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
/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2017 Intel Corporation
 */

#include <string.h>

#include <rte_mbuf.h>
#include <rte_malloc.h>
#include <rte_ethdev_driver.h>
#include <rte_tcp.h>
#include <rte_bus_vdev.h>
#include <rte_kvargs.h>

#include "rte_eth_bond.h"
#include "eth_bond_private.h"
#include "eth_bond_8023ad_private.h"

int
check_for_bonded_ethdev(const struct rte_eth_dev *eth_dev)
{
	/* Check valid pointer */
	if (eth_dev == NULL ||
		eth_dev->device == NULL ||
		eth_dev->device->driver == NULL ||
		eth_dev->device->driver->name == NULL)
		return -1;

	/* return 0 if driver name matches */
	return eth_dev->device->driver->name != pmd_bond_drv.driver.name;
}

int
valid_bonded_port_id(uint16_t port_id)
{
	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -1);
	return check_for_bonded_ethdev(&rte_eth_devices[port_id]);
}

int
check_for_master_bonded_ethdev(const struct rte_eth_dev *eth_dev)
{
	int i;
	struct bond_dev_private *internals;

	if (check_for_bonded_ethdev(eth_dev) != 0)
		return 0;

	internals = eth_dev->data->dev_private;

	/* Check if any of slave devices is a bonded device */
	for (i = 0; i < internals->slave_count; i++)
		if (valid_bonded_port_id(internals->slaves[i].port_id) == 0)
			return 1;

	return 0;
}

int
valid_slave_port_id(uint16_t port_id, uint8_t mode)
{
	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -1);

	/* Verify that port_id refers to a non bonded port */
	if (check_for_bonded_ethdev(&rte_eth_devices[port_id]) == 0 &&
			mode == BONDING_MODE_8023AD) {
		RTE_BOND_LOG(ERR, "Cannot add slave to bonded device in 802.3ad"
				" mode as slave is also a bonded device, only "
				"physical devices can be support in this mode.");
		return -1;
	}

	return 0;
}

void
activate_slave(struct rte_eth_dev *eth_dev, uint16_t port_id)
{
	struct bond_dev_private *internals = eth_dev->data->dev_private;
	uint16_t active_count = internals->active_slave_count;

	if (internals->mode == BONDING_MODE_8023AD)
		bond_mode_8023ad_activate_slave(eth_dev, port_id);

	if (internals->mode == BONDING_MODE_TLB
			|| internals->mode == BONDING_MODE_ALB) {

		internals->tlb_slaves_order[active_count] = port_id;
	}

	RTE_ASSERT(internals->active_slave_count <
			(RTE_DIM(internals->active_slaves) - 1));

	internals->active_slaves[internals->active_slave_count] = port_id;
	internals->active_slave_count++;

	if (internals->mode == BONDING_MODE_TLB)
		bond_tlb_activate_slave(internals);
	if (internals->mode == BONDING_MODE_ALB)
		bond_mode_alb_client_list_upd(eth_dev);
}

void
deactivate_slave(struct rte_eth_dev *eth_dev, uint16_t port_id)
{
	uint16_t slave_pos;
	struct bond_dev_private *internals = eth_dev->data->dev_private;
	uint16_t active_count = internals->active_slave_count;

	if (internals->mode == BONDING_MODE_8023AD) {
		bond_mode_8023ad_stop(eth_dev);
		bond_mode_8023ad_deactivate_slave(eth_dev, port_id);
	} else if (internals->mode == BONDING_MODE_TLB
			|| internals->mode == BONDING_MODE_ALB)
		bond_tlb_disable(internals);

	slave_pos = find_slave_by_id(internals->active_slaves, active_count,
			port_id);

	/* If slave was not at the end of the list
	 * shift active slaves up active array list */
	if (slave_pos < active_count) {
		active_count--;
		memmove(internals->active_slaves + slave_pos,
				internals->active_slaves + slave_pos + 1,
				(active_count - slave_pos) *
					sizeof(internals->active_slaves[0]));
	}

	RTE_ASSERT(active_count < RTE_DIM(internals->active_slaves));
	internals->active_slave_count = active_count;

	/* Resetting active_slave when reaches to max
	 * no of slaves in active list
	 */
	if (internals->active_slave >= active_count)
		internals->active_slave = 0;

	if (eth_dev->data->dev_started) {
		if (internals->mode == BONDING_MODE_8023AD) {
			bond_mode_8023ad_start(eth_dev);
		} else if (internals->mode == BONDING_MODE_TLB) {
			bond_tlb_enable(internals);
		} else if (internals->mode == BONDING_MODE_ALB) {
			bond_tlb_enable(internals);
			bond_mode_alb_client_list_upd(eth_dev);
		}
	}
}

int
rte_eth_bond_create(const char *name, uint8_t mode, uint8_t socket_id)
{
	struct bond_dev_private *internals;
	char devargs[52];
	uint16_t port_id;
	int ret;

	if (name == NULL) {
		RTE_BOND_LOG(ERR, "Invalid name specified");
		return -EINVAL;
	}

	ret = snprintf(devargs, sizeof(devargs),
		"driver=net_bonding,mode=%d,socket_id=%d", mode, socket_id);
	if (ret < 0 || ret >= (int)sizeof(devargs))
		return -ENOMEM;

	ret = rte_vdev_init(name, devargs);
	if (ret)
		return ret;

	ret = rte_eth_dev_get_port_by_name(name, &port_id);
	RTE_ASSERT(!ret);

	/*
	 * To make bond_ethdev_configure() happy we need to free the
	 * internals->kvlist here.
	 *
	 * Also see comment in bond_ethdev_configure().
	 */
	internals = rte_eth_devices[port_id].data->dev_private;
	rte_kvargs_free(internals->kvlist);
	internals->kvlist = NULL;

	return port_id;
}

int
rte_eth_bond_free(const char *name)
{
	return rte_vdev_uninit(name);
}

static int
slave_vlan_filter_set(uint16_t bonded_port_id, uint16_t slave_port_id)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;
	int found;
	int res = 0;
	uint64_t slab = 0;
	uint32_t pos = 0;
	uint16_t first;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	if ((bonded_eth_dev->data->dev_conf.rxmode.offloads &
			DEV_RX_OFFLOAD_VLAN_FILTER) == 0)
		return 0;

	internals = bonded_eth_dev->data->dev_private;
	found = rte_bitmap_scan(internals->vlan_filter_bmp, &pos, &slab);
	first = pos;

	if (!found)
		return 0;

	do {
		uint32_t i;
		uint64_t mask;

		for (i = 0, mask = 1;
		     i < RTE_BITMAP_SLAB_BIT_SIZE;
		     i ++, mask <<= 1) {
			if (unlikely(slab & mask)) {
				uint16_t vlan_id = pos + i;

				res = rte_eth_dev_vlan_filter(slave_port_id,
							      vlan_id, 1);
			}
		}
		found = rte_bitmap_scan(internals->vlan_filter_bmp,
					&pos, &slab);
	} while (found && first != pos && res == 0);

	return res;
}

static int
slave_rte_flow_prepare(uint16_t slave_id, struct bond_dev_private *internals)
{
	struct rte_flow *flow;
	struct rte_flow_error ferror;
	uint16_t slave_port_id = internals->slaves[slave_id].port_id;

	if (internals->flow_isolated_valid != 0) {
		rte_eth_dev_stop(slave_port_id);
		if (rte_flow_isolate(slave_port_id, internals->flow_isolated,
		    &ferror)) {
			RTE_BOND_LOG(ERR, "rte_flow_isolate failed for slave"
				     " %d: %s", slave_id, ferror.message ?
				     ferror.message : "(no stated reason)");
			return -1;
		}
	}
	TAILQ_FOREACH(flow, &internals->flow_list, next) {
		flow->flows[slave_id] = rte_flow_create(slave_port_id,
							flow->rule.attr,
							flow->rule.pattern,
							flow->rule.actions,
							&ferror);
		if (flow->flows[slave_id] == NULL) {
			RTE_BOND_LOG(ERR, "Cannot create flow for slave"
				     " %d: %s", slave_id,
				     ferror.message ? ferror.message :
				     "(no stated reason)");
			/* Destroy successful bond flows from the slave */
			TAILQ_FOREACH(flow, &internals->flow_list, next) {
				if (flow->flows[slave_id] != NULL) {
					rte_flow_destroy(slave_port_id,
							 flow->flows[slave_id],
							 &ferror);
					flow->flows[slave_id] = NULL;
				}
			}
			return -1;
		}
	}
	return 0;
}

static void
eth_bond_slave_inherit_dev_info_rx_first(struct bond_dev_private *internals,
					 const struct rte_eth_dev_info *di)
{
	struct rte_eth_rxconf *rxconf_i = &internals->default_rxconf;

	internals->reta_size = di->reta_size;

	/* Inherit Rx offload capabilities from the first slave device */
	internals->rx_offload_capa = di->rx_offload_capa;
	internals->rx_queue_offload_capa = di->rx_queue_offload_capa;
	internals->flow_type_rss_offloads = di->flow_type_rss_offloads;

	/* Inherit maximum Rx packet size from the first slave device */
	internals->candidate_max_rx_pktlen = di->max_rx_pktlen;

	/* Inherit default Rx queue settings from the first slave device */
	memcpy(rxconf_i, &di->default_rxconf, sizeof(*rxconf_i));

	/*
	 * Turn off descriptor prefetch and writeback by default for all
	 * slave devices. Applications may tweak this setting if need be.
	 */
	rxconf_i->rx_thresh.pthresh = 0;
	rxconf_i->rx_thresh.hthresh = 0;
	rxconf_i->rx_thresh.wthresh = 0;

	/* Setting this to zero should effectively enable default values */
	rxconf_i->rx_free_thresh = 0;

	/* Disable deferred start by default for all slave devices */
	rxconf_i->rx_deferred_start = 0;
}

static void
eth_bond_slave_inherit_dev_info_tx_first(struct bond_dev_private *internals,
					 const struct rte_eth_dev_info *di)
{
	struct rte_eth_txconf *txconf_i = &internals->default_txconf;

	/* Inherit Tx offload capabilities from the first slave device */
	internals->tx_offload_capa = di->tx_offload_capa;
	internals->tx_queue_offload_capa = di->tx_queue_offload_capa;

	/* Inherit default Tx queue settings from the first slave device */
	memcpy(txconf_i, &di->default_txconf, sizeof(*txconf_i));

	/*
	 * Turn off descriptor prefetch and writeback by default for all
	 * slave devices. Applications may tweak this setting if need be.
	 */
	txconf_i->tx_thresh.pthresh = 0;
	txconf_i->tx_thresh.hthresh = 0;
	txconf_i->tx_thresh.wthresh = 0;

	/*
	 * Setting these parameters to zero assumes that default
	 * values will be configured implicitly by slave devices.
	 */
	txconf_i->tx_free_thresh = 0;
	txconf_i->tx_rs_thresh = 0;

	/* Disable deferred start by default for all slave devices */
	txconf_i->tx_deferred_start = 0;
}

static void
eth_bond_slave_inherit_dev_info_rx_next(struct bond_dev_private *internals,
					const struct rte_eth_dev_info *di)
{
	struct rte_eth_rxconf *rxconf_i = &internals->default_rxconf;
	const struct rte_eth_rxconf *rxconf = &di->default_rxconf;

	internals->rx_offload_capa &= di->rx_offload_capa;
	internals->rx_queue_offload_capa &= di->rx_queue_offload_capa;
	internals->flow_type_rss_offloads &= di->flow_type_rss_offloads;

	/*
	 * If at least one slave device suggests enabling this
	 * setting by default, enable it for all slave devices
	 * since disabling it may not be necessarily supported.
	 */
	if (rxconf->rx_drop_en == 1)
		rxconf_i->rx_drop_en = 1;

	/*
	 * Adding a new slave device may cause some of previously inherited
	 * offloads to be withdrawn from the internal rx_queue_offload_capa
	 * value. Thus, the new internal value of default Rx queue offloads
	 * has to be masked by rx_queue_offload_capa to make sure that only
	 * commonly supported offloads are preserved from both the previous
	 * value and the value being inhereted from the new slave device.
	 */
	rxconf_i->offloads = (rxconf_i->offloads | rxconf->offloads) &
			     internals->rx_queue_offload_capa;

	/*
	 * RETA size is GCD of all slaves RETA sizes, so, if all sizes will be
	 * the power of 2, the lower one is GCD
	 */
	if (internals->reta_size > di->reta_size)
		internals->reta_size = di->reta_size;

	if (!internals->max_rx_pktlen &&
	    di->max_rx_pktlen < internals->candidate_max_rx_pktlen)
		internals->candidate_max_rx_pktlen = di->max_rx_pktlen;
}

static void
eth_bond_slave_inherit_dev_info_tx_next(struct bond_dev_private *internals,
					const struct rte_eth_dev_info *di)
{
	struct rte_eth_txconf *txconf_i = &internals->default_txconf;
	const struct rte_eth_txconf *txconf = &di->default_txconf;

	internals->tx_offload_capa &= di->tx_offload_capa;
	internals->tx_queue_offload_capa &= di->tx_queue_offload_capa;

	/*
	 * Adding a new slave device may cause some of previously inherited
	 * offloads to be withdrawn from the internal tx_queue_offload_capa
	 * value. Thus, the new internal value of default Tx queue offloads
	 * has to be masked by tx_queue_offload_capa to make sure that only
	 * commonly supported offloads are preserved from both the previous
	 * value and the value being inhereted from the new slave device.
	 */
	txconf_i->offloads = (txconf_i->offloads | txconf->offloads) &
			     internals->tx_queue_offload_capa;
}

static void
eth_bond_slave_inherit_desc_lim_first(struct rte_eth_desc_lim *bond_desc_lim,
		const struct rte_eth_desc_lim *slave_desc_lim)
{
	memcpy(bond_desc_lim, slave_desc_lim, sizeof(*bond_desc_lim));
}

static int
eth_bond_slave_inherit_desc_lim_next(struct rte_eth_desc_lim *bond_desc_lim,
		const struct rte_eth_desc_lim *slave_desc_lim)
{
	bond_desc_lim->nb_max = RTE_MIN(bond_desc_lim->nb_max,
					slave_desc_lim->nb_max);
	bond_desc_lim->nb_min = RTE_MAX(bond_desc_lim->nb_min,
					slave_desc_lim->nb_min);
	bond_desc_lim->nb_align = RTE_MAX(bond_desc_lim->nb_align,
					  slave_desc_lim->nb_align);

	if (bond_desc_lim->nb_min > bond_desc_lim->nb_max ||
	    bond_desc_lim->nb_align > bond_desc_lim->nb_max) {
		RTE_BOND_LOG(ERR, "Failed to inherit descriptor limits");
		return -EINVAL;
	}

	/* Treat maximum number of segments equal to 0 as unspecified */
	if (slave_desc_lim->nb_seg_max != 0 &&
	    (bond_desc_lim->nb_seg_max == 0 ||
	     slave_desc_lim->nb_seg_max < bond_desc_lim->nb_seg_max))
		bond_desc_lim->nb_seg_max = slave_desc_lim->nb_seg_max;
	if (slave_desc_lim->nb_mtu_seg_max != 0 &&
	    (bond_desc_lim->nb_mtu_seg_max == 0 ||
	     slave_desc_lim->nb_mtu_seg_max < bond_desc_lim->nb_mtu_seg_max))
		bond_desc_lim->nb_mtu_seg_max = slave_desc_lim->nb_mtu_seg_max;

	return 0;
}

static int
__eth_bond_slave_add_lock_free(uint16_t bonded_port_id, uint16_t slave_port_id)
{
	struct rte_eth_dev *bonded_eth_dev, *slave_eth_dev;
	struct bond_dev_private *internals;
	struct rte_eth_link link_props;
	struct rte_eth_dev_info dev_info;
	int ret;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	if (valid_slave_port_id(slave_port_id, internals->mode) != 0)
		return -1;

	slave_eth_dev = &rte_eth_devices[slave_port_id];
	if (slave_eth_dev->data->dev_flags & RTE_ETH_DEV_BONDED_SLAVE) {
		RTE_BOND_LOG(ERR, "Slave device is already a slave of a bonded device");
		return -1;
	}

	ret = rte_eth_dev_info_get(slave_port_id, &dev_info);
	if (ret != 0) {
		RTE_BOND_LOG(ERR,
			"%s: Error during getting device (port %u) info: %s\n",
			__func__, slave_port_id, strerror(-ret));

		return ret;
	}
	if (dev_info.max_rx_pktlen < internals->max_rx_pktlen) {
		RTE_BOND_LOG(ERR, "Slave (port %u) max_rx_pktlen too small",
			     slave_port_id);
		return -1;
	}

	slave_add(internals, slave_eth_dev);

	/* We need to store slaves reta_size to be able to synchronize RETA for all
	 * slave devices even if its sizes are different.
	 */
	internals->slaves[internals->slave_count].reta_size = dev_info.reta_size;

	if (internals->slave_count < 1) {
		/* if MAC is not user defined then use MAC of first slave add to
		 * bonded device */
		if (!internals->user_defined_mac) {
			if (mac_address_set(bonded_eth_dev,
					    slave_eth_dev->data->mac_addrs)) {
				RTE_BOND_LOG(ERR, "Failed to set MAC address");
				return -1;
			}
		}

		/* Make primary slave */
		internals->primary_port = slave_port_id;
		internals->current_primary_port = slave_port_id;

		/* Inherit queues settings from first slave */
		internals->nb_rx_queues = slave_eth_dev->data->nb_rx_queues;
		internals->nb_tx_queues = slave_eth_dev->data->nb_tx_queues;

		eth_bond_slave_inherit_dev_info_rx_first(internals, &dev_info);
		eth_bond_slave_inherit_dev_info_tx_first(internals, &dev_info);

		eth_bond_slave_inherit_desc_lim_first(&internals->rx_desc_lim,
						      &dev_info.rx_desc_lim);
		eth_bond_slave_inherit_desc_lim_first(&internals->tx_desc_lim,
						      &dev_info.tx_desc_lim);
	} else {
		int ret;

		eth_bond_slave_inherit_dev_info_rx_next(internals, &dev_info);
		eth_bond_slave_inherit_dev_info_tx_next(internals, &dev_info);

		ret = eth_bond_slave_inherit_desc_lim_next(
				&internals->rx_desc_lim, &dev_info.rx_desc_lim);
		if (ret != 0)
			return ret;

		ret = eth_bond_slave_inherit_desc_lim_next(
				&internals->tx_desc_lim, &dev_info.tx_desc_lim);
		if (ret != 0)
			return ret;
	}

	bonded_eth_dev->data->dev_conf.rx_adv_conf.rss_conf.rss_hf &=
			internals->flow_type_rss_offloads;

	if (slave_rte_flow_prepare(internals->slave_count, internals) != 0) {
		RTE_BOND_LOG(ERR, "Failed to prepare new slave flows: port=%d",
			     slave_port_id);
		return -1;
	}

	/* Add additional MAC addresses to the slave */
	if (slave_add_mac_addresses(bonded_eth_dev, slave_port_id) != 0) {
		RTE_BOND_LOG(ERR, "Failed to add mac address(es) to slave %hu",
				slave_port_id);
		return -1;
	}

	internals->slave_count++;

	if (bonded_eth_dev->data->dev_started) {
		if (slave_configure(bonded_eth_dev, slave_eth_dev) != 0) {
			internals->slave_count--;
			RTE_BOND_LOG(ERR, "rte_bond_slaves_configure: port=%d",
					slave_port_id);
			return -1;
		}
	}

	/* Update all slave devices MACs */
	mac_address_slaves_update(bonded_eth_dev);

	/* Register link status change callback with bonded device pointer as
	 * argument*/
	rte_eth_dev_callback_register(slave_port_id, RTE_ETH_EVENT_INTR_LSC,
			bond_ethdev_lsc_event_callback, &bonded_eth_dev->data->port_id);

	/* If bonded device is started then we can add the slave to our active
	 * slave array */
	if (bonded_eth_dev->data->dev_started) {
		ret = rte_eth_link_get_nowait(slave_port_id, &link_props);
		if (ret < 0) {
			rte_eth_dev_callback_unregister(slave_port_id,
					RTE_ETH_EVENT_INTR_LSC,
					bond_ethdev_lsc_event_callback,
					&bonded_eth_dev->data->port_id);
			internals->slave_count--;
			RTE_BOND_LOG(ERR,
				"Slave (port %u) link get failed: %s\n",
				slave_port_id, rte_strerror(-ret));
			return -1;
		}

		 if (link_props.link_status == ETH_LINK_UP) {
			if (internals->active_slave_count == 0 &&
			    !internals->user_defined_primary_port)
				bond_ethdev_primary_set(internals,
							slave_port_id);
		}
	}

	/* Add slave details to bonded device */
	slave_eth_dev->data->dev_flags |= RTE_ETH_DEV_BONDED_SLAVE;

	slave_vlan_filter_set(bonded_port_id, slave_port_id);

	return 0;

}

int
rte_eth_bond_slave_add(uint16_t bonded_port_id, uint16_t slave_port_id)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;

	int retval;

	/* Verify that port id's are valid bonded and slave ports */
	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	rte_spinlock_lock(&internals->lock);

	retval = __eth_bond_slave_add_lock_free(bonded_port_id, slave_port_id);

	rte_spinlock_unlock(&internals->lock);

	return retval;
}

static int
__eth_bond_slave_remove_lock_free(uint16_t bonded_port_id,
				   uint16_t slave_port_id)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;
	struct rte_eth_dev *slave_eth_dev;
	struct rte_flow_error flow_error;
	struct rte_flow *flow;
	int i, slave_idx;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	if (valid_slave_port_id(slave_port_id, internals->mode) < 0)
		return -1;

	/* first remove from active slave list */
	slave_idx = find_slave_by_id(internals->active_slaves,
		internals->active_slave_count, slave_port_id);

	if (slave_idx < internals->active_slave_count)
		deactivate_slave(bonded_eth_dev, slave_port_id);

	slave_idx = -1;
	/* now find in slave list */
	for (i = 0; i < internals->slave_count; i++)
		if (internals->slaves[i].port_id == slave_port_id) {
			slave_idx = i;
			break;
		}

	if (slave_idx < 0) {
		RTE_BOND_LOG(ERR, "Couldn't find slave in port list, slave count %d",
				internals->slave_count);
		return -1;
	}

	/* Un-register link status change callback with bonded device pointer as
	 * argument*/
	rte_eth_dev_callback_unregister(slave_port_id, RTE_ETH_EVENT_INTR_LSC,
			bond_ethdev_lsc_event_callback,
			&rte_eth_devices[bonded_port_id].data->port_id);

	/* Restore original MAC address of slave device */
	rte_eth_dev_default_mac_addr_set(slave_port_id,
			&(internals->slaves[slave_idx].persisted_mac_addr));

	/* remove additional MAC addresses from the slave */
	slave_remove_mac_addresses(bonded_eth_dev, slave_port_id);

	/*
	 * Remove bond device flows from slave device.
	 * Note: don't restore flow isolate mode.
	 */
	TAILQ_FOREACH(flow, &internals->flow_list, next) {
		if (flow->flows[slave_idx] != NULL) {
			rte_flow_destroy(slave_port_id, flow->flows[slave_idx],
					 &flow_error);
			flow->flows[slave_idx] = NULL;
		}
	}

	slave_eth_dev = &rte_eth_devices[slave_port_id];
	slave_remove(internals, slave_eth_dev);
	slave_eth_dev->data->dev_flags &= (~RTE_ETH_DEV_BONDED_SLAVE);

	/*  first slave in the active list will be the primary by default,
	 *  otherwise use first device in list */
	if (internals->current_primary_port == slave_port_id) {
		if (internals->active_slave_count > 0)
			internals->current_primary_port = internals->active_slaves[0];
		else if (internals->slave_count > 0)
			internals->current_primary_port = internals->slaves[0].port_id;
		else
			internals->primary_port = 0;
		mac_address_slaves_update(bonded_eth_dev);
	}

	if (internals->active_slave_count < 1) {
		/* if no slaves are any longer attached to bonded device and MAC is not
		 * user defined then clear MAC of bonded device as it will be reset
		 * when a new slave is added */
		if (internals->slave_count < 1 && !internals->user_defined_mac)
			memset(rte_eth_devices[bonded_port_id].data->mac_addrs, 0,
					sizeof(*(rte_eth_devices[bonded_port_id].data->mac_addrs)));
	}
	if (internals->slave_count == 0) {
		internals->rx_offload_capa = 0;
		internals->tx_offload_capa = 0;
		internals->rx_queue_offload_capa = 0;
		internals->tx_queue_offload_capa = 0;
		internals->flow_type_rss_offloads = ETH_RSS_PROTO_MASK;
		internals->reta_size = 0;
		internals->candidate_max_rx_pktlen = 0;
		internals->max_rx_pktlen = 0;
	}
	return 0;
}

int
rte_eth_bond_slave_remove(uint16_t bonded_port_id, uint16_t slave_port_id)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;
	int retval;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	rte_spinlock_lock(&internals->lock);

	retval = __eth_bond_slave_remove_lock_free(bonded_port_id, slave_port_id);

	rte_spinlock_unlock(&internals->lock);

	return retval;
}

int
rte_eth_bond_mode_set(uint16_t bonded_port_id, uint8_t mode)
{
	struct rte_eth_dev *bonded_eth_dev;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];

	if (check_for_master_bonded_ethdev(bonded_eth_dev) != 0 &&
			mode == BONDING_MODE_8023AD)
		return -1;

	return bond_ethdev_mode_set(bonded_eth_dev, mode);
}

int
rte_eth_bond_mode_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	return internals->mode;
}

int
rte_eth_bond_primary_set(uint16_t bonded_port_id, uint16_t slave_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	if (valid_slave_port_id(slave_port_id, internals->mode) != 0)
		return -1;

	internals->user_defined_primary_port = 1;
	internals->primary_port = slave_port_id;

	bond_ethdev_primary_set(internals, slave_port_id);

	return 0;
}

int
rte_eth_bond_primary_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	if (internals->slave_count < 1)
		return -1;

	return internals->current_primary_port;
}

int
rte_eth_bond_slaves_get(uint16_t bonded_port_id, uint16_t slaves[],
			uint16_t len)
{
	struct bond_dev_private *internals;
	uint16_t i;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	if (slaves == NULL)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	if (internals->slave_count > len)
		return -1;

	for (i = 0; i < internals->slave_count; i++)
		slaves[i] = internals->slaves[i].port_id;

	return internals->slave_count;
}

int
rte_eth_bond_active_slaves_get(uint16_t bonded_port_id, uint16_t slaves[],
		uint16_t len)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	if (slaves == NULL)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	if (internals->active_slave_count > len)
		return -1;

	memcpy(slaves, internals->active_slaves,
	internals->active_slave_count * sizeof(internals->active_slaves[0]));

	return internals->active_slave_count;
}

int
rte_eth_bond_mac_address_set(uint16_t bonded_port_id,
		struct rte_ether_addr *mac_addr)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	/* Set MAC Address of Bonded Device */
	if (mac_address_set(bonded_eth_dev, mac_addr))
		return -1;

	internals->user_defined_mac = 1;

	/* Update all slave devices MACs*/
	if (internals->slave_count > 0)
		return mac_address_slaves_update(bonded_eth_dev);

	return 0;
}

int
rte_eth_bond_mac_address_reset(uint16_t bonded_port_id)
{
	struct rte_eth_dev *bonded_eth_dev;
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	bonded_eth_dev = &rte_eth_devices[bonded_port_id];
	internals = bonded_eth_dev->data->dev_private;

	internals->user_defined_mac = 0;

	if (internals->slave_count > 0) {
		int slave_port;
		/* Get the primary slave location based on the primary port
		 * number as, while slave_add(), we will keep the primary
		 * slave based on slave_count,but not based on the primary port.
		 */
		for (slave_port = 0; slave_port < internals->slave_count;
		     slave_port++) {
			if (internals->slaves[slave_port].port_id ==
			    internals->primary_port)
				break;
		}

		/* Set MAC Address of Bonded Device */
		if (mac_address_set(bonded_eth_dev,
			&internals->slaves[slave_port].persisted_mac_addr)
				!= 0) {
			RTE_BOND_LOG(ERR, "Failed to set MAC address on bonded device");
			return -1;
		}
		/* Update all slave devices MAC addresses */
		return mac_address_slaves_update(bonded_eth_dev);
	}
	/* No need to update anything as no slaves present */
	return 0;
}

int
rte_eth_bond_xmit_policy_set(uint16_t bonded_port_id, uint8_t policy)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	switch (policy) {
	case BALANCE_XMIT_POLICY_LAYER2:
		internals->balance_xmit_policy = policy;
		internals->burst_xmit_hash = burst_xmit_l2_hash;
		break;
	case BALANCE_XMIT_POLICY_LAYER23:
		internals->balance_xmit_policy = policy;
		internals->burst_xmit_hash = burst_xmit_l23_hash;
		break;
	case BALANCE_XMIT_POLICY_LAYER34:
		internals->balance_xmit_policy = policy;
		internals->burst_xmit_hash = burst_xmit_l34_hash;
		break;

	default:
		return -1;
	}
	return 0;
}

int
rte_eth_bond_xmit_policy_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	return internals->balance_xmit_policy;
}

int
rte_eth_bond_link_monitoring_set(uint16_t bonded_port_id, uint32_t internal_ms)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;
	internals->link_status_polling_interval_ms = internal_ms;

	return 0;
}

int
rte_eth_bond_link_monitoring_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	return internals->link_status_polling_interval_ms;
}

int
rte_eth_bond_link_down_prop_delay_set(uint16_t bonded_port_id,
				       uint32_t delay_ms)

{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;
	internals->link_down_delay_ms = delay_ms;

	return 0;
}

int
rte_eth_bond_link_down_prop_delay_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	return internals->link_down_delay_ms;
}

int
rte_eth_bond_link_up_prop_delay_set(uint16_t bonded_port_id, uint32_t delay_ms)

{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;
	internals->link_up_delay_ms = delay_ms;

	return 0;
}

int
rte_eth_bond_link_up_prop_delay_get(uint16_t bonded_port_id)
{
	struct bond_dev_private *internals;

	if (valid_bonded_port_id(bonded_port_id) != 0)
		return -1;

	internals = rte_eth_devices[bonded_port_id].data->dev_private;

	return internals->link_up_delay_ms;
}