summaryrefslogtreecommitdiffstats
path: root/crypto/async_tx/async_raid6_recov.c
blob: a3a72a784421fcece0f0468808a43b27a9d390e8 (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
/*
 * Asynchronous RAID-6 recovery calculations ASYNC_TX API.
 * Copyright(c) 2009 Intel Corporation
 *
 * based on raid6recov.c:
 *   Copyright 2002 H. Peter Anvin
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option)
 * any later version.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 51
 * Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
 *
 */
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/dma-mapping.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
#include <linux/dmaengine.h>

static struct dma_async_tx_descriptor *
async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef,
		  size_t len, struct async_submit_ctl *submit)
{
	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
						      &dest, 1, srcs, 2, len);
	struct dma_device *dma = chan ? chan->device : NULL;
	struct dmaengine_unmap_data *unmap = NULL;
	const u8 *amul, *bmul;
	u8 ax, bx;
	u8 *a, *b, *c;

	if (dma)
		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);

	if (unmap) {
		struct device *dev = dma->dev;
		dma_addr_t pq[2];
		struct dma_async_tx_descriptor *tx;
		enum dma_ctrl_flags dma_flags = DMA_COMPL_SKIP_SRC_UNMAP |
						DMA_COMPL_SKIP_DEST_UNMAP |
						DMA_PREP_PQ_DISABLE_P;

		if (submit->flags & ASYNC_TX_FENCE)
			dma_flags |= DMA_PREP_FENCE;
		unmap->addr[0] = dma_map_page(dev, srcs[0], 0, len, DMA_TO_DEVICE);
		unmap->addr[1] = dma_map_page(dev, srcs[1], 0, len, DMA_TO_DEVICE);
		unmap->to_cnt = 2;

		unmap->addr[2] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
		unmap->bidi_cnt = 1;
		/* engine only looks at Q, but expects it to follow P */
		pq[1] = unmap->addr[2];

		unmap->len = len;
		tx = dma->device_prep_dma_pq(chan, pq, unmap->addr, 2, coef,
					     len, dma_flags);
		if (tx) {
			dma_set_unmap(tx, unmap);
			async_tx_submit(chan, tx, submit);
			dmaengine_unmap_put(unmap);
			return tx;
		}

		/* could not get a descriptor, unmap and fall through to
		 * the synchronous path
		 */
		dmaengine_unmap_put(unmap);
	}

	/* run the operation synchronously */
	async_tx_quiesce(&submit->depend_tx);
	amul = raid6_gfmul[coef[0]];
	bmul = raid6_gfmul[coef[1]];
	a = page_address(srcs[0]);
	b = page_address(srcs[1]);
	c = page_address(dest);

	while (len--) {
		ax    = amul[*a++];
		bx    = bmul[*b++];
		*c++ = ax ^ bx;
	}

	return NULL;
}

static struct dma_async_tx_descriptor *
async_mult(struct page *dest, struct page *src, u8 coef, size_t len,
	   struct async_submit_ctl *submit)
{
	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
						      &dest, 1, &src, 1, len);
	struct dma_device *dma = chan ? chan->device : NULL;
	struct dmaengine_unmap_data *unmap = NULL;
	const u8 *qmul; /* Q multiplier table */
	u8 *d, *s;

	if (dma)
		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO);

	if (unmap) {
		dma_addr_t dma_dest[2];
		struct device *dev = dma->dev;
		struct dma_async_tx_descriptor *tx;
		enum dma_ctrl_flags dma_flags = DMA_COMPL_SKIP_SRC_UNMAP |
						DMA_COMPL_SKIP_DEST_UNMAP |
						DMA_PREP_PQ_DISABLE_P;

		if (submit->flags & ASYNC_TX_FENCE)
			dma_flags |= DMA_PREP_FENCE;
		unmap->addr[0] = dma_map_page(dev, src, 0, len, DMA_TO_DEVICE);
		unmap->to_cnt++;
		unmap->addr[1] = dma_map_page(dev, dest, 0, len, DMA_BIDIRECTIONAL);
		dma_dest[1] = unmap->addr[1];
		unmap->bidi_cnt++;
		unmap->len = len;

		/* this looks funny, but the engine looks for Q at
		 * dma_dest[1] and ignores dma_dest[0] as a dest
		 * due to DMA_PREP_PQ_DISABLE_P
		 */
		tx = dma->device_prep_dma_pq(chan, dma_dest, unmap->addr,
					     1, &coef, len, dma_flags);

		if (tx) {
			dma_set_unmap(tx, unmap);
			dmaengine_unmap_put(unmap);
			async_tx_submit(chan, tx, submit);
			return tx;
		}

		/* could not get a descriptor, unmap and fall through to
		 * the synchronous path
		 */
		dmaengine_unmap_put(unmap);
	}

	/* no channel available, or failed to allocate a descriptor, so
	 * perform the operation synchronously
	 */
	async_tx_quiesce(&submit->depend_tx);
	qmul  = raid6_gfmul[coef];
	d = page_address(dest);
	s = page_address(src);

	while (len--)
		*d++ = qmul[*s++];

	return NULL;
}

static struct dma_async_tx_descriptor *
__2data_recov_4(int disks, size_t bytes, int faila, int failb,
		struct page **blocks, struct async_submit_ctl *submit)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct page *p, *q, *a, *b;
	struct page *srcs[2];
	unsigned char coef[2];
	enum async_tx_flags flags = submit->flags;
	dma_async_tx_callback cb_fn = submit->cb_fn;
	void *cb_param = submit->cb_param;
	void *scribble = submit->scribble;

	p = blocks[disks-2];
	q = blocks[disks-1];

	a = blocks[faila];
	b = blocks[failb];

	/* in the 4 disk case P + Pxy == P and Q + Qxy == Q */
	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
	srcs[0] = p;
	srcs[1] = q;
	coef[0] = raid6_gfexi[failb-faila];
	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_sum_product(b, srcs, coef, bytes, submit);

	/* Dy = P+Pxy+Dx */
	srcs[0] = p;
	srcs[1] = b;
	init_async_submit(submit, flags | ASYNC_TX_XOR_ZERO_DST, tx, cb_fn,
			  cb_param, scribble);
	tx = async_xor(a, srcs, 0, 2, bytes, submit);

	return tx;

}

static struct dma_async_tx_descriptor *
__2data_recov_5(int disks, size_t bytes, int faila, int failb,
		struct page **blocks, struct async_submit_ctl *submit)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct page *p, *q, *g, *dp, *dq;
	struct page *srcs[2];
	unsigned char coef[2];
	enum async_tx_flags flags = submit->flags;
	dma_async_tx_callback cb_fn = submit->cb_fn;
	void *cb_param = submit->cb_param;
	void *scribble = submit->scribble;
	int good_srcs, good, i;

	good_srcs = 0;
	good = -1;
	for (i = 0; i < disks-2; i++) {
		if (blocks[i] == NULL)
			continue;
		if (i == faila || i == failb)
			continue;
		good = i;
		good_srcs++;
	}
	BUG_ON(good_srcs > 1);

	p = blocks[disks-2];
	q = blocks[disks-1];
	g = blocks[good];

	/* Compute syndrome with zero for the missing data pages
	 * Use the dead data pages as temporary storage for delta p and
	 * delta q
	 */
	dp = blocks[faila];
	dq = blocks[failb];

	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_memcpy(dp, g, 0, 0, bytes, submit);
	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);

	/* compute P + Pxy */
	srcs[0] = dp;
	srcs[1] = p;
	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  NULL, NULL, scribble);
	tx = async_xor(dp, srcs, 0, 2, bytes, submit);

	/* compute Q + Qxy */
	srcs[0] = dq;
	srcs[1] = q;
	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  NULL, NULL, scribble);
	tx = async_xor(dq, srcs, 0, 2, bytes, submit);

	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
	srcs[0] = dp;
	srcs[1] = dq;
	coef[0] = raid6_gfexi[failb-faila];
	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_sum_product(dq, srcs, coef, bytes, submit);

	/* Dy = P+Pxy+Dx */
	srcs[0] = dp;
	srcs[1] = dq;
	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
			  cb_param, scribble);
	tx = async_xor(dp, srcs, 0, 2, bytes, submit);

	return tx;
}

static struct dma_async_tx_descriptor *
__2data_recov_n(int disks, size_t bytes, int faila, int failb,
	      struct page **blocks, struct async_submit_ctl *submit)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct page *p, *q, *dp, *dq;
	struct page *srcs[2];
	unsigned char coef[2];
	enum async_tx_flags flags = submit->flags;
	dma_async_tx_callback cb_fn = submit->cb_fn;
	void *cb_param = submit->cb_param;
	void *scribble = submit->scribble;

	p = blocks[disks-2];
	q = blocks[disks-1];

	/* Compute syndrome with zero for the missing data pages
	 * Use the dead data pages as temporary storage for
	 * delta p and delta q
	 */
	dp = blocks[faila];
	blocks[faila] = NULL;
	blocks[disks-2] = dp;
	dq = blocks[failb];
	blocks[failb] = NULL;
	blocks[disks-1] = dq;

	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);

	/* Restore pointer table */
	blocks[faila]   = dp;
	blocks[failb]   = dq;
	blocks[disks-2] = p;
	blocks[disks-1] = q;

	/* compute P + Pxy */
	srcs[0] = dp;
	srcs[1] = p;
	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  NULL, NULL, scribble);
	tx = async_xor(dp, srcs, 0, 2, bytes, submit);

	/* compute Q + Qxy */
	srcs[0] = dq;
	srcs[1] = q;
	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  NULL, NULL, scribble);
	tx = async_xor(dq, srcs, 0, 2, bytes, submit);

	/* Dx = A*(P+Pxy) + B*(Q+Qxy) */
	srcs[0] = dp;
	srcs[1] = dq;
	coef[0] = raid6_gfexi[failb-faila];
	coef[1] = raid6_gfinv[raid6_gfexp[faila]^raid6_gfexp[failb]];
	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_sum_product(dq, srcs, coef, bytes, submit);

	/* Dy = P+Pxy+Dx */
	srcs[0] = dp;
	srcs[1] = dq;
	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
			  cb_param, scribble);
	tx = async_xor(dp, srcs, 0, 2, bytes, submit);

	return tx;
}

/**
 * async_raid6_2data_recov - asynchronously calculate two missing data blocks
 * @disks: number of disks in the RAID-6 array
 * @bytes: block size
 * @faila: first failed drive index
 * @failb: second failed drive index
 * @blocks: array of source pointers where the last two entries are p and q
 * @submit: submission/completion modifiers
 */
struct dma_async_tx_descriptor *
async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
			struct page **blocks, struct async_submit_ctl *submit)
{
	void *scribble = submit->scribble;
	int non_zero_srcs, i;

	BUG_ON(faila == failb);
	if (failb < faila)
		swap(faila, failb);

	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);

	/* if a dma resource is not available or a scribble buffer is not
	 * available punt to the synchronous path.  In the 'dma not
	 * available' case be sure to use the scribble buffer to
	 * preserve the content of 'blocks' as the caller intended.
	 */
	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
		void **ptrs = scribble ? scribble : (void **) blocks;

		async_tx_quiesce(&submit->depend_tx);
		for (i = 0; i < disks; i++)
			if (blocks[i] == NULL)
				ptrs[i] = (void *) raid6_empty_zero_page;
			else
				ptrs[i] = page_address(blocks[i]);

		raid6_2data_recov(disks, bytes, faila, failb, ptrs);

		async_tx_sync_epilog(submit);

		return NULL;
	}

	non_zero_srcs = 0;
	for (i = 0; i < disks-2 && non_zero_srcs < 4; i++)
		if (blocks[i])
			non_zero_srcs++;
	switch (non_zero_srcs) {
	case 0:
	case 1:
		/* There must be at least 2 sources - the failed devices. */
		BUG();

	case 2:
		/* dma devices do not uniformly understand a zero source pq
		 * operation (in contrast to the synchronous case), so
		 * explicitly handle the special case of a 4 disk array with
		 * both data disks missing.
		 */
		return __2data_recov_4(disks, bytes, faila, failb, blocks, submit);
	case 3:
		/* dma devices do not uniformly understand a single
		 * source pq operation (in contrast to the synchronous
		 * case), so explicitly handle the special case of a 5 disk
		 * array with 2 of 3 data disks missing.
		 */
		return __2data_recov_5(disks, bytes, faila, failb, blocks, submit);
	default:
		return __2data_recov_n(disks, bytes, faila, failb, blocks, submit);
	}
}
EXPORT_SYMBOL_GPL(async_raid6_2data_recov);

/**
 * async_raid6_datap_recov - asynchronously calculate a data and the 'p' block
 * @disks: number of disks in the RAID-6 array
 * @bytes: block size
 * @faila: failed drive index
 * @blocks: array of source pointers where the last two entries are p and q
 * @submit: submission/completion modifiers
 */
struct dma_async_tx_descriptor *
async_raid6_datap_recov(int disks, size_t bytes, int faila,
			struct page **blocks, struct async_submit_ctl *submit)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct page *p, *q, *dq;
	u8 coef;
	enum async_tx_flags flags = submit->flags;
	dma_async_tx_callback cb_fn = submit->cb_fn;
	void *cb_param = submit->cb_param;
	void *scribble = submit->scribble;
	int good_srcs, good, i;
	struct page *srcs[2];

	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);

	/* if a dma resource is not available or a scribble buffer is not
	 * available punt to the synchronous path.  In the 'dma not
	 * available' case be sure to use the scribble buffer to
	 * preserve the content of 'blocks' as the caller intended.
	 */
	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
		void **ptrs = scribble ? scribble : (void **) blocks;

		async_tx_quiesce(&submit->depend_tx);
		for (i = 0; i < disks; i++)
			if (blocks[i] == NULL)
				ptrs[i] = (void*)raid6_empty_zero_page;
			else
				ptrs[i] = page_address(blocks[i]);

		raid6_datap_recov(disks, bytes, faila, ptrs);

		async_tx_sync_epilog(submit);

		return NULL;
	}

	good_srcs = 0;
	good = -1;
	for (i = 0; i < disks-2; i++) {
		if (i == faila)
			continue;
		if (blocks[i]) {
			good = i;
			good_srcs++;
			if (good_srcs > 1)
				break;
		}
	}
	BUG_ON(good_srcs == 0);

	p = blocks[disks-2];
	q = blocks[disks-1];

	/* Compute syndrome with zero for the missing data page
	 * Use the dead data page as temporary storage for delta q
	 */
	dq = blocks[faila];
	blocks[faila] = NULL;
	blocks[disks-1] = dq;

	/* in the 4-disk case we only need to perform a single source
	 * multiplication with the one good data block.
	 */
	if (good_srcs == 1) {
		struct page *g = blocks[good];

		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
				  scribble);
		tx = async_memcpy(p, g, 0, 0, bytes, submit);

		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
				  scribble);
		tx = async_mult(dq, g, raid6_gfexp[good], bytes, submit);
	} else {
		init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL,
				  scribble);
		tx = async_gen_syndrome(blocks, 0, disks, bytes, submit);
	}

	/* Restore pointer table */
	blocks[faila]   = dq;
	blocks[disks-1] = q;

	/* calculate g^{-faila} */
	coef = raid6_gfinv[raid6_gfexp[faila]];

	srcs[0] = dq;
	srcs[1] = q;
	init_async_submit(submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  NULL, NULL, scribble);
	tx = async_xor(dq, srcs, 0, 2, bytes, submit);

	init_async_submit(submit, ASYNC_TX_FENCE, tx, NULL, NULL, scribble);
	tx = async_mult(dq, dq, coef, bytes, submit);

	srcs[0] = p;
	srcs[1] = dq;
	init_async_submit(submit, flags | ASYNC_TX_XOR_DROP_DST, tx, cb_fn,
			  cb_param, scribble);
	tx = async_xor(p, srcs, 0, 2, bytes, submit);

	return tx;
}
EXPORT_SYMBOL_GPL(async_raid6_datap_recov);

MODULE_AUTHOR("Dan Williams <dan.j.williams@intel.com>");
MODULE_DESCRIPTION("asynchronous RAID-6 recovery api");
MODULE_LICENSE("GPL");