summaryrefslogtreecommitdiff
path: root/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
blob: 5117959bed8a2c847df8cec3a847e9f08855170f (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-only
/*
 * VDPA simulator for block device.
 *
 * Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
 * Copyright (c) 2021, Red Hat Inc. All rights reserved.
 *
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/blkdev.h>
#include <linux/vringh.h>
#include <linux/vdpa.h>
#include <uapi/linux/virtio_blk.h>

#include "vdpa_sim.h"

#define DRV_VERSION  "0.1"
#define DRV_AUTHOR   "Max Gurtovoy <mgurtovoy@nvidia.com>"
#define DRV_DESC     "vDPA Device Simulator for block device"
#define DRV_LICENSE  "GPL v2"

#define VDPASIM_BLK_FEATURES	(VDPASIM_FEATURES | \
				 (1ULL << VIRTIO_BLK_F_FLUSH)    | \
				 (1ULL << VIRTIO_BLK_F_SIZE_MAX) | \
				 (1ULL << VIRTIO_BLK_F_SEG_MAX)  | \
				 (1ULL << VIRTIO_BLK_F_BLK_SIZE) | \
				 (1ULL << VIRTIO_BLK_F_TOPOLOGY) | \
				 (1ULL << VIRTIO_BLK_F_MQ)       | \
				 (1ULL << VIRTIO_BLK_F_DISCARD)  | \
				 (1ULL << VIRTIO_BLK_F_WRITE_ZEROES))

#define VDPASIM_BLK_CAPACITY	0x40000
#define VDPASIM_BLK_SIZE_MAX	0x1000
#define VDPASIM_BLK_SEG_MAX	32
#define VDPASIM_BLK_DWZ_MAX_SECTORS UINT_MAX

/* 1 virtqueue, 1 address space, 1 virtqueue group */
#define VDPASIM_BLK_VQ_NUM	1
#define VDPASIM_BLK_AS_NUM	1
#define VDPASIM_BLK_GROUP_NUM	1

static char vdpasim_blk_id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim";

static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector,
				    u64 num_sectors, u64 max_sectors)
{
	if (start_sector > VDPASIM_BLK_CAPACITY) {
		dev_dbg(&vdpasim->vdpa.dev,
			"starting sector exceeds the capacity - start: 0x%llx capacity: 0x%x\n",
			start_sector, VDPASIM_BLK_CAPACITY);
	}

	if (num_sectors > max_sectors) {
		dev_dbg(&vdpasim->vdpa.dev,
			"number of sectors exceeds the max allowed in a request - num: 0x%llx max: 0x%llx\n",
			num_sectors, max_sectors);
		return false;
	}

	if (num_sectors > VDPASIM_BLK_CAPACITY - start_sector) {
		dev_dbg(&vdpasim->vdpa.dev,
			"request exceeds the capacity - start: 0x%llx num: 0x%llx capacity: 0x%x\n",
			start_sector, num_sectors, VDPASIM_BLK_CAPACITY);
		return false;
	}

	return true;
}

/* Returns 'true' if the request is handled (with or without an I/O error)
 * and the status is correctly written in the last byte of the 'in iov',
 * 'false' otherwise.
 */
static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim,
				   struct vdpasim_virtqueue *vq)
{
	size_t pushed = 0, to_pull, to_push;
	struct virtio_blk_outhdr hdr;
	bool handled = false;
	ssize_t bytes;
	loff_t offset;
	u64 sector;
	u8 status;
	u32 type;
	int ret;

	ret = vringh_getdesc_iotlb(&vq->vring, &vq->out_iov, &vq->in_iov,
				   &vq->head, GFP_ATOMIC);
	if (ret != 1)
		return false;

	if (vq->out_iov.used < 1 || vq->in_iov.used < 1) {
		dev_dbg(&vdpasim->vdpa.dev, "missing headers - out_iov: %u in_iov %u\n",
			vq->out_iov.used, vq->in_iov.used);
		goto err;
	}

	if (vq->in_iov.iov[vq->in_iov.used - 1].iov_len < 1) {
		dev_dbg(&vdpasim->vdpa.dev, "request in header too short\n");
		goto err;
	}

	/* The last byte is the status and we checked if the last iov has
	 * enough room for it.
	 */
	to_push = vringh_kiov_length(&vq->in_iov) - 1;

	to_pull = vringh_kiov_length(&vq->out_iov);

	bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, &hdr,
				      sizeof(hdr));
	if (bytes != sizeof(hdr)) {
		dev_dbg(&vdpasim->vdpa.dev, "request out header too short\n");
		goto err;
	}

	to_pull -= bytes;

	type = vdpasim32_to_cpu(vdpasim, hdr.type);
	sector = vdpasim64_to_cpu(vdpasim, hdr.sector);
	offset = sector << SECTOR_SHIFT;
	status = VIRTIO_BLK_S_OK;

	if (type != VIRTIO_BLK_T_IN && type != VIRTIO_BLK_T_OUT &&
	    sector != 0) {
		dev_dbg(&vdpasim->vdpa.dev,
			"sector must be 0 for %u request - sector: 0x%llx\n",
			type, sector);
		status = VIRTIO_BLK_S_IOERR;
		goto err_status;
	}

	switch (type) {
	case VIRTIO_BLK_T_IN:
		if (!vdpasim_blk_check_range(vdpasim, sector,
					     to_push >> SECTOR_SHIFT,
					     VDPASIM_BLK_SIZE_MAX * VDPASIM_BLK_SEG_MAX)) {
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov,
					      vdpasim->buffer + offset,
					      to_push);
		if (bytes < 0) {
			dev_dbg(&vdpasim->vdpa.dev,
				"vringh_iov_push_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n",
				bytes, offset, to_push);
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		pushed += bytes;
		break;

	case VIRTIO_BLK_T_OUT:
		if (!vdpasim_blk_check_range(vdpasim, sector,
					     to_pull >> SECTOR_SHIFT,
					     VDPASIM_BLK_SIZE_MAX * VDPASIM_BLK_SEG_MAX)) {
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov,
					      vdpasim->buffer + offset,
					      to_pull);
		if (bytes < 0) {
			dev_dbg(&vdpasim->vdpa.dev,
				"vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n",
				bytes, offset, to_pull);
			status = VIRTIO_BLK_S_IOERR;
			break;
		}
		break;

	case VIRTIO_BLK_T_GET_ID:
		bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov,
					      vdpasim_blk_id,
					      VIRTIO_BLK_ID_BYTES);
		if (bytes < 0) {
			dev_dbg(&vdpasim->vdpa.dev,
				"vringh_iov_push_iotlb() error: %zd\n", bytes);
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		pushed += bytes;
		break;

	case VIRTIO_BLK_T_FLUSH:
		/* nothing to do */
		break;

	case VIRTIO_BLK_T_DISCARD:
	case VIRTIO_BLK_T_WRITE_ZEROES: {
		struct virtio_blk_discard_write_zeroes range;
		u32 num_sectors, flags;

		if (to_pull != sizeof(range)) {
			dev_dbg(&vdpasim->vdpa.dev,
				"discard/write_zeroes header len: 0x%zx [expected: 0x%zx]\n",
				to_pull, sizeof(range));
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, &range,
					      to_pull);
		if (bytes < 0) {
			dev_dbg(&vdpasim->vdpa.dev,
				"vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n",
				bytes, offset, to_pull);
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		sector = le64_to_cpu(range.sector);
		offset = sector << SECTOR_SHIFT;
		num_sectors = le32_to_cpu(range.num_sectors);
		flags = le32_to_cpu(range.flags);

		if (type == VIRTIO_BLK_T_DISCARD && flags != 0) {
			dev_dbg(&vdpasim->vdpa.dev,
				"discard unexpected flags set - flags: 0x%x\n",
				flags);
			status = VIRTIO_BLK_S_UNSUPP;
			break;
		}

		if (type == VIRTIO_BLK_T_WRITE_ZEROES &&
		    flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) {
			dev_dbg(&vdpasim->vdpa.dev,
				"write_zeroes unexpected flags set - flags: 0x%x\n",
				flags);
			status = VIRTIO_BLK_S_UNSUPP;
			break;
		}

		if (!vdpasim_blk_check_range(vdpasim, sector, num_sectors,
					     VDPASIM_BLK_DWZ_MAX_SECTORS)) {
			status = VIRTIO_BLK_S_IOERR;
			break;
		}

		if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
			memset(vdpasim->buffer + offset, 0,
			       num_sectors << SECTOR_SHIFT);
		}

		break;
	}
	default:
		dev_dbg(&vdpasim->vdpa.dev,
			"Unsupported request type %d\n", type);
		status = VIRTIO_BLK_S_IOERR;
		break;
	}

err_status:
	/* If some operations fail, we need to skip the remaining bytes
	 * to put the status in the last byte
	 */
	if (to_push - pushed > 0)
		vringh_kiov_advance(&vq->in_iov, to_push - pushed);

	/* Last byte is the status */
	bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, &status, 1);
	if (bytes != 1)
		goto err;

	pushed += bytes;

	/* Make sure data is wrote before advancing index */
	smp_wmb();

	handled = true;

err:
	vringh_complete_iotlb(&vq->vring, vq->head, pushed);

	return handled;
}

static void vdpasim_blk_work(struct work_struct *work)
{
	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
	bool reschedule = false;
	int i;

	spin_lock(&vdpasim->lock);

	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
		goto out;

	if (!vdpasim->running)
		goto out;

	for (i = 0; i < VDPASIM_BLK_VQ_NUM; i++) {
		struct vdpasim_virtqueue *vq = &vdpasim->vqs[i];
		int reqs = 0;

		if (!vq->ready)
			continue;

		while (vdpasim_blk_handle_req(vdpasim, vq)) {
			/* Make sure used is visible before rasing the interrupt. */
			smp_wmb();

			local_bh_disable();
			if (vringh_need_notify_iotlb(&vq->vring) > 0)
				vringh_notify(&vq->vring);
			local_bh_enable();

			if (++reqs > 4) {
				reschedule = true;
				break;
			}
		}
	}
out:
	spin_unlock(&vdpasim->lock);

	if (reschedule)
		schedule_work(&vdpasim->work);
}

static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config)
{
	struct virtio_blk_config *blk_config = config;

	memset(config, 0, sizeof(struct virtio_blk_config));

	blk_config->capacity = cpu_to_vdpasim64(vdpasim, VDPASIM_BLK_CAPACITY);
	blk_config->size_max = cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_SIZE_MAX);
	blk_config->seg_max = cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_SEG_MAX);
	blk_config->num_queues = cpu_to_vdpasim16(vdpasim, VDPASIM_BLK_VQ_NUM);
	blk_config->min_io_size = cpu_to_vdpasim16(vdpasim, 1);
	blk_config->opt_io_size = cpu_to_vdpasim32(vdpasim, 1);
	blk_config->blk_size = cpu_to_vdpasim32(vdpasim, SECTOR_SIZE);
	/* VIRTIO_BLK_F_DISCARD */
	blk_config->discard_sector_alignment =
		cpu_to_vdpasim32(vdpasim, SECTOR_SIZE);
	blk_config->max_discard_sectors =
		cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_DWZ_MAX_SECTORS);
	blk_config->max_discard_seg = cpu_to_vdpasim32(vdpasim, 1);
	/* VIRTIO_BLK_F_WRITE_ZEROES */
	blk_config->max_write_zeroes_sectors =
		cpu_to_vdpasim32(vdpasim, VDPASIM_BLK_DWZ_MAX_SECTORS);
	blk_config->max_write_zeroes_seg = cpu_to_vdpasim32(vdpasim, 1);

}

static void vdpasim_blk_mgmtdev_release(struct device *dev)
{
}

static struct device vdpasim_blk_mgmtdev = {
	.init_name = "vdpasim_blk",
	.release = vdpasim_blk_mgmtdev_release,
};

static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
			       const struct vdpa_dev_set_config *config)
{
	struct vdpasim_dev_attr dev_attr = {};
	struct vdpasim *simdev;
	int ret;

	dev_attr.mgmt_dev = mdev;
	dev_attr.name = name;
	dev_attr.id = VIRTIO_ID_BLOCK;
	dev_attr.supported_features = VDPASIM_BLK_FEATURES;
	dev_attr.nvqs = VDPASIM_BLK_VQ_NUM;
	dev_attr.ngroups = VDPASIM_BLK_GROUP_NUM;
	dev_attr.nas = VDPASIM_BLK_AS_NUM;
	dev_attr.alloc_size = sizeof(struct vdpasim);
	dev_attr.config_size = sizeof(struct virtio_blk_config);
	dev_attr.get_config = vdpasim_blk_get_config;
	dev_attr.work_fn = vdpasim_blk_work;
	dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT;

	simdev = vdpasim_create(&dev_attr, config);
	if (IS_ERR(simdev))
		return PTR_ERR(simdev);

	ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_BLK_VQ_NUM);
	if (ret)
		goto put_dev;

	return 0;

put_dev:
	put_device(&simdev->vdpa.dev);
	return ret;
}

static void vdpasim_blk_dev_del(struct vdpa_mgmt_dev *mdev,
				struct vdpa_device *dev)
{
	struct vdpasim *simdev = container_of(dev, struct vdpasim, vdpa);

	_vdpa_unregister_device(&simdev->vdpa);
}

static const struct vdpa_mgmtdev_ops vdpasim_blk_mgmtdev_ops = {
	.dev_add = vdpasim_blk_dev_add,
	.dev_del = vdpasim_blk_dev_del
};

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static struct vdpa_mgmt_dev mgmt_dev = {
	.device = &vdpasim_blk_mgmtdev,
	.id_table = id_table,
	.ops = &vdpasim_blk_mgmtdev_ops,
};

static int __init vdpasim_blk_init(void)
{
	int ret;

	ret = device_register(&vdpasim_blk_mgmtdev);
	if (ret) {
		put_device(&vdpasim_blk_mgmtdev);
		return ret;
	}

	ret = vdpa_mgmtdev_register(&mgmt_dev);
	if (ret)
		goto parent_err;

	return 0;

parent_err:
	device_unregister(&vdpasim_blk_mgmtdev);
	return ret;
}

static void __exit vdpasim_blk_exit(void)
{
	vdpa_mgmtdev_unregister(&mgmt_dev);
	device_unregister(&vdpasim_blk_mgmtdev);
}

module_init(vdpasim_blk_init)
module_exit(vdpasim_blk_exit)

MODULE_VERSION(DRV_VERSION);
MODULE_LICENSE(DRV_LICENSE);
MODULE_AUTHOR(DRV_AUTHOR);
MODULE_DESCRIPTION(DRV_DESC);