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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2018 Intel Corporation
 */

#ifndef _VHOST_NET_CDEV_H_
#define _VHOST_NET_CDEV_H_
#include <stdint.h>
#include <stdio.h>
#include <stdbool.h>
#include <sys/types.h>
#include <sys/queue.h>
#include <unistd.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h>
#include <sys/socket.h>
#include <linux/if.h>

#include <rte_log.h>
#include <rte_ether.h>
#include <rte_rwlock.h>
#include <rte_malloc.h>

#include "rte_vhost.h"
#include "rte_vdpa.h"
#include "rte_vdpa_dev.h"

#include "rte_vhost_async.h"

/* Used to indicate that the device is running on a data core */
#define VIRTIO_DEV_RUNNING 1
/* Used to indicate that the device is ready to operate */
#define VIRTIO_DEV_READY 2
/* Used to indicate that the built-in vhost net device backend is enabled */
#define VIRTIO_DEV_BUILTIN_VIRTIO_NET 4
/* Used to indicate that the device has its own data path and configured */
#define VIRTIO_DEV_VDPA_CONFIGURED 8
/* Used to indicate that the feature negotiation failed */
#define VIRTIO_DEV_FEATURES_FAILED 16

/* Backend value set by guest. */
#define VIRTIO_DEV_STOPPED -1

#define BUF_VECTOR_MAX 256

#define VHOST_LOG_CACHE_NR 32

#define MAX_PKT_BURST 32

#define ASYNC_MAX_POLL_SEG 255

#define VHOST_MAX_ASYNC_IT (MAX_PKT_BURST * 2)
#define VHOST_MAX_ASYNC_VEC (BUF_VECTOR_MAX * 2)

#define PACKED_DESC_ENQUEUE_USED_FLAG(w)	\
	((w) ? (VRING_DESC_F_AVAIL | VRING_DESC_F_USED | VRING_DESC_F_WRITE) : \
		VRING_DESC_F_WRITE)
#define PACKED_DESC_DEQUEUE_USED_FLAG(w)	\
	((w) ? (VRING_DESC_F_AVAIL | VRING_DESC_F_USED) : 0x0)
#define PACKED_DESC_SINGLE_DEQUEUE_FLAG (VRING_DESC_F_NEXT | \
					 VRING_DESC_F_INDIRECT)

#define PACKED_BATCH_SIZE (RTE_CACHE_LINE_SIZE / \
			    sizeof(struct vring_packed_desc))
#define PACKED_BATCH_MASK (PACKED_BATCH_SIZE - 1)

#ifdef VHOST_GCC_UNROLL_PRAGMA
#define vhost_for_each_try_unroll(iter, val, size) _Pragma("GCC unroll 4") \
	for (iter = val; iter < size; iter++)
#endif

#ifdef VHOST_CLANG_UNROLL_PRAGMA
#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll 4") \
	for (iter = val; iter < size; iter++)
#endif

#ifdef VHOST_ICC_UNROLL_PRAGMA
#define vhost_for_each_try_unroll(iter, val, size) _Pragma("unroll (4)") \
	for (iter = val; iter < size; iter++)
#endif

#ifndef vhost_for_each_try_unroll
#define vhost_for_each_try_unroll(iter, val, num) \
	for (iter = val; iter < num; iter++)
#endif

/**
 * Structure contains buffer address, length and descriptor index
 * from vring to do scatter RX.
 */
struct buf_vector {
	uint64_t buf_iova;
	uint64_t buf_addr;
	uint32_t buf_len;
	uint32_t desc_idx;
};

/*
 * A structure to hold some fields needed in zero copy code path,
 * mainly for associating an mbuf with the right desc_idx.
 */
struct zcopy_mbuf {
	struct rte_mbuf *mbuf;
	uint32_t desc_idx;
	uint16_t desc_count;
	uint16_t in_use;

	TAILQ_ENTRY(zcopy_mbuf) next;
};
TAILQ_HEAD(zcopy_mbuf_list, zcopy_mbuf);

/*
 * Structure contains the info for each batched memory copy.
 */
struct batch_copy_elem {
	void *dst;
	void *src;
	uint32_t len;
	uint64_t log_addr;
};

/*
 * Structure that contains the info for batched dirty logging.
 */
struct log_cache_entry {
	uint32_t offset;
	unsigned long val;
};

struct vring_used_elem_packed {
	uint16_t id;
	uint16_t flags;
	uint32_t len;
	uint32_t count;
};

/**
 * Structure contains variables relevant to RX/TX virtqueues.
 */
struct vhost_virtqueue {
	union {
		struct vring_desc	*desc;
		struct vring_packed_desc   *desc_packed;
	};
	union {
		struct vring_avail	*avail;
		struct vring_packed_desc_event *driver_event;
	};
	union {
		struct vring_used	*used;
		struct vring_packed_desc_event *device_event;
	};
	uint32_t		size;

	uint16_t		last_avail_idx;
	uint16_t		last_used_idx;
	/* Last used index we notify to front end. */
	uint16_t		signalled_used;
	bool			signalled_used_valid;
#define VIRTIO_INVALID_EVENTFD		(-1)
#define VIRTIO_UNINITIALIZED_EVENTFD	(-2)

	/* Backend value to determine if device should started/stopped */
	int			backend;
	int			enabled;
	int			access_ok;
	int			ready;
	int			notif_enable;
#define VIRTIO_UNINITIALIZED_NOTIF	(-1)

	rte_spinlock_t		access_lock;

	/* Used to notify the guest (trigger interrupt) */
	int			callfd;
	/* Currently unused as polling mode is enabled */
	int			kickfd;

	/* Physical address of used ring, for logging */
	uint64_t		log_guest_addr;

	/* inflight share memory info */
	union {
		struct rte_vhost_inflight_info_split *inflight_split;
		struct rte_vhost_inflight_info_packed *inflight_packed;
	};
	struct rte_vhost_resubmit_info *resubmit_inflight;
	uint64_t		global_counter;

	uint16_t		nr_zmbuf;
	uint16_t		zmbuf_size;
	uint16_t		last_zmbuf_idx;
	struct zcopy_mbuf	*zmbufs;
	struct zcopy_mbuf_list	zmbuf_list;

	union {
		struct vring_used_elem  *shadow_used_split;
		struct vring_used_elem_packed *shadow_used_packed;
	};
	uint16_t                shadow_used_idx;
	/* Record packed ring enqueue latest desc cache aligned index */
	uint16_t		shadow_aligned_idx;
	/* Record packed ring first dequeue desc index */
	uint16_t		shadow_last_used_idx;
	struct vhost_vring_addr ring_addrs;

	struct batch_copy_elem	*batch_copy_elems;
	uint16_t		batch_copy_nb_elems;
	bool			used_wrap_counter;
	bool			avail_wrap_counter;

	struct log_cache_entry log_cache[VHOST_LOG_CACHE_NR];
	uint16_t log_cache_nb_elem;

	rte_rwlock_t	iotlb_lock;
	rte_rwlock_t	iotlb_pending_lock;
	struct rte_mempool *iotlb_pool;
	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_list;
	int				iotlb_cache_nr;
	TAILQ_HEAD(, vhost_iotlb_entry) iotlb_pending_list;

	/* operation callbacks for async dma */
	struct rte_vhost_async_channel_ops	async_ops;

	struct rte_vhost_iov_iter it_pool[VHOST_MAX_ASYNC_IT];
	struct iovec vec_pool[VHOST_MAX_ASYNC_VEC];

	/* async data transfer status */
	uintptr_t	**async_pkts_pending;
	#define		ASYNC_PENDING_INFO_N_MSK 0xFFFF
	#define		ASYNC_PENDING_INFO_N_SFT 16
	uint64_t	*async_pending_info;
	uint16_t	async_pkts_idx;
	uint16_t	async_pkts_inflight_n;
	uint16_t	async_last_seg_n;

	/* vq async features */
	bool		async_inorder;
	bool		async_registered;
	uint16_t	async_threshold;
} __rte_cache_aligned;

/* Virtio device status as per Virtio specification */
#define VIRTIO_DEVICE_STATUS_ACK		0x01
#define VIRTIO_DEVICE_STATUS_DRIVER		0x02
#define VIRTIO_DEVICE_STATUS_DRIVER_OK		0x04
#define VIRTIO_DEVICE_STATUS_FEATURES_OK	0x08
#define VIRTIO_DEVICE_STATUS_DEV_NEED_RESET	0x40
#define VIRTIO_DEVICE_STATUS_FAILED		0x80

#define VHOST_MAX_VRING			0x100
#define VHOST_MAX_QUEUE_PAIRS		0x80

/* Declare IOMMU related bits for older kernels */
#ifndef VIRTIO_F_IOMMU_PLATFORM

#define VIRTIO_F_IOMMU_PLATFORM 33

struct vhost_iotlb_msg {
	__u64 iova;
	__u64 size;
	__u64 uaddr;
#define VHOST_ACCESS_RO      0x1
#define VHOST_ACCESS_WO      0x2
#define VHOST_ACCESS_RW      0x3
	__u8 perm;
#define VHOST_IOTLB_MISS           1
#define VHOST_IOTLB_UPDATE         2
#define VHOST_IOTLB_INVALIDATE     3
#define VHOST_IOTLB_ACCESS_FAIL    4
	__u8 type;
};

#define VHOST_IOTLB_MSG 0x1

struct vhost_msg {
	int type;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};
#endif

/*
 * Define virtio 1.0 for older kernels
 */
#ifndef VIRTIO_F_VERSION_1
 #define VIRTIO_F_VERSION_1 32
#endif

/* Declare packed ring related bits for older kernels */
#ifndef VIRTIO_F_RING_PACKED

#define VIRTIO_F_RING_PACKED 34

struct vring_packed_desc {
	uint64_t addr;
	uint32_t len;
	uint16_t id;
	uint16_t flags;
};

struct vring_packed_desc_event {
	uint16_t off_wrap;
	uint16_t flags;
};
#endif

/*
 * Declare below packed ring defines unconditionally
 * as Kernel header might use different names.
 */
#define VRING_DESC_F_AVAIL	(1ULL << 7)
#define VRING_DESC_F_USED	(1ULL << 15)

#define VRING_EVENT_F_ENABLE 0x0
#define VRING_EVENT_F_DISABLE 0x1
#define VRING_EVENT_F_DESC 0x2

/*
 * Available and used descs are in same order
 */
#ifndef VIRTIO_F_IN_ORDER
#define VIRTIO_F_IN_ORDER      35
#endif

/* Features supported by this builtin vhost-user net driver. */
#define VIRTIO_NET_SUPPORTED_FEATURES ((1ULL << VIRTIO_NET_F_MRG_RXBUF) | \
				(1ULL << VIRTIO_F_ANY_LAYOUT) | \
				(1ULL << VIRTIO_NET_F_CTRL_VQ) | \
				(1ULL << VIRTIO_NET_F_CTRL_RX) | \
				(1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) | \
				(1ULL << VIRTIO_NET_F_MQ)      | \
				(1ULL << VIRTIO_F_VERSION_1)   | \
				(1ULL << VHOST_F_LOG_ALL)      | \
				(1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
				(1ULL << VIRTIO_NET_F_GSO) | \
				(1ULL << VIRTIO_NET_F_HOST_TSO4) | \
				(1ULL << VIRTIO_NET_F_HOST_TSO6) | \
				(1ULL << VIRTIO_NET_F_HOST_UFO) | \
				(1ULL << VIRTIO_NET_F_HOST_ECN) | \
				(1ULL << VIRTIO_NET_F_CSUM)    | \
				(1ULL << VIRTIO_NET_F_GUEST_CSUM) | \
				(1ULL << VIRTIO_NET_F_GUEST_TSO4) | \
				(1ULL << VIRTIO_NET_F_GUEST_TSO6) | \
				(1ULL << VIRTIO_NET_F_GUEST_UFO) | \
				(1ULL << VIRTIO_NET_F_GUEST_ECN) | \
				(1ULL << VIRTIO_RING_F_INDIRECT_DESC) | \
				(1ULL << VIRTIO_RING_F_EVENT_IDX) | \
				(1ULL << VIRTIO_NET_F_MTU)  | \
				(1ULL << VIRTIO_F_IN_ORDER) | \
				(1ULL << VIRTIO_F_IOMMU_PLATFORM) | \
				(1ULL << VIRTIO_F_RING_PACKED))


struct guest_page {
	uint64_t guest_phys_addr;
	uint64_t host_phys_addr;
	uint64_t size;
};

struct inflight_mem_info {
	int		fd;
	void		*addr;
	uint64_t	size;
};

/**
 * Device structure contains all configuration information relating
 * to the device.
 */
struct virtio_net {
	/* Frontend (QEMU) memory and memory region information */
	struct rte_vhost_memory	*mem;
	uint64_t		features;
	uint64_t		protocol_features;
	int			vid;
	uint32_t		flags;
	uint16_t		vhost_hlen;
	/* to tell if we need broadcast rarp packet */
	int16_t			broadcast_rarp;
	uint32_t		nr_vring;
	int			dequeue_zero_copy;
	int			async_copy;
	int			extbuf;
	int			linearbuf;
	struct vhost_virtqueue	*virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];
	struct inflight_mem_info *inflight_info;
#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
	char			ifname[IF_NAME_SZ];
	uint64_t		log_size;
	uint64_t		log_base;
	uint64_t		log_addr;
	struct rte_ether_addr	mac;
	uint16_t		mtu;
	uint8_t			status;

	struct vhost_device_ops const *notify_ops;

	uint32_t		nr_guest_pages;
	uint32_t		max_guest_pages;
	struct guest_page       *guest_pages;

	int			slave_req_fd;
	rte_spinlock_t		slave_req_lock;

	int			postcopy_ufd;
	int			postcopy_listening;

	struct rte_vdpa_device *vdpa_dev;

	/* context data for the external message handlers */
	void			*extern_data;
	/* pre and post vhost user message handlers for the device */
	struct rte_vhost_user_extern_ops extern_ops;
} __rte_cache_aligned;

static __rte_always_inline bool
vq_is_packed(struct virtio_net *dev)
{
	return dev->features & (1ull << VIRTIO_F_RING_PACKED);
}

static inline bool
desc_is_avail(struct vring_packed_desc *desc, bool wrap_counter)
{
	uint16_t flags = __atomic_load_n(&desc->flags, __ATOMIC_ACQUIRE);

	return wrap_counter == !!(flags & VRING_DESC_F_AVAIL) &&
		wrap_counter != !!(flags & VRING_DESC_F_USED);
}

static inline void
vq_inc_last_used_packed(struct vhost_virtqueue *vq, uint16_t num)
{
	vq->last_used_idx += num;
	if (vq->last_used_idx >= vq->size) {
		vq->used_wrap_counter ^= 1;
		vq->last_used_idx -= vq->size;
	}
}

static inline void
vq_inc_last_avail_packed(struct vhost_virtqueue *vq, uint16_t num)
{
	vq->last_avail_idx += num;
	if (vq->last_avail_idx >= vq->size) {
		vq->avail_wrap_counter ^= 1;
		vq->last_avail_idx -= vq->size;
	}
}

void __vhost_log_cache_write(struct virtio_net *dev,
		struct vhost_virtqueue *vq,
		uint64_t addr, uint64_t len);
void __vhost_log_cache_write_iova(struct virtio_net *dev,
		struct vhost_virtqueue *vq,
		uint64_t iova, uint64_t len);
void __vhost_log_cache_sync(struct virtio_net *dev,
		struct vhost_virtqueue *vq);
void __vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len);
void __vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
			    uint64_t iova, uint64_t len);

static __rte_always_inline void
vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
{
	if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL)))
		__vhost_log_write(dev, addr, len);
}

static __rte_always_inline void
vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL)))
		__vhost_log_cache_sync(dev, vq);
}

static __rte_always_inline void
vhost_log_cache_write(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t addr, uint64_t len)
{
	if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL)))
		__vhost_log_cache_write(dev, vq, addr, len);
}

static __rte_always_inline void
vhost_log_cache_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t offset, uint64_t len)
{
	if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL))) {
		if (unlikely(vq->log_guest_addr == 0))
			return;
		__vhost_log_cache_write(dev, vq, vq->log_guest_addr + offset,
					len);
	}
}

static __rte_always_inline void
vhost_log_used_vring(struct virtio_net *dev, struct vhost_virtqueue *vq,
		     uint64_t offset, uint64_t len)
{
	if (unlikely(dev->features & (1ULL << VHOST_F_LOG_ALL))) {
		if (unlikely(vq->log_guest_addr == 0))
			return;
		__vhost_log_write(dev, vq->log_guest_addr + offset, len);
	}
}

static __rte_always_inline void
vhost_log_cache_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
			   uint64_t iova, uint64_t len)
{
	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
		return;

	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
		__vhost_log_cache_write_iova(dev, vq, iova, len);
	else
		__vhost_log_cache_write(dev, vq, iova, len);
}

static __rte_always_inline void
vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
			   uint64_t iova, uint64_t len)
{
	if (likely(!(dev->features & (1ULL << VHOST_F_LOG_ALL))))
		return;

	if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
		__vhost_log_write_iova(dev, vq, iova, len);
	else
		__vhost_log_write(dev, iova, len);
}

extern int vhost_config_log_level;
extern int vhost_data_log_level;

#define VHOST_LOG_CONFIG(level, fmt, args...)			\
	rte_log(RTE_LOG_ ## level, vhost_config_log_level,	\
		"VHOST_CONFIG: " fmt, ##args)

#define VHOST_LOG_DATA(level, fmt, args...) \
	(void)((RTE_LOG_ ## level <= RTE_LOG_DP_LEVEL) ?	\
	 rte_log(RTE_LOG_ ## level,  vhost_data_log_level,	\
		"VHOST_DATA : " fmt, ##args) :			\
	 0)

#ifdef RTE_LIBRTE_VHOST_DEBUG
#define VHOST_MAX_PRINT_BUFF 6072
#define PRINT_PACKET(device, addr, size, header) do { \
	char *pkt_addr = (char *)(addr); \
	unsigned int index; \
	char packet[VHOST_MAX_PRINT_BUFF]; \
	\
	if ((header)) \
		snprintf(packet, VHOST_MAX_PRINT_BUFF, "(%d) Header size %d: ", (device->vid), (size)); \
	else \
		snprintf(packet, VHOST_MAX_PRINT_BUFF, "(%d) Packet size %d: ", (device->vid), (size)); \
	for (index = 0; index < (size); index++) { \
		snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), \
			"%02hhx ", pkt_addr[index]); \
	} \
	snprintf(packet + strnlen(packet, VHOST_MAX_PRINT_BUFF), VHOST_MAX_PRINT_BUFF - strnlen(packet, VHOST_MAX_PRINT_BUFF), "\n"); \
	\
	VHOST_LOG_DATA(DEBUG, "%s", packet); \
} while (0)
#else
#define PRINT_PACKET(device, addr, size, header) do {} while (0)
#endif

#define MAX_VHOST_DEVICE	1024
extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];

#define VHOST_BINARY_SEARCH_THRESH 256

static __rte_always_inline int guest_page_addrcmp(const void *p1,
						const void *p2)
{
	const struct guest_page *page1 = (const struct guest_page *)p1;
	const struct guest_page *page2 = (const struct guest_page *)p2;

	if (page1->guest_phys_addr > page2->guest_phys_addr)
		return 1;
	if (page1->guest_phys_addr < page2->guest_phys_addr)
		return -1;

	return 0;
}

/* Convert guest physical address to host physical address */
static __rte_always_inline rte_iova_t
gpa_to_hpa(struct virtio_net *dev, uint64_t gpa, uint64_t size)
{
	uint32_t i;
	struct guest_page *page;
	struct guest_page key;

	if (dev->nr_guest_pages >= VHOST_BINARY_SEARCH_THRESH) {
		key.guest_phys_addr = gpa;
		page = bsearch(&key, dev->guest_pages, dev->nr_guest_pages,
			       sizeof(struct guest_page), guest_page_addrcmp);
		if (page) {
			if (gpa + size < page->guest_phys_addr + page->size)
				return gpa - page->guest_phys_addr +
					page->host_phys_addr;
		}
	} else {
		for (i = 0; i < dev->nr_guest_pages; i++) {
			page = &dev->guest_pages[i];

			if (gpa >= page->guest_phys_addr &&
			    gpa + size < page->guest_phys_addr +
			    page->size)
				return gpa - page->guest_phys_addr +
				       page->host_phys_addr;
		}
	}

	return 0;
}

static __rte_always_inline rte_iova_t
gpa_to_first_hpa(struct virtio_net *dev, uint64_t gpa,
	uint64_t gpa_size, uint64_t *hpa_size)
{
	uint32_t i;
	struct guest_page *page;
	struct guest_page key;

	*hpa_size = gpa_size;
	if (dev->nr_guest_pages >= VHOST_BINARY_SEARCH_THRESH) {
		key.guest_phys_addr = gpa & ~(dev->guest_pages[0].size - 1);
		page = bsearch(&key, dev->guest_pages, dev->nr_guest_pages,
			       sizeof(struct guest_page), guest_page_addrcmp);
		if (page) {
			if (gpa + gpa_size <=
					page->guest_phys_addr + page->size) {
				return gpa - page->guest_phys_addr +
					page->host_phys_addr;
			} else if (gpa < page->guest_phys_addr +
						page->size) {
				*hpa_size = page->guest_phys_addr +
					page->size - gpa;
				return gpa - page->guest_phys_addr +
					page->host_phys_addr;
			}
		}
	} else {
		for (i = 0; i < dev->nr_guest_pages; i++) {
			page = &dev->guest_pages[i];

			if (gpa >= page->guest_phys_addr) {
				if (gpa + gpa_size <=
					page->guest_phys_addr + page->size) {
					return gpa - page->guest_phys_addr +
						page->host_phys_addr;
				} else if (gpa < page->guest_phys_addr +
							page->size) {
					*hpa_size = page->guest_phys_addr +
						page->size - gpa;
					return gpa - page->guest_phys_addr +
						page->host_phys_addr;
				}
			}
		}
	}

	*hpa_size = 0;
	return 0;
}

static __rte_always_inline uint64_t
hva_to_gpa(struct virtio_net *dev, uint64_t vva, uint64_t len)
{
	struct rte_vhost_mem_region *r;
	uint32_t i;

	if (unlikely(!dev || !dev->mem))
		return 0;

	for (i = 0; i < dev->mem->nregions; i++) {
		r = &dev->mem->regions[i];

		if (vva >= r->host_user_addr &&
		    vva + len <  r->host_user_addr + r->size) {
			return r->guest_phys_addr + vva - r->host_user_addr;
		}
	}
	return 0;
}

static __rte_always_inline struct virtio_net *
get_device(int vid)
{
	struct virtio_net *dev = vhost_devices[vid];

	if (unlikely(!dev)) {
		VHOST_LOG_CONFIG(ERR,
			"(%d) device not found.\n", vid);
	}

	return dev;
}

int vhost_new_device(void);
void cleanup_device(struct virtio_net *dev, int destroy);
void reset_device(struct virtio_net *dev);
void vhost_destroy_device(int);
void vhost_destroy_device_notify(struct virtio_net *dev);

void cleanup_vq(struct vhost_virtqueue *vq, int destroy);
void cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq);
void free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq);

int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx);

void vhost_attach_vdpa_device(int vid, struct rte_vdpa_device *dev);

void vhost_set_ifname(int, const char *if_name, unsigned int if_len);
void vhost_enable_dequeue_zero_copy(int vid);
void vhost_set_builtin_virtio_net(int vid, bool enable);
void vhost_enable_extbuf(int vid);
void vhost_enable_linearbuf(int vid);
int vhost_enable_guest_notification(struct virtio_net *dev,
		struct vhost_virtqueue *vq, int enable);

struct vhost_device_ops const *vhost_driver_callback_get(const char *path);

/*
 * Backend-specific cleanup.
 *
 * TODO: fix it; we have one backend now
 */
void vhost_backend_cleanup(struct virtio_net *dev);

uint64_t __vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t iova, uint64_t *len, uint8_t perm);
void *vhost_alloc_copy_ind_table(struct virtio_net *dev,
			struct vhost_virtqueue *vq,
			uint64_t desc_addr, uint64_t desc_len);
int vring_translate(struct virtio_net *dev, struct vhost_virtqueue *vq);
uint64_t translate_log_addr(struct virtio_net *dev, struct vhost_virtqueue *vq,
		uint64_t log_addr);
void vring_invalidate(struct virtio_net *dev, struct vhost_virtqueue *vq);

static __rte_always_inline uint64_t
vhost_iova_to_vva(struct virtio_net *dev, struct vhost_virtqueue *vq,
			uint64_t iova, uint64_t *len, uint8_t perm)
{
	if (!(dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
		return rte_vhost_va_from_guest_pa(dev->mem, iova, len);

	return __vhost_iova_to_vva(dev, vq, iova, len, perm);
}

#define vhost_avail_event(vr) \
	(*(volatile uint16_t*)&(vr)->used->ring[(vr)->size])
#define vhost_used_event(vr) \
	(*(volatile uint16_t*)&(vr)->avail->ring[(vr)->size])

/*
 * The following is used with VIRTIO_RING_F_EVENT_IDX.
 * Assuming a given event_idx value from the other size, if we have
 * just incremented index from old to new_idx, should we trigger an
 * event?
 */
static __rte_always_inline int
vhost_need_event(uint16_t event_idx, uint16_t new_idx, uint16_t old)
{
	return (uint16_t)(new_idx - event_idx - 1) < (uint16_t)(new_idx - old);
}

static __rte_always_inline void
vhost_vring_call_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	/* Flush used->idx update before we read avail->flags. */
	rte_smp_mb();

	/* Don't kick guest if we don't reach index specified by guest. */
	if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX)) {
		uint16_t old = vq->signalled_used;
		uint16_t new = vq->async_pkts_inflight_n ?
					vq->used->idx:vq->last_used_idx;
		bool signalled_used_valid = vq->signalled_used_valid;

		vq->signalled_used = new;
		vq->signalled_used_valid = true;

		VHOST_LOG_DATA(DEBUG, "%s: used_event_idx=%d, old=%d, new=%d\n",
			__func__,
			vhost_used_event(vq),
			old, new);

		if ((vhost_need_event(vhost_used_event(vq), new, old) &&
					(vq->callfd >= 0)) ||
				unlikely(!signalled_used_valid)) {
			eventfd_write(vq->callfd, (eventfd_t) 1);
			if (dev->notify_ops->guest_notified)
				dev->notify_ops->guest_notified(dev->vid);
		}
	} else {
		/* Kick the guest if necessary. */
		if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
				&& (vq->callfd >= 0)) {
			eventfd_write(vq->callfd, (eventfd_t)1);
			if (dev->notify_ops->guest_notified)
				dev->notify_ops->guest_notified(dev->vid);
		}
	}
}

static __rte_always_inline void
vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
	uint16_t old, new, off, off_wrap;
	bool signalled_used_valid, kick = false;

	/* Flush used desc update. */
	rte_smp_mb();

	if (!(dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))) {
		if (vq->driver_event->flags !=
				VRING_EVENT_F_DISABLE)
			kick = true;
		goto kick;
	}

	old = vq->signalled_used;
	new = vq->last_used_idx;
	vq->signalled_used = new;
	signalled_used_valid = vq->signalled_used_valid;
	vq->signalled_used_valid = true;

	if (vq->driver_event->flags != VRING_EVENT_F_DESC) {
		if (vq->driver_event->flags != VRING_EVENT_F_DISABLE)
			kick = true;
		goto kick;
	}

	if (unlikely(!signalled_used_valid)) {
		kick = true;
		goto kick;
	}

	rte_smp_rmb();

	off_wrap = vq->driver_event->off_wrap;
	off = off_wrap & ~(1 << 15);

	if (new <= old)
		old -= vq->size;

	if (vq->used_wrap_counter != off_wrap >> 15)
		off -= vq->size;

	if (vhost_need_event(off, new, old))
		kick = true;
kick:
	if (kick) {
		eventfd_write(vq->callfd, (eventfd_t)1);
		if (dev->notify_ops->guest_notified)
			dev->notify_ops->guest_notified(dev->vid);
	}
}

static __rte_always_inline void
free_ind_table(void *idesc)
{
	rte_free(idesc);
}

static __rte_always_inline void
restore_mbuf(struct rte_mbuf *m)
{
	uint32_t mbuf_size, priv_size;

	while (m) {
		priv_size = rte_pktmbuf_priv_size(m->pool);
		mbuf_size = sizeof(struct rte_mbuf) + priv_size;
		/* start of buffer is after mbuf structure and priv data */

		m->buf_addr = (char *)m + mbuf_size;
		m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size;
		m = m->next;
	}
}

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

	return true;
}

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

#endif /* _VHOST_NET_CDEV_H_ */