aboutsummaryrefslogtreecommitdiff
path: root/crypto/async_tx/async_pq.c
blob: f9cdc5e91664b7cc0aae578ad61ef878cacae742 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright(c) 2007 Yuri Tikhonov <yur@emcraft.com>
 * Copyright(c) 2009 Intel Corporation
 */
#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/gfp.h>

/**
 * pq_scribble_page - space to hold throwaway P or Q buffer for
 * synchronous gen_syndrome
 */
static struct page *pq_scribble_page;

/* the struct page *blocks[] parameter passed to async_gen_syndrome()
 * and async_syndrome_val() contains the 'P' destination address at
 * blocks[disks-2] and the 'Q' destination address at blocks[disks-1]
 *
 * note: these are macros as they are used as lvalues
 */
#define P(b, d) (b[d-2])
#define Q(b, d) (b[d-1])

#define MAX_DISKS 255

/**
 * do_async_gen_syndrome - asynchronously calculate P and/or Q
 */
static __async_inline struct dma_async_tx_descriptor *
do_async_gen_syndrome(struct dma_chan *chan,
		      const unsigned char *scfs, int disks,
		      struct dmaengine_unmap_data *unmap,
		      enum dma_ctrl_flags dma_flags,
		      struct async_submit_ctl *submit)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct dma_device *dma = chan->device;
	enum async_tx_flags flags_orig = submit->flags;
	dma_async_tx_callback cb_fn_orig = submit->cb_fn;
	dma_async_tx_callback cb_param_orig = submit->cb_param;
	int src_cnt = disks - 2;
	unsigned short pq_src_cnt;
	dma_addr_t dma_dest[2];
	int src_off = 0;

	while (src_cnt > 0) {
		submit->flags = flags_orig;
		pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
		/* if we are submitting additional pqs, leave the chain open,
		 * clear the callback parameters, and leave the destination
		 * buffers mapped
		 */
		if (src_cnt > pq_src_cnt) {
			submit->flags &= ~ASYNC_TX_ACK;
			submit->flags |= ASYNC_TX_FENCE;
			submit->cb_fn = NULL;
			submit->cb_param = NULL;
		} else {
			submit->cb_fn = cb_fn_orig;
			submit->cb_param = cb_param_orig;
			if (cb_fn_orig)
				dma_flags |= DMA_PREP_INTERRUPT;
		}
		if (submit->flags & ASYNC_TX_FENCE)
			dma_flags |= DMA_PREP_FENCE;

		/* Drivers force forward progress in case they can not provide
		 * a descriptor
		 */
		for (;;) {
			dma_dest[0] = unmap->addr[disks - 2];
			dma_dest[1] = unmap->addr[disks - 1];
			tx = dma->device_prep_dma_pq(chan, dma_dest,
						     &unmap->addr[src_off],
						     pq_src_cnt,
						     &scfs[src_off], unmap->len,
						     dma_flags);
			if (likely(tx))
				break;
			async_tx_quiesce(&submit->depend_tx);
			dma_async_issue_pending(chan);
		}

		dma_set_unmap(tx, unmap);
		async_tx_submit(chan, tx, submit);
		submit->depend_tx = tx;

		/* drop completed sources */
		src_cnt -= pq_src_cnt;
		src_off += pq_src_cnt;

		dma_flags |= DMA_PREP_CONTINUE;
	}

	return tx;
}

/**
 * do_sync_gen_syndrome - synchronously calculate a raid6 syndrome
 */
static void
do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
		     size_t len, struct async_submit_ctl *submit)
{
	void **srcs;
	int i;
	int start = -1, stop = disks - 3;

	if (submit->scribble)
		srcs = submit->scribble;
	else
		srcs = (void **) blocks;

	for (i = 0; i < disks; i++) {
		if (blocks[i] == NULL) {
			BUG_ON(i > disks - 3); /* P or Q can't be zero */
			srcs[i] = (void*)raid6_empty_zero_page;
		} else {
			srcs[i] = page_address(blocks[i]) + offsets[i];

			if (i < disks - 2) {
				stop = i;
				if (start == -1)
					start = i;
			}
		}
	}
	if (submit->flags & ASYNC_TX_PQ_XOR_DST) {
		BUG_ON(!raid6_call.xor_syndrome);
		if (start >= 0)
			raid6_call.xor_syndrome(disks, start, stop, len, srcs);
	} else
		raid6_call.gen_syndrome(disks, len, srcs);
	async_tx_sync_epilog(submit);
}

static inline bool
is_dma_pq_aligned_offs(struct dma_device *dev, unsigned int *offs,
				     int src_cnt, size_t len)
{
	int i;

	for (i = 0; i < src_cnt; i++) {
		if (!is_dma_pq_aligned(dev, offs[i], 0, len))
			return false;
	}
	return true;
}

/**
 * async_gen_syndrome - asynchronously calculate a raid6 syndrome
 * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
 * @offsets: offset array into each block (src and dest) to start transaction
 * @disks: number of blocks (including missing P or Q, see below)
 * @len: length of operation in bytes
 * @submit: submission/completion modifiers
 *
 * General note: This routine assumes a field of GF(2^8) with a
 * primitive polynomial of 0x11d and a generator of {02}.
 *
 * 'disks' note: callers can optionally omit either P or Q (but not
 * both) from the calculation by setting blocks[disks-2] or
 * blocks[disks-1] to NULL.  When P or Q is omitted 'len' must be <=
 * PAGE_SIZE as a temporary buffer of this size is used in the
 * synchronous path.  'disks' always accounts for both destination
 * buffers.  If any source buffers (blocks[i] where i < disks - 2) are
 * set to NULL those buffers will be replaced with the raid6_zero_page
 * in the synchronous path and omitted in the hardware-asynchronous
 * path.
 */
struct dma_async_tx_descriptor *
async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
		   size_t len, struct async_submit_ctl *submit)
{
	int src_cnt = disks - 2;
	struct dma_chan *chan = async_tx_find_channel(submit, DMA_PQ,
						      &P(blocks, disks), 2,
						      blocks, src_cnt, len);
	struct dma_device *device = chan ? chan->device : NULL;
	struct dmaengine_unmap_data *unmap = NULL;

	BUG_ON(disks > MAX_DISKS || !(P(blocks, disks) || Q(blocks, disks)));

	if (device)
		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);

	/* XORing P/Q is only implemented in software */
	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
	    (src_cnt <= dma_maxpq(device, 0) ||
	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
		struct dma_async_tx_descriptor *tx;
		enum dma_ctrl_flags dma_flags = 0;
		unsigned char coefs[MAX_DISKS];
		int i, j;

		/* run the p+q asynchronously */
		pr_debug("%s: (async) disks: %d len: %zu\n",
			 __func__, disks, len);

		/* convert source addresses being careful to collapse 'empty'
		 * sources and update the coefficients accordingly
		 */
		unmap->len = len;
		for (i = 0, j = 0; i < src_cnt; i++) {
			if (blocks[i] == NULL)
				continue;
			unmap->addr[j] = dma_map_page(device->dev, blocks[i],
						offsets[i], len, DMA_TO_DEVICE);
			coefs[j] = raid6_gfexp[i];
			unmap->to_cnt++;
			j++;
		}

		/*
		 * DMAs use destinations as sources,
		 * so use BIDIRECTIONAL mapping
		 */
		unmap->bidi_cnt++;
		if (P(blocks, disks))
			unmap->addr[j++] = dma_map_page(device->dev, P(blocks, disks),
							P(offsets, disks),
							len, DMA_BIDIRECTIONAL);
		else {
			unmap->addr[j++] = 0;
			dma_flags |= DMA_PREP_PQ_DISABLE_P;
		}

		unmap->bidi_cnt++;
		if (Q(blocks, disks))
			unmap->addr[j++] = dma_map_page(device->dev, Q(blocks, disks),
							Q(offsets, disks),
							len, DMA_BIDIRECTIONAL);
		else {
			unmap->addr[j++] = 0;
			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
		}

		tx = do_async_gen_syndrome(chan, coefs, j, unmap, dma_flags, submit);
		dmaengine_unmap_put(unmap);
		return tx;
	}

	dmaengine_unmap_put(unmap);

	/* run the pq synchronously */
	pr_debug("%s: (sync) disks: %d len: %zu\n", __func__, disks, len);

	/* wait for any prerequisite operations */
	async_tx_quiesce(&submit->depend_tx);

	if (!P(blocks, disks)) {
		P(blocks, disks) = pq_scribble_page;
		P(offsets, disks) = 0;
	}
	if (!Q(blocks, disks)) {
		Q(blocks, disks) = pq_scribble_page;
		Q(offsets, disks) = 0;
	}
	do_sync_gen_syndrome(blocks, offsets, disks, len, submit);

	return NULL;
}
EXPORT_SYMBOL_GPL(async_gen_syndrome);

static inline struct dma_chan *
pq_val_chan(struct async_submit_ctl *submit, struct page **blocks, int disks, size_t len)
{
	#ifdef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA
	return NULL;
	#endif
	return async_tx_find_channel(submit, DMA_PQ_VAL, NULL, 0,  blocks,
				     disks, len);
}

/**
 * async_syndrome_val - asynchronously validate a raid6 syndrome
 * @blocks: source blocks from idx 0..disks-3, P @ disks-2 and Q @ disks-1
 * @offset: common offset into each block (src and dest) to start transaction
 * @disks: number of blocks (including missing P or Q, see below)
 * @len: length of operation in bytes
 * @pqres: on val failure SUM_CHECK_P_RESULT and/or SUM_CHECK_Q_RESULT are set
 * @spare: temporary result buffer for the synchronous case
 * @s_off: spare buffer page offset
 * @submit: submission / completion modifiers
 *
 * The same notes from async_gen_syndrome apply to the 'blocks',
 * and 'disks' parameters of this routine.  The synchronous path
 * requires a temporary result buffer and submit->scribble to be
 * specified.
 */
struct dma_async_tx_descriptor *
async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
		   size_t len, enum sum_check_flags *pqres, struct page *spare,
		   unsigned int s_off, struct async_submit_ctl *submit)
{
	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
	struct dma_device *device = chan ? chan->device : NULL;
	struct dma_async_tx_descriptor *tx;
	unsigned char coefs[MAX_DISKS];
	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
	struct dmaengine_unmap_data *unmap = NULL;

	BUG_ON(disks < 4 || disks > MAX_DISKS);

	if (device)
		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);

	if (unmap && disks <= dma_maxpq(device, 0) &&
	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
		struct device *dev = device->dev;
		dma_addr_t pq[2];
		int i, j = 0, src_cnt = 0;

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

		unmap->len = len;
		for (i = 0; i < disks-2; i++)
			if (likely(blocks[i])) {
				unmap->addr[j] = dma_map_page(dev, blocks[i],
							      offsets[i], len,
							      DMA_TO_DEVICE);
				coefs[j] = raid6_gfexp[i];
				unmap->to_cnt++;
				src_cnt++;
				j++;
			}

		if (!P(blocks, disks)) {
			pq[0] = 0;
			dma_flags |= DMA_PREP_PQ_DISABLE_P;
		} else {
			pq[0] = dma_map_page(dev, P(blocks, disks),
					     P(offsets, disks), len,
					     DMA_TO_DEVICE);
			unmap->addr[j++] = pq[0];
			unmap->to_cnt++;
		}
		if (!Q(blocks, disks)) {
			pq[1] = 0;
			dma_flags |= DMA_PREP_PQ_DISABLE_Q;
		} else {
			pq[1] = dma_map_page(dev, Q(blocks, disks),
					     Q(offsets, disks), len,
					     DMA_TO_DEVICE);
			unmap->addr[j++] = pq[1];
			unmap->to_cnt++;
		}

		if (submit->flags & ASYNC_TX_FENCE)
			dma_flags |= DMA_PREP_FENCE;
		for (;;) {
			tx = device->device_prep_dma_pq_val(chan, pq,
							    unmap->addr,
							    src_cnt,
							    coefs,
							    len, pqres,
							    dma_flags);
			if (likely(tx))
				break;
			async_tx_quiesce(&submit->depend_tx);
			dma_async_issue_pending(chan);
		}

		dma_set_unmap(tx, unmap);
		async_tx_submit(chan, tx, submit);
	} else {
		struct page *p_src = P(blocks, disks);
		unsigned int p_off = P(offsets, disks);
		struct page *q_src = Q(blocks, disks);
		unsigned int q_off = Q(offsets, disks);
		enum async_tx_flags flags_orig = submit->flags;
		dma_async_tx_callback cb_fn_orig = submit->cb_fn;
		void *scribble = submit->scribble;
		void *cb_param_orig = submit->cb_param;
		void *p, *q, *s;

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

		/* caller must provide a temporary result buffer and
		 * allow the input parameters to be preserved
		 */
		BUG_ON(!spare || !scribble);

		/* wait for any prerequisite operations */
		async_tx_quiesce(&submit->depend_tx);

		/* recompute p and/or q into the temporary buffer and then
		 * check to see the result matches the current value
		 */
		tx = NULL;
		*pqres = 0;
		if (p_src) {
			init_async_submit(submit, ASYNC_TX_XOR_ZERO_DST, NULL,
					  NULL, NULL, scribble);
			tx = async_xor_offs(spare, s_off,
					blocks, offsets, disks-2, len, submit);
			async_tx_quiesce(&tx);
			p = page_address(p_src) + p_off;
			s = page_address(spare) + s_off;
			*pqres |= !!memcmp(p, s, len) << SUM_CHECK_P;
		}

		if (q_src) {
			P(blocks, disks) = NULL;
			Q(blocks, disks) = spare;
			Q(offsets, disks) = s_off;
			init_async_submit(submit, 0, NULL, NULL, NULL, scribble);
			tx = async_gen_syndrome(blocks, offsets, disks,
					len, submit);
			async_tx_quiesce(&tx);
			q = page_address(q_src) + q_off;
			s = page_address(spare) + s_off;
			*pqres |= !!memcmp(q, s, len) << SUM_CHECK_Q;
		}

		/* restore P, Q and submit */
		P(blocks, disks) = p_src;
		P(offsets, disks) = p_off;
		Q(blocks, disks) = q_src;
		Q(offsets, disks) = q_off;

		submit->cb_fn = cb_fn_orig;
		submit->cb_param = cb_param_orig;
		submit->flags = flags_orig;
		async_tx_sync_epilog(submit);
		tx = NULL;
	}
	dmaengine_unmap_put(unmap);

	return tx;
}
EXPORT_SYMBOL_GPL(async_syndrome_val);

static int __init async_pq_init(void)
{
	pq_scribble_page = alloc_page(GFP_KERNEL);

	if (pq_scribble_page)
		return 0;

	pr_err("%s: failed to allocate required spare page\n", __func__);

	return -ENOMEM;
}

static void __exit async_pq_exit(void)
{
	__free_page(pq_scribble_page);
}

module_init(async_pq_init);
module_exit(async_pq_exit);

MODULE_DESCRIPTION("asynchronous raid6 syndrome generation/validation");
MODULE_LICENSE("GPL");