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
 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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2016 Intel Corporation
 */

#include <sys/socket.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/un.h>
#include <string.h>
#include <errno.h>

#include <rte_alarm.h>
#include <rte_string_fns.h>
#include <rte_fbarray.h>

#include "vhost.h"
#include "virtio_user_dev.h"

struct vhost_user_data {
	int vhostfd;
	int listenfd;
	uint64_t protocol_features;
};

#ifndef VHOST_USER_F_PROTOCOL_FEATURES
#define VHOST_USER_F_PROTOCOL_FEATURES 30
#endif

/** Protocol features. */
#ifndef VHOST_USER_PROTOCOL_F_MQ
#define VHOST_USER_PROTOCOL_F_MQ 0
#endif

#ifndef VHOST_USER_PROTOCOL_F_REPLY_ACK
#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
#endif

#ifndef VHOST_USER_PROTOCOL_F_STATUS
#define VHOST_USER_PROTOCOL_F_STATUS 16
#endif

#define VHOST_USER_SUPPORTED_PROTOCOL_FEATURES		\
	(1ULL << VHOST_USER_PROTOCOL_F_MQ |		\
	 1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK |	\
	 1ULL << VHOST_USER_PROTOCOL_F_STATUS)

/* The version of the protocol we support */
#define VHOST_USER_VERSION    0x1

#define VHOST_MEMORY_MAX_NREGIONS 8
struct vhost_memory {
	uint32_t nregions;
	uint32_t padding;
	struct vhost_memory_region regions[VHOST_MEMORY_MAX_NREGIONS];
};

enum vhost_user_request {
	VHOST_USER_NONE = 0,
	VHOST_USER_GET_FEATURES = 1,
	VHOST_USER_SET_FEATURES = 2,
	VHOST_USER_SET_OWNER = 3,
	VHOST_USER_RESET_OWNER = 4,
	VHOST_USER_SET_MEM_TABLE = 5,
	VHOST_USER_SET_LOG_BASE = 6,
	VHOST_USER_SET_LOG_FD = 7,
	VHOST_USER_SET_VRING_NUM = 8,
	VHOST_USER_SET_VRING_ADDR = 9,
	VHOST_USER_SET_VRING_BASE = 10,
	VHOST_USER_GET_VRING_BASE = 11,
	VHOST_USER_SET_VRING_KICK = 12,
	VHOST_USER_SET_VRING_CALL = 13,
	VHOST_USER_SET_VRING_ERR = 14,
	VHOST_USER_GET_PROTOCOL_FEATURES = 15,
	VHOST_USER_SET_PROTOCOL_FEATURES = 16,
	VHOST_USER_GET_QUEUE_NUM = 17,
	VHOST_USER_SET_VRING_ENABLE = 18,
	VHOST_USER_SET_STATUS = 39,
	VHOST_USER_GET_STATUS = 40,
	VHOST_USER_MAX
};

struct vhost_user_msg {
	enum vhost_user_request request;

#define VHOST_USER_VERSION_MASK     0x3
#define VHOST_USER_REPLY_MASK       (0x1 << 2)
#define VHOST_USER_NEED_REPLY_MASK  (0x1 << 3)
	uint32_t flags;
	uint32_t size; /* the following payload size */
	union {
#define VHOST_USER_VRING_IDX_MASK   0xff
#define VHOST_USER_VRING_NOFD_MASK  (0x1 << 8)
		uint64_t u64;
		struct vhost_vring_state state;
		struct vhost_vring_addr addr;
		struct vhost_memory memory;
	} payload;
	int fds[VHOST_MEMORY_MAX_NREGIONS];
} __rte_packed;

#define VHOST_USER_HDR_SIZE offsetof(struct vhost_user_msg, payload.u64)
#define VHOST_USER_PAYLOAD_SIZE \
	(sizeof(struct vhost_user_msg) - VHOST_USER_HDR_SIZE)

static int
vhost_user_write(int fd, struct vhost_user_msg *msg, int *fds, int fd_num)
{
	int r;
	struct msghdr msgh;
	struct iovec iov;
	size_t fd_size = fd_num * sizeof(int);
	char control[CMSG_SPACE(fd_size)];
	struct cmsghdr *cmsg;

	memset(&msgh, 0, sizeof(msgh));
	memset(control, 0, sizeof(control));

	iov.iov_base = (uint8_t *)msg;
	iov.iov_len = VHOST_USER_HDR_SIZE + msg->size;

	msgh.msg_iov = &iov;
	msgh.msg_iovlen = 1;
	msgh.msg_control = control;
	msgh.msg_controllen = sizeof(control);

	cmsg = CMSG_FIRSTHDR(&msgh);
	cmsg->cmsg_len = CMSG_LEN(fd_size);
	cmsg->cmsg_level = SOL_SOCKET;
	cmsg->cmsg_type = SCM_RIGHTS;
	memcpy(CMSG_DATA(cmsg), fds, fd_size);

	do {
		r = sendmsg(fd, &msgh, 0);
	} while (r < 0 && errno == EINTR);

	if (r < 0)
		PMD_DRV_LOG(ERR, "Failed to send msg: %s", strerror(errno));

	return r;
}

static int
vhost_user_read(int fd, struct vhost_user_msg *msg)
{
	uint32_t valid_flags = VHOST_USER_REPLY_MASK | VHOST_USER_VERSION;
	int ret, sz_hdr = VHOST_USER_HDR_SIZE, sz_payload;

	ret = recv(fd, (void *)msg, sz_hdr, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to recv msg header: %s", strerror(errno));
		return -1;
	} else if (ret < sz_hdr) {
		PMD_DRV_LOG(ERR, "Failed to recv msg hdr: %d instead of %d.",
			    ret, sz_hdr);
		return -1;
	}

	/* validate msg flags */
	if (msg->flags != (valid_flags)) {
		PMD_DRV_LOG(ERR, "Failed to recv msg: flags 0x%x instead of 0x%x.",
			    msg->flags, valid_flags);
		return -1;
	}

	sz_payload = msg->size;

	if ((size_t)sz_payload > sizeof(msg->payload)) {
		PMD_DRV_LOG(ERR, "Payload size overflow, header says %d but max %zu\n",
				sz_payload, sizeof(msg->payload));
		return -1;
	}

	if (sz_payload) {
		ret = recv(fd, (void *)((char *)msg + sz_hdr), sz_payload, 0);
		if (ret < 0) {
			PMD_DRV_LOG(ERR, "Failed to recv msg payload: %s", strerror(errno));
			return -1;
		} else if (ret < sz_payload) {
			PMD_DRV_LOG(ERR, "Failed to recv msg payload: %d instead of %u.",
				ret, msg->size);
			return -1;
		}
	}

	return 0;
}

static int
vhost_user_check_reply_ack(struct virtio_user_dev *dev, struct vhost_user_msg *msg)
{
	struct vhost_user_data *data = dev->backend_data;
	enum vhost_user_request req = msg->request;
	int ret;

	if (!(msg->flags & VHOST_USER_NEED_REPLY_MASK))
		return 0;

	ret = vhost_user_read(data->vhostfd, msg);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to read reply-ack");
		return -1;
	}

	if (req != msg->request) {
		PMD_DRV_LOG(ERR, "Unexpected reply-ack request type (%d)", msg->request);
		return -1;
	}

	if (msg->size != sizeof(msg->payload.u64)) {
		PMD_DRV_LOG(ERR, "Unexpected reply-ack payload size (%u)", msg->size);
		return -1;
	}

	if (msg->payload.u64) {
		PMD_DRV_LOG(ERR, "Slave replied NACK to request type (%d)", msg->request);
		return -1;
	}

	return 0;
}

static int
vhost_user_set_owner(struct virtio_user_dev *dev)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_OWNER,
		.flags = VHOST_USER_VERSION,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to set owner");
		return -1;
	}

	return 0;
}

static int
vhost_user_get_protocol_features(struct virtio_user_dev *dev, uint64_t *features)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_GET_PROTOCOL_FEATURES,
		.flags = VHOST_USER_VERSION,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0)
		goto err;

	ret = vhost_user_read(data->vhostfd, &msg);
	if (ret < 0)
		goto err;

	if (msg.request != VHOST_USER_GET_PROTOCOL_FEATURES) {
		PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
		goto err;
	}

	if (msg.size != sizeof(*features)) {
		PMD_DRV_LOG(ERR, "Unexpected payload size (%u)", msg.size);
		goto err;
	}

	*features = msg.payload.u64;

	return 0;
err:
	PMD_DRV_LOG(ERR, "Failed to get backend protocol features");

	return -1;
}

static int
vhost_user_set_protocol_features(struct virtio_user_dev *dev, uint64_t features)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_PROTOCOL_FEATURES,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(features),
		.payload.u64 = features,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to set protocol features");
		return -1;
	}

	return 0;
}

static int
vhost_user_get_features(struct virtio_user_dev *dev, uint64_t *features)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_GET_FEATURES,
		.flags = VHOST_USER_VERSION,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0)
		goto err;

	ret = vhost_user_read(data->vhostfd, &msg);
	if (ret < 0)
		goto err;

	if (msg.request != VHOST_USER_GET_FEATURES) {
		PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
		goto err;
	}

	if (msg.size != sizeof(*features)) {
		PMD_DRV_LOG(ERR, "Unexpected payload size (%u)", msg.size);
		goto err;
	}

	*features = msg.payload.u64;

	if (!(*features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
		return 0;

	/* Negotiate protocol features */
	ret = vhost_user_get_protocol_features(dev, &data->protocol_features);
	if (ret < 0)
		goto err;

	data->protocol_features &= VHOST_USER_SUPPORTED_PROTOCOL_FEATURES;

	ret = vhost_user_set_protocol_features(dev, data->protocol_features);
	if (ret < 0)
		goto err;

	if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_MQ)))
		dev->unsupported_features |= (1ull << VIRTIO_NET_F_MQ);

	return 0;
err:
	PMD_DRV_LOG(ERR, "Failed to get backend features");

	return -1;
}

static int
vhost_user_set_features(struct virtio_user_dev *dev, uint64_t features)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_FEATURES,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(features),
		.payload.u64 = features,
	};

	msg.payload.u64 |= dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES);

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to set features");
		return -1;
	}

	return 0;
}

struct walk_arg {
	struct vhost_memory *vm;
	int *fds;
	int region_nr;
};

static int
update_memory_region(const struct rte_memseg_list *msl __rte_unused,
		const struct rte_memseg *ms, void *arg)
{
	struct walk_arg *wa = arg;
	struct vhost_memory_region *mr;
	uint64_t start_addr, end_addr;
	size_t offset;
	int i, fd;

	fd = rte_memseg_get_fd_thread_unsafe(ms);
	if (fd < 0) {
		PMD_DRV_LOG(ERR, "Failed to get fd, ms=%p rte_errno=%d",
			ms, rte_errno);
		return -1;
	}

	if (rte_memseg_get_fd_offset_thread_unsafe(ms, &offset) < 0) {
		PMD_DRV_LOG(ERR, "Failed to get offset, ms=%p rte_errno=%d",
			ms, rte_errno);
		return -1;
	}

	start_addr = (uint64_t)(uintptr_t)ms->addr;
	end_addr = start_addr + ms->len;

	for (i = 0; i < wa->region_nr; i++) {
		if (wa->fds[i] != fd)
			continue;

		mr = &wa->vm->regions[i];

		if (mr->userspace_addr + mr->memory_size < end_addr)
			mr->memory_size = end_addr - mr->userspace_addr;

		if (mr->userspace_addr > start_addr) {
			mr->userspace_addr = start_addr;
			mr->guest_phys_addr = start_addr;
		}

		if (mr->mmap_offset > offset)
			mr->mmap_offset = offset;

		PMD_DRV_LOG(DEBUG, "index=%d fd=%d offset=0x%" PRIx64
			" addr=0x%" PRIx64 " len=%" PRIu64, i, fd,
			mr->mmap_offset, mr->userspace_addr,
			mr->memory_size);

		return 0;
	}

	if (i >= VHOST_MEMORY_MAX_NREGIONS) {
		PMD_DRV_LOG(ERR, "Too many memory regions");
		return -1;
	}

	mr = &wa->vm->regions[i];
	wa->fds[i] = fd;

	mr->guest_phys_addr = start_addr;
	mr->userspace_addr = start_addr;
	mr->memory_size = ms->len;
	mr->mmap_offset = offset;

	PMD_DRV_LOG(DEBUG, "index=%d fd=%d offset=0x%" PRIx64
		" addr=0x%" PRIx64 " len=%" PRIu64, i, fd,
		mr->mmap_offset, mr->userspace_addr,
		mr->memory_size);

	wa->region_nr++;

	return 0;
}

static int
vhost_user_set_memory_table(struct virtio_user_dev *dev)
{
	struct walk_arg wa;
	int fds[VHOST_MEMORY_MAX_NREGIONS];
	int ret, fd_num;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_MEM_TABLE,
		.flags = VHOST_USER_VERSION,
	};

	if (data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
		msg.flags |= VHOST_USER_NEED_REPLY_MASK;

	wa.region_nr = 0;
	wa.vm = &msg.payload.memory;
	wa.fds = fds;

	/*
	 * The memory lock has already been taken by memory subsystem
	 * or virtio_user_start_device().
	 */
	ret = rte_memseg_walk_thread_unsafe(update_memory_region, &wa);
	if (ret < 0)
		goto err;

	fd_num = wa.region_nr;
	msg.payload.memory.nregions = wa.region_nr;
	msg.payload.memory.padding = 0;

	msg.size = sizeof(msg.payload.memory.nregions);
	msg.size += sizeof(msg.payload.memory.padding);
	msg.size += fd_num * sizeof(struct vhost_memory_region);

	ret = vhost_user_write(data->vhostfd, &msg, fds, fd_num);
	if (ret < 0)
		goto err;

	return vhost_user_check_reply_ack(dev, &msg);
err:
	PMD_DRV_LOG(ERR, "Failed to set memory table");
	return -1;
}

static int
vhost_user_set_vring(struct virtio_user_dev *dev, enum vhost_user_request req,
		struct vhost_vring_state *state)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = req,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(*state),
		.payload.state = *state,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to set vring state (request %d)", req);
		return -1;
	}

	return 0;
}

static int
vhost_user_set_vring_enable(struct virtio_user_dev *dev, struct vhost_vring_state *state)
{
	return vhost_user_set_vring(dev, VHOST_USER_SET_VRING_ENABLE, state);
}

static int
vhost_user_set_vring_num(struct virtio_user_dev *dev, struct vhost_vring_state *state)
{
	return vhost_user_set_vring(dev, VHOST_USER_SET_VRING_NUM, state);
}

static int
vhost_user_set_vring_base(struct virtio_user_dev *dev, struct vhost_vring_state *state)
{
	return vhost_user_set_vring(dev, VHOST_USER_SET_VRING_BASE, state);
}

static int
vhost_user_get_vring_base(struct virtio_user_dev *dev, struct vhost_vring_state *state)
{
	int ret;
	struct vhost_user_msg msg;
	struct vhost_user_data *data = dev->backend_data;
	unsigned int index = state->index;

	ret = vhost_user_set_vring(dev, VHOST_USER_GET_VRING_BASE, state);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to send request");
		goto err;
	}

	ret = vhost_user_read(data->vhostfd, &msg);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to read reply");
		goto err;
	}

	if (msg.request != VHOST_USER_GET_VRING_BASE) {
		PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
		goto err;
	}

	if (msg.size != sizeof(*state)) {
		PMD_DRV_LOG(ERR, "Unexpected payload size (%u)", msg.size);
		goto err;
	}

	if (msg.payload.state.index != index) {
		PMD_DRV_LOG(ERR, "Unexpected ring index (%u)", state->index);
		goto err;
	}

	*state = msg.payload.state;

	return 0;
err:
	PMD_DRV_LOG(ERR, "Failed to get vring base");
	return -1;
}

static int
vhost_user_set_vring_file(struct virtio_user_dev *dev, enum vhost_user_request req,
		struct vhost_vring_file *file)
{
	int ret;
	int fd = file->fd;
	int num_fd = 0;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = req,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(msg.payload.u64),
		.payload.u64 = file->index & VHOST_USER_VRING_IDX_MASK,
	};

	if (fd >= 0)
		num_fd++;
	else
		msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;

	ret = vhost_user_write(data->vhostfd, &msg, &fd, num_fd);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to set vring file (request %d)", req);
		return -1;
	}

	return 0;
}

static int
vhost_user_set_vring_call(struct virtio_user_dev *dev, struct vhost_vring_file *file)
{
	return vhost_user_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file);
}

static int
vhost_user_set_vring_kick(struct virtio_user_dev *dev, struct vhost_vring_file *file)
{
	return vhost_user_set_vring_file(dev, VHOST_USER_SET_VRING_KICK, file);
}


static int
vhost_user_set_vring_addr(struct virtio_user_dev *dev, struct vhost_vring_addr *addr)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_VRING_ADDR,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(*addr),
		.payload.addr = *addr,
	};

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to send vring addresses");
		return -1;
	}

	return 0;
}

static int
vhost_user_get_status(struct virtio_user_dev *dev, uint8_t *status)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_GET_STATUS,
		.flags = VHOST_USER_VERSION,
	};

	/*
	 * If features have not been negotiated, we don't know if the backend
	 * supports protocol features
	 */
	if (!(dev->status & VIRTIO_CONFIG_STATUS_FEATURES_OK))
		return -ENOTSUP;

	/* Status protocol feature requires protocol features support */
	if (!(dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
		return -ENOTSUP;

	if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
		return -ENOTSUP;

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to send request");
		goto err;
	}

	ret = vhost_user_read(data->vhostfd, &msg);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to recv request");
		goto err;
	}

	if (msg.request != VHOST_USER_GET_STATUS) {
		PMD_DRV_LOG(ERR, "Unexpected request type (%d)", msg.request);
		goto err;
	}

	if (msg.size != sizeof(msg.payload.u64)) {
		PMD_DRV_LOG(ERR, "Unexpected payload size (%u)", msg.size);
		goto err;
	}

	*status = (uint8_t)msg.payload.u64;

	return 0;
err:
	PMD_DRV_LOG(ERR, "Failed to get device status");
	return -1;
}

static int
vhost_user_set_status(struct virtio_user_dev *dev, uint8_t status)
{
	int ret;
	struct vhost_user_data *data = dev->backend_data;
	struct vhost_user_msg msg = {
		.request = VHOST_USER_SET_STATUS,
		.flags = VHOST_USER_VERSION,
		.size = sizeof(msg.payload.u64),
		.payload.u64 = status,
	};

	/*
	 * If features have not been negotiated, we don't know if the backend
	 * supports protocol features
	 */
	if (!(dev->status & VIRTIO_CONFIG_STATUS_FEATURES_OK))
		return -ENOTSUP;

	/* Status protocol feature requires protocol features support */
	if (!(dev->device_features & (1ULL << VHOST_USER_F_PROTOCOL_FEATURES)))
		return -ENOTSUP;

	if (!(data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_STATUS)))
		return -ENOTSUP;

	if (data->protocol_features & (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK))
		msg.flags |= VHOST_USER_NEED_REPLY_MASK;

	ret = vhost_user_write(data->vhostfd, &msg, NULL, 0);
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "Failed to send get status request");
		return -1;
	}

	return vhost_user_check_reply_ack(dev, &msg);
}

#define MAX_VIRTIO_USER_BACKLOG 1
static int
vhost_user_start_server(struct virtio_user_dev *dev, struct sockaddr_un *un)
{
	int ret;
	int flag;
	struct vhost_user_data *data = dev->backend_data;
	int fd = data->listenfd;

	ret = bind(fd, (struct sockaddr *)un, sizeof(*un));
	if (ret < 0) {
		PMD_DRV_LOG(ERR, "failed to bind to %s: %s; remove it and try again\n",
			    dev->path, strerror(errno));
		return -1;
	}
	ret = listen(fd, MAX_VIRTIO_USER_BACKLOG);
	if (ret < 0)
		return -1;

	PMD_DRV_LOG(NOTICE, "(%s) waiting for client connection...", dev->path);
	data->vhostfd = accept(fd, NULL, NULL);
	if (data->vhostfd < 0) {
		PMD_DRV_LOG(ERR, "Failed to accept initial client connection (%s)",
				strerror(errno));
		return -1;
	}

	flag = fcntl(fd, F_GETFL);
	if (fcntl(fd, F_SETFL, flag | O_NONBLOCK) < 0) {
		PMD_DRV_LOG(ERR, "fcntl failed, %s", strerror(errno));
		return -1;
	}

	return 0;
}

static int
vhost_user_server_disconnect(struct virtio_user_dev *dev)
{
	struct vhost_user_data *data = dev->backend_data;

	if (data->vhostfd < 0) {
		PMD_DRV_LOG(ERR, "(%s) Expected valid Vhost FD", dev->path);
		return -1;
	}

	close(data->vhostfd);
	data->vhostfd = -1;

	return 0;
}

static int
vhost_user_server_reconnect(struct virtio_user_dev *dev)
{
	struct vhost_user_data *data = dev->backend_data;
	int fd;

	fd = accept(data->listenfd, NULL, NULL);
	if (fd < 0)
		return -1;

	data->vhostfd = fd;

	return 0;
}

/**
 * Set up environment to talk with a vhost user backend.
 *
 * @return
 *   - (-1) if fail;
 *   - (0) if succeed.
 */
static int
vhost_user_setup(struct virtio_user_dev *dev)
{
	int fd;
	int flag;
	struct sockaddr_un un;
	struct vhost_user_data *data;

	data = malloc(sizeof(*data));
	if (!data) {
		PMD_DRV_LOG(ERR, "(%s) Failed to allocate Vhost-user data\n", dev->path);
		return -1;
	}

	memset(data, 0, sizeof(*data));

	dev->backend_data = data;

	data->vhostfd = -1;
	data->listenfd = -1;

	fd = socket(AF_UNIX, SOCK_STREAM, 0);
	if (fd < 0) {
		PMD_DRV_LOG(ERR, "socket() error, %s", strerror(errno));
		goto err_data;
	}

	flag = fcntl(fd, F_GETFD);
	if (fcntl(fd, F_SETFD, flag | FD_CLOEXEC) < 0)
		PMD_DRV_LOG(WARNING, "fcntl failed, %s", strerror(errno));

	memset(&un, 0, sizeof(un));
	un.sun_family = AF_UNIX;
	strlcpy(un.sun_path, dev->path, sizeof(un.sun_path));

	if (dev->is_server) {
		data->listenfd = fd;
		if (vhost_user_start_server(dev, &un) < 0) {
			PMD_DRV_LOG(ERR, "virtio-user startup fails in server mode");
			goto err_socket;
		}
	} else {
		if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
			PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
			goto err_socket;
		}
		data->vhostfd = fd;
	}

	return 0;

err_socket:
	close(fd);
err_data:
	free(data);
	dev->backend_data = NULL;

	return -1;
}

static int
vhost_user_destroy(struct virtio_user_dev *dev)
{
	struct vhost_user_data *data = dev->backend_data;

	if (!data)
		return 0;

	if (data->vhostfd >= 0) {
		close(data->vhostfd);
		data->vhostfd = -1;
	}

	if (data->listenfd >= 0) {
		close(data->listenfd);
		data->listenfd = -1;
	}

	free(data);
	dev->backend_data = NULL;

	return 0;
}

static int
vhost_user_enable_queue_pair(struct virtio_user_dev *dev,
			     uint16_t pair_idx,
			     int enable)
{
	struct vhost_user_data *data = dev->backend_data;
	int i;

	if (data->vhostfd < 0)
		return 0;

	if (dev->qp_enabled[pair_idx] == enable)
		return 0;

	for (i = 0; i < 2; ++i) {
		struct vhost_vring_state state = {
			.index = pair_idx * 2 + i,
			.num = enable,
		};

		if (vhost_user_set_vring_enable(dev, &state))
			return -1;
	}

	dev->qp_enabled[pair_idx] = enable;
	return 0;
}

static int
vhost_user_get_backend_features(uint64_t *features)
{
	*features = 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;

	return 0;
}

static int
vhost_user_update_link_state(struct virtio_user_dev *dev)
{
	struct vhost_user_data *data = dev->backend_data;
	char buf[128];

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

		flags = fcntl(data->vhostfd, F_GETFL);
		if (fcntl(data->vhostfd, F_SETFL, flags | O_NONBLOCK) == -1) {
			PMD_DRV_LOG(ERR, "error setting O_NONBLOCK flag");
			return -1;
		}

		r = recv(data->vhostfd, buf, 128, MSG_PEEK);
		if (r == 0 || (r < 0 && errno != EAGAIN)) {
			dev->net_status &= (~VIRTIO_NET_S_LINK_UP);
			PMD_DRV_LOG(ERR, "virtio-user port %u is down", dev->port_id);

			/* This function could be called in the process
			 * of interrupt handling, callback cannot be
			 * unregistered here, set an alarm to do it.
			 */
			rte_eal_alarm_set(1, virtio_user_dev_delayed_handler, (void *)dev);
		} else {
			dev->net_status |= VIRTIO_NET_S_LINK_UP;
		}

		if (fcntl(data->vhostfd, F_SETFL,
					flags & ~O_NONBLOCK) == -1) {
			PMD_DRV_LOG(ERR, "error clearing O_NONBLOCK flag");
			return -1;
		}
	} else if (dev->is_server) {
		dev->net_status &= (~VIRTIO_NET_S_LINK_UP);
		if (virtio_user_dev_server_reconnect(dev) >= 0)
			dev->net_status |= VIRTIO_NET_S_LINK_UP;
	}

	return 0;
}

static int
vhost_user_get_intr_fd(struct virtio_user_dev *dev)
{
	struct vhost_user_data *data = dev->backend_data;

	if (dev->is_server && data->vhostfd == -1)
		return data->listenfd;

	return data->vhostfd;
}

struct virtio_user_backend_ops virtio_ops_user = {
	.setup = vhost_user_setup,
	.destroy = vhost_user_destroy,
	.get_backend_features = vhost_user_get_backend_features,
	.set_owner = vhost_user_set_owner,
	.get_features = vhost_user_get_features,
	.set_features = vhost_user_set_features,
	.set_memory_table = vhost_user_set_memory_table,
	.set_vring_num = vhost_user_set_vring_num,
	.set_vring_base = vhost_user_set_vring_base,
	.get_vring_base = vhost_user_get_vring_base,
	.set_vring_call = vhost_user_set_vring_call,
	.set_vring_kick = vhost_user_set_vring_kick,
	.set_vring_addr = vhost_user_set_vring_addr,
	.get_status = vhost_user_get_status,
	.set_status = vhost_user_set_status,
	.enable_qp = vhost_user_enable_queue_pair,
	.update_link_state = vhost_user_update_link_state,
	.server_disconnect = vhost_user_server_disconnect,
	.server_reconnect = vhost_user_server_reconnect,
	.get_intr_fd = vhost_user_get_intr_fd,
};