summaryrefslogtreecommitdiffstats
path: root/lib/librte_vhost/virtio_net.c
blob: 337470d64ad3875722e3934a940c217890e20dea (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
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdint.h>
#include <stdbool.h>
#include <linux/virtio_net.h>

#include <rte_mbuf.h>
#include <rte_memcpy.h>
#include <rte_ether.h>
#include <rte_ip.h>
#include <rte_virtio_net.h>
#include <rte_tcp.h>
#include <rte_udp.h>
#include <rte_sctp.h>
#include <rte_arp.h>

#include "vhost.h"

#define MAX_PKT_BURST 32
#define VHOST_LOG_PAGE	4096

static inline void __attribute__((always_inline))
vhost_log_page(uint8_t *log_base, uint64_t page)
{
	log_base[page / 8] |= 1 << (page % 8);
}

static inline void __attribute__((always_inline))
vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
{
	uint64_t page;

	if (likely(((dev->features & (1ULL << VHOST_F_LOG_ALL)) == 0) ||
		   !dev->log_base || !len))
		return;

	if (unlikely(dev->log_size <= ((addr + len - 1) / VHOST_LOG_PAGE / 8)))
		return;

	/* To make sure guest memory updates are committed before logging */
	rte_smp_wmb();

	page = addr / VHOST_LOG_PAGE;
	while (page * VHOST_LOG_PAGE < addr + len) {
		vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
		page += 1;
	}
}

static inline void __attribute__((always_inline))
vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
		     uint64_t offset, uint64_t len)
{
	vhost_log_write(dev, vq->log_guest_addr + offset, len);
}

static bool
is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t qp_nb)
{
	return (is_tx ^ (idx & 1)) == 0 && idx < qp_nb * VIRTIO_QNUM;
}

static inline void __attribute__((always_inline))
do_flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
			  uint16_t to, uint16_t from, uint16_t size)
{
	rte_memcpy(&vq->used->ring[to],
			&vq->shadow_used_ring[from],
			size * sizeof(struct vring_used_elem));
	vhost_log_used_vring(dev, vq,
			offsetof(struct vring_used, ring[to]),
			size * sizeof(struct vring_used_elem));
}

static inline void __attribute__((always_inline))
flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	uint16_t used_idx = vq->last_used_idx & (vq->size - 1);

	if (used_idx + vq->shadow_used_idx <= vq->size) {
		do_flush_shadow_used_ring(dev, vq, used_idx, 0,
					  vq->shadow_used_idx);
	} else {
		uint16_t size;

		/* update used ring interval [used_idx, vq->size] */
		size = vq->size - used_idx;
		do_flush_shadow_used_ring(dev, vq, used_idx, 0, size);

		/* update the left half used ring interval [0, left_size] */
		do_flush_shadow_used_ring(dev, vq, 0, size,
					  vq->shadow_used_idx - size);
	}
	vq->last_used_idx += vq->shadow_used_idx;

	rte_smp_wmb();

	*(volatile uint16_t *)&vq->used->idx += vq->shadow_used_idx;
	vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
		sizeof(vq->used->idx));
}

static inline void __attribute__((always_inline))
update_shadow_used_ring(struct vhost_virtqueue *vq,
			 uint16_t desc_idx, uint16_t len)
{
	uint16_t i = vq->shadow_used_idx++;

	vq->shadow_used_ring[i].id  = desc_idx;
	vq->shadow_used_ring[i].len = len;
}

static void
virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
{
	if (m_buf->ol_flags & PKT_TX_L4_MASK) {
		net_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
		net_hdr->csum_start = m_buf->l2_len + m_buf->l3_len;

		switch (m_buf->ol_flags & PKT_TX_L4_MASK) {
		case PKT_TX_TCP_CKSUM:
			net_hdr->csum_offset = (offsetof(struct tcp_hdr,
						cksum));
			break;
		case PKT_TX_UDP_CKSUM:
			net_hdr->csum_offset = (offsetof(struct udp_hdr,
						dgram_cksum));
			break;
		case PKT_TX_SCTP_CKSUM:
			net_hdr->csum_offset = (offsetof(struct sctp_hdr,
						cksum));
			break;
		}
	}

	if (m_buf->ol_flags & PKT_TX_TCP_SEG) {
		if (m_buf->ol_flags & PKT_TX_IPV4)
			net_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
		else
			net_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
		net_hdr->gso_size = m_buf->tso_segsz;
		net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
					+ m_buf->l4_len;
	}
}

static inline void
copy_virtio_net_hdr(struct virtio_net *dev, uint64_t desc_addr,
		    struct virtio_net_hdr_mrg_rxbuf hdr)
{
	if (dev->vhost_hlen == sizeof(struct virtio_net_hdr_mrg_rxbuf))
		*(struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)desc_addr = hdr;
	else
		*(struct virtio_net_hdr *)(uintptr_t)desc_addr = hdr.hdr;
}

static inline int __attribute__((always_inline))
copy_mbuf_to_desc(struct virtio_net *dev, struct vring_desc *descs,
		  struct rte_mbuf *m, uint16_t desc_idx, uint32_t size)
{
	uint32_t desc_avail, desc_offset;
	uint32_t mbuf_avail, mbuf_offset;
	uint32_t cpy_len;
	struct vring_desc *desc;
	uint64_t desc_addr;
	struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0};
	/* A counter to avoid desc dead loop chain */
	uint16_t nr_desc = 1;

	desc = &descs[desc_idx];
	desc_addr = gpa_to_vva(dev, desc->addr);
	/*
	 * Checking of 'desc_addr' placed outside of 'unlikely' macro to avoid
	 * performance issue with some versions of gcc (4.8.4 and 5.3.0) which
	 * otherwise stores offset on the stack instead of in a register.
	 */
	if (unlikely(desc->len < dev->vhost_hlen) || !desc_addr)
		return -1;

	rte_prefetch0((void *)(uintptr_t)desc_addr);

	virtio_enqueue_offload(m, &virtio_hdr.hdr);
	copy_virtio_net_hdr(dev, desc_addr, virtio_hdr);
	vhost_log_write(dev, desc->addr, dev->vhost_hlen);
	PRINT_PACKET(dev, (uintptr_t)desc_addr, dev->vhost_hlen, 0);

	desc_offset = dev->vhost_hlen;
	desc_avail  = desc->len - dev->vhost_hlen;

	mbuf_avail  = rte_pktmbuf_data_len(m);
	mbuf_offset = 0;
	while (mbuf_avail != 0 || m->next != NULL) {
		/* done with current mbuf, fetch next */
		if (mbuf_avail == 0) {
			m = m->next;

			mbuf_offset = 0;
			mbuf_avail  = rte_pktmbuf_data_len(m);
		}

		/* done with current desc buf, fetch next */
		if (desc_avail == 0) {
			if ((desc->flags & VRING_DESC_F_NEXT) == 0) {
				/* Room in vring buffer is not enough */
				return -1;
			}
			if (unlikely(desc->next >= size || ++nr_desc > size))
				return -1;

			desc = &descs[desc->next];
			desc_addr = gpa_to_vva(dev, desc->addr);
			if (unlikely(!desc_addr))
				return -1;

			desc_offset = 0;
			desc_avail  = desc->len;
		}

		cpy_len = RTE_MIN(desc_avail, mbuf_avail);
		rte_memcpy((void *)((uintptr_t)(desc_addr + desc_offset)),
			rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
			cpy_len);
		vhost_log_write(dev, desc->addr + desc_offset, cpy_len);
		PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset),
			     cpy_len, 0);

		mbuf_avail  -= cpy_len;
		mbuf_offset += cpy_len;
		desc_avail  -= cpy_len;
		desc_offset += cpy_len;
	}

	return 0;
}

/**
 * This function adds buffers to the virtio devices RX virtqueue. Buffers can
 * be received from the physical port or from another virtio device. A packet
 * count is returned to indicate the number of packets that are succesfully
 * added to the RX queue. This function works when the mbuf is scattered, but
 * it doesn't support the mergeable feature.
 */
static inline uint32_t __attribute__((always_inline))
virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
	      struct rte_mbuf **pkts, uint32_t count)
{
	struct vhost_virtqueue *vq;
	uint16_t avail_idx, free_entries, start_idx;
	uint16_t desc_indexes[MAX_PKT_BURST];
	struct vring_desc *descs;
	uint16_t used_idx;
	uint32_t i, sz;

	LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
	if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->virt_qp_nb))) {
		RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
			dev->vid, __func__, queue_id);
		return 0;
	}

	vq = dev->virtqueue[queue_id];
	if (unlikely(vq->enabled == 0))
		return 0;

	avail_idx = *((volatile uint16_t *)&vq->avail->idx);
	start_idx = vq->last_used_idx;
	free_entries = avail_idx - start_idx;
	count = RTE_MIN(count, free_entries);
	count = RTE_MIN(count, (uint32_t)MAX_PKT_BURST);
	if (count == 0)
		return 0;

	LOG_DEBUG(VHOST_DATA, "(%d) start_idx %d | end_idx %d\n",
		dev->vid, start_idx, start_idx + count);

	/* Retrieve all of the desc indexes first to avoid caching issues. */
	rte_prefetch0(&vq->avail->ring[start_idx & (vq->size - 1)]);
	for (i = 0; i < count; i++) {
		used_idx = (start_idx + i) & (vq->size - 1);
		desc_indexes[i] = vq->avail->ring[used_idx];
		vq->used->ring[used_idx].id = desc_indexes[i];
		vq->used->ring[used_idx].len = pkts[i]->pkt_len +
					       dev->vhost_hlen;
		vhost_log_used_vring(dev, vq,
			offsetof(struct vring_used, ring[used_idx]),
			sizeof(vq->used->ring[used_idx]));
	}

	rte_prefetch0(&vq->desc[desc_indexes[0]]);
	for (i = 0; i < count; i++) {
		uint16_t desc_idx = desc_indexes[i];
		int err;

		if (vq->desc[desc_idx].flags & VRING_DESC_F_INDIRECT) {
			descs = (struct vring_desc *)(uintptr_t)gpa_to_vva(dev,
					vq->desc[desc_idx].addr);
			if (unlikely(!descs)) {
				count = i;
				break;
			}

			desc_idx = 0;
			sz = vq->desc[desc_idx].len / sizeof(*descs);
		} else {
			descs = vq->desc;
			sz = vq->size;
		}

		err = copy_mbuf_to_desc(dev, descs, pkts[i], desc_idx, sz);
		if (unlikely(err)) {
			used_idx = (start_idx + i) & (vq->size - 1);
			vq->used->ring[used_idx].len = dev->vhost_hlen;
			vhost_log_used_vring(dev, vq,
				offsetof(struct vring_used, ring[used_idx]),
				sizeof(vq->used->ring[used_idx]));
		}

		if (i + 1 < count)
			rte_prefetch0(&vq->desc[desc_indexes[i+1]]);
	}

	rte_smp_wmb();

	*(volatile uint16_t *)&vq->used->idx += count;
	vq->last_used_idx += count;
	vhost_log_used_vring(dev, vq,
		offsetof(struct vring_used, idx),
		sizeof(vq->used->idx));

	/* flush used->idx update before we read avail->flags. */
	rte_mb();

	/* Kick the guest if necessary. */
	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
			&& (vq->callfd >= 0))
		eventfd_write(vq->callfd, (eventfd_t)1);
	return count;
}

static inline int __attribute__((always_inline))
fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq,
			 uint32_t avail_idx, uint32_t *vec_idx,
			 struct buf_vector *buf_vec, uint16_t *desc_chain_head,
			 uint16_t *desc_chain_len)
{
	uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
	uint32_t vec_id = *vec_idx;
	uint32_t len    = 0;
	struct vring_desc *descs = vq->desc;

	*desc_chain_head = idx;

	if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) {
		descs = (struct vring_desc *)(uintptr_t)
					gpa_to_vva(dev, vq->desc[idx].addr);
		if (unlikely(!descs))
			return -1;

		idx = 0;
	}

	while (1) {
		if (unlikely(vec_id >= BUF_VECTOR_MAX || idx >= vq->size))
			return -1;

		len += descs[idx].len;
		buf_vec[vec_id].buf_addr = descs[idx].addr;
		buf_vec[vec_id].buf_len  = descs[idx].len;
		buf_vec[vec_id].desc_idx = idx;
		vec_id++;

		if ((descs[idx].flags & VRING_DESC_F_NEXT) == 0)
			break;

		idx = descs[idx].next;
	}

	*desc_chain_len = len;
	*vec_idx = vec_id;

	return 0;
}

/*
 * Returns -1 on fail, 0 on success
 */
static inline int
reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq,
				uint32_t size, struct buf_vector *buf_vec,
				uint16_t *num_buffers, uint16_t avail_head)
{
	uint16_t cur_idx;
	uint32_t vec_idx = 0;
	uint16_t tries = 0;

	uint16_t head_idx = 0;
	uint16_t len = 0;

	*num_buffers = 0;
	cur_idx  = vq->last_avail_idx;

	while (size > 0) {
		if (unlikely(cur_idx == avail_head))
			return -1;

		if (unlikely(fill_vec_buf(dev, vq, cur_idx, &vec_idx, buf_vec,
						&head_idx, &len) < 0))
			return -1;
		len = RTE_MIN(len, size);
		update_shadow_used_ring(vq, head_idx, len);
		size -= len;

		cur_idx++;
		tries++;
		*num_buffers += 1;

		/*
		 * if we tried all available ring items, and still
		 * can't get enough buf, it means something abnormal
		 * happened.
		 */
		if (unlikely(tries >= vq->size))
			return -1;
	}

	return 0;
}

static inline int __attribute__((always_inline))
copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct rte_mbuf *m,
			    struct buf_vector *buf_vec, uint16_t num_buffers)
{
	struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0, 0, 0, 0, 0, 0}, 0};
	uint32_t vec_idx = 0;
	uint64_t desc_addr;
	uint32_t mbuf_offset, mbuf_avail;
	uint32_t desc_offset, desc_avail;
	uint32_t cpy_len;
	uint64_t hdr_addr, hdr_phys_addr;
	struct rte_mbuf *hdr_mbuf;

	if (unlikely(m == NULL))
		return -1;

	desc_addr = gpa_to_vva(dev, buf_vec[vec_idx].buf_addr);
	if (buf_vec[vec_idx].buf_len < dev->vhost_hlen || !desc_addr)
		return -1;

	hdr_mbuf = m;
	hdr_addr = desc_addr;
	hdr_phys_addr = buf_vec[vec_idx].buf_addr;
	rte_prefetch0((void *)(uintptr_t)hdr_addr);

	virtio_hdr.num_buffers = num_buffers;
	LOG_DEBUG(VHOST_DATA, "(%d) RX: num merge buffers %d\n",
		dev->vid, num_buffers);

	desc_avail  = buf_vec[vec_idx].buf_len - dev->vhost_hlen;
	desc_offset = dev->vhost_hlen;

	mbuf_avail  = rte_pktmbuf_data_len(m);
	mbuf_offset = 0;
	while (mbuf_avail != 0 || m->next != NULL) {
		/* done with current desc buf, get the next one */
		if (desc_avail == 0) {
			vec_idx++;
			desc_addr = gpa_to_vva(dev, buf_vec[vec_idx].buf_addr);
			if (unlikely(!desc_addr))
				return -1;

			/* Prefetch buffer address. */
			rte_prefetch0((void *)(uintptr_t)desc_addr);
			desc_offset = 0;
			desc_avail  = buf_vec[vec_idx].buf_len;
		}

		/* done with current mbuf, get the next one */
		if (mbuf_avail == 0) {
			m = m->next;

			mbuf_offset = 0;
			mbuf_avail  = rte_pktmbuf_data_len(m);
		}

		if (hdr_addr) {
			virtio_enqueue_offload(hdr_mbuf, &virtio_hdr.hdr);
			copy_virtio_net_hdr(dev, hdr_addr, virtio_hdr);
			vhost_log_write(dev, hdr_phys_addr, dev->vhost_hlen);
			PRINT_PACKET(dev, (uintptr_t)hdr_addr,
				     dev->vhost_hlen, 0);

			hdr_addr = 0;
		}

		cpy_len = RTE_MIN(desc_avail, mbuf_avail);
		rte_memcpy((void *)((uintptr_t)(desc_addr + desc_offset)),
			rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
			cpy_len);
		vhost_log_write(dev, buf_vec[vec_idx].buf_addr + desc_offset,
			cpy_len);
		PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset),
			cpy_len, 0);

		mbuf_avail  -= cpy_len;
		mbuf_offset += cpy_len;
		desc_avail  -= cpy_len;
		desc_offset += cpy_len;
	}

	return 0;
}

static inline uint32_t __attribute__((always_inline))
virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
	struct rte_mbuf **pkts, uint32_t count)
{
	struct vhost_virtqueue *vq;
	uint32_t pkt_idx = 0;
	uint16_t num_buffers;
	struct buf_vector buf_vec[BUF_VECTOR_MAX];
	uint16_t avail_head;

	LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
	if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->virt_qp_nb))) {
		RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
			dev->vid, __func__, queue_id);
		return 0;
	}

	vq = dev->virtqueue[queue_id];
	if (unlikely(vq->enabled == 0))
		return 0;

	count = RTE_MIN((uint32_t)MAX_PKT_BURST, count);
	if (count == 0)
		return 0;

	rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);

	vq->shadow_used_idx = 0;
	avail_head = *((volatile uint16_t *)&vq->avail->idx);
	for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
		uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen;

		if (unlikely(reserve_avail_buf_mergeable(dev, vq,
						pkt_len, buf_vec, &num_buffers,
						avail_head) < 0)) {
			LOG_DEBUG(VHOST_DATA,
				"(%d) failed to get enough desc from vring\n",
				dev->vid);
			vq->shadow_used_idx -= num_buffers;
			break;
		}

		LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
			dev->vid, vq->last_avail_idx,
			vq->last_avail_idx + num_buffers);

		if (copy_mbuf_to_desc_mergeable(dev, pkts[pkt_idx],
						buf_vec, num_buffers) < 0) {
			vq->shadow_used_idx -= num_buffers;
			break;
		}

		vq->last_avail_idx += num_buffers;
	}

	if (likely(vq->shadow_used_idx)) {
		flush_shadow_used_ring(dev, vq);

		/* flush used->idx update before we read avail->flags. */
		rte_mb();

		/* Kick the guest if necessary. */
		if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
				&& (vq->callfd >= 0))
			eventfd_write(vq->callfd, (eventfd_t)1);
	}

	return pkt_idx;
}

uint16_t
rte_vhost_enqueue_burst(int vid, uint16_t queue_id,
	struct rte_mbuf **pkts, uint16_t count)
{
	struct virtio_net *dev = get_device(vid);

	if (!dev)
		return 0;

	if (dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF))
		return virtio_dev_merge_rx(dev, queue_id, pkts, count);
	else
		return virtio_dev_rx(dev, queue_id, pkts, count);
}

static inline bool
virtio_net_with_host_offload(struct virtio_net *dev)
{
	if (dev->features &
			(VIRTIO_NET_F_CSUM | VIRTIO_NET_F_HOST_ECN |
			 VIRTIO_NET_F_HOST_TSO4 | VIRTIO_NET_F_HOST_TSO6 |
			 VIRTIO_NET_F_HOST_UFO))
		return true;

	return false;
}

static void
parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr)
{
	struct ipv4_hdr *ipv4_hdr;
	struct ipv6_hdr *ipv6_hdr;
	void *l3_hdr = NULL;
	struct ether_hdr *eth_hdr;
	uint16_t ethertype;

	eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);

	m->l2_len = sizeof(struct ether_hdr);
	ethertype = rte_be_to_cpu_16(eth_hdr->ether_type);

	if (ethertype == ETHER_TYPE_VLAN) {
		struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1);

		m->l2_len += sizeof(struct vlan_hdr);
		ethertype = rte_be_to_cpu_16(vlan_hdr->eth_proto);
	}

	l3_hdr = (char *)eth_hdr + m->l2_len;

	switch (ethertype) {
	case ETHER_TYPE_IPv4:
		ipv4_hdr = (struct ipv4_hdr *)l3_hdr;
		*l4_proto = ipv4_hdr->next_proto_id;
		m->l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4;
		*l4_hdr = (char *)l3_hdr + m->l3_len;
		m->ol_flags |= PKT_TX_IPV4;
		break;
	case ETHER_TYPE_IPv6:
		ipv6_hdr = (struct ipv6_hdr *)l3_hdr;
		*l4_proto = ipv6_hdr->proto;
		m->l3_len = sizeof(struct ipv6_hdr);
		*l4_hdr = (char *)l3_hdr + m->l3_len;
		m->ol_flags |= PKT_TX_IPV6;
		break;
	default:
		m->l3_len = 0;
		*l4_proto = 0;
		*l4_hdr = NULL;
		break;
	}
}

static inline void __attribute__((always_inline))
vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
{
	uint16_t l4_proto = 0;
	void *l4_hdr = NULL;
	struct tcp_hdr *tcp_hdr = NULL;

	if (hdr->flags == 0 && hdr->gso_type == VIRTIO_NET_HDR_GSO_NONE)
		return;

	parse_ethernet(m, &l4_proto, &l4_hdr);
	if (hdr->flags == VIRTIO_NET_HDR_F_NEEDS_CSUM) {
		if (hdr->csum_start == (m->l2_len + m->l3_len)) {
			switch (hdr->csum_offset) {
			case (offsetof(struct tcp_hdr, cksum)):
				if (l4_proto == IPPROTO_TCP)
					m->ol_flags |= PKT_TX_TCP_CKSUM;
				break;
			case (offsetof(struct udp_hdr, dgram_cksum)):
				if (l4_proto == IPPROTO_UDP)
					m->ol_flags |= PKT_TX_UDP_CKSUM;
				break;
			case (offsetof(struct sctp_hdr, cksum)):
				if (l4_proto == IPPROTO_SCTP)
					m->ol_flags |= PKT_TX_SCTP_CKSUM;
				break;
			default:
				break;
			}
		}
	}

	if (l4_hdr && hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
		case VIRTIO_NET_HDR_GSO_TCPV4:
		case VIRTIO_NET_HDR_GSO_TCPV6:
			tcp_hdr = (struct tcp_hdr *)l4_hdr;
			m->ol_flags |= PKT_TX_TCP_SEG;
			m->tso_segsz = hdr->gso_size;
			m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
			break;
		default:
			RTE_LOG(WARNING, VHOST_DATA,
				"unsupported gso type %u.\n", hdr->gso_type);
			break;
		}
	}
}

#define RARP_PKT_SIZE	64

static int
make_rarp_packet(struct rte_mbuf *rarp_mbuf, const struct ether_addr *mac)
{
	struct ether_hdr *eth_hdr;
	struct arp_hdr  *rarp;

	if (rarp_mbuf->buf_len < 64) {
		RTE_LOG(WARNING, VHOST_DATA,
			"failed to make RARP; mbuf size too small %u (< %d)\n",
			rarp_mbuf->buf_len, RARP_PKT_SIZE);
		return -1;
	}

	/* Ethernet header. */
	eth_hdr = rte_pktmbuf_mtod_offset(rarp_mbuf, struct ether_hdr *, 0);
	memset(eth_hdr->d_addr.addr_bytes, 0xff, ETHER_ADDR_LEN);
	ether_addr_copy(mac, &eth_hdr->s_addr);
	eth_hdr->ether_type = htons(ETHER_TYPE_RARP);

	/* RARP header. */
	rarp = (struct arp_hdr *)(eth_hdr + 1);
	rarp->arp_hrd = htons(ARP_HRD_ETHER);
	rarp->arp_pro = htons(ETHER_TYPE_IPv4);
	rarp->arp_hln = ETHER_ADDR_LEN;
	rarp->arp_pln = 4;
	rarp->arp_op  = htons(ARP_OP_REVREQUEST);

	ether_addr_copy(mac, &rarp->arp_data.arp_sha);
	ether_addr_copy(mac, &rarp->arp_data.arp_tha);
	memset(&rarp->arp_data.arp_sip, 0x00, 4);
	memset(&rarp->arp_data.arp_tip, 0x00, 4);

	rarp_mbuf->pkt_len  = rarp_mbuf->data_len = RARP_PKT_SIZE;

	return 0;
}

static inline void __attribute__((always_inline))
put_zmbuf(struct zcopy_mbuf *zmbuf)
{
	zmbuf->in_use = 0;
}

static inline int __attribute__((always_inline))
copy_desc_to_mbuf(struct virtio_net *dev, struct vring_desc *descs,
		  uint16_t max_desc, struct rte_mbuf *m, uint16_t desc_idx,
		  struct rte_mempool *mbuf_pool)
{
	struct vring_desc *desc;
	uint64_t desc_addr;
	uint32_t desc_avail, desc_offset;
	uint32_t mbuf_avail, mbuf_offset;
	uint32_t cpy_len;
	struct rte_mbuf *cur = m, *prev = m;
	struct virtio_net_hdr *hdr = NULL;
	/* A counter to avoid desc dead loop chain */
	uint32_t nr_desc = 1;

	desc = &descs[desc_idx];
	if (unlikely((desc->len < dev->vhost_hlen)) ||
			(desc->flags & VRING_DESC_F_INDIRECT))
		return -1;

	desc_addr = gpa_to_vva(dev, desc->addr);
	if (unlikely(!desc_addr))
		return -1;

	if (virtio_net_with_host_offload(dev)) {
		hdr = (struct virtio_net_hdr *)((uintptr_t)desc_addr);
		rte_prefetch0(hdr);
	}

	/*
	 * A virtio driver normally uses at least 2 desc buffers
	 * for Tx: the first for storing the header, and others
	 * for storing the data.
	 */
	if (likely((desc->len == dev->vhost_hlen) &&
		   (desc->flags & VRING_DESC_F_NEXT) != 0)) {
		desc = &descs[desc->next];
		if (unlikely(desc->flags & VRING_DESC_F_INDIRECT))
			return -1;

		desc_addr = gpa_to_vva(dev, desc->addr);
		if (unlikely(!desc_addr))
			return -1;

		desc_offset = 0;
		desc_avail  = desc->len;
		nr_desc    += 1;
	} else {
		desc_avail  = desc->len - dev->vhost_hlen;
		desc_offset = dev->vhost_hlen;
	}

	rte_prefetch0((void *)(uintptr_t)(desc_addr + desc_offset));

	PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset), desc_avail, 0);

	mbuf_offset = 0;
	mbuf_avail  = m->buf_len - RTE_PKTMBUF_HEADROOM;
	while (1) {
		uint64_t hpa;

		cpy_len = RTE_MIN(desc_avail, mbuf_avail);

		/*
		 * A desc buf might across two host physical pages that are
		 * not continuous. In such case (gpa_to_hpa returns 0), data
		 * will be copied even though zero copy is enabled.
		 */
		if (unlikely(dev->dequeue_zero_copy && (hpa = gpa_to_hpa(dev,
					desc->addr + desc_offset, cpy_len)))) {
			cur->data_len = cpy_len;
			cur->data_off = 0;
			cur->buf_addr = (void *)(uintptr_t)desc_addr;
			cur->buf_physaddr = hpa;

			/*
			 * In zero copy mode, one mbuf can only reference data
			 * for one or partial of one desc buff.
			 */
			mbuf_avail = cpy_len;
		} else {
			rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *,
							   mbuf_offset),
				(void *)((uintptr_t)(desc_addr + desc_offset)),
				cpy_len);
		}

		mbuf_avail  -= cpy_len;
		mbuf_offset += cpy_len;
		desc_avail  -= cpy_len;
		desc_offset += cpy_len;

		/* This desc reaches to its end, get the next one */
		if (desc_avail == 0) {
			if ((desc->flags & VRING_DESC_F_NEXT) == 0)
				break;

			if (unlikely(desc->next >= max_desc ||
				     ++nr_desc > max_desc))
				return -1;
			desc = &descs[desc->next];
			if (unlikely(desc->flags & VRING_DESC_F_INDIRECT))
				return -1;

			desc_addr = gpa_to_vva(dev, desc->addr);
			if (unlikely(!desc_addr))
				return -1;

			rte_prefetch0((void *)(uintptr_t)desc_addr);

			desc_offset = 0;
			desc_avail  = desc->len;

			PRINT_PACKET(dev, (uintptr_t)desc_addr, desc->len, 0);
		}

		/*
		 * This mbuf reaches to its end, get a new one
		 * to hold more data.
		 */
		if (mbuf_avail == 0) {
			cur = rte_pktmbuf_alloc(mbuf_pool);
			if (unlikely(cur == NULL)) {
				RTE_LOG(ERR, VHOST_DATA, "Failed to "
					"allocate memory for mbuf.\n");
				return -1;
			}

			prev->next = cur;
			prev->data_len = mbuf_offset;
			m->nb_segs += 1;
			m->pkt_len += mbuf_offset;
			prev = cur;

			mbuf_offset = 0;
			mbuf_avail  = cur->buf_len - RTE_PKTMBUF_HEADROOM;
		}
	}

	prev->data_len = mbuf_offset;
	m->pkt_len    += mbuf_offset;

	if (hdr)
		vhost_dequeue_offload(hdr, m);

	return 0;
}

static inline void __attribute__((always_inline))
update_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
		 uint32_t used_idx, uint32_t desc_idx)
{
	vq->used->ring[used_idx].id  = desc_idx;
	vq->used->ring[used_idx].len = 0;
	vhost_log_used_vring(dev, vq,
			offsetof(struct vring_used, ring[used_idx]),
			sizeof(vq->used->ring[used_idx]));
}

static inline void __attribute__((always_inline))
update_used_idx(struct virtio_net *dev, struct vhost_virtqueue *vq,
		uint32_t count)
{
	if (unlikely(count == 0))
		return;

	rte_smp_wmb();
	rte_smp_rmb();

	vq->used->idx += count;
	vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
			sizeof(vq->used->idx));

	/* Kick guest if required. */
	if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
			&& (vq->callfd >= 0))
		eventfd_write(vq->callfd, (eventfd_t)1);
}

static inline struct zcopy_mbuf *__attribute__((always_inline))
get_zmbuf(struct vhost_virtqueue *vq)
{
	uint16_t i;
	uint16_t last;
	int tries = 0;

	/* search [last_zmbuf_idx, zmbuf_size) */
	i = vq->last_zmbuf_idx;
	last = vq->zmbuf_size;

again:
	for (; i < last; i++) {
		if (vq->zmbufs[i].in_use == 0) {
			vq->last_zmbuf_idx = i + 1;
			vq->zmbufs[i].in_use = 1;
			return &vq->zmbufs[i];
		}
	}

	tries++;
	if (tries == 1) {
		/* search [0, last_zmbuf_idx) */
		i = 0;
		last = vq->last_zmbuf_idx;
		goto again;
	}

	return NULL;
}

static inline bool __attribute__((always_inline))
mbuf_is_consumed(struct rte_mbuf *m)
{
	while (m) {
		if (rte_mbuf_refcnt_read(m) > 1)
			return false;
		m = m->next;
	}

	return true;
}

uint16_t
rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
	struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
{
	struct virtio_net *dev;
	struct rte_mbuf *rarp_mbuf = NULL;
	struct vhost_virtqueue *vq;
	uint32_t desc_indexes[MAX_PKT_BURST];
	uint32_t used_idx;
	uint32_t i = 0;
	uint16_t free_entries;
	uint16_t avail_idx;

	dev = get_device(vid);
	if (!dev)
		return 0;

	if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->virt_qp_nb))) {
		RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
			dev->vid, __func__, queue_id);
		return 0;
	}

	vq = dev->virtqueue[queue_id];
	if (unlikely(vq->enabled == 0))
		return 0;

	if (unlikely(dev->dequeue_zero_copy)) {
		struct zcopy_mbuf *zmbuf, *next;
		int nr_updated = 0;

		for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
		     zmbuf != NULL; zmbuf = next) {
			next = TAILQ_NEXT(zmbuf, next);

			if (mbuf_is_consumed(zmbuf->mbuf)) {
				used_idx = vq->last_used_idx++ & (vq->size - 1);
				update_used_ring(dev, vq, used_idx,
						 zmbuf->desc_idx);
				nr_updated += 1;

				TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
				rte_pktmbuf_free(zmbuf->mbuf);
				put_zmbuf(zmbuf);
				vq->nr_zmbuf -= 1;
			}
		}

		update_used_idx(dev, vq, nr_updated);
	}

	/*
	 * Construct a RARP broadcast packet, and inject it to the "pkts"
	 * array, to looks like that guest actually send such packet.
	 *
	 * Check user_send_rarp() for more information.
	 */
	if (unlikely(rte_atomic16_cmpset((volatile uint16_t *)
					 &dev->broadcast_rarp.cnt, 1, 0))) {
		rarp_mbuf = rte_pktmbuf_alloc(mbuf_pool);
		if (rarp_mbuf == NULL) {
			RTE_LOG(ERR, VHOST_DATA,
				"Failed to allocate memory for mbuf.\n");
			return 0;
		}

		if (make_rarp_packet(rarp_mbuf, &dev->mac)) {
			rte_pktmbuf_free(rarp_mbuf);
			rarp_mbuf = NULL;
		} else {
			count -= 1;
		}
	}

	free_entries = *((volatile uint16_t *)&vq->avail->idx) -
			vq->last_avail_idx;
	if (free_entries == 0)
		goto out;

	LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);

	/* Prefetch available and used ring */
	avail_idx = vq->last_avail_idx & (vq->size - 1);
	used_idx  = vq->last_used_idx  & (vq->size - 1);
	rte_prefetch0(&vq->avail->ring[avail_idx]);
	rte_prefetch0(&vq->used->ring[used_idx]);

	count = RTE_MIN(count, MAX_PKT_BURST);
	count = RTE_MIN(count, free_entries);
	LOG_DEBUG(VHOST_DATA, "(%d) about to dequeue %u buffers\n",
			dev->vid, count);

	/* Retrieve all of the head indexes first to avoid caching issues. */
	for (i = 0; i < count; i++) {
		avail_idx = (vq->last_avail_idx + i) & (vq->size - 1);
		used_idx  = (vq->last_used_idx  + i) & (vq->size - 1);
		desc_indexes[i] = vq->avail->ring[avail_idx];

		if (likely(dev->dequeue_zero_copy == 0))
			update_used_ring(dev, vq, used_idx, desc_indexes[i]);
	}

	/* Prefetch descriptor index. */
	rte_prefetch0(&vq->desc[desc_indexes[0]]);
	for (i = 0; i < count; i++) {
		struct vring_desc *desc;
		uint16_t sz, idx;
		int err;

		if (likely(i + 1 < count))
			rte_prefetch0(&vq->desc[desc_indexes[i + 1]]);

		if (vq->desc[desc_indexes[i]].flags & VRING_DESC_F_INDIRECT) {
			desc = (struct vring_desc *)(uintptr_t)gpa_to_vva(dev,
					vq->desc[desc_indexes[i]].addr);
			if (unlikely(!desc))
				break;

			rte_prefetch0(desc);
			sz = vq->desc[desc_indexes[i]].len / sizeof(*desc);
			idx = 0;
		} else {
			desc = vq->desc;
			sz = vq->size;
			idx = desc_indexes[i];
		}

		pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
		if (unlikely(pkts[i] == NULL)) {
			RTE_LOG(ERR, VHOST_DATA,
				"Failed to allocate memory for mbuf.\n");
			break;
		}

		err = copy_desc_to_mbuf(dev, desc, sz, pkts[i], idx, mbuf_pool);
		if (unlikely(err)) {
			rte_pktmbuf_free(pkts[i]);
			break;
		}

		if (unlikely(dev->dequeue_zero_copy)) {
			struct zcopy_mbuf *zmbuf;

			zmbuf = get_zmbuf(vq);
			if (!zmbuf) {
				rte_pktmbuf_free(pkts[i]);
				break;
			}
			zmbuf->mbuf = pkts[i];
			zmbuf->desc_idx = desc_indexes[i];

			/*
			 * Pin lock the mbuf; we will check later to see
			 * whether the mbuf is freed (when we are the last
			 * user) or not. If that's the case, we then could
			 * update the used ring safely.
			 */
			rte_mbuf_refcnt_update(pkts[i], 1);

			vq->nr_zmbuf += 1;
			TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next);
		}
	}
	vq->last_avail_idx += i;

	if (likely(dev->dequeue_zero_copy == 0)) {
		vq->last_used_idx += i;
		update_used_idx(dev, vq, i);
	}

out:
	if (unlikely(rarp_mbuf != NULL)) {
		/*
		 * Inject it to the head of "pkts" array, so that switch's mac
		 * learning table will get updated first.
		 */
		memmove(&pkts[1], pkts, i * sizeof(struct rte_mbuf *));
		pkts[0] = rarp_mbuf;
		i += 1;
	}

	return i;
}