summaryrefslogtreecommitdiffstats
path: root/drivers/nvme/target/io-cmd-file.c
blob: 1dd1a0fe2e819dbe6a1d4b5d071972bd35fda314 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * NVMe Over Fabrics Target File I/O commands implementation.
 * Copyright (c) 2017-2018 Western Digital Corporation or its
 * affiliates.
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/uio.h>
#include <linux/falloc.h>
#include <linux/file.h>
#include "nvmet.h"

#define NVMET_MAX_MPOOL_BVEC		16
#define NVMET_MIN_MPOOL_OBJ		16

int nvmet_file_ns_revalidate(struct nvmet_ns *ns)
{
	struct kstat stat;
	int ret;

	ret = vfs_getattr(&ns->file->f_path, &stat, STATX_SIZE,
			  AT_STATX_FORCE_SYNC);
	if (!ret)
		ns->size = stat.size;
	return ret;
}

void nvmet_file_ns_disable(struct nvmet_ns *ns)
{
	if (ns->file) {
		if (ns->buffered_io)
			flush_workqueue(buffered_io_wq);
		mempool_destroy(ns->bvec_pool);
		ns->bvec_pool = NULL;
		kmem_cache_destroy(ns->bvec_cache);
		ns->bvec_cache = NULL;
		fput(ns->file);
		ns->file = NULL;
	}
}

int nvmet_file_ns_enable(struct nvmet_ns *ns)
{
	int flags = O_RDWR | O_LARGEFILE;
	int ret;

	if (!ns->buffered_io)
		flags |= O_DIRECT;

	ns->file = filp_open(ns->device_path, flags, 0);
	if (IS_ERR(ns->file)) {
		ret = PTR_ERR(ns->file);
		pr_err("failed to open file %s: (%d)\n",
			ns->device_path, ret);
		ns->file = NULL;
		return ret;
	}

	ret = nvmet_file_ns_revalidate(ns);
	if (ret)
		goto err;

	/*
	 * i_blkbits can be greater than the universally accepted upper bound,
	 * so make sure we export a sane namespace lba_shift.
	 */
	ns->blksize_shift = min_t(u8,
			file_inode(ns->file)->i_blkbits, 12);

	ns->bvec_cache = kmem_cache_create("nvmet-bvec",
			NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec),
			0, SLAB_HWCACHE_ALIGN, NULL);
	if (!ns->bvec_cache) {
		ret = -ENOMEM;
		goto err;
	}

	ns->bvec_pool = mempool_create(NVMET_MIN_MPOOL_OBJ, mempool_alloc_slab,
			mempool_free_slab, ns->bvec_cache);

	if (!ns->bvec_pool) {
		ret = -ENOMEM;
		goto err;
	}

	return ret;
err:
	ns->size = 0;
	ns->blksize_shift = 0;
	nvmet_file_ns_disable(ns);
	return ret;
}

static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg)
{
	bv->bv_page = sg_page(sg);
	bv->bv_offset = sg->offset;
	bv->bv_len = sg->length;
}

static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
		unsigned long nr_segs, size_t count, int ki_flags)
{
	struct kiocb *iocb = &req->f.iocb;
	ssize_t (*call_iter)(struct kiocb *iocb, struct iov_iter *iter);
	struct iov_iter iter;
	int rw;

	if (req->cmd->rw.opcode == nvme_cmd_write) {
		if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
			ki_flags |= IOCB_DSYNC;
		call_iter = req->ns->file->f_op->write_iter;
		rw = WRITE;
	} else {
		call_iter = req->ns->file->f_op->read_iter;
		rw = READ;
	}

	iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count);

	iocb->ki_pos = pos;
	iocb->ki_filp = req->ns->file;
	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);

	return call_iter(iocb, &iter);
}

static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
{
	struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb);
	u16 status = NVME_SC_SUCCESS;

	if (req->f.bvec != req->inline_bvec) {
		if (likely(req->f.mpool_alloc == false))
			kfree(req->f.bvec);
		else
			mempool_free(req->f.bvec, req->ns->bvec_pool);
	}

	if (unlikely(ret != req->transfer_len))
		status = errno_to_nvme_status(req, ret);
	nvmet_req_complete(req, status);
}

static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
{
	ssize_t nr_bvec = req->sg_cnt;
	unsigned long bv_cnt = 0;
	bool is_sync = false;
	size_t len = 0, total_len = 0;
	ssize_t ret = 0;
	loff_t pos;
	int i;
	struct scatterlist *sg;

	if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
		is_sync = true;

	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
	if (unlikely(pos + req->transfer_len > req->ns->size)) {
		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
		return true;
	}

	memset(&req->f.iocb, 0, sizeof(struct kiocb));
	for_each_sg(req->sg, sg, req->sg_cnt, i) {
		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg);
		len += req->f.bvec[bv_cnt].bv_len;
		total_len += req->f.bvec[bv_cnt].bv_len;
		bv_cnt++;

		WARN_ON_ONCE((nr_bvec - 1) < 0);

		if (unlikely(is_sync) &&
		    (nr_bvec - 1 == 0 || bv_cnt == NVMET_MAX_MPOOL_BVEC)) {
			ret = nvmet_file_submit_bvec(req, pos, bv_cnt, len, 0);
			if (ret < 0)
				goto complete;

			pos += len;
			bv_cnt = 0;
			len = 0;
		}
		nr_bvec--;
	}

	if (WARN_ON_ONCE(total_len != req->transfer_len)) {
		ret = -EIO;
		goto complete;
	}

	if (unlikely(is_sync)) {
		ret = total_len;
		goto complete;
	}

	/*
	 * A NULL ki_complete ask for synchronous execution, which we want
	 * for the IOCB_NOWAIT case.
	 */
	if (!(ki_flags & IOCB_NOWAIT))
		req->f.iocb.ki_complete = nvmet_file_io_done;

	ret = nvmet_file_submit_bvec(req, pos, bv_cnt, total_len, ki_flags);

	switch (ret) {
	case -EIOCBQUEUED:
		return true;
	case -EAGAIN:
		if (WARN_ON_ONCE(!(ki_flags & IOCB_NOWAIT)))
			goto complete;
		return false;
	case -EOPNOTSUPP:
		/*
		 * For file systems returning error -EOPNOTSUPP, handle
		 * IOCB_NOWAIT error case separately and retry without
		 * IOCB_NOWAIT.
		 */
		if ((ki_flags & IOCB_NOWAIT))
			return false;
		break;
	}

complete:
	nvmet_file_io_done(&req->f.iocb, ret, 0);
	return true;
}

static void nvmet_file_buffered_io_work(struct work_struct *w)
{
	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);

	nvmet_file_execute_io(req, 0);
}

static void nvmet_file_submit_buffered_io(struct nvmet_req *req)
{
	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
	queue_work(buffered_io_wq, &req->f.work);
}

static void nvmet_file_execute_rw(struct nvmet_req *req)
{
	ssize_t nr_bvec = req->sg_cnt;

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

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

	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
				GFP_KERNEL);
	else
		req->f.bvec = req->inline_bvec;

	if (unlikely(!req->f.bvec)) {
		/* fallback under memory pressure */
		req->f.bvec = mempool_alloc(req->ns->bvec_pool, GFP_KERNEL);
		req->f.mpool_alloc = true;
	} else
		req->f.mpool_alloc = false;

	if (req->ns->buffered_io) {
		if (likely(!req->f.mpool_alloc) &&
				nvmet_file_execute_io(req, IOCB_NOWAIT))
			return;
		nvmet_file_submit_buffered_io(req);
	} else
		nvmet_file_execute_io(req, 0);
}

u16 nvmet_file_flush(struct nvmet_req *req)
{
	return errno_to_nvme_status(req, vfs_fsync(req->ns->file, 1));
}

static void nvmet_file_flush_work(struct work_struct *w)
{
	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);

	nvmet_req_complete(req, nvmet_file_flush(req));
}

static void nvmet_file_execute_flush(struct nvmet_req *req)
{
	if (!nvmet_check_transfer_len(req, 0))
		return;
	INIT_WORK(&req->f.work, nvmet_file_flush_work);
	schedule_work(&req->f.work);
}

static void nvmet_file_execute_discard(struct nvmet_req *req)
{
	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
	struct nvme_dsm_range range;
	loff_t offset, len;
	u16 status = 0;
	int ret;
	int i;

	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;

		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
		len = le32_to_cpu(range.nlb);
		len <<= req->ns->blksize_shift;
		if (offset + len > req->ns->size) {
			req->error_slba = le64_to_cpu(range.slba);
			status = errno_to_nvme_status(req, -ENOSPC);
			break;
		}

		ret = vfs_fallocate(req->ns->file, mode, offset, len);
		if (ret && ret != -EOPNOTSUPP) {
			req->error_slba = le64_to_cpu(range.slba);
			status = errno_to_nvme_status(req, ret);
			break;
		}
	}

	nvmet_req_complete(req, status);
}

static void nvmet_file_dsm_work(struct work_struct *w)
{
	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);

	switch (le32_to_cpu(req->cmd->dsm.attributes)) {
	case NVME_DSMGMT_AD:
		nvmet_file_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_file_execute_dsm(struct nvmet_req *req)
{
	if (!nvmet_check_data_len_lte(req, nvmet_dsm_len(req)))
		return;
	INIT_WORK(&req->f.work, nvmet_file_dsm_work);
	schedule_work(&req->f.work);
}

static void nvmet_file_write_zeroes_work(struct work_struct *w)
{
	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
	struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes;
	int mode = FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE;
	loff_t offset;
	loff_t len;
	int ret;

	offset = le64_to_cpu(write_zeroes->slba) << req->ns->blksize_shift;
	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
			req->ns->blksize_shift);

	if (unlikely(offset + len > req->ns->size)) {
		nvmet_req_complete(req, errno_to_nvme_status(req, -ENOSPC));
		return;
	}

	ret = vfs_fallocate(req->ns->file, mode, offset, len);
	nvmet_req_complete(req, ret < 0 ? errno_to_nvme_status(req, ret) : 0);
}

static void nvmet_file_execute_write_zeroes(struct nvmet_req *req)
{
	if (!nvmet_check_transfer_len(req, 0))
		return;
	INIT_WORK(&req->f.work, nvmet_file_write_zeroes_work);
	schedule_work(&req->f.work);
}

u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
{
	switch (req->cmd->common.opcode) {
	case nvme_cmd_read:
	case nvme_cmd_write:
		req->execute = nvmet_file_execute_rw;
		return 0;
	case nvme_cmd_flush:
		req->execute = nvmet_file_execute_flush;
		return 0;
	case nvme_cmd_dsm:
		req->execute = nvmet_file_execute_dsm;
		return 0;
	case nvme_cmd_write_zeroes:
		req->execute = nvmet_file_execute_write_zeroes;
		return 0;
	default:
		return nvmet_report_invalid_opcode(req);
	}
}