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
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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2019 Intel Corporation
 */

#include "ice_rxtx_vec_common.h"

#include <x86intrin.h>

#ifndef __INTEL_COMPILER
#pragma GCC diagnostic ignored "-Wcast-qual"
#endif

#define ICE_DESCS_PER_LOOP_AVX 8

static inline void
ice_rxq_rearm(struct ice_rx_queue *rxq)
{
	int i;
	uint16_t rx_id;
	volatile union ice_rx_flex_desc *rxdp;
	struct ice_rx_entry *rxep = &rxq->sw_ring[rxq->rxrearm_start];
	struct rte_mempool_cache *cache = rte_mempool_default_cache(rxq->mp,
			rte_lcore_id());

	rxdp = rxq->rx_ring + rxq->rxrearm_start;

	/* We need to pull 'n' more MBUFs into the software ring */
	if (cache->len < ICE_RXQ_REARM_THRESH) {
		uint32_t req = ICE_RXQ_REARM_THRESH + (cache->size -
				cache->len);

		int ret = rte_mempool_ops_dequeue_bulk(rxq->mp,
				&cache->objs[cache->len], req);
		if (ret == 0) {
			cache->len += req;
		} else {
			if (rxq->rxrearm_nb + ICE_RXQ_REARM_THRESH >=
			    rxq->nb_rx_desc) {
				__m128i dma_addr0;

				dma_addr0 = _mm_setzero_si128();
				for (i = 0; i < ICE_DESCS_PER_LOOP; i++) {
					rxep[i].mbuf = &rxq->fake_mbuf;
					_mm_store_si128
						((__m128i *)&rxdp[i].read,
							dma_addr0);
				}
			}
			rte_eth_devices[rxq->port_id].data->rx_mbuf_alloc_failed +=
				ICE_RXQ_REARM_THRESH;
			return;
		}
	}

	const __m512i iova_offsets =  _mm512_set1_epi64
		(offsetof(struct rte_mbuf, buf_iova));
	const __m512i headroom = _mm512_set1_epi64(RTE_PKTMBUF_HEADROOM);

#ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
	/* shuffle the iova into correct slots. Values 4-7 will contain
	 * zeros, so use 7 for a zero-value.
	 */
	const __m512i permute_idx = _mm512_set_epi64(7, 7, 3, 1, 7, 7, 2, 0);
#else
	const __m512i permute_idx = _mm512_set_epi64(7, 3, 6, 2, 5, 1, 4, 0);
#endif

	/* fill up the rxd in vector, process 8 mbufs in one loop */
	for (i = 0; i < ICE_RXQ_REARM_THRESH / 8; i++) {
		const __m512i mbuf_ptrs = _mm512_loadu_si512
			(&cache->objs[cache->len - 8]);
		_mm512_store_si512(rxep, mbuf_ptrs);

		/* gather iova of mbuf0-7 into one zmm reg */
		const __m512i iova_base_addrs = _mm512_i64gather_epi64
			(_mm512_add_epi64(mbuf_ptrs, iova_offsets),
				0, /* base */
				1  /* scale */);
		const __m512i iova_addrs = _mm512_add_epi64(iova_base_addrs,
				headroom);
#ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
		const __m512i iovas0 = _mm512_castsi256_si512
			(_mm512_extracti64x4_epi64(iova_addrs, 0));
		const __m512i iovas1 = _mm512_castsi256_si512
			(_mm512_extracti64x4_epi64(iova_addrs, 1));

		/* permute leaves iova 2-3 in hdr_addr of desc 0-1
		 * but these are ignored by driver since header split not
		 * enabled. Similarly for desc 4 & 5.
		 */
		const __m512i desc0_1 = _mm512_permutexvar_epi64
			(permute_idx, iovas0);
		const __m512i desc2_3 = _mm512_bsrli_epi128(desc0_1, 8);

		const __m512i desc4_5 = _mm512_permutexvar_epi64
			(permute_idx, iovas1);
		const __m512i desc6_7 = _mm512_bsrli_epi128(desc4_5, 8);

		_mm512_store_si512((void *)rxdp, desc0_1);
		_mm512_store_si512((void *)(rxdp + 2), desc2_3);
		_mm512_store_si512((void *)(rxdp + 4), desc4_5);
		_mm512_store_si512((void *)(rxdp + 6), desc6_7);
#else
		/* permute leaves iova 4-7 in hdr_addr of desc 0-3
		 * but these are ignored by driver since header split not
		 * enabled.
		 */
		const __m512i desc0_3 = _mm512_permutexvar_epi64
			(permute_idx, iova_addrs);
		const __m512i desc4_7 = _mm512_bsrli_epi128(desc0_3, 8);

		_mm512_store_si512((void *)rxdp, desc0_3);
		_mm512_store_si512((void *)(rxdp + 4), desc4_7);
#endif
		rxep += 8, rxdp += 8, cache->len -= 8;
	}

	rxq->rxrearm_start += ICE_RXQ_REARM_THRESH;
	if (rxq->rxrearm_start >= rxq->nb_rx_desc)
		rxq->rxrearm_start = 0;

	rxq->rxrearm_nb -= ICE_RXQ_REARM_THRESH;

	rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
			     (rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));

	/* Update the tail pointer on the NIC */
	ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
}

static inline __m256i
ice_flex_rxd_to_fdir_flags_vec_avx512(const __m256i fdir_id0_7)
{
#define FDID_MIS_MAGIC 0xFFFFFFFF
	RTE_BUILD_BUG_ON(PKT_RX_FDIR != (1 << 2));
	RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
	const __m256i pkt_fdir_bit = _mm256_set1_epi32(PKT_RX_FDIR |
			PKT_RX_FDIR_ID);
	/* desc->flow_id field == 0xFFFFFFFF means fdir mismatch */
	const __m256i fdir_mis_mask = _mm256_set1_epi32(FDID_MIS_MAGIC);
	__m256i fdir_mask = _mm256_cmpeq_epi32(fdir_id0_7,
			fdir_mis_mask);
	/* this XOR op results to bit-reverse the fdir_mask */
	fdir_mask = _mm256_xor_si256(fdir_mask, fdir_mis_mask);
	const __m256i fdir_flags = _mm256_and_si256(fdir_mask, pkt_fdir_bit);

	return fdir_flags;
}

static inline uint16_t
_ice_recv_raw_pkts_vec_avx512(struct ice_rx_queue *rxq,
			      struct rte_mbuf **rx_pkts,
			      uint16_t nb_pkts, uint8_t *split_packet)
{
	const uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
	const __m256i mbuf_init = _mm256_set_epi64x(0, 0,
			0, rxq->mbuf_initializer);
	struct ice_rx_entry *sw_ring = &rxq->sw_ring[rxq->rx_tail];
	volatile union ice_rx_flex_desc *rxdp = rxq->rx_ring + rxq->rx_tail;

	rte_prefetch0(rxdp);

	/* nb_pkts has to be floor-aligned to ICE_DESCS_PER_LOOP_AVX */
	nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, ICE_DESCS_PER_LOOP_AVX);

	/* See if we need to rearm the RX queue - gives the prefetch a bit
	 * of time to act
	 */
	if (rxq->rxrearm_nb > ICE_RXQ_REARM_THRESH)
		ice_rxq_rearm(rxq);

	/* Before we start moving massive data around, check to see if
	 * there is actually a packet available
	 */
	if (!(rxdp->wb.status_error0 &
			rte_cpu_to_le_32(1 << ICE_RX_FLEX_DESC_STATUS0_DD_S)))
		return 0;

	/* constants used in processing loop */
	const __m512i crc_adjust =
		_mm512_set4_epi32
			(0,             /* ignore non-length fields */
			 -rxq->crc_len, /* sub crc on data_len */
			 -rxq->crc_len, /* sub crc on pkt_len */
			 0              /* ignore non-length fields */
			);

	/* 8 packets DD mask, LSB in each 32-bit value */
	const __m256i dd_check = _mm256_set1_epi32(1);

	/* 8 packets EOP mask, second-LSB in each 32-bit value */
	const __m256i eop_check = _mm256_slli_epi32(dd_check,
			ICE_RX_DESC_STATUS_EOF_S);

	/* mask to shuffle from desc. to mbuf (4 descriptors)*/
	const __m512i shuf_msk =
		_mm512_set4_epi32
			(/* rss hash parsed separately */
			 0xFFFFFFFF,
			 /* octet 10~11, 16 bits vlan_macip */
			 /* octet 4~5, 16 bits data_len */
			 11 << 24 | 10 << 16 | 5 << 8 | 4,
			 /* skip hi 16 bits pkt_len, zero out */
			 /* octet 4~5, 16 bits pkt_len */
			 0xFFFF << 16 | 5 << 8 | 4,
			 /* pkt_type set as unknown */
			 0xFFFFFFFF
			);

	/**
	 * compile-time check the above crc and shuffle layout is correct.
	 * NOTE: the first field (lowest address) is given last in set_epi
	 * calls above.
	 */
	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
	RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
			offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);

	/* Status/Error flag masks */
	/**
	 * mask everything except Checksum Reports, RSS indication
	 * and VLAN indication.
	 * bit6:4 for IP/L4 checksum errors.
	 * bit12 is for RSS indication.
	 * bit13 is for VLAN indication.
	 */
	const __m256i flags_mask =
		 _mm256_set1_epi32((7 << 4) | (1 << 12) | (1 << 13));
	/**
	 * data to be shuffled by the result of the flags mask shifted by 4
	 * bits.  This gives use the l3_l4 flags.
	 */
	const __m256i l3_l4_flags_shuf = _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0, 0,
			/* shift right 1 bit to make sure it not exceed 255 */
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
			 PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
			 PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
			 PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
			 PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1,
			/* 2nd 128-bits */
			0, 0, 0, 0, 0, 0, 0, 0,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
			 PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD |
			 PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
			 PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_EIP_CKSUM_BAD | PKT_RX_L4_CKSUM_GOOD |
			 PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_L4_CKSUM_BAD | PKT_RX_IP_CKSUM_GOOD) >> 1,
			(PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD) >> 1,
			(PKT_RX_L4_CKSUM_GOOD | PKT_RX_IP_CKSUM_GOOD) >> 1);
	const __m256i cksum_mask =
		 _mm256_set1_epi32(PKT_RX_IP_CKSUM_GOOD | PKT_RX_IP_CKSUM_BAD |
				   PKT_RX_L4_CKSUM_GOOD | PKT_RX_L4_CKSUM_BAD |
				   PKT_RX_EIP_CKSUM_BAD);
	/**
	 * data to be shuffled by result of flag mask, shifted down 12.
	 * If RSS(bit12)/VLAN(bit13) are set,
	 * shuffle moves appropriate flags in place.
	 */
	const __m256i rss_vlan_flags_shuf = _mm256_set_epi8(0, 0, 0, 0,
			0, 0, 0, 0,
			0, 0, 0, 0,
			PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
			PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
			PKT_RX_RSS_HASH, 0,
			/* 2nd 128-bits */
			0, 0, 0, 0,
			0, 0, 0, 0,
			0, 0, 0, 0,
			PKT_RX_RSS_HASH | PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
			PKT_RX_VLAN | PKT_RX_VLAN_STRIPPED,
			PKT_RX_RSS_HASH, 0);

	uint16_t i, received;

	for (i = 0, received = 0; i < nb_pkts;
	     i += ICE_DESCS_PER_LOOP_AVX,
	     rxdp += ICE_DESCS_PER_LOOP_AVX) {
		/* step 1, copy over 8 mbuf pointers to rx_pkts array */
		_mm256_storeu_si256((void *)&rx_pkts[i],
				    _mm256_loadu_si256((void *)&sw_ring[i]));
#ifdef RTE_ARCH_X86_64
		_mm256_storeu_si256
			((void *)&rx_pkts[i + 4],
			 _mm256_loadu_si256((void *)&sw_ring[i + 4]));
#endif

		__m512i raw_desc0_3, raw_desc4_7;
		__m256i raw_desc0_1, raw_desc2_3, raw_desc4_5, raw_desc6_7;

		/* load in descriptors, in reverse order */
		const __m128i raw_desc7 =
			_mm_load_si128((void *)(rxdp + 7));
		rte_compiler_barrier();
		const __m128i raw_desc6 =
			_mm_load_si128((void *)(rxdp + 6));
		rte_compiler_barrier();
		const __m128i raw_desc5 =
			_mm_load_si128((void *)(rxdp + 5));
		rte_compiler_barrier();
		const __m128i raw_desc4 =
			_mm_load_si128((void *)(rxdp + 4));
		rte_compiler_barrier();
		const __m128i raw_desc3 =
			_mm_load_si128((void *)(rxdp + 3));
		rte_compiler_barrier();
		const __m128i raw_desc2 =
			_mm_load_si128((void *)(rxdp + 2));
		rte_compiler_barrier();
		const __m128i raw_desc1 =
			_mm_load_si128((void *)(rxdp + 1));
		rte_compiler_barrier();
		const __m128i raw_desc0 =
			_mm_load_si128((void *)(rxdp + 0));

		raw_desc6_7 =
			_mm256_inserti128_si256
				(_mm256_castsi128_si256(raw_desc6),
				 raw_desc7, 1);
		raw_desc4_5 =
			_mm256_inserti128_si256
				(_mm256_castsi128_si256(raw_desc4),
				 raw_desc5, 1);
		raw_desc2_3 =
			_mm256_inserti128_si256
				(_mm256_castsi128_si256(raw_desc2),
				 raw_desc3, 1);
		raw_desc0_1 =
			_mm256_inserti128_si256
				(_mm256_castsi128_si256(raw_desc0),
				 raw_desc1, 1);

		raw_desc4_7 =
			_mm512_inserti64x4
				(_mm512_castsi256_si512(raw_desc4_5),
				 raw_desc6_7, 1);
		raw_desc0_3 =
			_mm512_inserti64x4
				(_mm512_castsi256_si512(raw_desc0_1),
				 raw_desc2_3, 1);

		if (split_packet) {
			int j;

			for (j = 0; j < ICE_DESCS_PER_LOOP_AVX; j++)
				rte_mbuf_prefetch_part2(rx_pkts[i + j]);
		}

		/**
		 * convert descriptors 0-7 into mbufs, re-arrange fields.
		 * Then write into the mbuf.
		 */
		__m512i mb4_7 = _mm512_shuffle_epi8(raw_desc4_7, shuf_msk);
		__m512i mb0_3 = _mm512_shuffle_epi8(raw_desc0_3, shuf_msk);

		mb4_7 = _mm512_add_epi32(mb4_7, crc_adjust);
		mb0_3 = _mm512_add_epi32(mb0_3, crc_adjust);

		/**
		 * to get packet types, ptype is located in bit16-25
		 * of each 128bits
		 */
		const __m512i ptype_mask =
			_mm512_set1_epi16(ICE_RX_FLEX_DESC_PTYPE_M);

		/**
		 * to get packet types, ptype is located in bit16-25
		 * of each 128bits
		 */
		const __m512i ptypes4_7 =
			_mm512_and_si512(raw_desc4_7, ptype_mask);
		const __m512i ptypes0_3 =
			_mm512_and_si512(raw_desc0_3, ptype_mask);

		const __m256i ptypes6_7 =
			_mm512_extracti64x4_epi64(ptypes4_7, 1);
		const __m256i ptypes4_5 =
			_mm512_extracti64x4_epi64(ptypes4_7, 0);
		const __m256i ptypes2_3 =
			_mm512_extracti64x4_epi64(ptypes0_3, 1);
		const __m256i ptypes0_1 =
			_mm512_extracti64x4_epi64(ptypes0_3, 0);
		const uint16_t ptype7 = _mm256_extract_epi16(ptypes6_7, 9);
		const uint16_t ptype6 = _mm256_extract_epi16(ptypes6_7, 1);
		const uint16_t ptype5 = _mm256_extract_epi16(ptypes4_5, 9);
		const uint16_t ptype4 = _mm256_extract_epi16(ptypes4_5, 1);
		const uint16_t ptype3 = _mm256_extract_epi16(ptypes2_3, 9);
		const uint16_t ptype2 = _mm256_extract_epi16(ptypes2_3, 1);
		const uint16_t ptype1 = _mm256_extract_epi16(ptypes0_1, 9);
		const uint16_t ptype0 = _mm256_extract_epi16(ptypes0_1, 1);

		const __m512i ptype4_7 = _mm512_set_epi32
			(0, 0, 0, ptype_tbl[ptype7],
			 0, 0, 0, ptype_tbl[ptype6],
			 0, 0, 0, ptype_tbl[ptype5],
			 0, 0, 0, ptype_tbl[ptype4]);
		const __m512i ptype0_3 = _mm512_set_epi32
			(0, 0, 0, ptype_tbl[ptype3],
			 0, 0, 0, ptype_tbl[ptype2],
			 0, 0, 0, ptype_tbl[ptype1],
			 0, 0, 0, ptype_tbl[ptype0]);

		mb4_7 = _mm512_mask_blend_epi32(0x1111, mb4_7, ptype4_7);
		mb0_3 = _mm512_mask_blend_epi32(0x1111, mb0_3, ptype0_3);

		__m256i mb4_5 = _mm512_extracti64x4_epi64(mb4_7, 0);
		__m256i mb6_7 = _mm512_extracti64x4_epi64(mb4_7, 1);
		__m256i mb0_1 = _mm512_extracti64x4_epi64(mb0_3, 0);
		__m256i mb2_3 = _mm512_extracti64x4_epi64(mb0_3, 1);

		/**
		 * use permute/extract to get status content
		 * After the operations, the packets status flags are in the
		 * order (hi->lo): [1, 3, 5, 7, 0, 2, 4, 6]
		 */
		/* merge the status bits into one register */
		const __m512i status_permute_msk = _mm512_set_epi32
			(0, 0, 0, 0,
			 0, 0, 0, 0,
			 22, 30, 6, 14,
			 18, 26, 2, 10);
		const __m512i raw_status0_7 = _mm512_permutex2var_epi32
			(raw_desc4_7, status_permute_msk, raw_desc0_3);
		__m256i status0_7 = _mm512_extracti64x4_epi64
			(raw_status0_7, 0);

		/* now do flag manipulation */

		/* get only flag/error bits we want */
		const __m256i flag_bits =
			_mm256_and_si256(status0_7, flags_mask);
		/**
		 * l3_l4_error flags, shuffle, then shift to correct adjustment
		 * of flags in flags_shuf, and finally mask out extra bits
		 */
		__m256i l3_l4_flags = _mm256_shuffle_epi8(l3_l4_flags_shuf,
				_mm256_srli_epi32(flag_bits, 4));
		l3_l4_flags = _mm256_slli_epi32(l3_l4_flags, 1);
		l3_l4_flags = _mm256_and_si256(l3_l4_flags, cksum_mask);
		/* set rss and vlan flags */
		const __m256i rss_vlan_flag_bits =
			_mm256_srli_epi32(flag_bits, 12);
		const __m256i rss_vlan_flags =
			_mm256_shuffle_epi8(rss_vlan_flags_shuf,
					    rss_vlan_flag_bits);

		/* merge flags */
		__m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
						     rss_vlan_flags);

		if (rxq->fdir_enabled) {
			const __m256i fdir_id4_7 =
				_mm256_unpackhi_epi32(raw_desc6_7, raw_desc4_5);

			const __m256i fdir_id0_3 =
				_mm256_unpackhi_epi32(raw_desc2_3, raw_desc0_1);

			const __m256i fdir_id0_7 =
				_mm256_unpackhi_epi64(fdir_id4_7, fdir_id0_3);

			const __m256i fdir_flags =
				ice_flex_rxd_to_fdir_flags_vec_avx512
					(fdir_id0_7);

			/* merge with fdir_flags */
			mbuf_flags = _mm256_or_si256(mbuf_flags, fdir_flags);

			/* write to mbuf: have to use scalar store here */
			rx_pkts[i + 0]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 3);

			rx_pkts[i + 1]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 7);

			rx_pkts[i + 2]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 2);

			rx_pkts[i + 3]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 6);

			rx_pkts[i + 4]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 1);

			rx_pkts[i + 5]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 5);

			rx_pkts[i + 6]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 0);

			rx_pkts[i + 7]->hash.fdir.hi =
				_mm256_extract_epi32(fdir_id0_7, 4);
		} /* if() on fdir_enabled */

#ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
		/**
		 * needs to load 2nd 16B of each desc for RSS hash parsing,
		 * will cause performance drop to get into this context.
		 */
		if (rxq->vsi->adapter->eth_dev->data->dev_conf.rxmode.offloads &
				DEV_RX_OFFLOAD_RSS_HASH) {
			/* load bottom half of every 32B desc */
			const __m128i raw_desc_bh7 =
				_mm_load_si128
					((void *)(&rxdp[7].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh6 =
				_mm_load_si128
					((void *)(&rxdp[6].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh5 =
				_mm_load_si128
					((void *)(&rxdp[5].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh4 =
				_mm_load_si128
					((void *)(&rxdp[4].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh3 =
				_mm_load_si128
					((void *)(&rxdp[3].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh2 =
				_mm_load_si128
					((void *)(&rxdp[2].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh1 =
				_mm_load_si128
					((void *)(&rxdp[1].wb.status_error1));
			rte_compiler_barrier();
			const __m128i raw_desc_bh0 =
				_mm_load_si128
					((void *)(&rxdp[0].wb.status_error1));

			__m256i raw_desc_bh6_7 =
				_mm256_inserti128_si256
					(_mm256_castsi128_si256(raw_desc_bh6),
					raw_desc_bh7, 1);
			__m256i raw_desc_bh4_5 =
				_mm256_inserti128_si256
					(_mm256_castsi128_si256(raw_desc_bh4),
					raw_desc_bh5, 1);
			__m256i raw_desc_bh2_3 =
				_mm256_inserti128_si256
					(_mm256_castsi128_si256(raw_desc_bh2),
					raw_desc_bh3, 1);
			__m256i raw_desc_bh0_1 =
				_mm256_inserti128_si256
					(_mm256_castsi128_si256(raw_desc_bh0),
					raw_desc_bh1, 1);

			/**
			 * to shift the 32b RSS hash value to the
			 * highest 32b of each 128b before mask
			 */
			__m256i rss_hash6_7 =
				_mm256_slli_epi64(raw_desc_bh6_7, 32);
			__m256i rss_hash4_5 =
				_mm256_slli_epi64(raw_desc_bh4_5, 32);
			__m256i rss_hash2_3 =
				_mm256_slli_epi64(raw_desc_bh2_3, 32);
			__m256i rss_hash0_1 =
				_mm256_slli_epi64(raw_desc_bh0_1, 32);

			__m256i rss_hash_msk =
				_mm256_set_epi32(0xFFFFFFFF, 0, 0, 0,
						 0xFFFFFFFF, 0, 0, 0);

			rss_hash6_7 = _mm256_and_si256
					(rss_hash6_7, rss_hash_msk);
			rss_hash4_5 = _mm256_and_si256
					(rss_hash4_5, rss_hash_msk);
			rss_hash2_3 = _mm256_and_si256
					(rss_hash2_3, rss_hash_msk);
			rss_hash0_1 = _mm256_and_si256
					(rss_hash0_1, rss_hash_msk);

			mb6_7 = _mm256_or_si256(mb6_7, rss_hash6_7);
			mb4_5 = _mm256_or_si256(mb4_5, rss_hash4_5);
			mb2_3 = _mm256_or_si256(mb2_3, rss_hash2_3);
			mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1);
		} /* if() on RSS hash parsing */
#endif

		/**
		 * At this point, we have the 8 sets of flags in the low 16-bits
		 * of each 32-bit value in vlan0.
		 * We want to extract these, and merge them with the mbuf init
		 * data so we can do a single write to the mbuf to set the flags
		 * and all the other initialization fields. Extracting the
		 * appropriate flags means that we have to do a shift and blend
		 * for each mbuf before we do the write. However, we can also
		 * add in the previously computed rx_descriptor fields to
		 * make a single 256-bit write per mbuf
		 */
		/* check the structure matches expectations */
		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
				 offsetof(struct rte_mbuf, rearm_data) + 8);
		RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
				 RTE_ALIGN(offsetof(struct rte_mbuf,
						    rearm_data),
					   16));
		/* build up data and do writes */
		__m256i rearm0, rearm1, rearm2, rearm3, rearm4, rearm5,
			rearm6, rearm7;

		rearm6 = _mm256_blend_epi32(mbuf_init,
					    _mm256_slli_si256(mbuf_flags, 8),
					    0x04);
		rearm4 = _mm256_blend_epi32(mbuf_init,
					    _mm256_slli_si256(mbuf_flags, 4),
					    0x04);
		rearm2 = _mm256_blend_epi32(mbuf_init, mbuf_flags, 0x04);
		rearm0 = _mm256_blend_epi32(mbuf_init,
					    _mm256_srli_si256(mbuf_flags, 4),
					    0x04);

		/* permute to add in the rx_descriptor e.g. rss fields */
		rearm6 = _mm256_permute2f128_si256(rearm6, mb6_7, 0x20);
		rearm4 = _mm256_permute2f128_si256(rearm4, mb4_5, 0x20);
		rearm2 = _mm256_permute2f128_si256(rearm2, mb2_3, 0x20);
		rearm0 = _mm256_permute2f128_si256(rearm0, mb0_1, 0x20);

		/* write to mbuf */
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 6]->rearm_data,
				    rearm6);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 4]->rearm_data,
				    rearm4);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 2]->rearm_data,
				    rearm2);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 0]->rearm_data,
				    rearm0);

		/* repeat for the odd mbufs */
		const __m256i odd_flags =
			_mm256_castsi128_si256
				(_mm256_extracti128_si256(mbuf_flags, 1));
		rearm7 = _mm256_blend_epi32(mbuf_init,
					    _mm256_slli_si256(odd_flags, 8),
					    0x04);
		rearm5 = _mm256_blend_epi32(mbuf_init,
					    _mm256_slli_si256(odd_flags, 4),
					    0x04);
		rearm3 = _mm256_blend_epi32(mbuf_init, odd_flags, 0x04);
		rearm1 = _mm256_blend_epi32(mbuf_init,
					    _mm256_srli_si256(odd_flags, 4),
					    0x04);

		/* since odd mbufs are already in hi 128-bits use blend */
		rearm7 = _mm256_blend_epi32(rearm7, mb6_7, 0xF0);
		rearm5 = _mm256_blend_epi32(rearm5, mb4_5, 0xF0);
		rearm3 = _mm256_blend_epi32(rearm3, mb2_3, 0xF0);
		rearm1 = _mm256_blend_epi32(rearm1, mb0_1, 0xF0);
		/* again write to mbufs */
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 7]->rearm_data,
				    rearm7);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 5]->rearm_data,
				    rearm5);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 3]->rearm_data,
				    rearm3);
		_mm256_storeu_si256((__m256i *)&rx_pkts[i + 1]->rearm_data,
				    rearm1);

		/* extract and record EOP bit */
		if (split_packet) {
			const __m128i eop_mask =
				_mm_set1_epi16(1 << ICE_RX_DESC_STATUS_EOF_S);
			const __m256i eop_bits256 = _mm256_and_si256(status0_7,
								     eop_check);
			/* pack status bits into a single 128-bit register */
			const __m128i eop_bits =
				_mm_packus_epi32
					(_mm256_castsi256_si128(eop_bits256),
					 _mm256_extractf128_si256(eop_bits256,
								  1));
			/**
			 * flip bits, and mask out the EOP bit, which is now
			 * a split-packet bit i.e. !EOP, rather than EOP one.
			 */
			__m128i split_bits = _mm_andnot_si128(eop_bits,
					eop_mask);
			/**
			 * eop bits are out of order, so we need to shuffle them
			 * back into order again. In doing so, only use low 8
			 * bits, which acts like another pack instruction
			 * The original order is (hi->lo): 1,3,5,7,0,2,4,6
			 * [Since we use epi8, the 16-bit positions are
			 * multiplied by 2 in the eop_shuffle value.]
			 */
			__m128i eop_shuffle =
				_mm_set_epi8(/* zero hi 64b */
					     0xFF, 0xFF, 0xFF, 0xFF,
					     0xFF, 0xFF, 0xFF, 0xFF,
					     /* move values to lo 64b */
					     8, 0, 10, 2,
					     12, 4, 14, 6);
			split_bits = _mm_shuffle_epi8(split_bits, eop_shuffle);
			*(uint64_t *)split_packet =
				_mm_cvtsi128_si64(split_bits);
			split_packet += ICE_DESCS_PER_LOOP_AVX;
		}

		/* perform dd_check */
		status0_7 = _mm256_and_si256(status0_7, dd_check);
		status0_7 = _mm256_packs_epi32(status0_7,
					       _mm256_setzero_si256());

		uint64_t burst = __builtin_popcountll
					(_mm_cvtsi128_si64
						(_mm256_extracti128_si256
							(status0_7, 1)));
		burst += __builtin_popcountll
				(_mm_cvtsi128_si64
					(_mm256_castsi256_si128(status0_7)));
		received += burst;
		if (burst != ICE_DESCS_PER_LOOP_AVX)
			break;
	}

	/* update tail pointers */
	rxq->rx_tail += received;
	rxq->rx_tail &= (rxq->nb_rx_desc - 1);
	if ((rxq->rx_tail & 1) == 1 && received > 1) { /* keep avx2 aligned */
		rxq->rx_tail--;
		received--;
	}
	rxq->rxrearm_nb += received;
	return received;
}

/**
 * Notice:
 * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
 */
uint16_t
ice_recv_pkts_vec_avx512(void *rx_queue, struct rte_mbuf **rx_pkts,
			 uint16_t nb_pkts)
{
	return _ice_recv_raw_pkts_vec_avx512(rx_queue, rx_pkts, nb_pkts, NULL);
}

/**
 * vPMD receive routine that reassembles single burst of 32 scattered packets
 * Notice:
 * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
 */
static uint16_t
ice_recv_scattered_burst_vec_avx512(void *rx_queue, struct rte_mbuf **rx_pkts,
				    uint16_t nb_pkts)
{
	struct ice_rx_queue *rxq = rx_queue;
	uint8_t split_flags[ICE_VPMD_RX_BURST] = {0};

	/* get some new buffers */
	uint16_t nb_bufs = _ice_recv_raw_pkts_vec_avx512(rxq, rx_pkts, nb_pkts,
						       split_flags);
	if (nb_bufs == 0)
		return 0;

	/* happy day case, full burst + no packets to be joined */
	const uint64_t *split_fl64 = (uint64_t *)split_flags;

	if (!rxq->pkt_first_seg &&
	    split_fl64[0] == 0 && split_fl64[1] == 0 &&
	    split_fl64[2] == 0 && split_fl64[3] == 0)
		return nb_bufs;

	/* reassemble any packets that need reassembly */
	unsigned int i = 0;

	if (!rxq->pkt_first_seg) {
		/* find the first split flag, and only reassemble then */
		while (i < nb_bufs && !split_flags[i])
			i++;
		if (i == nb_bufs)
			return nb_bufs;
		rxq->pkt_first_seg = rx_pkts[i];
	}
	return i + ice_rx_reassemble_packets(rxq, &rx_pkts[i], nb_bufs - i,
					     &split_flags[i]);
}

/**
 * vPMD receive routine that reassembles scattered packets.
 * Main receive routine that can handle arbitrary burst sizes
 * Notice:
 * - nb_pkts < ICE_DESCS_PER_LOOP, just return no packet
 */
uint16_t
ice_recv_scattered_pkts_vec_avx512(void *rx_queue, struct rte_mbuf **rx_pkts,
				   uint16_t nb_pkts)
{
	uint16_t retval = 0;

	while (nb_pkts > ICE_VPMD_RX_BURST) {
		uint16_t burst = ice_recv_scattered_burst_vec_avx512(rx_queue,
				rx_pkts + retval, ICE_VPMD_RX_BURST);
		retval += burst;
		nb_pkts -= burst;
		if (burst < ICE_VPMD_RX_BURST)
			return retval;
	}
	return retval + ice_recv_scattered_burst_vec_avx512(rx_queue,
				rx_pkts + retval, nb_pkts);
}

static __rte_always_inline int
ice_tx_free_bufs_avx512(struct ice_tx_queue *txq)
{
	struct ice_vec_tx_entry *txep;
	uint32_t n;
	uint32_t i;
	int nb_free = 0;
	struct rte_mbuf *m, *free[ICE_TX_MAX_FREE_BUF_SZ];

	/* check DD bits on threshold descriptor */
	if ((txq->tx_ring[txq->tx_next_dd].cmd_type_offset_bsz &
			rte_cpu_to_le_64(ICE_TXD_QW1_DTYPE_M)) !=
			rte_cpu_to_le_64(ICE_TX_DESC_DTYPE_DESC_DONE))
		return 0;

	n = txq->tx_rs_thresh;

	/* first buffer to free from S/W ring is at index
	 * tx_next_dd - (tx_rs_thresh - 1)
	 */
	txep = (void *)txq->sw_ring;
	txep += txq->tx_next_dd - (n - 1);

	if (txq->offloads & DEV_TX_OFFLOAD_MBUF_FAST_FREE && (n & 31) == 0) {
		struct rte_mempool *mp = txep[0].mbuf->pool;
		void **cache_objs;
		struct rte_mempool_cache *cache = rte_mempool_default_cache(mp,
				rte_lcore_id());

		if (!cache || cache->len == 0)
			goto normal;

		cache_objs = &cache->objs[cache->len];

		if (n > RTE_MEMPOOL_CACHE_MAX_SIZE) {
			rte_mempool_ops_enqueue_bulk(mp, (void *)txep, n);
			goto done;
		}

		/* The cache follows the following algorithm
		 *   1. Add the objects to the cache
		 *   2. Anything greater than the cache min value (if it
		 *   crosses the cache flush threshold) is flushed to the ring.
		 */
		/* Add elements back into the cache */
		uint32_t copied = 0;
		/* n is multiple of 32 */
		while (copied < n) {
			const __m512i a = _mm512_loadu_si512(&txep[copied]);
			const __m512i b = _mm512_loadu_si512(&txep[copied + 8]);
			const __m512i c = _mm512_loadu_si512(&txep[copied + 16]);
			const __m512i d = _mm512_loadu_si512(&txep[copied + 24]);

			_mm512_storeu_si512(&cache_objs[copied], a);
			_mm512_storeu_si512(&cache_objs[copied + 8], b);
			_mm512_storeu_si512(&cache_objs[copied + 16], c);
			_mm512_storeu_si512(&cache_objs[copied + 24], d);
			copied += 32;
		}
		cache->len += n;

		if (cache->len >= cache->flushthresh) {
			rte_mempool_ops_enqueue_bulk
				(mp, &cache->objs[cache->size],
				 cache->len - cache->size);
			cache->len = cache->size;
		}
		goto done;
	}

normal:
	m = rte_pktmbuf_prefree_seg(txep[0].mbuf);
	if (likely(m)) {
		free[0] = m;
		nb_free = 1;
		for (i = 1; i < n; i++) {
			m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
			if (likely(m)) {
				if (likely(m->pool == free[0]->pool)) {
					free[nb_free++] = m;
				} else {
					rte_mempool_put_bulk(free[0]->pool,
							     (void *)free,
							     nb_free);
					free[0] = m;
					nb_free = 1;
				}
			}
		}
		rte_mempool_put_bulk(free[0]->pool, (void **)free, nb_free);
	} else {
		for (i = 1; i < n; i++) {
			m = rte_pktmbuf_prefree_seg(txep[i].mbuf);
			if (m)
				rte_mempool_put(m->pool, m);
		}
	}

done:
	/* buffers were freed, update counters */
	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free + txq->tx_rs_thresh);
	txq->tx_next_dd = (uint16_t)(txq->tx_next_dd + txq->tx_rs_thresh);
	if (txq->tx_next_dd >= txq->nb_tx_desc)
		txq->tx_next_dd = (uint16_t)(txq->tx_rs_thresh - 1);

	return txq->tx_rs_thresh;
}

static inline void
ice_vtx1(volatile struct ice_tx_desc *txdp,
	 struct rte_mbuf *pkt, uint64_t flags)
{
	uint64_t high_qw =
		(ICE_TX_DESC_DTYPE_DATA |
		 ((uint64_t)flags  << ICE_TXD_QW1_CMD_S) |
		 ((uint64_t)pkt->data_len << ICE_TXD_QW1_TX_BUF_SZ_S));

	__m128i descriptor = _mm_set_epi64x(high_qw,
				pkt->buf_iova + pkt->data_off);
	_mm_store_si128((__m128i *)txdp, descriptor);
}

static inline void
ice_vtx(volatile struct ice_tx_desc *txdp,
	struct rte_mbuf **pkt, uint16_t nb_pkts,  uint64_t flags)
{
	const uint64_t hi_qw_tmpl = (ICE_TX_DESC_DTYPE_DATA |
			((uint64_t)flags  << ICE_TXD_QW1_CMD_S));

	for (; nb_pkts > 3; txdp += 4, pkt += 4, nb_pkts -= 4) {
		uint64_t hi_qw3 =
			hi_qw_tmpl |
			((uint64_t)pkt[3]->data_len <<
			 ICE_TXD_QW1_TX_BUF_SZ_S);
		uint64_t hi_qw2 =
			hi_qw_tmpl |
			((uint64_t)pkt[2]->data_len <<
			 ICE_TXD_QW1_TX_BUF_SZ_S);
		uint64_t hi_qw1 =
			hi_qw_tmpl |
			((uint64_t)pkt[1]->data_len <<
			 ICE_TXD_QW1_TX_BUF_SZ_S);
		uint64_t hi_qw0 =
			hi_qw_tmpl |
			((uint64_t)pkt[0]->data_len <<
			 ICE_TXD_QW1_TX_BUF_SZ_S);

		__m512i desc0_3 =
			_mm512_set_epi64
				(hi_qw3,
				 pkt[3]->buf_iova + pkt[3]->data_off,
				 hi_qw2,
				 pkt[2]->buf_iova + pkt[2]->data_off,
				 hi_qw1,
				 pkt[1]->buf_iova + pkt[1]->data_off,
				 hi_qw0,
				 pkt[0]->buf_iova + pkt[0]->data_off);
		_mm512_storeu_si512((void *)txdp, desc0_3);
	}

	/* do any last ones */
	while (nb_pkts) {
		ice_vtx1(txdp, *pkt, flags);
		txdp++, pkt++, nb_pkts--;
	}
}

static __rte_always_inline void
ice_tx_backlog_entry_avx512(struct ice_vec_tx_entry *txep,
			    struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
{
	int i;

	for (i = 0; i < (int)nb_pkts; ++i)
		txep[i].mbuf = tx_pkts[i];
}

static inline uint16_t
ice_xmit_fixed_burst_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
				uint16_t nb_pkts)
{
	struct ice_tx_queue *txq = (struct ice_tx_queue *)tx_queue;
	volatile struct ice_tx_desc *txdp;
	struct ice_vec_tx_entry *txep;
	uint16_t n, nb_commit, tx_id;
	uint64_t flags = ICE_TD_CMD;
	uint64_t rs = ICE_TX_DESC_CMD_RS | ICE_TD_CMD;

	/* cross rx_thresh boundary is not allowed */
	nb_pkts = RTE_MIN(nb_pkts, txq->tx_rs_thresh);

	if (txq->nb_tx_free < txq->tx_free_thresh)
		ice_tx_free_bufs_avx512(txq);

	nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
	if (unlikely(nb_pkts == 0))
		return 0;

	tx_id = txq->tx_tail;
	txdp = &txq->tx_ring[tx_id];
	txep = (void *)txq->sw_ring;
	txep += tx_id;

	txq->nb_tx_free = (uint16_t)(txq->nb_tx_free - nb_pkts);

	n = (uint16_t)(txq->nb_tx_desc - tx_id);
	if (nb_commit >= n) {
		ice_tx_backlog_entry_avx512(txep, tx_pkts, n);

		ice_vtx(txdp, tx_pkts, n - 1, flags);
		tx_pkts += (n - 1);
		txdp += (n - 1);

		ice_vtx1(txdp, *tx_pkts++, rs);

		nb_commit = (uint16_t)(nb_commit - n);

		tx_id = 0;
		txq->tx_next_rs = (uint16_t)(txq->tx_rs_thresh - 1);

		/* avoid reach the end of ring */
		txdp = txq->tx_ring;
		txep = (void *)txq->sw_ring;
	}

	ice_tx_backlog_entry_avx512(txep, tx_pkts, nb_commit);

	ice_vtx(txdp, tx_pkts, nb_commit, flags);

	tx_id = (uint16_t)(tx_id + nb_commit);
	if (tx_id > txq->tx_next_rs) {
		txq->tx_ring[txq->tx_next_rs].cmd_type_offset_bsz |=
			rte_cpu_to_le_64(((uint64_t)ICE_TX_DESC_CMD_RS) <<
					 ICE_TXD_QW1_CMD_S);
		txq->tx_next_rs =
			(uint16_t)(txq->tx_next_rs + txq->tx_rs_thresh);
	}

	txq->tx_tail = tx_id;

	ICE_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);

	return nb_pkts;
}

uint16_t
ice_xmit_pkts_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts,
			 uint16_t nb_pkts)
{
	uint16_t nb_tx = 0;
	struct ice_tx_queue *txq = (struct ice_tx_queue *)tx_queue;

	while (nb_pkts) {
		uint16_t ret, num;

		num = (uint16_t)RTE_MIN(nb_pkts, txq->tx_rs_thresh);
		ret = ice_xmit_fixed_burst_vec_avx512(tx_queue,
						      &tx_pkts[nb_tx], num);
		nb_tx += ret;
		nb_pkts -= ret;
		if (ret < num)
			break;
	}

	return nb_tx;
}