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
|
/*
* Copyright (c) 2016, Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/etherdevice.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/mlx5_ifc.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
#include "mlx5_core.h"
#include "eswitch.h"
#include "en.h"
#include "fs_core.h"
#include "lib/devcom.h"
#include "ecpf.h"
#include "lib/eq.h"
enum {
FDB_FAST_PATH = 0,
FDB_SLOW_PATH
};
/* There are two match-all miss flows, one for unicast dst mac and
* one for multicast.
*/
#define MLX5_ESW_MISS_FLOWS (2)
#define fdb_prio_table(esw, chain, prio, level) \
(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
#define UPLINK_REP_INDEX 0
/* The rep getter/iterator are only valid after esw->total_vports
* and vport->vport are initialized in mlx5_eswitch_init.
*/
#define mlx5_esw_for_all_reps(esw, i, rep) \
for ((i) = MLX5_VPORT_PF; \
(rep) = &(esw)->offloads.vport_reps[i], \
(i) < (esw)->total_vports; (i)++)
#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs) \
for ((i) = MLX5_VPORT_FIRST_VF; \
(rep) = &(esw)->offloads.vport_reps[i], \
(i) <= (nvfs); (i)++)
#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs) \
for ((i) = (nvfs); \
(rep) = &(esw)->offloads.vport_reps[i], \
(i) >= MLX5_VPORT_FIRST_VF; (i)--)
#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs) \
for ((vport) = MLX5_VPORT_FIRST_VF; \
(vport) <= (nvfs); (vport)++)
#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs) \
for ((vport) = (nvfs); \
(vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
u16 vport_num)
{
u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
WARN_ON(idx > esw->total_vports - 1);
return &esw->offloads.vport_reps[idx];
}
static struct mlx5_flow_table *
esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
static void
esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw)
{
return (!!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED));
}
u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)
{
if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
return FDB_MAX_CHAIN;
return 0;
}
u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
{
if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
return FDB_MAX_PRIO;
return 1;
}
struct mlx5_flow_handle *
mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
bool split = !!(attr->split_count);
struct mlx5_flow_handle *rule;
struct mlx5_flow_table *fdb;
int j, i = 0;
void *misc;
if (esw->mode != SRIOV_OFFLOADS)
return ERR_PTR(-EOPNOTSUPP);
flow_act.action = attr->action;
/* if per flow vlan pop/push is emulated, don't set that into the firmware */
if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
flow_act.vlan[0].vid = attr->vlan_vid[0];
flow_act.vlan[0].prio = attr->vlan_prio[0];
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
flow_act.vlan[1].vid = attr->vlan_vid[1];
flow_act.vlan[1].prio = attr->vlan_prio[1];
}
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
if (attr->dest_chain) {
struct mlx5_flow_table *ft;
ft = esw_get_prio_table(esw, attr->dest_chain, 1, 0);
if (IS_ERR(ft)) {
rule = ERR_CAST(ft);
goto err_create_goto_table;
}
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
dest[i].ft = ft;
i++;
} else {
for (j = attr->split_count; j < attr->out_count; j++) {
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest[i].vport.num = attr->dests[j].rep->vport;
dest[i].vport.vhca_id =
MLX5_CAP_GEN(attr->dests[j].mdev, vhca_id);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
dest[i].vport.flags |=
MLX5_FLOW_DEST_VPORT_VHCA_ID;
if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
flow_act.reformat_id = attr->dests[j].encap_id;
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
dest[i].vport.reformat_id =
attr->dests[j].encap_id;
}
i++;
}
}
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
dest[i].counter_id = mlx5_fc_id(attr->counter);
i++;
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
MLX5_SET(fte_match_set_misc, misc,
source_eswitch_owner_vhca_id,
MLX5_CAP_GEN(attr->in_mdev, vhca_id));
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
MLX5_SET_TO_ONES(fte_match_set_misc, misc,
source_eswitch_owner_vhca_id);
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
if (attr->tunnel_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
if (attr->match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
} else if (attr->match_level != MLX5_MATCH_NONE) {
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
}
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
flow_act.modify_id = attr->mod_hdr_id;
fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
if (IS_ERR(fdb)) {
rule = ERR_CAST(fdb);
goto err_esw_get;
}
rule = mlx5_add_flow_rules(fdb, spec, &flow_act, dest, i);
if (IS_ERR(rule))
goto err_add_rule;
else
esw->offloads.num_flows++;
return rule;
err_add_rule:
esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
err_esw_get:
if (attr->dest_chain)
esw_put_prio_table(esw, attr->dest_chain, 1, 0);
err_create_goto_table:
return rule;
}
struct mlx5_flow_handle *
mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_spec *spec,
struct mlx5_esw_flow_attr *attr)
{
struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
struct mlx5_flow_table *fast_fdb;
struct mlx5_flow_table *fwd_fdb;
struct mlx5_flow_handle *rule;
void *misc;
int i;
fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
if (IS_ERR(fast_fdb)) {
rule = ERR_CAST(fast_fdb);
goto err_get_fast;
}
fwd_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 1);
if (IS_ERR(fwd_fdb)) {
rule = ERR_CAST(fwd_fdb);
goto err_get_fwd;
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
for (i = 0; i < attr->split_count; i++) {
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest[i].vport.num = attr->dests[i].rep->vport;
dest[i].vport.vhca_id =
MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
dest[i].vport.reformat_id = attr->dests[i].encap_id;
}
}
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
dest[i].ft = fwd_fdb,
i++;
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
MLX5_SET(fte_match_set_misc, misc,
source_eswitch_owner_vhca_id,
MLX5_CAP_GEN(attr->in_mdev, vhca_id));
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
MLX5_SET_TO_ONES(fte_match_set_misc, misc,
source_eswitch_owner_vhca_id);
if (attr->match_level == MLX5_MATCH_NONE)
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
else
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
MLX5_MATCH_MISC_PARAMETERS;
rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
if (IS_ERR(rule))
goto add_err;
esw->offloads.num_flows++;
return rule;
add_err:
esw_put_prio_table(esw, attr->chain, attr->prio, 1);
err_get_fwd:
esw_put_prio_table(esw, attr->chain, attr->prio, 0);
err_get_fast:
return rule;
}
static void
__mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr,
bool fwd_rule)
{
bool split = (attr->split_count > 0);
mlx5_del_flow_rules(rule);
esw->offloads.num_flows--;
if (fwd_rule) {
esw_put_prio_table(esw, attr->chain, attr->prio, 1);
esw_put_prio_table(esw, attr->chain, attr->prio, 0);
} else {
esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
if (attr->dest_chain)
esw_put_prio_table(esw, attr->dest_chain, 1, 0);
}
}
void
mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr)
{
__mlx5_eswitch_del_rule(esw, rule, attr, false);
}
void
mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *rule,
struct mlx5_esw_flow_attr *attr)
{
__mlx5_eswitch_del_rule(esw, rule, attr, true);
}
static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
{
struct mlx5_eswitch_rep *rep;
int vf_vport, err = 0;
esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
rep = &esw->offloads.vport_reps[vf_vport];
if (rep->rep_if[REP_ETH].state != REP_LOADED)
continue;
err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
if (err)
goto out;
}
out:
return err;
}
static struct mlx5_eswitch_rep *
esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
{
struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;
in_rep = attr->in_rep;
out_rep = attr->dests[0].rep;
if (push)
vport = in_rep;
else if (pop)
vport = out_rep;
else
vport = in_rep;
return vport;
}
static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
bool push, bool pop, bool fwd)
{
struct mlx5_eswitch_rep *in_rep, *out_rep;
if ((push || pop) && !fwd)
goto out_notsupp;
in_rep = attr->in_rep;
out_rep = attr->dests[0].rep;
if (push && in_rep->vport == MLX5_VPORT_UPLINK)
goto out_notsupp;
if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
goto out_notsupp;
/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
if (!push && !pop && fwd)
if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
goto out_notsupp;
/* protects against (1) setting rules with different vlans to push and
* (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
*/
if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
goto out_notsupp;
return 0;
out_notsupp:
return -EOPNOTSUPP;
}
int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
struct mlx5_esw_flow_attr *attr)
{
struct offloads_fdb *offloads = &esw->fdb_table.offloads;
struct mlx5_eswitch_rep *vport = NULL;
bool push, pop, fwd;
int err = 0;
/* nop if we're on the vlan push/pop non emulation mode */
if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
return 0;
push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
fwd = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
!attr->dest_chain);
err = esw_add_vlan_action_check(attr, push, pop, fwd);
if (err)
return err;
attr->vlan_handled = false;
vport = esw_vlan_action_get_vport(attr, push, pop);
if (!push && !pop && fwd) {
/* tracks VF --> wire rules without vlan push action */
if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
vport->vlan_refcount++;
attr->vlan_handled = true;
}
return 0;
}
if (!push && !pop)
return 0;
if (!(offloads->vlan_push_pop_refcount)) {
/* it's the 1st vlan rule, apply global vlan pop policy */
err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP);
if (err)
goto out;
}
offloads->vlan_push_pop_refcount++;
if (push) {
if (vport->vlan_refcount)
goto skip_set_push;
err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
SET_VLAN_INSERT | SET_VLAN_STRIP);
if (err)
goto out;
vport->vlan = attr->vlan_vid[0];
skip_set_push:
vport->vlan_refcount++;
}
out:
if (!err)
attr->vlan_handled = true;
return err;
}
int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
struct mlx5_esw_flow_attr *attr)
{
struct offloads_fdb *offloads = &esw->fdb_table.offloads;
struct mlx5_eswitch_rep *vport = NULL;
bool push, pop, fwd;
int err = 0;
/* nop if we're on the vlan push/pop non emulation mode */
if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
return 0;
if (!attr->vlan_handled)
return 0;
push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
vport = esw_vlan_action_get_vport(attr, push, pop);
if (!push && !pop && fwd) {
/* tracks VF --> wire rules without vlan push action */
if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
vport->vlan_refcount--;
return 0;
}
if (push) {
vport->vlan_refcount--;
if (vport->vlan_refcount)
goto skip_unset_push;
vport->vlan = 0;
err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport,
0, 0, SET_VLAN_STRIP);
if (err)
goto out;
}
skip_unset_push:
offloads->vlan_push_pop_refcount--;
if (offloads->vlan_push_pop_refcount)
return 0;
/* no more vlan rules, stop global vlan pop policy */
err = esw_set_global_vlan_pop(esw, 0);
out:
return err;
}
struct mlx5_flow_handle *
mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn)
{
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest = {};
struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
flow_rule = ERR_PTR(-ENOMEM);
goto out;
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
/* source vport is the esw manager */
MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport.num = vport;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
&flow_act, &dest, 1);
if (IS_ERR(flow_rule))
esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule));
out:
kvfree(spec);
return flow_rule;
}
EXPORT_SYMBOL(mlx5_eswitch_add_send_to_vport_rule);
void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
{
mlx5_del_flow_rules(rule);
}
static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
struct mlx5_flow_spec *spec,
struct mlx5_flow_destination *dest)
{
void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
MLX5_CAP_GEN(peer_dev, vhca_id));
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
MLX5_SET_TO_ONES(fte_match_set_misc, misc,
source_eswitch_owner_vhca_id);
dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest->vport.num = peer_dev->priv.eswitch->manager_vport;
dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
}
static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
struct mlx5_core_dev *peer_dev)
{
struct mlx5_flow_destination dest = {};
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_handle **flows;
struct mlx5_flow_handle *flow;
struct mlx5_flow_spec *spec;
/* total vports is the same for both e-switches */
int nvports = esw->total_vports;
void *misc;
int err, i;
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec)
return -ENOMEM;
peer_miss_rules_setup(peer_dev, spec, &dest);
flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
if (!flows) {
err = -ENOMEM;
goto alloc_flows_err;
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
misc_parameters);
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
err = PTR_ERR(flow);
goto add_pf_flow_err;
}
flows[MLX5_VPORT_PF] = flow;
}
if (mlx5_ecpf_vport_exists(esw->dev)) {
MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
err = PTR_ERR(flow);
goto add_ecpf_flow_err;
}
flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
}
mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) {
MLX5_SET(fte_match_set_misc, misc, source_port, i);
flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
spec, &flow_act, &dest, 1);
if (IS_ERR(flow)) {
err = PTR_ERR(flow);
goto add_vf_flow_err;
}
flows[i] = flow;
}
esw->fdb_table.offloads.peer_miss_rules = flows;
kvfree(spec);
return 0;
add_vf_flow_err:
nvports = --i;
mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports)
mlx5_del_flow_rules(flows[i]);
if (mlx5_ecpf_vport_exists(esw->dev))
mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
add_ecpf_flow_err:
if (mlx5_core_is_ecpf_esw_manager(esw->dev))
mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
add_pf_flow_err:
esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
kvfree(flows);
alloc_flows_err:
kvfree(spec);
return err;
}
static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
{
struct mlx5_flow_handle **flows;
int i;
flows = esw->fdb_table.offloads.peer_miss_rules;
mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev))
mlx5_del_flow_rules(flows[i]);
if (mlx5_ecpf_vport_exists(esw->dev))
mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
if (mlx5_core_is_ecpf_esw_manager(esw->dev))
mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
kvfree(flows);
}
static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
{
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_destination dest = {};
struct mlx5_flow_handle *flow_rule = NULL;
struct mlx5_flow_spec *spec;
void *headers_c;
void *headers_v;
int err = 0;
u8 *dmac_c;
u8 *dmac_v;
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
err = -ENOMEM;
goto out;
}
spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
outer_headers);
dmac_c = MLX5_ADDR_OF(fte_match_param, headers_c,
outer_headers.dmac_47_16);
dmac_c[0] = 0x01;
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport.num = esw->manager_vport;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
&flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add unicast miss flow rule err %d\n", err);
goto out;
}
esw->fdb_table.offloads.miss_rule_uni = flow_rule;
headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
outer_headers);
dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v,
outer_headers.dmac_47_16);
dmac_v[0] = 0x01;
flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
&flow_act, &dest, 1);
if (IS_ERR(flow_rule)) {
err = PTR_ERR(flow_rule);
esw_warn(esw->dev, "FDB: Failed to add multicast miss flow rule err %d\n", err);
mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
goto out;
}
esw->fdb_table.offloads.miss_rule_multi = flow_rule;
out:
kvfree(spec);
return err;
}
#define ESW_OFFLOADS_NUM_GROUPS 4
/* Firmware currently has 4 pool of 4 sizes that it supports (ESW_POOLS),
* and a virtual memory region of 16M (ESW_SIZE), this region is duplicated
* for each flow table pool. We can allocate up to 16M of each pool,
* and we keep track of how much we used via put/get_sz_to_pool.
* Firmware doesn't report any of this for now.
* ESW_POOL is expected to be sorted from large to small
*/
#define ESW_SIZE (16 * 1024 * 1024)
const unsigned int ESW_POOLS[4] = { 4 * 1024 * 1024, 1 * 1024 * 1024,
64 * 1024, 4 * 1024 };
static int
get_sz_from_pool(struct mlx5_eswitch *esw)
{
int sz = 0, i;
for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
if (esw->fdb_table.offloads.fdb_left[i]) {
--esw->fdb_table.offloads.fdb_left[i];
sz = ESW_POOLS[i];
break;
}
}
return sz;
}
static void
put_sz_to_pool(struct mlx5_eswitch *esw, int sz)
{
int i;
for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++) {
if (sz >= ESW_POOLS[i]) {
++esw->fdb_table.offloads.fdb_left[i];
break;
}
}
}
static struct mlx5_flow_table *
create_next_size_table(struct mlx5_eswitch *esw,
struct mlx5_flow_namespace *ns,
u16 table_prio,
int level,
u32 flags)
{
struct mlx5_flow_table *fdb;
int sz;
sz = get_sz_from_pool(esw);
if (!sz)
return ERR_PTR(-ENOSPC);
fdb = mlx5_create_auto_grouped_flow_table(ns,
table_prio,
sz,
ESW_OFFLOADS_NUM_GROUPS,
level,
flags);
if (IS_ERR(fdb)) {
esw_warn(esw->dev, "Failed to create FDB Table err %d (table prio: %d, level: %d, size: %d)\n",
(int)PTR_ERR(fdb), table_prio, level, sz);
put_sz_to_pool(esw, sz);
}
return fdb;
}
static struct mlx5_flow_table *
esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
{
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_table *fdb = NULL;
struct mlx5_flow_namespace *ns;
int table_prio, l = 0;
u32 flags = 0;
if (chain == FDB_SLOW_PATH_CHAIN)
return esw->fdb_table.offloads.slow_fdb;
mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
fdb = fdb_prio_table(esw, chain, prio, level).fdb;
if (fdb) {
/* take ref on earlier levels as well */
while (level >= 0)
fdb_prio_table(esw, chain, prio, level--).num_rules++;
mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
return fdb;
}
ns = mlx5_get_fdb_sub_ns(dev, chain);
if (!ns) {
esw_warn(dev, "Failed to get FDB sub namespace\n");
mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
return ERR_PTR(-EOPNOTSUPP);
}
if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
table_prio = (chain * FDB_MAX_PRIO) + prio - 1;
/* create earlier levels for correct fs_core lookup when
* connecting tables
*/
for (l = 0; l <= level; l++) {
if (fdb_prio_table(esw, chain, prio, l).fdb) {
fdb_prio_table(esw, chain, prio, l).num_rules++;
continue;
}
fdb = create_next_size_table(esw, ns, table_prio, l, flags);
if (IS_ERR(fdb)) {
l--;
goto err_create_fdb;
}
fdb_prio_table(esw, chain, prio, l).fdb = fdb;
fdb_prio_table(esw, chain, prio, l).num_rules = 1;
}
mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
return fdb;
err_create_fdb:
mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
if (l >= 0)
esw_put_prio_table(esw, chain, prio, l);
return fdb;
}
static void
esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
{
int l;
if (chain == FDB_SLOW_PATH_CHAIN)
return;
mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
for (l = level; l >= 0; l--) {
if (--(fdb_prio_table(esw, chain, prio, l).num_rules) > 0)
continue;
put_sz_to_pool(esw, fdb_prio_table(esw, chain, prio, l).fdb->max_fte);
mlx5_destroy_flow_table(fdb_prio_table(esw, chain, prio, l).fdb);
fdb_prio_table(esw, chain, prio, l).fdb = NULL;
}
mutex_unlock(&esw->fdb_table.offloads.fdb_prio_lock);
}
static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
{
/* If lazy creation isn't supported, deref the fast path tables */
if (!(esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)) {
esw_put_prio_table(esw, 0, 1, 1);
esw_put_prio_table(esw, 0, 1, 0);
}
}
#define MAX_PF_SQ 256
#define MAX_SQ_NVPORTS 32
static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_core_dev *dev = esw->dev;
u32 *flow_group_in, max_flow_counter;
struct mlx5_flow_namespace *root_ns;
struct mlx5_flow_table *fdb = NULL;
int table_size, ix, err = 0, i;
struct mlx5_flow_group *g;
u32 flags = 0, fdb_max;
void *match_criteria;
u8 *dmac;
esw_debug(esw->dev, "Create offloads FDB Tables\n");
flow_group_in = kvzalloc(inlen, GFP_KERNEL);
if (!flow_group_in)
return -ENOMEM;
root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
if (!root_ns) {
esw_warn(dev, "Failed to get FDB flow namespace\n");
err = -EOPNOTSUPP;
goto ns_err;
}
max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
MLX5_CAP_GEN(dev, max_flow_counter_15_0);
fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(2^%d))\n",
MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size),
max_flow_counter, ESW_OFFLOADS_NUM_GROUPS,
fdb_max);
for (i = 0; i < ARRAY_SIZE(ESW_POOLS); i++)
esw->fdb_table.offloads.fdb_left[i] =
ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
MLX5_ESW_MISS_FLOWS + esw->total_vports;
/* create the slow path fdb with encap set, so further table instances
* can be created at run time while VFs are probed if the FW allows that.
*/
if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
ft_attr.flags = flags;
ft_attr.max_fte = table_size;
ft_attr.prio = FDB_SLOW_PATH;
fdb = mlx5_create_flow_table(root_ns, &ft_attr);
if (IS_ERR(fdb)) {
err = PTR_ERR(fdb);
esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err);
goto slow_fdb_err;
}
esw->fdb_table.offloads.slow_fdb = fdb;
/* If lazy creation isn't supported, open the fast path tables now */
if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, multi_fdb_encap) &&
esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
esw->fdb_table.flags &= ~ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
esw_warn(dev, "Lazy creation of flow tables isn't supported, ignoring priorities\n");
esw_get_prio_table(esw, 0, 1, 0);
esw_get_prio_table(esw, 0, 1, 1);
} else {
esw_debug(dev, "Lazy creation of flow tables supported, deferring table opening\n");
esw->fdb_table.flags |= ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED;
}
/* create send-to-vport group */
memset(flow_group_in, 0, inlen);
MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
MLX5_MATCH_MISC_PARAMETERS);
match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn);
MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port);
ix = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ;
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, ix - 1);
g = mlx5_create_flow_group(fdb, flow_group_in);
if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create send-to-vport flow group err(%d)\n", err);
goto send_vport_err;
}
esw->fdb_table.offloads.send_to_vport_grp = g;
/* create peer esw miss group */
memset(flow_group_in, 0, inlen);
MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
MLX5_MATCH_MISC_PARAMETERS);
match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
match_criteria);
MLX5_SET_TO_ONES(fte_match_param, match_criteria,
misc_parameters.source_port);
MLX5_SET_TO_ONES(fte_match_param, match_criteria,
misc_parameters.source_eswitch_owner_vhca_id);
MLX5_SET(create_flow_group_in, flow_group_in,
source_eswitch_owner_vhca_id_valid, 1);
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
ix + esw->total_vports - 1);
ix += esw->total_vports;
g = mlx5_create_flow_group(fdb, flow_group_in);
if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
goto peer_miss_err;
}
esw->fdb_table.offloads.peer_miss_grp = g;
/* create miss group */
memset(flow_group_in, 0, inlen);
MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
MLX5_MATCH_OUTER_HEADERS);
match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
match_criteria);
dmac = MLX5_ADDR_OF(fte_match_param, match_criteria,
outer_headers.dmac_47_16);
dmac[0] = 0x01;
MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
ix + MLX5_ESW_MISS_FLOWS);
g = mlx5_create_flow_group(fdb, flow_group_in);
if (IS_ERR(g)) {
err = PTR_ERR(g);
esw_warn(dev, "Failed to create miss flow group err(%d)\n", err);
goto miss_err;
}
esw->fdb_table.offloads.miss_grp = g;
err = esw_add_fdb_miss_rule(esw);
if (err)
goto miss_rule_err;
esw->nvports = nvports;
kvfree(flow_group_in);
return 0;
miss_rule_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
miss_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
peer_miss_err:
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
send_vport_err:
esw_destroy_offloads_fast_fdb_tables(esw);
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
slow_fdb_err:
ns_err:
kvfree(flow_group_in);
return err;
}
static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
{
if (!esw->fdb_table.offloads.slow_fdb)
return;
esw_debug(esw->dev, "Destroy offloads FDB Tables\n");
mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
esw_destroy_offloads_fast_fdb_tables(esw);
}
static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
{
struct mlx5_flow_table_attr ft_attr = {};
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_flow_table *ft_offloads;
struct mlx5_flow_namespace *ns;
int err = 0;
ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
if (!ns) {
esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
return -EOPNOTSUPP;
}
ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
if (IS_ERR(ft_offloads)) {
err = PTR_ERR(ft_offloads);
esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err);
return err;
}
esw->offloads.ft_offloads = ft_offloads;
return 0;
}
static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
{
struct mlx5_esw_offload *offloads = &esw->offloads;
mlx5_destroy_flow_table(offloads->ft_offloads);
}
static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
{
int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
struct mlx5_flow_group *g;
u32 *flow_group_in;
void *match_criteria, *misc;
int err = 0;
nvports = nvports + MLX5_ESW_MISS_FLOWS;
flow_group_in = kvzalloc(inlen, GFP_KERNEL);
if (!flow_group_in)
return -ENOMEM;
/* create vport rx group */
memset(flow_group_in, 0, inlen);
MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
MLX5_MATCH_MISC_PARAMETERS);
match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
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, nvports - 1);
g = mlx5_create_flow_group(esw->offloads.ft_offloads, flow_group_in);
if (IS_ERR(g)) {
err = PTR_ERR(g);
mlx5_core_warn(esw->dev, "Failed to create vport rx group err %d\n", err);
goto out;
}
esw->offloads.vport_rx_group = g;
out:
kvfree(flow_group_in);
return err;
}
static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw)
{
mlx5_destroy_flow_group(esw->offloads.vport_rx_group);
}
struct mlx5_flow_handle *
mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport,
struct mlx5_flow_destination *dest)
{
struct mlx5_flow_act flow_act = {0};
struct mlx5_flow_handle *flow_rule;
struct mlx5_flow_spec *spec;
void *misc;
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
flow_rule = ERR_PTR(-ENOMEM);
goto out;
}
misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
MLX5_SET(fte_match_set_misc, misc, source_port, vport);
misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
&flow_act, dest, 1);
if (IS_ERR(flow_rule)) {
esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule));
goto out;
}
out:
kvfree(spec);
return flow_rule;
}
static int esw_offloads_start(struct mlx5_eswitch *esw,
struct netlink_ext_ack *extack)
{
int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
if (esw->mode != SRIOV_LEGACY &&
!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
NL_SET_ERR_MSG_MOD(extack,
"Can't set offloads mode, SRIOV legacy not enabled");
return -EINVAL;
}
mlx5_eswitch_disable_sriov(esw);
err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch to offloads");
err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
if (err1) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch back to legacy");
}
}
if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
if (mlx5_eswitch_inline_mode_get(esw,
num_vfs,
&esw->offloads.inline_mode)) {
esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
NL_SET_ERR_MSG_MOD(extack,
"Inline mode is different between vports");
}
}
return err;
}
void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
{
kfree(esw->offloads.vport_reps);
}
int esw_offloads_init_reps(struct mlx5_eswitch *esw)
{
int total_vports = MLX5_TOTAL_VPORTS(esw->dev);
struct mlx5_core_dev *dev = esw->dev;
struct mlx5_eswitch_rep *rep;
u8 hw_id[ETH_ALEN], rep_type;
int vport;
esw->offloads.vport_reps = kcalloc(total_vports,
sizeof(struct mlx5_eswitch_rep),
GFP_KERNEL);
if (!esw->offloads.vport_reps)
return -ENOMEM;
mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
mlx5_esw_for_all_reps(esw, vport, rep) {
rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
ether_addr_copy(rep->hw_id, hw_id);
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
rep->rep_if[rep_type].state = REP_UNREGISTERED;
}
return 0;
}
static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep, u8 rep_type)
{
if (rep->rep_if[rep_type].state != REP_LOADED)
return;
rep->rep_if[rep_type].unload(rep);
rep->rep_if[rep_type].state = REP_REGISTERED;
}
static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
if (mlx5_ecpf_vport_exists(esw->dev)) {
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
__esw_offloads_unload_rep(esw, rep, rep_type);
}
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
__esw_offloads_unload_rep(esw, rep, rep_type);
}
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
__esw_offloads_unload_rep(esw, rep, rep_type);
}
static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
int i;
mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
__esw_offloads_unload_rep(esw, rep, rep_type);
}
static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
{
u8 rep_type = NUM_REP_TYPES;
while (rep_type-- > 0)
__unload_reps_vf_vport(esw, nvports, rep_type);
}
static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
u8 rep_type)
{
__unload_reps_vf_vport(esw, nvports, rep_type);
/* Special vports must be the last to unload. */
__unload_reps_special_vport(esw, rep_type);
}
static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
{
u8 rep_type = NUM_REP_TYPES;
while (rep_type-- > 0)
__unload_reps_all_vport(esw, nvports, rep_type);
}
static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep, u8 rep_type)
{
int err = 0;
if (rep->rep_if[rep_type].state != REP_REGISTERED)
return 0;
err = rep->rep_if[rep_type].load(esw->dev, rep);
if (err)
return err;
rep->rep_if[rep_type].state = REP_LOADED;
return 0;
}
static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
int err;
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
err = __esw_offloads_load_rep(esw, rep, rep_type);
if (err)
return err;
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
err = __esw_offloads_load_rep(esw, rep, rep_type);
if (err)
goto err_pf;
}
if (mlx5_ecpf_vport_exists(esw->dev)) {
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
err = __esw_offloads_load_rep(esw, rep, rep_type);
if (err)
goto err_ecpf;
}
return 0;
err_ecpf:
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
__esw_offloads_unload_rep(esw, rep, rep_type);
}
err_pf:
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
__esw_offloads_unload_rep(esw, rep, rep_type);
return err;
}
static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
int err, i;
mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
err = __esw_offloads_load_rep(esw, rep, rep_type);
if (err)
goto err_vf;
}
return 0;
err_vf:
__unload_reps_vf_vport(esw, --i, rep_type);
return err;
}
static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
{
u8 rep_type = 0;
int err;
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
err = __load_reps_vf_vport(esw, nvports, rep_type);
if (err)
goto err_reps;
}
return err;
err_reps:
while (rep_type-- > 0)
__unload_reps_vf_vport(esw, nvports, rep_type);
return err;
}
static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
u8 rep_type)
{
int err;
/* Special vports must be loaded first. */
err = __load_reps_special_vport(esw, rep_type);
if (err)
return err;
err = __load_reps_vf_vport(esw, nvports, rep_type);
if (err)
goto err_vfs;
return 0;
err_vfs:
__unload_reps_special_vport(esw, rep_type);
return err;
}
static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports)
{
u8 rep_type = 0;
int err;
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
err = __load_reps_all_vport(esw, nvports, rep_type);
if (err)
goto err_reps;
}
return err;
err_reps:
while (rep_type-- > 0)
__unload_reps_all_vport(esw, nvports, rep_type);
return err;
}
#define ESW_OFFLOADS_DEVCOM_PAIR (0)
#define ESW_OFFLOADS_DEVCOM_UNPAIR (1)
static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
struct mlx5_eswitch *peer_esw)
{
int err;
err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
if (err)
return err;
return 0;
}
static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
{
mlx5e_tc_clean_fdb_peer_flows(esw);
esw_del_fdb_peer_miss_rules(esw);
}
static int mlx5_esw_offloads_devcom_event(int event,
void *my_data,
void *event_data)
{
struct mlx5_eswitch *esw = my_data;
struct mlx5_eswitch *peer_esw = event_data;
struct mlx5_devcom *devcom = esw->dev->priv.devcom;
int err;
switch (event) {
case ESW_OFFLOADS_DEVCOM_PAIR:
err = mlx5_esw_offloads_pair(esw, peer_esw);
if (err)
goto err_out;
err = mlx5_esw_offloads_pair(peer_esw, esw);
if (err)
goto err_pair;
mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true);
break;
case ESW_OFFLOADS_DEVCOM_UNPAIR:
if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
break;
mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
mlx5_esw_offloads_unpair(peer_esw);
mlx5_esw_offloads_unpair(esw);
break;
}
return 0;
err_pair:
mlx5_esw_offloads_unpair(esw);
err_out:
mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
event, err);
return err;
}
static void esw_offloads_devcom_init(struct mlx5_eswitch *esw)
{
struct mlx5_devcom *devcom = esw->dev->priv.devcom;
INIT_LIST_HEAD(&esw->offloads.peer_flows);
mutex_init(&esw->offloads.peer_mutex);
if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
return;
mlx5_devcom_register_component(devcom,
MLX5_DEVCOM_ESW_OFFLOADS,
mlx5_esw_offloads_devcom_event,
esw);
mlx5_devcom_send_event(devcom,
MLX5_DEVCOM_ESW_OFFLOADS,
ESW_OFFLOADS_DEVCOM_PAIR, esw);
}
static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
{
struct mlx5_devcom *devcom = esw->dev->priv.devcom;
if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
return;
mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
ESW_OFFLOADS_DEVCOM_UNPAIR, esw);
mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
}
static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
{
int err;
memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
err = esw_create_offloads_fdb_tables(esw, nvports);
if (err)
return err;
err = esw_create_offloads_table(esw, nvports);
if (err)
goto create_ft_err;
err = esw_create_vport_rx_group(esw, nvports);
if (err)
goto create_fg_err;
return 0;
create_fg_err:
esw_destroy_offloads_table(esw);
create_ft_err:
esw_destroy_offloads_fdb_tables(esw);
return err;
}
static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
{
esw_destroy_vport_rx_group(esw);
esw_destroy_offloads_table(esw);
esw_destroy_offloads_fdb_tables(esw);
}
static void esw_host_params_event_handler(struct work_struct *work)
{
struct mlx5_host_work *host_work;
struct mlx5_eswitch *esw;
int err, num_vf = 0;
host_work = container_of(work, struct mlx5_host_work, work);
esw = host_work->esw;
err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf);
if (err || num_vf == esw->host_info.num_vfs)
goto out;
/* Number of VFs can only change from "0 to x" or "x to 0". */
if (esw->host_info.num_vfs > 0) {
esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs);
} else {
err = esw_offloads_load_vf_reps(esw, num_vf);
if (err)
goto out;
}
esw->host_info.num_vfs = num_vf;
out:
kfree(host_work);
}
static int esw_host_params_event(struct notifier_block *nb,
unsigned long type, void *data)
{
struct mlx5_host_work *host_work;
struct mlx5_host_info *host_info;
struct mlx5_eswitch *esw;
host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
if (!host_work)
return NOTIFY_DONE;
host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb);
esw = container_of(host_info, struct mlx5_eswitch, host_info);
host_work->esw = esw;
INIT_WORK(&host_work->work, esw_host_params_event_handler);
queue_work(esw->work_queue, &host_work->work);
return NOTIFY_OK;
}
int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
int total_nvports)
{
int err;
err = esw_offloads_steering_init(esw, total_nvports);
if (err)
return err;
err = esw_offloads_load_all_reps(esw, vf_nvports);
if (err)
goto err_reps;
esw_offloads_devcom_init(esw);
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event,
HOST_PARAMS_CHANGE);
mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb);
esw->host_info.num_vfs = vf_nvports;
}
return 0;
err_reps:
esw_offloads_steering_cleanup(esw);
return err;
}
static int esw_offloads_stop(struct mlx5_eswitch *esw,
struct netlink_ext_ack *extack)
{
int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
mlx5_eswitch_disable_sriov(esw);
err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
if (err1) {
NL_SET_ERR_MSG_MOD(extack,
"Failed setting eswitch back to offloads");
}
}
return err;
}
void esw_offloads_cleanup(struct mlx5_eswitch *esw)
{
u16 num_vfs;
if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb);
flush_workqueue(esw->work_queue);
num_vfs = esw->host_info.num_vfs;
} else {
num_vfs = esw->dev->priv.sriov.num_vfs;
}
esw_offloads_devcom_cleanup(esw);
esw_offloads_unload_all_reps(esw, num_vfs);
esw_offloads_steering_cleanup(esw);
}
static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
{
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
*mlx5_mode = SRIOV_LEGACY;
break;
case DEVLINK_ESWITCH_MODE_SWITCHDEV:
*mlx5_mode = SRIOV_OFFLOADS;
break;
default:
return -EINVAL;
}
return 0;
}
static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
{
switch (mlx5_mode) {
case SRIOV_LEGACY:
*mode = DEVLINK_ESWITCH_MODE_LEGACY;
break;
case SRIOV_OFFLOADS:
*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
break;
default:
return -EINVAL;
}
return 0;
}
static int esw_inline_mode_from_devlink(u8 mode, u8 *mlx5_mode)
{
switch (mode) {
case DEVLINK_ESWITCH_INLINE_MODE_NONE:
*mlx5_mode = MLX5_INLINE_MODE_NONE;
break;
case DEVLINK_ESWITCH_INLINE_MODE_LINK:
*mlx5_mode = MLX5_INLINE_MODE_L2;
break;
case DEVLINK_ESWITCH_INLINE_MODE_NETWORK:
*mlx5_mode = MLX5_INLINE_MODE_IP;
break;
case DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT:
*mlx5_mode = MLX5_INLINE_MODE_TCP_UDP;
break;
default:
return -EINVAL;
}
return 0;
}
static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode)
{
switch (mlx5_mode) {
case MLX5_INLINE_MODE_NONE:
*mode = DEVLINK_ESWITCH_INLINE_MODE_NONE;
break;
case MLX5_INLINE_MODE_L2:
*mode = DEVLINK_ESWITCH_INLINE_MODE_LINK;
break;
case MLX5_INLINE_MODE_IP:
*mode = DEVLINK_ESWITCH_INLINE_MODE_NETWORK;
break;
case MLX5_INLINE_MODE_TCP_UDP:
*mode = DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT;
break;
default:
return -EINVAL;
}
return 0;
}
static int mlx5_devlink_eswitch_check(struct devlink *devlink)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
return -EOPNOTSUPP;
if(!MLX5_ESWITCH_MANAGER(dev))
return -EPERM;
if (dev->priv.eswitch->mode == SRIOV_NONE &&
!mlx5_core_is_ecpf_esw_manager(dev))
return -EOPNOTSUPP;
return 0;
}
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
u16 cur_mlx5_mode, mlx5_mode = 0;
int err;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
cur_mlx5_mode = dev->priv.eswitch->mode;
if (esw_mode_from_devlink(mode, &mlx5_mode))
return -EINVAL;
if (cur_mlx5_mode == mlx5_mode)
return 0;
if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
return esw_offloads_start(dev->priv.eswitch, extack);
else if (mode == DEVLINK_ESWITCH_MODE_LEGACY)
return esw_offloads_stop(dev->priv.eswitch, extack);
else
return -EINVAL;
}
int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
int err;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
return esw_mode_to_devlink(dev->priv.eswitch->mode, mode);
}
int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
int err, vport;
u8 mlx5_mode;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
return 0;
/* fall through */
case MLX5_CAP_INLINE_MODE_L2:
NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set");
return -EOPNOTSUPP;
case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
break;
}
if (esw->offloads.num_flows > 0) {
NL_SET_ERR_MSG_MOD(extack,
"Can't set inline mode when flows are configured");
return -EOPNOTSUPP;
}
err = esw_inline_mode_from_devlink(mode, &mlx5_mode);
if (err)
goto out;
for (vport = 1; vport < esw->enabled_vports; vport++) {
err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
"Failed to set min inline on vport");
goto revert_inline_mode;
}
}
esw->offloads.inline_mode = mlx5_mode;
return 0;
revert_inline_mode:
while (--vport > 0)
mlx5_modify_nic_vport_min_inline(dev,
vport,
esw->offloads.inline_mode);
out:
return err;
}
int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
int err;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
}
int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
{
u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
struct mlx5_core_dev *dev = esw->dev;
int vport;
if (!MLX5_CAP_GEN(dev, vport_group_manager))
return -EOPNOTSUPP;
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
mlx5_mode = MLX5_INLINE_MODE_NONE;
goto out;
case MLX5_CAP_INLINE_MODE_L2:
mlx5_mode = MLX5_INLINE_MODE_L2;
goto out;
case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
goto query_vports;
}
query_vports:
for (vport = 1; vport <= nvfs; vport++) {
mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
if (vport > 1 && prev_mlx5_mode != mlx5_mode)
return -EINVAL;
prev_mlx5_mode = mlx5_mode;
}
out:
*mode = mlx5_mode;
return 0;
}
int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap,
struct netlink_ext_ack *extack)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
int err;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE &&
(!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)))
return -EOPNOTSUPP;
if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
return -EOPNOTSUPP;
if (esw->mode == SRIOV_LEGACY) {
esw->offloads.encap = encap;
return 0;
}
if (esw->offloads.encap == encap)
return 0;
if (esw->offloads.num_flows > 0) {
NL_SET_ERR_MSG_MOD(extack,
"Can't set encapsulation when flows are configured");
return -EOPNOTSUPP;
}
esw_destroy_offloads_fdb_tables(esw);
esw->offloads.encap = encap;
err = esw_create_offloads_fdb_tables(esw, esw->nvports);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
"Failed re-creating fast FDB table");
esw->offloads.encap = !encap;
(void)esw_create_offloads_fdb_tables(esw, esw->nvports);
}
return err;
}
int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
{
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
int err;
err = mlx5_devlink_eswitch_check(devlink);
if (err)
return err;
*encap = esw->offloads.encap;
return 0;
}
void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep_if *__rep_if,
u8 rep_type)
{
struct mlx5_eswitch_rep_if *rep_if;
struct mlx5_eswitch_rep *rep;
int i;
mlx5_esw_for_all_reps(esw, i, rep) {
rep_if = &rep->rep_if[rep_type];
rep_if->load = __rep_if->load;
rep_if->unload = __rep_if->unload;
rep_if->get_proto_dev = __rep_if->get_proto_dev;
rep_if->priv = __rep_if->priv;
rep_if->state = REP_REGISTERED;
}
}
EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
{
u16 max_vf = mlx5_core_max_vfs(esw->dev);
struct mlx5_eswitch_rep *rep;
int i;
if (esw->mode == SRIOV_OFFLOADS)
__unload_reps_all_vport(esw, max_vf, rep_type);
mlx5_esw_for_all_reps(esw, i, rep)
rep->rep_if[rep_type].state = REP_UNREGISTERED;
}
EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
return rep->rep_if[rep_type].priv;
}
void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
int vport,
u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
rep = mlx5_eswitch_get_rep(esw, vport);
if (rep->rep_if[rep_type].state == REP_LOADED &&
rep->rep_if[rep_type].get_proto_dev)
return rep->rep_if[rep_type].get_proto_dev(rep);
return NULL;
}
EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
{
return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
}
EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);
struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
int vport)
{
return mlx5_eswitch_get_rep(esw, vport);
}
EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
|