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
1087
1088
1089
1090
/*-
 *   BSD LICENSE
 *
 *   Copyright 2016 6WIND S.A.
 *   Copyright 2016 Mellanox.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of 6WIND S.A. nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#ifndef RTE_FLOW_H_
#define RTE_FLOW_H_

/**
 * @file
 * RTE generic flow API
 *
 * This interface provides the ability to program packet matching and
 * associated actions in hardware through flow rules.
 */

#include <rte_arp.h>
#include <rte_ether.h>
#include <rte_icmp.h>
#include <rte_ip.h>
#include <rte_sctp.h>
#include <rte_tcp.h>
#include <rte_udp.h>

#ifdef __cplusplus
extern "C" {
#endif

/**
 * Flow rule attributes.
 *
 * Priorities are set on two levels: per group and per rule within groups.
 *
 * Lower values denote higher priority, the highest priority for both levels
 * is 0, so that a rule with priority 0 in group 8 is always matched after a
 * rule with priority 8 in group 0.
 *
 * Although optional, applications are encouraged to group similar rules as
 * much as possible to fully take advantage of hardware capabilities
 * (e.g. optimized matching) and work around limitations (e.g. a single
 * pattern type possibly allowed in a given group).
 *
 * Group and priority levels are arbitrary and up to the application, they
 * do not need to be contiguous nor start from 0, however the maximum number
 * varies between devices and may be affected by existing flow rules.
 *
 * If a packet is matched by several rules of a given group for a given
 * priority level, the outcome is undefined. It can take any path, may be
 * duplicated or even cause unrecoverable errors.
 *
 * Note that support for more than a single group and priority level is not
 * guaranteed.
 *
 * Flow rules can apply to inbound and/or outbound traffic (ingress/egress).
 *
 * Several pattern items and actions are valid and can be used in both
 * directions. Those valid for only one direction are described as such.
 *
 * At least one direction must be specified.
 *
 * Specifying both directions at once for a given rule is not recommended
 * but may be valid in a few cases (e.g. shared counter).
 */
struct rte_flow_attr {
	uint32_t group; /**< Priority group. */
	uint32_t priority; /**< Priority level within group. */
	uint32_t ingress:1; /**< Rule applies to ingress traffic. */
	uint32_t egress:1; /**< Rule applies to egress traffic. */
	uint32_t reserved:30; /**< Reserved, must be zero. */
};

/**
 * Matching pattern item types.
 *
 * Pattern items fall in two categories:
 *
 * - Matching protocol headers and packet data (ANY, RAW, ETH, VLAN, IPV4,
 *   IPV6, ICMP, UDP, TCP, SCTP, VXLAN and so on), usually associated with a
 *   specification structure. These must be stacked in the same order as the
 *   protocol layers to match, starting from the lowest.
 *
 * - Matching meta-data or affecting pattern processing (END, VOID, INVERT,
 *   PF, VF, PORT and so on), often without a specification structure. Since
 *   they do not match packet contents, these can be specified anywhere
 *   within item lists without affecting others.
 *
 * See the description of individual types for more information. Those
 * marked with [META] fall into the second category.
 */
enum rte_flow_item_type {
	/**
	 * [META]
	 *
	 * End marker for item lists. Prevents further processing of items,
	 * thereby ending the pattern.
	 *
	 * No associated specification structure.
	 */
	RTE_FLOW_ITEM_TYPE_END,

	/**
	 * [META]
	 *
	 * Used as a placeholder for convenience. It is ignored and simply
	 * discarded by PMDs.
	 *
	 * No associated specification structure.
	 */
	RTE_FLOW_ITEM_TYPE_VOID,

	/**
	 * [META]
	 *
	 * Inverted matching, i.e. process packets that do not match the
	 * pattern.
	 *
	 * No associated specification structure.
	 */
	RTE_FLOW_ITEM_TYPE_INVERT,

	/**
	 * Matches any protocol in place of the current layer, a single ANY
	 * may also stand for several protocol layers.
	 *
	 * See struct rte_flow_item_any.
	 */
	RTE_FLOW_ITEM_TYPE_ANY,

	/**
	 * [META]
	 *
	 * Matches packets addressed to the physical function of the device.
	 *
	 * If the underlying device function differs from the one that would
	 * normally receive the matched traffic, specifying this item
	 * prevents it from reaching that device unless the flow rule
	 * contains a PF action. Packets are not duplicated between device
	 * instances by default.
	 *
	 * No associated specification structure.
	 */
	RTE_FLOW_ITEM_TYPE_PF,

	/**
	 * [META]
	 *
	 * Matches packets addressed to a virtual function ID of the device.
	 *
	 * If the underlying device function differs from the one that would
	 * normally receive the matched traffic, specifying this item
	 * prevents it from reaching that device unless the flow rule
	 * contains a VF action. Packets are not duplicated between device
	 * instances by default.
	 *
	 * See struct rte_flow_item_vf.
	 */
	RTE_FLOW_ITEM_TYPE_VF,

	/**
	 * [META]
	 *
	 * Matches packets coming from the specified physical port of the
	 * underlying device.
	 *
	 * The first PORT item overrides the physical port normally
	 * associated with the specified DPDK input port (port_id). This
	 * item can be provided several times to match additional physical
	 * ports.
	 *
	 * See struct rte_flow_item_port.
	 */
	RTE_FLOW_ITEM_TYPE_PORT,

	/**
	 * Matches a byte string of a given length at a given offset.
	 *
	 * See struct rte_flow_item_raw.
	 */
	RTE_FLOW_ITEM_TYPE_RAW,

	/**
	 * Matches an Ethernet header.
	 *
	 * See struct rte_flow_item_eth.
	 */
	RTE_FLOW_ITEM_TYPE_ETH,

	/**
	 * Matches an 802.1Q/ad VLAN tag.
	 *
	 * See struct rte_flow_item_vlan.
	 */
	RTE_FLOW_ITEM_TYPE_VLAN,

	/**
	 * Matches an IPv4 header.
	 *
	 * See struct rte_flow_item_ipv4.
	 */
	RTE_FLOW_ITEM_TYPE_IPV4,

	/**
	 * Matches an IPv6 header.
	 *
	 * See struct rte_flow_item_ipv6.
	 */
	RTE_FLOW_ITEM_TYPE_IPV6,

	/**
	 * Matches an ICMP header.
	 *
	 * See struct rte_flow_item_icmp.
	 */
	RTE_FLOW_ITEM_TYPE_ICMP,

	/**
	 * Matches a UDP header.
	 *
	 * See struct rte_flow_item_udp.
	 */
	RTE_FLOW_ITEM_TYPE_UDP,

	/**
	 * Matches a TCP header.
	 *
	 * See struct rte_flow_item_tcp.
	 */
	RTE_FLOW_ITEM_TYPE_TCP,

	/**
	 * Matches a SCTP header.
	 *
	 * See struct rte_flow_item_sctp.
	 */
	RTE_FLOW_ITEM_TYPE_SCTP,

	/**
	 * Matches a VXLAN header.
	 *
	 * See struct rte_flow_item_vxlan.
	 */
	RTE_FLOW_ITEM_TYPE_VXLAN,

	/**
	 * Matches a E_TAG header.
	 *
	 * See struct rte_flow_item_e_tag.
	 */
	RTE_FLOW_ITEM_TYPE_E_TAG,

	/**
	 * Matches a NVGRE header.
	 *
	 * See struct rte_flow_item_nvgre.
	 */
	RTE_FLOW_ITEM_TYPE_NVGRE,
};

/**
 * RTE_FLOW_ITEM_TYPE_ANY
 *
 * Matches any protocol in place of the current layer, a single ANY may also
 * stand for several protocol layers.
 *
 * This is usually specified as the first pattern item when looking for a
 * protocol anywhere in a packet.
 *
 * A zeroed mask stands for any number of layers.
 */
struct rte_flow_item_any {
	uint32_t num; /**< Number of layers covered. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_ANY. */
static const struct rte_flow_item_any rte_flow_item_any_mask = {
	.num = 0x00000000,
};

/**
 * RTE_FLOW_ITEM_TYPE_VF
 *
 * Matches packets addressed to a virtual function ID of the device.
 *
 * If the underlying device function differs from the one that would
 * normally receive the matched traffic, specifying this item prevents it
 * from reaching that device unless the flow rule contains a VF
 * action. Packets are not duplicated between device instances by default.
 *
 * - Likely to return an error or never match any traffic if this causes a
 *   VF device to match traffic addressed to a different VF.
 * - Can be specified multiple times to match traffic addressed to several
 *   VF IDs.
 * - Can be combined with a PF item to match both PF and VF traffic.
 *
 * A zeroed mask can be used to match any VF ID.
 */
struct rte_flow_item_vf {
	uint32_t id; /**< Destination VF ID. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_VF. */
static const struct rte_flow_item_vf rte_flow_item_vf_mask = {
	.id = 0x00000000,
};

/**
 * RTE_FLOW_ITEM_TYPE_PORT
 *
 * Matches packets coming from the specified physical port of the underlying
 * device.
 *
 * The first PORT item overrides the physical port normally associated with
 * the specified DPDK input port (port_id). This item can be provided
 * several times to match additional physical ports.
 *
 * Note that physical ports are not necessarily tied to DPDK input ports
 * (port_id) when those are not under DPDK control. Possible values are
 * specific to each device, they are not necessarily indexed from zero and
 * may not be contiguous.
 *
 * As a device property, the list of allowed values as well as the value
 * associated with a port_id should be retrieved by other means.
 *
 * A zeroed mask can be used to match any port index.
 */
struct rte_flow_item_port {
	uint32_t index; /**< Physical port index. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_PORT. */
static const struct rte_flow_item_port rte_flow_item_port_mask = {
	.index = 0x00000000,
};

/**
 * RTE_FLOW_ITEM_TYPE_RAW
 *
 * Matches a byte string of a given length at a given offset.
 *
 * Offset is either absolute (using the start of the packet) or relative to
 * the end of the previous matched item in the stack, in which case negative
 * values are allowed.
 *
 * If search is enabled, offset is used as the starting point. The search
 * area can be delimited by setting limit to a nonzero value, which is the
 * maximum number of bytes after offset where the pattern may start.
 *
 * Matching a zero-length pattern is allowed, doing so resets the relative
 * offset for subsequent items.
 *
 * This type does not support ranges (struct rte_flow_item.last).
 */
struct rte_flow_item_raw {
	uint32_t relative:1; /**< Look for pattern after the previous item. */
	uint32_t search:1; /**< Search pattern from offset (see also limit). */
	uint32_t reserved:30; /**< Reserved, must be set to zero. */
	int32_t offset; /**< Absolute or relative offset for pattern. */
	uint16_t limit; /**< Search area limit for start of pattern. */
	uint16_t length; /**< Pattern length. */
	uint8_t pattern[]; /**< Byte string to look for. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_RAW. */
static const struct rte_flow_item_raw rte_flow_item_raw_mask = {
	.relative = 1,
	.search = 1,
	.reserved = 0x3fffffff,
	.offset = 0xffffffff,
	.limit = 0xffff,
	.length = 0xffff,
};

/**
 * RTE_FLOW_ITEM_TYPE_ETH
 *
 * Matches an Ethernet header.
 */
struct rte_flow_item_eth {
	struct ether_addr dst; /**< Destination MAC. */
	struct ether_addr src; /**< Source MAC. */
	uint16_t type; /**< EtherType. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_ETH. */
static const struct rte_flow_item_eth rte_flow_item_eth_mask = {
	.dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
	.src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
	.type = 0x0000,
};

/**
 * RTE_FLOW_ITEM_TYPE_VLAN
 *
 * Matches an 802.1Q/ad VLAN tag.
 *
 * This type normally follows either RTE_FLOW_ITEM_TYPE_ETH or
 * RTE_FLOW_ITEM_TYPE_VLAN.
 */
struct rte_flow_item_vlan {
	uint16_t tpid; /**< Tag protocol identifier. */
	uint16_t tci; /**< Tag control information. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_VLAN. */
static const struct rte_flow_item_vlan rte_flow_item_vlan_mask = {
	.tpid = 0x0000,
	.tci = 0xffff,
};

/**
 * RTE_FLOW_ITEM_TYPE_IPV4
 *
 * Matches an IPv4 header.
 *
 * Note: IPv4 options are handled by dedicated pattern items.
 */
struct rte_flow_item_ipv4 {
	struct ipv4_hdr hdr; /**< IPv4 header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_IPV4. */
static const struct rte_flow_item_ipv4 rte_flow_item_ipv4_mask = {
	.hdr = {
		.src_addr = 0xffffffff,
		.dst_addr = 0xffffffff,
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_IPV6.
 *
 * Matches an IPv6 header.
 *
 * Note: IPv6 options are handled by dedicated pattern items.
 */
struct rte_flow_item_ipv6 {
	struct ipv6_hdr hdr; /**< IPv6 header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_IPV6. */
static const struct rte_flow_item_ipv6 rte_flow_item_ipv6_mask = {
	.hdr = {
		.src_addr =
			"\xff\xff\xff\xff\xff\xff\xff\xff"
			"\xff\xff\xff\xff\xff\xff\xff\xff",
		.dst_addr =
			"\xff\xff\xff\xff\xff\xff\xff\xff"
			"\xff\xff\xff\xff\xff\xff\xff\xff",
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_ICMP.
 *
 * Matches an ICMP header.
 */
struct rte_flow_item_icmp {
	struct icmp_hdr hdr; /**< ICMP header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_ICMP. */
static const struct rte_flow_item_icmp rte_flow_item_icmp_mask = {
	.hdr = {
		.icmp_type = 0xff,
		.icmp_code = 0xff,
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_UDP.
 *
 * Matches a UDP header.
 */
struct rte_flow_item_udp {
	struct udp_hdr hdr; /**< UDP header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_UDP. */
static const struct rte_flow_item_udp rte_flow_item_udp_mask = {
	.hdr = {
		.src_port = 0xffff,
		.dst_port = 0xffff,
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_TCP.
 *
 * Matches a TCP header.
 */
struct rte_flow_item_tcp {
	struct tcp_hdr hdr; /**< TCP header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_TCP. */
static const struct rte_flow_item_tcp rte_flow_item_tcp_mask = {
	.hdr = {
		.src_port = 0xffff,
		.dst_port = 0xffff,
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_SCTP.
 *
 * Matches a SCTP header.
 */
struct rte_flow_item_sctp {
	struct sctp_hdr hdr; /**< SCTP header definition. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_SCTP. */
static const struct rte_flow_item_sctp rte_flow_item_sctp_mask = {
	.hdr = {
		.src_port = 0xffff,
		.dst_port = 0xffff,
	},
};

/**
 * RTE_FLOW_ITEM_TYPE_VXLAN.
 *
 * Matches a VXLAN header (RFC 7348).
 */
struct rte_flow_item_vxlan {
	uint8_t flags; /**< Normally 0x08 (I flag). */
	uint8_t rsvd0[3]; /**< Reserved, normally 0x000000. */
	uint8_t vni[3]; /**< VXLAN identifier. */
	uint8_t rsvd1; /**< Reserved, normally 0x00. */
};

/** Default mask for RTE_FLOW_ITEM_TYPE_VXLAN. */
static const struct rte_flow_item_vxlan rte_flow_item_vxlan_mask = {
	.vni = "\xff\xff\xff",
};

/**
 * RTE_FLOW_ITEM_TYPE_E_TAG.
 *
 * Matches a E-tag header.
 */
struct rte_flow_item_e_tag {
	uint16_t tpid; /**< Tag protocol identifier (0x893F). */
	/**
	 * E-Tag control information (E-TCI).
	 * E-PCP (3b), E-DEI (1b), ingress E-CID base (12b).
	 */
	uint16_t epcp_edei_in_ecid_b;
	/** Reserved (2b), GRP (2b), E-CID base (12b). */
	uint16_t rsvd_grp_ecid_b;
	uint8_t in_ecid_e; /**< Ingress E-CID ext. */
	uint8_t ecid_e; /**< E-CID ext. */
};

/**
 * RTE_FLOW_ITEM_TYPE_NVGRE.
 *
 * Matches a NVGRE header.
 */
struct rte_flow_item_nvgre {
	/**
	 * Checksum (1b), undefined (1b), key bit (1b), sequence number (1b),
	 * reserved 0 (9b), version (3b).
	 *
	 * c_k_s_rsvd0_ver must have value 0x2000 according to RFC 7637.
	 */
	uint16_t c_k_s_rsvd0_ver;
	uint16_t protocol; /**< Protocol type (0x6558). */
	uint8_t tni[3]; /**< Virtual subnet ID. */
	uint8_t flow_id; /**< Flow ID. */
};

/**
 * Matching pattern item definition.
 *
 * A pattern is formed by stacking items starting from the lowest protocol
 * layer to match. This stacking restriction does not apply to meta items
 * which can be placed anywhere in the stack without affecting the meaning
 * of the resulting pattern.
 *
 * Patterns are terminated by END items.
 *
 * The spec field should be a valid pointer to a structure of the related
 * item type. It may remain unspecified (NULL) in many cases to request
 * broad (nonspecific) matching. In such cases, last and mask must also be
 * set to NULL.
 *
 * Optionally, last can point to a structure of the same type to define an
 * inclusive range. This is mostly supported by integer and address fields,
 * may cause errors otherwise. Fields that do not support ranges must be set
 * to 0 or to the same value as the corresponding fields in spec.
 *
 * Only the fields defined to nonzero values in the default masks (see
 * rte_flow_item_{name}_mask constants) are considered relevant by
 * default. This can be overridden by providing a mask structure of the
 * same type with applicable bits set to one. It can also be used to
 * partially filter out specific fields (e.g. as an alternate mean to match
 * ranges of IP addresses).
 *
 * Mask is a simple bit-mask applied before interpreting the contents of
 * spec and last, which may yield unexpected results if not used
 * carefully. For example, if for an IPv4 address field, spec provides
 * 10.1.2.3, last provides 10.3.4.5 and mask provides 255.255.0.0, the
 * effective range becomes 10.1.0.0 to 10.3.255.255.
 */
struct rte_flow_item {
	enum rte_flow_item_type type; /**< Item type. */
	const void *spec; /**< Pointer to item specification structure. */
	const void *last; /**< Defines an inclusive range (spec to last). */
	const void *mask; /**< Bit-mask applied to spec and last. */
};

/**
 * Action types.
 *
 * Each possible action is represented by a type. Some have associated
 * configuration structures. Several actions combined in a list can be
 * affected to a flow rule. That list is not ordered.
 *
 * They fall in three categories:
 *
 * - Terminating actions (such as QUEUE, DROP, RSS, PF, VF) that prevent
 *   processing matched packets by subsequent flow rules, unless overridden
 *   with PASSTHRU.
 *
 * - Non terminating actions (PASSTHRU, DUP) that leave matched packets up
 *   for additional processing by subsequent flow rules.
 *
 * - Other non terminating meta actions that do not affect the fate of
 *   packets (END, VOID, MARK, FLAG, COUNT).
 *
 * When several actions are combined in a flow rule, they should all have
 * different types (e.g. dropping a packet twice is not possible).
 *
 * Only the last action of a given type is taken into account. PMDs still
 * perform error checking on the entire list.
 *
 * Note that PASSTHRU is the only action able to override a terminating
 * rule.
 */
enum rte_flow_action_type {
	/**
	 * [META]
	 *
	 * End marker for action lists. Prevents further processing of
	 * actions, thereby ending the list.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_END,

	/**
	 * [META]
	 *
	 * Used as a placeholder for convenience. It is ignored and simply
	 * discarded by PMDs.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_VOID,

	/**
	 * Leaves packets up for additional processing by subsequent flow
	 * rules. This is the default when a rule does not contain a
	 * terminating action, but can be specified to force a rule to
	 * become non-terminating.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_PASSTHRU,

	/**
	 * [META]
	 *
	 * Attaches an integer value to packets and sets PKT_RX_FDIR and
	 * PKT_RX_FDIR_ID mbuf flags.
	 *
	 * See struct rte_flow_action_mark.
	 */
	RTE_FLOW_ACTION_TYPE_MARK,

	/**
	 * [META]
	 *
	 * Flags packets. Similar to MARK without a specific value; only
	 * sets the PKT_RX_FDIR mbuf flag.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_FLAG,

	/**
	 * Assigns packets to a given queue index.
	 *
	 * See struct rte_flow_action_queue.
	 */
	RTE_FLOW_ACTION_TYPE_QUEUE,

	/**
	 * Drops packets.
	 *
	 * PASSTHRU overrides this action if both are specified.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_DROP,

	/**
	 * [META]
	 *
	 * Enables counters for this rule.
	 *
	 * These counters can be retrieved and reset through rte_flow_query(),
	 * see struct rte_flow_query_count.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_COUNT,

	/**
	 * Duplicates packets to a given queue index.
	 *
	 * This is normally combined with QUEUE, however when used alone, it
	 * is actually similar to QUEUE + PASSTHRU.
	 *
	 * See struct rte_flow_action_dup.
	 */
	RTE_FLOW_ACTION_TYPE_DUP,

	/**
	 * Similar to QUEUE, except RSS is additionally performed on packets
	 * to spread them among several queues according to the provided
	 * parameters.
	 *
	 * See struct rte_flow_action_rss.
	 */
	RTE_FLOW_ACTION_TYPE_RSS,

	/**
	 * Redirects packets to the physical function (PF) of the current
	 * device.
	 *
	 * No associated configuration structure.
	 */
	RTE_FLOW_ACTION_TYPE_PF,

	/**
	 * Redirects packets to the virtual function (VF) of the current
	 * device with the specified ID.
	 *
	 * See struct rte_flow_action_vf.
	 */
	RTE_FLOW_ACTION_TYPE_VF,
};

/**
 * RTE_FLOW_ACTION_TYPE_MARK
 *
 * Attaches an integer value to packets and sets PKT_RX_FDIR and
 * PKT_RX_FDIR_ID mbuf flags.
 *
 * This value is arbitrary and application-defined. Maximum allowed value
 * depends on the underlying implementation. It is returned in the
 * hash.fdir.hi mbuf field.
 */
struct rte_flow_action_mark {
	uint32_t id; /**< Integer value to return with packets. */
};

/**
 * RTE_FLOW_ACTION_TYPE_QUEUE
 *
 * Assign packets to a given queue index.
 *
 * Terminating by default.
 */
struct rte_flow_action_queue {
	uint16_t index; /**< Queue index to use. */
};

/**
 * RTE_FLOW_ACTION_TYPE_COUNT (query)
 *
 * Query structure to retrieve and reset flow rule counters.
 */
struct rte_flow_query_count {
	uint32_t reset:1; /**< Reset counters after query [in]. */
	uint32_t hits_set:1; /**< hits field is set [out]. */
	uint32_t bytes_set:1; /**< bytes field is set [out]. */
	uint32_t reserved:29; /**< Reserved, must be zero [in, out]. */
	uint64_t hits; /**< Number of hits for this rule [out]. */
	uint64_t bytes; /**< Number of bytes through this rule [out]. */
};

/**
 * RTE_FLOW_ACTION_TYPE_DUP
 *
 * Duplicates packets to a given queue index.
 *
 * This is normally combined with QUEUE, however when used alone, it is
 * actually similar to QUEUE + PASSTHRU.
 *
 * Non-terminating by default.
 */
struct rte_flow_action_dup {
	uint16_t index; /**< Queue index to duplicate packets to. */
};

/**
 * RTE_FLOW_ACTION_TYPE_RSS
 *
 * Similar to QUEUE, except RSS is additionally performed on packets to
 * spread them among several queues according to the provided parameters.
 *
 * Note: RSS hash result is stored in the hash.rss mbuf field which overlaps
 * hash.fdir.lo. Since the MARK action sets the hash.fdir.hi field only,
 * both can be requested simultaneously.
 *
 * Terminating by default.
 */
struct rte_flow_action_rss {
	const struct rte_eth_rss_conf *rss_conf; /**< RSS parameters. */
	uint16_t num; /**< Number of entries in queue[]. */
	uint16_t queue[]; /**< Queues indices to use. */
};

/**
 * RTE_FLOW_ACTION_TYPE_VF
 *
 * Redirects packets to a virtual function (VF) of the current device.
 *
 * Packets matched by a VF pattern item can be redirected to their original
 * VF ID instead of the specified one. This parameter may not be available
 * and is not guaranteed to work properly if the VF part is matched by a
 * prior flow rule or if packets are not addressed to a VF in the first
 * place.
 *
 * Terminating by default.
 */
struct rte_flow_action_vf {
	uint32_t original:1; /**< Use original VF ID if possible. */
	uint32_t reserved:31; /**< Reserved, must be zero. */
	uint32_t id; /**< VF ID to redirect packets to. */
};

/**
 * Definition of a single action.
 *
 * A list of actions is terminated by a END action.
 *
 * For simple actions without a configuration structure, conf remains NULL.
 */
struct rte_flow_action {
	enum rte_flow_action_type type; /**< Action type. */
	const void *conf; /**< Pointer to action configuration structure. */
};

/**
 * Opaque type returned after successfully creating a flow.
 *
 * This handle can be used to manage and query the related flow (e.g. to
 * destroy it or retrieve counters).
 */
struct rte_flow;

/**
 * Verbose error types.
 *
 * Most of them provide the type of the object referenced by struct
 * rte_flow_error.cause.
 */
enum rte_flow_error_type {
	RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */
	RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */
	RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */
	RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */
	RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */
	RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */
	RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */
	RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */
	RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */
	RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */
	RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */
	RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */
};

/**
 * Verbose error structure definition.
 *
 * This object is normally allocated by applications and set by PMDs, the
 * message points to a constant string which does not need to be freed by
 * the application, however its pointer can be considered valid only as long
 * as its associated DPDK port remains configured. Closing the underlying
 * device or unloading the PMD invalidates it.
 *
 * Both cause and message may be NULL regardless of the error type.
 */
struct rte_flow_error {
	enum rte_flow_error_type type; /**< Cause field and error types. */
	const void *cause; /**< Object responsible for the error. */
	const char *message; /**< Human-readable error message. */
};

/**
 * Check whether a flow rule can be created on a given port.
 *
 * While this function has no effect on the target device, the flow rule is
 * validated against its current configuration state and the returned value
 * should be considered valid by the caller for that state only.
 *
 * The returned value is guaranteed to remain valid only as long as no
 * successful calls to rte_flow_create() or rte_flow_destroy() are made in
 * the meantime and no device parameter affecting flow rules in any way are
 * modified, due to possible collisions or resource limitations (although in
 * such cases EINVAL should not be returned).
 *
 * @param port_id
 *   Port identifier of Ethernet device.
 * @param[in] attr
 *   Flow rule attributes.
 * @param[in] pattern
 *   Pattern specification (list terminated by the END pattern item).
 * @param[in] actions
 *   Associated actions (list terminated by the END action).
 * @param[out] error
 *   Perform verbose error reporting if not NULL. PMDs initialize this
 *   structure in case of error only.
 *
 * @return
 *   0 if flow rule is valid and can be created. A negative errno value
 *   otherwise (rte_errno is also set), the following errors are defined:
 *
 *   -ENOSYS: underlying device does not support this functionality.
 *
 *   -EINVAL: unknown or invalid rule specification.
 *
 *   -ENOTSUP: valid but unsupported rule specification (e.g. partial
 *   bit-masks are unsupported).
 *
 *   -EEXIST: collision with an existing rule.
 *
 *   -ENOMEM: not enough resources.
 *
 *   -EBUSY: action cannot be performed due to busy device resources, may
 *   succeed if the affected queues or even the entire port are in a stopped
 *   state (see rte_eth_dev_rx_queue_stop() and rte_eth_dev_stop()).
 */
int
rte_flow_validate(uint8_t port_id,
		  const struct rte_flow_attr *attr,
		  const struct rte_flow_item pattern[],
		  const struct rte_flow_action actions[],
		  struct rte_flow_error *error);

/**
 * Create a flow rule on a given port.
 *
 * @param port_id
 *   Port identifier of Ethernet device.
 * @param[in] attr
 *   Flow rule attributes.
 * @param[in] pattern
 *   Pattern specification (list terminated by the END pattern item).
 * @param[in] actions
 *   Associated actions (list terminated by the END action).
 * @param[out] error
 *   Perform verbose error reporting if not NULL. PMDs initialize this
 *   structure in case of error only.
 *
 * @return
 *   A valid handle in case of success, NULL otherwise and rte_errno is set
 *   to the positive version of one of the error codes defined for
 *   rte_flow_validate().
 */
struct rte_flow *
rte_flow_create(uint8_t port_id,
		const struct rte_flow_attr *attr,
		const struct rte_flow_item pattern[],
		const struct rte_flow_action actions[],
		struct rte_flow_error *error);

/**
 * Destroy a flow rule on a given port.
 *
 * Failure to destroy a flow rule handle may occur when other flow rules
 * depend on it, and destroying it would result in an inconsistent state.
 *
 * This function is only guaranteed to succeed if handles are destroyed in
 * reverse order of their creation.
 *
 * @param port_id
 *   Port identifier of Ethernet device.
 * @param flow
 *   Flow rule handle to destroy.
 * @param[out] error
 *   Perform verbose error reporting if not NULL. PMDs initialize this
 *   structure in case of error only.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
rte_flow_destroy(uint8_t port_id,
		 struct rte_flow *flow,
		 struct rte_flow_error *error);

/**
 * Destroy all flow rules associated with a port.
 *
 * In the unlikely event of failure, handles are still considered destroyed
 * and no longer valid but the port must be assumed to be in an inconsistent
 * state.
 *
 * @param port_id
 *   Port identifier of Ethernet device.
 * @param[out] error
 *   Perform verbose error reporting if not NULL. PMDs initialize this
 *   structure in case of error only.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
rte_flow_flush(uint8_t port_id,
	       struct rte_flow_error *error);

/**
 * Query an existing flow rule.
 *
 * This function allows retrieving flow-specific data such as counters.
 * Data is gathered by special actions which must be present in the flow
 * rule definition.
 *
 * \see RTE_FLOW_ACTION_TYPE_COUNT
 *
 * @param port_id
 *   Port identifier of Ethernet device.
 * @param flow
 *   Flow rule handle to query.
 * @param action
 *   Action type to query.
 * @param[in, out] data
 *   Pointer to storage for the associated query data type.
 * @param[out] error
 *   Perform verbose error reporting if not NULL. PMDs initialize this
 *   structure in case of error only.
 *
 * @return
 *   0 on success, a negative errno value otherwise and rte_errno is set.
 */
int
rte_flow_query(uint8_t port_id,
	       struct rte_flow *flow,
	       enum rte_flow_action_type action,
	       void *data,
	       struct rte_flow_error *error);

#ifdef __cplusplus
}
#endif

#endif /* RTE_FLOW_H_ */