DPDK logo

Elixir Cross Referencer

  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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2014 Intel Corporation
 */

#ifndef _VIRTQUEUE_H_
#define _VIRTQUEUE_H_

#include <stdint.h>

#include <rte_atomic.h>
#include <rte_memory.h>
#include <rte_mempool.h>
#include <rte_net.h>

#include "virtio_pci.h"
#include "virtio_ring.h"
#include "virtio_logs.h"
#include "virtio_rxtx.h"

struct rte_mbuf;

#define DEFAULT_TX_FREE_THRESH 32
#define DEFAULT_RX_FREE_THRESH 32

#define VIRTIO_MBUF_BURST_SZ 64
/*
 * Per virtio_ring.h in Linux.
 *     For virtio_pci on SMP, we don't need to order with respect to MMIO
 *     accesses through relaxed memory I/O windows, so smp_mb() et al are
 *     sufficient.
 *
 *     For using virtio to talk to real devices (eg. vDPA) we do need real
 *     barriers.
 */
static inline void
virtio_mb(uint8_t weak_barriers)
{
	if (weak_barriers)
		rte_smp_mb();
	else
		rte_mb();
}

static inline void
virtio_rmb(uint8_t weak_barriers)
{
	if (weak_barriers)
		rte_smp_rmb();
	else
		rte_cio_rmb();
}

static inline void
virtio_wmb(uint8_t weak_barriers)
{
	if (weak_barriers)
		rte_smp_wmb();
	else
		rte_cio_wmb();
}

static inline uint16_t
virtqueue_fetch_flags_packed(struct vring_packed_desc *dp,
			      uint8_t weak_barriers)
{
	uint16_t flags;

	if (weak_barriers) {
/* x86 prefers to using rte_smp_rmb over __atomic_load_n as it reports
 * a better perf(~1.5%), which comes from the saved branch by the compiler.
 * The if and else branch are identical with the smp and cio barriers both
 * defined as compiler barriers on x86.
 */
#ifdef RTE_ARCH_X86_64
		flags = dp->flags;
		rte_smp_rmb();
#else
		flags = __atomic_load_n(&dp->flags, __ATOMIC_ACQUIRE);
#endif
	} else {
		flags = dp->flags;
		rte_cio_rmb();
	}

	return flags;
}

static inline void
virtqueue_store_flags_packed(struct vring_packed_desc *dp,
			      uint16_t flags, uint8_t weak_barriers)
{
	if (weak_barriers) {
/* x86 prefers to using rte_smp_wmb over __atomic_store_n as it reports
 * a better perf(~1.5%), which comes from the saved branch by the compiler.
 * The if and else branch are identical with the smp and cio barriers both
 * defined as compiler barriers on x86.
 */
#ifdef RTE_ARCH_X86_64
		rte_smp_wmb();
		dp->flags = flags;
#else
		__atomic_store_n(&dp->flags, flags, __ATOMIC_RELEASE);
#endif
	} else {
		rte_cio_wmb();
		dp->flags = flags;
	}
}
#ifdef RTE_PMD_PACKET_PREFETCH
#define rte_packet_prefetch(p)  rte_prefetch1(p)
#else
#define rte_packet_prefetch(p)  do {} while(0)
#endif

#define VIRTQUEUE_MAX_NAME_SZ 32

#ifdef RTE_VIRTIO_USER
/**
 * Return the physical address (or virtual address in case of
 * virtio-user) of mbuf data buffer.
 *
 * The address is firstly casted to the word size (sizeof(uintptr_t))
 * before casting it to uint64_t. This is to make it work with different
 * combination of word size (64 bit and 32 bit) and virtio device
 * (virtio-pci and virtio-user).
 */
#define VIRTIO_MBUF_ADDR(mb, vq) \
	((uint64_t)(*(uintptr_t *)((uintptr_t)(mb) + (vq)->offset)))
#else
#define VIRTIO_MBUF_ADDR(mb, vq) ((mb)->buf_iova)
#endif

/**
 * Return the physical address (or virtual address in case of
 * virtio-user) of mbuf data buffer, taking care of mbuf data offset
 */
#define VIRTIO_MBUF_DATA_DMA_ADDR(mb, vq) \
	(VIRTIO_MBUF_ADDR(mb, vq) + (mb)->data_off)

#define VTNET_SQ_RQ_QUEUE_IDX 0
#define VTNET_SQ_TQ_QUEUE_IDX 1
#define VTNET_SQ_CQ_QUEUE_IDX 2

enum { VTNET_RQ = 0, VTNET_TQ = 1, VTNET_CQ = 2 };
/**
 * The maximum virtqueue size is 2^15. Use that value as the end of
 * descriptor chain terminator since it will never be a valid index
 * in the descriptor table. This is used to verify we are correctly
 * handling vq_free_cnt.
 */
#define VQ_RING_DESC_CHAIN_END 32768

/**
 * Control the RX mode, ie. promiscuous, allmulti, etc...
 * All commands require an "out" sg entry containing a 1 byte
 * state value, zero = disable, non-zero = enable.  Commands
 * 0 and 1 are supported with the VIRTIO_NET_F_CTRL_RX feature.
 * Commands 2-5 are added with VIRTIO_NET_F_CTRL_RX_EXTRA.
 */
#define VIRTIO_NET_CTRL_RX              0
#define VIRTIO_NET_CTRL_RX_PROMISC      0
#define VIRTIO_NET_CTRL_RX_ALLMULTI     1
#define VIRTIO_NET_CTRL_RX_ALLUNI       2
#define VIRTIO_NET_CTRL_RX_NOMULTI      3
#define VIRTIO_NET_CTRL_RX_NOUNI        4
#define VIRTIO_NET_CTRL_RX_NOBCAST      5

/**
 * Control the MAC
 *
 * The MAC filter table is managed by the hypervisor, the guest should
 * assume the size is infinite.  Filtering should be considered
 * non-perfect, ie. based on hypervisor resources, the guest may
 * received packets from sources not specified in the filter list.
 *
 * In addition to the class/cmd header, the TABLE_SET command requires
 * two out scatterlists.  Each contains a 4 byte count of entries followed
 * by a concatenated byte stream of the ETH_ALEN MAC addresses.  The
 * first sg list contains unicast addresses, the second is for multicast.
 * This functionality is present if the VIRTIO_NET_F_CTRL_RX feature
 * is available.
 *
 * The ADDR_SET command requests one out scatterlist, it contains a
 * 6 bytes MAC address. This functionality is present if the
 * VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
 */
struct virtio_net_ctrl_mac {
	uint32_t entries;
	uint8_t macs[][RTE_ETHER_ADDR_LEN];
} __rte_packed;

#define VIRTIO_NET_CTRL_MAC    1
#define VIRTIO_NET_CTRL_MAC_TABLE_SET        0
#define VIRTIO_NET_CTRL_MAC_ADDR_SET         1

/**
 * Control VLAN filtering
 *
 * The VLAN filter table is controlled via a simple ADD/DEL interface.
 * VLAN IDs not added may be filtered by the hypervisor.  Del is the
 * opposite of add.  Both commands expect an out entry containing a 2
 * byte VLAN ID.  VLAN filtering is available with the
 * VIRTIO_NET_F_CTRL_VLAN feature bit.
 */
#define VIRTIO_NET_CTRL_VLAN     2
#define VIRTIO_NET_CTRL_VLAN_ADD 0
#define VIRTIO_NET_CTRL_VLAN_DEL 1

/*
 * Control link announce acknowledgement
 *
 * The command VIRTIO_NET_CTRL_ANNOUNCE_ACK is used to indicate that
 * driver has recevied the notification; device would clear the
 * VIRTIO_NET_S_ANNOUNCE bit in the status field after it receives
 * this command.
 */
#define VIRTIO_NET_CTRL_ANNOUNCE     3
#define VIRTIO_NET_CTRL_ANNOUNCE_ACK 0

struct virtio_net_ctrl_hdr {
	uint8_t class;
	uint8_t cmd;
} __rte_packed;

typedef uint8_t virtio_net_ctrl_ack;

#define VIRTIO_NET_OK     0
#define VIRTIO_NET_ERR    1

#define VIRTIO_MAX_CTRL_DATA 2048

struct virtio_pmd_ctrl {
	struct virtio_net_ctrl_hdr hdr;
	virtio_net_ctrl_ack status;
	uint8_t data[VIRTIO_MAX_CTRL_DATA];
};

struct vq_desc_extra {
	void *cookie;
	uint16_t ndescs;
	uint16_t next;
};

struct virtqueue {
	struct virtio_hw  *hw; /**< virtio_hw structure pointer. */
	union {
		struct {
			/**< vring keeping desc, used and avail */
			struct vring ring;
		} vq_split;

		struct {
			/**< vring keeping descs and events */
			struct vring_packed ring;
			bool used_wrap_counter;
			uint16_t cached_flags; /**< cached flags for descs */
			uint16_t event_flags_shadow;
		} vq_packed;
	};

	uint16_t vq_used_cons_idx; /**< last consumed descriptor */
	uint16_t vq_nentries;  /**< vring desc numbers */
	uint16_t vq_free_cnt;  /**< num of desc available */
	uint16_t vq_avail_idx; /**< sync until needed */
	uint16_t vq_free_thresh; /**< free threshold */

	void *vq_ring_virt_mem;  /**< linear address of vring*/
	unsigned int vq_ring_size;

	union {
		struct virtnet_rx rxq;
		struct virtnet_tx txq;
		struct virtnet_ctl cq;
	};

	rte_iova_t vq_ring_mem; /**< physical address of vring,
	                         * or virtual address for virtio_user. */

	/**
	 * Head of the free chain in the descriptor table. If
	 * there are no free descriptors, this will be set to
	 * VQ_RING_DESC_CHAIN_END.
	 */
	uint16_t  vq_desc_head_idx;
	uint16_t  vq_desc_tail_idx;
	uint16_t  vq_queue_index;   /**< PCI queue index */
	uint16_t offset; /**< relative offset to obtain addr in mbuf */
	uint16_t  *notify_addr;
	struct rte_mbuf **sw_ring;  /**< RX software ring. */
	struct vq_desc_extra vq_descx[0];
};

/* If multiqueue is provided by host, then we suppport it. */
#define VIRTIO_NET_CTRL_MQ   4
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET        0
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
#define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000

/**
 * This is the first element of the scatter-gather list.  If you don't
 * specify GSO or CSUM features, you can simply ignore the header.
 */
struct virtio_net_hdr {
#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1    /**< Use csum_start,csum_offset*/
#define VIRTIO_NET_HDR_F_DATA_VALID 2    /**< Checksum is valid */
	uint8_t flags;
#define VIRTIO_NET_HDR_GSO_NONE     0    /**< Not a GSO frame */
#define VIRTIO_NET_HDR_GSO_TCPV4    1    /**< GSO frame, IPv4 TCP (TSO) */
#define VIRTIO_NET_HDR_GSO_UDP      3    /**< GSO frame, IPv4 UDP (UFO) */
#define VIRTIO_NET_HDR_GSO_TCPV6    4    /**< GSO frame, IPv6 TCP */
#define VIRTIO_NET_HDR_GSO_ECN      0x80 /**< TCP has ECN set */
	uint8_t gso_type;
	uint16_t hdr_len;     /**< Ethernet + IP + tcp/udp hdrs */
	uint16_t gso_size;    /**< Bytes to append to hdr_len per frame */
	uint16_t csum_start;  /**< Position to start checksumming from */
	uint16_t csum_offset; /**< Offset after that to place checksum */
};

/**
 * This is the version of the header to use when the MRG_RXBUF
 * feature has been negotiated.
 */
struct virtio_net_hdr_mrg_rxbuf {
	struct   virtio_net_hdr hdr;
	uint16_t num_buffers; /**< Number of merged rx buffers */
};

/* Region reserved to allow for transmit header and indirect ring */
#define VIRTIO_MAX_TX_INDIRECT 8
struct virtio_tx_region {
	struct virtio_net_hdr_mrg_rxbuf tx_hdr;
	struct vring_desc tx_indir[VIRTIO_MAX_TX_INDIRECT]
		__rte_aligned(16);
};

static inline int
desc_is_used(struct vring_packed_desc *desc, struct virtqueue *vq)
{
	uint16_t used, avail, flags;

	flags = virtqueue_fetch_flags_packed(desc, vq->hw->weak_barriers);
	used = !!(flags & VRING_PACKED_DESC_F_USED);
	avail = !!(flags & VRING_PACKED_DESC_F_AVAIL);

	return avail == used && used == vq->vq_packed.used_wrap_counter;
}

static inline void
vring_desc_init_packed(struct virtqueue *vq, int n)
{
	int i;
	for (i = 0; i < n - 1; i++) {
		vq->vq_packed.ring.desc[i].id = i;
		vq->vq_descx[i].next = i + 1;
	}
	vq->vq_packed.ring.desc[i].id = i;
	vq->vq_descx[i].next = VQ_RING_DESC_CHAIN_END;
}

/* Chain all the descriptors in the ring with an END */
static inline void
vring_desc_init_split(struct vring_desc *dp, uint16_t n)
{
	uint16_t i;

	for (i = 0; i < n - 1; i++)
		dp[i].next = (uint16_t)(i + 1);
	dp[i].next = VQ_RING_DESC_CHAIN_END;
}

/**
 * Tell the backend not to interrupt us. Implementation for packed virtqueues.
 */
static inline void
virtqueue_disable_intr_packed(struct virtqueue *vq)
{
	if (vq->vq_packed.event_flags_shadow != RING_EVENT_FLAGS_DISABLE) {
		vq->vq_packed.event_flags_shadow = RING_EVENT_FLAGS_DISABLE;
		vq->vq_packed.ring.driver->desc_event_flags =
			vq->vq_packed.event_flags_shadow;
	}
}

/**
 * Tell the backend not to interrupt us. Implementation for split virtqueues.
 */
static inline void
virtqueue_disable_intr_split(struct virtqueue *vq)
{
	vq->vq_split.ring.avail->flags |= VRING_AVAIL_F_NO_INTERRUPT;
}

/**
 * Tell the backend not to interrupt us.
 */
static inline void
virtqueue_disable_intr(struct virtqueue *vq)
{
	if (vtpci_packed_queue(vq->hw))
		virtqueue_disable_intr_packed(vq);
	else
		virtqueue_disable_intr_split(vq);
}

/**
 * Tell the backend to interrupt. Implementation for packed virtqueues.
 */
static inline void
virtqueue_enable_intr_packed(struct virtqueue *vq)
{
	if (vq->vq_packed.event_flags_shadow == RING_EVENT_FLAGS_DISABLE) {
		vq->vq_packed.event_flags_shadow = RING_EVENT_FLAGS_ENABLE;
		vq->vq_packed.ring.driver->desc_event_flags =
			vq->vq_packed.event_flags_shadow;
	}
}

/**
 * Tell the backend to interrupt. Implementation for split virtqueues.
 */
static inline void
virtqueue_enable_intr_split(struct virtqueue *vq)
{
	vq->vq_split.ring.avail->flags &= (~VRING_AVAIL_F_NO_INTERRUPT);
}

/**
 * Tell the backend to interrupt us.
 */
static inline void
virtqueue_enable_intr(struct virtqueue *vq)
{
	if (vtpci_packed_queue(vq->hw))
		virtqueue_enable_intr_packed(vq);
	else
		virtqueue_enable_intr_split(vq);
}

/**
 *  Dump virtqueue internal structures, for debug purpose only.
 */
void virtqueue_dump(struct virtqueue *vq);
/**
 *  Get all mbufs to be freed.
 */
struct rte_mbuf *virtqueue_detach_unused(struct virtqueue *vq);

/* Flush the elements in the used ring. */
void virtqueue_rxvq_flush(struct virtqueue *vq);

int virtqueue_rxvq_reset_packed(struct virtqueue *vq);

int virtqueue_txvq_reset_packed(struct virtqueue *vq);

static inline int
virtqueue_full(const struct virtqueue *vq)
{
	return vq->vq_free_cnt == 0;
}

static inline int
virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx)
{
	if (vtpci_queue_idx == hw->max_queue_pairs * 2)
		return VTNET_CQ;
	else if (vtpci_queue_idx % 2 == 0)
		return VTNET_RQ;
	else
		return VTNET_TQ;
}

/* virtqueue_nused has load-acquire or rte_cio_rmb insed */
static inline uint16_t
virtqueue_nused(const struct virtqueue *vq)
{
	uint16_t idx;

	if (vq->hw->weak_barriers) {
	/**
	 * x86 prefers to using rte_smp_rmb over __atomic_load_n as it
	 * reports a slightly better perf, which comes from the saved
	 * branch by the compiler.
	 * The if and else branches are identical with the smp and cio
	 * barriers both defined as compiler barriers on x86.
	 */
#ifdef RTE_ARCH_X86_64
		idx = vq->vq_split.ring.used->idx;
		rte_smp_rmb();
#else
		idx = __atomic_load_n(&(vq)->vq_split.ring.used->idx,
				__ATOMIC_ACQUIRE);
#endif
	} else {
		idx = vq->vq_split.ring.used->idx;
		rte_cio_rmb();
	}
	return idx - vq->vq_used_cons_idx;
}

void vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx);
void vq_ring_free_chain_packed(struct virtqueue *vq, uint16_t used_idx);
void vq_ring_free_inorder(struct virtqueue *vq, uint16_t desc_idx,
			  uint16_t num);

static inline void
vq_update_avail_idx(struct virtqueue *vq)
{
	if (vq->hw->weak_barriers) {
	/* x86 prefers to using rte_smp_wmb over __atomic_store_n as
	 * it reports a slightly better perf, which comes from the
	 * saved branch by the compiler.
	 * The if and else branches are identical with the smp and
	 * cio barriers both defined as compiler barriers on x86.
	 */
#ifdef RTE_ARCH_X86_64
		rte_smp_wmb();
		vq->vq_split.ring.avail->idx = vq->vq_avail_idx;
#else
		__atomic_store_n(&vq->vq_split.ring.avail->idx,
				 vq->vq_avail_idx, __ATOMIC_RELEASE);
#endif
	} else {
		rte_cio_wmb();
		vq->vq_split.ring.avail->idx = vq->vq_avail_idx;
	}
}

static inline void
vq_update_avail_ring(struct virtqueue *vq, uint16_t desc_idx)
{
	uint16_t avail_idx;
	/*
	 * Place the head of the descriptor chain into the next slot and make
	 * it usable to the host. The chain is made available now rather than
	 * deferring to virtqueue_notify() in the hopes that if the host is
	 * currently running on another CPU, we can keep it processing the new
	 * descriptor.
	 */
	avail_idx = (uint16_t)(vq->vq_avail_idx & (vq->vq_nentries - 1));
	if (unlikely(vq->vq_split.ring.avail->ring[avail_idx] != desc_idx))
		vq->vq_split.ring.avail->ring[avail_idx] = desc_idx;
	vq->vq_avail_idx++;
}

static inline int
virtqueue_kick_prepare(struct virtqueue *vq)
{
	/*
	 * Ensure updated avail->idx is visible to vhost before reading
	 * the used->flags.
	 */
	virtio_mb(vq->hw->weak_barriers);
	return !(vq->vq_split.ring.used->flags & VRING_USED_F_NO_NOTIFY);
}

static inline int
virtqueue_kick_prepare_packed(struct virtqueue *vq)
{
	uint16_t flags;

	/*
	 * Ensure updated data is visible to vhost before reading the flags.
	 */
	virtio_mb(vq->hw->weak_barriers);
	flags = vq->vq_packed.ring.device->desc_event_flags;

	return flags != RING_EVENT_FLAGS_DISABLE;
}

/*
 * virtqueue_kick_prepare*() or the virtio_wmb() should be called
 * before this function to be sure that all the data is visible to vhost.
 */
static inline void
virtqueue_notify(struct virtqueue *vq)
{
	VTPCI_OPS(vq->hw)->notify_queue(vq->hw, vq);
}

#ifdef RTE_LIBRTE_VIRTIO_DEBUG_DUMP
#define VIRTQUEUE_DUMP(vq) do { \
	uint16_t used_idx, nused; \
	used_idx = __atomic_load_n(&(vq)->vq_split.ring.used->idx, \
				   __ATOMIC_RELAXED); \
	nused = (uint16_t)(used_idx - (vq)->vq_used_cons_idx); \
	if (vtpci_packed_queue((vq)->hw)) { \
		PMD_INIT_LOG(DEBUG, \
		"VQ: - size=%d; free=%d; used_cons_idx=%d; avail_idx=%d;" \
		" cached_flags=0x%x; used_wrap_counter=%d", \
		(vq)->vq_nentries, (vq)->vq_free_cnt, (vq)->vq_used_cons_idx, \
		(vq)->vq_avail_idx, (vq)->vq_packed.cached_flags, \
		(vq)->vq_packed.used_wrap_counter); \
		break; \
	} \
	PMD_INIT_LOG(DEBUG, \
	  "VQ: - size=%d; free=%d; used=%d; desc_head_idx=%d;" \
	  " avail.idx=%d; used_cons_idx=%d; used.idx=%d;" \
	  " avail.flags=0x%x; used.flags=0x%x", \
	  (vq)->vq_nentries, (vq)->vq_free_cnt, nused, (vq)->vq_desc_head_idx, \
	  (vq)->vq_split.ring.avail->idx, (vq)->vq_used_cons_idx, \
	  __atomic_load_n(&(vq)->vq_split.ring.used->idx, __ATOMIC_RELAXED), \
	  (vq)->vq_split.ring.avail->flags, (vq)->vq_split.ring.used->flags); \
} while (0)
#else
#define VIRTQUEUE_DUMP(vq) do { } while (0)
#endif

/* avoid write operation when necessary, to lessen cache issues */
#define ASSIGN_UNLESS_EQUAL(var, val) do {	\
	typeof(var) var_ = (var);		\
	typeof(val) val_ = (val);		\
	if ((var_) != (val_))			\
		(var_) = (val_);		\
} while (0)

#define virtqueue_clear_net_hdr(hdr) do {		\
	typeof(hdr) hdr_ = (hdr);			\
	ASSIGN_UNLESS_EQUAL((hdr_)->csum_start, 0);	\
	ASSIGN_UNLESS_EQUAL((hdr_)->csum_offset, 0);	\
	ASSIGN_UNLESS_EQUAL((hdr_)->flags, 0);		\
	ASSIGN_UNLESS_EQUAL((hdr_)->gso_type, 0);	\
	ASSIGN_UNLESS_EQUAL((hdr_)->gso_size, 0);	\
	ASSIGN_UNLESS_EQUAL((hdr_)->hdr_len, 0);	\
} while (0)

static inline void
virtqueue_xmit_offload(struct virtio_net_hdr *hdr,
			struct rte_mbuf *cookie,
			bool offload)
{
	if (offload) {
		if (cookie->ol_flags & PKT_TX_TCP_SEG)
			cookie->ol_flags |= PKT_TX_TCP_CKSUM;

		switch (cookie->ol_flags & PKT_TX_L4_MASK) {
		case PKT_TX_UDP_CKSUM:
			hdr->csum_start = cookie->l2_len + cookie->l3_len;
			hdr->csum_offset = offsetof(struct rte_udp_hdr,
				dgram_cksum);
			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
			break;

		case PKT_TX_TCP_CKSUM:
			hdr->csum_start = cookie->l2_len + cookie->l3_len;
			hdr->csum_offset = offsetof(struct rte_tcp_hdr, cksum);
			hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
			break;

		default:
			ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0);
			ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0);
			ASSIGN_UNLESS_EQUAL(hdr->flags, 0);
			break;
		}

		/* TCP Segmentation Offload */
		if (cookie->ol_flags & PKT_TX_TCP_SEG) {
			hdr->gso_type = (cookie->ol_flags & PKT_TX_IPV6) ?
				VIRTIO_NET_HDR_GSO_TCPV6 :
				VIRTIO_NET_HDR_GSO_TCPV4;
			hdr->gso_size = cookie->tso_segsz;
			hdr->hdr_len =
				cookie->l2_len +
				cookie->l3_len +
				cookie->l4_len;
		} else {
			ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0);
			ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0);
			ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0);
		}
	}
}

static inline void
virtqueue_enqueue_xmit_packed(struct virtnet_tx *txvq, struct rte_mbuf *cookie,
			      uint16_t needed, int can_push, int in_order)
{
	struct virtio_tx_region *txr = txvq->virtio_net_hdr_mz->addr;
	struct vq_desc_extra *dxp;
	struct virtqueue *vq = txvq->vq;
	struct vring_packed_desc *start_dp, *head_dp;
	uint16_t idx, id, head_idx, head_flags;
	int16_t head_size = vq->hw->vtnet_hdr_size;
	struct virtio_net_hdr *hdr;
	uint16_t prev;
	bool prepend_header = false;

	id = in_order ? vq->vq_avail_idx : vq->vq_desc_head_idx;

	dxp = &vq->vq_descx[id];
	dxp->ndescs = needed;
	dxp->cookie = cookie;

	head_idx = vq->vq_avail_idx;
	idx = head_idx;
	prev = head_idx;
	start_dp = vq->vq_packed.ring.desc;

	head_dp = &vq->vq_packed.ring.desc[idx];
	head_flags = cookie->next ? VRING_DESC_F_NEXT : 0;
	head_flags |= vq->vq_packed.cached_flags;

	if (can_push) {
		/* prepend cannot fail, checked by caller */
		hdr = rte_pktmbuf_mtod_offset(cookie, struct virtio_net_hdr *,
					      -head_size);
		prepend_header = true;

		/* if offload disabled, it is not zeroed below, do it now */
		if (!vq->hw->has_tx_offload)
			virtqueue_clear_net_hdr(hdr);
	} else {
		/* setup first tx ring slot to point to header
		 * stored in reserved region.
		 */
		start_dp[idx].addr  = txvq->virtio_net_hdr_mem +
			RTE_PTR_DIFF(&txr[idx].tx_hdr, txr);
		start_dp[idx].len   = vq->hw->vtnet_hdr_size;
		hdr = (struct virtio_net_hdr *)&txr[idx].tx_hdr;
		idx++;
		if (idx >= vq->vq_nentries) {
			idx -= vq->vq_nentries;
			vq->vq_packed.cached_flags ^=
				VRING_PACKED_DESC_F_AVAIL_USED;
		}
	}

	virtqueue_xmit_offload(hdr, cookie, vq->hw->has_tx_offload);

	do {
		uint16_t flags;

		start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq);
		start_dp[idx].len  = cookie->data_len;
		if (prepend_header) {
			start_dp[idx].addr -= head_size;
			start_dp[idx].len += head_size;
			prepend_header = false;
		}

		if (likely(idx != head_idx)) {
			flags = cookie->next ? VRING_DESC_F_NEXT : 0;
			flags |= vq->vq_packed.cached_flags;
			start_dp[idx].flags = flags;
		}
		prev = idx;
		idx++;
		if (idx >= vq->vq_nentries) {
			idx -= vq->vq_nentries;
			vq->vq_packed.cached_flags ^=
				VRING_PACKED_DESC_F_AVAIL_USED;
		}
	} while ((cookie = cookie->next) != NULL);

	start_dp[prev].id = id;

	vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - needed);
	vq->vq_avail_idx = idx;

	if (!in_order) {
		vq->vq_desc_head_idx = dxp->next;
		if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END)
			vq->vq_desc_tail_idx = VQ_RING_DESC_CHAIN_END;
	}

	virtqueue_store_flags_packed(head_dp, head_flags,
				     vq->hw->weak_barriers);
}

static void
vq_ring_free_id_packed(struct virtqueue *vq, uint16_t id)
{
	struct vq_desc_extra *dxp;

	dxp = &vq->vq_descx[id];
	vq->vq_free_cnt += dxp->ndescs;

	if (vq->vq_desc_tail_idx == VQ_RING_DESC_CHAIN_END)
		vq->vq_desc_head_idx = id;
	else
		vq->vq_descx[vq->vq_desc_tail_idx].next = id;

	vq->vq_desc_tail_idx = id;
	dxp->next = VQ_RING_DESC_CHAIN_END;
}

static void
virtio_xmit_cleanup_inorder_packed(struct virtqueue *vq, int num)
{
	uint16_t used_idx, id, curr_id, free_cnt = 0;
	uint16_t size = vq->vq_nentries;
	struct vring_packed_desc *desc = vq->vq_packed.ring.desc;
	struct vq_desc_extra *dxp;

	used_idx = vq->vq_used_cons_idx;
	/* desc_is_used has a load-acquire or rte_cio_rmb inside
	 * and wait for used desc in virtqueue.
	 */
	while (num > 0 && desc_is_used(&desc[used_idx], vq)) {
		id = desc[used_idx].id;
		do {
			curr_id = used_idx;
			dxp = &vq->vq_descx[used_idx];
			used_idx += dxp->ndescs;
			free_cnt += dxp->ndescs;
			num -= dxp->ndescs;
			if (used_idx >= size) {
				used_idx -= size;
				vq->vq_packed.used_wrap_counter ^= 1;
			}
			if (dxp->cookie != NULL) {
				rte_pktmbuf_free(dxp->cookie);
				dxp->cookie = NULL;
			}
		} while (curr_id != id);
	}
	vq->vq_used_cons_idx = used_idx;
	vq->vq_free_cnt += free_cnt;
}

static void
virtio_xmit_cleanup_normal_packed(struct virtqueue *vq, int num)
{
	uint16_t used_idx, id;
	uint16_t size = vq->vq_nentries;
	struct vring_packed_desc *desc = vq->vq_packed.ring.desc;
	struct vq_desc_extra *dxp;

	used_idx = vq->vq_used_cons_idx;
	/* desc_is_used has a load-acquire or rte_cio_rmb inside
	 * and wait for used desc in virtqueue.
	 */
	while (num-- && desc_is_used(&desc[used_idx], vq)) {
		id = desc[used_idx].id;
		dxp = &vq->vq_descx[id];
		vq->vq_used_cons_idx += dxp->ndescs;
		if (vq->vq_used_cons_idx >= size) {
			vq->vq_used_cons_idx -= size;
			vq->vq_packed.used_wrap_counter ^= 1;
		}
		vq_ring_free_id_packed(vq, id);
		if (dxp->cookie != NULL) {
			rte_pktmbuf_free(dxp->cookie);
			dxp->cookie = NULL;
		}
		used_idx = vq->vq_used_cons_idx;
	}
}

/* Cleanup from completed transmits. */
static inline void
virtio_xmit_cleanup_packed(struct virtqueue *vq, int num, int in_order)
{
	if (in_order)
		virtio_xmit_cleanup_inorder_packed(vq, num);
	else
		virtio_xmit_cleanup_normal_packed(vq, num);
}

static inline void
virtio_xmit_cleanup(struct virtqueue *vq, uint16_t num)
{
	uint16_t i, used_idx, desc_idx;
	for (i = 0; i < num; i++) {
		struct vring_used_elem *uep;
		struct vq_desc_extra *dxp;

		used_idx = (uint16_t)(vq->vq_used_cons_idx &
				(vq->vq_nentries - 1));
		uep = &vq->vq_split.ring.used->ring[used_idx];

		desc_idx = (uint16_t)uep->id;
		dxp = &vq->vq_descx[desc_idx];
		vq->vq_used_cons_idx++;
		vq_ring_free_chain(vq, desc_idx);

		if (dxp->cookie != NULL) {
			rte_pktmbuf_free(dxp->cookie);
			dxp->cookie = NULL;
		}
	}
}

/* Cleanup from completed inorder transmits. */
static __rte_always_inline void
virtio_xmit_cleanup_inorder(struct virtqueue *vq, uint16_t num)
{
	uint16_t i, idx = vq->vq_used_cons_idx;
	int16_t free_cnt = 0;
	struct vq_desc_extra *dxp = NULL;

	if (unlikely(num == 0))
		return;

	for (i = 0; i < num; i++) {
		dxp = &vq->vq_descx[idx++ & (vq->vq_nentries - 1)];
		free_cnt += dxp->ndescs;
		if (dxp->cookie != NULL) {
			rte_pktmbuf_free(dxp->cookie);
			dxp->cookie = NULL;
		}
	}

	vq->vq_free_cnt += free_cnt;
	vq->vq_used_cons_idx = idx;
}
#endif /* _VIRTQUEUE_H_ */