summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
blob: bd8de6b9be718f967ca6967a06c00be21d2e3b6c (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
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
/*
 * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
 * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
 * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
 * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. 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.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/rhashtable.h>
#include <linux/bitops.h>
#include <linux/in6.h>
#include <linux/notifier.h>
#include <linux/inetdevice.h>
#include <net/netevent.h>
#include <net/neighbour.h>
#include <net/arp.h>
#include <net/ip_fib.h>

#include "spectrum.h"
#include "core.h"
#include "reg.h"

#define mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) \
	for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT)

static bool
mlxsw_sp_prefix_usage_subset(struct mlxsw_sp_prefix_usage *prefix_usage1,
			     struct mlxsw_sp_prefix_usage *prefix_usage2)
{
	unsigned char prefix;

	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage1) {
		if (!test_bit(prefix, prefix_usage2->b))
			return false;
	}
	return true;
}

static bool
mlxsw_sp_prefix_usage_eq(struct mlxsw_sp_prefix_usage *prefix_usage1,
			 struct mlxsw_sp_prefix_usage *prefix_usage2)
{
	return !memcmp(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1));
}

static bool
mlxsw_sp_prefix_usage_none(struct mlxsw_sp_prefix_usage *prefix_usage)
{
	struct mlxsw_sp_prefix_usage prefix_usage_none = {{ 0 } };

	return mlxsw_sp_prefix_usage_eq(prefix_usage, &prefix_usage_none);
}

static void
mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1,
			  struct mlxsw_sp_prefix_usage *prefix_usage2)
{
	memcpy(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1));
}

static void
mlxsw_sp_prefix_usage_zero(struct mlxsw_sp_prefix_usage *prefix_usage)
{
	memset(prefix_usage, 0, sizeof(*prefix_usage));
}

static void
mlxsw_sp_prefix_usage_set(struct mlxsw_sp_prefix_usage *prefix_usage,
			  unsigned char prefix_len)
{
	set_bit(prefix_len, prefix_usage->b);
}

static void
mlxsw_sp_prefix_usage_clear(struct mlxsw_sp_prefix_usage *prefix_usage,
			    unsigned char prefix_len)
{
	clear_bit(prefix_len, prefix_usage->b);
}

struct mlxsw_sp_fib_key {
	unsigned char addr[sizeof(struct in6_addr)];
	unsigned char prefix_len;
};

enum mlxsw_sp_fib_entry_type {
	MLXSW_SP_FIB_ENTRY_TYPE_REMOTE,
	MLXSW_SP_FIB_ENTRY_TYPE_LOCAL,
	MLXSW_SP_FIB_ENTRY_TYPE_TRAP,
};

struct mlxsw_sp_nexthop_group;

struct mlxsw_sp_fib_node {
	struct list_head entry_list;
	struct list_head list;
	struct rhash_head ht_node;
	struct mlxsw_sp_vr *vr;
	struct mlxsw_sp_fib_key key;
};

struct mlxsw_sp_fib_entry_params {
	u32 tb_id;
	u32 prio;
	u8 tos;
	u8 type;
};

struct mlxsw_sp_fib_entry {
	struct list_head list;
	struct mlxsw_sp_fib_node *fib_node;
	enum mlxsw_sp_fib_entry_type type;
	struct list_head nexthop_group_node;
	struct mlxsw_sp_nexthop_group *nh_group;
	struct mlxsw_sp_fib_entry_params params;
	bool offloaded;
};

struct mlxsw_sp_fib {
	struct rhashtable ht;
	struct list_head node_list;
	unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT];
	struct mlxsw_sp_prefix_usage prefix_usage;
};

static const struct rhashtable_params mlxsw_sp_fib_ht_params;

static struct mlxsw_sp_fib *mlxsw_sp_fib_create(void)
{
	struct mlxsw_sp_fib *fib;
	int err;

	fib = kzalloc(sizeof(*fib), GFP_KERNEL);
	if (!fib)
		return ERR_PTR(-ENOMEM);
	err = rhashtable_init(&fib->ht, &mlxsw_sp_fib_ht_params);
	if (err)
		goto err_rhashtable_init;
	INIT_LIST_HEAD(&fib->node_list);
	return fib;

err_rhashtable_init:
	kfree(fib);
	return ERR_PTR(err);
}

static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib)
{
	WARN_ON(!list_empty(&fib->node_list));
	rhashtable_destroy(&fib->ht);
	kfree(fib);
}

static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp, bool one_reserved)
{
	static struct mlxsw_sp_lpm_tree *lpm_tree;
	int i;

	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
		if (lpm_tree->ref_count == 0) {
			if (one_reserved)
				one_reserved = false;
			else
				return lpm_tree;
		}
	}
	return NULL;
}

static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp,
				   struct mlxsw_sp_lpm_tree *lpm_tree)
{
	char ralta_pl[MLXSW_REG_RALTA_LEN];

	mlxsw_reg_ralta_pack(ralta_pl, true,
			     (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
			     lpm_tree->id);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
}

static int mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_lpm_tree *lpm_tree)
{
	char ralta_pl[MLXSW_REG_RALTA_LEN];

	mlxsw_reg_ralta_pack(ralta_pl, false,
			     (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto,
			     lpm_tree->id);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
}

static int
mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_prefix_usage *prefix_usage,
				  struct mlxsw_sp_lpm_tree *lpm_tree)
{
	char ralst_pl[MLXSW_REG_RALST_LEN];
	u8 root_bin = 0;
	u8 prefix;
	u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD;

	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage)
		root_bin = prefix;

	mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id);
	mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) {
		if (prefix == 0)
			continue;
		mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix,
					 MLXSW_REG_RALST_BIN_NO_CHILD);
		last_prefix = prefix;
	}
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl);
}

static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp,
			 struct mlxsw_sp_prefix_usage *prefix_usage,
			 enum mlxsw_sp_l3proto proto, bool one_reserved)
{
	struct mlxsw_sp_lpm_tree *lpm_tree;
	int err;

	lpm_tree = mlxsw_sp_lpm_tree_find_unused(mlxsw_sp, one_reserved);
	if (!lpm_tree)
		return ERR_PTR(-EBUSY);
	lpm_tree->proto = proto;
	err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree);
	if (err)
		return ERR_PTR(err);

	err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage,
						lpm_tree);
	if (err)
		goto err_left_struct_set;
	memcpy(&lpm_tree->prefix_usage, prefix_usage,
	       sizeof(lpm_tree->prefix_usage));
	return lpm_tree;

err_left_struct_set:
	mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
	return ERR_PTR(err);
}

static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp,
				     struct mlxsw_sp_lpm_tree *lpm_tree)
{
	return mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree);
}

static struct mlxsw_sp_lpm_tree *
mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp,
		      struct mlxsw_sp_prefix_usage *prefix_usage,
		      enum mlxsw_sp_l3proto proto, bool one_reserved)
{
	struct mlxsw_sp_lpm_tree *lpm_tree;
	int i;

	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
		if (lpm_tree->ref_count != 0 &&
		    lpm_tree->proto == proto &&
		    mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage,
					     prefix_usage))
			goto inc_ref_count;
	}
	lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage,
					    proto, one_reserved);
	if (IS_ERR(lpm_tree))
		return lpm_tree;

inc_ref_count:
	lpm_tree->ref_count++;
	return lpm_tree;
}

static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
				 struct mlxsw_sp_lpm_tree *lpm_tree)
{
	if (--lpm_tree->ref_count == 0)
		return mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree);
	return 0;
}

static void mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp)
{
	struct mlxsw_sp_lpm_tree *lpm_tree;
	int i;

	for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) {
		lpm_tree = &mlxsw_sp->router.lpm_trees[i];
		lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN;
	}
}

static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp)
{
	struct mlxsw_sp_vr *vr;
	int i;

	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
		vr = &mlxsw_sp->router.vrs[i];
		if (!vr->used)
			return vr;
	}
	return NULL;
}

static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp,
				     struct mlxsw_sp_vr *vr)
{
	char raltb_pl[MLXSW_REG_RALTB_LEN];

	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
			     (enum mlxsw_reg_ralxx_protocol) vr->proto,
			     vr->lpm_tree->id);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
}

static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp,
				       struct mlxsw_sp_vr *vr)
{
	char raltb_pl[MLXSW_REG_RALTB_LEN];

	/* Bind to tree 0 which is default */
	mlxsw_reg_raltb_pack(raltb_pl, vr->id,
			     (enum mlxsw_reg_ralxx_protocol) vr->proto, 0);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
}

static u32 mlxsw_sp_fix_tb_id(u32 tb_id)
{
	/* For our purpose, squash main and local table into one */
	if (tb_id == RT_TABLE_LOCAL)
		tb_id = RT_TABLE_MAIN;
	return tb_id;
}

static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp,
					    u32 tb_id,
					    enum mlxsw_sp_l3proto proto)
{
	struct mlxsw_sp_vr *vr;
	int i;

	tb_id = mlxsw_sp_fix_tb_id(tb_id);

	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
		vr = &mlxsw_sp->router.vrs[i];
		if (vr->used && vr->proto == proto && vr->tb_id == tb_id)
			return vr;
	}
	return NULL;
}

static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp,
					      unsigned char prefix_len,
					      u32 tb_id,
					      enum mlxsw_sp_l3proto proto)
{
	struct mlxsw_sp_prefix_usage req_prefix_usage;
	struct mlxsw_sp_lpm_tree *lpm_tree;
	struct mlxsw_sp_vr *vr;
	int err;

	vr = mlxsw_sp_vr_find_unused(mlxsw_sp);
	if (!vr)
		return ERR_PTR(-EBUSY);
	vr->fib = mlxsw_sp_fib_create();
	if (IS_ERR(vr->fib))
		return ERR_CAST(vr->fib);

	vr->proto = proto;
	vr->tb_id = tb_id;
	mlxsw_sp_prefix_usage_zero(&req_prefix_usage);
	mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
	lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage,
					 proto, true);
	if (IS_ERR(lpm_tree)) {
		err = PTR_ERR(lpm_tree);
		goto err_tree_get;
	}
	vr->lpm_tree = lpm_tree;
	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
	if (err)
		goto err_tree_bind;

	vr->used = true;
	return vr;

err_tree_bind:
	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
err_tree_get:
	mlxsw_sp_fib_destroy(vr->fib);

	return ERR_PTR(err);
}

static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp,
				struct mlxsw_sp_vr *vr)
{
	mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, vr);
	mlxsw_sp_lpm_tree_put(mlxsw_sp, vr->lpm_tree);
	mlxsw_sp_fib_destroy(vr->fib);
	vr->used = false;
}

static int
mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
			   struct mlxsw_sp_prefix_usage *req_prefix_usage)
{
	struct mlxsw_sp_lpm_tree *lpm_tree = vr->lpm_tree;
	struct mlxsw_sp_lpm_tree *new_tree;
	int err;

	if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage))
		return 0;

	new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage,
					 vr->proto, false);
	if (IS_ERR(new_tree)) {
		/* We failed to get a tree according to the required
		 * prefix usage. However, the current tree might be still good
		 * for us if our requirement is subset of the prefixes used
		 * in the tree.
		 */
		if (mlxsw_sp_prefix_usage_subset(req_prefix_usage,
						 &lpm_tree->prefix_usage))
			return 0;
		return PTR_ERR(new_tree);
	}

	/* Prevent packet loss by overwriting existing binding */
	vr->lpm_tree = new_tree;
	err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, vr);
	if (err)
		goto err_tree_bind;
	mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree);

	return 0;

err_tree_bind:
	vr->lpm_tree = lpm_tree;
	mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree);
	return err;
}

static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp,
					   unsigned char prefix_len,
					   u32 tb_id,
					   enum mlxsw_sp_l3proto proto)
{
	struct mlxsw_sp_vr *vr;
	int err;

	tb_id = mlxsw_sp_fix_tb_id(tb_id);
	vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id, proto);
	if (!vr) {
		vr = mlxsw_sp_vr_create(mlxsw_sp, prefix_len, tb_id, proto);
		if (IS_ERR(vr))
			return vr;
	} else {
		struct mlxsw_sp_prefix_usage req_prefix_usage;

		mlxsw_sp_prefix_usage_cpy(&req_prefix_usage,
					  &vr->fib->prefix_usage);
		mlxsw_sp_prefix_usage_set(&req_prefix_usage, prefix_len);
		/* Need to replace LPM tree in case new prefix is required. */
		err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
						 &req_prefix_usage);
		if (err)
			return ERR_PTR(err);
	}
	return vr;
}

static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr)
{
	/* Destroy virtual router entity in case the associated FIB is empty
	 * and allow it to be used for other tables in future. Otherwise,
	 * check if some prefix usage did not disappear and change tree if
	 * that is the case. Note that in case new, smaller tree cannot be
	 * allocated, the original one will be kept being used.
	 */
	if (mlxsw_sp_prefix_usage_none(&vr->fib->prefix_usage))
		mlxsw_sp_vr_destroy(mlxsw_sp, vr);
	else
		mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, vr,
					   &vr->fib->prefix_usage);
}

static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp)
{
	struct mlxsw_sp_vr *vr;
	u64 max_vrs;
	int i;

	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_VRS))
		return -EIO;

	max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS);
	mlxsw_sp->router.vrs = kcalloc(max_vrs, sizeof(struct mlxsw_sp_vr),
				       GFP_KERNEL);
	if (!mlxsw_sp->router.vrs)
		return -ENOMEM;

	for (i = 0; i < max_vrs; i++) {
		vr = &mlxsw_sp->router.vrs[i];
		vr->id = i;
	}

	return 0;
}

static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp);

static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp)
{
	/* At this stage we're guaranteed not to have new incoming
	 * FIB notifications and the work queue is free from FIBs
	 * sitting on top of mlxsw netdevs. However, we can still
	 * have other FIBs queued. Flush the queue before flushing
	 * the device's tables. No need for locks, as we're the only
	 * writer.
	 */
	mlxsw_core_flush_owq();
	mlxsw_sp_router_fib_flush(mlxsw_sp);
	kfree(mlxsw_sp->router.vrs);
}

struct mlxsw_sp_neigh_key {
	struct neighbour *n;
};

struct mlxsw_sp_neigh_entry {
	struct list_head rif_list_node;
	struct rhash_head ht_node;
	struct mlxsw_sp_neigh_key key;
	u16 rif;
	bool connected;
	unsigned char ha[ETH_ALEN];
	struct list_head nexthop_list; /* list of nexthops using
					* this neigh entry
					*/
	struct list_head nexthop_neighs_list_node;
};

static const struct rhashtable_params mlxsw_sp_neigh_ht_params = {
	.key_offset = offsetof(struct mlxsw_sp_neigh_entry, key),
	.head_offset = offsetof(struct mlxsw_sp_neigh_entry, ht_node),
	.key_len = sizeof(struct mlxsw_sp_neigh_key),
};

static struct mlxsw_sp_neigh_entry *
mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n,
			   u16 rif)
{
	struct mlxsw_sp_neigh_entry *neigh_entry;

	neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_KERNEL);
	if (!neigh_entry)
		return NULL;

	neigh_entry->key.n = n;
	neigh_entry->rif = rif;
	INIT_LIST_HEAD(&neigh_entry->nexthop_list);

	return neigh_entry;
}

static void mlxsw_sp_neigh_entry_free(struct mlxsw_sp_neigh_entry *neigh_entry)
{
	kfree(neigh_entry);
}

static int
mlxsw_sp_neigh_entry_insert(struct mlxsw_sp *mlxsw_sp,
			    struct mlxsw_sp_neigh_entry *neigh_entry)
{
	return rhashtable_insert_fast(&mlxsw_sp->router.neigh_ht,
				      &neigh_entry->ht_node,
				      mlxsw_sp_neigh_ht_params);
}

static void
mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp,
			    struct mlxsw_sp_neigh_entry *neigh_entry)
{
	rhashtable_remove_fast(&mlxsw_sp->router.neigh_ht,
			       &neigh_entry->ht_node,
			       mlxsw_sp_neigh_ht_params);
}

static struct mlxsw_sp_neigh_entry *
mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
{
	struct mlxsw_sp_neigh_entry *neigh_entry;
	struct mlxsw_sp_rif *r;
	int err;

	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
	if (!r)
		return ERR_PTR(-EINVAL);

	neigh_entry = mlxsw_sp_neigh_entry_alloc(mlxsw_sp, n, r->rif);
	if (!neigh_entry)
		return ERR_PTR(-ENOMEM);

	err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry);
	if (err)
		goto err_neigh_entry_insert;

	list_add(&neigh_entry->rif_list_node, &r->neigh_list);

	return neigh_entry;

err_neigh_entry_insert:
	mlxsw_sp_neigh_entry_free(neigh_entry);
	return ERR_PTR(err);
}

static void
mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp *mlxsw_sp,
			     struct mlxsw_sp_neigh_entry *neigh_entry)
{
	list_del(&neigh_entry->rif_list_node);
	mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry);
	mlxsw_sp_neigh_entry_free(neigh_entry);
}

static struct mlxsw_sp_neigh_entry *
mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, struct neighbour *n)
{
	struct mlxsw_sp_neigh_key key;

	key.n = n;
	return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht,
				      &key, mlxsw_sp_neigh_ht_params);
}

static void
mlxsw_sp_router_neighs_update_interval_init(struct mlxsw_sp *mlxsw_sp)
{
	unsigned long interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME);

	mlxsw_sp->router.neighs_update.interval = jiffies_to_msecs(interval);
}

static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp,
						   char *rauhtd_pl,
						   int ent_index)
{
	struct net_device *dev;
	struct neighbour *n;
	__be32 dipn;
	u32 dip;
	u16 rif;

	mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip);

	if (!mlxsw_sp->rifs[rif]) {
		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n");
		return;
	}

	dipn = htonl(dip);
	dev = mlxsw_sp->rifs[rif]->dev;
	n = neigh_lookup(&arp_tbl, &dipn, dev);
	if (!n) {
		netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n",
			   &dip);
		return;
	}

	netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip);
	neigh_event_send(n, NULL);
	neigh_release(n);
}

static void mlxsw_sp_router_neigh_rec_ipv4_process(struct mlxsw_sp *mlxsw_sp,
						   char *rauhtd_pl,
						   int rec_index)
{
	u8 num_entries;
	int i;

	num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl,
								rec_index);
	/* Hardware starts counting at 0, so add 1. */
	num_entries++;

	/* Each record consists of several neighbour entries. */
	for (i = 0; i < num_entries; i++) {
		int ent_index;

		ent_index = rec_index * MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC + i;
		mlxsw_sp_router_neigh_ent_ipv4_process(mlxsw_sp, rauhtd_pl,
						       ent_index);
	}

}

static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp,
					      char *rauhtd_pl, int rec_index)
{
	switch (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, rec_index)) {
	case MLXSW_REG_RAUHTD_TYPE_IPV4:
		mlxsw_sp_router_neigh_rec_ipv4_process(mlxsw_sp, rauhtd_pl,
						       rec_index);
		break;
	case MLXSW_REG_RAUHTD_TYPE_IPV6:
		WARN_ON_ONCE(1);
		break;
	}
}

static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl)
{
	u8 num_rec, last_rec_index, num_entries;

	num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
	last_rec_index = num_rec - 1;

	if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM)
		return false;
	if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) ==
	    MLXSW_REG_RAUHTD_TYPE_IPV6)
		return true;

	num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl,
								last_rec_index);
	if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC)
		return true;
	return false;
}

static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp)
{
	char *rauhtd_pl;
	u8 num_rec;
	int i, err;

	rauhtd_pl = kmalloc(MLXSW_REG_RAUHTD_LEN, GFP_KERNEL);
	if (!rauhtd_pl)
		return -ENOMEM;

	/* Make sure the neighbour's netdev isn't removed in the
	 * process.
	 */
	rtnl_lock();
	do {
		mlxsw_reg_rauhtd_pack(rauhtd_pl, MLXSW_REG_RAUHTD_TYPE_IPV4);
		err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd),
				      rauhtd_pl);
		if (err) {
			dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to dump neighbour talbe\n");
			break;
		}
		num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl);
		for (i = 0; i < num_rec; i++)
			mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl,
							  i);
	} while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl));
	rtnl_unlock();

	kfree(rauhtd_pl);
	return err;
}

static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp)
{
	struct mlxsw_sp_neigh_entry *neigh_entry;

	/* Take RTNL mutex here to prevent lists from changes */
	rtnl_lock();
	list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list,
			    nexthop_neighs_list_node)
		/* If this neigh have nexthops, make the kernel think this neigh
		 * is active regardless of the traffic.
		 */
		neigh_event_send(neigh_entry->key.n, NULL);
	rtnl_unlock();
}

static void
mlxsw_sp_router_neighs_update_work_schedule(struct mlxsw_sp *mlxsw_sp)
{
	unsigned long interval = mlxsw_sp->router.neighs_update.interval;

	mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw,
			       msecs_to_jiffies(interval));
}

static void mlxsw_sp_router_neighs_update_work(struct work_struct *work)
{
	struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp,
						 router.neighs_update.dw.work);
	int err;

	err = mlxsw_sp_router_neighs_update_rauhtd(mlxsw_sp);
	if (err)
		dev_err(mlxsw_sp->bus_info->dev, "Could not update kernel for neigh activity");

	mlxsw_sp_router_neighs_update_nh(mlxsw_sp);

	mlxsw_sp_router_neighs_update_work_schedule(mlxsw_sp);
}

static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work)
{
	struct mlxsw_sp_neigh_entry *neigh_entry;
	struct mlxsw_sp *mlxsw_sp = container_of(work, struct mlxsw_sp,
						 router.nexthop_probe_dw.work);

	/* Iterate over nexthop neighbours, find those who are unresolved and
	 * send arp on them. This solves the chicken-egg problem when
	 * the nexthop wouldn't get offloaded until the neighbor is resolved
	 * but it wouldn't get resolved ever in case traffic is flowing in HW
	 * using different nexthop.
	 *
	 * Take RTNL mutex here to prevent lists from changes.
	 */
	rtnl_lock();
	list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list,
			    nexthop_neighs_list_node)
		if (!neigh_entry->connected)
			neigh_event_send(neigh_entry->key.n, NULL);
	rtnl_unlock();

	mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw,
			       MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL);
}

static void
mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
			      struct mlxsw_sp_neigh_entry *neigh_entry,
			      bool removing);

static enum mlxsw_reg_rauht_op mlxsw_sp_rauht_op(bool adding)
{
	return adding ? MLXSW_REG_RAUHT_OP_WRITE_ADD :
			MLXSW_REG_RAUHT_OP_WRITE_DELETE;
}

static void
mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp,
				struct mlxsw_sp_neigh_entry *neigh_entry,
				enum mlxsw_reg_rauht_op op)
{
	struct neighbour *n = neigh_entry->key.n;
	u32 dip = ntohl(*((__be32 *) n->primary_key));
	char rauht_pl[MLXSW_REG_RAUHT_LEN];

	mlxsw_reg_rauht_pack4(rauht_pl, op, neigh_entry->rif, neigh_entry->ha,
			      dip);
	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
}

static void
mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp,
			    struct mlxsw_sp_neigh_entry *neigh_entry,
			    bool adding)
{
	if (!adding && !neigh_entry->connected)
		return;
	neigh_entry->connected = adding;
	if (neigh_entry->key.n->tbl == &arp_tbl)
		mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry,
						mlxsw_sp_rauht_op(adding));
	else
		WARN_ON_ONCE(1);
}

struct mlxsw_sp_neigh_event_work {
	struct work_struct work;
	struct mlxsw_sp *mlxsw_sp;
	struct neighbour *n;
};

static void mlxsw_sp_router_neigh_event_work(struct work_struct *work)
{
	struct mlxsw_sp_neigh_event_work *neigh_work =
		container_of(work, struct mlxsw_sp_neigh_event_work, work);
	struct mlxsw_sp *mlxsw_sp = neigh_work->mlxsw_sp;
	struct mlxsw_sp_neigh_entry *neigh_entry;
	struct neighbour *n = neigh_work->n;
	unsigned char ha[ETH_ALEN];
	bool entry_connected;
	u8 nud_state, dead;

	/* If these parameters are changed after we release the lock,
	 * then we are guaranteed to receive another event letting us
	 * know about it.
	 */
	read_lock_bh(&n->lock);
	memcpy(ha, n->ha, ETH_ALEN);
	nud_state = n->nud_state;
	dead = n->dead;
	read_unlock_bh(&n->lock);

	rtnl_lock();
	entry_connected = nud_state & NUD_VALID && !dead;
	neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
	if (!entry_connected && !neigh_entry)
		goto out;
	if (!neigh_entry) {
		neigh_entry = mlxsw_sp_neigh_entry_create(mlxsw_sp, n);
		if (IS_ERR(neigh_entry))
			goto out;
	}

	memcpy(neigh_entry->ha, ha, ETH_ALEN);
	mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, entry_connected);
	mlxsw_sp_nexthop_neigh_update(mlxsw_sp, neigh_entry, !entry_connected);

	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);

out:
	rtnl_unlock();
	neigh_release(n);
	kfree(neigh_work);
}

int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
				   unsigned long event, void *ptr)
{
	struct mlxsw_sp_neigh_event_work *neigh_work;
	struct mlxsw_sp_port *mlxsw_sp_port;
	struct mlxsw_sp *mlxsw_sp;
	unsigned long interval;
	struct neigh_parms *p;
	struct neighbour *n;

	switch (event) {
	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
		p = ptr;

		/* We don't care about changes in the default table. */
		if (!p->dev || p->tbl != &arp_tbl)
			return NOTIFY_DONE;

		/* We are in atomic context and can't take RTNL mutex,
		 * so use RCU variant to walk the device chain.
		 */
		mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(p->dev);
		if (!mlxsw_sp_port)
			return NOTIFY_DONE;

		mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
		interval = jiffies_to_msecs(NEIGH_VAR(p, DELAY_PROBE_TIME));
		mlxsw_sp->router.neighs_update.interval = interval;

		mlxsw_sp_port_dev_put(mlxsw_sp_port);
		break;
	case NETEVENT_NEIGH_UPDATE:
		n = ptr;

		if (n->tbl != &arp_tbl)
			return NOTIFY_DONE;

		mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(n->dev);
		if (!mlxsw_sp_port)
			return NOTIFY_DONE;

		neigh_work = kzalloc(sizeof(*neigh_work), GFP_ATOMIC);
		if (!neigh_work) {
			mlxsw_sp_port_dev_put(mlxsw_sp_port);
			return NOTIFY_BAD;
		}

		INIT_WORK(&neigh_work->work, mlxsw_sp_router_neigh_event_work);
		neigh_work->mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
		neigh_work->n = n;

		/* Take a reference to ensure the neighbour won't be
		 * destructed until we drop the reference in delayed
		 * work.
		 */
		neigh_clone(n);
		mlxsw_core_schedule_work(&neigh_work->work);
		mlxsw_sp_port_dev_put(mlxsw_sp_port);
		break;
	}

	return NOTIFY_DONE;
}

static int mlxsw_sp_neigh_init(struct mlxsw_sp *mlxsw_sp)
{
	int err;

	err = rhashtable_init(&mlxsw_sp->router.neigh_ht,
			      &mlxsw_sp_neigh_ht_params);
	if (err)
		return err;

	/* Initialize the polling interval according to the default
	 * table.
	 */
	mlxsw_sp_router_neighs_update_interval_init(mlxsw_sp);

	/* Create the delayed works for the activity_update */
	INIT_DELAYED_WORK(&mlxsw_sp->router.neighs_update.dw,
			  mlxsw_sp_router_neighs_update_work);
	INIT_DELAYED_WORK(&mlxsw_sp->router.nexthop_probe_dw,
			  mlxsw_sp_router_probe_unresolved_nexthops);
	mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, 0);
	mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, 0);
	return 0;
}

static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
{
	cancel_delayed_work_sync(&mlxsw_sp->router.neighs_update.dw);
	cancel_delayed_work_sync(&mlxsw_sp->router.nexthop_probe_dw);
	rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
}

static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp,
				    const struct mlxsw_sp_rif *r)
{
	char rauht_pl[MLXSW_REG_RAUHT_LEN];

	mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL,
			     r->rif, r->addr);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl);
}

static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
					 struct mlxsw_sp_rif *r)
{
	struct mlxsw_sp_neigh_entry *neigh_entry, *tmp;

	mlxsw_sp_neigh_rif_flush(mlxsw_sp, r);
	list_for_each_entry_safe(neigh_entry, tmp, &r->neigh_list,
				 rif_list_node)
		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);
}

struct mlxsw_sp_nexthop_key {
	struct fib_nh *fib_nh;
};

struct mlxsw_sp_nexthop {
	struct list_head neigh_list_node; /* member of neigh entry list */
	struct list_head rif_list_node;
	struct mlxsw_sp_nexthop_group *nh_grp; /* pointer back to the group
						* this belongs to
						*/
	struct rhash_head ht_node;
	struct mlxsw_sp_nexthop_key key;
	struct mlxsw_sp_rif *r;
	u8 should_offload:1, /* set indicates this neigh is connected and
			      * should be put to KVD linear area of this group.
			      */
	   offloaded:1, /* set in case the neigh is actually put into
			 * KVD linear area of this group.
			 */
	   update:1; /* set indicates that MAC of this neigh should be
		      * updated in HW
		      */
	struct mlxsw_sp_neigh_entry *neigh_entry;
};

struct mlxsw_sp_nexthop_group_key {
	struct fib_info *fi;
};

struct mlxsw_sp_nexthop_group {
	struct rhash_head ht_node;
	struct list_head fib_list; /* list of fib entries that use this group */
	struct mlxsw_sp_nexthop_group_key key;
	u8 adj_index_valid:1,
	   gateway:1; /* routes using the group use a gateway */
	u32 adj_index;
	u16 ecmp_size;
	u16 count;
	struct mlxsw_sp_nexthop nexthops[0];
#define nh_rif	nexthops[0].r
};

static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = {
	.key_offset = offsetof(struct mlxsw_sp_nexthop_group, key),
	.head_offset = offsetof(struct mlxsw_sp_nexthop_group, ht_node),
	.key_len = sizeof(struct mlxsw_sp_nexthop_group_key),
};

static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp,
					 struct mlxsw_sp_nexthop_group *nh_grp)
{
	return rhashtable_insert_fast(&mlxsw_sp->router.nexthop_group_ht,
				      &nh_grp->ht_node,
				      mlxsw_sp_nexthop_group_ht_params);
}

static void mlxsw_sp_nexthop_group_remove(struct mlxsw_sp *mlxsw_sp,
					  struct mlxsw_sp_nexthop_group *nh_grp)
{
	rhashtable_remove_fast(&mlxsw_sp->router.nexthop_group_ht,
			       &nh_grp->ht_node,
			       mlxsw_sp_nexthop_group_ht_params);
}

static struct mlxsw_sp_nexthop_group *
mlxsw_sp_nexthop_group_lookup(struct mlxsw_sp *mlxsw_sp,
			      struct mlxsw_sp_nexthop_group_key key)
{
	return rhashtable_lookup_fast(&mlxsw_sp->router.nexthop_group_ht, &key,
				      mlxsw_sp_nexthop_group_ht_params);
}

static const struct rhashtable_params mlxsw_sp_nexthop_ht_params = {
	.key_offset = offsetof(struct mlxsw_sp_nexthop, key),
	.head_offset = offsetof(struct mlxsw_sp_nexthop, ht_node),
	.key_len = sizeof(struct mlxsw_sp_nexthop_key),
};

static int mlxsw_sp_nexthop_insert(struct mlxsw_sp *mlxsw_sp,
				   struct mlxsw_sp_nexthop *nh)
{
	return rhashtable_insert_fast(&mlxsw_sp->router.nexthop_ht,
				      &nh->ht_node, mlxsw_sp_nexthop_ht_params);
}

static void mlxsw_sp_nexthop_remove(struct mlxsw_sp *mlxsw_sp,
				    struct mlxsw_sp_nexthop *nh)
{
	rhashtable_remove_fast(&mlxsw_sp->router.nexthop_ht, &nh->ht_node,
			       mlxsw_sp_nexthop_ht_params);
}

static struct mlxsw_sp_nexthop *
mlxsw_sp_nexthop_lookup(struct mlxsw_sp *mlxsw_sp,
			struct mlxsw_sp_nexthop_key key)
{
	return rhashtable_lookup_fast(&mlxsw_sp->router.nexthop_ht, &key,
				      mlxsw_sp_nexthop_ht_params);
}

static int mlxsw_sp_adj_index_mass_update_vr(struct mlxsw_sp *mlxsw_sp,
					     struct mlxsw_sp_vr *vr,
					     u32 adj_index, u16 ecmp_size,
					     u32 new_adj_index,
					     u16 new_ecmp_size)
{
	char raleu_pl[MLXSW_REG_RALEU_LEN];

	mlxsw_reg_raleu_pack(raleu_pl,
			     (enum mlxsw_reg_ralxx_protocol) vr->proto, vr->id,
			     adj_index, ecmp_size, new_adj_index,
			     new_ecmp_size);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raleu), raleu_pl);
}

static int mlxsw_sp_adj_index_mass_update(struct mlxsw_sp *mlxsw_sp,
					  struct mlxsw_sp_nexthop_group *nh_grp,
					  u32 old_adj_index, u16 old_ecmp_size)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	struct mlxsw_sp_vr *vr = NULL;
	int err;

	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
		if (vr == fib_entry->fib_node->vr)
			continue;
		vr = fib_entry->fib_node->vr;
		err = mlxsw_sp_adj_index_mass_update_vr(mlxsw_sp, vr,
							old_adj_index,
							old_ecmp_size,
							nh_grp->adj_index,
							nh_grp->ecmp_size);
		if (err)
			return err;
	}
	return 0;
}

static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
				       struct mlxsw_sp_nexthop *nh)
{
	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
	char ratr_pl[MLXSW_REG_RATR_LEN];

	mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY,
			    true, adj_index, neigh_entry->rif);
	mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl);
}

static int
mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_nexthop_group *nh_grp,
				  bool reallocate)
{
	u32 adj_index = nh_grp->adj_index; /* base */
	struct mlxsw_sp_nexthop *nh;
	int i;
	int err;

	for (i = 0; i < nh_grp->count; i++) {
		nh = &nh_grp->nexthops[i];

		if (!nh->should_offload) {
			nh->offloaded = 0;
			continue;
		}

		if (nh->update || reallocate) {
			err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
							  adj_index, nh);
			if (err)
				return err;
			nh->update = 0;
			nh->offloaded = 1;
		}
		adj_index++;
	}
	return 0;
}

static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
				     struct mlxsw_sp_fib_entry *fib_entry);

static int
mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp,
				    struct mlxsw_sp_nexthop_group *nh_grp)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	int err;

	list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) {
		err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
		if (err)
			return err;
	}
	return 0;
}

static void
mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
			       struct mlxsw_sp_nexthop_group *nh_grp)
{
	struct mlxsw_sp_nexthop *nh;
	bool offload_change = false;
	u32 adj_index;
	u16 ecmp_size = 0;
	bool old_adj_index_valid;
	u32 old_adj_index;
	u16 old_ecmp_size;
	int ret;
	int i;
	int err;

	if (!nh_grp->gateway) {
		mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
		return;
	}

	for (i = 0; i < nh_grp->count; i++) {
		nh = &nh_grp->nexthops[i];

		if (nh->should_offload ^ nh->offloaded) {
			offload_change = true;
			if (nh->should_offload)
				nh->update = 1;
		}
		if (nh->should_offload)
			ecmp_size++;
	}
	if (!offload_change) {
		/* Nothing was added or removed, so no need to reallocate. Just
		 * update MAC on existing adjacency indexes.
		 */
		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp,
							false);
		if (err) {
			dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
			goto set_trap;
		}
		return;
	}
	if (!ecmp_size)
		/* No neigh of this group is connected so we just set
		 * the trap and let everthing flow through kernel.
		 */
		goto set_trap;

	ret = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size);
	if (ret < 0) {
		/* We ran out of KVD linear space, just set the
		 * trap and let everything flow through kernel.
		 */
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to allocate KVD linear area for nexthop group.\n");
		goto set_trap;
	}
	adj_index = ret;
	old_adj_index_valid = nh_grp->adj_index_valid;
	old_adj_index = nh_grp->adj_index;
	old_ecmp_size = nh_grp->ecmp_size;
	nh_grp->adj_index_valid = 1;
	nh_grp->adj_index = adj_index;
	nh_grp->ecmp_size = ecmp_size;
	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true);
	if (err) {
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
		goto set_trap;
	}

	if (!old_adj_index_valid) {
		/* The trap was set for fib entries, so we have to call
		 * fib entry update to unset it and use adjacency index.
		 */
		err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
		if (err) {
			dev_warn(mlxsw_sp->bus_info->dev, "Failed to add adjacency index to fib entries.\n");
			goto set_trap;
		}
		return;
	}

	err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
					     old_adj_index, old_ecmp_size);
	mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index);
	if (err) {
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
		goto set_trap;
	}
	return;

set_trap:
	old_adj_index_valid = nh_grp->adj_index_valid;
	nh_grp->adj_index_valid = 0;
	for (i = 0; i < nh_grp->count; i++) {
		nh = &nh_grp->nexthops[i];
		nh->offloaded = 0;
	}
	err = mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp);
	if (err)
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
	if (old_adj_index_valid)
		mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index);
}

static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
					    bool removing)
{
	if (!removing && !nh->should_offload)
		nh->should_offload = 1;
	else if (removing && nh->offloaded)
		nh->should_offload = 0;
	nh->update = 1;
}

static void
mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp *mlxsw_sp,
			      struct mlxsw_sp_neigh_entry *neigh_entry,
			      bool removing)
{
	struct mlxsw_sp_nexthop *nh;

	list_for_each_entry(nh, &neigh_entry->nexthop_list,
			    neigh_list_node) {
		__mlxsw_sp_nexthop_neigh_update(nh, removing);
		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
	}
}

static void mlxsw_sp_nexthop_rif_init(struct mlxsw_sp_nexthop *nh,
				      struct mlxsw_sp_rif *r)
{
	if (nh->r)
		return;

	nh->r = r;
	list_add(&nh->rif_list_node, &r->nexthop_list);
}

static void mlxsw_sp_nexthop_rif_fini(struct mlxsw_sp_nexthop *nh)
{
	if (!nh->r)
		return;

	list_del(&nh->rif_list_node);
	nh->r = NULL;
}

static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp,
				       struct mlxsw_sp_nexthop *nh)
{
	struct mlxsw_sp_neigh_entry *neigh_entry;
	struct fib_nh *fib_nh = nh->key.fib_nh;
	struct neighbour *n;
	u8 nud_state, dead;
	int err;

	if (!nh->nh_grp->gateway || nh->neigh_entry)
		return 0;

	/* Take a reference of neigh here ensuring that neigh would
	 * not be detructed before the nexthop entry is finished.
	 * The reference is taken either in neigh_lookup() or
	 * in neigh_create() in case n is not found.
	 */
	n = neigh_lookup(&arp_tbl, &fib_nh->nh_gw, fib_nh->nh_dev);
	if (!n) {
		n = neigh_create(&arp_tbl, &fib_nh->nh_gw, fib_nh->nh_dev);
		if (IS_ERR(n))
			return PTR_ERR(n);
		neigh_event_send(n, NULL);
	}
	neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n);
	if (!neigh_entry) {
		neigh_entry = mlxsw_sp_neigh_entry_create(mlxsw_sp, n);
		if (IS_ERR(neigh_entry)) {
			err = -EINVAL;
			goto err_neigh_entry_create;
		}
	}

	/* If that is the first nexthop connected to that neigh, add to
	 * nexthop_neighs_list
	 */
	if (list_empty(&neigh_entry->nexthop_list))
		list_add_tail(&neigh_entry->nexthop_neighs_list_node,
			      &mlxsw_sp->router.nexthop_neighs_list);

	nh->neigh_entry = neigh_entry;
	list_add_tail(&nh->neigh_list_node, &neigh_entry->nexthop_list);
	read_lock_bh(&n->lock);
	nud_state = n->nud_state;
	dead = n->dead;
	read_unlock_bh(&n->lock);
	__mlxsw_sp_nexthop_neigh_update(nh, !(nud_state & NUD_VALID && !dead));

	return 0;

err_neigh_entry_create:
	neigh_release(n);
	return err;
}

static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp,
					struct mlxsw_sp_nexthop *nh)
{
	struct mlxsw_sp_neigh_entry *neigh_entry = nh->neigh_entry;
	struct neighbour *n;

	if (!neigh_entry)
		return;
	n = neigh_entry->key.n;

	__mlxsw_sp_nexthop_neigh_update(nh, true);
	list_del(&nh->neigh_list_node);
	nh->neigh_entry = NULL;

	/* If that is the last nexthop connected to that neigh, remove from
	 * nexthop_neighs_list
	 */
	if (list_empty(&neigh_entry->nexthop_list))
		list_del(&neigh_entry->nexthop_neighs_list_node);

	if (!neigh_entry->connected && list_empty(&neigh_entry->nexthop_list))
		mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry);

	neigh_release(n);
}

static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp,
				 struct mlxsw_sp_nexthop_group *nh_grp,
				 struct mlxsw_sp_nexthop *nh,
				 struct fib_nh *fib_nh)
{
	struct net_device *dev = fib_nh->nh_dev;
	struct in_device *in_dev;
	struct mlxsw_sp_rif *r;
	int err;

	nh->nh_grp = nh_grp;
	nh->key.fib_nh = fib_nh;
	err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh);
	if (err)
		return err;

	in_dev = __in_dev_get_rtnl(dev);
	if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
	    fib_nh->nh_flags & RTNH_F_LINKDOWN)
		return 0;

	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
	if (!r)
		return 0;
	mlxsw_sp_nexthop_rif_init(nh, r);

	err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
	if (err)
		goto err_nexthop_neigh_init;

	return 0;

err_nexthop_neigh_init:
	mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
	return err;
}

static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_nexthop *nh)
{
	mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
	mlxsw_sp_nexthop_rif_fini(nh);
	mlxsw_sp_nexthop_remove(mlxsw_sp, nh);
}

static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp,
				   unsigned long event, struct fib_nh *fib_nh)
{
	struct mlxsw_sp_nexthop_key key;
	struct mlxsw_sp_nexthop *nh;
	struct mlxsw_sp_rif *r;

	if (mlxsw_sp->router.aborted)
		return;

	key.fib_nh = fib_nh;
	nh = mlxsw_sp_nexthop_lookup(mlxsw_sp, key);
	if (WARN_ON_ONCE(!nh))
		return;

	r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev);
	if (!r)
		return;

	switch (event) {
	case FIB_EVENT_NH_ADD:
		mlxsw_sp_nexthop_rif_init(nh, r);
		mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh);
		break;
	case FIB_EVENT_NH_DEL:
		mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
		mlxsw_sp_nexthop_rif_fini(nh);
		break;
	}

	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
}

static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
					   struct mlxsw_sp_rif *r)
{
	struct mlxsw_sp_nexthop *nh, *tmp;

	list_for_each_entry_safe(nh, tmp, &r->nexthop_list, rif_list_node) {
		mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh);
		mlxsw_sp_nexthop_rif_fini(nh);
		mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp);
	}
}

static struct mlxsw_sp_nexthop_group *
mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
{
	struct mlxsw_sp_nexthop_group *nh_grp;
	struct mlxsw_sp_nexthop *nh;
	struct fib_nh *fib_nh;
	size_t alloc_size;
	int i;
	int err;

	alloc_size = sizeof(*nh_grp) +
		     fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop);
	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
	if (!nh_grp)
		return ERR_PTR(-ENOMEM);
	INIT_LIST_HEAD(&nh_grp->fib_list);
	nh_grp->gateway = fi->fib_nh->nh_scope == RT_SCOPE_LINK;
	nh_grp->count = fi->fib_nhs;
	nh_grp->key.fi = fi;
	for (i = 0; i < nh_grp->count; i++) {
		nh = &nh_grp->nexthops[i];
		fib_nh = &fi->fib_nh[i];
		err = mlxsw_sp_nexthop_init(mlxsw_sp, nh_grp, nh, fib_nh);
		if (err)
			goto err_nexthop_init;
	}
	err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp);
	if (err)
		goto err_nexthop_group_insert;
	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
	return nh_grp;

err_nexthop_group_insert:
err_nexthop_init:
	for (i--; i >= 0; i--) {
		nh = &nh_grp->nexthops[i];
		mlxsw_sp_nexthop_fini(mlxsw_sp, nh);
	}
	kfree(nh_grp);
	return ERR_PTR(err);
}

static void
mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp,
			       struct mlxsw_sp_nexthop_group *nh_grp)
{
	struct mlxsw_sp_nexthop *nh;
	int i;

	mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp);
	for (i = 0; i < nh_grp->count; i++) {
		nh = &nh_grp->nexthops[i];
		mlxsw_sp_nexthop_fini(mlxsw_sp, nh);
	}
	mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp);
	WARN_ON_ONCE(nh_grp->adj_index_valid);
	kfree(nh_grp);
}

static int mlxsw_sp_nexthop_group_get(struct mlxsw_sp *mlxsw_sp,
				      struct mlxsw_sp_fib_entry *fib_entry,
				      struct fib_info *fi)
{
	struct mlxsw_sp_nexthop_group_key key;
	struct mlxsw_sp_nexthop_group *nh_grp;

	key.fi = fi;
	nh_grp = mlxsw_sp_nexthop_group_lookup(mlxsw_sp, key);
	if (!nh_grp) {
		nh_grp = mlxsw_sp_nexthop_group_create(mlxsw_sp, fi);
		if (IS_ERR(nh_grp))
			return PTR_ERR(nh_grp);
	}
	list_add_tail(&fib_entry->nexthop_group_node, &nh_grp->fib_list);
	fib_entry->nh_group = nh_grp;
	return 0;
}

static void mlxsw_sp_nexthop_group_put(struct mlxsw_sp *mlxsw_sp,
				       struct mlxsw_sp_fib_entry *fib_entry)
{
	struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;

	list_del(&fib_entry->nexthop_group_node);
	if (!list_empty(&nh_grp->fib_list))
		return;
	mlxsw_sp_nexthop_group_destroy(mlxsw_sp, nh_grp);
}

static bool
mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry)
{
	struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group;

	if (fib_entry->params.tos)
		return false;

	switch (fib_entry->type) {
	case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE:
		return !!nh_group->adj_index_valid;
	case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
		return !!nh_group->nh_rif;
	default:
		return false;
	}
}

static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
{
	fib_entry->offloaded = true;

	switch (fib_entry->fib_node->vr->proto) {
	case MLXSW_SP_L3_PROTO_IPV4:
		fib_info_offload_inc(fib_entry->nh_group->key.fi);
		break;
	case MLXSW_SP_L3_PROTO_IPV6:
		WARN_ON_ONCE(1);
	}
}

static void
mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
{
	switch (fib_entry->fib_node->vr->proto) {
	case MLXSW_SP_L3_PROTO_IPV4:
		fib_info_offload_dec(fib_entry->nh_group->key.fi);
		break;
	case MLXSW_SP_L3_PROTO_IPV6:
		WARN_ON_ONCE(1);
	}

	fib_entry->offloaded = false;
}

static void
mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry,
				   enum mlxsw_reg_ralue_op op, int err)
{
	switch (op) {
	case MLXSW_REG_RALUE_OP_WRITE_DELETE:
		if (!fib_entry->offloaded)
			return;
		return mlxsw_sp_fib_entry_offload_unset(fib_entry);
	case MLXSW_REG_RALUE_OP_WRITE_WRITE:
		if (err)
			return;
		if (mlxsw_sp_fib_entry_should_offload(fib_entry) &&
		    !fib_entry->offloaded)
			mlxsw_sp_fib_entry_offload_set(fib_entry);
		else if (!mlxsw_sp_fib_entry_should_offload(fib_entry) &&
			 fib_entry->offloaded)
			mlxsw_sp_fib_entry_offload_unset(fib_entry);
		return;
	default:
		return;
	}
}

static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp,
					 struct mlxsw_sp_fib_entry *fib_entry,
					 enum mlxsw_reg_ralue_op op)
{
	char ralue_pl[MLXSW_REG_RALUE_LEN];
	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
	enum mlxsw_reg_ralue_trap_action trap_action;
	u16 trap_id = 0;
	u32 adjacency_index = 0;
	u16 ecmp_size = 0;

	/* In case the nexthop group adjacency index is valid, use it
	 * with provided ECMP size. Otherwise, setup trap and pass
	 * traffic to kernel.
	 */
	if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
		adjacency_index = fib_entry->nh_group->adj_index;
		ecmp_size = fib_entry->nh_group->ecmp_size;
	} else {
		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
		trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
	}

	mlxsw_reg_ralue_pack4(ralue_pl,
			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
			      vr->id, fib_entry->fib_node->key.prefix_len,
			      *p_dip);
	mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id,
					adjacency_index, ecmp_size);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}

static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp,
					struct mlxsw_sp_fib_entry *fib_entry,
					enum mlxsw_reg_ralue_op op)
{
	struct mlxsw_sp_rif *r = fib_entry->nh_group->nh_rif;
	enum mlxsw_reg_ralue_trap_action trap_action;
	char ralue_pl[MLXSW_REG_RALUE_LEN];
	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;
	u16 trap_id = 0;
	u16 rif = 0;

	if (mlxsw_sp_fib_entry_should_offload(fib_entry)) {
		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP;
		rif = r->rif;
	} else {
		trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP;
		trap_id = MLXSW_TRAP_ID_RTR_INGRESS0;
	}

	mlxsw_reg_ralue_pack4(ralue_pl,
			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
			      vr->id, fib_entry->fib_node->key.prefix_len,
			      *p_dip);
	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}

static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp,
				       struct mlxsw_sp_fib_entry *fib_entry,
				       enum mlxsw_reg_ralue_op op)
{
	char ralue_pl[MLXSW_REG_RALUE_LEN];
	u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr;
	struct mlxsw_sp_vr *vr = fib_entry->fib_node->vr;

	mlxsw_reg_ralue_pack4(ralue_pl,
			      (enum mlxsw_reg_ralxx_protocol) vr->proto, op,
			      vr->id, fib_entry->fib_node->key.prefix_len,
			      *p_dip);
	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}

static int mlxsw_sp_fib_entry_op4(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_fib_entry *fib_entry,
				  enum mlxsw_reg_ralue_op op)
{
	switch (fib_entry->type) {
	case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE:
		return mlxsw_sp_fib_entry_op4_remote(mlxsw_sp, fib_entry, op);
	case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
		return mlxsw_sp_fib_entry_op4_local(mlxsw_sp, fib_entry, op);
	case MLXSW_SP_FIB_ENTRY_TYPE_TRAP:
		return mlxsw_sp_fib_entry_op4_trap(mlxsw_sp, fib_entry, op);
	}
	return -EINVAL;
}

static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
				 struct mlxsw_sp_fib_entry *fib_entry,
				 enum mlxsw_reg_ralue_op op)
{
	int err = -EINVAL;

	switch (fib_entry->fib_node->vr->proto) {
	case MLXSW_SP_L3_PROTO_IPV4:
		err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op);
		break;
	case MLXSW_SP_L3_PROTO_IPV6:
		return err;
	}
	mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, err);
	return err;
}

static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
				     struct mlxsw_sp_fib_entry *fib_entry)
{
	return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
				     MLXSW_REG_RALUE_OP_WRITE_WRITE);
}

static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp,
				  struct mlxsw_sp_fib_entry *fib_entry)
{
	return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
				     MLXSW_REG_RALUE_OP_WRITE_DELETE);
}

static int
mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
			     const struct fib_entry_notifier_info *fen_info,
			     struct mlxsw_sp_fib_entry *fib_entry)
{
	struct fib_info *fi = fen_info->fi;

	if (fen_info->type == RTN_LOCAL || fen_info->type == RTN_BROADCAST) {
		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
		return 0;
	}
	if (fen_info->type != RTN_UNICAST)
		return -EINVAL;
	if (fi->fib_nh->nh_scope != RT_SCOPE_LINK)
		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
	else
		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE;
	return 0;
}

static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp,
			   struct mlxsw_sp_fib_node *fib_node,
			   const struct fib_entry_notifier_info *fen_info)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	int err;

	fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL);
	if (!fib_entry) {
		err = -ENOMEM;
		goto err_fib_entry_alloc;
	}

	err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry);
	if (err)
		goto err_fib4_entry_type_set;

	err = mlxsw_sp_nexthop_group_get(mlxsw_sp, fib_entry, fen_info->fi);
	if (err)
		goto err_nexthop_group_get;

	fib_entry->params.prio = fen_info->fi->fib_priority;
	fib_entry->params.tb_id = fen_info->tb_id;
	fib_entry->params.type = fen_info->type;
	fib_entry->params.tos = fen_info->tos;

	fib_entry->fib_node = fib_node;

	return fib_entry;

err_nexthop_group_get:
err_fib4_entry_type_set:
	kfree(fib_entry);
err_fib_entry_alloc:
	return ERR_PTR(err);
}

static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp,
					struct mlxsw_sp_fib_entry *fib_entry)
{
	mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry);
	kfree(fib_entry);
}

static struct mlxsw_sp_fib_node *
mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
		       const struct fib_entry_notifier_info *fen_info);

static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib4_entry_lookup(struct mlxsw_sp *mlxsw_sp,
			   const struct fib_entry_notifier_info *fen_info)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	struct mlxsw_sp_fib_node *fib_node;

	fib_node = mlxsw_sp_fib4_node_get(mlxsw_sp, fen_info);
	if (IS_ERR(fib_node))
		return NULL;

	list_for_each_entry(fib_entry, &fib_node->entry_list, list) {
		if (fib_entry->params.tb_id == fen_info->tb_id &&
		    fib_entry->params.tos == fen_info->tos &&
		    fib_entry->params.type == fen_info->type &&
		    fib_entry->nh_group->key.fi == fen_info->fi) {
			return fib_entry;
		}
	}

	return NULL;
}

static const struct rhashtable_params mlxsw_sp_fib_ht_params = {
	.key_offset = offsetof(struct mlxsw_sp_fib_node, key),
	.head_offset = offsetof(struct mlxsw_sp_fib_node, ht_node),
	.key_len = sizeof(struct mlxsw_sp_fib_key),
	.automatic_shrinking = true,
};

static int mlxsw_sp_fib_node_insert(struct mlxsw_sp_fib *fib,
				    struct mlxsw_sp_fib_node *fib_node)
{
	return rhashtable_insert_fast(&fib->ht, &fib_node->ht_node,
				      mlxsw_sp_fib_ht_params);
}

static void mlxsw_sp_fib_node_remove(struct mlxsw_sp_fib *fib,
				     struct mlxsw_sp_fib_node *fib_node)
{
	rhashtable_remove_fast(&fib->ht, &fib_node->ht_node,
			       mlxsw_sp_fib_ht_params);
}

static struct mlxsw_sp_fib_node *
mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr,
			 size_t addr_len, unsigned char prefix_len)
{
	struct mlxsw_sp_fib_key key;

	memset(&key, 0, sizeof(key));
	memcpy(key.addr, addr, addr_len);
	key.prefix_len = prefix_len;
	return rhashtable_lookup_fast(&fib->ht, &key, mlxsw_sp_fib_ht_params);
}

static struct mlxsw_sp_fib_node *
mlxsw_sp_fib_node_create(struct mlxsw_sp_vr *vr, const void *addr,
			 size_t addr_len, unsigned char prefix_len)
{
	struct mlxsw_sp_fib_node *fib_node;

	fib_node = kzalloc(sizeof(*fib_node), GFP_KERNEL);
	if (!fib_node)
		return NULL;

	INIT_LIST_HEAD(&fib_node->entry_list);
	list_add(&fib_node->list, &vr->fib->node_list);
	memcpy(fib_node->key.addr, addr, addr_len);
	fib_node->key.prefix_len = prefix_len;
	mlxsw_sp_fib_node_insert(vr->fib, fib_node);
	fib_node->vr = vr;

	return fib_node;
}

static void mlxsw_sp_fib_node_destroy(struct mlxsw_sp_fib_node *fib_node)
{
	mlxsw_sp_fib_node_remove(fib_node->vr->fib, fib_node);
	list_del(&fib_node->list);
	WARN_ON(!list_empty(&fib_node->entry_list));
	kfree(fib_node);
}

static bool
mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node,
				 const struct mlxsw_sp_fib_entry *fib_entry)
{
	return list_first_entry(&fib_node->entry_list,
				struct mlxsw_sp_fib_entry, list) == fib_entry;
}

static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node)
{
	unsigned char prefix_len = fib_node->key.prefix_len;
	struct mlxsw_sp_fib *fib = fib_node->vr->fib;

	if (fib->prefix_ref_count[prefix_len]++ == 0)
		mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len);
}

static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node)
{
	unsigned char prefix_len = fib_node->key.prefix_len;
	struct mlxsw_sp_fib *fib = fib_node->vr->fib;

	if (--fib->prefix_ref_count[prefix_len] == 0)
		mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len);
}

static struct mlxsw_sp_fib_node *
mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp,
		       const struct fib_entry_notifier_info *fen_info)
{
	struct mlxsw_sp_fib_node *fib_node;
	struct mlxsw_sp_vr *vr;
	int err;

	vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->dst_len, fen_info->tb_id,
			     MLXSW_SP_L3_PROTO_IPV4);
	if (IS_ERR(vr))
		return ERR_CAST(vr);

	fib_node = mlxsw_sp_fib_node_lookup(vr->fib, &fen_info->dst,
					    sizeof(fen_info->dst),
					    fen_info->dst_len);
	if (fib_node)
		return fib_node;

	fib_node = mlxsw_sp_fib_node_create(vr, &fen_info->dst,
					    sizeof(fen_info->dst),
					    fen_info->dst_len);
	if (!fib_node) {
		err = -ENOMEM;
		goto err_fib_node_create;
	}

	return fib_node;

err_fib_node_create:
	mlxsw_sp_vr_put(mlxsw_sp, vr);
	return ERR_PTR(err);
}

static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp,
				   struct mlxsw_sp_fib_node *fib_node)
{
	struct mlxsw_sp_vr *vr = fib_node->vr;

	if (!list_empty(&fib_node->entry_list))
		return;
	mlxsw_sp_fib_node_destroy(fib_node);
	mlxsw_sp_vr_put(mlxsw_sp, vr);
}

static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib4_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
			      const struct mlxsw_sp_fib_entry_params *params)
{
	struct mlxsw_sp_fib_entry *fib_entry;

	list_for_each_entry(fib_entry, &fib_node->entry_list, list) {
		if (fib_entry->params.tb_id > params->tb_id)
			continue;
		if (fib_entry->params.tb_id != params->tb_id)
			break;
		if (fib_entry->params.tos > params->tos)
			continue;
		if (fib_entry->params.prio >= params->prio ||
		    fib_entry->params.tos < params->tos)
			return fib_entry;
	}

	return NULL;
}

static int mlxsw_sp_fib4_node_list_append(struct mlxsw_sp_fib_entry *fib_entry,
					  struct mlxsw_sp_fib_entry *new_entry)
{
	struct mlxsw_sp_fib_node *fib_node;

	if (WARN_ON(!fib_entry))
		return -EINVAL;

	fib_node = fib_entry->fib_node;
	list_for_each_entry_from(fib_entry, &fib_node->entry_list, list) {
		if (fib_entry->params.tb_id != new_entry->params.tb_id ||
		    fib_entry->params.tos != new_entry->params.tos ||
		    fib_entry->params.prio != new_entry->params.prio)
			break;
	}

	list_add_tail(&new_entry->list, &fib_entry->list);
	return 0;
}

static int
mlxsw_sp_fib4_node_list_insert(struct mlxsw_sp_fib_node *fib_node,
			       struct mlxsw_sp_fib_entry *new_entry,
			       bool replace, bool append)
{
	struct mlxsw_sp_fib_entry *fib_entry;

	fib_entry = mlxsw_sp_fib4_node_entry_find(fib_node, &new_entry->params);

	if (append)
		return mlxsw_sp_fib4_node_list_append(fib_entry, new_entry);
	if (replace && WARN_ON(!fib_entry))
		return -EINVAL;

	/* Insert new entry before replaced one, so that we can later
	 * remove the second.
	 */
	if (fib_entry) {
		list_add_tail(&new_entry->list, &fib_entry->list);
	} else {
		struct mlxsw_sp_fib_entry *last;

		list_for_each_entry(last, &fib_node->entry_list, list) {
			if (new_entry->params.tb_id > last->params.tb_id)
				break;
			fib_entry = last;
		}

		if (fib_entry)
			list_add(&new_entry->list, &fib_entry->list);
		else
			list_add(&new_entry->list, &fib_node->entry_list);
	}

	return 0;
}

static void
mlxsw_sp_fib4_node_list_remove(struct mlxsw_sp_fib_entry *fib_entry)
{
	list_del(&fib_entry->list);
}

static int
mlxsw_sp_fib4_node_entry_add(struct mlxsw_sp *mlxsw_sp,
			     const struct mlxsw_sp_fib_node *fib_node,
			     struct mlxsw_sp_fib_entry *fib_entry)
{
	if (!mlxsw_sp_fib_node_entry_is_first(fib_node, fib_entry))
		return 0;

	/* To prevent packet loss, overwrite the previously offloaded
	 * entry.
	 */
	if (!list_is_singular(&fib_node->entry_list)) {
		enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_DELETE;
		struct mlxsw_sp_fib_entry *n = list_next_entry(fib_entry, list);

		mlxsw_sp_fib_entry_offload_refresh(n, op, 0);
	}

	return mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
}

static void
mlxsw_sp_fib4_node_entry_del(struct mlxsw_sp *mlxsw_sp,
			     const struct mlxsw_sp_fib_node *fib_node,
			     struct mlxsw_sp_fib_entry *fib_entry)
{
	if (!mlxsw_sp_fib_node_entry_is_first(fib_node, fib_entry))
		return;

	/* Promote the next entry by overwriting the deleted entry */
	if (!list_is_singular(&fib_node->entry_list)) {
		struct mlxsw_sp_fib_entry *n = list_next_entry(fib_entry, list);
		enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_DELETE;

		mlxsw_sp_fib_entry_update(mlxsw_sp, n);
		mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, 0);
		return;
	}

	mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
}

static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp,
					 struct mlxsw_sp_fib_entry *fib_entry,
					 bool replace, bool append)
{
	struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
	int err;

	err = mlxsw_sp_fib4_node_list_insert(fib_node, fib_entry, replace,
					     append);
	if (err)
		return err;

	err = mlxsw_sp_fib4_node_entry_add(mlxsw_sp, fib_node, fib_entry);
	if (err)
		goto err_fib4_node_entry_add;

	mlxsw_sp_fib_node_prefix_inc(fib_node);

	return 0;

err_fib4_node_entry_add:
	mlxsw_sp_fib4_node_list_remove(fib_entry);
	return err;
}

static void
mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
				struct mlxsw_sp_fib_entry *fib_entry)
{
	struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;

	mlxsw_sp_fib_node_prefix_dec(fib_node);
	mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry);
	mlxsw_sp_fib4_node_list_remove(fib_entry);
}

static void mlxsw_sp_fib4_entry_replace(struct mlxsw_sp *mlxsw_sp,
					struct mlxsw_sp_fib_entry *fib_entry,
					bool replace)
{
	struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node;
	struct mlxsw_sp_fib_entry *replaced;

	if (!replace)
		return;

	/* We inserted the new entry before replaced one */
	replaced = list_next_entry(fib_entry, list);

	mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, replaced);
	mlxsw_sp_fib4_entry_destroy(mlxsw_sp, replaced);
	mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node);
}

static int
mlxsw_sp_router_fib4_add(struct mlxsw_sp *mlxsw_sp,
			 const struct fib_entry_notifier_info *fen_info,
			 bool replace, bool append)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	struct mlxsw_sp_fib_node *fib_node;
	int err;

	if (mlxsw_sp->router.aborted)
		return 0;

	fib_node = mlxsw_sp_fib4_node_get(mlxsw_sp, fen_info);
	if (IS_ERR(fib_node)) {
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to get FIB node\n");
		return PTR_ERR(fib_node);
	}

	fib_entry = mlxsw_sp_fib4_entry_create(mlxsw_sp, fib_node, fen_info);
	if (IS_ERR(fib_entry)) {
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to create FIB entry\n");
		err = PTR_ERR(fib_entry);
		goto err_fib4_entry_create;
	}

	err = mlxsw_sp_fib4_node_entry_link(mlxsw_sp, fib_entry, replace,
					    append);
	if (err) {
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to link FIB entry to node\n");
		goto err_fib4_node_entry_link;
	}

	mlxsw_sp_fib4_entry_replace(mlxsw_sp, fib_entry, replace);

	return 0;

err_fib4_node_entry_link:
	mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry);
err_fib4_entry_create:
	mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node);
	return err;
}

static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
				     struct fib_entry_notifier_info *fen_info)
{
	struct mlxsw_sp_fib_entry *fib_entry;
	struct mlxsw_sp_fib_node *fib_node;

	if (mlxsw_sp->router.aborted)
		return;

	fib_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info);
	if (WARN_ON(!fib_entry))
		return;
	fib_node = fib_entry->fib_node;

	mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib_entry);
	mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry);
	mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node);
}

static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp)
{
	char ralta_pl[MLXSW_REG_RALTA_LEN];
	char ralst_pl[MLXSW_REG_RALST_LEN];
	char raltb_pl[MLXSW_REG_RALTB_LEN];
	char ralue_pl[MLXSW_REG_RALUE_LEN];
	int err;

	mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4,
			     MLXSW_SP_LPM_TREE_MIN);
	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl);
	if (err)
		return err;

	mlxsw_reg_ralst_pack(ralst_pl, 0xff, MLXSW_SP_LPM_TREE_MIN);
	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl);
	if (err)
		return err;

	mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4,
			     MLXSW_SP_LPM_TREE_MIN);
	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl);
	if (err)
		return err;

	mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4,
			      MLXSW_REG_RALUE_OP_WRITE_WRITE, 0, 0, 0);
	mlxsw_reg_ralue_act_ip2me_pack(ralue_pl);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
}

static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp,
				     struct mlxsw_sp_fib_node *fib_node)
{
	struct mlxsw_sp_fib_entry *fib_entry, *tmp;

	list_for_each_entry_safe(fib_entry, tmp, &fib_node->entry_list, list) {
		bool do_break = &tmp->list == &fib_node->entry_list;

		mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib_entry);
		mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry);
		mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node);
		/* Break when entry list is empty and node was freed.
		 * Otherwise, we'll access freed memory in the next
		 * iteration.
		 */
		if (do_break)
			break;
	}
}

static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp,
				    struct mlxsw_sp_fib_node *fib_node)
{
	switch (fib_node->vr->proto) {
	case MLXSW_SP_L3_PROTO_IPV4:
		mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node);
		break;
	case MLXSW_SP_L3_PROTO_IPV6:
		WARN_ON_ONCE(1);
		break;
	}
}

static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp)
{
	struct mlxsw_sp_fib_node *fib_node, *tmp;
	struct mlxsw_sp_vr *vr;
	int i;

	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) {
		vr = &mlxsw_sp->router.vrs[i];

		if (!vr->used)
			continue;

		list_for_each_entry_safe(fib_node, tmp, &vr->fib->node_list,
					 list) {
			bool do_break = &tmp->list == &vr->fib->node_list;

			mlxsw_sp_fib_node_flush(mlxsw_sp, fib_node);
			if (do_break)
				break;
		}
	}
}

static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp)
{
	int err;

	if (mlxsw_sp->router.aborted)
		return;
	dev_warn(mlxsw_sp->bus_info->dev, "FIB abort triggered. Note that FIB entries are no longer being offloaded to this device.\n");
	mlxsw_sp_router_fib_flush(mlxsw_sp);
	mlxsw_sp->router.aborted = true;
	err = mlxsw_sp_router_set_abort_trap(mlxsw_sp);
	if (err)
		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n");
}

static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
{
	char ritr_pl[MLXSW_REG_RITR_LEN];
	int err;

	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
	if (WARN_ON_ONCE(err))
		return err;

	mlxsw_reg_ritr_enable_set(ritr_pl, false);
	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
}

void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
				   struct mlxsw_sp_rif *r)
{
	mlxsw_sp_router_rif_disable(mlxsw_sp, r->rif);
	mlxsw_sp_nexthop_rif_gone_sync(mlxsw_sp, r);
	mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, r);
}

static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
{
	char rgcr_pl[MLXSW_REG_RGCR_LEN];
	u64 max_rifs;
	int err;

	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
		return -EIO;

	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
	mlxsw_sp->rifs = kcalloc(max_rifs, sizeof(struct mlxsw_sp_rif *),
				 GFP_KERNEL);
	if (!mlxsw_sp->rifs)
		return -ENOMEM;

	mlxsw_reg_rgcr_pack(rgcr_pl, true);
	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
	if (err)
		goto err_rgcr_fail;

	return 0;

err_rgcr_fail:
	kfree(mlxsw_sp->rifs);
	return err;
}

static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
{
	char rgcr_pl[MLXSW_REG_RGCR_LEN];
	int i;

	mlxsw_reg_rgcr_pack(rgcr_pl, false);
	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);

	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++)
		WARN_ON_ONCE(mlxsw_sp->rifs[i]);

	kfree(mlxsw_sp->rifs);
}

struct mlxsw_sp_fib_event_work {
	struct work_struct work;
	union {
		struct fib_entry_notifier_info fen_info;
		struct fib_nh_notifier_info fnh_info;
	};
	struct mlxsw_sp *mlxsw_sp;
	unsigned long event;
};

static void mlxsw_sp_router_fib_event_work(struct work_struct *work)
{
	struct mlxsw_sp_fib_event_work *fib_work =
		container_of(work, struct mlxsw_sp_fib_event_work, work);
	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
	bool replace, append;
	int err;

	/* Protect internal structures from changes */
	rtnl_lock();
	switch (fib_work->event) {
	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
	case FIB_EVENT_ENTRY_APPEND: /* fall through */
	case FIB_EVENT_ENTRY_ADD:
		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
		append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
		err = mlxsw_sp_router_fib4_add(mlxsw_sp, &fib_work->fen_info,
					       replace, append);
		if (err)
			mlxsw_sp_router_fib4_abort(mlxsw_sp);
		fib_info_put(fib_work->fen_info.fi);
		break;
	case FIB_EVENT_ENTRY_DEL:
		mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info);
		fib_info_put(fib_work->fen_info.fi);
		break;
	case FIB_EVENT_RULE_ADD: /* fall through */
	case FIB_EVENT_RULE_DEL:
		mlxsw_sp_router_fib4_abort(mlxsw_sp);
		break;
	case FIB_EVENT_NH_ADD: /* fall through */
	case FIB_EVENT_NH_DEL:
		mlxsw_sp_nexthop_event(mlxsw_sp, fib_work->event,
				       fib_work->fnh_info.fib_nh);
		fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
		break;
	}
	rtnl_unlock();
	kfree(fib_work);
}

/* Called with rcu_read_lock() */
static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
				     unsigned long event, void *ptr)
{
	struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);
	struct mlxsw_sp_fib_event_work *fib_work;
	struct fib_notifier_info *info = ptr;

	if (!net_eq(info->net, &init_net))
		return NOTIFY_DONE;

	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
	if (WARN_ON(!fib_work))
		return NOTIFY_BAD;

	INIT_WORK(&fib_work->work, mlxsw_sp_router_fib_event_work);
	fib_work->mlxsw_sp = mlxsw_sp;
	fib_work->event = event;

	switch (event) {
	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
	case FIB_EVENT_ENTRY_APPEND: /* fall through */
	case FIB_EVENT_ENTRY_ADD: /* fall through */
	case FIB_EVENT_ENTRY_DEL:
		memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
		/* Take referece on fib_info to prevent it from being
		 * freed while work is queued. Release it afterwards.
		 */
		fib_info_hold(fib_work->fen_info.fi);
		break;
	case FIB_EVENT_NH_ADD: /* fall through */
	case FIB_EVENT_NH_DEL:
		memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info));
		fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
		break;
	}

	mlxsw_core_schedule_work(&fib_work->work);

	return NOTIFY_DONE;
}

static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb)
{
	struct mlxsw_sp *mlxsw_sp = container_of(nb, struct mlxsw_sp, fib_nb);

	/* Flush pending FIB notifications and then flush the device's
	 * table before requesting another dump. The FIB notification
	 * block is unregistered, so no need to take RTNL.
	 */
	mlxsw_core_flush_owq();
	mlxsw_sp_router_fib_flush(mlxsw_sp);
}

int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
{
	int err;

	INIT_LIST_HEAD(&mlxsw_sp->router.nexthop_neighs_list);
	err = __mlxsw_sp_router_init(mlxsw_sp);
	if (err)
		return err;

	err = rhashtable_init(&mlxsw_sp->router.nexthop_ht,
			      &mlxsw_sp_nexthop_ht_params);
	if (err)
		goto err_nexthop_ht_init;

	err = rhashtable_init(&mlxsw_sp->router.nexthop_group_ht,
			      &mlxsw_sp_nexthop_group_ht_params);
	if (err)
		goto err_nexthop_group_ht_init;

	mlxsw_sp_lpm_init(mlxsw_sp);
	err = mlxsw_sp_vrs_init(mlxsw_sp);
	if (err)
		goto err_vrs_init;

	err = mlxsw_sp_neigh_init(mlxsw_sp);
	if (err)
		goto err_neigh_init;

	mlxsw_sp->fib_nb.notifier_call = mlxsw_sp_router_fib_event;
	err = register_fib_notifier(&mlxsw_sp->fib_nb,
				    mlxsw_sp_router_fib_dump_flush);
	if (err)
		goto err_register_fib_notifier;

	return 0;

err_register_fib_notifier:
	mlxsw_sp_neigh_fini(mlxsw_sp);
err_neigh_init:
	mlxsw_sp_vrs_fini(mlxsw_sp);
err_vrs_init:
	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
err_nexthop_group_ht_init:
	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
err_nexthop_ht_init:
	__mlxsw_sp_router_fini(mlxsw_sp);
	return err;
}

void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
{
	unregister_fib_notifier(&mlxsw_sp->fib_nb);
	mlxsw_sp_neigh_fini(mlxsw_sp);
	mlxsw_sp_vrs_fini(mlxsw_sp);
	rhashtable_destroy(&mlxsw_sp->router.nexthop_group_ht);
	rhashtable_destroy(&mlxsw_sp->router.nexthop_ht);
	__mlxsw_sp_router_fini(mlxsw_sp);
}