summaryrefslogtreecommitdiff
path: root/drivers/lightnvm/pblk-read.c
blob: 140927ebf41e9a1f178a71771d28c57ee579f317 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2016 CNEX Labs
 * Initial release: Javier Gonzalez <javier@cnexlabs.com>
 *                  Matias Bjorling <matias@cnexlabs.com>
 *
 * 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.
 *
 * 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.
 *
 * pblk-read.c - pblk's read path
 */

#include "pblk.h"

/*
 * There is no guarantee that the value read from cache has not been updated and
 * resides at another location in the cache. We guarantee though that if the
 * value is read from the cache, it belongs to the mapped lba. In order to
 * guarantee and order between writes and reads are ordered, a flush must be
 * issued.
 */
static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
				sector_t lba, struct ppa_addr ppa)
{
#ifdef CONFIG_NVM_PBLK_DEBUG
	/* Callers must ensure that the ppa points to a cache address */
	BUG_ON(pblk_ppa_empty(ppa));
	BUG_ON(!pblk_addr_in_cache(ppa));
#endif

	return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba, ppa);
}

static int pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
				 struct bio *bio, sector_t blba,
				 bool *from_cache)
{
	void *meta_list = rqd->meta_list;
	int nr_secs, i;

retry:
	nr_secs = pblk_lookup_l2p_seq(pblk, rqd->ppa_list, blba, rqd->nr_ppas,
					from_cache);

	if (!*from_cache)
		goto end;

	for (i = 0; i < nr_secs; i++) {
		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
		sector_t lba = blba + i;

		if (pblk_ppa_empty(rqd->ppa_list[i])) {
			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);

			meta->lba = addr_empty;
		} else if (pblk_addr_in_cache(rqd->ppa_list[i])) {
			/*
			 * Try to read from write buffer. The address is later
			 * checked on the write buffer to prevent retrieving
			 * overwritten data.
			 */
			if (!pblk_read_from_cache(pblk, bio, lba,
							rqd->ppa_list[i])) {
				if (i == 0) {
					/*
					 * We didn't call with bio_advance()
					 * yet, so we can just retry.
					 */
					goto retry;
				} else {
					/*
					 * We already call bio_advance()
					 * so we cannot retry and we need
					 * to quit that function in order
					 * to allow caller to handle the bio
					 * splitting in the current sector
					 * position.
					 */
					nr_secs = i;
					goto end;
				}
			}
			meta->lba = cpu_to_le64(lba);
#ifdef CONFIG_NVM_PBLK_DEBUG
			atomic_long_inc(&pblk->cache_reads);
#endif
		}
		bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
	}

end:
	if (pblk_io_aligned(pblk, nr_secs))
		rqd->is_seq = 1;

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_add(nr_secs, &pblk->inflight_reads);
#endif

	return nr_secs;
}


static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
				sector_t blba)
{
	void *meta_list = rqd->meta_list;
	int nr_lbas = rqd->nr_ppas;
	int i;

	if (!pblk_is_oob_meta_supported(pblk))
		return;

	for (i = 0; i < nr_lbas; i++) {
		struct pblk_sec_meta *meta = pblk_get_meta(pblk, meta_list, i);
		u64 lba = le64_to_cpu(meta->lba);

		if (lba == ADDR_EMPTY)
			continue;

		if (lba != blba + i) {
#ifdef CONFIG_NVM_PBLK_DEBUG
			struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);

			print_ppa(pblk, &ppa_list[i], "seq", i);
#endif
			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
							lba, (u64)blba + i);
			WARN_ON(1);
		}
	}
}

/*
 * There can be holes in the lba list.
 */
static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
				 u64 *lba_list, int nr_lbas)
{
	void *meta_lba_list = rqd->meta_list;
	int i, j;

	if (!pblk_is_oob_meta_supported(pblk))
		return;

	for (i = 0, j = 0; i < nr_lbas; i++) {
		struct pblk_sec_meta *meta = pblk_get_meta(pblk,
							   meta_lba_list, j);
		u64 lba = lba_list[i];
		u64 meta_lba;

		if (lba == ADDR_EMPTY)
			continue;

		meta_lba = le64_to_cpu(meta->lba);

		if (lba != meta_lba) {
#ifdef CONFIG_NVM_PBLK_DEBUG
			struct ppa_addr *ppa_list = nvm_rq_to_ppa_list(rqd);

			print_ppa(pblk, &ppa_list[j], "rnd", j);
#endif
			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
							meta_lba, lba);
			WARN_ON(1);
		}

		j++;
	}

	WARN_ONCE(j != rqd->nr_ppas, "pblk: corrupted random request\n");
}

static void pblk_end_user_read(struct bio *bio, int error)
{
	if (error && error != NVM_RSP_WARN_HIGHECC)
		bio_io_error(bio);
	else
		bio_endio(bio);
}

static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
			       bool put_line)
{
	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
	struct bio *int_bio = rqd->bio;
	unsigned long start_time = r_ctx->start_time;

	bio_end_io_acct(int_bio, start_time);

	if (rqd->error)
		pblk_log_read_err(pblk, rqd);

	pblk_read_check_seq(pblk, rqd, r_ctx->lba);
	bio_put(int_bio);

	if (put_line)
		pblk_rq_to_line_put(pblk, rqd);

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
#endif

	pblk_free_rqd(pblk, rqd, PBLK_READ);
	atomic_dec(&pblk->inflight_io);
}

static void pblk_end_io_read(struct nvm_rq *rqd)
{
	struct pblk *pblk = rqd->private;
	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
	struct bio *bio = (struct bio *)r_ctx->private;

	pblk_end_user_read(bio, rqd->error);
	__pblk_end_io_read(pblk, rqd, true);
}

static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
			 sector_t lba, bool *from_cache)
{
	struct pblk_sec_meta *meta = pblk_get_meta(pblk, rqd->meta_list, 0);
	struct ppa_addr ppa;

	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache);

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_inc(&pblk->inflight_reads);
#endif

retry:
	if (pblk_ppa_empty(ppa)) {
		__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);

		meta->lba = addr_empty;
		return;
	}

	/* Try to read from write buffer. The address is later checked on the
	 * write buffer to prevent retrieving overwritten data.
	 */
	if (pblk_addr_in_cache(ppa)) {
		if (!pblk_read_from_cache(pblk, bio, lba, ppa)) {
			pblk_lookup_l2p_seq(pblk, &ppa, lba, 1, from_cache);
			goto retry;
		}

		meta->lba = cpu_to_le64(lba);

#ifdef CONFIG_NVM_PBLK_DEBUG
		atomic_long_inc(&pblk->cache_reads);
#endif
	} else {
		rqd->ppa_addr = ppa;
	}
}

void pblk_submit_read(struct pblk *pblk, struct bio *bio)
{
	sector_t blba = pblk_get_lba(bio);
	unsigned int nr_secs = pblk_get_secs(bio);
	bool from_cache;
	struct pblk_g_ctx *r_ctx;
	struct nvm_rq *rqd;
	struct bio *int_bio, *split_bio;
	unsigned long start_time;

	start_time = bio_start_io_acct(bio);

	rqd = pblk_alloc_rqd(pblk, PBLK_READ);

	rqd->opcode = NVM_OP_PREAD;
	rqd->nr_ppas = nr_secs;
	rqd->private = pblk;
	rqd->end_io = pblk_end_io_read;

	r_ctx = nvm_rq_to_pdu(rqd);
	r_ctx->start_time = start_time;
	r_ctx->lba = blba;

	if (pblk_alloc_rqd_meta(pblk, rqd)) {
		bio_io_error(bio);
		pblk_free_rqd(pblk, rqd, PBLK_READ);
		return;
	}

	/* Clone read bio to deal internally with:
	 * -read errors when reading from drive
	 * -bio_advance() calls during cache reads
	 */
	int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);

	if (nr_secs > 1)
		nr_secs = pblk_read_ppalist_rq(pblk, rqd, int_bio, blba,
						&from_cache);
	else
		pblk_read_rq(pblk, rqd, int_bio, blba, &from_cache);

split_retry:
	r_ctx->private = bio; /* original bio */
	rqd->bio = int_bio; /* internal bio */

	if (from_cache && nr_secs == rqd->nr_ppas) {
		/* All data was read from cache, we can complete the IO. */
		pblk_end_user_read(bio, 0);
		atomic_inc(&pblk->inflight_io);
		__pblk_end_io_read(pblk, rqd, false);
	} else if (nr_secs != rqd->nr_ppas) {
		/* The read bio request could be partially filled by the write
		 * buffer, but there are some holes that need to be read from
		 * the drive. In order to handle this, we will use block layer
		 * mechanism to split this request in to smaller ones and make
		 * a chain of it.
		 */
		split_bio = bio_split(bio, nr_secs * NR_PHY_IN_LOG, GFP_KERNEL,
					&pblk_bio_set);
		bio_chain(split_bio, bio);
		generic_make_request(bio);

		/* New bio contains first N sectors of the previous one, so
		 * we can continue to use existing rqd, but we need to shrink
		 * the number of PPAs in it. New bio is also guaranteed that
		 * it contains only either data from cache or from drive, newer
		 * mix of them.
		 */
		bio = split_bio;
		rqd->nr_ppas = nr_secs;
		if (rqd->nr_ppas == 1)
			rqd->ppa_addr = rqd->ppa_list[0];

		/* Recreate int_bio - existing might have some needed internal
		 * fields modified already.
		 */
		bio_put(int_bio);
		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
		goto split_retry;
	} else if (pblk_submit_io(pblk, rqd, NULL)) {
		/* Submitting IO to drive failed, let's report an error */
		rqd->error = -ENODEV;
		pblk_end_io_read(rqd);
	}
}

static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
			      struct pblk_line *line, u64 *lba_list,
			      u64 *paddr_list_gc, unsigned int nr_secs)
{
	struct ppa_addr ppa_list_l2p[NVM_MAX_VLBA];
	struct ppa_addr ppa_gc;
	int valid_secs = 0;
	int i;

	pblk_lookup_l2p_rand(pblk, ppa_list_l2p, lba_list, nr_secs);

	for (i = 0; i < nr_secs; i++) {
		if (lba_list[i] == ADDR_EMPTY)
			continue;

		ppa_gc = addr_to_gen_ppa(pblk, paddr_list_gc[i], line->id);
		if (!pblk_ppa_comp(ppa_list_l2p[i], ppa_gc)) {
			paddr_list_gc[i] = lba_list[i] = ADDR_EMPTY;
			continue;
		}

		rqd->ppa_list[valid_secs++] = ppa_list_l2p[i];
	}

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_add(valid_secs, &pblk->inflight_reads);
#endif

	return valid_secs;
}

static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
		      struct pblk_line *line, sector_t lba,
		      u64 paddr_gc)
{
	struct ppa_addr ppa_l2p, ppa_gc;
	int valid_secs = 0;

	if (lba == ADDR_EMPTY)
		goto out;

	/* logic error: lba out-of-bounds */
	if (lba >= pblk->capacity) {
		WARN(1, "pblk: read lba out of bounds\n");
		goto out;
	}

	spin_lock(&pblk->trans_lock);
	ppa_l2p = pblk_trans_map_get(pblk, lba);
	spin_unlock(&pblk->trans_lock);

	ppa_gc = addr_to_gen_ppa(pblk, paddr_gc, line->id);
	if (!pblk_ppa_comp(ppa_l2p, ppa_gc))
		goto out;

	rqd->ppa_addr = ppa_l2p;
	valid_secs = 1;

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_inc(&pblk->inflight_reads);
#endif

out:
	return valid_secs;
}

int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
{
	struct nvm_rq rqd;
	int ret = NVM_IO_OK;

	memset(&rqd, 0, sizeof(struct nvm_rq));

	ret = pblk_alloc_rqd_meta(pblk, &rqd);
	if (ret)
		return ret;

	if (gc_rq->nr_secs > 1) {
		gc_rq->secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, gc_rq->line,
							gc_rq->lba_list,
							gc_rq->paddr_list,
							gc_rq->nr_secs);
		if (gc_rq->secs_to_gc == 1)
			rqd.ppa_addr = rqd.ppa_list[0];
	} else {
		gc_rq->secs_to_gc = read_rq_gc(pblk, &rqd, gc_rq->line,
							gc_rq->lba_list[0],
							gc_rq->paddr_list[0]);
	}

	if (!(gc_rq->secs_to_gc))
		goto out;

	rqd.opcode = NVM_OP_PREAD;
	rqd.nr_ppas = gc_rq->secs_to_gc;

	if (pblk_submit_io_sync(pblk, &rqd, gc_rq->data)) {
		ret = -EIO;
		goto err_free_dma;
	}

	pblk_read_check_rand(pblk, &rqd, gc_rq->lba_list, gc_rq->nr_secs);

	atomic_dec(&pblk->inflight_io);

	if (rqd.error) {
		atomic_long_inc(&pblk->read_failed_gc);
#ifdef CONFIG_NVM_PBLK_DEBUG
		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
#endif
	}

#ifdef CONFIG_NVM_PBLK_DEBUG
	atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads);
	atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads);
	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
#endif

out:
	pblk_free_rqd_meta(pblk, &rqd);
	return ret;

err_free_dma:
	pblk_free_rqd_meta(pblk, &rqd);
	return ret;
}