summaryrefslogtreecommitdiff
path: root/drivers/net/virtio/virtio_user_ethdev.c
blob: 129c2b9efb9fb52f54e0645b4a601bba05089df9 (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
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2016 Intel Corporation
 */

#include <stdint.h>
#include <sys/types.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/socket.h>

#include <rte_malloc.h>
#include <rte_kvargs.h>
#include <rte_ethdev_vdev.h>
#include <rte_bus_vdev.h>
#include <rte_alarm.h>

#include "virtio_ethdev.h"
#include "virtio_logs.h"
#include "virtio_pci.h"
#include "virtqueue.h"
#include "virtio_rxtx.h"
#include "virtio_user/virtio_user_dev.h"

#define virtio_user_get_dev(hw) \
	((struct virtio_user_dev *)(hw)->virtio_user_dev)

static int
virtio_user_server_reconnect(struct virtio_user_dev *dev)
{
	int ret;
	int connectfd;
	struct rte_eth_dev *eth_dev = &rte_eth_devices[dev->port_id];

	connectfd = accept(dev->listenfd, NULL, NULL);
	if (connectfd < 0)
		return -1;

	dev->vhostfd = connectfd;
	if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
				   &dev->device_features) < 0) {
		PMD_INIT_LOG(ERR, "get_features failed: %s",
			     strerror(errno));
		return -1;
	}

	dev->device_features |= dev->frontend_features;

	/* umask vhost-user unsupported features */
	dev->device_features &= ~(dev->unsupported_features);

	dev->features &= dev->device_features;

	ret = virtio_user_start_device(dev);
	if (ret < 0)
		return -1;

	if (dev->queue_pairs > 1) {
		ret = virtio_user_handle_mq(dev, dev->queue_pairs);
		if (ret != 0) {
			PMD_INIT_LOG(ERR, "Fails to enable multi-queue pairs!");
			return -1;
		}
	}
	if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) {
		if (rte_intr_disable(eth_dev->intr_handle) < 0) {
			PMD_DRV_LOG(ERR, "interrupt disable failed");
			return -1;
		}
		rte_intr_callback_unregister(eth_dev->intr_handle,
					     virtio_interrupt_handler,
					     eth_dev);
		eth_dev->intr_handle->fd = connectfd;
		rte_intr_callback_register(eth_dev->intr_handle,
					   virtio_interrupt_handler, eth_dev);

		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
			PMD_DRV_LOG(ERR, "interrupt enable failed");
			return -1;
		}
	}
	PMD_INIT_LOG(NOTICE, "server mode virtio-user reconnection succeeds!");
	return 0;
}

static void
virtio_user_delayed_handler(void *param)
{
	struct virtio_hw *hw = (struct virtio_hw *)param;
	struct rte_eth_dev *eth_dev = &rte_eth_devices[hw->port_id];
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (rte_intr_disable(eth_dev->intr_handle) < 0) {
		PMD_DRV_LOG(ERR, "interrupt disable failed");
		return;
	}
	rte_intr_callback_unregister(eth_dev->intr_handle,
				     virtio_interrupt_handler, eth_dev);
	if (dev->is_server) {
		if (dev->vhostfd >= 0) {
			close(dev->vhostfd);
			dev->vhostfd = -1;
		}
		eth_dev->intr_handle->fd = dev->listenfd;
		rte_intr_callback_register(eth_dev->intr_handle,
					   virtio_interrupt_handler, eth_dev);
		if (rte_intr_enable(eth_dev->intr_handle) < 0) {
			PMD_DRV_LOG(ERR, "interrupt enable failed");
			return;
		}
	}
}

static void
virtio_user_read_dev_config(struct virtio_hw *hw, size_t offset,
		     void *dst, int length)
{
	int i;
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (offset == offsetof(struct virtio_net_config, mac) &&
	    length == ETHER_ADDR_LEN) {
		for (i = 0; i < ETHER_ADDR_LEN; ++i)
			((uint8_t *)dst)[i] = dev->mac_addr[i];
		return;
	}

	if (offset == offsetof(struct virtio_net_config, status)) {
		char buf[128];

		if (dev->vhostfd >= 0) {
			int r;
			int flags;

			flags = fcntl(dev->vhostfd, F_GETFL);
			if (fcntl(dev->vhostfd, F_SETFL,
					flags | O_NONBLOCK) == -1) {
				PMD_DRV_LOG(ERR, "error setting O_NONBLOCK flag");
				return;
			}
			r = recv(dev->vhostfd, buf, 128, MSG_PEEK);
			if (r == 0 || (r < 0 && errno != EAGAIN)) {
				dev->status &= (~VIRTIO_NET_S_LINK_UP);
				PMD_DRV_LOG(ERR, "virtio-user port %u is down",
					    hw->port_id);

				/* This function could be called in the process
				 * of interrupt handling, callback cannot be
				 * unregistered here, set an alarm to do it.
				 */
				rte_eal_alarm_set(1,
						  virtio_user_delayed_handler,
						  (void *)hw);
			} else {
				dev->status |= VIRTIO_NET_S_LINK_UP;
			}
			if (fcntl(dev->vhostfd, F_SETFL,
					flags & ~O_NONBLOCK) == -1) {
				PMD_DRV_LOG(ERR, "error clearing O_NONBLOCK flag");
				return;
			}
		} else if (dev->is_server) {
			dev->status &= (~VIRTIO_NET_S_LINK_UP);
			if (virtio_user_server_reconnect(dev) >= 0)
				dev->status |= VIRTIO_NET_S_LINK_UP;
		}

		*(uint16_t *)dst = dev->status;
	}

	if (offset == offsetof(struct virtio_net_config, max_virtqueue_pairs))
		*(uint16_t *)dst = dev->max_queue_pairs;
}

static void
virtio_user_write_dev_config(struct virtio_hw *hw, size_t offset,
		      const void *src, int length)
{
	int i;
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if ((offset == offsetof(struct virtio_net_config, mac)) &&
	    (length == ETHER_ADDR_LEN))
		for (i = 0; i < ETHER_ADDR_LEN; ++i)
			dev->mac_addr[i] = ((const uint8_t *)src)[i];
	else
		PMD_DRV_LOG(ERR, "not supported offset=%zu, len=%d",
			    offset, length);
}

static void
virtio_user_reset(struct virtio_hw *hw)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (dev->status & VIRTIO_CONFIG_STATUS_DRIVER_OK)
		virtio_user_stop_device(dev);
}

static void
virtio_user_set_status(struct virtio_hw *hw, uint8_t status)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (status & VIRTIO_CONFIG_STATUS_DRIVER_OK)
		virtio_user_start_device(dev);
	else if (status == VIRTIO_CONFIG_STATUS_RESET)
		virtio_user_reset(hw);
	dev->status = status;
}

static uint8_t
virtio_user_get_status(struct virtio_hw *hw)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	return dev->status;
}

static uint64_t
virtio_user_get_features(struct virtio_hw *hw)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	/* unmask feature bits defined in vhost user protocol */
	return dev->device_features & VIRTIO_PMD_SUPPORTED_GUEST_FEATURES;
}

static void
virtio_user_set_features(struct virtio_hw *hw, uint64_t features)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	dev->features = features & dev->device_features;
}

static uint8_t
virtio_user_get_isr(struct virtio_hw *hw __rte_unused)
{
	/* rxq interrupts and config interrupt are separated in virtio-user,
	 * here we only report config change.
	 */
	return VIRTIO_PCI_ISR_CONFIG;
}

static uint16_t
virtio_user_set_config_irq(struct virtio_hw *hw __rte_unused,
		    uint16_t vec __rte_unused)
{
	return 0;
}

static uint16_t
virtio_user_set_queue_irq(struct virtio_hw *hw __rte_unused,
			  struct virtqueue *vq __rte_unused,
			  uint16_t vec)
{
	/* pretend we have done that */
	return vec;
}

/* This function is to get the queue size, aka, number of descs, of a specified
 * queue. Different with the VHOST_USER_GET_QUEUE_NUM, which is used to get the
 * max supported queues.
 */
static uint16_t
virtio_user_get_queue_num(struct virtio_hw *hw, uint16_t queue_id __rte_unused)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	/* Currently, each queue has same queue size */
	return dev->queue_size;
}

static void
virtio_user_setup_queue_packed(struct virtqueue *vq,
			       struct virtio_user_dev *dev)
{
	uint16_t queue_idx = vq->vq_queue_index;
	struct vring_packed *vring;
	uint64_t desc_addr;
	uint64_t avail_addr;
	uint64_t used_addr;
	uint16_t i;

	vring  = &dev->packed_vrings[queue_idx];
	desc_addr = (uintptr_t)vq->vq_ring_virt_mem;
	avail_addr = desc_addr + vq->vq_nentries *
		sizeof(struct vring_packed_desc);
	used_addr = RTE_ALIGN_CEIL(avail_addr +
			   sizeof(struct vring_packed_desc_event),
			   VIRTIO_PCI_VRING_ALIGN);
	vring->num = vq->vq_nentries;
	vring->desc = (void *)(uintptr_t)desc_addr;
	vring->driver = (void *)(uintptr_t)avail_addr;
	vring->device = (void *)(uintptr_t)used_addr;
	dev->packed_queues[queue_idx].avail_wrap_counter = true;
	dev->packed_queues[queue_idx].used_wrap_counter = true;

	for (i = 0; i < vring->num; i++)
		vring->desc[i].flags = 0;
}

static void
virtio_user_setup_queue_split(struct virtqueue *vq, struct virtio_user_dev *dev)
{
	uint16_t queue_idx = vq->vq_queue_index;
	uint64_t desc_addr, avail_addr, used_addr;

	desc_addr = (uintptr_t)vq->vq_ring_virt_mem;
	avail_addr = desc_addr + vq->vq_nentries * sizeof(struct vring_desc);
	used_addr = RTE_ALIGN_CEIL(avail_addr + offsetof(struct vring_avail,
							 ring[vq->vq_nentries]),
				   VIRTIO_PCI_VRING_ALIGN);

	dev->vrings[queue_idx].num = vq->vq_nentries;
	dev->vrings[queue_idx].desc = (void *)(uintptr_t)desc_addr;
	dev->vrings[queue_idx].avail = (void *)(uintptr_t)avail_addr;
	dev->vrings[queue_idx].used = (void *)(uintptr_t)used_addr;
}

static int
virtio_user_setup_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (vtpci_packed_queue(hw))
		virtio_user_setup_queue_packed(vq, dev);
	else
		virtio_user_setup_queue_split(vq, dev);

	return 0;
}

static void
virtio_user_del_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	/* For legacy devices, write 0 to VIRTIO_PCI_QUEUE_PFN port, QEMU
	 * correspondingly stops the ioeventfds, and reset the status of
	 * the device.
	 * For modern devices, set queue desc, avail, used in PCI bar to 0,
	 * not see any more behavior in QEMU.
	 *
	 * Here we just care about what information to deliver to vhost-user
	 * or vhost-kernel. So we just close ioeventfd for now.
	 */
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	close(dev->callfds[vq->vq_queue_index]);
	close(dev->kickfds[vq->vq_queue_index]);
}

static void
virtio_user_notify_queue(struct virtio_hw *hw, struct virtqueue *vq)
{
	uint64_t buf = 1;
	struct virtio_user_dev *dev = virtio_user_get_dev(hw);

	if (hw->cvq && (hw->cvq->vq == vq)) {
		if (vtpci_packed_queue(vq->hw))
			virtio_user_handle_cq_packed(dev, vq->vq_queue_index);
		else
			virtio_user_handle_cq(dev, vq->vq_queue_index);
		return;
	}

	if (write(dev->kickfds[vq->vq_queue_index], &buf, sizeof(buf)) < 0)
		PMD_DRV_LOG(ERR, "failed to kick backend: %s",
			    strerror(errno));
}

const struct virtio_pci_ops virtio_user_ops = {
	.read_dev_cfg	= virtio_user_read_dev_config,
	.write_dev_cfg	= virtio_user_write_dev_config,
	.get_status	= virtio_user_get_status,
	.set_status	= virtio_user_set_status,
	.get_features	= virtio_user_get_features,
	.set_features	= virtio_user_set_features,
	.get_isr	= virtio_user_get_isr,
	.set_config_irq	= virtio_user_set_config_irq,
	.set_queue_irq	= virtio_user_set_queue_irq,
	.get_queue_num	= virtio_user_get_queue_num,
	.setup_queue	= virtio_user_setup_queue,
	.del_queue	= virtio_user_del_queue,
	.notify_queue	= virtio_user_notify_queue,
};

static const char *valid_args[] = {
#define VIRTIO_USER_ARG_QUEUES_NUM     "queues"
	VIRTIO_USER_ARG_QUEUES_NUM,
#define VIRTIO_USER_ARG_CQ_NUM         "cq"
	VIRTIO_USER_ARG_CQ_NUM,
#define VIRTIO_USER_ARG_MAC            "mac"
	VIRTIO_USER_ARG_MAC,
#define VIRTIO_USER_ARG_PATH           "path"
	VIRTIO_USER_ARG_PATH,
#define VIRTIO_USER_ARG_QUEUE_SIZE     "queue_size"
	VIRTIO_USER_ARG_QUEUE_SIZE,
#define VIRTIO_USER_ARG_INTERFACE_NAME "iface"
	VIRTIO_USER_ARG_INTERFACE_NAME,
#define VIRTIO_USER_ARG_SERVER_MODE    "server"
	VIRTIO_USER_ARG_SERVER_MODE,
#define VIRTIO_USER_ARG_MRG_RXBUF      "mrg_rxbuf"
	VIRTIO_USER_ARG_MRG_RXBUF,
#define VIRTIO_USER_ARG_IN_ORDER       "in_order"
	VIRTIO_USER_ARG_IN_ORDER,
#define VIRTIO_USER_ARG_PACKED_VQ      "packed_vq"
	VIRTIO_USER_ARG_PACKED_VQ,
	NULL
};

#define VIRTIO_USER_DEF_CQ_EN	0
#define VIRTIO_USER_DEF_Q_NUM	1
#define VIRTIO_USER_DEF_Q_SZ	256
#define VIRTIO_USER_DEF_SERVER_MODE	0

static int
get_string_arg(const char *key __rte_unused,
	       const char *value, void *extra_args)
{
	if (!value || !extra_args)
		return -EINVAL;

	*(char **)extra_args = strdup(value);

	if (!*(char **)extra_args)
		return -ENOMEM;

	return 0;
}

static int
get_integer_arg(const char *key __rte_unused,
		const char *value, void *extra_args)
{
	if (!value || !extra_args)
		return -EINVAL;

	*(uint64_t *)extra_args = strtoull(value, NULL, 0);

	return 0;
}

static struct rte_vdev_driver virtio_user_driver;

static struct rte_eth_dev *
virtio_user_eth_dev_alloc(struct rte_vdev_device *vdev)
{
	struct rte_eth_dev *eth_dev;
	struct rte_eth_dev_data *data;
	struct virtio_hw *hw;
	struct virtio_user_dev *dev;

	eth_dev = rte_eth_vdev_allocate(vdev, sizeof(*hw));
	if (!eth_dev) {
		PMD_INIT_LOG(ERR, "cannot alloc rte_eth_dev");
		return NULL;
	}

	data = eth_dev->data;
	hw = eth_dev->data->dev_private;

	dev = rte_zmalloc(NULL, sizeof(*dev), 0);
	if (!dev) {
		PMD_INIT_LOG(ERR, "malloc virtio_user_dev failed");
		rte_eth_dev_release_port(eth_dev);
		return NULL;
	}

	hw->port_id = data->port_id;
	dev->port_id = data->port_id;
	virtio_hw_internal[hw->port_id].vtpci_ops = &virtio_user_ops;
	/*
	 * MSIX is required to enable LSC (see virtio_init_device).
	 * Here just pretend that we support msix.
	 */
	hw->use_msix = 1;
	hw->modern   = 0;
	hw->use_simple_rx = 0;
	hw->use_inorder_rx = 0;
	hw->use_inorder_tx = 0;
	hw->virtio_user_dev = dev;
	return eth_dev;
}

static void
virtio_user_eth_dev_free(struct rte_eth_dev *eth_dev)
{
	struct rte_eth_dev_data *data = eth_dev->data;
	struct virtio_hw *hw = data->dev_private;

	rte_free(hw->virtio_user_dev);
	rte_eth_dev_release_port(eth_dev);
}

/* Dev initialization routine. Invoked once for each virtio vdev at
 * EAL init time, see rte_bus_probe().
 * Returns 0 on success.
 */
static int
virtio_user_pmd_probe(struct rte_vdev_device *dev)
{
	struct rte_kvargs *kvlist = NULL;
	struct rte_eth_dev *eth_dev;
	struct virtio_hw *hw;
	uint64_t queues = VIRTIO_USER_DEF_Q_NUM;
	uint64_t cq = VIRTIO_USER_DEF_CQ_EN;
	uint64_t queue_size = VIRTIO_USER_DEF_Q_SZ;
	uint64_t server_mode = VIRTIO_USER_DEF_SERVER_MODE;
	uint64_t mrg_rxbuf = 1;
	uint64_t in_order = 1;
	uint64_t packed_vq = 0;
	char *path = NULL;
	char *ifname = NULL;
	char *mac_addr = NULL;
	int ret = -1;

	if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
		const char *name = rte_vdev_device_name(dev);
		eth_dev = rte_eth_dev_attach_secondary(name);
		if (!eth_dev) {
			RTE_LOG(ERR, PMD, "Failed to probe %s\n", name);
			return -1;
		}

		if (eth_virtio_dev_init(eth_dev) < 0) {
			PMD_INIT_LOG(ERR, "eth_virtio_dev_init fails");
			rte_eth_dev_release_port(eth_dev);
			return -1;
		}

		eth_dev->dev_ops = &virtio_user_secondary_eth_dev_ops;
		eth_dev->device = &dev->device;
		rte_eth_dev_probing_finish(eth_dev);
		return 0;
	}

	kvlist = rte_kvargs_parse(rte_vdev_device_args(dev), valid_args);
	if (!kvlist) {
		PMD_INIT_LOG(ERR, "error when parsing param");
		goto end;
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_PATH) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_PATH,
				       &get_string_arg, &path) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_PATH);
			goto end;
		}
	} else {
		PMD_INIT_LOG(ERR, "arg %s is mandatory for virtio_user",
			     VIRTIO_USER_ARG_PATH);
		goto end;
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_INTERFACE_NAME) == 1) {
		if (is_vhost_user_by_type(path)) {
			PMD_INIT_LOG(ERR,
				"arg %s applies only to vhost-kernel backend",
				VIRTIO_USER_ARG_INTERFACE_NAME);
			goto end;
		}

		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_INTERFACE_NAME,
				       &get_string_arg, &ifname) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_INTERFACE_NAME);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_MAC) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_MAC,
				       &get_string_arg, &mac_addr) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_MAC);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_QUEUE_SIZE) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_QUEUE_SIZE,
				       &get_integer_arg, &queue_size) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_QUEUE_SIZE);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_QUEUES_NUM) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_QUEUES_NUM,
				       &get_integer_arg, &queues) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_QUEUES_NUM);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_SERVER_MODE) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_SERVER_MODE,
				       &get_integer_arg, &server_mode) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_SERVER_MODE);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_CQ_NUM) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_CQ_NUM,
				       &get_integer_arg, &cq) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_CQ_NUM);
			goto end;
		}
	} else if (queues > 1) {
		cq = 1;
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_PACKED_VQ) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_PACKED_VQ,
				       &get_integer_arg, &packed_vq) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_PACKED_VQ);
			goto end;
		}
	}

	if (queues > 1 && cq == 0) {
		PMD_INIT_LOG(ERR, "multi-q requires ctrl-q");
		goto end;
	}

	if (queues > VIRTIO_MAX_VIRTQUEUE_PAIRS) {
		PMD_INIT_LOG(ERR, "arg %s %" PRIu64 " exceeds the limit %u",
			VIRTIO_USER_ARG_QUEUES_NUM, queues,
			VIRTIO_MAX_VIRTQUEUE_PAIRS);
		goto end;
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_MRG_RXBUF) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_MRG_RXBUF,
				       &get_integer_arg, &mrg_rxbuf) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_MRG_RXBUF);
			goto end;
		}
	}

	if (rte_kvargs_count(kvlist, VIRTIO_USER_ARG_IN_ORDER) == 1) {
		if (rte_kvargs_process(kvlist, VIRTIO_USER_ARG_IN_ORDER,
				       &get_integer_arg, &in_order) < 0) {
			PMD_INIT_LOG(ERR, "error to parse %s",
				     VIRTIO_USER_ARG_IN_ORDER);
			goto end;
		}
	}

	eth_dev = virtio_user_eth_dev_alloc(dev);
	if (!eth_dev) {
		PMD_INIT_LOG(ERR, "virtio_user fails to alloc device");
		goto end;
	}

	hw = eth_dev->data->dev_private;
	if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq,
			 queue_size, mac_addr, &ifname, server_mode,
			 mrg_rxbuf, in_order, packed_vq) < 0) {
		PMD_INIT_LOG(ERR, "virtio_user_dev_init fails");
		virtio_user_eth_dev_free(eth_dev);
		goto end;
	}

	/* previously called by rte_pci_probe() for physical dev */
	if (eth_virtio_dev_init(eth_dev) < 0) {
		PMD_INIT_LOG(ERR, "eth_virtio_dev_init fails");
		virtio_user_eth_dev_free(eth_dev);
		goto end;
	}

	rte_eth_dev_probing_finish(eth_dev);
	ret = 0;

end:
	if (kvlist)
		rte_kvargs_free(kvlist);
	if (path)
		free(path);
	if (mac_addr)
		free(mac_addr);
	if (ifname)
		free(ifname);
	return ret;
}

static int
virtio_user_pmd_remove(struct rte_vdev_device *vdev)
{
	const char *name;
	struct rte_eth_dev *eth_dev;
	struct virtio_hw *hw;
	struct virtio_user_dev *dev;

	if (!vdev)
		return -EINVAL;

	name = rte_vdev_device_name(vdev);
	PMD_DRV_LOG(INFO, "Un-Initializing %s", name);
	eth_dev = rte_eth_dev_allocated(name);
	if (!eth_dev)
		return -ENODEV;

	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
		return rte_eth_dev_release_port(eth_dev);

	/* make sure the device is stopped, queues freed */
	rte_eth_dev_close(eth_dev->data->port_id);

	hw = eth_dev->data->dev_private;
	dev = hw->virtio_user_dev;
	virtio_user_dev_uninit(dev);

	rte_eth_dev_release_port(eth_dev);

	return 0;
}

static struct rte_vdev_driver virtio_user_driver = {
	.probe = virtio_user_pmd_probe,
	.remove = virtio_user_pmd_remove,
};

RTE_PMD_REGISTER_VDEV(net_virtio_user, virtio_user_driver);
RTE_PMD_REGISTER_ALIAS(net_virtio_user, virtio_user);
RTE_PMD_REGISTER_PARAM_STRING(net_virtio_user,
	"path=<path> "
	"mac=<mac addr> "
	"cq=<int> "
	"queue_size=<int> "
	"queues=<int> "
	"iface=<string> "
	"server=<0|1> "
	"mrg_rxbuf=<0|1> "
	"in_order=<0|1> "
	"packed_vq=<0|1>");