aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
blob: 25f51f80a9b468e4ab3d2c3f15d9816434ebc7ca (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
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* Copyright (c) 2019 Mellanox Technologies. */

#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_acct.h>
#include <uapi/linux/tc_act/tc_pedit.h>
#include <net/tc_act/tc_ct.h>
#include <net/flow_offload.h>
#include <net/netfilter/nf_flow_table.h>
#include <linux/workqueue.h>
#include <linux/refcount.h>
#include <linux/xarray.h>
#include <linux/if_macvlan.h>
#include <linux/debugfs.h>

#include "lib/fs_chains.h"
#include "en/tc_ct.h"
#include "en/tc/ct_fs.h"
#include "en/tc_priv.h"
#include "en/mod_hdr.h"
#include "en/mapping.h"
#include "en/tc/post_act.h"
#include "en.h"
#include "en_tc.h"
#include "en_rep.h"
#include "fs_core.h"

#define MLX5_CT_STATE_ESTABLISHED_BIT BIT(1)
#define MLX5_CT_STATE_TRK_BIT BIT(2)
#define MLX5_CT_STATE_NAT_BIT BIT(3)
#define MLX5_CT_STATE_REPLY_BIT BIT(4)
#define MLX5_CT_STATE_RELATED_BIT BIT(5)
#define MLX5_CT_STATE_INVALID_BIT BIT(6)

#define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen)
#define MLX5_CT_LABELS_MASK GENMASK(MLX5_CT_LABELS_BITS - 1, 0)

/* Statically allocate modify actions for
 * ipv6 and port nat (5) + tuple fields (4) + nic mode zone restore (1) = 10.
 * This will be increased dynamically if needed (for the ipv6 snat + dnat).
 */
#define MLX5_CT_MIN_MOD_ACTS 10

#define ct_dbg(fmt, args...)\
	netdev_dbg(ct_priv->netdev, "ct_debug: " fmt "\n", ##args)

struct mlx5_tc_ct_debugfs {
	struct {
		atomic_t offloaded;
		atomic_t rx_dropped;
	} stats;

	struct dentry *root;
};

struct mlx5_tc_ct_priv {
	struct mlx5_core_dev *dev;
	const struct net_device *netdev;
	struct mod_hdr_tbl *mod_hdr_tbl;
	struct xarray tuple_ids;
	struct rhashtable zone_ht;
	struct rhashtable ct_tuples_ht;
	struct rhashtable ct_tuples_nat_ht;
	struct mlx5_flow_table *ct;
	struct mlx5_flow_table *ct_nat;
	struct mlx5e_post_act *post_act;
	struct mutex control_lock; /* guards parallel adds/dels */
	struct mapping_ctx *zone_mapping;
	struct mapping_ctx *labels_mapping;
	enum mlx5_flow_namespace_type ns_type;
	struct mlx5_fs_chains *chains;
	struct mlx5_ct_fs *fs;
	struct mlx5_ct_fs_ops *fs_ops;
	spinlock_t ht_lock; /* protects ft entries */

	struct mlx5_tc_ct_debugfs debugfs;
};

struct mlx5_ct_flow {
	struct mlx5_flow_attr *pre_ct_attr;
	struct mlx5_flow_handle *pre_ct_rule;
	struct mlx5_ct_ft *ft;
	u32 chain_mapping;
};

struct mlx5_ct_zone_rule {
	struct mlx5_ct_fs_rule *rule;
	struct mlx5e_mod_hdr_handle *mh;
	struct mlx5_flow_attr *attr;
	bool nat;
};

struct mlx5_tc_ct_pre {
	struct mlx5_flow_table *ft;
	struct mlx5_flow_group *flow_grp;
	struct mlx5_flow_group *miss_grp;
	struct mlx5_flow_handle *flow_rule;
	struct mlx5_flow_handle *miss_rule;
	struct mlx5_modify_hdr *modify_hdr;
};

struct mlx5_ct_ft {
	struct rhash_head node;
	u16 zone;
	u32 zone_restore_id;
	refcount_t refcount;
	struct nf_flowtable *nf_ft;
	struct mlx5_tc_ct_priv *ct_priv;
	struct rhashtable ct_entries_ht;
	struct mlx5_tc_ct_pre pre_ct;
	struct mlx5_tc_ct_pre pre_ct_nat;
};

struct mlx5_ct_tuple {
	u16 addr_type;
	__be16 n_proto;
	u8 ip_proto;
	struct {
		union {
			__be32 src_v4;
			struct in6_addr src_v6;
		};
		union {
			__be32 dst_v4;
			struct in6_addr dst_v6;
		};
	} ip;
	struct {
		__be16 src;
		__be16 dst;
	} port;

	u16 zone;
};

struct mlx5_ct_counter {
	struct mlx5_fc *counter;
	refcount_t refcount;
	bool is_shared;
};

enum {
	MLX5_CT_ENTRY_FLAG_VALID,
};

struct mlx5_ct_entry {
	struct rhash_head node;
	struct rhash_head tuple_node;
	struct rhash_head tuple_nat_node;
	struct mlx5_ct_counter *counter;
	unsigned long cookie;
	unsigned long restore_cookie;
	struct mlx5_ct_tuple tuple;
	struct mlx5_ct_tuple tuple_nat;
	struct mlx5_ct_zone_rule zone_rules[2];

	struct mlx5_tc_ct_priv *ct_priv;
	struct work_struct work;

	refcount_t refcnt;
	unsigned long flags;
};

static void
mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
				 struct mlx5_flow_attr *attr,
				 struct mlx5e_mod_hdr_handle *mh);

static const struct rhashtable_params cts_ht_params = {
	.head_offset = offsetof(struct mlx5_ct_entry, node),
	.key_offset = offsetof(struct mlx5_ct_entry, cookie),
	.key_len = sizeof(((struct mlx5_ct_entry *)0)->cookie),
	.automatic_shrinking = true,
	.min_size = 16 * 1024,
};

static const struct rhashtable_params zone_params = {
	.head_offset = offsetof(struct mlx5_ct_ft, node),
	.key_offset = offsetof(struct mlx5_ct_ft, zone),
	.key_len = sizeof(((struct mlx5_ct_ft *)0)->zone),
	.automatic_shrinking = true,
};

static const struct rhashtable_params tuples_ht_params = {
	.head_offset = offsetof(struct mlx5_ct_entry, tuple_node),
	.key_offset = offsetof(struct mlx5_ct_entry, tuple),
	.key_len = sizeof(((struct mlx5_ct_entry *)0)->tuple),
	.automatic_shrinking = true,
	.min_size = 16 * 1024,
};

static const struct rhashtable_params tuples_nat_ht_params = {
	.head_offset = offsetof(struct mlx5_ct_entry, tuple_nat_node),
	.key_offset = offsetof(struct mlx5_ct_entry, tuple_nat),
	.key_len = sizeof(((struct mlx5_ct_entry *)0)->tuple_nat),
	.automatic_shrinking = true,
	.min_size = 16 * 1024,
};

static bool
mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry)
{
	return !!(entry->tuple_nat_node.next);
}

static int
mlx5_get_label_mapping(struct mlx5_tc_ct_priv *ct_priv,
		       u32 *labels, u32 *id)
{
	if (!memchr_inv(labels, 0, sizeof(u32) * 4)) {
		*id = 0;
		return 0;
	}

	if (mapping_add(ct_priv->labels_mapping, labels, id))
		return -EOPNOTSUPP;

	return 0;
}

static void
mlx5_put_label_mapping(struct mlx5_tc_ct_priv *ct_priv, u32 id)
{
	if (id)
		mapping_remove(ct_priv->labels_mapping, id);
}

static int
mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule)
{
	struct flow_match_control control;
	struct flow_match_basic basic;

	flow_rule_match_basic(rule, &basic);
	flow_rule_match_control(rule, &control);

	tuple->n_proto = basic.key->n_proto;
	tuple->ip_proto = basic.key->ip_proto;
	tuple->addr_type = control.key->addr_type;

	if (tuple->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
		struct flow_match_ipv4_addrs match;

		flow_rule_match_ipv4_addrs(rule, &match);
		tuple->ip.src_v4 = match.key->src;
		tuple->ip.dst_v4 = match.key->dst;
	} else if (tuple->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
		struct flow_match_ipv6_addrs match;

		flow_rule_match_ipv6_addrs(rule, &match);
		tuple->ip.src_v6 = match.key->src;
		tuple->ip.dst_v6 = match.key->dst;
	} else {
		return -EOPNOTSUPP;
	}

	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
		struct flow_match_ports match;

		flow_rule_match_ports(rule, &match);
		switch (tuple->ip_proto) {
		case IPPROTO_TCP:
		case IPPROTO_UDP:
			tuple->port.src = match.key->src;
			tuple->port.dst = match.key->dst;
			break;
		default:
			return -EOPNOTSUPP;
		}
	} else {
		if (tuple->ip_proto != IPPROTO_GRE)
			return -EOPNOTSUPP;
	}

	return 0;
}

static int
mlx5_tc_ct_rule_to_tuple_nat(struct mlx5_ct_tuple *tuple,
			     struct flow_rule *rule)
{
	struct flow_action *flow_action = &rule->action;
	struct flow_action_entry *act;
	u32 offset, val, ip6_offset;
	int i;

	flow_action_for_each(i, act, flow_action) {
		if (act->id != FLOW_ACTION_MANGLE)
			continue;

		offset = act->mangle.offset;
		val = act->mangle.val;
		switch (act->mangle.htype) {
		case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
			if (offset == offsetof(struct iphdr, saddr))
				tuple->ip.src_v4 = cpu_to_be32(val);
			else if (offset == offsetof(struct iphdr, daddr))
				tuple->ip.dst_v4 = cpu_to_be32(val);
			else
				return -EOPNOTSUPP;
			break;

		case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
			ip6_offset = (offset - offsetof(struct ipv6hdr, saddr));
			ip6_offset /= 4;
			if (ip6_offset < 4)
				tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val);
			else if (ip6_offset < 8)
				tuple->ip.dst_v6.s6_addr32[ip6_offset - 4] = cpu_to_be32(val);
			else
				return -EOPNOTSUPP;
			break;

		case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
			if (offset == offsetof(struct tcphdr, source))
				tuple->port.src = cpu_to_be16(val);
			else if (offset == offsetof(struct tcphdr, dest))
				tuple->port.dst = cpu_to_be16(val);
			else
				return -EOPNOTSUPP;
			break;

		case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
			if (offset == offsetof(struct udphdr, source))
				tuple->port.src = cpu_to_be16(val);
			else if (offset == offsetof(struct udphdr, dest))
				tuple->port.dst = cpu_to_be16(val);
			else
				return -EOPNOTSUPP;
			break;

		default:
			return -EOPNOTSUPP;
		}
	}

	return 0;
}

static int
mlx5_tc_ct_get_flow_source_match(struct mlx5_tc_ct_priv *ct_priv,
				 struct net_device *ndev)
{
	struct mlx5e_priv *other_priv = netdev_priv(ndev);
	struct mlx5_core_dev *mdev = ct_priv->dev;
	bool vf_rep, uplink_rep;

	vf_rep = mlx5e_eswitch_vf_rep(ndev) && mlx5_same_hw_devs(mdev, other_priv->mdev);
	uplink_rep = mlx5e_eswitch_uplink_rep(ndev) && mlx5_same_hw_devs(mdev, other_priv->mdev);

	if (vf_rep)
		return MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
	if (uplink_rep)
		return MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
	if (is_vlan_dev(ndev))
		return mlx5_tc_ct_get_flow_source_match(ct_priv, vlan_dev_real_dev(ndev));
	if (netif_is_macvlan(ndev))
		return mlx5_tc_ct_get_flow_source_match(ct_priv, macvlan_dev_real_dev(ndev));
	if (mlx5e_get_tc_tun(ndev) || netif_is_lag_master(ndev))
		return MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;

	return MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT;
}

static int
mlx5_tc_ct_set_tuple_match(struct mlx5_tc_ct_priv *ct_priv,
			   struct mlx5_flow_spec *spec,
			   struct flow_rule *rule)
{
	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
				       outer_headers);
	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
				       outer_headers);
	u16 addr_type = 0;
	u8 ip_proto = 0;

	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
		struct flow_match_basic match;

		flow_rule_match_basic(rule, &match);

		mlx5e_tc_set_ethertype(ct_priv->dev, &match, true, headers_c, headers_v);
		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
			 match.mask->ip_proto);
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
			 match.key->ip_proto);

		ip_proto = match.key->ip_proto;
	}

	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
		struct flow_match_control match;

		flow_rule_match_control(rule, &match);
		addr_type = match.key->addr_type;
	}

	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
		struct flow_match_ipv4_addrs match;

		flow_rule_match_ipv4_addrs(rule, &match);
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
		       &match.mask->src, sizeof(match.mask->src));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
		       &match.key->src, sizeof(match.key->src));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
		       &match.mask->dst, sizeof(match.mask->dst));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
		       &match.key->dst, sizeof(match.key->dst));
	}

	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
		struct flow_match_ipv6_addrs match;

		flow_rule_match_ipv6_addrs(rule, &match);
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
		       &match.mask->src, sizeof(match.mask->src));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
		       &match.key->src, sizeof(match.key->src));

		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
		       &match.mask->dst, sizeof(match.mask->dst));
		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
		       &match.key->dst, sizeof(match.key->dst));
	}

	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
		struct flow_match_ports match;

		flow_rule_match_ports(rule, &match);
		switch (ip_proto) {
		case IPPROTO_TCP:
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 tcp_sport, ntohs(match.mask->src));
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 tcp_sport, ntohs(match.key->src));

			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 tcp_dport, ntohs(match.mask->dst));
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 tcp_dport, ntohs(match.key->dst));
			break;

		case IPPROTO_UDP:
			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 udp_sport, ntohs(match.mask->src));
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 udp_sport, ntohs(match.key->src));

			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
				 udp_dport, ntohs(match.mask->dst));
			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
				 udp_dport, ntohs(match.key->dst));
			break;
		default:
			break;
		}
	}

	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
		struct flow_match_tcp match;

		flow_rule_match_tcp(rule, &match);
		MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags,
			 ntohs(match.mask->flags));
		MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags,
			 ntohs(match.key->flags));
	}

	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) {
			struct net_device *dev;

			dev = dev_get_by_index(&init_net, match.key->ingress_ifindex);
			if (dev && MLX5_CAP_ESW_FLOWTABLE(ct_priv->dev, flow_source))
				spec->flow_context.flow_source =
					mlx5_tc_ct_get_flow_source_match(ct_priv, dev);

			dev_put(dev);
		}
	}

	return 0;
}

static void
mlx5_tc_ct_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
{
	if (entry->counter->is_shared &&
	    !refcount_dec_and_test(&entry->counter->refcount))
		return;

	mlx5_fc_destroy(ct_priv->dev, entry->counter->counter);
	kfree(entry->counter);
}

static void
mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv,
			  struct mlx5_ct_entry *entry,
			  bool nat)
{
	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
	struct mlx5_flow_attr *attr = zone_rule->attr;

	ct_dbg("Deleting ct entry rule in zone %d", entry->tuple.zone);

	ct_priv->fs_ops->ct_rule_del(ct_priv->fs, zone_rule->rule);
	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh);
	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
	kfree(attr);
}

static void
mlx5_tc_ct_entry_del_rules(struct mlx5_tc_ct_priv *ct_priv,
			   struct mlx5_ct_entry *entry)
{
	mlx5_tc_ct_entry_del_rule(ct_priv, entry, true);
	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);

	atomic_dec(&ct_priv->debugfs.stats.offloaded);
}

static struct flow_action_entry *
mlx5_tc_ct_get_ct_metadata_action(struct flow_rule *flow_rule)
{
	struct flow_action *flow_action = &flow_rule->action;
	struct flow_action_entry *act;
	int i;

	flow_action_for_each(i, act, flow_action) {
		if (act->id == FLOW_ACTION_CT_METADATA)
			return act;
	}

	return NULL;
}

static int
mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv,
			       struct mlx5e_tc_mod_hdr_acts *mod_acts,
			       u8 ct_state,
			       u32 mark,
			       u32 labels_id,
			       u8 zone_restore_id)
{
	enum mlx5_flow_namespace_type ns = ct_priv->ns_type;
	struct mlx5_core_dev *dev = ct_priv->dev;
	int err;

	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
					CTSTATE_TO_REG, ct_state);
	if (err)
		return err;

	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
					MARK_TO_REG, mark);
	if (err)
		return err;

	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
					LABELS_TO_REG, labels_id);
	if (err)
		return err;

	err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
					ZONE_RESTORE_TO_REG, zone_restore_id);
	if (err)
		return err;

	/* Make another copy of zone id in reg_b for
	 * NIC rx flows since we don't copy reg_c1 to
	 * reg_b upon miss.
	 */
	if (ns != MLX5_FLOW_NAMESPACE_FDB) {
		err = mlx5e_tc_match_to_reg_set(dev, mod_acts, ns,
						NIC_ZONE_RESTORE_TO_REG, zone_restore_id);
		if (err)
			return err;
	}
	return 0;
}

int mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv,
				 struct mlx5e_tc_mod_hdr_acts *mod_acts)
{
		return mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0);
}

static int
mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act,
				   char *modact)
{
	u32 offset = act->mangle.offset, field;

	switch (act->mangle.htype) {
	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
		MLX5_SET(set_action_in, modact, length, 0);
		if (offset == offsetof(struct iphdr, saddr))
			field = MLX5_ACTION_IN_FIELD_OUT_SIPV4;
		else if (offset == offsetof(struct iphdr, daddr))
			field = MLX5_ACTION_IN_FIELD_OUT_DIPV4;
		else
			return -EOPNOTSUPP;
		break;

	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
		MLX5_SET(set_action_in, modact, length, 0);
		if (offset == offsetof(struct ipv6hdr, saddr) + 12)
			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0;
		else if (offset == offsetof(struct ipv6hdr, saddr) + 8)
			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64;
		else if (offset == offsetof(struct ipv6hdr, saddr))
			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96;
		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0;
		else if (offset == offsetof(struct ipv6hdr, daddr) + 8)
			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64;
		else if (offset == offsetof(struct ipv6hdr, daddr))
			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96;
		else
			return -EOPNOTSUPP;
		break;

	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
		MLX5_SET(set_action_in, modact, length, 16);
		if (offset == offsetof(struct tcphdr, source))
			field = MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT;
		else if (offset == offsetof(struct tcphdr, dest))
			field = MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT;
		else
			return -EOPNOTSUPP;
		break;

	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
		MLX5_SET(set_action_in, modact, length, 16);
		if (offset == offsetof(struct udphdr, source))
			field = MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT;
		else if (offset == offsetof(struct udphdr, dest))
			field = MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT;
		else
			return -EOPNOTSUPP;
		break;

	default:
		return -EOPNOTSUPP;
	}

	MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET);
	MLX5_SET(set_action_in, modact, offset, 0);
	MLX5_SET(set_action_in, modact, field, field);
	MLX5_SET(set_action_in, modact, data, act->mangle.val);

	return 0;
}

static int
mlx5_tc_ct_entry_create_nat(struct mlx5_tc_ct_priv *ct_priv,
			    struct flow_rule *flow_rule,
			    struct mlx5e_tc_mod_hdr_acts *mod_acts)
{
	struct flow_action *flow_action = &flow_rule->action;
	struct mlx5_core_dev *mdev = ct_priv->dev;
	struct flow_action_entry *act;
	char *modact;
	int err, i;

	flow_action_for_each(i, act, flow_action) {
		switch (act->id) {
		case FLOW_ACTION_MANGLE: {
			modact = mlx5e_mod_hdr_alloc(mdev, ct_priv->ns_type, mod_acts);
			if (IS_ERR(modact))
				return PTR_ERR(modact);

			err = mlx5_tc_ct_parse_mangle_to_mod_act(act, modact);
			if (err)
				return err;

			mod_acts->num_actions++;
		}
		break;

		case FLOW_ACTION_CT_METADATA:
			/* Handled earlier */
			continue;
		default:
			return -EOPNOTSUPP;
		}
	}

	return 0;
}

static int
mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
				struct mlx5_flow_attr *attr,
				struct flow_rule *flow_rule,
				struct mlx5e_mod_hdr_handle **mh,
				u8 zone_restore_id, bool nat_table, bool has_nat)
{
	DECLARE_MOD_HDR_ACTS_ACTIONS(actions_arr, MLX5_CT_MIN_MOD_ACTS);
	DECLARE_MOD_HDR_ACTS(mod_acts, actions_arr);
	struct flow_action_entry *meta;
	u16 ct_state = 0;
	int err;

	meta = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
	if (!meta)
		return -EOPNOTSUPP;

	err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels,
				     &attr->ct_attr.ct_labels_id);
	if (err)
		return -EOPNOTSUPP;
	if (nat_table) {
		if (has_nat) {
			err = mlx5_tc_ct_entry_create_nat(ct_priv, flow_rule, &mod_acts);
			if (err)
				goto err_mapping;
		}

		ct_state |= MLX5_CT_STATE_NAT_BIT;
	}

	ct_state |= MLX5_CT_STATE_ESTABLISHED_BIT | MLX5_CT_STATE_TRK_BIT;
	ct_state |= meta->ct_metadata.orig_dir ? 0 : MLX5_CT_STATE_REPLY_BIT;
	err = mlx5_tc_ct_entry_set_registers(ct_priv, &mod_acts,
					     ct_state,
					     meta->ct_metadata.mark,
					     attr->ct_attr.ct_labels_id,
					     zone_restore_id);
	if (err)
		goto err_mapping;

	if (nat_table && has_nat) {
		attr->modify_hdr = mlx5_modify_header_alloc(ct_priv->dev, ct_priv->ns_type,
							    mod_acts.num_actions,
							    mod_acts.actions);
		if (IS_ERR(attr->modify_hdr)) {
			err = PTR_ERR(attr->modify_hdr);
			goto err_mapping;
		}

		*mh = NULL;
	} else {
		*mh = mlx5e_mod_hdr_attach(ct_priv->dev,
					   ct_priv->mod_hdr_tbl,
					   ct_priv->ns_type,
					   &mod_acts);
		if (IS_ERR(*mh)) {
			err = PTR_ERR(*mh);
			goto err_mapping;
		}
		attr->modify_hdr = mlx5e_mod_hdr_get(*mh);
	}

	mlx5e_mod_hdr_dealloc(&mod_acts);
	return 0;

err_mapping:
	mlx5e_mod_hdr_dealloc(&mod_acts);
	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
	return err;
}

static void
mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
				 struct mlx5_flow_attr *attr,
				 struct mlx5e_mod_hdr_handle *mh)
{
	if (mh)
		mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, mh);
	else
		mlx5_modify_header_dealloc(ct_priv->dev, attr->modify_hdr);
}

static int
mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
			  struct flow_rule *flow_rule,
			  struct mlx5_ct_entry *entry,
			  bool nat, u8 zone_restore_id)
{
	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
	struct mlx5_flow_spec *spec = NULL;
	struct mlx5_flow_attr *attr;
	int err;

	zone_rule->nat = nat;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec)
		return -ENOMEM;

	attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
	if (!attr) {
		err = -ENOMEM;
		goto err_attr;
	}

	err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule,
					      &zone_rule->mh,
					      zone_restore_id,
					      nat,
					      mlx5_tc_ct_entry_has_nat(entry));
	if (err) {
		ct_dbg("Failed to create ct entry mod hdr");
		goto err_mod_hdr;
	}

	attr->action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
		       MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
		       MLX5_FLOW_CONTEXT_ACTION_COUNT;
	attr->dest_chain = 0;
	attr->dest_ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act);
	attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
	if (entry->tuple.ip_proto == IPPROTO_TCP ||
	    entry->tuple.ip_proto == IPPROTO_UDP)
		attr->outer_match_level = MLX5_MATCH_L4;
	else
		attr->outer_match_level = MLX5_MATCH_L3;
	attr->counter = entry->counter->counter;
	attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT;
	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB)
		attr->esw_attr->in_mdev = priv->mdev;

	mlx5_tc_ct_set_tuple_match(ct_priv, spec, flow_rule);
	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, entry->tuple.zone, MLX5_CT_ZONE_MASK);

	zone_rule->rule = ct_priv->fs_ops->ct_rule_add(ct_priv->fs, spec, attr, flow_rule);
	if (IS_ERR(zone_rule->rule)) {
		err = PTR_ERR(zone_rule->rule);
		ct_dbg("Failed to add ct entry rule, nat: %d", nat);
		goto err_rule;
	}

	zone_rule->attr = attr;

	kvfree(spec);
	ct_dbg("Offloaded ct entry rule in zone %d", entry->tuple.zone);

	return 0;

err_rule:
	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh);
	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
err_mod_hdr:
	kfree(attr);
err_attr:
	kvfree(spec);
	return err;
}

static bool
mlx5_tc_ct_entry_valid(struct mlx5_ct_entry *entry)
{
	return test_bit(MLX5_CT_ENTRY_FLAG_VALID, &entry->flags);
}

static struct mlx5_ct_entry *
mlx5_tc_ct_entry_get(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_tuple *tuple)
{
	struct mlx5_ct_entry *entry;

	entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, tuple,
				       tuples_ht_params);
	if (entry && mlx5_tc_ct_entry_valid(entry) &&
	    refcount_inc_not_zero(&entry->refcnt)) {
		return entry;
	} else if (!entry) {
		entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_nat_ht,
					       tuple, tuples_nat_ht_params);
		if (entry && mlx5_tc_ct_entry_valid(entry) &&
		    refcount_inc_not_zero(&entry->refcnt))
			return entry;
	}

	return entry ? ERR_PTR(-EINVAL) : NULL;
}

static void mlx5_tc_ct_entry_remove_from_tuples(struct mlx5_ct_entry *entry)
{
	struct mlx5_tc_ct_priv *ct_priv = entry->ct_priv;

	rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht,
			       &entry->tuple_nat_node,
			       tuples_nat_ht_params);
	rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
			       tuples_ht_params);
}

static void mlx5_tc_ct_entry_del(struct mlx5_ct_entry *entry)
{
	struct mlx5_tc_ct_priv *ct_priv = entry->ct_priv;

	mlx5_tc_ct_entry_del_rules(ct_priv, entry);

	spin_lock_bh(&ct_priv->ht_lock);
	mlx5_tc_ct_entry_remove_from_tuples(entry);
	spin_unlock_bh(&ct_priv->ht_lock);

	mlx5_tc_ct_counter_put(ct_priv, entry);
	kfree(entry);
}

static void
mlx5_tc_ct_entry_put(struct mlx5_ct_entry *entry)
{
	if (!refcount_dec_and_test(&entry->refcnt))
		return;

	mlx5_tc_ct_entry_del(entry);
}

static void mlx5_tc_ct_entry_del_work(struct work_struct *work)
{
	struct mlx5_ct_entry *entry = container_of(work, struct mlx5_ct_entry, work);

	mlx5_tc_ct_entry_del(entry);
}

static void
__mlx5_tc_ct_entry_put(struct mlx5_ct_entry *entry)
{
	struct mlx5e_priv *priv;

	if (!refcount_dec_and_test(&entry->refcnt))
		return;

	priv = netdev_priv(entry->ct_priv->netdev);
	INIT_WORK(&entry->work, mlx5_tc_ct_entry_del_work);
	queue_work(priv->wq, &entry->work);
}

static struct mlx5_ct_counter *
mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
{
	struct mlx5_ct_counter *counter;
	int ret;

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

	counter->is_shared = false;
	counter->counter = mlx5_fc_create_ex(ct_priv->dev, true);
	if (IS_ERR(counter->counter)) {
		ct_dbg("Failed to create counter for ct entry");
		ret = PTR_ERR(counter->counter);
		kfree(counter);
		return ERR_PTR(ret);
	}

	return counter;
}

static struct mlx5_ct_counter *
mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
			      struct mlx5_ct_entry *entry)
{
	struct mlx5_ct_tuple rev_tuple = entry->tuple;
	struct mlx5_ct_counter *shared_counter;
	struct mlx5_ct_entry *rev_entry;

	/* get the reversed tuple */
	swap(rev_tuple.port.src, rev_tuple.port.dst);

	if (rev_tuple.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
		__be32 tmp_addr = rev_tuple.ip.src_v4;

		rev_tuple.ip.src_v4 = rev_tuple.ip.dst_v4;
		rev_tuple.ip.dst_v4 = tmp_addr;
	} else if (rev_tuple.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
		struct in6_addr tmp_addr = rev_tuple.ip.src_v6;

		rev_tuple.ip.src_v6 = rev_tuple.ip.dst_v6;
		rev_tuple.ip.dst_v6 = tmp_addr;
	} else {
		return ERR_PTR(-EOPNOTSUPP);
	}

	/* Use the same counter as the reverse direction */
	spin_lock_bh(&ct_priv->ht_lock);
	rev_entry = mlx5_tc_ct_entry_get(ct_priv, &rev_tuple);

	if (IS_ERR(rev_entry)) {
		spin_unlock_bh(&ct_priv->ht_lock);
		goto create_counter;
	}

	if (rev_entry && refcount_inc_not_zero(&rev_entry->counter->refcount)) {
		ct_dbg("Using shared counter entry=0x%p rev=0x%p", entry, rev_entry);
		shared_counter = rev_entry->counter;
		spin_unlock_bh(&ct_priv->ht_lock);

		mlx5_tc_ct_entry_put(rev_entry);
		return shared_counter;
	}

	spin_unlock_bh(&ct_priv->ht_lock);

create_counter:

	shared_counter = mlx5_tc_ct_counter_create(ct_priv);
	if (IS_ERR(shared_counter))
		return shared_counter;

	shared_counter->is_shared = true;
	refcount_set(&shared_counter->refcount, 1);
	return shared_counter;
}

static int
mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv,
			   struct flow_rule *flow_rule,
			   struct mlx5_ct_entry *entry,
			   u8 zone_restore_id)
{
	int err;

	if (nf_ct_acct_enabled(dev_net(ct_priv->netdev)))
		entry->counter = mlx5_tc_ct_counter_create(ct_priv);
	else
		entry->counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);

	if (IS_ERR(entry->counter)) {
		err = PTR_ERR(entry->counter);
		return err;
	}

	err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, false,
					zone_restore_id);
	if (err)
		goto err_orig;

	err = mlx5_tc_ct_entry_add_rule(ct_priv, flow_rule, entry, true,
					zone_restore_id);
	if (err)
		goto err_nat;

	atomic_inc(&ct_priv->debugfs.stats.offloaded);
	return 0;

err_nat:
	mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
err_orig:
	mlx5_tc_ct_counter_put(ct_priv, entry);
	return err;
}

static int
mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
				  struct flow_cls_offload *flow)
{
	struct flow_rule *flow_rule = flow_cls_offload_flow_rule(flow);
	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
	struct flow_action_entry *meta_action;
	unsigned long cookie = flow->cookie;
	struct mlx5_ct_entry *entry;
	int err;

	meta_action = mlx5_tc_ct_get_ct_metadata_action(flow_rule);
	if (!meta_action)
		return -EOPNOTSUPP;

	spin_lock_bh(&ct_priv->ht_lock);
	entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params);
	if (entry && refcount_inc_not_zero(&entry->refcnt)) {
		spin_unlock_bh(&ct_priv->ht_lock);
		mlx5_tc_ct_entry_put(entry);
		return -EEXIST;
	}
	spin_unlock_bh(&ct_priv->ht_lock);

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

	entry->tuple.zone = ft->zone;
	entry->cookie = flow->cookie;
	entry->restore_cookie = meta_action->ct_metadata.cookie;
	refcount_set(&entry->refcnt, 2);
	entry->ct_priv = ct_priv;

	err = mlx5_tc_ct_rule_to_tuple(&entry->tuple, flow_rule);
	if (err)
		goto err_set;

	memcpy(&entry->tuple_nat, &entry->tuple, sizeof(entry->tuple));
	err = mlx5_tc_ct_rule_to_tuple_nat(&entry->tuple_nat, flow_rule);
	if (err)
		goto err_set;

	spin_lock_bh(&ct_priv->ht_lock);

	err = rhashtable_lookup_insert_fast(&ft->ct_entries_ht, &entry->node,
					    cts_ht_params);
	if (err)
		goto err_entries;

	err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_ht,
					    &entry->tuple_node,
					    tuples_ht_params);
	if (err)
		goto err_tuple;

	if (memcmp(&entry->tuple, &entry->tuple_nat, sizeof(entry->tuple))) {
		err = rhashtable_lookup_insert_fast(&ct_priv->ct_tuples_nat_ht,
						    &entry->tuple_nat_node,
						    tuples_nat_ht_params);
		if (err)
			goto err_tuple_nat;
	}
	spin_unlock_bh(&ct_priv->ht_lock);

	err = mlx5_tc_ct_entry_add_rules(ct_priv, flow_rule, entry,
					 ft->zone_restore_id);
	if (err)
		goto err_rules;

	set_bit(MLX5_CT_ENTRY_FLAG_VALID, &entry->flags);
	mlx5_tc_ct_entry_put(entry); /* this function reference */

	return 0;

err_rules:
	spin_lock_bh(&ct_priv->ht_lock);
	if (mlx5_tc_ct_entry_has_nat(entry))
		rhashtable_remove_fast(&ct_priv->ct_tuples_nat_ht,
				       &entry->tuple_nat_node, tuples_nat_ht_params);
err_tuple_nat:
	rhashtable_remove_fast(&ct_priv->ct_tuples_ht,
			       &entry->tuple_node,
			       tuples_ht_params);
err_tuple:
	rhashtable_remove_fast(&ft->ct_entries_ht,
			       &entry->node,
			       cts_ht_params);
err_entries:
	spin_unlock_bh(&ct_priv->ht_lock);
err_set:
	kfree(entry);
	if (err != -EEXIST)
		netdev_warn(ct_priv->netdev, "Failed to offload ct entry, err: %d\n", err);
	return err;
}

static int
mlx5_tc_ct_block_flow_offload_del(struct mlx5_ct_ft *ft,
				  struct flow_cls_offload *flow)
{
	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
	unsigned long cookie = flow->cookie;
	struct mlx5_ct_entry *entry;

	spin_lock_bh(&ct_priv->ht_lock);
	entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params);
	if (!entry) {
		spin_unlock_bh(&ct_priv->ht_lock);
		return -ENOENT;
	}

	if (!mlx5_tc_ct_entry_valid(entry)) {
		spin_unlock_bh(&ct_priv->ht_lock);
		return -EINVAL;
	}

	rhashtable_remove_fast(&ft->ct_entries_ht, &entry->node, cts_ht_params);
	spin_unlock_bh(&ct_priv->ht_lock);

	mlx5_tc_ct_entry_put(entry);

	return 0;
}

static int
mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
				    struct flow_cls_offload *f)
{
	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
	unsigned long cookie = f->cookie;
	struct mlx5_ct_entry *entry;
	u64 lastuse, packets, bytes;

	spin_lock_bh(&ct_priv->ht_lock);
	entry = rhashtable_lookup_fast(&ft->ct_entries_ht, &cookie, cts_ht_params);
	if (!entry) {
		spin_unlock_bh(&ct_priv->ht_lock);
		return -ENOENT;
	}

	if (!mlx5_tc_ct_entry_valid(entry) || !refcount_inc_not_zero(&entry->refcnt)) {
		spin_unlock_bh(&ct_priv->ht_lock);
		return -EINVAL;
	}

	spin_unlock_bh(&ct_priv->ht_lock);

	mlx5_fc_query_cached(entry->counter->counter, &bytes, &packets, &lastuse);
	flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
			  FLOW_ACTION_HW_STATS_DELAYED);

	mlx5_tc_ct_entry_put(entry);
	return 0;
}

static int
mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
			      void *cb_priv)
{
	struct flow_cls_offload *f = type_data;
	struct mlx5_ct_ft *ft = cb_priv;

	if (type != TC_SETUP_CLSFLOWER)
		return -EOPNOTSUPP;

	switch (f->command) {
	case FLOW_CLS_REPLACE:
		return mlx5_tc_ct_block_flow_offload_add(ft, f);
	case FLOW_CLS_DESTROY:
		return mlx5_tc_ct_block_flow_offload_del(ft, f);
	case FLOW_CLS_STATS:
		return mlx5_tc_ct_block_flow_offload_stats(ft, f);
	default:
		break;
	}

	return -EOPNOTSUPP;
}

static bool
mlx5_tc_ct_skb_to_tuple(struct sk_buff *skb, struct mlx5_ct_tuple *tuple,
			u16 zone)
{
	struct flow_keys flow_keys;

	skb_reset_network_header(skb);
	skb_flow_dissect_flow_keys(skb, &flow_keys, FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP);

	tuple->zone = zone;

	if (flow_keys.basic.ip_proto != IPPROTO_TCP &&
	    flow_keys.basic.ip_proto != IPPROTO_UDP &&
	    flow_keys.basic.ip_proto != IPPROTO_GRE)
		return false;

	if (flow_keys.basic.ip_proto == IPPROTO_TCP ||
	    flow_keys.basic.ip_proto == IPPROTO_UDP) {
		tuple->port.src = flow_keys.ports.src;
		tuple->port.dst = flow_keys.ports.dst;
	}
	tuple->n_proto = flow_keys.basic.n_proto;
	tuple->ip_proto = flow_keys.basic.ip_proto;

	switch (flow_keys.basic.n_proto) {
	case htons(ETH_P_IP):
		tuple->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
		tuple->ip.src_v4 = flow_keys.addrs.v4addrs.src;
		tuple->ip.dst_v4 = flow_keys.addrs.v4addrs.dst;
		break;

	case htons(ETH_P_IPV6):
		tuple->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
		tuple->ip.src_v6 = flow_keys.addrs.v6addrs.src;
		tuple->ip.dst_v6 = flow_keys.addrs.v6addrs.dst;
		break;
	default:
		goto out;
	}

	return true;

out:
	return false;
}

int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec)
{
	u32 ctstate = 0, ctstate_mask = 0;

	mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG,
					&ctstate, &ctstate_mask);

	if ((ctstate & ctstate_mask) == MLX5_CT_STATE_TRK_BIT)
		return -EOPNOTSUPP;

	ctstate_mask |= MLX5_CT_STATE_TRK_BIT;
	mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG,
				    ctstate, ctstate_mask);

	return 0;
}

void mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr)
{
	if (!priv || !ct_attr->ct_labels_id)
		return;

	mlx5_put_label_mapping(priv, ct_attr->ct_labels_id);
}

int
mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
		     struct mlx5_flow_spec *spec,
		     struct flow_cls_offload *f,
		     struct mlx5_ct_attr *ct_attr,
		     struct netlink_ext_ack *extack)
{
	bool trk, est, untrk, unest, new, rpl, unrpl, rel, unrel, inv, uninv;
	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
	struct flow_dissector_key_ct *mask, *key;
	u32 ctstate = 0, ctstate_mask = 0;
	u16 ct_state_on, ct_state_off;
	u16 ct_state, ct_state_mask;
	struct flow_match_ct match;
	u32 ct_labels[4];

	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CT))
		return 0;

	if (!priv) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload of ct matching isn't available");
		return -EOPNOTSUPP;
	}

	flow_rule_match_ct(rule, &match);

	key = match.key;
	mask = match.mask;

	ct_state = key->ct_state;
	ct_state_mask = mask->ct_state;

	if (ct_state_mask & ~(TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
			      TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED |
			      TCA_FLOWER_KEY_CT_FLAGS_NEW |
			      TCA_FLOWER_KEY_CT_FLAGS_REPLY |
			      TCA_FLOWER_KEY_CT_FLAGS_RELATED |
			      TCA_FLOWER_KEY_CT_FLAGS_INVALID)) {
		NL_SET_ERR_MSG_MOD(extack,
				   "only ct_state trk, est, new and rpl are supported for offload");
		return -EOPNOTSUPP;
	}

	ct_state_on = ct_state & ct_state_mask;
	ct_state_off = (ct_state & ct_state_mask) ^ ct_state_mask;
	trk = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_TRACKED;
	new = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_NEW;
	est = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED;
	rpl = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_REPLY;
	rel = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_RELATED;
	inv = ct_state_on & TCA_FLOWER_KEY_CT_FLAGS_INVALID;
	untrk = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_TRACKED;
	unest = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED;
	unrpl = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_REPLY;
	unrel = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_RELATED;
	uninv = ct_state_off & TCA_FLOWER_KEY_CT_FLAGS_INVALID;

	ctstate |= trk ? MLX5_CT_STATE_TRK_BIT : 0;
	ctstate |= est ? MLX5_CT_STATE_ESTABLISHED_BIT : 0;
	ctstate |= rpl ? MLX5_CT_STATE_REPLY_BIT : 0;
	ctstate_mask |= (untrk || trk) ? MLX5_CT_STATE_TRK_BIT : 0;
	ctstate_mask |= (unest || est) ? MLX5_CT_STATE_ESTABLISHED_BIT : 0;
	ctstate_mask |= (unrpl || rpl) ? MLX5_CT_STATE_REPLY_BIT : 0;
	ctstate_mask |= unrel ? MLX5_CT_STATE_RELATED_BIT : 0;
	ctstate_mask |= uninv ? MLX5_CT_STATE_INVALID_BIT : 0;

	if (rel) {
		NL_SET_ERR_MSG_MOD(extack,
				   "matching on ct_state +rel isn't supported");
		return -EOPNOTSUPP;
	}

	if (inv) {
		NL_SET_ERR_MSG_MOD(extack,
				   "matching on ct_state +inv isn't supported");
		return -EOPNOTSUPP;
	}

	if (new) {
		NL_SET_ERR_MSG_MOD(extack,
				   "matching on ct_state +new isn't supported");
		return -EOPNOTSUPP;
	}

	if (mask->ct_zone)
		mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG,
					    key->ct_zone, MLX5_CT_ZONE_MASK);
	if (ctstate_mask)
		mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG,
					    ctstate, ctstate_mask);
	if (mask->ct_mark)
		mlx5e_tc_match_to_reg_match(spec, MARK_TO_REG,
					    key->ct_mark, mask->ct_mark);
	if (mask->ct_labels[0] || mask->ct_labels[1] || mask->ct_labels[2] ||
	    mask->ct_labels[3]) {
		ct_labels[0] = key->ct_labels[0] & mask->ct_labels[0];
		ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1];
		ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2];
		ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3];
		if (mlx5_get_label_mapping(priv, ct_labels, &ct_attr->ct_labels_id))
			return -EOPNOTSUPP;
		mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id,
					    MLX5_CT_LABELS_MASK);
	}

	return 0;
}

int
mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
			struct mlx5_flow_attr *attr,
			struct mlx5e_tc_mod_hdr_acts *mod_acts,
			const struct flow_action_entry *act,
			struct netlink_ext_ack *extack)
{
	if (!priv) {
		NL_SET_ERR_MSG_MOD(extack,
				   "offload of ct action isn't available");
		return -EOPNOTSUPP;
	}

	attr->ct_attr.zone = act->ct.zone;
	attr->ct_attr.ct_action = act->ct.action;
	attr->ct_attr.nf_ft = act->ct.flow_table;

	return 0;
}

static int tc_ct_pre_ct_add_rules(struct mlx5_ct_ft *ct_ft,
				  struct mlx5_tc_ct_pre *pre_ct,
				  bool nat)
{
	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
	struct mlx5e_tc_mod_hdr_acts pre_mod_acts = {};
	struct mlx5_core_dev *dev = ct_priv->dev;
	struct mlx5_flow_table *ft = pre_ct->ft;
	struct mlx5_flow_destination dest = {};
	struct mlx5_flow_act flow_act = {};
	struct mlx5_modify_hdr *mod_hdr;
	struct mlx5_flow_handle *rule;
	struct mlx5_flow_spec *spec;
	u32 ctstate;
	u16 zone;
	int err;

	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
	if (!spec)
		return -ENOMEM;

	zone = ct_ft->zone & MLX5_CT_ZONE_MASK;
	err = mlx5e_tc_match_to_reg_set(dev, &pre_mod_acts, ct_priv->ns_type,
					ZONE_TO_REG, zone);
	if (err) {
		ct_dbg("Failed to set zone register mapping");
		goto err_mapping;
	}

	mod_hdr = mlx5_modify_header_alloc(dev, ct_priv->ns_type,
					   pre_mod_acts.num_actions,
					   pre_mod_acts.actions);

	if (IS_ERR(mod_hdr)) {
		err = PTR_ERR(mod_hdr);
		ct_dbg("Failed to create pre ct mod hdr");
		goto err_mapping;
	}
	pre_ct->modify_hdr = mod_hdr;

	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
			  MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
	flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
	flow_act.modify_hdr = mod_hdr;
	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;

	/* add flow rule */
	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG,
				    zone, MLX5_CT_ZONE_MASK);
	ctstate = MLX5_CT_STATE_TRK_BIT;
	if (nat)
		ctstate |= MLX5_CT_STATE_NAT_BIT;
	mlx5e_tc_match_to_reg_match(spec, CTSTATE_TO_REG, ctstate, ctstate);

	dest.ft = mlx5e_tc_post_act_get_ft(ct_priv->post_act);
	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
	if (IS_ERR(rule)) {
		err = PTR_ERR(rule);
		ct_dbg("Failed to add pre ct flow rule zone %d", zone);
		goto err_flow_rule;
	}
	pre_ct->flow_rule = rule;

	/* add miss rule */
	dest.ft = nat ? ct_priv->ct_nat : ct_priv->ct;
	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, &dest, 1);
	if (IS_ERR(rule)) {
		err = PTR_ERR(rule);
		ct_dbg("Failed to add pre ct miss rule zone %d", zone);
		goto err_miss_rule;
	}
	pre_ct->miss_rule = rule;

	mlx5e_mod_hdr_dealloc(&pre_mod_acts);
	kvfree(spec);
	return 0;

err_miss_rule:
	mlx5_del_flow_rules(pre_ct->flow_rule);
err_flow_rule:
	mlx5_modify_header_dealloc(dev, pre_ct->modify_hdr);
err_mapping:
	mlx5e_mod_hdr_dealloc(&pre_mod_acts);
	kvfree(spec);
	return err;
}

static void
tc_ct_pre_ct_del_rules(struct mlx5_ct_ft *ct_ft,
		       struct mlx5_tc_ct_pre *pre_ct)
{
	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
	struct mlx5_core_dev *dev = ct_priv->dev;

	mlx5_del_flow_rules(pre_ct->flow_rule);
	mlx5_del_flow_rules(pre_ct->miss_rule);
	mlx5_modify_header_dealloc(dev, pre_ct->modify_hdr);
}

static int
mlx5_tc_ct_alloc_pre_ct(struct mlx5_ct_ft *ct_ft,
			struct mlx5_tc_ct_pre *pre_ct,
			bool nat)
{
	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
	struct mlx5_tc_ct_priv *ct_priv = ct_ft->ct_priv;
	struct mlx5_core_dev *dev = ct_priv->dev;
	struct mlx5_flow_table_attr ft_attr = {};
	struct mlx5_flow_namespace *ns;
	struct mlx5_flow_table *ft;
	struct mlx5_flow_group *g;
	u32 metadata_reg_c_2_mask;
	u32 *flow_group_in;
	void *misc;
	int err;

	ns = mlx5_get_flow_namespace(dev, ct_priv->ns_type);
	if (!ns) {
		err = -EOPNOTSUPP;
		ct_dbg("Failed to get flow namespace");
		return err;
	}

	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
	if (!flow_group_in)
		return -ENOMEM;

	ft_attr.flags = MLX5_FLOW_TABLE_UNMANAGED;
	ft_attr.prio =  ct_priv->ns_type ==  MLX5_FLOW_NAMESPACE_FDB ?
			FDB_TC_OFFLOAD : MLX5E_TC_PRIO;
	ft_attr.max_fte = 2;
	ft_attr.level = 1;
	ft = mlx5_create_flow_table(ns, &ft_attr);
	if (IS_ERR(ft)) {
		err = PTR_ERR(ft);
		ct_dbg("Failed to create pre ct table");
		goto out_free;
	}
	pre_ct->ft = ft;

	/* create flow group */
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
		 MLX5_MATCH_MISC_PARAMETERS_2);

	misc = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
			    match_criteria.misc_parameters_2);

	metadata_reg_c_2_mask = MLX5_CT_ZONE_MASK;
	metadata_reg_c_2_mask |= (MLX5_CT_STATE_TRK_BIT << 16);
	if (nat)
		metadata_reg_c_2_mask |= (MLX5_CT_STATE_NAT_BIT << 16);

	MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_2,
		 metadata_reg_c_2_mask);

	g = mlx5_create_flow_group(ft, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		ct_dbg("Failed to create pre ct group");
		goto err_flow_grp;
	}
	pre_ct->flow_grp = g;

	/* create miss group */
	memset(flow_group_in, 0, inlen);
	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
	g = mlx5_create_flow_group(ft, flow_group_in);
	if (IS_ERR(g)) {
		err = PTR_ERR(g);
		ct_dbg("Failed to create pre ct miss group");
		goto err_miss_grp;
	}
	pre_ct->miss_grp = g;

	err = tc_ct_pre_ct_add_rules(ct_ft, pre_ct, nat);
	if (err)
		goto err_add_rules;

	kvfree(flow_group_in);
	return 0;

err_add_rules:
	mlx5_destroy_flow_group(pre_ct->miss_grp);
err_miss_grp:
	mlx5_destroy_flow_group(pre_ct->flow_grp);
err_flow_grp:
	mlx5_destroy_flow_table(ft);
out_free:
	kvfree(flow_group_in);
	return err;
}

static void
mlx5_tc_ct_free_pre_ct(struct mlx5_ct_ft *ct_ft,
		       struct mlx5_tc_ct_pre *pre_ct)
{
	tc_ct_pre_ct_del_rules(ct_ft, pre_ct);
	mlx5_destroy_flow_group(pre_ct->miss_grp);
	mlx5_destroy_flow_group(pre_ct->flow_grp);
	mlx5_destroy_flow_table(pre_ct->ft);
}

static int
mlx5_tc_ct_alloc_pre_ct_tables(struct mlx5_ct_ft *ft)
{
	int err;

	err = mlx5_tc_ct_alloc_pre_ct(ft, &ft->pre_ct, false);
	if (err)
		return err;

	err = mlx5_tc_ct_alloc_pre_ct(ft, &ft->pre_ct_nat, true);
	if (err)
		goto err_pre_ct_nat;

	return 0;

err_pre_ct_nat:
	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct);
	return err;
}

static void
mlx5_tc_ct_free_pre_ct_tables(struct mlx5_ct_ft *ft)
{
	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct_nat);
	mlx5_tc_ct_free_pre_ct(ft, &ft->pre_ct);
}

/* To avoid false lock dependency warning set the ct_entries_ht lock
 * class different than the lock class of the ht being used when deleting
 * last flow from a group and then deleting a group, we get into del_sw_flow_group()
 * which call rhashtable_destroy on fg->ftes_hash which will take ht->mutex but
 * it's different than the ht->mutex here.
 */
static struct lock_class_key ct_entries_ht_lock_key;

static struct mlx5_ct_ft *
mlx5_tc_ct_add_ft_cb(struct mlx5_tc_ct_priv *ct_priv, u16 zone,
		     struct nf_flowtable *nf_ft)
{
	struct mlx5_ct_ft *ft;
	int err;

	ft = rhashtable_lookup_fast(&ct_priv->zone_ht, &zone, zone_params);
	if (ft) {
		refcount_inc(&ft->refcount);
		return ft;
	}

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

	err = mapping_add(ct_priv->zone_mapping, &zone, &ft->zone_restore_id);
	if (err)
		goto err_mapping;

	ft->zone = zone;
	ft->nf_ft = nf_ft;
	ft->ct_priv = ct_priv;
	refcount_set(&ft->refcount, 1);

	err = mlx5_tc_ct_alloc_pre_ct_tables(ft);
	if (err)
		goto err_alloc_pre_ct;

	err = rhashtable_init(&ft->ct_entries_ht, &cts_ht_params);
	if (err)
		goto err_init;

	lockdep_set_class(&ft->ct_entries_ht.mutex, &ct_entries_ht_lock_key);

	err = rhashtable_insert_fast(&ct_priv->zone_ht, &ft->node,
				     zone_params);
	if (err)
		goto err_insert;

	err = nf_flow_table_offload_add_cb(ft->nf_ft,
					   mlx5_tc_ct_block_flow_offload, ft);
	if (err)
		goto err_add_cb;

	return ft;

err_add_cb:
	rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params);
err_insert:
	rhashtable_destroy(&ft->ct_entries_ht);
err_init:
	mlx5_tc_ct_free_pre_ct_tables(ft);
err_alloc_pre_ct:
	mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id);
err_mapping:
	kfree(ft);
	return ERR_PTR(err);
}

static void
mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg)
{
	struct mlx5_ct_entry *entry = ptr;

	mlx5_tc_ct_entry_put(entry);
}

static void
mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft)
{
	struct mlx5e_priv *priv;

	if (!refcount_dec_and_test(&ft->refcount))
		return;

	nf_flow_table_offload_del_cb(ft->nf_ft,
				     mlx5_tc_ct_block_flow_offload, ft);
	rhashtable_remove_fast(&ct_priv->zone_ht, &ft->node, zone_params);
	rhashtable_free_and_destroy(&ft->ct_entries_ht,
				    mlx5_tc_ct_flush_ft_entry,
				    ct_priv);
	priv = netdev_priv(ct_priv->netdev);
	flush_workqueue(priv->wq);
	mlx5_tc_ct_free_pre_ct_tables(ft);
	mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id);
	kfree(ft);
}

/* We translate the tc filter with CT action to the following HW model:
 *
 * +---------------------+
 * + ft prio (tc chain)  +
 * + original match      +
 * +---------------------+
 *      | set chain miss mapping
 *      | set fte_id
 *      | set tunnel_id
 *      | do decap
 *      v
 * +---------------------+
 * + pre_ct/pre_ct_nat   +  if matches     +-------------------------+
 * + zone+nat match      +---------------->+ post_act (see below)    +
 * +---------------------+  set zone       +-------------------------+
 *      | set zone
 *      v
 * +--------------------+
 * + CT (nat or no nat) +
 * + tuple + zone match +
 * +--------------------+
 *      | set mark
 *      | set labels_id
 *      | set established
 *	| set zone_restore
 *      | do nat (if needed)
 *      v
 * +--------------+
 * + post_act     + original filter actions
 * + fte_id match +------------------------>
 * +--------------+
 */
static struct mlx5_flow_handle *
__mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
			  struct mlx5_flow_spec *orig_spec,
			  struct mlx5_flow_attr *attr)
{
	bool nat = attr->ct_attr.ct_action & TCA_CT_ACT_NAT;
	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
	struct mlx5e_tc_mod_hdr_acts *pre_mod_acts;
	u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type);
	struct mlx5_flow_attr *pre_ct_attr;
	struct mlx5_modify_hdr *mod_hdr;
	struct mlx5_ct_flow *ct_flow;
	int chain_mapping = 0, err;
	struct mlx5_ct_ft *ft;

	ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL);
	if (!ct_flow) {
		return ERR_PTR(-ENOMEM);
	}

	/* Register for CT established events */
	ft = mlx5_tc_ct_add_ft_cb(ct_priv, attr->ct_attr.zone,
				  attr->ct_attr.nf_ft);
	if (IS_ERR(ft)) {
		err = PTR_ERR(ft);
		ct_dbg("Failed to register to ft callback");
		goto err_ft;
	}
	ct_flow->ft = ft;

	/* Base flow attributes of both rules on original rule attribute */
	ct_flow->pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
	if (!ct_flow->pre_ct_attr) {
		err = -ENOMEM;
		goto err_alloc_pre;
	}

	pre_ct_attr = ct_flow->pre_ct_attr;
	memcpy(pre_ct_attr, attr, attr_sz);
	pre_mod_acts = &pre_ct_attr->parse_attr->mod_hdr_acts;

	/* Modify the original rule's action to fwd and modify, leave decap */
	pre_ct_attr->action = attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP;
	pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
			       MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;

	/* Write chain miss tag for miss in ct table as we
	 * don't go though all prios of this chain as normal tc rules
	 * miss.
	 */
	err = mlx5_chains_get_chain_mapping(ct_priv->chains, attr->chain,
					    &chain_mapping);
	if (err) {
		ct_dbg("Failed to get chain register mapping for chain");
		goto err_get_chain;
	}
	ct_flow->chain_mapping = chain_mapping;

	err = mlx5e_tc_match_to_reg_set(priv->mdev, pre_mod_acts, ct_priv->ns_type,
					CHAIN_TO_REG, chain_mapping);
	if (err) {
		ct_dbg("Failed to set chain register mapping");
		goto err_mapping;
	}

	/* If original flow is decap, we do it before going into ct table
	 * so add a rewrite for the tunnel match_id.
	 */
	if ((pre_ct_attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
	    attr->chain == 0) {
		err = mlx5e_tc_match_to_reg_set(priv->mdev, pre_mod_acts,
						ct_priv->ns_type,
						TUNNEL_TO_REG,
						attr->tunnel_id);
		if (err) {
			ct_dbg("Failed to set tunnel register mapping");
			goto err_mapping;
		}
	}

	mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
					   pre_mod_acts->num_actions,
					   pre_mod_acts->actions);
	if (IS_ERR(mod_hdr)) {
		err = PTR_ERR(mod_hdr);
		ct_dbg("Failed to create pre ct mod hdr");
		goto err_mapping;
	}
	pre_ct_attr->modify_hdr = mod_hdr;

	/* Change original rule point to ct table */
	pre_ct_attr->dest_chain = 0;
	pre_ct_attr->dest_ft = nat ? ft->pre_ct_nat.ft : ft->pre_ct.ft;
	ct_flow->pre_ct_rule = mlx5_tc_rule_insert(priv, orig_spec,
						   pre_ct_attr);
	if (IS_ERR(ct_flow->pre_ct_rule)) {
		err = PTR_ERR(ct_flow->pre_ct_rule);
		ct_dbg("Failed to add pre ct rule");
		goto err_insert_orig;
	}

	attr->ct_attr.ct_flow = ct_flow;
	mlx5e_mod_hdr_dealloc(pre_mod_acts);

	return ct_flow->pre_ct_rule;

err_insert_orig:
	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
err_mapping:
	mlx5e_mod_hdr_dealloc(pre_mod_acts);
	mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
err_get_chain:
	kfree(ct_flow->pre_ct_attr);
err_alloc_pre:
	mlx5_tc_ct_del_ft_cb(ct_priv, ft);
err_ft:
	kfree(ct_flow);
	netdev_warn(priv->netdev, "Failed to offload ct flow, err %d\n", err);
	return ERR_PTR(err);
}

struct mlx5_flow_handle *
mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
			struct mlx5_flow_spec *spec,
			struct mlx5_flow_attr *attr,
			struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
{
	struct mlx5_flow_handle *rule;

	if (!priv)
		return ERR_PTR(-EOPNOTSUPP);

	mutex_lock(&priv->control_lock);
	rule = __mlx5_tc_ct_flow_offload(priv, spec, attr);
	mutex_unlock(&priv->control_lock);

	return rule;
}

static void
__mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,
			 struct mlx5_ct_flow *ct_flow,
			 struct mlx5_flow_attr *attr)
{
	struct mlx5_flow_attr *pre_ct_attr = ct_flow->pre_ct_attr;
	struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);

	mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, pre_ct_attr);
	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);

	mlx5_chains_put_chain_mapping(ct_priv->chains, ct_flow->chain_mapping);
	mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft);

	kfree(ct_flow->pre_ct_attr);
	kfree(ct_flow);
}

void
mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
		       struct mlx5_flow_attr *attr)
{
	struct mlx5_ct_flow *ct_flow = attr->ct_attr.ct_flow;

	/* We are called on error to clean up stuff from parsing
	 * but we don't have anything for now
	 */
	if (!ct_flow)
		return;

	mutex_lock(&priv->control_lock);
	__mlx5_tc_ct_delete_flow(priv, ct_flow, attr);
	mutex_unlock(&priv->control_lock);
}

static int
mlx5_tc_ct_fs_init(struct mlx5_tc_ct_priv *ct_priv)
{
	struct mlx5_flow_table *post_ct = mlx5e_tc_post_act_get_ft(ct_priv->post_act);
	struct mlx5_ct_fs_ops *fs_ops = mlx5_ct_fs_dmfs_ops_get();
	int err;

	if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB &&
	    ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) {
		ct_dbg("Using SMFS ct flow steering provider");
		fs_ops = mlx5_ct_fs_smfs_ops_get();
	}

	ct_priv->fs = kzalloc(sizeof(*ct_priv->fs) + fs_ops->priv_size, GFP_KERNEL);
	if (!ct_priv->fs)
		return -ENOMEM;

	ct_priv->fs->netdev = ct_priv->netdev;
	ct_priv->fs->dev = ct_priv->dev;
	ct_priv->fs_ops = fs_ops;

	err = ct_priv->fs_ops->init(ct_priv->fs, ct_priv->ct, ct_priv->ct_nat, post_ct);
	if (err)
		goto err_init;

	return 0;

err_init:
	kfree(ct_priv->fs);
	return err;
}

static int
mlx5_tc_ct_init_check_esw_support(struct mlx5_eswitch *esw,
				  const char **err_msg)
{
	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) {
		/* vlan workaround should be avoided for multi chain rules.
		 * This is just a sanity check as pop vlan action should
		 * be supported by any FW that supports ignore_flow_level
		 */

		*err_msg = "firmware vlan actions support is missing";
		return -EOPNOTSUPP;
	}

	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev,
				    fdb_modify_header_fwd_to_table)) {
		/* CT always writes to registers which are mod header actions.
		 * Therefore, mod header and goto is required
		 */

		*err_msg = "firmware fwd and modify support is missing";
		return -EOPNOTSUPP;
	}

	if (!mlx5_eswitch_reg_c1_loopback_enabled(esw)) {
		*err_msg = "register loopback isn't supported";
		return -EOPNOTSUPP;
	}

	return 0;
}

static int
mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
			      enum mlx5_flow_namespace_type ns_type,
			      struct mlx5e_post_act *post_act)
{
	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
	const char *err_msg = NULL;
	int err = 0;

#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
	/* cannot restore chain ID on HW miss */

	err_msg = "tc skb extension missing";
	err = -EOPNOTSUPP;
	goto out_err;
#endif
	if (IS_ERR_OR_NULL(post_act)) {
		/* Ignore_flow_level support isn't supported by default for VFs and so post_act
		 * won't be supported. Skip showing error msg.
		 */
		if (priv->mdev->coredev_type != MLX5_COREDEV_VF)
			err_msg = "post action is missing";
		err = -EOPNOTSUPP;
		goto out_err;
	}

	if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
		err = mlx5_tc_ct_init_check_esw_support(esw, &err_msg);

out_err:
	if (err && err_msg)
		netdev_dbg(priv->netdev, "tc ct offload not supported, %s\n", err_msg);
	return err;
}

static void
mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
{
	bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
	struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
	char dirname[16] = {};

	if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
		return;

	ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
	debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
				&ct_dbgfs->stats.offloaded);
	debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,
				&ct_dbgfs->stats.rx_dropped);
}

static void
mlx5_ct_tc_remove_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
{
	debugfs_remove_recursive(ct_priv->debugfs.root);
}

#define INIT_ERR_PREFIX "tc ct offload init failed"

struct mlx5_tc_ct_priv *
mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
		struct mod_hdr_tbl *mod_hdr,
		enum mlx5_flow_namespace_type ns_type,
		struct mlx5e_post_act *post_act)
{
	struct mlx5_tc_ct_priv *ct_priv;
	struct mlx5_core_dev *dev;
	u64 mapping_id;
	int err;

	dev = priv->mdev;
	err = mlx5_tc_ct_init_check_support(priv, ns_type, post_act);
	if (err)
		goto err_support;

	ct_priv = kzalloc(sizeof(*ct_priv), GFP_KERNEL);
	if (!ct_priv)
		goto err_alloc;

	mapping_id = mlx5_query_nic_system_image_guid(dev);

	ct_priv->zone_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_ZONE,
						      sizeof(u16), 0, true);
	if (IS_ERR(ct_priv->zone_mapping)) {
		err = PTR_ERR(ct_priv->zone_mapping);
		goto err_mapping_zone;
	}

	ct_priv->labels_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_LABELS,
							sizeof(u32) * 4, 0, true);
	if (IS_ERR(ct_priv->labels_mapping)) {
		err = PTR_ERR(ct_priv->labels_mapping);
		goto err_mapping_labels;
	}

	spin_lock_init(&ct_priv->ht_lock);
	ct_priv->ns_type = ns_type;
	ct_priv->chains = chains;
	ct_priv->netdev = priv->netdev;
	ct_priv->dev = priv->mdev;
	ct_priv->mod_hdr_tbl = mod_hdr;
	ct_priv->ct = mlx5_chains_create_global_table(chains);
	if (IS_ERR(ct_priv->ct)) {
		err = PTR_ERR(ct_priv->ct);
		mlx5_core_warn(dev,
			       "%s, failed to create ct table err: %d\n",
			       INIT_ERR_PREFIX, err);
		goto err_ct_tbl;
	}

	ct_priv->ct_nat = mlx5_chains_create_global_table(chains);
	if (IS_ERR(ct_priv->ct_nat)) {
		err = PTR_ERR(ct_priv->ct_nat);
		mlx5_core_warn(dev,
			       "%s, failed to create ct nat table err: %d\n",
			       INIT_ERR_PREFIX, err);
		goto err_ct_nat_tbl;
	}

	ct_priv->post_act = post_act;
	mutex_init(&ct_priv->control_lock);
	if (rhashtable_init(&ct_priv->zone_ht, &zone_params))
		goto err_ct_zone_ht;
	if (rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params))
		goto err_ct_tuples_ht;
	if (rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params))
		goto err_ct_tuples_nat_ht;

	err = mlx5_tc_ct_fs_init(ct_priv);
	if (err)
		goto err_init_fs;

	mlx5_ct_tc_create_dbgfs(ct_priv);
	return ct_priv;

err_init_fs:
	rhashtable_destroy(&ct_priv->ct_tuples_nat_ht);
err_ct_tuples_nat_ht:
	rhashtable_destroy(&ct_priv->ct_tuples_ht);
err_ct_tuples_ht:
	rhashtable_destroy(&ct_priv->zone_ht);
err_ct_zone_ht:
	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
err_ct_nat_tbl:
	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
err_ct_tbl:
	mapping_destroy(ct_priv->labels_mapping);
err_mapping_labels:
	mapping_destroy(ct_priv->zone_mapping);
err_mapping_zone:
	kfree(ct_priv);
err_alloc:
err_support:

	return NULL;
}

void
mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
{
	struct mlx5_fs_chains *chains;

	if (!ct_priv)
		return;

	mlx5_ct_tc_remove_dbgfs(ct_priv);
	chains = ct_priv->chains;

	ct_priv->fs_ops->destroy(ct_priv->fs);
	kfree(ct_priv->fs);

	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
	mapping_destroy(ct_priv->zone_mapping);
	mapping_destroy(ct_priv->labels_mapping);

	rhashtable_destroy(&ct_priv->ct_tuples_ht);
	rhashtable_destroy(&ct_priv->ct_tuples_nat_ht);
	rhashtable_destroy(&ct_priv->zone_ht);
	mutex_destroy(&ct_priv->control_lock);
	kfree(ct_priv);
}

bool
mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
			 struct sk_buff *skb, u8 zone_restore_id)
{
	struct mlx5_ct_tuple tuple = {};
	struct mlx5_ct_entry *entry;
	u16 zone;

	if (!ct_priv || !zone_restore_id)
		return true;

	if (mapping_find(ct_priv->zone_mapping, zone_restore_id, &zone))
		goto out_inc_drop;

	if (!mlx5_tc_ct_skb_to_tuple(skb, &tuple, zone))
		goto out_inc_drop;

	spin_lock(&ct_priv->ht_lock);

	entry = mlx5_tc_ct_entry_get(ct_priv, &tuple);
	if (!entry) {
		spin_unlock(&ct_priv->ht_lock);
		goto out_inc_drop;
	}

	if (IS_ERR(entry)) {
		spin_unlock(&ct_priv->ht_lock);
		goto out_inc_drop;
	}
	spin_unlock(&ct_priv->ht_lock);

	tcf_ct_flow_table_restore_skb(skb, entry->restore_cookie);
	__mlx5_tc_ct_entry_put(entry);

	return true;

out_inc_drop:
	atomic_inc(&ct_priv->debugfs.stats.rx_dropped);
	return false;
}