_f.q_disable = !!(flags & DMA_PREP_PQ_DISABLE_Q);

		len -= xfer_size;
		offset += xfer_size;
	} while (++i < num_descs);

	/* last pq descriptor carries the unmap parameters and fence bit */
	desc->txd.flags = flags;
	desc->len = total_len;
	if (result)
		desc->result = result;
	pq->ctl_f.fence = !!(flags & DMA_PREP_FENCE);

	/* with cb3.3 we should be able to do completion w/o a null desc */
	pq->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
	pq->ctl_f.compl_write = 1;

	dump_pq16_desc_dbg(ioat_chan, desc);

	/* we leave the channel locked to ensure in order submission */
	return &desc->txd;
}

static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
{
	if (dmaf_p_disabled_continue(flags))
		return src_cnt + 1;
	else if (dmaf_continue(flags))
		return src_cnt + 3;
	else
		return src_cnt;
}

struct dma_async_tx_descriptor *
ioat_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
	      unsigned int src_cnt, const unsigned char *scf, size_t len,
	      unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	/* specify valid address for disabled result */
	if (flags & DMA_PREP_PQ_DISABLE_P)
		dst[0] = dst[1];
	if (flags & DMA_PREP_PQ_DISABLE_Q)
		dst[1] = dst[0];

	/* handle the single source multiply case from the raid6
	 * recovery path
	 */
	if ((flags & DMA_PREP_PQ_DISABLE_P) && src_cnt == 1) {
		dma_addr_t single_source[2];
		unsigned char single_source_coef[2];

		BUG_ON(flags & DMA_PREP_PQ_DISABLE_Q);
		single_source[0] = src[0];
		single_source[1] = src[0];
		single_source_coef[0] = scf[0];
		single_source_coef[1] = 0;

		return src_cnt_flags(src_cnt, flags) > 8 ?
			__ioat_prep_pq16_lock(chan, NULL, dst, single_source,
					       2, single_source_coef, len,
					       flags) :
			__ioat_prep_pq_lock(chan, NULL, dst, single_source, 2,
					     single_source_coef, len, flags);

	} else {
		return src_cnt_flags(src_cnt, flags) > 8 ?
			__ioat_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
					       scf, len, flags) :
			__ioat_prep_pq_lock(chan, NULL, dst, src, src_cnt,
					     scf, len, flags);
	}
}

struct dma_async_tx_descriptor *
ioat_prep_pq_val(struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src,
		  unsigned int src_cnt, const unsigned char *scf, size_t len,
		  enum sum_check_flags *pqres, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	/* specify valid address for disabled result */
	if (flags & DMA_PREP_PQ_DISABLE_P)
		pq[0] = pq[1];
	if (flags & DMA_PREP_PQ_DISABLE_Q)
		pq[1] = pq[0];

	/* the cleanup routine only sets bits on validate failure, it
	 * does not clear bits on validate success... so clear it here
	 */
	*pqres = 0;

	return src_cnt_flags(src_cnt, flags) > 8 ?
		__ioat_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
				       flags) :
		__ioat_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
				     flags);
}

struct dma_async_tx_descriptor *
ioat_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
		 unsigned int src_cnt, size_t len, unsigned long flags)
{
	unsigned char scf[MAX_SCF];
	dma_addr_t pq[2];
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	if (src_cnt > MAX_SCF)
		return NULL;

	memset(scf, 0, src_cnt);
	pq[0] = dst;
	flags |= DMA_PREP_PQ_DISABLE_Q;
	pq[1] = dst; /* specify valid address for disabled result */

	return src_cnt_flags(src_cnt, flags) > 8 ?
		__ioat_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
				       flags) :
		__ioat_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
				     flags);
}

struct dma_async_tx_descriptor *
ioat_prep_pqxor_val(struct dma_chan *chan, dma_addr_t *src,
		     unsigned int src_cnt, size_t len,
		     enum sum_check_flags *result, unsigned long flags)
{
	unsigned char scf[MAX_SCF];
	dma_addr_t pq[2];
	struct ioatdma_chan *ioat_chan = to_ioat_chan(chan);

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	if (src_cnt > MAX_SCF)
		return NULL;

	/* the cleanup routine only sets bits on validate failure, it
	 * does not clear bits on validate success... so clear it here
	 */
	*result = 0;

	memset(scf, 0, src_cnt);
	pq[0] = src[0];
	flags |= DMA_PREP_PQ_DISABLE_Q;
	pq[1] = pq[0]; /* specify valid address for disabled result */

	return src_cnt_flags(src_cnt, flags) > 8 ?
		__ioat_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
				       scf, len, flags) :
		__ioat_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
				     scf, len, flags);
}

struct dma_async_tx_descriptor *
ioat_prep_interrupt_lock(struct dma_chan *c, unsigned long flags)
{
	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
	struct ioat_ring_ent *desc;
	struct ioat_dma_descriptor *hw;

	if (test_bit(IOAT_CHAN_DOWN, &ioat_chan->state))
		return NULL;

	if (ioat_check_space_lock(ioat_chan, 1) == 0)
		desc = ioat_get_ring_ent(ioat_chan, ioat_chan->head);
	else
		return NULL;

	hw = desc->hw;
	hw->ctl = 0;
	hw->ctl_f.null = 1;
	hw->ctl_f.int_en = 1;
	hw->ctl_f.fence = !!(flags & DMA_PREP_FENCE);
	hw->ctl_f.compl_write = 1;
	hw->size = NULL_DESC_BUFFER_SIZE;
	hw->src_addr = 0;
	hw->dst_addr = 0;

	desc->txd.flags = flags;
	desc->len = 1;

	dump_desc_dbg(ioat_chan, desc);

	/* we leave the channel locked to ensure in order submission */
	return &desc->txd;
}