summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/netronome/nfp/flower/conntrack.c
blob: 497766ecdd91da13961e5cd399e619df9f03f9b9 (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
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
/* Copyright (C) 2021 Corigine, Inc. */

#include <net/tc_act/tc_csum.h>
#include <net/tc_act/tc_ct.h>

#include "conntrack.h"
#include "../nfp_port.h"

const struct rhashtable_params nfp_tc_ct_merge_params = {
	.head_offset		= offsetof(struct nfp_fl_ct_tc_merge,
					   hash_node),
	.key_len		= sizeof(unsigned long) * 2,
	.key_offset		= offsetof(struct nfp_fl_ct_tc_merge, cookie),
	.automatic_shrinking	= true,
};

const struct rhashtable_params nfp_nft_ct_merge_params = {
	.head_offset		= offsetof(struct nfp_fl_nft_tc_merge,
					   hash_node),
	.key_len		= sizeof(unsigned long) * 3,
	.key_offset		= offsetof(struct nfp_fl_nft_tc_merge, cookie),
	.automatic_shrinking	= true,
};

static struct flow_action_entry *get_flow_act(struct flow_rule *rule,
					      enum flow_action_id act_id);

/**
 * get_hashentry() - Wrapper around hashtable lookup.
 * @ht:		hashtable where entry could be found
 * @key:	key to lookup
 * @params:	hashtable params
 * @size:	size of entry to allocate if not in table
 *
 * Returns an entry from a hashtable. If entry does not exist
 * yet allocate the memory for it and return the new entry.
 */
static void *get_hashentry(struct rhashtable *ht, void *key,
			   const struct rhashtable_params params, size_t size)
{
	void *result;

	result = rhashtable_lookup_fast(ht, key, params);

	if (result)
		return result;

	result = kzalloc(size, GFP_KERNEL);
	if (!result)
		return ERR_PTR(-ENOMEM);

	return result;
}

bool is_pre_ct_flow(struct flow_cls_offload *flow)
{
	struct flow_action_entry *act;
	int i;

	flow_action_for_each(i, act, &flow->rule->action) {
		if (act->id == FLOW_ACTION_CT) {
			/* The pre_ct rule only have the ct or ct nat action, cannot
			 * contains other ct action e.g ct commit and so on.
			 */
			if ((!act->ct.action || act->ct.action == TCA_CT_ACT_NAT))
				return true;
			else
				return false;
		}
	}

	return false;
}

bool is_post_ct_flow(struct flow_cls_offload *flow)
{
	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
	struct flow_dissector *dissector = rule->match.dissector;
	struct flow_action_entry *act;
	bool exist_ct_clear = false;
	struct flow_match_ct ct;
	int i;

	/* post ct entry cannot contains any ct action except ct_clear. */
	flow_action_for_each(i, act, &flow->rule->action) {
		if (act->id == FLOW_ACTION_CT) {
			/* ignore ct clear action. */
			if (act->ct.action == TCA_CT_ACT_CLEAR) {
				exist_ct_clear = true;
				continue;
			}

			return false;
		}
	}

	if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) {
		flow_rule_match_ct(rule, &ct);
		if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED)
			return true;
	} else {
		/* when do nat with ct, the post ct entry ignore the ct status,
		 * will match the nat field(sip/dip) instead. In this situation,
		 * the flow chain index is not zero and contains ct clear action.
		 */
		if (flow->common.chain_index && exist_ct_clear)
			return true;
	}

	return false;
}

/**
 * get_mangled_key() - Mangle the key if mangle act exists
 * @rule:	rule that carries the actions
 * @buf:	pointer to key to be mangled
 * @offset:	used to adjust mangled offset in L2/L3/L4 header
 * @key_sz:	key size
 * @htype:	mangling type
 *
 * Returns buf where the mangled key stores.
 */
static void *get_mangled_key(struct flow_rule *rule, void *buf,
			     u32 offset, size_t key_sz,
			     enum flow_action_mangle_base htype)
{
	struct flow_action_entry *act;
	u32 *val = (u32 *)buf;
	u32 off, msk, key;
	int i;

	flow_action_for_each(i, act, &rule->action) {
		if (act->id == FLOW_ACTION_MANGLE &&
		    act->mangle.htype == htype) {
			off = act->mangle.offset - offset;
			msk = act->mangle.mask;
			key = act->mangle.val;

			/* Mangling is supposed to be u32 aligned */
			if (off % 4 || off >= key_sz)
				continue;

			val[off >> 2] &= msk;
			val[off >> 2] |= key;
		}
	}

	return buf;
}

/* Only tos and ttl are involved in flow_match_ip structure, which
 * doesn't conform to the layout of ip/ipv6 header definition. So
 * they need particular process here: fill them into the ip/ipv6
 * header, so that mangling actions can work directly.
 */
#define NFP_IPV4_TOS_MASK	GENMASK(23, 16)
#define NFP_IPV4_TTL_MASK	GENMASK(31, 24)
#define NFP_IPV6_TCLASS_MASK	GENMASK(27, 20)
#define NFP_IPV6_HLIMIT_MASK	GENMASK(7, 0)
static void *get_mangled_tos_ttl(struct flow_rule *rule, void *buf,
				 bool is_v6)
{
	struct flow_match_ip match;
	/* IPv4's ttl field is in third dword. */
	__be32 ip_hdr[3];
	u32 tmp, hdr_len;

	flow_rule_match_ip(rule, &match);

	if (is_v6) {
		tmp = FIELD_PREP(NFP_IPV6_TCLASS_MASK, match.key->tos);
		ip_hdr[0] = cpu_to_be32(tmp);
		tmp = FIELD_PREP(NFP_IPV6_HLIMIT_MASK, match.key->ttl);
		ip_hdr[1] = cpu_to_be32(tmp);
		hdr_len = 2 * sizeof(__be32);
	} else {
		tmp = FIELD_PREP(NFP_IPV4_TOS_MASK, match.key->tos);
		ip_hdr[0] = cpu_to_be32(tmp);
		tmp = FIELD_PREP(NFP_IPV4_TTL_MASK, match.key->ttl);
		ip_hdr[2] = cpu_to_be32(tmp);
		hdr_len = 3 * sizeof(__be32);
	}

	get_mangled_key(rule, ip_hdr, 0, hdr_len,
			is_v6 ? FLOW_ACT_MANGLE_HDR_TYPE_IP6 :
				FLOW_ACT_MANGLE_HDR_TYPE_IP4);

	match.key = buf;

	if (is_v6) {
		tmp = be32_to_cpu(ip_hdr[0]);
		match.key->tos = FIELD_GET(NFP_IPV6_TCLASS_MASK, tmp);
		tmp = be32_to_cpu(ip_hdr[1]);
		match.key->ttl = FIELD_GET(NFP_IPV6_HLIMIT_MASK, tmp);
	} else {
		tmp = be32_to_cpu(ip_hdr[0]);
		match.key->tos = FIELD_GET(NFP_IPV4_TOS_MASK, tmp);
		tmp = be32_to_cpu(ip_hdr[2]);
		match.key->ttl = FIELD_GET(NFP_IPV4_TTL_MASK, tmp);
	}

	return buf;
}

/* Note entry1 and entry2 are not swappable. only skip ip and
 * tport merge check for pre_ct and post_ct when pre_ct do nat.
 */
static bool nfp_ct_merge_check_cannot_skip(struct nfp_fl_ct_flow_entry *entry1,
					   struct nfp_fl_ct_flow_entry *entry2)
{
	/* only pre_ct have NFP_FL_ACTION_DO_NAT flag. */
	if ((entry1->flags & NFP_FL_ACTION_DO_NAT) &&
	    entry2->type == CT_TYPE_POST_CT)
		return false;

	return true;
}

/* Note entry1 and entry2 are not swappable, entry1 should be
 * the former flow whose mangle action need be taken into account
 * if existed, and entry2 should be the latter flow whose action
 * we don't care.
 */
static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1,
			      struct nfp_fl_ct_flow_entry *entry2)
{
	unsigned int ovlp_keys = entry1->rule->match.dissector->used_keys &
				 entry2->rule->match.dissector->used_keys;
	bool out, is_v6 = false;
	u8 ip_proto = 0;
	/* Temporary buffer for mangling keys, 64 is enough to cover max
	 * struct size of key in various fields that may be mangled.
	 * Supported fields to mangle:
	 * mac_src/mac_dst(struct flow_match_eth_addrs, 12B)
	 * nw_tos/nw_ttl(struct flow_match_ip, 2B)
	 * nw_src/nw_dst(struct flow_match_ipv4/6_addrs, 32B)
	 * tp_src/tp_dst(struct flow_match_ports, 4B)
	 */
	char buf[64];

	if (entry1->netdev && entry2->netdev &&
	    entry1->netdev != entry2->netdev)
		return -EINVAL;

	/* Check the overlapped fields one by one, the unmasked part
	 * should not conflict with each other.
	 */
	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) {
		struct flow_match_control match1, match2;

		flow_rule_match_control(entry1->rule, &match1);
		flow_rule_match_control(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) {
		struct flow_match_basic match1, match2;

		flow_rule_match_basic(entry1->rule, &match1);
		flow_rule_match_basic(entry2->rule, &match2);

		/* n_proto field is a must in ct-related flows,
		 * it should be either ipv4 or ipv6.
		 */
		is_v6 = match1.key->n_proto == htons(ETH_P_IPV6);
		/* ip_proto field is a must when port field is cared */
		ip_proto = match1.key->ip_proto;

		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	/* if pre ct entry do nat, the nat ip exists in nft entry,
	 * will be do merge check when do nft and post ct merge,
	 * so skip this ip merge check here.
	 */
	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) &&
	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
		struct flow_match_ipv4_addrs match1, match2;

		flow_rule_match_ipv4_addrs(entry1->rule, &match1);
		flow_rule_match_ipv4_addrs(entry2->rule, &match2);

		memcpy(buf, match1.key, sizeof(*match1.key));
		match1.key = get_mangled_key(entry1->rule, buf,
					     offsetof(struct iphdr, saddr),
					     sizeof(*match1.key),
					     FLOW_ACT_MANGLE_HDR_TYPE_IP4);

		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	/* if pre ct entry do nat, the nat ip exists in nft entry,
	 * will be do merge check when do nft and post ct merge,
	 * so skip this ip merge check here.
	 */
	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) &&
	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
		struct flow_match_ipv6_addrs match1, match2;

		flow_rule_match_ipv6_addrs(entry1->rule, &match1);
		flow_rule_match_ipv6_addrs(entry2->rule, &match2);

		memcpy(buf, match1.key, sizeof(*match1.key));
		match1.key = get_mangled_key(entry1->rule, buf,
					     offsetof(struct ipv6hdr, saddr),
					     sizeof(*match1.key),
					     FLOW_ACT_MANGLE_HDR_TYPE_IP6);

		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	/* if pre ct entry do nat, the nat tport exists in nft entry,
	 * will be do merge check when do nft and post ct merge,
	 * so skip this tport merge check here.
	 */
	if ((ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) &&
	    nfp_ct_merge_check_cannot_skip(entry1, entry2)) {
		enum flow_action_mangle_base htype = FLOW_ACT_MANGLE_UNSPEC;
		struct flow_match_ports match1, match2;

		flow_rule_match_ports(entry1->rule, &match1);
		flow_rule_match_ports(entry2->rule, &match2);

		if (ip_proto == IPPROTO_UDP)
			htype = FLOW_ACT_MANGLE_HDR_TYPE_UDP;
		else if (ip_proto == IPPROTO_TCP)
			htype = FLOW_ACT_MANGLE_HDR_TYPE_TCP;

		memcpy(buf, match1.key, sizeof(*match1.key));
		match1.key = get_mangled_key(entry1->rule, buf, 0,
					     sizeof(*match1.key), htype);

		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
		struct flow_match_eth_addrs match1, match2;

		flow_rule_match_eth_addrs(entry1->rule, &match1);
		flow_rule_match_eth_addrs(entry2->rule, &match2);

		memcpy(buf, match1.key, sizeof(*match1.key));
		match1.key = get_mangled_key(entry1->rule, buf, 0,
					     sizeof(*match1.key),
					     FLOW_ACT_MANGLE_HDR_TYPE_ETH);

		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_VLAN)) {
		struct flow_match_vlan match1, match2;

		flow_rule_match_vlan(entry1->rule, &match1);
		flow_rule_match_vlan(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_MPLS)) {
		struct flow_match_mpls match1, match2;

		flow_rule_match_mpls(entry1->rule, &match1);
		flow_rule_match_mpls(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_TCP)) {
		struct flow_match_tcp match1, match2;

		flow_rule_match_tcp(entry1->rule, &match1);
		flow_rule_match_tcp(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IP)) {
		struct flow_match_ip match1, match2;

		flow_rule_match_ip(entry1->rule, &match1);
		flow_rule_match_ip(entry2->rule, &match2);

		match1.key = get_mangled_tos_ttl(entry1->rule, buf, is_v6);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_KEYID)) {
		struct flow_match_enc_keyid match1, match2;

		flow_rule_match_enc_keyid(entry1->rule, &match1);
		flow_rule_match_enc_keyid(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
		struct flow_match_ipv4_addrs match1, match2;

		flow_rule_match_enc_ipv4_addrs(entry1->rule, &match1);
		flow_rule_match_enc_ipv4_addrs(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
		struct flow_match_ipv6_addrs match1, match2;

		flow_rule_match_enc_ipv6_addrs(entry1->rule, &match1);
		flow_rule_match_enc_ipv6_addrs(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
		struct flow_match_control match1, match2;

		flow_rule_match_enc_control(entry1->rule, &match1);
		flow_rule_match_enc_control(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IP)) {
		struct flow_match_ip match1, match2;

		flow_rule_match_enc_ip(entry1->rule, &match1);
		flow_rule_match_enc_ip(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_OPTS)) {
		struct flow_match_enc_opts match1, match2;

		flow_rule_match_enc_opts(entry1->rule, &match1);
		flow_rule_match_enc_opts(entry2->rule, &match2);
		COMPARE_UNMASKED_FIELDS(match1, match2, &out);
		if (out)
			goto check_failed;
	}

	return 0;

check_failed:
	return -EINVAL;
}

static int nfp_ct_check_vlan_merge(struct flow_action_entry *a_in,
				   struct flow_rule *rule)
{
	struct flow_match_vlan match;

	if (unlikely(flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)))
		return -EOPNOTSUPP;

	/* post_ct does not match VLAN KEY, can be merged. */
	if (likely(!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)))
		return 0;

	switch (a_in->id) {
	/* pre_ct has pop vlan, post_ct cannot match VLAN KEY, cannot be merged. */
	case FLOW_ACTION_VLAN_POP:
		return -EOPNOTSUPP;

	case FLOW_ACTION_VLAN_PUSH:
	case FLOW_ACTION_VLAN_MANGLE:
		flow_rule_match_vlan(rule, &match);
		/* different vlan id, cannot be merged. */
		if ((match.key->vlan_id & match.mask->vlan_id) ^
		    (a_in->vlan.vid & match.mask->vlan_id))
			return -EOPNOTSUPP;

		/* different tpid, cannot be merged. */
		if ((match.key->vlan_tpid & match.mask->vlan_tpid) ^
		    (a_in->vlan.proto & match.mask->vlan_tpid))
			return -EOPNOTSUPP;

		/* different priority, cannot be merged. */
		if ((match.key->vlan_priority & match.mask->vlan_priority) ^
		    (a_in->vlan.prio & match.mask->vlan_priority))
			return -EOPNOTSUPP;

		break;
	default:
		return -EOPNOTSUPP;
	}

	return 0;
}

static int nfp_ct_merge_act_check(struct nfp_fl_ct_flow_entry *pre_ct_entry,
				  struct nfp_fl_ct_flow_entry *post_ct_entry,
				  struct nfp_fl_ct_flow_entry *nft_entry)
{
	struct flow_action_entry *act;
	int i, err;

	/* Check for pre_ct->action conflicts */
	flow_action_for_each(i, act, &pre_ct_entry->rule->action) {
		switch (act->id) {
		case FLOW_ACTION_VLAN_PUSH:
		case FLOW_ACTION_VLAN_POP:
		case FLOW_ACTION_VLAN_MANGLE:
			err = nfp_ct_check_vlan_merge(act, post_ct_entry->rule);
			if (err)
				return err;
			break;
		case FLOW_ACTION_MPLS_PUSH:
		case FLOW_ACTION_MPLS_POP:
		case FLOW_ACTION_MPLS_MANGLE:
			return -EOPNOTSUPP;
		default:
			break;
		}
	}

	/* Check for nft->action conflicts */
	flow_action_for_each(i, act, &nft_entry->rule->action) {
		switch (act->id) {
		case FLOW_ACTION_VLAN_PUSH:
		case FLOW_ACTION_VLAN_POP:
		case FLOW_ACTION_VLAN_MANGLE:
		case FLOW_ACTION_MPLS_PUSH:
		case FLOW_ACTION_MPLS_POP:
		case FLOW_ACTION_MPLS_MANGLE:
			return -EOPNOTSUPP;
		default:
			break;
		}
	}
	return 0;
}

static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry,
			     struct nfp_fl_ct_flow_entry *nft_entry)
{
	struct flow_dissector *dissector = post_ct_entry->rule->match.dissector;
	struct flow_action_entry *ct_met;
	struct flow_match_ct ct;
	int i;

	ct_met = get_flow_act(nft_entry->rule, FLOW_ACTION_CT_METADATA);
	if (ct_met && (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))) {
		u32 *act_lbl;

		act_lbl = ct_met->ct_metadata.labels;
		flow_rule_match_ct(post_ct_entry->rule, &ct);
		for (i = 0; i < 4; i++) {
			if ((ct.key->ct_labels[i] & ct.mask->ct_labels[i]) ^
			    (act_lbl[i] & ct.mask->ct_labels[i]))
				return -EINVAL;
		}

		if ((ct.key->ct_mark & ct.mask->ct_mark) ^
		    (ct_met->ct_metadata.mark & ct.mask->ct_mark))
			return -EINVAL;

		return 0;
	} else {
		/* post_ct with ct clear action will not match the
		 * ct status when nft is nat entry.
		 */
		if (nft_entry->flags & NFP_FL_ACTION_DO_MANGLE)
			return 0;
	}

	return -EINVAL;
}

static int
nfp_fl_calc_key_layers_sz(struct nfp_fl_key_ls in_key_ls, uint16_t *map)
{
	int key_size;

	/* This field must always be present */
	key_size = sizeof(struct nfp_flower_meta_tci);
	map[FLOW_PAY_META_TCI] = 0;

	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_EXT_META) {
		map[FLOW_PAY_EXT_META] = key_size;
		key_size += sizeof(struct nfp_flower_ext_meta);
	}
	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_PORT) {
		map[FLOW_PAY_INPORT] = key_size;
		key_size += sizeof(struct nfp_flower_in_port);
	}
	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_MAC) {
		map[FLOW_PAY_MAC_MPLS] = key_size;
		key_size += sizeof(struct nfp_flower_mac_mpls);
	}
	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_TP) {
		map[FLOW_PAY_L4] = key_size;
		key_size += sizeof(struct nfp_flower_tp_ports);
	}
	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_IPV4) {
		map[FLOW_PAY_IPV4] = key_size;
		key_size += sizeof(struct nfp_flower_ipv4);
	}
	if (in_key_ls.key_layer & NFP_FLOWER_LAYER_IPV6) {
		map[FLOW_PAY_IPV6] = key_size;
		key_size += sizeof(struct nfp_flower_ipv6);
	}

	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_QINQ) {
		map[FLOW_PAY_QINQ] = key_size;
		key_size += sizeof(struct nfp_flower_vlan);
	}

	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GRE) {
		map[FLOW_PAY_GRE] = key_size;
		if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6)
			key_size += sizeof(struct nfp_flower_ipv6_gre_tun);
		else
			key_size += sizeof(struct nfp_flower_ipv4_gre_tun);
	}

	if ((in_key_ls.key_layer & NFP_FLOWER_LAYER_VXLAN) ||
	    (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GENEVE)) {
		map[FLOW_PAY_UDP_TUN] = key_size;
		if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6)
			key_size += sizeof(struct nfp_flower_ipv6_udp_tun);
		else
			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
	}

	if (in_key_ls.key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
		map[FLOW_PAY_GENEVE_OPT] = key_size;
		key_size += sizeof(struct nfp_flower_geneve_options);
	}

	return key_size;
}

/* get the csum flag according the ip proto and mangle action. */
static void nfp_fl_get_csum_flag(struct flow_action_entry *a_in, u8 ip_proto, u32 *csum)
{
	if (a_in->id != FLOW_ACTION_MANGLE)
		return;

	switch (a_in->mangle.htype) {
	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
		*csum |= TCA_CSUM_UPDATE_FLAG_IPV4HDR;
		if (ip_proto == IPPROTO_TCP)
			*csum |= TCA_CSUM_UPDATE_FLAG_TCP;
		else if (ip_proto == IPPROTO_UDP)
			*csum |= TCA_CSUM_UPDATE_FLAG_UDP;
		break;
	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
		*csum |= TCA_CSUM_UPDATE_FLAG_TCP;
		break;
	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
		*csum |= TCA_CSUM_UPDATE_FLAG_UDP;
		break;
	default:
		break;
	}
}

static int nfp_fl_merge_actions_offload(struct flow_rule **rules,
					struct nfp_flower_priv *priv,
					struct net_device *netdev,
					struct nfp_fl_payload *flow_pay)
{
	enum flow_action_hw_stats tmp_stats = FLOW_ACTION_HW_STATS_DONT_CARE;
	struct flow_action_entry *a_in;
	int i, j, num_actions, id;
	struct flow_rule *a_rule;
	int err = 0, offset = 0;

	num_actions = rules[CT_TYPE_PRE_CT]->action.num_entries +
		      rules[CT_TYPE_NFT]->action.num_entries +
		      rules[CT_TYPE_POST_CT]->action.num_entries;

	/* Add one action to make sure there is enough room to add an checksum action
	 * when do nat.
	 */
	a_rule = flow_rule_alloc(num_actions + 1);
	if (!a_rule)
		return -ENOMEM;

	/* Actions need a BASIC dissector. */
	a_rule->match = rules[CT_TYPE_PRE_CT]->match;
	/* post_ct entry have one action at least. */
	if (rules[CT_TYPE_POST_CT]->action.num_entries != 0) {
		tmp_stats = rules[CT_TYPE_POST_CT]->action.entries[0].hw_stats;
	}

	/* Copy actions */
	for (j = 0; j < _CT_TYPE_MAX; j++) {
		u32 csum_updated = 0;
		u8 ip_proto = 0;

		if (flow_rule_match_key(rules[j], FLOW_DISSECTOR_KEY_BASIC)) {
			struct flow_match_basic match;

			/* ip_proto is the only field that is needed in later compile_action,
			 * needed to set the correct checksum flags. It doesn't really matter
			 * which input rule's ip_proto field we take as the earlier merge checks
			 * would have made sure that they don't conflict. We do not know which
			 * of the subflows would have the ip_proto filled in, so we need to iterate
			 * through the subflows and assign the proper subflow to a_rule
			 */
			flow_rule_match_basic(rules[j], &match);
			if (match.mask->ip_proto) {
				a_rule->match = rules[j]->match;
				ip_proto = match.key->ip_proto;
			}
		}

		for (i = 0; i < rules[j]->action.num_entries; i++) {
			a_in = &rules[j]->action.entries[i];
			id = a_in->id;

			/* Ignore CT related actions as these would already have
			 * been taken care of by previous checks, and we do not send
			 * any CT actions to the firmware.
			 */
			switch (id) {
			case FLOW_ACTION_CT:
			case FLOW_ACTION_GOTO:
			case FLOW_ACTION_CT_METADATA:
				continue;
			default:
				/* nft entry is generated by tc ct, which mangle action do not care
				 * the stats, inherit the post entry stats to meet the
				 * flow_action_hw_stats_check.
				 */
				if (j == CT_TYPE_NFT) {
					if (a_in->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE)
						a_in->hw_stats = tmp_stats;
					nfp_fl_get_csum_flag(a_in, ip_proto, &csum_updated);
				}
				memcpy(&a_rule->action.entries[offset++],
				       a_in, sizeof(struct flow_action_entry));
				break;
			}
		}
		/* nft entry have mangle action, but do not have checksum action when do NAT,
		 * hardware will automatically fix IPv4 and TCP/UDP checksum. so add an csum action
		 * to meet csum action check.
		 */
		if (csum_updated) {
			struct flow_action_entry *csum_action;

			csum_action = &a_rule->action.entries[offset++];
			csum_action->id = FLOW_ACTION_CSUM;
			csum_action->csum_flags = csum_updated;
			csum_action->hw_stats = tmp_stats;
		}
	}

	/* Some actions would have been ignored, so update the num_entries field */
	a_rule->action.num_entries = offset;
	err = nfp_flower_compile_action(priv->app, a_rule, netdev, flow_pay, NULL);
	kfree(a_rule);

	return err;
}

static int nfp_fl_ct_add_offload(struct nfp_fl_nft_tc_merge *m_entry)
{
	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
	struct nfp_fl_ct_zone_entry *zt = m_entry->zt;
	struct nfp_fl_key_ls key_layer, tmp_layer;
	struct nfp_flower_priv *priv = zt->priv;
	u16 key_map[_FLOW_PAY_LAYERS_MAX];
	struct nfp_fl_payload *flow_pay;

	struct flow_rule *rules[_CT_TYPE_MAX];
	u8 *key, *msk, *kdata, *mdata;
	struct nfp_port *port = NULL;
	struct net_device *netdev;
	bool qinq_sup;
	u32 port_id;
	u16 offset;
	int i, err;

	netdev = m_entry->netdev;
	qinq_sup = !!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_QINQ);

	rules[CT_TYPE_PRE_CT] = m_entry->tc_m_parent->pre_ct_parent->rule;
	rules[CT_TYPE_NFT] = m_entry->nft_parent->rule;
	rules[CT_TYPE_POST_CT] = m_entry->tc_m_parent->post_ct_parent->rule;

	memset(&key_layer, 0, sizeof(struct nfp_fl_key_ls));
	memset(&key_map, 0, sizeof(key_map));

	/* Calculate the resultant key layer and size for offload */
	for (i = 0; i < _CT_TYPE_MAX; i++) {
		err = nfp_flower_calculate_key_layers(priv->app,
						      m_entry->netdev,
						      &tmp_layer, rules[i],
						      &tun_type, NULL);
		if (err)
			return err;

		key_layer.key_layer |= tmp_layer.key_layer;
		key_layer.key_layer_two |= tmp_layer.key_layer_two;
	}
	key_layer.key_size = nfp_fl_calc_key_layers_sz(key_layer, key_map);

	flow_pay = nfp_flower_allocate_new(&key_layer);
	if (!flow_pay)
		return -ENOMEM;

	memset(flow_pay->unmasked_data, 0, key_layer.key_size);
	memset(flow_pay->mask_data, 0, key_layer.key_size);

	kdata = flow_pay->unmasked_data;
	mdata = flow_pay->mask_data;

	offset = key_map[FLOW_PAY_META_TCI];
	key = kdata + offset;
	msk = mdata + offset;
	nfp_flower_compile_meta((struct nfp_flower_meta_tci *)key,
				(struct nfp_flower_meta_tci *)msk,
				key_layer.key_layer);

	if (NFP_FLOWER_LAYER_EXT_META & key_layer.key_layer) {
		offset =  key_map[FLOW_PAY_EXT_META];
		key = kdata + offset;
		msk = mdata + offset;
		nfp_flower_compile_ext_meta((struct nfp_flower_ext_meta *)key,
					    key_layer.key_layer_two);
		nfp_flower_compile_ext_meta((struct nfp_flower_ext_meta *)msk,
					    key_layer.key_layer_two);
	}

	/* Using in_port from the -trk rule. The tc merge checks should already
	 * be checking that the ingress netdevs are the same
	 */
	port_id = nfp_flower_get_port_id_from_netdev(priv->app, netdev);
	offset = key_map[FLOW_PAY_INPORT];
	key = kdata + offset;
	msk = mdata + offset;
	err = nfp_flower_compile_port((struct nfp_flower_in_port *)key,
				      port_id, false, tun_type, NULL);
	if (err)
		goto ct_offload_err;
	err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
				      port_id, true, tun_type, NULL);
	if (err)
		goto ct_offload_err;

	/* This following part works on the assumption that previous checks has
	 * already filtered out flows that has different values for the different
	 * layers. Here we iterate through all three rules and merge their respective
	 * masked value(cared bits), basic method is:
	 * final_key = (r1_key & r1_mask) | (r2_key & r2_mask) | (r3_key & r3_mask)
	 * final_mask = r1_mask | r2_mask | r3_mask
	 * If none of the rules contains a match that is also fine, that simply means
	 * that the layer is not present.
	 */
	if (!qinq_sup) {
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			offset = key_map[FLOW_PAY_META_TCI];
			key = kdata + offset;
			msk = mdata + offset;
			nfp_flower_compile_tci((struct nfp_flower_meta_tci *)key,
					       (struct nfp_flower_meta_tci *)msk,
					       rules[i]);
		}
	}

	if (NFP_FLOWER_LAYER_MAC & key_layer.key_layer) {
		offset = key_map[FLOW_PAY_MAC_MPLS];
		key = kdata + offset;
		msk = mdata + offset;
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)key,
					       (struct nfp_flower_mac_mpls *)msk,
					       rules[i]);
			err = nfp_flower_compile_mpls((struct nfp_flower_mac_mpls *)key,
						      (struct nfp_flower_mac_mpls *)msk,
						      rules[i], NULL);
			if (err)
				goto ct_offload_err;
		}
	}

	if (NFP_FLOWER_LAYER_IPV4 & key_layer.key_layer) {
		offset = key_map[FLOW_PAY_IPV4];
		key = kdata + offset;
		msk = mdata + offset;
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)key,
						(struct nfp_flower_ipv4 *)msk,
						rules[i]);
		}
	}

	if (NFP_FLOWER_LAYER_IPV6 & key_layer.key_layer) {
		offset = key_map[FLOW_PAY_IPV6];
		key = kdata + offset;
		msk = mdata + offset;
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)key,
						(struct nfp_flower_ipv6 *)msk,
						rules[i]);
		}
	}

	if (NFP_FLOWER_LAYER_TP & key_layer.key_layer) {
		offset = key_map[FLOW_PAY_L4];
		key = kdata + offset;
		msk = mdata + offset;
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			nfp_flower_compile_tport((struct nfp_flower_tp_ports *)key,
						 (struct nfp_flower_tp_ports *)msk,
						 rules[i]);
		}
	}

	if (NFP_FLOWER_LAYER2_QINQ & key_layer.key_layer_two) {
		offset = key_map[FLOW_PAY_QINQ];
		key = kdata + offset;
		msk = mdata + offset;
		for (i = 0; i < _CT_TYPE_MAX; i++) {
			nfp_flower_compile_vlan((struct nfp_flower_vlan *)key,
						(struct nfp_flower_vlan *)msk,
						rules[i]);
		}
	}

	if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_GRE) {
		offset = key_map[FLOW_PAY_GRE];
		key = kdata + offset;
		msk = mdata + offset;
		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) {
			struct nfp_flower_ipv6_gre_tun *gre_match;
			struct nfp_ipv6_addr_entry *entry;
			struct in6_addr *dst;

			for (i = 0; i < _CT_TYPE_MAX; i++) {
				nfp_flower_compile_ipv6_gre_tun((void *)key,
								(void *)msk, rules[i]);
			}
			gre_match = (struct nfp_flower_ipv6_gre_tun *)key;
			dst = &gre_match->ipv6.dst;

			entry = nfp_tunnel_add_ipv6_off(priv->app, dst);
			if (!entry) {
				err = -ENOMEM;
				goto ct_offload_err;
			}

			flow_pay->nfp_tun_ipv6 = entry;
		} else {
			__be32 dst;

			for (i = 0; i < _CT_TYPE_MAX; i++) {
				nfp_flower_compile_ipv4_gre_tun((void *)key,
								(void *)msk, rules[i]);
			}
			dst = ((struct nfp_flower_ipv4_gre_tun *)key)->ipv4.dst;

			/* Store the tunnel destination in the rule data.
			 * This must be present and be an exact match.
			 */
			flow_pay->nfp_tun_ipv4_addr = dst;
			nfp_tunnel_add_ipv4_off(priv->app, dst);
		}
	}

	if (key_layer.key_layer & NFP_FLOWER_LAYER_VXLAN ||
	    key_layer.key_layer_two & NFP_FLOWER_LAYER2_GENEVE) {
		offset = key_map[FLOW_PAY_UDP_TUN];
		key = kdata + offset;
		msk = mdata + offset;
		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_TUN_IPV6) {
			struct nfp_flower_ipv6_udp_tun *udp_match;
			struct nfp_ipv6_addr_entry *entry;
			struct in6_addr *dst;

			for (i = 0; i < _CT_TYPE_MAX; i++) {
				nfp_flower_compile_ipv6_udp_tun((void *)key,
								(void *)msk, rules[i]);
			}
			udp_match = (struct nfp_flower_ipv6_udp_tun *)key;
			dst = &udp_match->ipv6.dst;

			entry = nfp_tunnel_add_ipv6_off(priv->app, dst);
			if (!entry) {
				err = -ENOMEM;
				goto ct_offload_err;
			}

			flow_pay->nfp_tun_ipv6 = entry;
		} else {
			__be32 dst;

			for (i = 0; i < _CT_TYPE_MAX; i++) {
				nfp_flower_compile_ipv4_udp_tun((void *)key,
								(void *)msk, rules[i]);
			}
			dst = ((struct nfp_flower_ipv4_udp_tun *)key)->ipv4.dst;

			/* Store the tunnel destination in the rule data.
			 * This must be present and be an exact match.
			 */
			flow_pay->nfp_tun_ipv4_addr = dst;
			nfp_tunnel_add_ipv4_off(priv->app, dst);
		}

		if (key_layer.key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
			offset = key_map[FLOW_PAY_GENEVE_OPT];
			key = kdata + offset;
			msk = mdata + offset;
			for (i = 0; i < _CT_TYPE_MAX; i++)
				nfp_flower_compile_geneve_opt(key, msk, rules[i]);
		}
	}

	/* Merge actions into flow_pay */
	err = nfp_fl_merge_actions_offload(rules, priv, netdev, flow_pay);
	if (err)
		goto ct_offload_err;

	/* Use the pointer address as the cookie, but set the last bit to 1.
	 * This is to avoid the 'is_merge_flow' check from detecting this as
	 * an already merged flow. This works since address alignment means
	 * that the last bit for pointer addresses will be 0.
	 */
	flow_pay->tc_flower_cookie = ((unsigned long)flow_pay) | 0x1;
	err = nfp_compile_flow_metadata(priv->app, flow_pay->tc_flower_cookie,
					flow_pay, netdev, NULL);
	if (err)
		goto ct_offload_err;

	if (nfp_netdev_is_nfp_repr(netdev))
		port = nfp_port_from_netdev(netdev);

	err = rhashtable_insert_fast(&priv->flow_table, &flow_pay->fl_node,
				     nfp_flower_table_params);
	if (err)
		goto ct_release_offload_meta_err;

	err = nfp_flower_xmit_flow(priv->app, flow_pay,
				   NFP_FLOWER_CMSG_TYPE_FLOW_ADD);
	if (err)
		goto ct_remove_rhash_err;

	m_entry->tc_flower_cookie = flow_pay->tc_flower_cookie;
	m_entry->flow_pay = flow_pay;

	if (port)
		port->tc_offload_cnt++;

	return err;

ct_remove_rhash_err:
	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
					    &flow_pay->fl_node,
					    nfp_flower_table_params));
ct_release_offload_meta_err:
	nfp_modify_flow_metadata(priv->app, flow_pay);
ct_offload_err:
	if (flow_pay->nfp_tun_ipv4_addr)
		nfp_tunnel_del_ipv4_off(priv->app, flow_pay->nfp_tun_ipv4_addr);
	if (flow_pay->nfp_tun_ipv6)
		nfp_tunnel_put_ipv6_off(priv->app, flow_pay->nfp_tun_ipv6);
	kfree(flow_pay->action_data);
	kfree(flow_pay->mask_data);
	kfree(flow_pay->unmasked_data);
	kfree(flow_pay);
	return err;
}

static int nfp_fl_ct_del_offload(struct nfp_app *app, unsigned long cookie,
				 struct net_device *netdev)
{
	struct nfp_flower_priv *priv = app->priv;
	struct nfp_fl_payload *flow_pay;
	struct nfp_port *port = NULL;
	int err = 0;

	if (nfp_netdev_is_nfp_repr(netdev))
		port = nfp_port_from_netdev(netdev);

	flow_pay = nfp_flower_search_fl_table(app, cookie, netdev);
	if (!flow_pay)
		return -ENOENT;

	err = nfp_modify_flow_metadata(app, flow_pay);
	if (err)
		goto err_free_merge_flow;

	if (flow_pay->nfp_tun_ipv4_addr)
		nfp_tunnel_del_ipv4_off(app, flow_pay->nfp_tun_ipv4_addr);

	if (flow_pay->nfp_tun_ipv6)
		nfp_tunnel_put_ipv6_off(app, flow_pay->nfp_tun_ipv6);

	if (!flow_pay->in_hw) {
		err = 0;
		goto err_free_merge_flow;
	}

	err = nfp_flower_xmit_flow(app, flow_pay,
				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);

err_free_merge_flow:
	nfp_flower_del_linked_merge_flows(app, flow_pay);
	if (port)
		port->tc_offload_cnt--;
	kfree(flow_pay->action_data);
	kfree(flow_pay->mask_data);
	kfree(flow_pay->unmasked_data);
	WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
					    &flow_pay->fl_node,
					    nfp_flower_table_params));
	kfree_rcu(flow_pay, rcu);
	return err;
}

static int nfp_ct_do_nft_merge(struct nfp_fl_ct_zone_entry *zt,
			       struct nfp_fl_ct_flow_entry *nft_entry,
			       struct nfp_fl_ct_tc_merge *tc_m_entry)
{
	struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry;
	struct nfp_fl_nft_tc_merge *nft_m_entry;
	unsigned long new_cookie[3];
	int err;

	pre_ct_entry = tc_m_entry->pre_ct_parent;
	post_ct_entry = tc_m_entry->post_ct_parent;

	err = nfp_ct_merge_act_check(pre_ct_entry, post_ct_entry, nft_entry);
	if (err)
		return err;

	/* Check that the two tc flows are also compatible with
	 * the nft entry. No need to check the pre_ct and post_ct
	 * entries as that was already done during pre_merge.
	 * The nft entry does not have a chain populated, so
	 * skip this check.
	 */
	err = nfp_ct_merge_check(pre_ct_entry, nft_entry);
	if (err)
		return err;
	err = nfp_ct_merge_check(nft_entry, post_ct_entry);
	if (err)
		return err;
	err = nfp_ct_check_meta(post_ct_entry, nft_entry);
	if (err)
		return err;

	/* Combine tc_merge and nft cookies for this cookie. */
	new_cookie[0] = tc_m_entry->cookie[0];
	new_cookie[1] = tc_m_entry->cookie[1];
	new_cookie[2] = nft_entry->cookie;
	nft_m_entry = get_hashentry(&zt->nft_merge_tb,
				    &new_cookie,
				    nfp_nft_ct_merge_params,
				    sizeof(*nft_m_entry));

	if (IS_ERR(nft_m_entry))
		return PTR_ERR(nft_m_entry);

	/* nft_m_entry already present, not merging again */
	if (!memcmp(&new_cookie, nft_m_entry->cookie, sizeof(new_cookie)))
		return 0;

	memcpy(&nft_m_entry->cookie, &new_cookie, sizeof(new_cookie));
	nft_m_entry->zt = zt;
	nft_m_entry->tc_m_parent = tc_m_entry;
	nft_m_entry->nft_parent = nft_entry;
	nft_m_entry->tc_flower_cookie = 0;
	/* Copy the netdev from the pre_ct entry. When the tc_m_entry was created
	 * it only combined them if the netdevs were the same, so can use any of them.
	 */
	nft_m_entry->netdev = pre_ct_entry->netdev;

	/* Add this entry to the tc_m_list and nft_flow lists */
	list_add(&nft_m_entry->tc_merge_list, &tc_m_entry->children);
	list_add(&nft_m_entry->nft_flow_list, &nft_entry->children);

	/* Generate offload structure and send to nfp */
	err = nfp_fl_ct_add_offload(nft_m_entry);
	if (err)
		goto err_nft_ct_offload;

	err = rhashtable_insert_fast(&zt->nft_merge_tb, &nft_m_entry->hash_node,
				     nfp_nft_ct_merge_params);
	if (err)
		goto err_nft_ct_merge_insert;

	zt->nft_merge_count++;

	return err;

err_nft_ct_merge_insert:
	nfp_fl_ct_del_offload(zt->priv->app, nft_m_entry->tc_flower_cookie,
			      nft_m_entry->netdev);
err_nft_ct_offload:
	list_del(&nft_m_entry->tc_merge_list);
	list_del(&nft_m_entry->nft_flow_list);
	kfree(nft_m_entry);
	return err;
}

static int nfp_ct_do_tc_merge(struct nfp_fl_ct_zone_entry *zt,
			      struct nfp_fl_ct_flow_entry *ct_entry1,
			      struct nfp_fl_ct_flow_entry *ct_entry2)
{
	struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry;
	struct nfp_fl_ct_flow_entry *nft_entry, *nft_tmp;
	struct nfp_fl_ct_tc_merge *m_entry;
	unsigned long new_cookie[2];
	int err;

	if (ct_entry1->type == CT_TYPE_PRE_CT) {
		pre_ct_entry = ct_entry1;
		post_ct_entry = ct_entry2;
	} else {
		post_ct_entry = ct_entry1;
		pre_ct_entry = ct_entry2;
	}

	/* Checks that the chain_index of the filter matches the
	 * chain_index of the GOTO action.
	 */
	if (post_ct_entry->chain_index != pre_ct_entry->goto_chain_index)
		return -EINVAL;

	err = nfp_ct_merge_check(pre_ct_entry, post_ct_entry);
	if (err)
		return err;

	new_cookie[0] = pre_ct_entry->cookie;
	new_cookie[1] = post_ct_entry->cookie;
	m_entry = get_hashentry(&zt->tc_merge_tb, &new_cookie,
				nfp_tc_ct_merge_params, sizeof(*m_entry));
	if (IS_ERR(m_entry))
		return PTR_ERR(m_entry);

	/* m_entry already present, not merging again */
	if (!memcmp(&new_cookie, m_entry->cookie, sizeof(new_cookie)))
		return 0;

	memcpy(&m_entry->cookie, &new_cookie, sizeof(new_cookie));
	m_entry->zt = zt;
	m_entry->post_ct_parent = post_ct_entry;
	m_entry->pre_ct_parent = pre_ct_entry;

	/* Add this entry to the pre_ct and post_ct lists */
	list_add(&m_entry->post_ct_list, &post_ct_entry->children);
	list_add(&m_entry->pre_ct_list, &pre_ct_entry->children);
	INIT_LIST_HEAD(&m_entry->children);

	err = rhashtable_insert_fast(&zt->tc_merge_tb, &m_entry->hash_node,
				     nfp_tc_ct_merge_params);
	if (err)
		goto err_ct_tc_merge_insert;
	zt->tc_merge_count++;

	/* Merge with existing nft flows */
	list_for_each_entry_safe(nft_entry, nft_tmp, &zt->nft_flows_list,
				 list_node) {
		nfp_ct_do_nft_merge(zt, nft_entry, m_entry);
	}

	return 0;

err_ct_tc_merge_insert:
	list_del(&m_entry->post_ct_list);
	list_del(&m_entry->pre_ct_list);
	kfree(m_entry);
	return err;
}

static struct
nfp_fl_ct_zone_entry *get_nfp_zone_entry(struct nfp_flower_priv *priv,
					 u16 zone, bool wildcarded)
{
	struct nfp_fl_ct_zone_entry *zt;
	int err;

	if (wildcarded && priv->ct_zone_wc)
		return priv->ct_zone_wc;

	if (!wildcarded) {
		zt = get_hashentry(&priv->ct_zone_table, &zone,
				   nfp_zone_table_params, sizeof(*zt));

		/* If priv is set this is an existing entry, just return it */
		if (IS_ERR(zt) || zt->priv)
			return zt;
	} else {
		zt = kzalloc(sizeof(*zt), GFP_KERNEL);
		if (!zt)
			return ERR_PTR(-ENOMEM);
	}

	zt->zone = zone;
	zt->priv = priv;
	zt->nft = NULL;

	/* init the various hash tables and lists */
	INIT_LIST_HEAD(&zt->pre_ct_list);
	INIT_LIST_HEAD(&zt->post_ct_list);
	INIT_LIST_HEAD(&zt->nft_flows_list);

	err = rhashtable_init(&zt->tc_merge_tb, &nfp_tc_ct_merge_params);
	if (err)
		goto err_tc_merge_tb_init;

	err = rhashtable_init(&zt->nft_merge_tb, &nfp_nft_ct_merge_params);
	if (err)
		goto err_nft_merge_tb_init;

	if (wildcarded) {
		priv->ct_zone_wc = zt;
	} else {
		err = rhashtable_insert_fast(&priv->ct_zone_table,
					     &zt->hash_node,
					     nfp_zone_table_params);
		if (err)
			goto err_zone_insert;
	}

	return zt;

err_zone_insert:
	rhashtable_destroy(&zt->nft_merge_tb);
err_nft_merge_tb_init:
	rhashtable_destroy(&zt->tc_merge_tb);
err_tc_merge_tb_init:
	kfree(zt);
	return ERR_PTR(err);
}

static struct net_device *get_netdev_from_rule(struct flow_rule *rule)
{
	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) {
		struct flow_match_meta match;

		flow_rule_match_meta(rule, &match);
		if (match.key->ingress_ifindex & match.mask->ingress_ifindex)
			return __dev_get_by_index(&init_net,
						  match.key->ingress_ifindex);
	}

	return NULL;
}

static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_action)
{
	if (mangle_action->id != FLOW_ACTION_MANGLE)
		return;

	switch (mangle_action->mangle.htype) {
	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
		mangle_action->mangle.val = (__force u32)cpu_to_be32(mangle_action->mangle.val);
		mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
		return;

	/* Both struct tcphdr and struct udphdr start with
	 *	__be16 source;
	 *	__be16 dest;
	 * so we can use the same code for both.
	 */
	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
		if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) {
			mangle_action->mangle.val =
				(__force u32)cpu_to_be32(mangle_action->mangle.val << 16);
			/* The mask of mangle action is inverse mask,
			 * so clear the dest tp port with 0xFFFF to
			 * instead of rotate-left operation.
			 */
			mangle_action->mangle.mask =
				(__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF);
		}
		if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) {
			mangle_action->mangle.offset = 0;
			mangle_action->mangle.val =
				(__force u32)cpu_to_be32(mangle_action->mangle.val);
			mangle_action->mangle.mask =
				(__force u32)cpu_to_be32(mangle_action->mangle.mask);
		}
		return;

	default:
		return;
	}
}

static int nfp_nft_ct_set_flow_flag(struct flow_action_entry *act,
				    struct nfp_fl_ct_flow_entry *entry)
{
	switch (act->id) {
	case FLOW_ACTION_CT:
		if (act->ct.action == TCA_CT_ACT_NAT)
			entry->flags |= NFP_FL_ACTION_DO_NAT;
		break;

	case FLOW_ACTION_MANGLE:
		entry->flags |= NFP_FL_ACTION_DO_MANGLE;
		break;

	default:
		break;
	}

	return 0;
}

static struct
nfp_fl_ct_flow_entry *nfp_fl_ct_add_flow(struct nfp_fl_ct_zone_entry *zt,
					 struct net_device *netdev,
					 struct flow_cls_offload *flow,
					 bool is_nft, struct netlink_ext_ack *extack)
{
	struct nf_flow_match *nft_match = NULL;
	struct nfp_fl_ct_flow_entry *entry;
	struct nfp_fl_ct_map_entry *map;
	struct flow_action_entry *act;
	int err, i;

	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
	if (!entry)
		return ERR_PTR(-ENOMEM);

	entry->rule = flow_rule_alloc(flow->rule->action.num_entries);
	if (!entry->rule) {
		err = -ENOMEM;
		goto err_pre_ct_rule;
	}

	/* nft flows gets destroyed after callback return, so need
	 * to do a full copy instead of just a reference.
	 */
	if (is_nft) {
		nft_match = kzalloc(sizeof(*nft_match), GFP_KERNEL);
		if (!nft_match) {
			err = -ENOMEM;
			goto err_pre_ct_act;
		}
		memcpy(&nft_match->dissector, flow->rule->match.dissector,
		       sizeof(nft_match->dissector));
		memcpy(&nft_match->mask, flow->rule->match.mask,
		       sizeof(nft_match->mask));
		memcpy(&nft_match->key, flow->rule->match.key,
		       sizeof(nft_match->key));
		entry->rule->match.dissector = &nft_match->dissector;
		entry->rule->match.mask = &nft_match->mask;
		entry->rule->match.key = &nft_match->key;

		if (!netdev)
			netdev = get_netdev_from_rule(entry->rule);
	} else {
		entry->rule->match.dissector = flow->rule->match.dissector;
		entry->rule->match.mask = flow->rule->match.mask;
		entry->rule->match.key = flow->rule->match.key;
	}

	entry->zt = zt;
	entry->netdev = netdev;
	entry->cookie = flow->cookie;
	entry->chain_index = flow->common.chain_index;
	entry->tun_offset = NFP_FL_CT_NO_TUN;

	/* Copy over action data. Unfortunately we do not get a handle to the
	 * original tcf_action data, and the flow objects gets destroyed, so we
	 * cannot just save a pointer to this either, so need to copy over the
	 * data unfortunately.
	 */
	entry->rule->action.num_entries = flow->rule->action.num_entries;
	flow_action_for_each(i, act, &flow->rule->action) {
		struct flow_action_entry *new_act;

		new_act = &entry->rule->action.entries[i];
		memcpy(new_act, act, sizeof(struct flow_action_entry));
		/* nft entry mangle field is host byte order, need translate to
		 * network byte order.
		 */
		if (is_nft)
			nfp_nft_ct_translate_mangle_action(new_act);

		nfp_nft_ct_set_flow_flag(new_act, entry);
		/* Entunnel is a special case, need to allocate and copy
		 * tunnel info.
		 */
		if (act->id == FLOW_ACTION_TUNNEL_ENCAP) {
			struct ip_tunnel_info *tun = act->tunnel;
			size_t tun_size = sizeof(*tun) + tun->options_len;

			new_act->tunnel = kmemdup(tun, tun_size, GFP_ATOMIC);
			if (!new_act->tunnel) {
				err = -ENOMEM;
				goto err_pre_ct_tun_cp;
			}
			entry->tun_offset = i;
		}
	}

	INIT_LIST_HEAD(&entry->children);

	/* Now add a ct map entry to flower-priv */
	map = get_hashentry(&zt->priv->ct_map_table, &flow->cookie,
			    nfp_ct_map_params, sizeof(*map));
	if (IS_ERR(map)) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload error: ct map entry creation failed");
		err = -ENOMEM;
		goto err_ct_flow_insert;
	}
	map->cookie = flow->cookie;
	map->ct_entry = entry;
	err = rhashtable_insert_fast(&zt->priv->ct_map_table,
				     &map->hash_node,
				     nfp_ct_map_params);
	if (err) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload error: ct map entry table add failed");
		goto err_map_insert;
	}

	return entry;

err_map_insert:
	kfree(map);
err_ct_flow_insert:
	if (entry->tun_offset != NFP_FL_CT_NO_TUN)
		kfree(entry->rule->action.entries[entry->tun_offset].tunnel);
err_pre_ct_tun_cp:
	kfree(nft_match);
err_pre_ct_act:
	kfree(entry->rule);
err_pre_ct_rule:
	kfree(entry);
	return ERR_PTR(err);
}

static void cleanup_nft_merge_entry(struct nfp_fl_nft_tc_merge *m_entry)
{
	struct nfp_fl_ct_zone_entry *zt;
	int err;

	zt = m_entry->zt;

	/* Flow is in HW, need to delete */
	if (m_entry->tc_flower_cookie) {
		err = nfp_fl_ct_del_offload(zt->priv->app, m_entry->tc_flower_cookie,
					    m_entry->netdev);
		if (err)
			return;
	}

	WARN_ON_ONCE(rhashtable_remove_fast(&zt->nft_merge_tb,
					    &m_entry->hash_node,
					    nfp_nft_ct_merge_params));
	zt->nft_merge_count--;
	list_del(&m_entry->tc_merge_list);
	list_del(&m_entry->nft_flow_list);

	kfree(m_entry);
}

static void nfp_free_nft_merge_children(void *entry, bool is_nft_flow)
{
	struct nfp_fl_nft_tc_merge *m_entry, *tmp;

	/* These post entries are parts of two lists, one is a list of nft_entries
	 * and the other is of from a list of tc_merge structures. Iterate
	 * through the relevant list and cleanup the entries.
	 */

	if (is_nft_flow) {
		/* Need to iterate through list of nft_flow entries */
		struct nfp_fl_ct_flow_entry *ct_entry = entry;

		list_for_each_entry_safe(m_entry, tmp, &ct_entry->children,
					 nft_flow_list) {
			cleanup_nft_merge_entry(m_entry);
		}
	} else {
		/* Need to iterate through list of tc_merged_flow entries */
		struct nfp_fl_ct_tc_merge *ct_entry = entry;

		list_for_each_entry_safe(m_entry, tmp, &ct_entry->children,
					 tc_merge_list) {
			cleanup_nft_merge_entry(m_entry);
		}
	}
}

static void nfp_del_tc_merge_entry(struct nfp_fl_ct_tc_merge *m_ent)
{
	struct nfp_fl_ct_zone_entry *zt;
	int err;

	zt = m_ent->zt;
	err = rhashtable_remove_fast(&zt->tc_merge_tb,
				     &m_ent->hash_node,
				     nfp_tc_ct_merge_params);
	if (err)
		pr_warn("WARNING: could not remove merge_entry from hashtable\n");
	zt->tc_merge_count--;
	list_del(&m_ent->post_ct_list);
	list_del(&m_ent->pre_ct_list);

	if (!list_empty(&m_ent->children))
		nfp_free_nft_merge_children(m_ent, false);
	kfree(m_ent);
}

static void nfp_free_tc_merge_children(struct nfp_fl_ct_flow_entry *entry)
{
	struct nfp_fl_ct_tc_merge *m_ent, *tmp;

	switch (entry->type) {
	case CT_TYPE_PRE_CT:
		list_for_each_entry_safe(m_ent, tmp, &entry->children, pre_ct_list) {
			nfp_del_tc_merge_entry(m_ent);
		}
		break;
	case CT_TYPE_POST_CT:
		list_for_each_entry_safe(m_ent, tmp, &entry->children, post_ct_list) {
			nfp_del_tc_merge_entry(m_ent);
		}
		break;
	default:
		break;
	}
}

void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry)
{
	list_del(&entry->list_node);

	if (!list_empty(&entry->children)) {
		if (entry->type == CT_TYPE_NFT)
			nfp_free_nft_merge_children(entry, true);
		else
			nfp_free_tc_merge_children(entry);
	}

	if (entry->tun_offset != NFP_FL_CT_NO_TUN)
		kfree(entry->rule->action.entries[entry->tun_offset].tunnel);

	if (entry->type == CT_TYPE_NFT) {
		struct nf_flow_match *nft_match;

		nft_match = container_of(entry->rule->match.dissector,
					 struct nf_flow_match, dissector);
		kfree(nft_match);
	}

	kfree(entry->rule);
	kfree(entry);
}

static struct flow_action_entry *get_flow_act(struct flow_rule *rule,
					      enum flow_action_id act_id)
{
	struct flow_action_entry *act = NULL;
	int i;

	flow_action_for_each(i, act, &rule->action) {
		if (act->id == act_id)
			return act;
	}
	return NULL;
}

static void
nfp_ct_merge_tc_entries(struct nfp_fl_ct_flow_entry *ct_entry1,
			struct nfp_fl_ct_zone_entry *zt_src,
			struct nfp_fl_ct_zone_entry *zt_dst)
{
	struct nfp_fl_ct_flow_entry *ct_entry2, *ct_tmp;
	struct list_head *ct_list;

	if (ct_entry1->type == CT_TYPE_PRE_CT)
		ct_list = &zt_src->post_ct_list;
	else if (ct_entry1->type == CT_TYPE_POST_CT)
		ct_list = &zt_src->pre_ct_list;
	else
		return;

	list_for_each_entry_safe(ct_entry2, ct_tmp, ct_list,
				 list_node) {
		nfp_ct_do_tc_merge(zt_dst, ct_entry2, ct_entry1);
	}
}

static void
nfp_ct_merge_nft_with_tc(struct nfp_fl_ct_flow_entry *nft_entry,
			 struct nfp_fl_ct_zone_entry *zt)
{
	struct nfp_fl_ct_tc_merge *tc_merge_entry;
	struct rhashtable_iter iter;

	rhashtable_walk_enter(&zt->tc_merge_tb, &iter);
	rhashtable_walk_start(&iter);
	while ((tc_merge_entry = rhashtable_walk_next(&iter)) != NULL) {
		if (IS_ERR(tc_merge_entry))
			continue;
		rhashtable_walk_stop(&iter);
		nfp_ct_do_nft_merge(zt, nft_entry, tc_merge_entry);
		rhashtable_walk_start(&iter);
	}
	rhashtable_walk_stop(&iter);
	rhashtable_walk_exit(&iter);
}

int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv,
			    struct net_device *netdev,
			    struct flow_cls_offload *flow,
			    struct netlink_ext_ack *extack)
{
	struct flow_action_entry *ct_act, *ct_goto;
	struct nfp_fl_ct_flow_entry *ct_entry;
	struct nfp_fl_ct_zone_entry *zt;
	int err;

	ct_act = get_flow_act(flow->rule, FLOW_ACTION_CT);
	if (!ct_act) {
		NL_SET_ERR_MSG_MOD(extack,
				   "unsupported offload: Conntrack action empty in conntrack offload");
		return -EOPNOTSUPP;
	}

	ct_goto = get_flow_act(flow->rule, FLOW_ACTION_GOTO);
	if (!ct_goto) {
		NL_SET_ERR_MSG_MOD(extack,
				   "unsupported offload: Conntrack requires ACTION_GOTO");
		return -EOPNOTSUPP;
	}

	zt = get_nfp_zone_entry(priv, ct_act->ct.zone, false);
	if (IS_ERR(zt)) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload error: Could not create zone table entry");
		return PTR_ERR(zt);
	}

	if (!zt->nft) {
		zt->nft = ct_act->ct.flow_table;
		err = nf_flow_table_offload_add_cb(zt->nft, nfp_fl_ct_handle_nft_flow, zt);
		if (err) {
			NL_SET_ERR_MSG_MOD(extack,
					   "offload error: Could not register nft_callback");
			return err;
		}
	}

	/* Add entry to pre_ct_list */
	ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack);
	if (IS_ERR(ct_entry))
		return PTR_ERR(ct_entry);
	ct_entry->type = CT_TYPE_PRE_CT;
	ct_entry->chain_index = flow->common.chain_index;
	ct_entry->goto_chain_index = ct_goto->chain_index;
	list_add(&ct_entry->list_node, &zt->pre_ct_list);
	zt->pre_ct_count++;

	nfp_ct_merge_tc_entries(ct_entry, zt, zt);

	/* Need to check and merge with tables in the wc_zone as well */
	if (priv->ct_zone_wc)
		nfp_ct_merge_tc_entries(ct_entry, priv->ct_zone_wc, zt);

	return 0;
}

int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
			     struct net_device *netdev,
			     struct flow_cls_offload *flow,
			     struct netlink_ext_ack *extack)
{
	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
	struct nfp_fl_ct_flow_entry *ct_entry;
	struct flow_action_entry *ct_goto;
	struct nfp_fl_ct_zone_entry *zt;
	struct flow_action_entry *act;
	bool wildcarded = false;
	struct flow_match_ct ct;
	int i;

	flow_action_for_each(i, act, &rule->action) {
		switch (act->id) {
		case FLOW_ACTION_REDIRECT:
		case FLOW_ACTION_REDIRECT_INGRESS:
		case FLOW_ACTION_MIRRED:
		case FLOW_ACTION_MIRRED_INGRESS:
			if (act->dev->rtnl_link_ops &&
			    !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) {
				NL_SET_ERR_MSG_MOD(extack,
						   "unsupported offload: out port is openvswitch internal port");
				return -EOPNOTSUPP;
			}
			break;
		default:
			break;
		}
	}

	flow_rule_match_ct(rule, &ct);
	if (!ct.mask->ct_zone) {
		wildcarded = true;
	} else if (ct.mask->ct_zone != U16_MAX) {
		NL_SET_ERR_MSG_MOD(extack,
				   "unsupported offload: partially wildcarded ct_zone is not supported");
		return -EOPNOTSUPP;
	}

	zt = get_nfp_zone_entry(priv, ct.key->ct_zone, wildcarded);
	if (IS_ERR(zt)) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload error: Could not create zone table entry");
		return PTR_ERR(zt);
	}

	/* Add entry to post_ct_list */
	ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack);
	if (IS_ERR(ct_entry))
		return PTR_ERR(ct_entry);

	ct_entry->type = CT_TYPE_POST_CT;
	ct_entry->chain_index = flow->common.chain_index;
	ct_goto = get_flow_act(flow->rule, FLOW_ACTION_GOTO);
	ct_entry->goto_chain_index = ct_goto ? ct_goto->chain_index : 0;
	list_add(&ct_entry->list_node, &zt->post_ct_list);
	zt->post_ct_count++;

	if (wildcarded) {
		/* Iterate through all zone tables if not empty, look for merges with
		 * pre_ct entries and merge them.
		 */
		struct rhashtable_iter iter;
		struct nfp_fl_ct_zone_entry *zone_table;

		rhashtable_walk_enter(&priv->ct_zone_table, &iter);
		rhashtable_walk_start(&iter);
		while ((zone_table = rhashtable_walk_next(&iter)) != NULL) {
			if (IS_ERR(zone_table))
				continue;
			rhashtable_walk_stop(&iter);
			nfp_ct_merge_tc_entries(ct_entry, zone_table, zone_table);
			rhashtable_walk_start(&iter);
		}
		rhashtable_walk_stop(&iter);
		rhashtable_walk_exit(&iter);
	} else {
		nfp_ct_merge_tc_entries(ct_entry, zt, zt);
	}

	return 0;
}

static void
nfp_fl_ct_sub_stats(struct nfp_fl_nft_tc_merge *nft_merge,
		    enum ct_entry_type type, u64 *m_pkts,
		    u64 *m_bytes, u64 *m_used)
{
	struct nfp_flower_priv *priv = nft_merge->zt->priv;
	struct nfp_fl_payload *nfp_flow;
	u32 ctx_id;

	nfp_flow = nft_merge->flow_pay;
	if (!nfp_flow)
		return;

	ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
	*m_pkts += priv->stats[ctx_id].pkts;
	*m_bytes += priv->stats[ctx_id].bytes;
	*m_used = max_t(u64, *m_used, priv->stats[ctx_id].used);

	/* If request is for a sub_flow which is part of a tunnel merged
	 * flow then update stats from tunnel merged flows first.
	 */
	if (!list_empty(&nfp_flow->linked_flows))
		nfp_flower_update_merge_stats(priv->app, nfp_flow);

	if (type != CT_TYPE_NFT) {
		/* Update nft cached stats */
		flow_stats_update(&nft_merge->nft_parent->stats,
				  priv->stats[ctx_id].bytes,
				  priv->stats[ctx_id].pkts,
				  0, priv->stats[ctx_id].used,
				  FLOW_ACTION_HW_STATS_DELAYED);
	} else {
		/* Update pre_ct cached stats */
		flow_stats_update(&nft_merge->tc_m_parent->pre_ct_parent->stats,
				  priv->stats[ctx_id].bytes,
				  priv->stats[ctx_id].pkts,
				  0, priv->stats[ctx_id].used,
				  FLOW_ACTION_HW_STATS_DELAYED);
		/* Update post_ct cached stats */
		flow_stats_update(&nft_merge->tc_m_parent->post_ct_parent->stats,
				  priv->stats[ctx_id].bytes,
				  priv->stats[ctx_id].pkts,
				  0, priv->stats[ctx_id].used,
				  FLOW_ACTION_HW_STATS_DELAYED);
	}
	/* Reset stats from the nfp */
	priv->stats[ctx_id].pkts = 0;
	priv->stats[ctx_id].bytes = 0;
}

int nfp_fl_ct_stats(struct flow_cls_offload *flow,
		    struct nfp_fl_ct_map_entry *ct_map_ent)
{
	struct nfp_fl_ct_flow_entry *ct_entry = ct_map_ent->ct_entry;
	struct nfp_fl_nft_tc_merge *nft_merge, *nft_m_tmp;
	struct nfp_fl_ct_tc_merge *tc_merge, *tc_m_tmp;

	u64 pkts = 0, bytes = 0, used = 0;
	u64 m_pkts, m_bytes, m_used;

	spin_lock_bh(&ct_entry->zt->priv->stats_lock);

	if (ct_entry->type == CT_TYPE_PRE_CT) {
		/* Iterate tc_merge entries associated with this flow */
		list_for_each_entry_safe(tc_merge, tc_m_tmp, &ct_entry->children,
					 pre_ct_list) {
			m_pkts = 0;
			m_bytes = 0;
			m_used = 0;
			/* Iterate nft_merge entries associated with this tc_merge flow */
			list_for_each_entry_safe(nft_merge, nft_m_tmp, &tc_merge->children,
						 tc_merge_list) {
				nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_PRE_CT,
						    &m_pkts, &m_bytes, &m_used);
			}
			pkts += m_pkts;
			bytes += m_bytes;
			used = max_t(u64, used, m_used);
			/* Update post_ct partner */
			flow_stats_update(&tc_merge->post_ct_parent->stats,
					  m_bytes, m_pkts, 0, m_used,
					  FLOW_ACTION_HW_STATS_DELAYED);
		}
	} else if (ct_entry->type == CT_TYPE_POST_CT) {
		/* Iterate tc_merge entries associated with this flow */
		list_for_each_entry_safe(tc_merge, tc_m_tmp, &ct_entry->children,
					 post_ct_list) {
			m_pkts = 0;
			m_bytes = 0;
			m_used = 0;
			/* Iterate nft_merge entries associated with this tc_merge flow */
			list_for_each_entry_safe(nft_merge, nft_m_tmp, &tc_merge->children,
						 tc_merge_list) {
				nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_POST_CT,
						    &m_pkts, &m_bytes, &m_used);
			}
			pkts += m_pkts;
			bytes += m_bytes;
			used = max_t(u64, used, m_used);
			/* Update pre_ct partner */
			flow_stats_update(&tc_merge->pre_ct_parent->stats,
					  m_bytes, m_pkts, 0, m_used,
					  FLOW_ACTION_HW_STATS_DELAYED);
		}
	} else  {
		/* Iterate nft_merge entries associated with this nft flow */
		list_for_each_entry_safe(nft_merge, nft_m_tmp, &ct_entry->children,
					 nft_flow_list) {
			nfp_fl_ct_sub_stats(nft_merge, CT_TYPE_NFT,
					    &pkts, &bytes, &used);
		}
	}

	/* Add stats from this request to stats potentially cached by
	 * previous requests.
	 */
	flow_stats_update(&ct_entry->stats, bytes, pkts, 0, used,
			  FLOW_ACTION_HW_STATS_DELAYED);
	/* Finally update the flow stats from the original stats request */
	flow_stats_update(&flow->stats, ct_entry->stats.bytes,
			  ct_entry->stats.pkts, 0,
			  ct_entry->stats.lastused,
			  FLOW_ACTION_HW_STATS_DELAYED);
	/* Stats has been synced to original flow, can now clear
	 * the cache.
	 */
	ct_entry->stats.pkts = 0;
	ct_entry->stats.bytes = 0;
	spin_unlock_bh(&ct_entry->zt->priv->stats_lock);

	return 0;
}

static int
nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offload *flow)
{
	struct nfp_fl_ct_map_entry *ct_map_ent;
	struct nfp_fl_ct_flow_entry *ct_entry;
	struct netlink_ext_ack *extack = NULL;

	extack = flow->common.extack;
	switch (flow->command) {
	case FLOW_CLS_REPLACE:
		/* Netfilter can request offload multiple times for the same
		 * flow - protect against adding duplicates.
		 */
		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
						    nfp_ct_map_params);
		if (!ct_map_ent) {
			ct_entry = nfp_fl_ct_add_flow(zt, NULL, flow, true, extack);
			if (IS_ERR(ct_entry))
				return PTR_ERR(ct_entry);
			ct_entry->type = CT_TYPE_NFT;
			list_add(&ct_entry->list_node, &zt->nft_flows_list);
			zt->nft_flows_count++;
			nfp_ct_merge_nft_with_tc(ct_entry, zt);
		}
		return 0;
	case FLOW_CLS_DESTROY:
		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
						    nfp_ct_map_params);
		return nfp_fl_ct_del_flow(ct_map_ent);
	case FLOW_CLS_STATS:
		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie,
						    nfp_ct_map_params);
		if (ct_map_ent)
			return nfp_fl_ct_stats(flow, ct_map_ent);
		break;
	default:
		break;
	}
	return -EINVAL;
}

int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data, void *cb_priv)
{
	struct flow_cls_offload *flow = type_data;
	struct nfp_fl_ct_zone_entry *zt = cb_priv;
	int err = -EOPNOTSUPP;

	switch (type) {
	case TC_SETUP_CLSFLOWER:
		while (!mutex_trylock(&zt->priv->nfp_fl_lock)) {
			if (!zt->nft) /* avoid deadlock */
				return err;
			msleep(20);
		}
		err = nfp_fl_ct_offload_nft_flow(zt, flow);
		mutex_unlock(&zt->priv->nfp_fl_lock);
		break;
	default:
		return -EOPNOTSUPP;
	}
	return err;
}

static void
nfp_fl_ct_clean_nft_entries(struct nfp_fl_ct_zone_entry *zt)
{
	struct nfp_fl_ct_flow_entry *nft_entry, *ct_tmp;
	struct nfp_fl_ct_map_entry *ct_map_ent;

	list_for_each_entry_safe(nft_entry, ct_tmp, &zt->nft_flows_list,
				 list_node) {
		ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table,
						    &nft_entry->cookie,
						    nfp_ct_map_params);
		nfp_fl_ct_del_flow(ct_map_ent);
	}
}

int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent)
{
	struct nfp_fl_ct_flow_entry *ct_entry;
	struct nfp_fl_ct_zone_entry *zt;
	struct rhashtable *m_table;
	struct nf_flowtable *nft;

	if (!ct_map_ent)
		return -ENOENT;

	zt = ct_map_ent->ct_entry->zt;
	ct_entry = ct_map_ent->ct_entry;
	m_table = &zt->priv->ct_map_table;

	switch (ct_entry->type) {
	case CT_TYPE_PRE_CT:
		zt->pre_ct_count--;
		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
				       nfp_ct_map_params);
		nfp_fl_ct_clean_flow_entry(ct_entry);
		kfree(ct_map_ent);

		if (!zt->pre_ct_count && zt->nft) {
			nft = zt->nft;
			zt->nft = NULL; /* avoid deadlock */
			nf_flow_table_offload_del_cb(nft,
						     nfp_fl_ct_handle_nft_flow,
						     zt);
			nfp_fl_ct_clean_nft_entries(zt);
		}
		break;
	case CT_TYPE_POST_CT:
		zt->post_ct_count--;
		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
				       nfp_ct_map_params);
		nfp_fl_ct_clean_flow_entry(ct_entry);
		kfree(ct_map_ent);
		break;
	case CT_TYPE_NFT:
		zt->nft_flows_count--;
		rhashtable_remove_fast(m_table, &ct_map_ent->hash_node,
				       nfp_ct_map_params);
		nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry);
		kfree(ct_map_ent);
		break;
	default:
		break;
	}

	return 0;
}