summaryrefslogtreecommitdiff
path: root/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
blob: 862f405362de27dc3ca88eefa3d3ac334a154fa5 (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
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VDPA simulator for networking device.
 *
 * Copyright (c) 2020, Red Hat Inc. All rights reserved.
 *     Author: Jason Wang <jasowang@redhat.com>
 *
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/etherdevice.h>
#include <linux/vringh.h>
#include <linux/vdpa.h>
#include <net/netlink.h>
#include <uapi/linux/virtio_net.h>
#include <uapi/linux/vdpa.h>

#include "vdpa_sim.h"

#define DRV_VERSION  "0.1"
#define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
#define DRV_DESC     "vDPA Device Simulator for networking device"
#define DRV_LICENSE  "GPL v2"

#define VDPASIM_NET_FEATURES	(VDPASIM_FEATURES | \
				 (1ULL << VIRTIO_NET_F_MAC) | \
				 (1ULL << VIRTIO_NET_F_STATUS) | \
				 (1ULL << VIRTIO_NET_F_MTU) | \
				 (1ULL << VIRTIO_NET_F_CTRL_VQ) | \
				 (1ULL << VIRTIO_NET_F_CTRL_MAC_ADDR))

/* 3 virtqueues, 2 address spaces, 2 virtqueue groups */
#define VDPASIM_NET_VQ_NUM	3
#define VDPASIM_NET_AS_NUM	2
#define VDPASIM_NET_GROUP_NUM	2

struct vdpasim_dataq_stats {
	struct u64_stats_sync syncp;
	u64 pkts;
	u64 bytes;
	u64 drops;
	u64 errors;
	u64 overruns;
};

struct vdpasim_cq_stats {
	struct u64_stats_sync syncp;
	u64 requests;
	u64 successes;
	u64 errors;
};

struct vdpasim_net{
	struct vdpasim vdpasim;
	struct vdpasim_dataq_stats tx_stats;
	struct vdpasim_dataq_stats rx_stats;
	struct vdpasim_cq_stats cq_stats;
};

static struct vdpasim_net *sim_to_net(struct vdpasim *vdpasim)
{
	return container_of(vdpasim, struct vdpasim_net, vdpasim);
}

static void vdpasim_net_complete(struct vdpasim_virtqueue *vq, size_t len)
{
	/* Make sure data is wrote before advancing index */
	smp_wmb();

	vringh_complete_iotlb(&vq->vring, vq->head, len);

	/* 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();
}

static bool receive_filter(struct vdpasim *vdpasim, size_t len)
{
	bool modern = vdpasim->features & (1ULL << VIRTIO_F_VERSION_1);
	size_t hdr_len = modern ? sizeof(struct virtio_net_hdr_v1) :
				  sizeof(struct virtio_net_hdr);
	struct virtio_net_config *vio_config = vdpasim->config;

	if (len < ETH_ALEN + hdr_len)
		return false;

	if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
	    is_multicast_ether_addr(vdpasim->buffer + hdr_len))
		return true;
	if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
		return true;

	return false;
}

static virtio_net_ctrl_ack vdpasim_handle_ctrl_mac(struct vdpasim *vdpasim,
						   u8 cmd)
{
	struct virtio_net_config *vio_config = vdpasim->config;
	struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2];
	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
	size_t read;

	switch (cmd) {
	case VIRTIO_NET_CTRL_MAC_ADDR_SET:
		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->in_iov,
					     vio_config->mac, ETH_ALEN);
		if (read == ETH_ALEN)
			status = VIRTIO_NET_OK;
		break;
	default:
		break;
	}

	return status;
}

static void vdpasim_handle_cvq(struct vdpasim *vdpasim)
{
	struct vdpasim_virtqueue *cvq = &vdpasim->vqs[2];
	struct vdpasim_net *net = sim_to_net(vdpasim);
	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
	struct virtio_net_ctrl_hdr ctrl;
	size_t read, write;
	u64 requests = 0, errors = 0, successes = 0;
	int err;

	if (!(vdpasim->features & (1ULL << VIRTIO_NET_F_CTRL_VQ)))
		return;

	if (!cvq->ready)
		return;

	while (true) {
		err = vringh_getdesc_iotlb(&cvq->vring, &cvq->in_iov,
					   &cvq->out_iov,
					   &cvq->head, GFP_ATOMIC);
		if (err <= 0)
			break;

		++requests;
		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->in_iov, &ctrl,
					     sizeof(ctrl));
		if (read != sizeof(ctrl)) {
			++errors;
			break;
		}

		switch (ctrl.class) {
		case VIRTIO_NET_CTRL_MAC:
			status = vdpasim_handle_ctrl_mac(vdpasim, ctrl.cmd);
			break;
		default:
			break;
		}

		if (status == VIRTIO_NET_OK)
			++successes;
		else
			++errors;

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

		write = vringh_iov_push_iotlb(&cvq->vring, &cvq->out_iov,
					      &status, sizeof(status));
		vringh_complete_iotlb(&cvq->vring, cvq->head, write);
		vringh_kiov_cleanup(&cvq->in_iov);
		vringh_kiov_cleanup(&cvq->out_iov);

		/* Make sure used is visible before rasing the interrupt. */
		smp_wmb();

		local_bh_disable();
		if (cvq->cb)
			cvq->cb(cvq->private);
		local_bh_enable();
	}

	u64_stats_update_begin(&net->cq_stats.syncp);
	net->cq_stats.requests += requests;
	net->cq_stats.errors += errors;
	net->cq_stats.successes += successes;
	u64_stats_update_end(&net->cq_stats.syncp);
}

static void vdpasim_net_work(struct work_struct *work)
{
	struct vdpasim *vdpasim = container_of(work, struct vdpasim, work);
	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
	struct vdpasim_net *net = sim_to_net(vdpasim);
	ssize_t read, write;
	u64 tx_pkts = 0, rx_pkts = 0, tx_bytes = 0, rx_bytes = 0;
	u64 rx_drops = 0, rx_overruns = 0, rx_errors = 0, tx_errors = 0;
	int err;

	spin_lock(&vdpasim->lock);

	if (!vdpasim->running)
		goto out;

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

	vdpasim_handle_cvq(vdpasim);

	if (!txq->ready || !rxq->ready)
		goto out;

	while (true) {
		err = vringh_getdesc_iotlb(&txq->vring, &txq->out_iov, NULL,
					   &txq->head, GFP_ATOMIC);
		if (err <= 0) {
			if (err)
				++tx_errors;
			break;
		}

		++tx_pkts;
		read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov,
					     vdpasim->buffer,
					     PAGE_SIZE);

		tx_bytes += read;

		if (!receive_filter(vdpasim, read)) {
			++rx_drops;
			vdpasim_net_complete(txq, 0);
			continue;
		}

		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->in_iov,
					   &rxq->head, GFP_ATOMIC);
		if (err <= 0) {
			++rx_overruns;
			vdpasim_net_complete(txq, 0);
			break;
		}

		write = vringh_iov_push_iotlb(&rxq->vring, &rxq->in_iov,
					      vdpasim->buffer, read);
		if (write <= 0) {
			++rx_errors;
			break;
		}

		++rx_pkts;
		rx_bytes += write;

		vdpasim_net_complete(txq, 0);
		vdpasim_net_complete(rxq, write);

		if (tx_pkts > 4) {
			schedule_work(&vdpasim->work);
			goto out;
		}
	}

out:
	spin_unlock(&vdpasim->lock);

	u64_stats_update_begin(&net->tx_stats.syncp);
	net->tx_stats.pkts += tx_pkts;
	net->tx_stats.bytes += tx_bytes;
	net->tx_stats.errors += tx_errors;
	u64_stats_update_end(&net->tx_stats.syncp);

	u64_stats_update_begin(&net->rx_stats.syncp);
	net->rx_stats.pkts += rx_pkts;
	net->rx_stats.bytes += rx_bytes;
	net->rx_stats.drops += rx_drops;
	net->rx_stats.errors += rx_errors;
	net->rx_stats.overruns += rx_overruns;
	u64_stats_update_end(&net->rx_stats.syncp);
}

static int vdpasim_net_get_stats(struct vdpasim *vdpasim, u16 idx,
				 struct sk_buff *msg,
				 struct netlink_ext_ack *extack)
{
	struct vdpasim_net *net = sim_to_net(vdpasim);
	u64 rx_pkts, rx_bytes, rx_errors, rx_overruns, rx_drops;
	u64 tx_pkts, tx_bytes, tx_errors, tx_drops;
	u64 cq_requests, cq_successes, cq_errors;
	unsigned int start;
	int err = -EMSGSIZE;

	switch(idx) {
	case 0:
		do {
			start = u64_stats_fetch_begin(&net->rx_stats.syncp);
			rx_pkts = net->rx_stats.pkts;
			rx_bytes = net->rx_stats.bytes;
			rx_errors = net->rx_stats.errors;
			rx_overruns = net->rx_stats.overruns;
			rx_drops = net->rx_stats.drops;
		} while (u64_stats_fetch_retry(&net->rx_stats.syncp, start));

		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
					"rx packets"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      rx_pkts, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "rx bytes"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      rx_bytes, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "rx errors"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      rx_errors, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "rx overruns"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      rx_overruns, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "rx drops"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      rx_drops, VDPA_ATTR_PAD))
			break;
		err = 0;
		break;
	case 1:
		do {
			start = u64_stats_fetch_begin(&net->tx_stats.syncp);
			tx_pkts = net->tx_stats.pkts;
			tx_bytes = net->tx_stats.bytes;
			tx_errors = net->tx_stats.errors;
			tx_drops = net->tx_stats.drops;
		} while (u64_stats_fetch_retry(&net->tx_stats.syncp, start));

		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "tx packets"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      tx_pkts, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "tx bytes"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      tx_bytes, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "tx errors"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      tx_errors, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "tx drops"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      tx_drops, VDPA_ATTR_PAD))
			break;
		err = 0;
		break;
	case 2:
		do {
			start = u64_stats_fetch_begin(&net->cq_stats.syncp);
			cq_requests = net->cq_stats.requests;
			cq_successes = net->cq_stats.successes;
			cq_errors = net->cq_stats.errors;
		} while (u64_stats_fetch_retry(&net->cq_stats.syncp, start));

		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "cvq requests"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      cq_requests, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "cvq successes"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      cq_successes, VDPA_ATTR_PAD))
			break;
		if (nla_put_string(msg, VDPA_ATTR_DEV_VENDOR_ATTR_NAME,
				  "cvq errors"))
			break;
		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,
				      cq_errors, VDPA_ATTR_PAD))
			break;
		err = 0;
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err;
}

static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
{
	struct virtio_net_config *net_config = config;

	net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
}

static void vdpasim_net_setup_config(struct vdpasim *vdpasim,
				     const struct vdpa_dev_set_config *config)
{
	struct virtio_net_config *vio_config = vdpasim->config;

	if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR))
		memcpy(vio_config->mac, config->net.mac, ETH_ALEN);
	if (config->mask & (1 << VDPA_ATTR_DEV_NET_CFG_MTU))
		vio_config->mtu = cpu_to_vdpasim16(vdpasim, config->net.mtu);
	else
		/* Setup default MTU to be 1500 */
		vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
}

static void vdpasim_net_mgmtdev_release(struct device *dev)
{
}

static struct device vdpasim_net_mgmtdev = {
	.init_name = "vdpasim_net",
	.release = vdpasim_net_mgmtdev_release,
};

static int vdpasim_net_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_net *net;
	struct vdpasim *simdev;
	int ret;

	dev_attr.mgmt_dev = mdev;
	dev_attr.name = name;
	dev_attr.id = VIRTIO_ID_NET;
	dev_attr.supported_features = VDPASIM_NET_FEATURES;
	dev_attr.nvqs = VDPASIM_NET_VQ_NUM;
	dev_attr.ngroups = VDPASIM_NET_GROUP_NUM;
	dev_attr.nas = VDPASIM_NET_AS_NUM;
	dev_attr.alloc_size = sizeof(struct vdpasim_net);
	dev_attr.config_size = sizeof(struct virtio_net_config);
	dev_attr.get_config = vdpasim_net_get_config;
	dev_attr.work_fn = vdpasim_net_work;
	dev_attr.get_stats = vdpasim_net_get_stats;
	dev_attr.buffer_size = PAGE_SIZE;

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

	vdpasim_net_setup_config(simdev, config);

	ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM);
	if (ret)
		goto reg_err;

	net = sim_to_net(simdev);

	u64_stats_init(&net->tx_stats.syncp);
	u64_stats_init(&net->rx_stats.syncp);
	u64_stats_init(&net->cq_stats.syncp);

	return 0;

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

static void vdpasim_net_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_net_mgmtdev_ops = {
	.dev_add = vdpasim_net_dev_add,
	.dev_del = vdpasim_net_dev_del
};

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

static struct vdpa_mgmt_dev mgmt_dev = {
	.device = &vdpasim_net_mgmtdev,
	.id_table = id_table,
	.ops = &vdpasim_net_mgmtdev_ops,
	.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
			     1 << VDPA_ATTR_DEV_NET_CFG_MTU |
		             1 << VDPA_ATTR_DEV_FEATURES),
	.max_supported_vqs = VDPASIM_NET_VQ_NUM,
	.supported_features = VDPASIM_NET_FEATURES,
};

static int __init vdpasim_net_init(void)
{
	int ret;

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

	ret = vdpa_mgmtdev_register(&mgmt_dev);
	if (ret)
		goto parent_err;
	return 0;

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

static void __exit vdpasim_net_exit(void)
{
	vdpa_mgmtdev_unregister(&mgmt_dev);
	device_unregister(&vdpasim_net_mgmtdev);
}

module_init(vdpasim_net_init);
module_exit(vdpasim_net_exit);

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