summaryrefslogtreecommitdiffstats
path: root/drivers/nvme/target/io-cmd-bdev.c
blob: 125dde3f410ee711de2e90009eb76f0c3e0d5255 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe I/O command implementation.
 * Copyright (c) 2015-2016 HGST, a Western Digital Company.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/blkdev.h>
#include <linux/module.h>
#include "nvmet.h"

void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
{
	const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
	/* Number of logical blocks per physical block. */
	const u32 lpp = ql->physical_block_size / ql->logical_block_size;
	/* Logical blocks per physical block, 0's based. */
	const __le16 lpp0b = to0based(lpp);

	/*
	 * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
	 * NAWUPF, and NACWU are defined for this namespace and should be
	 * used by the host for this namespace instead of the AWUN, AWUPF,
	 * and ACWU fields in the Identify Controller data structure. If
	 * any of these fields are zero that means that the corresponding
	 * field from the identify controller data structure should be used.
	 */
	id->nsfeat |= 1 << 1;
	id->nawun = lpp0b;
	id->nawupf = lpp0b;
	id->nacwu = lpp0b;

	/*
	 * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
	 * NOWS are defined for this namespace and should be used by
	 * the host for I/O optimization.
	 */
	id->nsfeat |= 1 << 4;
	/* NPWG = Namespace Preferred Write Granularity. 0's based */
	id->npwg = lpp0b;
	/* NPWA = Namespace Preferred Write Alignment. 0's based */
	id->npwa = id->npwg;
	/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
	id->npdg = to0based(ql->discard_granularity / ql->logical_block_size);
	/* NPDG = Namespace Preferred Deallocate Alignment */
	id->npda = id->npdg;
	/* NOWS = Namespace Optimal Write Size */
	id->nows = to0based(ql->io_opt / ql->logical_block_size);
}

static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
{
	struct blk_integrity *bi = bdev_get_integrity(ns->bdev);

	if (bi) {
		ns->metadata_size = bi->tuple_size;
		if (bi->profile == &t10_pi_type1_crc)
			ns->pi_type = NVME_NS_DPS_PI_TYPE1;
		else if (bi->profile == &t10_pi_type3_crc)
			ns->pi_type = NVME_NS_DPS_PI_TYPE3;
		else
			/* Unsupported metadata type */
			ns->metadata_size = 0;
	}
}

int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
{
	int ret;

	ns->bdev = blkdev_get_by_path(ns->device_path,
			FMODE_READ | FMODE_WRITE, NULL);
	if (IS_ERR(ns->bdev)) {
		ret = PTR_ERR(ns->bdev);
		if (ret != -ENOTBLK) {
			pr_err("failed to open block device %s: (%ld)\n",
					ns->device_path, PTR_ERR(ns->bdev));
		}
		ns->bdev = NULL;
		return ret;
	}
	ns->size = i_size_read(ns->bdev->bd_inode);
	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));

	ns->pi_type = 0;
	ns->metadata_size = 0;
	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10))
		nvmet_bdev_ns_enable_integrity(ns);

	return 0;
}

void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
	if (ns->bdev) {
		blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
		ns->bdev = NULL;
	}
}

void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns)
{
	ns->size = i_size_read(ns->bdev->bd_inode);
}

static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
{
	u16 status = NVME_SC_SUCCESS;

	if (likely(blk_sts == BLK_STS_OK))
		return status;
	/*
	 * Right now there exists M : 1 mapping between block layer error
	 * to the NVMe status code (see nvme_error_status()). For consistency,
	 * when we reverse map we use most appropriate NVMe Status code from
	 * the group of the NVMe staus codes used in the nvme_error_status().
	 */
	switch (blk_sts) {
	case BLK_STS_NOSPC:
		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
		req->error_loc = offsetof(struct nvme_rw_command, length);
		break;
	case BLK_STS_TARGET:
		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
		req->error_loc = offsetof(struct nvme_rw_command, slba);
		break;
	case BLK_STS_NOTSUPP:
		req->error_loc = offsetof(struct nvme_common_command, opcode);
		switch (req->cmd->common.opcode) {
		case nvme_cmd_dsm:
		case nvme_cmd_write_zeroes:
			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
			break;
		default:
			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
		}
		break;
	case BLK_STS_MEDIUM:
		status = NVME_SC_ACCESS_DENIED;
		req->error_loc = offsetof(struct nvme_rw_command, nsid);
		break;
	case BLK_STS_IOERR:
	default:
		status = NVME_SC_INTERNAL | NVME_SC_DNR;
		req->error_loc = offsetof(struct nvme_common_command, opcode);
	}

	switch (req->cmd->common.opcode) {
	case nvme_cmd_read:
	case nvme_cmd_write:
		req->error_slba = le64_to_cpu(req->cmd->rw.slba);
		break;
	case nvme_cmd_write_zeroes:
		req->error_slba =
			le64_to_cpu(req->cmd->write_zeroes.slba);
		break;
	default:
		req->error_slba = 0;
	}
	return status;
}

static void nvmet_bio_done(struct bio *bio)
{
	struct nvmet_req *req = bio->bi_private;

	nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
	if (bio != &req->b.inline_bio)
		bio_put(bio);
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio,
				struct sg_mapping_iter *miter)
{
	struct blk_integrity *bi;
	struct bio_integrity_payload *bip;
	struct block_device *bdev = req->ns->bdev;
	int rc;
	size_t resid, len;

	bi = bdev_get_integrity(bdev);
	if (unlikely(!bi)) {
		pr_err("Unable to locate bio_integrity\n");
		return -ENODEV;
	}

	bip = bio_integrity_alloc(bio, GFP_NOIO,
		min_t(unsigned int, req->metadata_sg_cnt, BIO_MAX_PAGES));
	if (IS_ERR(bip)) {
		pr_err("Unable to allocate bio_integrity_payload\n");
		return PTR_ERR(bip);
	}

	bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio));
	/* virtual start sector must be in integrity interval units */
	bip_set_seed(bip, bio->bi_iter.bi_sector >>
		     (bi->interval_exp - SECTOR_SHIFT));

	resid = bip->bip_iter.bi_size;
	while (resid > 0 && sg_miter_next(miter)) {
		len = min_t(size_t, miter->length, resid);
		rc = bio_integrity_add_page(bio, miter->page, len,
					    offset_in_page(miter->addr));
		if (unlikely(rc != len)) {
			pr_err("bio_integrity_add_page() failed; %d\n", rc);
			sg_miter_stop(miter);
			return -ENOMEM;
		}

		resid -= len;
		if (len < miter->length)
			miter->consumed -= miter->length - len;
	}
	sg_miter_stop(miter);

	return 0;
}
#else
static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio,
				struct sg_mapping_iter *miter)
{
	return -EINVAL;
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */

static void nvmet_bdev_execute_rw(struct nvmet_req *req)
{
	int sg_cnt = req->sg_cnt;
	struct bio *bio;
	struct scatterlist *sg;
	struct blk_plug plug;
	sector_t sector;
	int op, i, rc;
	struct sg_mapping_iter prot_miter;
	unsigned int iter_flags;
	unsigned int total_len = nvmet_rw_data_len(req) + req->metadata_len;

	if (!nvmet_check_transfer_len(req, total_len))
		return;

	if (!req->sg_cnt) {
		nvmet_req_complete(req, 0);
		return;
	}

	if (req->cmd->rw.opcode == nvme_cmd_write) {
		op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
			op |= REQ_FUA;
		iter_flags = SG_MITER_TO_SG;
	} else {
		op = REQ_OP_READ;
		iter_flags = SG_MITER_FROM_SG;
	}

	if (is_pci_p2pdma_page(sg_page(req->sg)))
		op |= REQ_NOMERGE;

	sector = le64_to_cpu(req->cmd->rw.slba);
	sector <<= (req->ns->blksize_shift - 9);

	if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
		bio = &req->b.inline_bio;
		bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
	} else {
		bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
	}
	bio_set_dev(bio, req->ns->bdev);
	bio->bi_iter.bi_sector = sector;
	bio->bi_private = req;
	bio->bi_end_io = nvmet_bio_done;
	bio->bi_opf = op;

	blk_start_plug(&plug);
	if (req->metadata_len)
		sg_miter_start(&prot_miter, req->metadata_sg,
			       req->metadata_sg_cnt, iter_flags);

	for_each_sg(req->sg, sg, req->sg_cnt, i) {
		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
				!= sg->length) {
			struct bio *prev = bio;

			if (req->metadata_len) {
				rc = nvmet_bdev_alloc_bip(req, bio,
							  &prot_miter);
				if (unlikely(rc)) {
					bio_io_error(bio);
					return;
				}
			}

			bio = bio_alloc(GFP_KERNEL, min(sg_cnt, BIO_MAX_PAGES));
			bio_set_dev(bio, req->ns->bdev);
			bio->bi_iter.bi_sector = sector;
			bio->bi_opf = op;

			bio_chain(bio, prev);
			submit_bio(prev);
		}

		sector += sg->length >> 9;
		sg_cnt--;
	}

	if (req->metadata_len) {
		rc = nvmet_bdev_alloc_bip(req, bio, &prot_miter);
		if (unlikely(rc)) {
			bio_io_error(bio);
			return;
		}
	}

	submit_bio(bio);
	blk_finish_plug(&plug);
}

static void nvmet_bdev_execute_flush(struct nvmet_req *req)
{
	struct bio *bio = &req->b.inline_bio;

	if (!nvmet_check_transfer_len(req, 0))
		return;

	bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
	bio_set_dev(bio, req->ns->bdev);
	bio->bi_private = req;
	bio->bi_end_io = nvmet_bio_done;
	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;

	submit_bio(bio);
}

u16 nvmet_bdev_flush(struct nvmet_req *req)
{
	if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL))
		return NVME_SC_INTERNAL | NVME_SC_DNR;
	return 0;
}

static u16 nvmet_bdev_discard_range(struct nvmet_req *req,
		struct nvme_dsm_range *range, struct bio **bio)
{
	struct nvmet_ns *ns = req->ns;
	int ret;

	ret = __blkdev_issue_discard(ns->bdev,
			le64_to_cpu(range->slba) << (ns->blksize_shift - 9),
			le32_to_cpu(range->nlb) << (ns->blksize_shift - 9),
			GFP_KERNEL, 0, bio);
	if (ret && ret != -EOPNOTSUPP) {
		req->error_slba = le64_to_cpu(range->slba);
		return errno_to_nvme_status(req, ret);
	}
	return NVME_SC_SUCCESS;
}

static void nvmet_bdev_execute_discard(struct nvmet_req *req)
{
	struct nvme_dsm_range range;
	struct bio *bio = NULL;
	int i;
	u16 status;

	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
		status = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
				sizeof(range));
		if (status)
			break;

		status = nvmet_bdev_discard_range(req, &range, &bio);
		if (status)
			break;
	}

	if (bio) {
		bio->bi_private = req;
		bio->bi_end_io = nvmet_bio_done;
		if (status)
			bio_io_error(bio);
		else
			submit_bio(bio);
	} else {
		nvmet_req_complete(req, status);
	}
}

static void nvmet_bdev_execute_dsm(struct nvmet_req *req)
{
	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
		return;

	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
	case NVME_DSMGMT_AD:
		nvmet_bdev_execute_discard(req);
		return;
	case NVME_DSMGMT_IDR:
	case NVME_DSMGMT_IDW:
	default:
		/* Not supported yet */
		nvmet_req_complete(req, 0);
		return;
	}
}

static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req)
{
	struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
	struct bio *bio = NULL;
	sector_t sector;
	sector_t nr_sector;
	int ret;

	if (!nvmet_check_transfer_len(req, 0))
		return;

	sector = le64_to_cpu(write_zeroes->slba) <<
		(req->ns->blksize_shift - 9);
	nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
		(req->ns->blksize_shift - 9));

	ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
			GFP_KERNEL, &bio, 0);
	if (bio) {
		bio->bi_private = req;
		bio->bi_end_io = nvmet_bio_done;
		submit_bio(bio);
	} else {
		nvmet_req_complete(req, errno_to_nvme_status(req, ret));
	}
}

u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
{
	struct nvme_command *cmd = req->cmd;

	switch (cmd->common.opcode) {
	case nvme_cmd_read:
	case nvme_cmd_write:
		req->execute = nvmet_bdev_execute_rw;
		if (req->sq->ctrl->pi_support && nvmet_ns_has_pi(req->ns))
			req->metadata_len = nvmet_rw_metadata_len(req);
		return 0;
	case nvme_cmd_flush:
		req->execute = nvmet_bdev_execute_flush;
		return 0;
	case nvme_cmd_dsm:
		req->execute = nvmet_bdev_execute_dsm;
		return 0;
	case nvme_cmd_write_zeroes:
		req->execute = nvmet_bdev_execute_write_zeroes;
		return 0;
	default:
		pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
		       req->sq->qid);
		req->error_loc = offsetof(struct nvme_common_command, opcode);
		return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
	}
}