aboutsummaryrefslogtreecommitdiffstats
path: root/lib/librte_mbuf/rte_mbuf.h
blob: 807a8d419af79a4649b718e2d0609d240bfc13d7 (plain)
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
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
 *   Copyright 2014 6WIND S.A.
 *   All rights reserved.
 *
 *   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 Intel Corporation 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_MBUF_H_
#define _RTE_MBUF_H_

/**
 * @file
 * RTE Mbuf
 *
 * The mbuf library provides the ability to create and destroy buffers
 * that may be used by the RTE application to store message
 * buffers. The message buffers are stored in a mempool, using the
 * RTE mempool library.
 *
 * The preferred way to create a mbuf pool is to use
 * rte_pktmbuf_pool_create(). However, in some situations, an
 * application may want to have more control (ex: populate the pool with
 * specific memory), in this case it is possible to use functions from
 * rte_mempool. See how rte_pktmbuf_pool_create() is implemented for
 * details.
 *
 * This library provides an API to allocate/free packet mbufs, which are
 * used to carry network packets.
 *
 * To understand the concepts of packet buffers or mbufs, you
 * should read "TCP/IP Illustrated, Volume 2: The Implementation,
 * Addison-Wesley, 1995, ISBN 0-201-63354-X from Richard Stevens"
 * http://www.kohala.com/start/tcpipiv2.html
 */

#include <stdint.h>
#include <rte_common.h>
#include <rte_config.h>
#include <rte_mempool.h>
#include <rte_memory.h>
#include <rte_atomic.h>
#include <rte_prefetch.h>
#include <rte_branch_prediction.h>
#include <rte_mbuf_ptype.h>

#ifdef __cplusplus
extern "C" {
#endif

/*
 * Packet Offload Features Flags. It also carry packet type information.
 * Critical resources. Both rx/tx shared these bits. Be cautious on any change
 *
 * - RX flags start at bit position zero, and get added to the left of previous
 *   flags.
 * - The most-significant 3 bits are reserved for generic mbuf flags
 * - TX flags therefore start at bit position 60 (i.e. 63-3), and new flags get
 *   added to the right of the previously defined flags i.e. they should count
 *   downwards, not upwards.
 *
 * Keep these flags synchronized with rte_get_rx_ol_flag_name() and
 * rte_get_tx_ol_flag_name().
 */

/**
 * The RX packet is a 802.1q VLAN packet, and the tci has been
 * saved in in mbuf->vlan_tci.
 * If the flag PKT_RX_VLAN_STRIPPED is also present, the VLAN
 * header has been stripped from mbuf data, else it is still
 * present.
 */
#define PKT_RX_VLAN          (1ULL << 0)

#define PKT_RX_RSS_HASH      (1ULL << 1)  /**< RX packet with RSS hash result. */
#define PKT_RX_FDIR          (1ULL << 2)  /**< RX packet with FDIR match indicate. */

/**
 * Deprecated.
 * Checking this flag alone is deprecated: check the 2 bits of
 * PKT_RX_L4_CKSUM_MASK.
 * This flag was set when the L4 checksum of a packet was detected as
 * wrong by the hardware.
 */
#define PKT_RX_L4_CKSUM_BAD  (1ULL << 3)

/**
 * Deprecated.
 * Checking this flag alone is deprecated: check the 2 bits of
 * PKT_RX_IP_CKSUM_MASK.
 * This flag was set when the IP checksum of a packet was detected as
 * wrong by the hardware.
 */
#define PKT_RX_IP_CKSUM_BAD  (1ULL << 4)

#define PKT_RX_EIP_CKSUM_BAD (1ULL << 5)  /**< External IP header checksum error. */

/**
 * A vlan has been stripped by the hardware and its tci is saved in
 * mbuf->vlan_tci. This can only happen if vlan stripping is enabled
 * in the RX configuration of the PMD.
 * When PKT_RX_VLAN_STRIPPED is set, PKT_RX_VLAN must also be set.
 */
#define PKT_RX_VLAN_STRIPPED (1ULL << 6)

/**
 * Mask of bits used to determine the status of RX IP checksum.
 * - PKT_RX_IP_CKSUM_UNKNOWN: no information about the RX IP checksum
 * - PKT_RX_IP_CKSUM_BAD: the IP checksum in the packet is wrong
 * - PKT_RX_IP_CKSUM_GOOD: the IP checksum in the packet is valid
 * - PKT_RX_IP_CKSUM_NONE: the IP checksum is not correct in the packet
 *   data, but the integrity of the IP header is verified.
 */
#define PKT_RX_IP_CKSUM_MASK ((1ULL << 4) | (1ULL << 7))

#define PKT_RX_IP_CKSUM_UNKNOWN 0
#define PKT_RX_IP_CKSUM_BAD     (1ULL << 4)
#define PKT_RX_IP_CKSUM_GOOD    (1ULL << 7)
#define PKT_RX_IP_CKSUM_NONE    ((1ULL << 4) | (1ULL << 7))

/**
 * Mask of bits used to determine the status of RX L4 checksum.
 * - PKT_RX_L4_CKSUM_UNKNOWN: no information about the RX L4 checksum
 * - PKT_RX_L4_CKSUM_BAD: the L4 checksum in the packet is wrong
 * - PKT_RX_L4_CKSUM_GOOD: the L4 checksum in the packet is valid
 * - PKT_RX_L4_CKSUM_NONE: the L4 checksum is not correct in the packet
 *   data, but the integrity of the L4 data is verified.
 */
#define PKT_RX_L4_CKSUM_MASK ((1ULL << 3) | (1ULL << 8))

#define PKT_RX_L4_CKSUM_UNKNOWN 0
#define PKT_RX_L4_CKSUM_BAD     (1ULL << 3)
#define PKT_RX_L4_CKSUM_GOOD    (1ULL << 8)
#define PKT_RX_L4_CKSUM_NONE    ((1ULL << 3) | (1ULL << 8))

#define PKT_RX_IEEE1588_PTP  (1ULL << 9)  /**< RX IEEE1588 L2 Ethernet PT Packet. */
#define PKT_RX_IEEE1588_TMST (1ULL << 10) /**< RX IEEE1588 L2/L4 timestamped packet.*/
#define PKT_RX_FDIR_ID       (1ULL << 13) /**< FD id reported if FDIR match. */
#define PKT_RX_FDIR_FLX      (1ULL << 14) /**< Flexible bytes reported if FDIR match. */

/**
 * The 2 vlans have been stripped by the hardware and their tci are
 * saved in mbuf->vlan_tci (inner) and mbuf->vlan_tci_outer (outer).
 * This can only happen if vlan stripping is enabled in the RX
 * configuration of the PMD. If this flag is set,
 * When PKT_RX_QINQ_STRIPPED is set, the flags (PKT_RX_VLAN |
 * PKT_RX_VLAN_STRIPPED | PKT_RX_QINQ) must also be set.
 */
#define PKT_RX_QINQ_STRIPPED (1ULL << 15)

/**
 * When packets are coalesced by a hardware or virtual driver, this flag
 * can be set in the RX mbuf, meaning that the m->tso_segsz field is
 * valid and is set to the segment size of original packets.
 */
#define PKT_RX_LRO           (1ULL << 16)

/**
 * Indicate that the timestamp field in the mbuf is valid.
 */
#define PKT_RX_TIMESTAMP     (1ULL << 17)

/**
 * Indicate that security offload processing was applied on the RX packet.
 */
#define PKT_RX_SEC_OFFLOAD		(1ULL << 18)

/**
 * Indicate that security offload processing failed on the RX packet.
 */
#define PKT_RX_SEC_OFFLOAD_FAILED  	(1ULL << 19)

/**
 * The RX packet is a double VLAN, and the outer tci has been
 * saved in in mbuf->vlan_tci_outer.
 * If the flag PKT_RX_QINQ_STRIPPED is also present, both VLANs
 * headers have been stripped from mbuf data, else they are still
 * present.
 */
#define PKT_RX_QINQ          (1ULL << 20)

/* add new RX flags here */

/* add new TX flags here */

/**
 * Request security offload processing on the TX packet.
 */
#define PKT_TX_SEC_OFFLOAD 		(1ULL << 43)

/**
 * Offload the MACsec. This flag must be set by the application to enable
 * this offload feature for a packet to be transmitted.
 */
#define PKT_TX_MACSEC        (1ULL << 44)

/**
 * Bits 45:48 used for the tunnel type.
 * The tunnel type must be specified for TSO or checksum on the inner part
 * of tunnel packets.
 * These flags can be used with PKT_TX_TCP_SEG for TSO, or PKT_TX_xxx_CKSUM.
 * The mbuf fields for inner and outer header lengths are required:
 * outer_l2_len, outer_l3_len, l2_len, l3_len, l4_len and tso_segsz for TSO.
 */
#define PKT_TX_TUNNEL_VXLAN   (0x1ULL << 45)
#define PKT_TX_TUNNEL_GRE     (0x2ULL << 45)
#define PKT_TX_TUNNEL_IPIP    (0x3ULL << 45)
#define PKT_TX_TUNNEL_GENEVE  (0x4ULL << 45)
/** TX packet with MPLS-in-UDP RFC 7510 header. */
#define PKT_TX_TUNNEL_MPLSINUDP (0x5ULL << 45)
/* add new TX TUNNEL type here */
#define PKT_TX_TUNNEL_MASK    (0xFULL << 45)

/**
 * Second VLAN insertion (QinQ) flag.
 */
#define PKT_TX_QINQ_PKT    (1ULL << 49)   /**< TX packet with double VLAN inserted. */

/**
 * TCP segmentation offload. To enable this offload feature for a
 * packet to be transmitted on hardware supporting TSO:
 *  - set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies
 *    PKT_TX_TCP_CKSUM)
 *  - set the flag PKT_TX_IPV4 or PKT_TX_IPV6
 *  - if it's IPv4, set the PKT_TX_IP_CKSUM flag
 *  - fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz
 */
#define PKT_TX_TCP_SEG       (1ULL << 50)

#define PKT_TX_IEEE1588_TMST (1ULL << 51) /**< TX IEEE1588 packet to timestamp. */

/**
 * Bits 52+53 used for L4 packet type with checksum enabled: 00: Reserved,
 * 01: TCP checksum, 10: SCTP checksum, 11: UDP checksum. To use hardware
 * L4 checksum offload, the user needs to:
 *  - fill l2_len and l3_len in mbuf
 *  - set the flags PKT_TX_TCP_CKSUM, PKT_TX_SCTP_CKSUM or PKT_TX_UDP_CKSUM
 *  - set the flag PKT_TX_IPV4 or PKT_TX_IPV6
 */
#define PKT_TX_L4_NO_CKSUM   (0ULL << 52) /**< Disable L4 cksum of TX pkt. */
#define PKT_TX_TCP_CKSUM     (1ULL << 52) /**< TCP cksum of TX pkt. computed by NIC. */
#define PKT_TX_SCTP_CKSUM    (2ULL << 52) /**< SCTP cksum of TX pkt. computed by NIC. */
#define PKT_TX_UDP_CKSUM     (3ULL << 52) /**< UDP cksum of TX pkt. computed by NIC. */
#define PKT_TX_L4_MASK       (3ULL << 52) /**< Mask for L4 cksum offload request. */

/**
 * Offload the IP checksum in the hardware. The flag PKT_TX_IPV4 should
 * also be set by the application, although a PMD will only check
 * PKT_TX_IP_CKSUM.
 *  - fill the mbuf offload information: l2_len, l3_len
 */
#define PKT_TX_IP_CKSUM      (1ULL << 54)

/**
 * Packet is IPv4. This flag must be set when using any offload feature
 * (TSO, L3 or L4 checksum) to tell the NIC that the packet is an IPv4
 * packet. If the packet is a tunneled packet, this flag is related to
 * the inner headers.
 */
#define PKT_TX_IPV4          (1ULL << 55)

/**
 * Packet is IPv6. This flag must be set when using an offload feature
 * (TSO or L4 checksum) to tell the NIC that the packet is an IPv6
 * packet. If the packet is a tunneled packet, this flag is related to
 * the inner headers.
 */
#define PKT_TX_IPV6          (1ULL << 56)

#define PKT_TX_VLAN_PKT      (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */

/**
 * Offload the IP checksum of an external header in the hardware. The
 * flag PKT_TX_OUTER_IPV4 should also be set by the application, although
 * a PMD will only check PKT_TX_OUTER_IP_CKSUM.
 *  - fill the mbuf offload information: outer_l2_len, outer_l3_len
 */
#define PKT_TX_OUTER_IP_CKSUM   (1ULL << 58)

/**
 * Packet outer header is IPv4. This flag must be set when using any
 * outer offload feature (L3 or L4 checksum) to tell the NIC that the
 * outer header of the tunneled packet is an IPv4 packet.
 */
#define PKT_TX_OUTER_IPV4   (1ULL << 59)

/**
 * Packet outer header is IPv6. This flag must be set when using any
 * outer offload feature (L4 checksum) to tell the NIC that the outer
 * header of the tunneled packet is an IPv6 packet.
 */
#define PKT_TX_OUTER_IPV6    (1ULL << 60)

/**
 * Bitmask of all supported packet Tx offload features flags,
 * which can be set for packet.
 */
#define PKT_TX_OFFLOAD_MASK (    \
		PKT_TX_IP_CKSUM |        \
		PKT_TX_L4_MASK |         \
		PKT_TX_OUTER_IP_CKSUM |  \
		PKT_TX_TCP_SEG |         \
		PKT_TX_IEEE1588_TMST |	 \
		PKT_TX_QINQ_PKT |        \
		PKT_TX_VLAN_PKT |        \
		PKT_TX_TUNNEL_MASK |	 \
		PKT_TX_MACSEC |		 \
		PKT_TX_SEC_OFFLOAD)

#define __RESERVED           (1ULL << 61) /**< reserved for future mbuf use */

#define IND_ATTACHED_MBUF    (1ULL << 62) /**< Indirect attached mbuf */

/* Use final bit of flags to indicate a control mbuf */
#define CTRL_MBUF_FLAG       (1ULL << 63) /**< Mbuf contains control data */

/** Alignment constraint of mbuf private area. */
#define RTE_MBUF_PRIV_ALIGN 8

/**
 * Get the name of a RX offload flag
 *
 * @param mask
 *   The mask describing the flag.
 * @return
 *   The name of this flag, or NULL if it's not a valid RX flag.
 */
const char *rte_get_rx_ol_flag_name(uint64_t mask);

/**
 * Dump the list of RX offload flags in a buffer
 *
 * @param mask
 *   The mask describing the RX flags.
 * @param buf
 *   The output buffer.
 * @param buflen
 *   The length of the buffer.
 * @return
 *   0 on success, (-1) on error.
 */
int rte_get_rx_ol_flag_list(uint64_t mask, char *buf, size_t buflen);

/**
 * Get the name of a TX offload flag
 *
 * @param mask
 *   The mask describing the flag. Usually only one bit must be set.
 *   Several bits can be given if they belong to the same mask.
 *   Ex: PKT_TX_L4_MASK.
 * @return
 *   The name of this flag, or NULL if it's not a valid TX flag.
 */
const char *rte_get_tx_ol_flag_name(uint64_t mask);

/**
 * Dump the list of TX offload flags in a buffer
 *
 * @param mask
 *   The mask describing the TX flags.
 * @param buf
 *   The output buffer.
 * @param buflen
 *   The length of the buffer.
 * @return
 *   0 on success, (-1) on error.
 */
int rte_get_tx_ol_flag_list(uint64_t mask, char *buf, size_t buflen);

/**
 * Some NICs need at least 2KB buffer to RX standard Ethernet frame without
 * splitting it into multiple segments.
 * So, for mbufs that planned to be involved into RX/TX, the recommended
 * minimal buffer length is 2KB + RTE_PKTMBUF_HEADROOM.
 */
#define	RTE_MBUF_DEFAULT_DATAROOM	2048
#define	RTE_MBUF_DEFAULT_BUF_SIZE	\
	(RTE_MBUF_DEFAULT_DATAROOM + RTE_PKTMBUF_HEADROOM)

/* define a set of marker types that can be used to refer to set points in the
 * mbuf */
__extension__
typedef void    *MARKER[0];   /**< generic marker for a point in a structure */
__extension__
typedef uint8_t  MARKER8[0];  /**< generic marker with 1B alignment */
__extension__
typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes
                               * with a single assignment */

/**
 * The generic rte_mbuf, containing a packet mbuf.
 */
struct rte_mbuf {
	MARKER cacheline0;

	void *buf_addr;           /**< Virtual address of segment buffer. */
	/**
	 * Physical address of segment buffer.
	 * Force alignment to 8-bytes, so as to ensure we have the exact
	 * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes
	 * working on vector drivers easier.
	 */
	RTE_STD_C11
	union {
		rte_iova_t buf_iova;
		rte_iova_t buf_physaddr; /**< deprecated */
	} __rte_aligned(sizeof(rte_iova_t));

	/* next 8 bytes are initialised on RX descriptor rearm */
	MARKER64 rearm_data;
	uint16_t data_off;

	/**
	 * Reference counter. Its size should at least equal to the size
	 * of port field (16 bits), to support zero-copy broadcast.
	 * It should only be accessed using the following functions:
	 * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and
	 * rte_mbuf_refcnt_set(). The functionality of these functions (atomic,
	 * or non-atomic) is controlled by the CONFIG_RTE_MBUF_REFCNT_ATOMIC
	 * config option.
	 */
	RTE_STD_C11
	union {
		rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */
		uint16_t refcnt;              /**< Non-atomically accessed refcnt */
	};
	uint16_t nb_segs;         /**< Number of segments. */

	/** Input port (16 bits to support more than 256 virtual ports). */
	uint16_t port;

	uint64_t ol_flags;        /**< Offload features. */

	/* remaining bytes are set on RX when pulling packet from descriptor */
	MARKER rx_descriptor_fields1;

	/*
	 * The packet type, which is the combination of outer/inner L2, L3, L4
	 * and tunnel types. The packet_type is about data really present in the
	 * mbuf. Example: if vlan stripping is enabled, a received vlan packet
	 * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the
	 * vlan is stripped from the data.
	 */
	RTE_STD_C11
	union {
		uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */
		struct {
			uint32_t l2_type:4; /**< (Outer) L2 type. */
			uint32_t l3_type:4; /**< (Outer) L3 type. */
			uint32_t l4_type:4; /**< (Outer) L4 type. */
			uint32_t tun_type:4; /**< Tunnel type. */
			RTE_STD_C11
			union {
				uint8_t inner_esp_next_proto;
				/**< ESP next protocol type, valid if
				 * RTE_PTYPE_TUNNEL_ESP tunnel type is set
				 * on both Tx and Rx.
				 */
				__extension__
				struct {
					uint8_t inner_l2_type:4;
					/**< Inner L2 type. */
					uint8_t inner_l3_type:4;
					/**< Inner L3 type. */
				};
			};
			uint32_t inner_l4_type:4; /**< Inner L4 type. */
		};
	};

	uint32_t pkt_len;         /**< Total pkt len: sum of all segments. */
	uint16_t data_len;        /**< Amount of data in segment buffer. */
	/** VLAN TCI (CPU order), valid if PKT_RX_VLAN_STRIPPED is set. */
	uint16_t vlan_tci;

	union {
		uint32_t rss;     /**< RSS hash result if RSS enabled */
		struct {
			RTE_STD_C11
			union {
				struct {
					uint16_t hash;
					uint16_t id;
				};
				uint32_t lo;
				/**< Second 4 flexible bytes */
			};
			uint32_t hi;
			/**< First 4 flexible bytes or FD ID, dependent on
			     PKT_RX_FDIR_* flag in ol_flags. */
		} fdir;           /**< Filter identifier if FDIR enabled */
		struct {
			uint32_t lo;
			uint32_t hi;
		} sched;          /**< Hierarchical scheduler */
		uint32_t usr;	  /**< User defined tags. See rte_distributor_process() */
	} hash;                   /**< hash information */

	/** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */
	uint16_t vlan_tci_outer;

	uint16_t buf_len;         /**< Length of segment buffer. */

	/** Valid if PKT_RX_TIMESTAMP is set. The unit and time reference
	 * are not normalized but are always the same for a given port.
	 */
	uint64_t timestamp;

	/* second cache line - fields only used in slow path or on TX */
	MARKER cacheline1 __rte_cache_min_aligned;

	RTE_STD_C11
	union {
		void *userdata;   /**< Can be used for external metadata */
		uint64_t udata64; /**< Allow 8-byte userdata on 32-bit */
	};

	struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */
	struct rte_mbuf *next;    /**< Next segment of scattered packet. */

	/* fields to support TX offloads */
	RTE_STD_C11
	union {
		uint64_t tx_offload;       /**< combined for easy fetch */
		__extension__
		struct {
			uint64_t l2_len:7;
			/**< L2 (MAC) Header Length for non-tunneling pkt.
			 * Outer_L4_len + ... + Inner_L2_len for tunneling pkt.
			 */
			uint64_t l3_len:9; /**< L3 (IP) Header Length. */
			uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */
			uint64_t tso_segsz:16; /**< TCP TSO segment size */

			/* fields for TX offloading of tunnels */
			uint64_t outer_l3_len:9; /**< Outer L3 (IP) Hdr Length. */
			uint64_t outer_l2_len:7; /**< Outer L2 (MAC) Hdr Length. */

			/* uint64_t unused:8; */
		};
	};

	/** Size of the application private data. In case of an indirect
	 * mbuf, it stores the direct mbuf private data size. */
	uint16_t priv_size;

	/** Timesync flags for use with IEEE1588. */
	uint16_t timesync;

	/** Sequence number. See also rte_reorder_insert(). */
	uint32_t seqn;

} __rte_cache_aligned;

/**< Maximum number of nb_segs allowed. */
#define RTE_MBUF_MAX_NB_SEGS	UINT16_MAX

/**
 * Prefetch the first part of the mbuf
 *
 * The first 64 bytes of the mbuf corresponds to fields that are used early
 * in the receive path. If the cache line of the architecture is higher than
 * 64B, the second part will also be prefetched.
 *
 * @param m
 *   The pointer to the mbuf.
 */
static inline void
rte_mbuf_prefetch_part1(struct rte_mbuf *m)
{
	rte_prefetch0(&m->cacheline0);
}

/**
 * Prefetch the second part of the mbuf
 *
 * The next 64 bytes of the mbuf corresponds to fields that are used in the
 * transmit path. If the cache line of the architecture is higher than 64B,
 * this function does nothing as it is expected that the full mbuf is
 * already in cache.
 *
 * @param m
 *   The pointer to the mbuf.
 */
static inline void
rte_mbuf_prefetch_part2(struct rte_mbuf *m)
{
#if RTE_CACHE_LINE_SIZE == 64
	rte_prefetch0(&m->cacheline1);
#else
	RTE_SET_USED(m);
#endif
}


static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp);

/**
 * Return the IO address of the beginning of the mbuf data
 *
 * @param mb
 *   The pointer to the mbuf.
 * @return
 *   The IO address of the beginning of the mbuf data
 */
static inline rte_iova_t
rte_mbuf_data_iova(const struct rte_mbuf *mb)
{
	return mb->buf_iova + mb->data_off;
}

__rte_deprecated
static inline phys_addr_t
rte_mbuf_data_dma_addr(const struct rte_mbuf *mb)
{
	return rte_mbuf_data_iova(mb);
}

/**
 * Return the default IO address of the beginning of the mbuf data
 *
 * This function is used by drivers in their receive function, as it
 * returns the location where data should be written by the NIC, taking
 * the default headroom in account.
 *
 * @param mb
 *   The pointer to the mbuf.
 * @return
 *   The IO address of the beginning of the mbuf data
 */
static inline rte_iova_t
rte_mbuf_data_iova_default(const struct rte_mbuf *mb)
{
	return mb->buf_iova + RTE_PKTMBUF_HEADROOM;
}

__rte_deprecated
static inline phys_addr_t
rte_mbuf_data_dma_addr_default(const struct rte_mbuf *mb)
{
	return rte_mbuf_data_iova_default(mb);
}

/**
 * Return the mbuf owning the data buffer address of an indirect mbuf.
 *
 * @param mi
 *   The pointer to the indirect mbuf.
 * @return
 *   The address of the direct mbuf corresponding to buffer_addr.
 */
static inline struct rte_mbuf *
rte_mbuf_from_indirect(struct rte_mbuf *mi)
{
	return (struct rte_mbuf *)RTE_PTR_SUB(mi->buf_addr, sizeof(*mi) + mi->priv_size);
}

/**
 * Return the buffer address embedded in the given mbuf.
 *
 * @param md
 *   The pointer to the mbuf.
 * @return
 *   The address of the data buffer owned by the mbuf.
 */
static inline char *
rte_mbuf_to_baddr(struct rte_mbuf *md)
{
	char *buffer_addr;
	buffer_addr = (char *)md + sizeof(*md) + rte_pktmbuf_priv_size(md->pool);
	return buffer_addr;
}

/**
 * Returns TRUE if given mbuf is indirect, or FALSE otherwise.
 */
#define RTE_MBUF_INDIRECT(mb)   ((mb)->ol_flags & IND_ATTACHED_MBUF)

/**
 * Returns TRUE if given mbuf is direct, or FALSE otherwise.
 */
#define RTE_MBUF_DIRECT(mb)     (!RTE_MBUF_INDIRECT(mb))

/**
 * Private data in case of pktmbuf pool.
 *
 * A structure that contains some pktmbuf_pool-specific data that are
 * appended after the mempool structure (in private data).
 */
struct rte_pktmbuf_pool_private {
	uint16_t mbuf_data_room_size; /**< Size of data space in each mbuf. */
	uint16_t mbuf_priv_size;      /**< Size of private area in each mbuf. */
};

#ifdef RTE_LIBRTE_MBUF_DEBUG

/**  check mbuf type in debug mode */
#define __rte_mbuf_sanity_check(m, is_h) rte_mbuf_sanity_check(m, is_h)

#else /*  RTE_LIBRTE_MBUF_DEBUG */

/**  check mbuf type in debug mode */
#define __rte_mbuf_sanity_check(m, is_h) do { } while (0)

#endif /*  RTE_LIBRTE_MBUF_DEBUG */

#ifdef RTE_MBUF_REFCNT_ATOMIC

/**
 * Reads the value of an mbuf's refcnt.
 * @param m
 *   Mbuf to read
 * @return
 *   Reference count number.
 */
static inline uint16_t
rte_mbuf_refcnt_read(const struct rte_mbuf *m)
{
	return (uint16_t)(rte_atomic16_read(&m->refcnt_atomic));
}

/**
 * Sets an mbuf's refcnt to a defined value.
 * @param m
 *   Mbuf to update
 * @param new_value
 *   Value set
 */
static inline void
rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value)
{
	rte_atomic16_set(&m->refcnt_atomic, new_value);
}

/* internal */
static inline uint16_t
__rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value)
{
	return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value));
}

/**
 * Adds given value to an mbuf's refcnt and returns its new value.
 * @param m
 *   Mbuf to update
 * @param value
 *   Value to add/subtract
 * @return
 *   Updated value
 */
static inline uint16_t
rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value)
{
	/*
	 * The atomic_add is an expensive operation, so we don't want to
	 * call it in the case where we know we are the uniq holder of
	 * this mbuf (i.e. ref_cnt == 1). Otherwise, an atomic
	 * operation has to be used because concurrent accesses on the
	 * reference counter can occur.
	 */
	if (likely(rte_mbuf_refcnt_read(m) == 1)) {
		rte_mbuf_refcnt_set(m, 1 + value);
		return 1 + value;
	}

	return __rte_mbuf_refcnt_update(m, value);
}

#else /* ! RTE_MBUF_REFCNT_ATOMIC */

/* internal */
static inline uint16_t
__rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value)
{
	m->refcnt = (uint16_t)(m->refcnt + value);
	return m->refcnt;
}

/**
 * Adds given value to an mbuf's refcnt and returns its new value.
 */
static inline uint16_t
rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value)
{
	return __rte_mbuf_refcnt_update(m, value);
}

/**
 * Reads the value of an mbuf's refcnt.
 */
static inline uint16_t
rte_mbuf_refcnt_read(const struct rte_mbuf *m)
{
	return m->refcnt;
}

/**
 * Sets an mbuf's refcnt to the defined value.
 */
static inline void
rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value)
{
	m->refcnt = new_value;
}

#endif /* RTE_MBUF_REFCNT_ATOMIC */

/** Mbuf prefetch */
#define RTE_MBUF_PREFETCH_TO_FREE(m) do {       \
	if ((m) != NULL)                        \
		rte_prefetch0(m);               \
} while (0)


/**
 * Sanity checks on an mbuf.
 *
 * Check the consistency of the given mbuf. The function will cause a
 * panic if corruption is detected.
 *
 * @param m
 *   The mbuf to be checked.
 * @param is_header
 *   True if the mbuf is a packet header, false if it is a sub-segment
 *   of a packet (in this case, some fields like nb_segs are not checked)
 */
void
rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header);

#define MBUF_RAW_ALLOC_CHECK(m) do {				\
	RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1);		\
	RTE_ASSERT((m)->next == NULL);				\
	RTE_ASSERT((m)->nb_segs == 1);				\
	__rte_mbuf_sanity_check(m, 0);				\
} while (0)

/**
 * Allocate an uninitialized mbuf from mempool *mp*.
 *
 * This function can be used by PMDs (especially in RX functions) to
 * allocate an uninitialized mbuf. The driver is responsible of
 * initializing all the required fields. See rte_pktmbuf_reset().
 * For standard needs, prefer rte_pktmbuf_alloc().
 *
 * The caller can expect that the following fields of the mbuf structure
 * are initialized: buf_addr, buf_iova, buf_len, refcnt=1, nb_segs=1,
 * next=NULL, pool, priv_size. The other fields must be initialized
 * by the caller.
 *
 * @param mp
 *   The mempool from which mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
static inline struct rte_mbuf *rte_mbuf_raw_alloc(struct rte_mempool *mp)
{
	struct rte_mbuf *m;
	void *mb = NULL;

	if (rte_mempool_get(mp, &mb) < 0)
		return NULL;
	m = (struct rte_mbuf *)mb;
	MBUF_RAW_ALLOC_CHECK(m);
	return m;
}

/**
 * Put mbuf back into its original mempool.
 *
 * The caller must ensure that the mbuf is direct and properly
 * reinitialized (refcnt=1, next=NULL, nb_segs=1), as done by
 * rte_pktmbuf_prefree_seg().
 *
 * This function should be used with care, when optimization is
 * required. For standard needs, prefer rte_pktmbuf_free() or
 * rte_pktmbuf_free_seg().
 *
 * @param m
 *   The mbuf to be freed.
 */
static __rte_always_inline void
rte_mbuf_raw_free(struct rte_mbuf *m)
{
	RTE_ASSERT(RTE_MBUF_DIRECT(m));
	RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1);
	RTE_ASSERT(m->next == NULL);
	RTE_ASSERT(m->nb_segs == 1);
	__rte_mbuf_sanity_check(m, 0);
	rte_mempool_put(m->pool, m);
}

/* compat with older versions */
__rte_deprecated
static inline void
__rte_mbuf_raw_free(struct rte_mbuf *m)
{
	rte_mbuf_raw_free(m);
}

/* Operations on ctrl mbuf */

/**
 * The control mbuf constructor.
 *
 * This function initializes some fields in an mbuf structure that are
 * not modified by the user once created (mbuf type, origin pool, buffer
 * start address, and so on). This function is given as a callback function
 * to rte_mempool_obj_iter() or rte_mempool_create() at pool creation time.
 *
 * @param mp
 *   The mempool from which the mbuf is allocated.
 * @param opaque_arg
 *   A pointer that can be used by the user to retrieve useful information
 *   for mbuf initialization. This pointer is the opaque argument passed to
 *   rte_mempool_obj_iter() or rte_mempool_create().
 * @param m
 *   The mbuf to initialize.
 * @param i
 *   The index of the mbuf in the pool table.
 */
void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg,
		void *m, unsigned i);

/**
 * Allocate a new mbuf (type is ctrl) from mempool *mp*.
 *
 * This new mbuf is initialized with data pointing to the beginning of
 * buffer, and with a length of zero.
 *
 * @param mp
 *   The mempool from which the mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
#define rte_ctrlmbuf_alloc(mp) rte_pktmbuf_alloc(mp)

/**
 * Free a control mbuf back into its original mempool.
 *
 * @param m
 *   The control mbuf to be freed.
 */
#define rte_ctrlmbuf_free(m) rte_pktmbuf_free(m)

/**
 * A macro that returns the pointer to the carried data.
 *
 * The value that can be read or assigned.
 *
 * @param m
 *   The control mbuf.
 */
#define rte_ctrlmbuf_data(m) ((char *)((m)->buf_addr) + (m)->data_off)

/**
 * A macro that returns the length of the carried data.
 *
 * The value that can be read or assigned.
 *
 * @param m
 *   The control mbuf.
 */
#define rte_ctrlmbuf_len(m) rte_pktmbuf_data_len(m)

/**
 * Tests if an mbuf is a control mbuf
 *
 * @param m
 *   The mbuf to be tested
 * @return
 *   - True (1) if the mbuf is a control mbuf
 *   - False(0) otherwise
 */
static inline int
rte_is_ctrlmbuf(struct rte_mbuf *m)
{
	return !!(m->ol_flags & CTRL_MBUF_FLAG);
}

/* Operations on pkt mbuf */

/**
 * The packet mbuf constructor.
 *
 * This function initializes some fields in the mbuf structure that are
 * not modified by the user once created (origin pool, buffer start
 * address, and so on). This function is given as a callback function to
 * rte_mempool_obj_iter() or rte_mempool_create() at pool creation time.
 *
 * @param mp
 *   The mempool from which mbufs originate.
 * @param opaque_arg
 *   A pointer that can be used by the user to retrieve useful information
 *   for mbuf initialization. This pointer is the opaque argument passed to
 *   rte_mempool_obj_iter() or rte_mempool_create().
 * @param m
 *   The mbuf to initialize.
 * @param i
 *   The index of the mbuf in the pool table.
 */
void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg,
		      void *m, unsigned i);


/**
 * A  packet mbuf pool constructor.
 *
 * This function initializes the mempool private data in the case of a
 * pktmbuf pool. This private data is needed by the driver. The
 * function must be called on the mempool before it is used, or it
 * can be given as a callback function to rte_mempool_create() at
 * pool creation. It can be extended by the user, for example, to
 * provide another packet size.
 *
 * @param mp
 *   The mempool from which mbufs originate.
 * @param opaque_arg
 *   A pointer that can be used by the user to retrieve useful information
 *   for mbuf initialization. This pointer is the opaque argument passed to
 *   rte_mempool_create().
 */
void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg);

/**
 * Create a mbuf pool.
 *
 * This function creates and initializes a packet mbuf pool. It is
 * a wrapper to rte_mempool functions.
 *
 * @param name
 *   The name of the mbuf pool.
 * @param n
 *   The number of elements in the mbuf pool. The optimum size (in terms
 *   of memory usage) for a mempool is when n is a power of two minus one:
 *   n = (2^q - 1).
 * @param cache_size
 *   Size of the per-core object cache. See rte_mempool_create() for
 *   details.
 * @param priv_size
 *   Size of application private are between the rte_mbuf structure
 *   and the data buffer. This value must be aligned to RTE_MBUF_PRIV_ALIGN.
 * @param data_room_size
 *   Size of data buffer in each mbuf, including RTE_PKTMBUF_HEADROOM.
 * @param socket_id
 *   The socket identifier where the memory should be allocated. The
 *   value can be *SOCKET_ID_ANY* if there is no NUMA constraint for the
 *   reserved zone.
 * @return
 *   The pointer to the new allocated mempool, on success. NULL on error
 *   with rte_errno set appropriately. Possible rte_errno values include:
 *    - E_RTE_NO_CONFIG - function could not get pointer to rte_config structure
 *    - E_RTE_SECONDARY - function was called from a secondary process instance
 *    - EINVAL - cache size provided is too large, or priv_size is not aligned.
 *    - ENOSPC - the maximum number of memzones has already been allocated
 *    - EEXIST - a memzone with the same name already exists
 *    - ENOMEM - no appropriate memory area found in which to create memzone
 */
struct rte_mempool *
rte_pktmbuf_pool_create(const char *name, unsigned n,
	unsigned cache_size, uint16_t priv_size, uint16_t data_room_size,
	int socket_id);

/**
 * Get the data room size of mbufs stored in a pktmbuf_pool
 *
 * The data room size is the amount of data that can be stored in a
 * mbuf including the headroom (RTE_PKTMBUF_HEADROOM).
 *
 * @param mp
 *   The packet mbuf pool.
 * @return
 *   The data room size of mbufs stored in this mempool.
 */
static inline uint16_t
rte_pktmbuf_data_room_size(struct rte_mempool *mp)
{
	struct rte_pktmbuf_pool_private *mbp_priv;

	mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp);
	return mbp_priv->mbuf_data_room_size;
}

/**
 * Get the application private size of mbufs stored in a pktmbuf_pool
 *
 * The private size of mbuf is a zone located between the rte_mbuf
 * structure and the data buffer where an application can store data
 * associated to a packet.
 *
 * @param mp
 *   The packet mbuf pool.
 * @return
 *   The private size of mbufs stored in this mempool.
 */
static inline uint16_t
rte_pktmbuf_priv_size(struct rte_mempool *mp)
{
	struct rte_pktmbuf_pool_private *mbp_priv;

	mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp);
	return mbp_priv->mbuf_priv_size;
}

/**
 * Reset the data_off field of a packet mbuf to its default value.
 *
 * The given mbuf must have only one segment, which should be empty.
 *
 * @param m
 *   The packet mbuf's data_off field has to be reset.
 */
static inline void rte_pktmbuf_reset_headroom(struct rte_mbuf *m)
{
	m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, (uint16_t)m->buf_len);
}

/**
 * Reset the fields of a packet mbuf to their default values.
 *
 * The given mbuf must have only one segment.
 *
 * @param m
 *   The packet mbuf to be resetted.
 */
#define MBUF_INVALID_PORT UINT16_MAX

static inline void rte_pktmbuf_reset(struct rte_mbuf *m)
{
	m->next = NULL;
	m->pkt_len = 0;
	m->tx_offload = 0;
	m->vlan_tci = 0;
	m->vlan_tci_outer = 0;
	m->nb_segs = 1;
	m->port = MBUF_INVALID_PORT;

	m->ol_flags = 0;
	m->packet_type = 0;
	rte_pktmbuf_reset_headroom(m);

	m->data_len = 0;
	__rte_mbuf_sanity_check(m, 1);
}

/**
 * Allocate a new mbuf from a mempool.
 *
 * This new mbuf contains one segment, which has a length of 0. The pointer
 * to data is initialized to have some bytes of headroom in the buffer
 * (if buffer size allows).
 *
 * @param mp
 *   The mempool from which the mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp)
{
	struct rte_mbuf *m;
	if ((m = rte_mbuf_raw_alloc(mp)) != NULL)
		rte_pktmbuf_reset(m);
	return m;
}

/**
 * Allocate a bulk of mbufs, initialize refcnt and reset the fields to default
 * values.
 *
 *  @param pool
 *    The mempool from which mbufs are allocated.
 *  @param mbufs
 *    Array of pointers to mbufs
 *  @param count
 *    Array size
 *  @return
 *   - 0: Success
 *   - -ENOENT: Not enough entries in the mempool; no mbufs are retrieved.
 */
static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool,
	 struct rte_mbuf **mbufs, unsigned count)
{
	unsigned idx = 0;
	int rc;

	rc = rte_mempool_get_bulk(pool, (void **)mbufs, count);
	if (unlikely(rc))
		return rc;

	/* To understand duff's device on loop unwinding optimization, see
	 * https://en.wikipedia.org/wiki/Duff's_device.
	 * Here while() loop is used rather than do() while{} to avoid extra
	 * check if count is zero.
	 */
	switch (count % 4) {
	case 0:
		while (idx != count) {
			MBUF_RAW_ALLOC_CHECK(mbufs[idx]);
			rte_pktmbuf_reset(mbufs[idx]);
			idx++;
			/* fall-through */
	case 3:
			MBUF_RAW_ALLOC_CHECK(mbufs[idx]);
			rte_pktmbuf_reset(mbufs[idx]);
			idx++;
			/* fall-through */
	case 2:
			MBUF_RAW_ALLOC_CHECK(mbufs[idx]);
			rte_pktmbuf_reset(mbufs[idx]);
			idx++;
			/* fall-through */
	case 1:
			MBUF_RAW_ALLOC_CHECK(mbufs[idx]);
			rte_pktmbuf_reset(mbufs[idx]);
			idx++;
			/* fall-through */
		}
	}
	return 0;
}

/**
 * Attach packet mbuf to another packet mbuf.
 *
 * After attachment we refer the mbuf we attached as 'indirect',
 * while mbuf we attached to as 'direct'.
 * The direct mbuf's reference counter is incremented.
 *
 * Right now, not supported:
 *  - attachment for already indirect mbuf (e.g. - mi has to be direct).
 *  - mbuf we trying to attach (mi) is used by someone else
 *    e.g. it's reference counter is greater then 1.
 *
 * @param mi
 *   The indirect packet mbuf.
 * @param m
 *   The packet mbuf we're attaching to.
 */
static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m)
{
	struct rte_mbuf *md;

	RTE_ASSERT(RTE_MBUF_DIRECT(mi) &&
	    rte_mbuf_refcnt_read(mi) == 1);

	/* if m is not direct, get the mbuf that embeds the data */
	if (RTE_MBUF_DIRECT(m))
		md = m;
	else
		md = rte_mbuf_from_indirect(m);

	rte_mbuf_refcnt_update(md, 1);
	mi->priv_size = m->priv_size;
	mi->buf_iova = m->buf_iova;
	mi->buf_addr = m->buf_addr;
	mi->buf_len = m->buf_len;

	mi->data_off = m->data_off;
	mi->data_len = m->data_len;
	mi->port = m->port;
	mi->vlan_tci = m->vlan_tci;
	mi->vlan_tci_outer = m->vlan_tci_outer;
	mi->tx_offload = m->tx_offload;
	mi->hash = m->hash;

	mi->next = NULL;
	mi->pkt_len = mi->data_len;
	mi->nb_segs = 1;
	mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF;
	mi->packet_type = m->packet_type;
	mi->timestamp = m->timestamp;

	__rte_mbuf_sanity_check(mi, 1);
	__rte_mbuf_sanity_check(m, 0);
}

/**
 * Detach an indirect packet mbuf.
 *
 *  - restore original mbuf address and length values.
 *  - reset pktmbuf data and data_len to their default values.
 *  - decrement the direct mbuf's reference counter. When the
 *  reference counter becomes 0, the direct mbuf is freed.
 *
 * All other fields of the given packet mbuf will be left intact.
 *
 * @param m
 *   The indirect attached packet mbuf.
 */
static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
{
	struct rte_mbuf *md = rte_mbuf_from_indirect(m);
	struct rte_mempool *mp = m->pool;
	uint32_t mbuf_size, buf_len, priv_size;

	priv_size = rte_pktmbuf_priv_size(mp);
	mbuf_size = sizeof(struct rte_mbuf) + priv_size;
	buf_len = rte_pktmbuf_data_room_size(mp);

	m->priv_size = priv_size;
	m->buf_addr = (char *)m + mbuf_size;
	m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size;
	m->buf_len = (uint16_t)buf_len;
	rte_pktmbuf_reset_headroom(m);
	m->data_len = 0;
	m->ol_flags = 0;

	if (rte_mbuf_refcnt_update(md, -1) == 0) {
		md->next = NULL;
		md->nb_segs = 1;
		rte_mbuf_refcnt_set(md, 1);
		rte_mbuf_raw_free(md);
	}
}

/**
 * Decrease reference counter and unlink a mbuf segment
 *
 * This function does the same than a free, except that it does not
 * return the segment to its pool.
 * It decreases the reference counter, and if it reaches 0, it is
 * detached from its parent for an indirect mbuf.
 *
 * @param m
 *   The mbuf to be unlinked
 * @return
 *   - (m) if it is the last reference. It can be recycled or freed.
 *   - (NULL) if the mbuf still has remaining references on it.
 */
static __rte_always_inline struct rte_mbuf *
rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
{
	__rte_mbuf_sanity_check(m, 0);

	if (likely(rte_mbuf_refcnt_read(m) == 1)) {

		if (RTE_MBUF_INDIRECT(m))
			rte_pktmbuf_detach(m);

		if (m->next != NULL) {
			m->next = NULL;
			m->nb_segs = 1;
		}

		return m;

	} else if (__rte_mbuf_refcnt_update(m, -1) == 0) {

		if (RTE_MBUF_INDIRECT(m))
			rte_pktmbuf_detach(m);

		if (m->next != NULL) {
			m->next = NULL;
			m->nb_segs = 1;
		}
		rte_mbuf_refcnt_set(m, 1);

		return m;
	}
	return NULL;
}

/* deprecated, replaced by rte_pktmbuf_prefree_seg() */
__rte_deprecated
static inline struct rte_mbuf *
__rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
{
	return rte_pktmbuf_prefree_seg(m);
}

/**
 * Free a segment of a packet mbuf into its original mempool.
 *
 * Free an mbuf, without parsing other segments in case of chained
 * buffers.
 *
 * @param m
 *   The packet mbuf segment to be freed.
 */
static __rte_always_inline void
rte_pktmbuf_free_seg(struct rte_mbuf *m)
{
	m = rte_pktmbuf_prefree_seg(m);
	if (likely(m != NULL))
		rte_mbuf_raw_free(m);
}

/**
 * Free a packet mbuf back into its original mempool.
 *
 * Free an mbuf, and all its segments in case of chained buffers. Each
 * segment is added back into its original mempool.
 *
 * @param m
 *   The packet mbuf to be freed. If NULL, the function does nothing.
 */
static inline void rte_pktmbuf_free(struct rte_mbuf *m)
{
	struct rte_mbuf *m_next;

	if (m != NULL)
		__rte_mbuf_sanity_check(m, 1);

	while (m != NULL) {
		m_next = m->next;
		rte_pktmbuf_free_seg(m);
		m = m_next;
	}
}

/**
 * Creates a "clone" of the given packet mbuf.
 *
 * Walks through all segments of the given packet mbuf, and for each of them:
 *  - Creates a new packet mbuf from the given pool.
 *  - Attaches newly created mbuf to the segment.
 * Then updates pkt_len and nb_segs of the "clone" packet mbuf to match values
 * from the original packet mbuf.
 *
 * @param md
 *   The packet mbuf to be cloned.
 * @param mp
 *   The mempool from which the "clone" mbufs are allocated.
 * @return
 *   - The pointer to the new "clone" mbuf on success.
 *   - NULL if allocation fails.
 */
static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md,
		struct rte_mempool *mp)
{
	struct rte_mbuf *mc, *mi, **prev;
	uint32_t pktlen;
	uint16_t nseg;

	if (unlikely ((mc = rte_pktmbuf_alloc(mp)) == NULL))
		return NULL;

	mi = mc;
	prev = &mi->next;
	pktlen = md->pkt_len;
	nseg = 0;

	do {
		nseg++;
		rte_pktmbuf_attach(mi, md);
		*prev = mi;
		prev = &mi->next;
	} while ((md = md->next) != NULL &&
	    (mi = rte_pktmbuf_alloc(mp)) != NULL);

	*prev = NULL;
	mc->nb_segs = nseg;
	mc->pkt_len = pktlen;

	/* Allocation of new indirect segment failed */
	if (unlikely (mi == NULL)) {
		rte_pktmbuf_free(mc);
		return NULL;
	}

	__rte_mbuf_sanity_check(mc, 1);
	return mc;
}

/**
 * Adds given value to the refcnt of all packet mbuf segments.
 *
 * Walks through all segments of given packet mbuf and for each of them
 * invokes rte_mbuf_refcnt_update().
 *
 * @param m
 *   The packet mbuf whose refcnt to be updated.
 * @param v
 *   The value to add to the mbuf's segments refcnt.
 */
static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v)
{
	__rte_mbuf_sanity_check(m, 1);

	do {
		rte_mbuf_refcnt_update(m, v);
	} while ((m = m->next) != NULL);
}

/**
 * Get the headroom in a packet mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The length of the headroom.
 */
static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m)
{
	__rte_mbuf_sanity_check(m, 0);
	return m->data_off;
}

/**
 * Get the tailroom of a packet mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The length of the tailroom.
 */
static inline uint16_t rte_pktmbuf_tailroom(const struct rte_mbuf *m)
{
	__rte_mbuf_sanity_check(m, 0);
	return (uint16_t)(m->buf_len - rte_pktmbuf_headroom(m) -
			  m->data_len);
}

/**
 * Get the last segment of the packet.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The last segment of the given mbuf.
 */
static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m)
{
	struct rte_mbuf *m2 = (struct rte_mbuf *)m;

	__rte_mbuf_sanity_check(m, 1);
	while (m2->next != NULL)
		m2 = m2->next;
	return m2;
}

/**
 * A macro that points to an offset into the data in the mbuf.
 *
 * The returned pointer is cast to type t. Before using this
 * function, the user must ensure that the first segment is large
 * enough to accommodate its data.
 *
 * @param m
 *   The packet mbuf.
 * @param o
 *   The offset into the mbuf data.
 * @param t
 *   The type to cast the result into.
 */
#define rte_pktmbuf_mtod_offset(m, t, o)	\
	((t)((char *)(m)->buf_addr + (m)->data_off + (o)))

/**
 * A macro that points to the start of the data in the mbuf.
 *
 * The returned pointer is cast to type t. Before using this
 * function, the user must ensure that the first segment is large
 * enough to accommodate its data.
 *
 * @param m
 *   The packet mbuf.
 * @param t
 *   The type to cast the result into.
 */
#define rte_pktmbuf_mtod(m, t) rte_pktmbuf_mtod_offset(m, t, 0)

/**
 * A macro that returns the IO address that points to an offset of the
 * start of the data in the mbuf
 *
 * @param m
 *   The packet mbuf.
 * @param o
 *   The offset into the data to calculate address from.
 */
#define rte_pktmbuf_iova_offset(m, o) \
	(rte_iova_t)((m)->buf_iova + (m)->data_off + (o))

/* deprecated */
#define rte_pktmbuf_mtophys_offset(m, o) \
	rte_pktmbuf_iova_offset(m, o)

/**
 * A macro that returns the IO address that points to the start of the
 * data in the mbuf
 *
 * @param m
 *   The packet mbuf.
 */
#define rte_pktmbuf_iova(m) rte_pktmbuf_iova_offset(m, 0)

/* deprecated */
#define rte_pktmbuf_mtophys(m) rte_pktmbuf_iova(m)

/**
 * A macro that returns the length of the packet.
 *
 * The value can be read or assigned.
 *
 * @param m
 *   The packet mbuf.
 */
#define rte_pktmbuf_pkt_len(m) ((m)->pkt_len)

/**
 * A macro that returns the length of the segment.
 *
 * The value can be read or assigned.
 *
 * @param m
 *   The packet mbuf.
 */
#define rte_pktmbuf_data_len(m) ((m)->data_len)

/**
 * Prepend len bytes to an mbuf data area.
 *
 * Returns a pointer to the new
 * data start address. If there is not enough headroom in the first
 * segment, the function will return NULL, without modifying the mbuf.
 *
 * @param m
 *   The pkt mbuf.
 * @param len
 *   The amount of data to prepend (in bytes).
 * @return
 *   A pointer to the start of the newly prepended data, or
 *   NULL if there is not enough headroom space in the first segment
 */
static inline char *rte_pktmbuf_prepend(struct rte_mbuf *m,
					uint16_t len)
{
	__rte_mbuf_sanity_check(m, 1);

	if (unlikely(len > rte_pktmbuf_headroom(m)))
		return NULL;

	m->data_off -= len;
	m->data_len = (uint16_t)(m->data_len + len);
	m->pkt_len  = (m->pkt_len + len);

	return (char *)m->buf_addr + m->data_off;
}

/**
 * Append len bytes to an mbuf.
 *
 * Append len bytes to an mbuf and return a pointer to the start address
 * of the added data. If there is not enough tailroom in the last
 * segment, the function will return NULL, without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to append (in bytes).
 * @return
 *   A pointer to the start of the newly appended data, or
 *   NULL if there is not enough tailroom space in the last segment
 */
static inline char *rte_pktmbuf_append(struct rte_mbuf *m, uint16_t len)
{
	void *tail;
	struct rte_mbuf *m_last;

	__rte_mbuf_sanity_check(m, 1);

	m_last = rte_pktmbuf_lastseg(m);
	if (unlikely(len > rte_pktmbuf_tailroom(m_last)))
		return NULL;

	tail = (char *)m_last->buf_addr + m_last->data_off + m_last->data_len;
	m_last->data_len = (uint16_t)(m_last->data_len + len);
	m->pkt_len  = (m->pkt_len + len);
	return (char*) tail;
}

/**
 * Remove len bytes at the beginning of an mbuf.
 *
 * Returns a pointer to the start address of the new data area. If the
 * length is greater than the length of the first segment, then the
 * function will fail and return NULL, without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to remove (in bytes).
 * @return
 *   A pointer to the new start of the data.
 */
static inline char *rte_pktmbuf_adj(struct rte_mbuf *m, uint16_t len)
{
	__rte_mbuf_sanity_check(m, 1);

	if (unlikely(len > m->data_len))
		return NULL;

	m->data_len = (uint16_t)(m->data_len - len);
	m->data_off += len;
	m->pkt_len  = (m->pkt_len - len);
	return (char *)m->buf_addr + m->data_off;
}

/**
 * Remove len bytes of data at the end of the mbuf.
 *
 * If the length is greater than the length of the last segment, the
 * function will fail and return -1 without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to remove (in bytes).
 * @return
 *   - 0: On success.
 *   - -1: On error.
 */
static inline int rte_pktmbuf_trim(struct rte_mbuf *m, uint16_t len)
{
	struct rte_mbuf *m_last;

	__rte_mbuf_sanity_check(m, 1);

	m_last = rte_pktmbuf_lastseg(m);
	if (unlikely(len > m_last->data_len))
		return -1;

	m_last->data_len = (uint16_t)(m_last->data_len - len);
	m->pkt_len  = (m->pkt_len - len);
	return 0;
}

/**
 * Test if mbuf data is contiguous.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   - 1, if all data is contiguous (one segment).
 *   - 0, if there is several segments.
 */
static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m)
{
	__rte_mbuf_sanity_check(m, 1);
	return !!(m->nb_segs == 1);
}

/**
 * @internal used by rte_pktmbuf_read().
 */
const void *__rte_pktmbuf_read(const struct rte_mbuf *m, uint32_t off,
	uint32_t len, void *buf);

/**
 * Read len data bytes in a mbuf at specified offset.
 *
 * If the data is contiguous, return the pointer in the mbuf data, else
 * copy the data in the buffer provided by the user and return its
 * pointer.
 *
 * @param m
 *   The pointer to the mbuf.
 * @param off
 *   The offset of the data in the mbuf.
 * @param len
 *   The amount of bytes to read.
 * @param buf
 *   The buffer where data is copied if it is not contiguous in mbuf
 *   data. Its length should be at least equal to the len parameter.
 * @return
 *   The pointer to the data, either in the mbuf if it is contiguous,
 *   or in the user buffer. If mbuf is too small, NULL is returned.
 */
static inline const void *rte_pktmbuf_read(const struct rte_mbuf *m,
	uint32_t off, uint32_t len, void *buf)
{
	if (likely(off + len <= rte_pktmbuf_data_len(m)))
		return rte_pktmbuf_mtod_offset(m, char *, off);
	else
		return __rte_pktmbuf_read(m, off, len, buf);
}

/**
 * Chain an mbuf to another, thereby creating a segmented packet.
 *
 * Note: The implementation will do a linear walk over the segments to find
 * the tail entry. For cases when there are many segments, it's better to
 * chain the entries manually.
 *
 * @param head
 *   The head of the mbuf chain (the first packet)
 * @param tail
 *   The mbuf to put last in the chain
 *
 * @return
 *   - 0, on success.
 *   - -EOVERFLOW, if the chain segment limit exceeded
 */
static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail)
{
	struct rte_mbuf *cur_tail;

	/* Check for number-of-segments-overflow */
	if (head->nb_segs + tail->nb_segs > RTE_MBUF_MAX_NB_SEGS)
		return -EOVERFLOW;

	/* Chain 'tail' onto the old tail */
	cur_tail = rte_pktmbuf_lastseg(head);
	cur_tail->next = tail;

	/* accumulate number of segments and total length. */
	head->nb_segs += tail->nb_segs;
	head->pkt_len += tail->pkt_len;

	/* pkt_len is only set in the head */
	tail->pkt_len = tail->data_len;

	return 0;
}

/**
 * Validate general requirements for Tx offload in mbuf.
 *
 * This function checks correctness and completeness of Tx offload settings.
 *
 * @param m
 *   The packet mbuf to be validated.
 * @return
 *   0 if packet is valid
 */
static inline int
rte_validate_tx_offload(const struct rte_mbuf *m)
{
	uint64_t ol_flags = m->ol_flags;
	uint64_t inner_l3_offset = m->l2_len;

	/* Does packet set any of available offloads? */
	if (!(ol_flags & PKT_TX_OFFLOAD_MASK))
		return 0;

	if (ol_flags & PKT_TX_OUTER_IP_CKSUM)
		inner_l3_offset += m->outer_l2_len + m->outer_l3_len;

	/* Headers are fragmented */
	if (rte_pktmbuf_data_len(m) < inner_l3_offset + m->l3_len + m->l4_len)
		return -ENOTSUP;

	/* IP checksum can be counted only for IPv4 packet */
	if ((ol_flags & PKT_TX_IP_CKSUM) && (ol_flags & PKT_TX_IPV6))
		return -EINVAL;

	/* IP type not set when required */
	if (ol_flags & (PKT_TX_L4_MASK | PKT_TX_TCP_SEG))
		if (!(ol_flags & (PKT_TX_IPV4 | PKT_TX_IPV6)))
			return -EINVAL;

	/* Check requirements for TSO packet */
	if (ol_flags & PKT_TX_TCP_SEG)
		if ((m->tso_segsz == 0) ||
				((ol_flags & PKT_TX_IPV4) &&
				!(ol_flags & PKT_TX_IP_CKSUM)))
			return -EINVAL;

	/* PKT_TX_OUTER_IP_CKSUM set for non outer IPv4 packet. */
	if ((ol_flags & PKT_TX_OUTER_IP_CKSUM) &&
			!(ol_flags & PKT_TX_OUTER_IPV4))
		return -EINVAL;

	return 0;
}

/**
 * Linearize data in mbuf.
 *
 * This function moves the mbuf data in the first segment if there is enough
 * tailroom. The subsequent segments are unchained and freed.
 *
 * @param mbuf
 *   mbuf to linearize
 * @return
 *   - 0, on success
 *   - -1, on error
 */
static inline int
rte_pktmbuf_linearize(struct rte_mbuf *mbuf)
{
	int seg_len, copy_len;
	struct rte_mbuf *m;
	struct rte_mbuf *m_next;
	char *buffer;

	if (rte_pktmbuf_is_contiguous(mbuf))
		return 0;

	/* Extend first segment to the total packet length */
	copy_len = rte_pktmbuf_pkt_len(mbuf) - rte_pktmbuf_data_len(mbuf);

	if (unlikely(copy_len > rte_pktmbuf_tailroom(mbuf)))
		return -1;

	buffer = rte_pktmbuf_mtod_offset(mbuf, char *, mbuf->data_len);
	mbuf->data_len = (uint16_t)(mbuf->pkt_len);

	/* Append data from next segments to the first one */
	m = mbuf->next;
	while (m != NULL) {
		m_next = m->next;

		seg_len = rte_pktmbuf_data_len(m);
		rte_memcpy(buffer, rte_pktmbuf_mtod(m, char *), seg_len);
		buffer += seg_len;

		rte_pktmbuf_free_seg(m);
		m = m_next;
	}

	mbuf->next = NULL;
	mbuf->nb_segs = 1;

	return 0;
}

/**
 * Dump an mbuf structure to a file.
 *
 * Dump all fields for the given packet mbuf and all its associated
 * segments (in the case of a chained buffer).
 *
 * @param f
 *   A pointer to a file for output
 * @param m
 *   The packet mbuf.
 * @param dump_len
 *   If dump_len != 0, also dump the "dump_len" first data bytes of
 *   the packet.
 */
void rte_pktmbuf_dump(FILE *f, const struct rte_mbuf *m, unsigned dump_len);

#ifdef __cplusplus
}
#endif

#endif /* _RTE_MBUF_H_ */