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
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
|
/*-
* Copyright (c) 2004 Ruslan Ermilov and Vsevolod Lobko.
* Copyright (c) 2014 Yandex LLC
* Copyright (c) 2014 Alexander V. Chernikov
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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 <sys/cdefs.h>
__FBSDID("$FreeBSD$");
/*
* Lookup table support for ipfw.
*
* This file contains handlers for all generic tables' operations:
* add/del/flush entries, list/dump tables etc..
*
* Table data modification is protected by both UH and runtime lock
* while reading configuration/data is protected by UH lock.
*
* Lookup algorithms for all table types are located in ip_fw_table_algo.c
*/
#include "opt_ipfw.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rwlock.h>
#include <sys/rmlock.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/queue.h>
#include <net/if.h> /* ip_fw.h requires IFNAMSIZ */
#include <netinet/in.h>
#include <netinet/ip_var.h> /* struct ipfw_rule_ref */
#include <netinet/ip_fw.h>
#include <netpfil/ipfw/ip_fw_private.h>
#include <netpfil/ipfw/ip_fw_table.h>
/*
* Table has the following `type` concepts:
*
* `no.type` represents lookup key type (addr, ifp, uid, etc..)
* vmask represents bitmask of table values which are present at the moment.
* Special IPFW_VTYPE_LEGACY ( (uint32_t)-1 ) represents old
* single-value-for-all approach.
*/
struct table_config {
struct named_object no;
uint8_t tflags; /* type flags */
uint8_t locked; /* 1 if locked from changes */
uint8_t linked; /* 1 if already linked */
uint8_t ochanged; /* used by set swapping */
uint8_t vshared; /* 1 if using shared value array */
uint8_t spare[3];
uint32_t count; /* Number of records */
uint32_t limit; /* Max number of records */
uint32_t vmask; /* bitmask with supported values */
uint32_t ocount; /* used by set swapping */
uint64_t gencnt; /* generation count */
char tablename[64]; /* table name */
struct table_algo *ta; /* Callbacks for given algo */
void *astate; /* algorithm state */
struct table_info ti_copy; /* data to put to table_info */
struct namedobj_instance *vi;
};
static int find_table_err(struct namedobj_instance *ni, struct tid_info *ti,
struct table_config **tc);
static struct table_config *find_table(struct namedobj_instance *ni,
struct tid_info *ti);
static struct table_config *alloc_table_config(struct ip_fw_chain *ch,
struct tid_info *ti, struct table_algo *ta, char *adata, uint8_t tflags);
static void free_table_config(struct namedobj_instance *ni,
struct table_config *tc);
static int create_table_internal(struct ip_fw_chain *ch, struct tid_info *ti,
char *aname, ipfw_xtable_info *i, uint16_t *pkidx, int ref);
static void link_table(struct ip_fw_chain *ch, struct table_config *tc);
static void unlink_table(struct ip_fw_chain *ch, struct table_config *tc);
static int find_ref_table(struct ip_fw_chain *ch, struct tid_info *ti,
struct tentry_info *tei, uint32_t count, int op, struct table_config **ptc);
#define OP_ADD 1
#define OP_DEL 0
static int export_tables(struct ip_fw_chain *ch, ipfw_obj_lheader *olh,
struct sockopt_data *sd);
static void export_table_info(struct ip_fw_chain *ch, struct table_config *tc,
ipfw_xtable_info *i);
static int dump_table_tentry(void *e, void *arg);
static int dump_table_xentry(void *e, void *arg);
static int swap_tables(struct ip_fw_chain *ch, struct tid_info *a,
struct tid_info *b);
static int check_table_name(const char *name);
static int check_table_space(struct ip_fw_chain *ch, struct tableop_state *ts,
struct table_config *tc, struct table_info *ti, uint32_t count);
static int destroy_table(struct ip_fw_chain *ch, struct tid_info *ti);
static struct table_algo *find_table_algo(struct tables_config *tableconf,
struct tid_info *ti, char *name);
static void objheader_to_ti(struct _ipfw_obj_header *oh, struct tid_info *ti);
static void ntlv_to_ti(struct _ipfw_obj_ntlv *ntlv, struct tid_info *ti);
#define CHAIN_TO_NI(chain) (CHAIN_TO_TCFG(chain)->namehash)
#define KIDX_TO_TI(ch, k) (&(((struct table_info *)(ch)->tablestate)[k]))
#define TA_BUF_SZ 128 /* On-stack buffer for add/delete state */
void
rollback_toperation_state(struct ip_fw_chain *ch, void *object)
{
struct tables_config *tcfg;
struct op_state *os;
tcfg = CHAIN_TO_TCFG(ch);
TAILQ_FOREACH(os, &tcfg->state_list, next)
os->func(object, os);
}
void
add_toperation_state(struct ip_fw_chain *ch, struct tableop_state *ts)
{
struct tables_config *tcfg;
tcfg = CHAIN_TO_TCFG(ch);
TAILQ_INSERT_HEAD(&tcfg->state_list, &ts->opstate, next);
}
void
del_toperation_state(struct ip_fw_chain *ch, struct tableop_state *ts)
{
struct tables_config *tcfg;
tcfg = CHAIN_TO_TCFG(ch);
TAILQ_REMOVE(&tcfg->state_list, &ts->opstate, next);
}
void
tc_ref(struct table_config *tc)
{
tc->no.refcnt++;
}
void
tc_unref(struct table_config *tc)
{
tc->no.refcnt--;
}
static struct table_value *
get_table_value(struct ip_fw_chain *ch, struct table_config *tc, uint32_t kidx)
{
struct table_value *pval;
pval = (struct table_value *)ch->valuestate;
return (&pval[kidx]);
}
/*
* Checks if we're able to insert/update entry @tei into table
* w.r.t @tc limits.
* May alter @tei to indicate insertion error / insert
* options.
*
* Returns 0 if operation can be performed/
*/
static int
check_table_limit(struct table_config *tc, struct tentry_info *tei)
{
if (tc->limit == 0 || tc->count < tc->limit)
return (0);
if ((tei->flags & TEI_FLAGS_UPDATE) == 0) {
/* Notify userland on error cause */
tei->flags |= TEI_FLAGS_LIMIT;
return (EFBIG);
}
/*
* We have UPDATE flag set.
* Permit updating record (if found),
* but restrict adding new one since we've
* already hit the limit.
*/
tei->flags |= TEI_FLAGS_DONTADD;
return (0);
}
/*
* Convert algorithm callback return code into
* one of pre-defined states known by userland.
*/
static void
store_tei_result(struct tentry_info *tei, int op, int error, uint32_t num)
{
int flag;
flag = 0;
switch (error) {
case 0:
if (op == OP_ADD && num != 0)
flag = TEI_FLAGS_ADDED;
if (op == OP_DEL)
flag = TEI_FLAGS_DELETED;
break;
case ENOENT:
flag = TEI_FLAGS_NOTFOUND;
break;
case EEXIST:
flag = TEI_FLAGS_EXISTS;
break;
default:
flag = TEI_FLAGS_ERROR;
}
tei->flags |= flag;
}
/*
* Creates and references table with default parameters.
* Saves table config, algo and allocated kidx info @ptc, @pta and
* @pkidx if non-zero.
* Used for table auto-creation to support old binaries.
*
* Returns 0 on success.
*/
static int
create_table_compat(struct ip_fw_chain *ch, struct tid_info *ti,
uint16_t *pkidx)
{
ipfw_xtable_info xi;
int error;
memset(&xi, 0, sizeof(xi));
/* Set default value mask for legacy clients */
xi.vmask = IPFW_VTYPE_LEGACY;
error = create_table_internal(ch, ti, NULL, &xi, pkidx, 1);
if (error != 0)
return (error);
return (0);
}
/*
* Find and reference existing table optionally
* creating new one.
*
* Saves found table config into @ptc.
* Note function may drop/acquire UH_WLOCK.
* Returns 0 if table was found/created and referenced
* or non-zero return code.
*/
static int
find_ref_table(struct ip_fw_chain *ch, struct tid_info *ti,
struct tentry_info *tei, uint32_t count, int op,
struct table_config **ptc)
{
struct namedobj_instance *ni;
struct table_config *tc;
uint16_t kidx;
int error;
IPFW_UH_WLOCK_ASSERT(ch);
ni = CHAIN_TO_NI(ch);
tc = NULL;
if ((tc = find_table(ni, ti)) != NULL) {
/* check table type */
if (tc->no.subtype != ti->type)
return (EINVAL);
if (tc->locked != 0)
return (EACCES);
/* Try to exit early on limit hit */
if (op == OP_ADD && count == 1 &&
check_table_limit(tc, tei) != 0)
return (EFBIG);
/* Reference and return */
tc->no.refcnt++;
*ptc = tc;
return (0);
}
if (op == OP_DEL)
return (ESRCH);
/* Compatibility mode: create new table for old clients */
if ((tei->flags & TEI_FLAGS_COMPAT) == 0)
return (ESRCH);
IPFW_UH_WUNLOCK(ch);
error = create_table_compat(ch, ti, &kidx);
IPFW_UH_WLOCK(ch);
if (error != 0)
return (error);
tc = (struct table_config *)ipfw_objhash_lookup_kidx(ni, kidx);
KASSERT(tc != NULL, ("create_table_compat returned bad idx %d", kidx));
/* OK, now we've got referenced table. */
*ptc = tc;
return (0);
}
/*
* Rolls back already @added to @tc entries using state array @ta_buf_m.
* Assume the following layout:
* 1) ADD state (ta_buf_m[0] ... t_buf_m[added - 1]) for handling update cases
* 2) DEL state (ta_buf_m[count[ ... t_buf_m[count + added - 1])
* for storing deleted state
*/
static void
rollback_added_entries(struct ip_fw_chain *ch, struct table_config *tc,
struct table_info *tinfo, struct tentry_info *tei, caddr_t ta_buf_m,
uint32_t count, uint32_t added)
{
struct table_algo *ta;
struct tentry_info *ptei;
caddr_t v, vv;
size_t ta_buf_sz;
int error, i;
uint32_t num;
IPFW_UH_WLOCK_ASSERT(ch);
ta = tc->ta;
ta_buf_sz = ta->ta_buf_size;
v = ta_buf_m;
vv = v + count * ta_buf_sz;
for (i = 0; i < added; i++, v += ta_buf_sz, vv += ta_buf_sz) {
ptei = &tei[i];
if ((ptei->flags & TEI_FLAGS_UPDATED) != 0) {
/*
* We have old value stored by previous
* call in @ptei->value. Do add once again
* to restore it.
*/
error = ta->add(tc->astate, tinfo, ptei, v, &num);
KASSERT(error == 0, ("rollback UPDATE fail"));
KASSERT(num == 0, ("rollback UPDATE fail2"));
continue;
}
error = ta->prepare_del(ch, ptei, vv);
KASSERT(error == 0, ("pre-rollback INSERT failed"));
error = ta->del(tc->astate, tinfo, ptei, vv, &num);
KASSERT(error == 0, ("rollback INSERT failed"));
tc->count -= num;
}
}
/*
* Prepares add/del state for all @count entries in @tei.
* Uses either stack buffer (@ta_buf) or allocates a new one.
* Stores pointer to allocated buffer back to @ta_buf.
*
* Returns 0 on success.
*/
static int
prepare_batch_buffer(struct ip_fw_chain *ch, struct table_algo *ta,
struct tentry_info *tei, uint32_t count, int op, caddr_t *ta_buf)
{
caddr_t ta_buf_m, v;
size_t ta_buf_sz, sz;
struct tentry_info *ptei;
int error, i;
error = 0;
ta_buf_sz = ta->ta_buf_size;
if (count == 1) {
/* Sigle add/delete, use on-stack buffer */
memset(*ta_buf, 0, TA_BUF_SZ);
ta_buf_m = *ta_buf;
} else {
/*
* Multiple adds/deletes, allocate larger buffer
*
* Note we need 2xcount buffer for add case:
* we have hold both ADD state
* and DELETE state (this may be needed
* if we need to rollback all changes)
*/
sz = count * ta_buf_sz;
ta_buf_m = malloc((op == OP_ADD) ? sz * 2 : sz, M_TEMP,
M_WAITOK | M_ZERO);
}
v = ta_buf_m;
for (i = 0; i < count; i++, v += ta_buf_sz) {
ptei = &tei[i];
error = (op == OP_ADD) ?
ta->prepare_add(ch, ptei, v) : ta->prepare_del(ch, ptei, v);
/*
* Some syntax error (incorrect mask, or address, or
* anything). Return error regardless of atomicity
* settings.
*/
if (error != 0)
break;
}
*ta_buf = ta_buf_m;
return (error);
}
/*
* Flushes allocated state for each @count entries in @tei.
* Frees @ta_buf_m if differs from stack buffer @ta_buf.
*/
static void
flush_batch_buffer(struct ip_fw_chain *ch, struct table_algo *ta,
struct tentry_info *tei, uint32_t count, int rollback,
caddr_t ta_buf_m, caddr_t ta_buf)
{
caddr_t v;
struct tentry_info *ptei;
size_t ta_buf_sz;
int i;
ta_buf_sz = ta->ta_buf_size;
/* Run cleaning callback anyway */
v = ta_buf_m;
for (i = 0; i < count; i++, v += ta_buf_sz) {
ptei = &tei[i];
ta->flush_entry(ch, ptei, v);
if (ptei->ptv != NULL) {
free(ptei->ptv, M_IPFW);
ptei->ptv = NULL;
}
}
/* Clean up "deleted" state in case of rollback */
if (rollback != 0) {
v = ta_buf_m + count * ta_buf_sz;
for (i = 0; i < count; i++, v += ta_buf_sz)
ta->flush_entry(ch, &tei[i], v);
}
if (ta_buf_m != ta_buf)
free(ta_buf_m, M_TEMP);
}
static void
rollback_add_entry(void *object, struct op_state *_state)
{
struct ip_fw_chain *ch;
struct tableop_state *ts;
ts = (struct tableop_state *)_state;
if (ts->tc != object && ts->ch != object)
return;
ch = ts->ch;
IPFW_UH_WLOCK_ASSERT(ch);
/* Call specifid unlockers */
rollback_table_values(ts);
/* Indicate we've called */
ts->modified = 1;
}
/*
* Adds/updates one or more entries in table @ti.
*
* Function may drop/reacquire UH wlock multiple times due to
* items alloc, algorithm callbacks (check_space), value linkage
* (new values, value storage realloc), etc..
* Other processes like other adds (which may involve storage resize),
* table swaps (which changes table data and may change algo type),
* table modify (which may change value mask) may be executed
* simultaneously so we need to deal with it.
*
* The following approach was implemented:
* we have per-chain linked list, protected with UH lock.
* add_table_entry prepares special on-stack structure wthich is passed
* to its descendants. Users add this structure to this list before unlock.
* After performing needed operations and acquiring UH lock back, each user
* checks if structure has changed. If true, it rolls local state back and
* returns without error to the caller.
* add_table_entry() on its own checks if structure has changed and restarts
* its operation from the beginning (goto restart).
*
* Functions which are modifying fields of interest (currently
* resize_shared_value_storage() and swap_tables() )
* traverses given list while holding UH lock immediately before
* performing their operations calling function provided be list entry
* ( currently rollback_add_entry ) which performs rollback for all necessary
* state and sets appropriate values in structure indicating rollback
* has happened.
*
* Algo interaction:
* Function references @ti first to ensure table won't
* disappear or change its type.
* After that, prepare_add callback is called for each @tei entry.
* Next, we try to add each entry under UH+WHLOCK
* using add() callback.
* Finally, we free all state by calling flush_entry callback
* for each @tei.
*
* Returns 0 on success.
*/
int
add_table_entry(struct ip_fw_chain *ch, struct tid_info *ti,
struct tentry_info *tei, uint8_t flags, uint32_t count)
{
struct table_config *tc;
struct table_algo *ta;
uint16_t kidx;
int error, first_error, i, rollback;
uint32_t num, numadd;
struct tentry_info *ptei;
struct tableop_state ts;
char ta_buf[TA_BUF_SZ];
caddr_t ta_buf_m, v;
memset(&ts, 0, sizeof(ts));
ta = NULL;
IPFW_UH_WLOCK(ch);
/*
* Find and reference existing table.
*/
restart:
if (ts.modified != 0) {
IPFW_UH_WUNLOCK(ch);
flush_batch_buffer(ch, ta, tei, count, rollback,
ta_buf_m, ta_buf);
memset(&ts, 0, sizeof(ts));
ta = NULL;
IPFW_UH_WLOCK(ch);
}
error = find_ref_table(ch, ti, tei, count, OP_ADD, &tc);
if (error != 0) {
IPFW_UH_WUNLOCK(ch);
return (error);
}
ta = tc->ta;
/* Fill in tablestate */
ts.ch = ch;
ts.opstate.func = rollback_add_entry;
ts.tc = tc;
ts.vshared = tc->vshared;
ts.vmask = tc->vmask;
ts.ta = ta;
ts.tei = tei;
ts.count = count;
rollback = 0;
add_toperation_state(ch, &ts);
IPFW_UH_WUNLOCK(ch);
/* Allocate memory and prepare record(s) */
/* Pass stack buffer by default */
ta_buf_m = ta_buf;
error = prepare_batch_buffer(ch, ta, tei, count, OP_ADD, &ta_buf_m);
IPFW_UH_WLOCK(ch);
del_toperation_state(ch, &ts);
/* Drop reference we've used in first search */
tc->no.refcnt--;
/* Check prepare_batch_buffer() error */
if (error != 0)
goto cleanup;
/*
* Check if table swap has happened.
* (so table algo might be changed).
* Restart operation to achieve consistent behavior.
*/
if (ts.modified != 0)
goto restart;
/*
* Link all values values to shared/per-table value array.
*
* May release/reacquire UH_WLOCK.
*/
error = ipfw_link_table_values(ch, &ts);
if (error != 0)
goto cleanup;
if (ts.modified != 0)
goto restart;
/*
* Ensure we are able to add all entries without additional
* memory allocations. May release/reacquire UH_WLOCK.
*/
kidx = tc->no.kidx;
error = check_table_space(ch, &ts, tc, KIDX_TO_TI(ch, kidx), count);
if (error != 0)
goto cleanup;
if (ts.modified != 0)
goto restart;
/* We've got valid table in @tc. Let's try to add data */
kidx = tc->no.kidx;
ta = tc->ta;
numadd = 0;
first_error = 0;
IPFW_WLOCK(ch);
v = ta_buf_m;
for (i = 0; i < count; i++, v += ta->ta_buf_size) {
ptei = &tei[i];
num = 0;
/* check limit before adding */
if ((error = check_table_limit(tc, ptei)) == 0) {
error = ta->add(tc->astate, KIDX_TO_TI(ch, kidx),
ptei, v, &num);
/* Set status flag to inform userland */
store_tei_result(ptei, OP_ADD, error, num);
}
if (error == 0) {
/* Update number of records to ease limit checking */
tc->count += num;
numadd += num;
continue;
}
if (first_error == 0)
first_error = error;
/*
* Some error have happened. Check our atomicity
* settings: continue if atomicity is not required,
* rollback changes otherwise.
*/
if ((flags & IPFW_CTF_ATOMIC) == 0)
continue;
rollback_added_entries(ch, tc, KIDX_TO_TI(ch, kidx),
tei, ta_buf_m, count, i);
rollback = 1;
break;
}
IPFW_WUNLOCK(ch);
ipfw_garbage_table_values(ch, tc, tei, count, rollback);
/* Permit post-add algorithm grow/rehash. */
if (numadd != 0)
check_table_space(ch, NULL, tc, KIDX_TO_TI(ch, kidx), 0);
/* Return first error to user, if any */
error = first_error;
cleanup:
IPFW_UH_WUNLOCK(ch);
flush_batch_buffer(ch, ta, tei, count, rollback, ta_buf_m, ta_buf);
return (error);
}
/*
* Deletes one or more entries in table @ti.
*
* Returns 0 on success.
*/
int
del_table_entry(struct ip_fw_chain *ch, struct tid_info *ti,
struct tentry_info *tei, uint8_t flags, uint32_t count)
{
struct table_config *tc;
struct table_algo *ta;
struct tentry_info *ptei;
uint16_t kidx;
int error, first_error, i;
uint32_t num, numdel;
char ta_buf[TA_BUF_SZ];
caddr_t ta_buf_m, v;
/*
* Find and reference existing table.
*/
IPFW_UH_WLOCK(ch);
error = find_ref_table(ch, ti, tei, count, OP_DEL, &tc);
if (error != 0) {
IPFW_UH_WUNLOCK(ch);
return (error);
}
ta = tc->ta;
IPFW_UH_WUNLOCK(ch);
/* Allocate memory and prepare record(s) */
/* Pass stack buffer by default */
ta_buf_m = ta_buf;
error = prepare_batch_buffer(ch, ta, tei, count, OP_DEL, &ta_buf_m);
if (error != 0)
goto cleanup;
IPFW_UH_WLOCK(ch);
/* Drop reference we've used in first search */
tc->no.refcnt--;
/*
* Check if table algo is still the same.
* (changed ta may be the result of table swap).
*/
if (ta != tc->ta) {
IPFW_UH_WUNLOCK(ch);
error = EINVAL;
goto cleanup;
}
kidx = tc->no.kidx;
numdel = 0;
first_error = 0;
IPFW_WLOCK(ch);
v = ta_buf_m;
for (i = 0; i < count; i++, v += ta->ta_buf_size) {
ptei = &tei[i];
num = 0;
error = ta->del(tc->astate, KIDX_TO_TI(ch, kidx), ptei, v,
&num);
/* Save state for userland */
store_tei_result(ptei, OP_DEL, error, num);
if (error != 0 && first_error == 0)
first_error = error;
tc->count -= num;
numdel += num;
}
IPFW_WUNLOCK(ch);
/* Unlink non-used values */
ipfw_garbage_table_values(ch, tc, tei, count, 0);
if (numdel != 0) {
/* Run post-del hook to permit shrinking */
check_table_space(ch, NULL, tc, KIDX_TO_TI(ch, kidx), 0);
}
IPFW_UH_WUNLOCK(ch);
/* Return first error to user, if any */
error = first_error;
cleanup:
flush_batch_buffer(ch, ta, tei, count, 0, ta_buf_m, ta_buf);
return (error);
}
/*
* Ensure that table @tc has enough space to add @count entries without
* need for reallocation.
*
* Callbacks order:
* 0) need_modify() (UH_WLOCK) - checks if @count items can be added w/o resize.
*
* 1) alloc_modify (no locks, M_WAITOK) - alloc new state based on @pflags.
* 2) prepare_modifyt (UH_WLOCK) - copy old data into new storage
* 3) modify (UH_WLOCK + WLOCK) - switch pointers
* 4) flush_modify (UH_WLOCK) - free state, if needed
*
* Returns 0 on success.
*/
static int
check_table_space(struct ip_fw_chain *ch, struct tableop_state *ts,
struct table_config *tc, struct table_info *ti, uint32_t count)
{
struct table_algo *ta;
uint64_t pflags;
char ta_buf[TA_BUF_SZ];
int error;
IPFW_UH_WLOCK_ASSERT(ch);
error = 0;
ta = tc->ta;
if (ta->need_modify == NULL)
return (0);
/* Acquire reference not to loose @tc between locks/unlocks */
tc->no.refcnt++;
/*
* TODO: think about avoiding race between large add/large delete
* operation on algorithm which implements shrinking along with
* growing.
*/
while (true) {
pflags = 0;
if (ta->need_modify(tc->astate, ti, count, &pflags) == 0) {
error = 0;
break;
}
/* We have to shrink/grow table */
if (ts != NULL)
add_toperation_state(ch, ts);
IPFW_UH_WUNLOCK(ch);
memset(&ta_buf, 0, sizeof(ta_buf));
error = ta->prepare_mod(ta_buf, &pflags);
IPFW_UH_WLOCK(ch);
if (ts != NULL)
del_toperation_state(ch, ts);
if (error != 0)
break;
if (ts != NULL && ts->modified != 0) {
/*
* Swap operation has happened
* so we're currently operating on other
* table data. Stop doing this.
*/
ta->flush_mod(ta_buf);
break;
}
/* Check if we still need to alter table */
ti = KIDX_TO_TI(ch, tc->no.kidx);
if (ta->need_modify(tc->astate, ti, count, &pflags) == 0) {
IPFW_UH_WUNLOCK(ch);
/*
* Other thread has already performed resize.
* Flush our state and return.
*/
ta->flush_mod(ta_buf);
break;
}
error = ta->fill_mod(tc->astate, ti, ta_buf, &pflags);
if (error == 0) {
/* Do actual modification */
IPFW_WLOCK(ch);
ta->modify(tc->astate, ti, ta_buf, pflags);
IPFW_WUNLOCK(ch);
}
/* Anyway, flush data and retry */
ta->flush_mod(ta_buf);
}
tc->no.refcnt--;
return (error);
}
/*
* Adds or deletes record in table.
* Data layout (v0):
* Request: [ ip_fw3_opheader ipfw_table_xentry ]
*
* Returns 0 on success
*/
static int
manage_table_ent_v0(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
ipfw_table_xentry *xent;
struct tentry_info tei;
struct tid_info ti;
struct table_value v;
int error, hdrlen, read;
hdrlen = offsetof(ipfw_table_xentry, k);
/* Check minimum header size */
if (sd->valsize < (sizeof(*op3) + hdrlen))
return (EINVAL);
read = sizeof(ip_fw3_opheader);
/* Check if xentry len field is valid */
xent = (ipfw_table_xentry *)(op3 + 1);
if (xent->len < hdrlen || xent->len + read > sd->valsize)
return (EINVAL);
memset(&tei, 0, sizeof(tei));
tei.paddr = &xent->k;
tei.masklen = xent->masklen;
ipfw_import_table_value_legacy(xent->value, &v);
tei.pvalue = &v;
/* Old requests compatibility */
tei.flags = TEI_FLAGS_COMPAT;
if (xent->type == IPFW_TABLE_ADDR) {
if (xent->len - hdrlen == sizeof(in_addr_t))
tei.subtype = AF_INET;
else
tei.subtype = AF_INET6;
}
memset(&ti, 0, sizeof(ti));
ti.uidx = xent->tbl;
ti.type = xent->type;
error = (op3->opcode == IP_FW_TABLE_XADD) ?
add_table_entry(ch, &ti, &tei, 0, 1) :
del_table_entry(ch, &ti, &tei, 0, 1);
return (error);
}
/*
* Adds or deletes record in table.
* Data layout (v1)(current):
* Request: [ ipfw_obj_header
* ipfw_obj_ctlv(IPFW_TLV_TBLENT_LIST) [ ipfw_obj_tentry x N ]
* ]
*
* Returns 0 on success
*/
static int
manage_table_ent_v1(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
ipfw_obj_tentry *tent, *ptent;
ipfw_obj_ctlv *ctlv;
ipfw_obj_header *oh;
struct tentry_info *ptei, tei, *tei_buf;
struct tid_info ti;
int error, i, kidx, read;
/* Check minimum header size */
if (sd->valsize < (sizeof(*oh) + sizeof(*ctlv)))
return (EINVAL);
/* Check if passed data is too long */
if (sd->valsize != sd->kavail)
return (EINVAL);
oh = (ipfw_obj_header *)sd->kbuf;
/* Basic length checks for TLVs */
if (oh->ntlv.head.length != sizeof(oh->ntlv))
return (EINVAL);
read = sizeof(*oh);
ctlv = (ipfw_obj_ctlv *)(oh + 1);
if (ctlv->head.length + read != sd->valsize)
return (EINVAL);
read += sizeof(*ctlv);
tent = (ipfw_obj_tentry *)(ctlv + 1);
if (ctlv->count * sizeof(*tent) + read != sd->valsize)
return (EINVAL);
if (ctlv->count == 0)
return (0);
/*
* Mark entire buffer as "read".
* This instructs sopt api write it back
* after function return.
*/
ipfw_get_sopt_header(sd, sd->valsize);
/* Perform basic checks for each entry */
ptent = tent;
kidx = tent->idx;
for (i = 0; i < ctlv->count; i++, ptent++) {
if (ptent->head.length != sizeof(*ptent))
return (EINVAL);
if (ptent->idx != kidx)
return (ENOTSUP);
}
/* Convert data into kernel request objects */
objheader_to_ti(oh, &ti);
ti.type = oh->ntlv.type;
ti.uidx = kidx;
/* Use on-stack buffer for single add/del */
if (ctlv->count == 1) {
memset(&tei, 0, sizeof(tei));
tei_buf = &tei;
} else
tei_buf = malloc(ctlv->count * sizeof(tei), M_TEMP,
M_WAITOK | M_ZERO);
ptei = tei_buf;
ptent = tent;
for (i = 0; i < ctlv->count; i++, ptent++, ptei++) {
ptei->paddr = &ptent->k;
ptei->subtype = ptent->subtype;
ptei->masklen = ptent->masklen;
if (ptent->head.flags & IPFW_TF_UPDATE)
ptei->flags |= TEI_FLAGS_UPDATE;
ipfw_import_table_value_v1(&ptent->v.value);
ptei->pvalue = (struct table_value *)&ptent->v.value;
}
error = (oh->opheader.opcode == IP_FW_TABLE_XADD) ?
add_table_entry(ch, &ti, tei_buf, ctlv->flags, ctlv->count) :
del_table_entry(ch, &ti, tei_buf, ctlv->flags, ctlv->count);
/* Translate result back to userland */
ptei = tei_buf;
ptent = tent;
for (i = 0; i < ctlv->count; i++, ptent++, ptei++) {
if (ptei->flags & TEI_FLAGS_ADDED)
ptent->result = IPFW_TR_ADDED;
else if (ptei->flags & TEI_FLAGS_DELETED)
ptent->result = IPFW_TR_DELETED;
else if (ptei->flags & TEI_FLAGS_UPDATED)
ptent->result = IPFW_TR_UPDATED;
else if (ptei->flags & TEI_FLAGS_LIMIT)
ptent->result = IPFW_TR_LIMIT;
else if (ptei->flags & TEI_FLAGS_ERROR)
ptent->result = IPFW_TR_ERROR;
else if (ptei->flags & TEI_FLAGS_NOTFOUND)
ptent->result = IPFW_TR_NOTFOUND;
else if (ptei->flags & TEI_FLAGS_EXISTS)
ptent->result = IPFW_TR_EXISTS;
ipfw_export_table_value_v1(ptei->pvalue, &ptent->v.value);
}
if (tei_buf != &tei)
free(tei_buf, M_TEMP);
return (error);
}
/*
* Looks up an entry in given table.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ipfw_obj_tentry ]
* Reply: [ ipfw_obj_header ipfw_obj_tentry ]
*
* Returns 0 on success
*/
static int
find_table_entry(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
ipfw_obj_tentry *tent;
ipfw_obj_header *oh;
struct tid_info ti;
struct table_config *tc;
struct table_algo *ta;
struct table_info *kti;
struct namedobj_instance *ni;
int error;
size_t sz;
/* Check minimum header size */
sz = sizeof(*oh) + sizeof(*tent);
if (sd->valsize != sz)
return (EINVAL);
oh = (struct _ipfw_obj_header *)ipfw_get_sopt_header(sd, sz);
tent = (ipfw_obj_tentry *)(oh + 1);
/* Basic length checks for TLVs */
if (oh->ntlv.head.length != sizeof(oh->ntlv))
return (EINVAL);
objheader_to_ti(oh, &ti);
ti.type = oh->ntlv.type;
ti.uidx = tent->idx;
IPFW_UH_RLOCK(ch);
ni = CHAIN_TO_NI(ch);
/*
* Find existing table and check its type .
*/
ta = NULL;
if ((tc = find_table(ni, &ti)) == NULL) {
IPFW_UH_RUNLOCK(ch);
return (ESRCH);
}
/* check table type */
if (tc->no.subtype != ti.type) {
IPFW_UH_RUNLOCK(ch);
return (EINVAL);
}
kti = KIDX_TO_TI(ch, tc->no.kidx);
ta = tc->ta;
if (ta->find_tentry == NULL)
return (ENOTSUP);
error = ta->find_tentry(tc->astate, kti, tent);
IPFW_UH_RUNLOCK(ch);
return (error);
}
/*
* Flushes all entries or destroys given table.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ]
*
* Returns 0 on success
*/
static int
flush_table_v0(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
int error;
struct _ipfw_obj_header *oh;
struct tid_info ti;
if (sd->valsize != sizeof(*oh))
return (EINVAL);
oh = (struct _ipfw_obj_header *)op3;
objheader_to_ti(oh, &ti);
if (op3->opcode == IP_FW_TABLE_XDESTROY)
error = destroy_table(ch, &ti);
else if (op3->opcode == IP_FW_TABLE_XFLUSH)
error = flush_table(ch, &ti);
else
return (ENOTSUP);
return (error);
}
static void
restart_flush(void *object, struct op_state *_state)
{
struct tableop_state *ts;
ts = (struct tableop_state *)_state;
if (ts->tc != object)
return;
/* Indicate we've called */
ts->modified = 1;
}
/*
* Flushes given table.
*
* Function create new table instance with the same
* parameters, swaps it with old one and
* flushes state without holding runtime WLOCK.
*
* Returns 0 on success.
*/
int
flush_table(struct ip_fw_chain *ch, struct tid_info *ti)
{
struct namedobj_instance *ni;
struct table_config *tc;
struct table_algo *ta;
struct table_info ti_old, ti_new, *tablestate;
void *astate_old, *astate_new;
char algostate[64], *pstate;
struct tableop_state ts;
int error, need_gc;
uint16_t kidx;
uint8_t tflags;
/*
* Stage 1: save table algorithm.
* Reference found table to ensure it won't disappear.
*/
IPFW_UH_WLOCK(ch);
ni = CHAIN_TO_NI(ch);
if ((tc = find_table(ni, ti)) == NULL) {
IPFW_UH_WUNLOCK(ch);
return (ESRCH);
}
need_gc = 0;
astate_new = NULL;
memset(&ti_new, 0, sizeof(ti_new));
restart:
/* Set up swap handler */
memset(&ts, 0, sizeof(ts));
ts.opstate.func = restart_flush;
ts.tc = tc;
ta = tc->ta;
/* Do not flush readonly tables */
if ((ta->flags & TA_FLAG_READONLY) != 0) {
IPFW_UH_WUNLOCK(ch);
return (EACCES);
}
/* Save startup algo parameters */
if (ta->print_config != NULL) {
ta->print_config(tc->astate, KIDX_TO_TI(ch, tc->no.kidx),
algostate, sizeof(algostate));
pstate = algostate;
} else
pstate = NULL;
tflags = tc->tflags;
tc->no.refcnt++;
add_toperation_state(ch, &ts);
IPFW_UH_WUNLOCK(ch);
/*
* Stage 1.5: if this is not the first attempt, destroy previous state
*/
if (need_gc != 0) {
ta->destroy(astate_new, &ti_new);
need_gc = 0;
}
/*
* Stage 2: allocate new table instance using same algo.
*/
memset(&ti_new, 0, sizeof(struct table_info));
error = ta->init(ch, &astate_new, &ti_new, pstate, tflags);
/*
* Stage 3: swap old state pointers with newly-allocated ones.
* Decrease refcount.
*/
IPFW_UH_WLOCK(ch);
tc->no.refcnt--;
del_toperation_state(ch, &ts);
if (error != 0) {
IPFW_UH_WUNLOCK(ch);
return (error);
}
/*
* Restart operation if table swap has happened:
* even if algo may be the same, algo init parameters
* may change. Restart operation instead of doing
* complex checks.
*/
if (ts.modified != 0) {
/* Delay destroying data since we're holding UH lock */
need_gc = 1;
goto restart;
}
ni = CHAIN_TO_NI(ch);
kidx = tc->no.kidx;
tablestate = (struct table_info *)ch->tablestate;
IPFW_WLOCK(ch);
ti_old = tablestate[kidx];
tablestate[kidx] = ti_new;
IPFW_WUNLOCK(ch);
astate_old = tc->astate;
tc->astate = astate_new;
tc->ti_copy = ti_new;
tc->count = 0;
/* Notify algo on real @ti address */
if (ta->change_ti != NULL)
ta->change_ti(tc->astate, &tablestate[kidx]);
/*
* Stage 4: unref values.
*/
ipfw_unref_table_values(ch, tc, ta, astate_old, &ti_old);
IPFW_UH_WUNLOCK(ch);
/*
* Stage 5: perform real flush/destroy.
*/
ta->destroy(astate_old, &ti_old);
return (0);
}
/*
* Swaps two tables.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ipfw_obj_ntlv ]
*
* Returns 0 on success
*/
static int
swap_table(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
int error;
struct _ipfw_obj_header *oh;
struct tid_info ti_a, ti_b;
if (sd->valsize != sizeof(*oh) + sizeof(ipfw_obj_ntlv))
return (EINVAL);
oh = (struct _ipfw_obj_header *)op3;
ntlv_to_ti(&oh->ntlv, &ti_a);
ntlv_to_ti((ipfw_obj_ntlv *)(oh + 1), &ti_b);
error = swap_tables(ch, &ti_a, &ti_b);
return (error);
}
/*
* Swaps two tables of the same type/valtype.
*
* Checks if tables are compatible and limits
* permits swap, than actually perform swap.
*
* Each table consists of 2 different parts:
* config:
* @tc (with name, set, kidx) and rule bindings, which is "stable".
* number of items
* table algo
* runtime:
* runtime data @ti (ch->tablestate)
* runtime cache in @tc
* algo-specific data (@tc->astate)
*
* So we switch:
* all runtime data
* number of items
* table algo
*
* After that we call @ti change handler for each table.
*
* Note that referencing @tc won't protect tc->ta from change.
* XXX: Do we need to restrict swap between locked tables?
* XXX: Do we need to exchange ftype?
*
* Returns 0 on success.
*/
static int
swap_tables(struct ip_fw_chain *ch, struct tid_info *a,
struct tid_info *b)
{
struct namedobj_instance *ni;
struct table_config *tc_a, *tc_b;
struct table_algo *ta;
struct table_info ti, *tablestate;
void *astate;
uint32_t count;
/*
* Stage 1: find both tables and ensure they are of
* the same type.
*/
IPFW_UH_WLOCK(ch);
ni = CHAIN_TO_NI(ch);
if ((tc_a = find_table(ni, a)) == NULL) {
IPFW_UH_WUNLOCK(ch);
return (ESRCH);
}
if ((tc_b = find_table(ni, b)) == NULL) {
IPFW_UH_WUNLOCK(ch);
return (ESRCH);
}
/* It is very easy to swap between the same table */
if (tc_a == tc_b) {
IPFW_UH_WUNLOCK(ch);
return (0);
}
/* Check type and value are the same */
if (tc_a->no.subtype!=tc_b->no.subtype || tc_a->tflags!=tc_b->tflags) {
IPFW_UH_WUNLOCK(ch);
return (EINVAL);
}
/* Check limits before swap */
if ((tc_a->limit != 0 && tc_b->count > tc_a->limit) ||
(tc_b->limit != 0 && tc_a->count > tc_b->limit)) {
IPFW_UH_WUNLOCK(ch);
return (EFBIG);
}
/* Check if one of the tables is readonly */
if (((tc_a->ta->flags | tc_b->ta->flags) & TA_FLAG_READONLY) != 0) {
IPFW_UH_WUNLOCK(ch);
return (EACCES);
}
/* Notify we're going to swap */
rollback_toperation_state(ch, tc_a);
rollback_toperation_state(ch, tc_b);
/* Everything is fine, prepare to swap */
tablestate = (struct table_info *)ch->tablestate;
ti = tablestate[tc_a->no.kidx];
ta = tc_a->ta;
astate = tc_a->astate;
count = tc_a->count;
IPFW_WLOCK(ch);
/* a <- b */
tablestate[tc_a->no.kidx] = tablestate[tc_b->no.kidx];
tc_a->ta = tc_b->ta;
tc_a->astate = tc_b->astate;
tc_a->count = tc_b->count;
/* b <- a */
tablestate[tc_b->no.kidx] = ti;
tc_b->ta = ta;
tc_b->astate = astate;
tc_b->count = count;
IPFW_WUNLOCK(ch);
/* Ensure tc.ti copies are in sync */
tc_a->ti_copy = tablestate[tc_a->no.kidx];
tc_b->ti_copy = tablestate[tc_b->no.kidx];
/* Notify both tables on @ti change */
if (tc_a->ta->change_ti != NULL)
tc_a->ta->change_ti(tc_a->astate, &tablestate[tc_a->no.kidx]);
if (tc_b->ta->change_ti != NULL)
tc_b->ta->change_ti(tc_b->astate, &tablestate[tc_b->no.kidx]);
IPFW_UH_WUNLOCK(ch);
return (0);
}
/*
* Destroys table specified by @ti.
* Data layout (v0)(current):
* Request: [ ip_fw3_opheader ]
*
* Returns 0 on success
*/
static int
destroy_table(struct ip_fw_chain *ch, struct tid_info *ti)
{
struct namedobj_instance *ni;
struct table_config *tc;
IPFW_UH_WLOCK(ch);
ni = CHAIN_TO_NI(ch);
if ((tc = find_table(ni, ti)) == NULL) {
IPFW_UH_WUNLOCK(ch);
return (ESRCH);
}
/* Do not permit destroying referenced tables */
if (tc->no.refcnt > 0) {
IPFW_UH_WUNLOCK(ch);
return (EBUSY);
}
IPFW_WLOCK(ch);
unlink_table(ch, tc);
IPFW_WUNLOCK(ch);
/* Free obj index */
if (ipfw_objhash_free_idx(ni, tc->no.kidx) != 0)
printf("Error unlinking kidx %d from table %s\n",
tc->no.kidx, tc->tablename);
/* Unref values used in tables while holding UH lock */
ipfw_unref_table_values(ch, tc, tc->ta, tc->astate, &tc->ti_copy);
IPFW_UH_WUNLOCK(ch);
free_table_config(ni, tc);
return (0);
}
static uint32_t
roundup2p(uint32_t v)
{
v--;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
v++;
return (v);
}
/*
* Grow tables index.
*
* Returns 0 on success.
*/
int
ipfw_resize_tables(struct ip_fw_chain *ch, unsigned int ntables)
{
unsigned int ntables_old, tbl;
struct namedobj_instance *ni;
void *new_idx, *old_tablestate, *tablestate;
struct table_info *ti;
struct table_config *tc;
int i, new_blocks;
/* Check new value for validity */
if (ntables == 0)
return (EINVAL);
if (ntables > IPFW_TABLES_MAX)
ntables = IPFW_TABLES_MAX;
/* Alight to nearest power of 2 */
ntables = (unsigned int)roundup2p(ntables);
/* Allocate new pointers */
tablestate = malloc(ntables * sizeof(struct table_info),
M_IPFW, M_WAITOK | M_ZERO);
ipfw_objhash_bitmap_alloc(ntables, (void *)&new_idx, &new_blocks);
IPFW_UH_WLOCK(ch);
tbl = (ntables >= V_fw_tables_max) ? V_fw_tables_max : ntables;
ni = CHAIN_TO_NI(ch);
/* Temporary restrict decreasing max_tables */
if (ntables < V_fw_tables_max) {
/*
* FIXME: Check if we really can shrink
*/
IPFW_UH_WUNLOCK(ch);
return (EINVAL);
}
/* Copy table info/indices */
memcpy(tablestate, ch->tablestate, sizeof(struct table_info) * tbl);
ipfw_objhash_bitmap_merge(ni, &new_idx, &new_blocks);
IPFW_WLOCK(ch);
/* Change pointers */
old_tablestate = ch->tablestate;
ch->tablestate = tablestate;
ipfw_objhash_bitmap_swap(ni, &new_idx, &new_blocks);
ntables_old = V_fw_tables_max;
V_fw_tables_max = ntables;
IPFW_WUNLOCK(ch);
/* Notify all consumers that their @ti pointer has changed */
ti = (struct table_info *)ch->tablestate;
for (i = 0; i < tbl; i++, ti++) {
if (ti->lookup == NULL)
continue;
tc = (struct table_config *)ipfw_objhash_lookup_kidx(ni, i);
if (tc == NULL || tc->ta->change_ti == NULL)
continue;
tc->ta->change_ti(tc->astate, ti);
}
IPFW_UH_WUNLOCK(ch);
/* Free old pointers */
free(old_tablestate, M_IPFW);
ipfw_objhash_bitmap_free(new_idx, new_blocks);
return (0);
}
/*
* Lookup an IP @addr in table @tbl.
* Stores found value in @val.
*
* Returns 1 if @addr was found.
*/
int
ipfw_lookup_table(struct ip_fw_chain *ch, uint16_t tbl, in_addr_t addr,
uint32_t *val)
{
struct table_info *ti;
ti = KIDX_TO_TI(ch, tbl);
return (ti->lookup(ti, &addr, sizeof(in_addr_t), val));
}
/*
* Lookup an arbtrary key @paddr of legth @plen in table @tbl.
* Stores found value in @val.
*
* Returns 1 if key was found.
*/
int
ipfw_lookup_table_extended(struct ip_fw_chain *ch, uint16_t tbl, uint16_t plen,
void *paddr, uint32_t *val)
{
struct table_info *ti;
ti = KIDX_TO_TI(ch, tbl);
return (ti->lookup(ti, paddr, plen, val));
}
/*
* Info/List/dump support for tables.
*
*/
/*
* High-level 'get' cmds sysctl handlers
*/
/*
* Lists all tables currently available in kernel.
* Data layout (v0)(current):
* Request: [ ipfw_obj_lheader ], size = ipfw_obj_lheader.size
* Reply: [ ipfw_obj_lheader ipfw_xtable_info x N ]
*
* Returns 0 on success
*/
static int
list_tables(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_lheader *olh;
int error;
olh = (struct _ipfw_obj_lheader *)ipfw_get_sopt_header(sd,sizeof(*olh));
if (olh == NULL)
return (EINVAL);
if (sd->valsize < olh->size)
return (EINVAL);
IPFW_UH_RLOCK(ch);
error = export_tables(ch, olh, sd);
IPFW_UH_RUNLOCK(ch);
return (error);
}
/*
* Store table info to buffer provided by @sd.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ipfw_xtable_info(empty)]
* Reply: [ ipfw_obj_header ipfw_xtable_info ]
*
* Returns 0 on success.
*/
static int
describe_table(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_header *oh;
struct table_config *tc;
struct tid_info ti;
size_t sz;
sz = sizeof(*oh) + sizeof(ipfw_xtable_info);
oh = (struct _ipfw_obj_header *)ipfw_get_sopt_header(sd, sz);
if (oh == NULL)
return (EINVAL);
objheader_to_ti(oh, &ti);
IPFW_UH_RLOCK(ch);
if ((tc = find_table(CHAIN_TO_NI(ch), &ti)) == NULL) {
IPFW_UH_RUNLOCK(ch);
return (ESRCH);
}
export_table_info(ch, tc, (ipfw_xtable_info *)(oh + 1));
IPFW_UH_RUNLOCK(ch);
return (0);
}
/*
* Modifies existing table.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ipfw_xtable_info ]
*
* Returns 0 on success
*/
static int
modify_table(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_header *oh;
ipfw_xtable_info *i;
char *tname;
struct tid_info ti;
struct namedobj_instance *ni;
struct table_config *tc;
if (sd->valsize != sizeof(*oh) + sizeof(ipfw_xtable_info))
return (EINVAL);
oh = (struct _ipfw_obj_header *)sd->kbuf;
i = (ipfw_xtable_info *)(oh + 1);
/*
* Verify user-supplied strings.
* Check for null-terminated/zero-length strings/
*/
tname = oh->ntlv.name;
if (check_table_name(tname) != 0)
return (EINVAL);
objheader_to_ti(oh, &ti);
ti.type = i->type;
IPFW_UH_WLOCK(ch);
ni = CHAIN_TO_NI(ch);
if ((tc = find_table(ni, &ti)) == NULL) {
IPFW_UH_WUNLOCK(ch);
return (ESRCH);
}
/* Do not support any modifications for readonly tables */
if ((tc->ta->flags & TA_FLAG_READONLY) != 0) {
IPFW_UH_WUNLOCK(ch);
return (EACCES);
}
if ((i->mflags & IPFW_TMFLAGS_LIMIT) != 0)
tc->limit = i->limit;
if ((i->mflags & IPFW_TMFLAGS_LOCK) != 0)
tc->locked = ((i->flags & IPFW_TGFLAGS_LOCKED) != 0);
IPFW_UH_WUNLOCK(ch);
return (0);
}
/*
* Creates new table.
* Data layout (v0)(current):
* Request: [ ipfw_obj_header ipfw_xtable_info ]
*
* Returns 0 on success
*/
static int
create_table(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_header *oh;
ipfw_xtable_info *i;
char *tname, *aname;
struct tid_info ti;
struct namedobj_instance *ni;
if (sd->valsize != sizeof(*oh) + sizeof(ipfw_xtable_info))
return (EINVAL);
oh = (struct _ipfw_obj_header *)sd->kbuf;
i = (ipfw_xtable_info *)(oh + 1);
/*
* Verify user-supplied strings.
* Check for null-terminated/zero-length strings/
*/
tname = oh->ntlv.name;
aname = i->algoname;
if (check_table_name(tname) != 0 ||
strnlen(aname, sizeof(i->algoname)) == sizeof(i->algoname))
return (EINVAL);
if (aname[0] == '\0') {
/* Use default algorithm */
aname = NULL;
}
objheader_to_ti(oh, &ti);
ti.type = i->type;
ni = CHAIN_TO_NI(ch);
IPFW_UH_RLOCK(ch);
if (find_table(ni, &ti) != NULL) {
IPFW_UH_RUNLOCK(ch);
return (EEXIST);
}
IPFW_UH_RUNLOCK(ch);
return (create_table_internal(ch, &ti, aname, i, NULL, 0));
}
/*
* Creates new table based on @ti and @aname.
*
* Assume @aname to be checked and valid.
* Stores allocated table kidx inside @pkidx (if non-NULL).
* Reference created table if @compat is non-zero.
*
* Returns 0 on success.
*/
static int
create_table_internal(struct ip_fw_chain *ch, struct tid_info *ti,
char *aname, ipfw_xtable_info *i, uint16_t *pkidx, int compat)
{
struct namedobj_instance *ni;
struct table_config *tc, *tc_new, *tmp;
struct table_algo *ta;
uint16_t kidx;
ni = CHAIN_TO_NI(ch);
ta = find_table_algo(CHAIN_TO_TCFG(ch), ti, aname);
if (ta == NULL)
return (ENOTSUP);
tc = alloc_table_config(ch, ti, ta, aname, i->tflags);
if (tc == NULL)
return (ENOMEM);
tc->vmask = i->vmask;
tc->limit = i->limit;
if (ta->flags & TA_FLAG_READONLY)
tc->locked = 1;
else
tc->locked = (i->flags & IPFW_TGFLAGS_LOCKED) != 0;
IPFW_UH_WLOCK(ch);
/* Check if table has been already created */
tc_new = find_table(ni, ti);
if (tc_new != NULL) {
/*
* Compat: do not fail if we're
* requesting to create existing table
* which has the same type
*/
if (compat == 0 || tc_new->no.subtype != tc->no.subtype) {
IPFW_UH_WUNLOCK(ch);
free_table_config(ni, tc);
return (EEXIST);
}
/* Exchange tc and tc_new for proper refcounting & freeing */
tmp = tc;
tc = tc_new;
tc_new = tmp;
} else {
/* New table */
if (ipfw_objhash_alloc_idx(ni, &kidx) != 0) {
IPFW_UH_WUNLOCK(ch);
printf("Unable to allocate table index."
" Consider increasing net.inet.ip.fw.tables_max");
free_table_config(ni, tc);
return (EBUSY);
}
tc->no.kidx = kidx;
tc->no.etlv = IPFW_TLV_TBL_NAME;
IPFW_WLOCK(ch);
link_table(ch, tc);
IPFW_WUNLOCK(ch);
}
if (compat != 0)
tc->no.refcnt++;
if (pkidx != NULL)
*pkidx = tc->no.kidx;
IPFW_UH_WUNLOCK(ch);
if (tc_new != NULL)
free_table_config(ni, tc_new);
return (0);
}
static void
ntlv_to_ti(ipfw_obj_ntlv *ntlv, struct tid_info *ti)
{
memset(ti, 0, sizeof(struct tid_info));
ti->set = ntlv->set;
ti->uidx = ntlv->idx;
ti->tlvs = ntlv;
ti->tlen = ntlv->head.length;
}
static void
objheader_to_ti(struct _ipfw_obj_header *oh, struct tid_info *ti)
{
ntlv_to_ti(&oh->ntlv, ti);
}
struct namedobj_instance *
ipfw_get_table_objhash(struct ip_fw_chain *ch)
{
return (CHAIN_TO_NI(ch));
}
/*
* Exports basic table info as name TLV.
* Used inside dump_static_rules() to provide info
* about all tables referenced by current ruleset.
*
* Returns 0 on success.
*/
int
ipfw_export_table_ntlv(struct ip_fw_chain *ch, uint16_t kidx,
struct sockopt_data *sd)
{
struct namedobj_instance *ni;
struct named_object *no;
ipfw_obj_ntlv *ntlv;
ni = CHAIN_TO_NI(ch);
no = ipfw_objhash_lookup_kidx(ni, kidx);
KASSERT(no != NULL, ("invalid table kidx passed"));
ntlv = (ipfw_obj_ntlv *)ipfw_get_sopt_space(sd, sizeof(*ntlv));
if (ntlv == NULL)
return (ENOMEM);
ntlv->head.type = IPFW_TLV_TBL_NAME;
ntlv->head.length = sizeof(*ntlv);
ntlv->idx = no->kidx;
strlcpy(ntlv->name, no->name, sizeof(ntlv->name));
return (0);
}
struct dump_args {
struct ip_fw_chain *ch;
struct table_info *ti;
struct table_config *tc;
struct sockopt_data *sd;
uint32_t cnt;
uint16_t uidx;
int error;
uint32_t size;
ipfw_table_entry *ent;
ta_foreach_f *f;
void *farg;
ipfw_obj_tentry tent;
};
static int
count_ext_entries(void *e, void *arg)
{
struct dump_args *da;
da = (struct dump_args *)arg;
da->cnt++;
return (0);
}
/*
* Gets number of items from table either using
* internal counter or calling algo callback for
* externally-managed tables.
*
* Returns number of records.
*/
static uint32_t
table_get_count(struct ip_fw_chain *ch, struct table_config *tc)
{
struct table_info *ti;
struct table_algo *ta;
struct dump_args da;
ti = KIDX_TO_TI(ch, tc->no.kidx);
ta = tc->ta;
/* Use internal counter for self-managed tables */
if ((ta->flags & TA_FLAG_READONLY) == 0)
return (tc->count);
/* Use callback to quickly get number of items */
if ((ta->flags & TA_FLAG_EXTCOUNTER) != 0)
return (ta->get_count(tc->astate, ti));
/* Count number of iterms ourselves */
memset(&da, 0, sizeof(da));
ta->foreach(tc->astate, ti, count_ext_entries, &da);
return (da.cnt);
}
/*
* Exports table @tc info into standard ipfw_xtable_info format.
*/
static void
export_table_info(struct ip_fw_chain *ch, struct table_config *tc,
ipfw_xtable_info *i)
{
struct table_info *ti;
struct table_algo *ta;
i->type = tc->no.subtype;
i->tflags = tc->tflags;
i->vmask = tc->vmask;
i->set = tc->no.set;
i->kidx = tc->no.kidx;
i->refcnt = tc->no.refcnt;
i->count = table_get_count(ch, tc);
i->limit = tc->limit;
i->flags |= (tc->locked != 0) ? IPFW_TGFLAGS_LOCKED : 0;
i->size = i->count * sizeof(ipfw_obj_tentry);
i->size += sizeof(ipfw_obj_header) + sizeof(ipfw_xtable_info);
strlcpy(i->tablename, tc->tablename, sizeof(i->tablename));
ti = KIDX_TO_TI(ch, tc->no.kidx);
ta = tc->ta;
if (ta->print_config != NULL) {
/* Use algo function to print table config to string */
ta->print_config(tc->astate, ti, i->algoname,
sizeof(i->algoname));
} else
strlcpy(i->algoname, ta->name, sizeof(i->algoname));
/* Dump algo-specific data, if possible */
if (ta->dump_tinfo != NULL) {
ta->dump_tinfo(tc->astate, ti, &i->ta_info);
i->ta_info.flags |= IPFW_TATFLAGS_DATA;
}
}
struct dump_table_args {
struct ip_fw_chain *ch;
struct sockopt_data *sd;
};
static int
export_table_internal(struct namedobj_instance *ni, struct named_object *no,
void *arg)
{
ipfw_xtable_info *i;
struct dump_table_args *dta;
dta = (struct dump_table_args *)arg;
i = (ipfw_xtable_info *)ipfw_get_sopt_space(dta->sd, sizeof(*i));
KASSERT(i != NULL, ("previously checked buffer is not enough"));
export_table_info(dta->ch, (struct table_config *)no, i);
return (0);
}
/*
* Export all tables as ipfw_xtable_info structures to
* storage provided by @sd.
*
* If supplied buffer is too small, fills in required size
* and returns ENOMEM.
* Returns 0 on success.
*/
static int
export_tables(struct ip_fw_chain *ch, ipfw_obj_lheader *olh,
struct sockopt_data *sd)
{
uint32_t size;
uint32_t count;
struct dump_table_args dta;
count = ipfw_objhash_count(CHAIN_TO_NI(ch));
size = count * sizeof(ipfw_xtable_info) + sizeof(ipfw_obj_lheader);
/* Fill in header regadless of buffer size */
olh->count = count;
olh->objsize = sizeof(ipfw_xtable_info);
if (size > olh->size) {
olh->size = size;
return (ENOMEM);
}
olh->size = size;
dta.ch = ch;
dta.sd = sd;
ipfw_objhash_foreach(CHAIN_TO_NI(ch), export_table_internal, &dta);
return (0);
}
/*
* Dumps all table data
* Data layout (v1)(current):
* Request: [ ipfw_obj_header ], size = ipfw_xtable_info.size
* Reply: [ ipfw_obj_header ipfw_xtable_info ipfw_obj_tentry x N ]
*
* Returns 0 on success
*/
static int
dump_table_v1(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_header *oh;
ipfw_xtable_info *i;
struct tid_info ti;
struct table_config *tc;
struct table_algo *ta;
struct dump_args da;
uint32_t sz;
sz = sizeof(ipfw_obj_header) + sizeof(ipfw_xtable_info);
oh = (struct _ipfw_obj_header *)ipfw_get_sopt_header(sd, sz);
if (oh == NULL)
return (EINVAL);
i = (ipfw_xtable_info *)(oh + 1);
objheader_to_ti(oh, &ti);
IPFW_UH_RLOCK(ch);
if ((tc = find_table(CHAIN_TO_NI(ch), &ti)) == NULL) {
IPFW_UH_RUNLOCK(ch);
return (ESRCH);
}
export_table_info(ch, tc, i);
if (sd->valsize < i->size) {
/*
* Submitted buffer size is not enough.
* WE've already filled in @i structure with
* relevant table info including size, so we
* can return. Buffer will be flushed automatically.
*/
IPFW_UH_RUNLOCK(ch);
return (ENOMEM);
}
/*
* Do the actual dump in eXtended format
*/
memset(&da, 0, sizeof(da));
da.ch = ch;
da.ti = KIDX_TO_TI(ch, tc->no.kidx);
da.tc = tc;
da.sd = sd;
ta = tc->ta;
ta->foreach(tc->astate, da.ti, dump_table_tentry, &da);
IPFW_UH_RUNLOCK(ch);
return (da.error);
}
/*
* Dumps all table data
* Data layout (version 0)(legacy):
* Request: [ ipfw_xtable ], size = IP_FW_TABLE_XGETSIZE()
* Reply: [ ipfw_xtable ipfw_table_xentry x N ]
*
* Returns 0 on success
*/
static int
dump_table_v0(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
ipfw_xtable *xtbl;
struct tid_info ti;
struct table_config *tc;
struct table_algo *ta;
struct dump_args da;
size_t sz, count;
xtbl = (ipfw_xtable *)ipfw_get_sopt_header(sd, sizeof(ipfw_xtable));
if (xtbl == NULL)
return (EINVAL);
memset(&ti, 0, sizeof(ti));
ti.uidx = xtbl->tbl;
IPFW_UH_RLOCK(ch);
if ((tc = find_table(CHAIN_TO_NI(ch), &ti)) == NULL) {
IPFW_UH_RUNLOCK(ch);
return (0);
}
count = table_get_count(ch, tc);
sz = count * sizeof(ipfw_table_xentry) + sizeof(ipfw_xtable);
xtbl->cnt = count;
xtbl->size = sz;
xtbl->type = tc->no.subtype;
xtbl->tbl = ti.uidx;
if (sd->valsize < sz) {
/*
* Submitted buffer size is not enough.
* WE've already filled in @i structure with
* relevant table info including size, so we
* can return. Buffer will be flushed automatically.
*/
IPFW_UH_RUNLOCK(ch);
return (ENOMEM);
}
/* Do the actual dump in eXtended format */
memset(&da, 0, sizeof(da));
da.ch = ch;
da.ti = KIDX_TO_TI(ch, tc->no.kidx);
da.tc = tc;
da.sd = sd;
ta = tc->ta;
ta->foreach(tc->astate, da.ti, dump_table_xentry, &da);
IPFW_UH_RUNLOCK(ch);
return (0);
}
/*
* Legacy function to retrieve number of items in table.
*/
static int
get_table_size(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
uint32_t *tbl;
struct tid_info ti;
size_t sz;
int error;
sz = sizeof(*op3) + sizeof(uint32_t);
op3 = (ip_fw3_opheader *)ipfw_get_sopt_header(sd, sz);
if (op3 == NULL)
return (EINVAL);
tbl = (uint32_t *)(op3 + 1);
memset(&ti, 0, sizeof(ti));
ti.uidx = *tbl;
IPFW_UH_RLOCK(ch);
error = ipfw_count_xtable(ch, &ti, tbl);
IPFW_UH_RUNLOCK(ch);
return (error);
}
/*
* Legacy IP_FW_TABLE_GETSIZE handler
*/
int
ipfw_count_table(struct ip_fw_chain *ch, struct tid_info *ti, uint32_t *cnt)
{
struct table_config *tc;
if ((tc = find_table(CHAIN_TO_NI(ch), ti)) == NULL)
return (ESRCH);
*cnt = table_get_count(ch, tc);
return (0);
}
/*
* Legacy IP_FW_TABLE_XGETSIZE handler
*/
int
ipfw_count_xtable(struct ip_fw_chain *ch, struct tid_info *ti, uint32_t *cnt)
{
struct table_config *tc;
uint32_t count;
if ((tc = find_table(CHAIN_TO_NI(ch), ti)) == NULL) {
*cnt = 0;
return (0); /* 'table all list' requires success */
}
count = table_get_count(ch, tc);
*cnt = count * sizeof(ipfw_table_xentry);
if (count > 0)
*cnt += sizeof(ipfw_xtable);
return (0);
}
static int
dump_table_entry(void *e, void *arg)
{
struct dump_args *da;
struct table_config *tc;
struct table_algo *ta;
ipfw_table_entry *ent;
struct table_value *pval;
int error;
da = (struct dump_args *)arg;
tc = da->tc;
ta = tc->ta;
/* Out of memory, returning */
if (da->cnt == da->size)
return (1);
ent = da->ent++;
ent->tbl = da->uidx;
da->cnt++;
error = ta->dump_tentry(tc->astate, da->ti, e, &da->tent);
if (error != 0)
return (error);
ent->addr = da->tent.k.addr.s_addr;
ent->masklen = da->tent.masklen;
pval = get_table_value(da->ch, da->tc, da->tent.v.kidx);
ent->value = ipfw_export_table_value_legacy(pval);
return (0);
}
/*
* Dumps table in pre-8.1 legacy format.
*/
int
ipfw_dump_table_legacy(struct ip_fw_chain *ch, struct tid_info *ti,
ipfw_table *tbl)
{
struct table_config *tc;
struct table_algo *ta;
struct dump_args da;
tbl->cnt = 0;
if ((tc = find_table(CHAIN_TO_NI(ch), ti)) == NULL)
return (0); /* XXX: We should return ESRCH */
ta = tc->ta;
/* This dump format supports IPv4 only */
if (tc->no.subtype != IPFW_TABLE_ADDR)
return (0);
memset(&da, 0, sizeof(da));
da.ch = ch;
da.ti = KIDX_TO_TI(ch, tc->no.kidx);
da.tc = tc;
da.ent = &tbl->ent[0];
da.size = tbl->size;
tbl->cnt = 0;
ta->foreach(tc->astate, da.ti, dump_table_entry, &da);
tbl->cnt = da.cnt;
return (0);
}
/*
* Dumps table entry in eXtended format (v1)(current).
*/
static int
dump_table_tentry(void *e, void *arg)
{
struct dump_args *da;
struct table_config *tc;
struct table_algo *ta;
struct table_value *pval;
ipfw_obj_tentry *tent;
int error;
da = (struct dump_args *)arg;
tc = da->tc;
ta = tc->ta;
tent = (ipfw_obj_tentry *)ipfw_get_sopt_space(da->sd, sizeof(*tent));
/* Out of memory, returning */
if (tent == NULL) {
da->error = ENOMEM;
return (1);
}
tent->head.length = sizeof(ipfw_obj_tentry);
tent->idx = da->uidx;
error = ta->dump_tentry(tc->astate, da->ti, e, tent);
if (error != 0)
return (error);
pval = get_table_value(da->ch, da->tc, tent->v.kidx);
ipfw_export_table_value_v1(pval, &tent->v.value);
return (0);
}
/*
* Dumps table entry in eXtended format (v0).
*/
static int
dump_table_xentry(void *e, void *arg)
{
struct dump_args *da;
struct table_config *tc;
struct table_algo *ta;
ipfw_table_xentry *xent;
ipfw_obj_tentry *tent;
struct table_value *pval;
int error;
da = (struct dump_args *)arg;
tc = da->tc;
ta = tc->ta;
xent = (ipfw_table_xentry *)ipfw_get_sopt_space(da->sd, sizeof(*xent));
/* Out of memory, returning */
if (xent == NULL)
return (1);
xent->len = sizeof(ipfw_table_xentry);
xent->tbl = da->uidx;
memset(&da->tent, 0, sizeof(da->tent));
tent = &da->tent;
error = ta->dump_tentry(tc->astate, da->ti, e, tent);
if (error != 0)
return (error);
/* Convert current format to previous one */
xent->masklen = tent->masklen;
pval = get_table_value(da->ch, da->tc, da->tent.v.kidx);
xent->value = ipfw_export_table_value_legacy(pval);
/* Apply some hacks */
if (tc->no.subtype == IPFW_TABLE_ADDR && tent->subtype == AF_INET) {
xent->k.addr6.s6_addr32[3] = tent->k.addr.s_addr;
xent->flags = IPFW_TCF_INET;
} else
memcpy(&xent->k, &tent->k, sizeof(xent->k));
return (0);
}
/*
* Helper function to export table algo data
* to tentry format before calling user function.
*
* Returns 0 on success.
*/
static int
prepare_table_tentry(void *e, void *arg)
{
struct dump_args *da;
struct table_config *tc;
struct table_algo *ta;
int error;
da = (struct dump_args *)arg;
tc = da->tc;
ta = tc->ta;
error = ta->dump_tentry(tc->astate, da->ti, e, &da->tent);
if (error != 0)
return (error);
da->f(&da->tent, da->farg);
return (0);
}
/*
* Allow external consumers to read table entries in standard format.
*/
int
ipfw_foreach_table_tentry(struct ip_fw_chain *ch, uint16_t kidx,
ta_foreach_f *f, void *arg)
{
struct namedobj_instance *ni;
struct table_config *tc;
struct table_algo *ta;
struct dump_args da;
ni = CHAIN_TO_NI(ch);
tc = (struct table_config *)ipfw_objhash_lookup_kidx(ni, kidx);
if (tc == NULL)
return (ESRCH);
ta = tc->ta;
memset(&da, 0, sizeof(da));
da.ch = ch;
da.ti = KIDX_TO_TI(ch, tc->no.kidx);
da.tc = tc;
da.f = f;
da.farg = arg;
ta->foreach(tc->astate, da.ti, prepare_table_tentry, &da);
return (0);
}
/*
* Table algorithms
*/
/*
* Finds algorithm by index, table type or supplied name.
*
* Returns pointer to algo or NULL.
*/
static struct table_algo *
find_table_algo(struct tables_config *tcfg, struct tid_info *ti, char *name)
{
int i, l;
struct table_algo *ta;
if (ti->type > IPFW_TABLE_MAXTYPE)
return (NULL);
/* Search by index */
if (ti->atype != 0) {
if (ti->atype > tcfg->algo_count)
return (NULL);
return (tcfg->algo[ti->atype]);
}
if (name == NULL) {
/* Return default algorithm for given type if set */
return (tcfg->def_algo[ti->type]);
}
/* Search by name */
/* TODO: better search */
for (i = 1; i <= tcfg->algo_count; i++) {
ta = tcfg->algo[i];
/*
* One can supply additional algorithm
* parameters so we compare only the first word
* of supplied name:
* 'addr:chash hsize=32'
* '^^^^^^^^^'
*
*/
l = strlen(ta->name);
if (strncmp(name, ta->name, l) != 0)
continue;
if (name[l] != '\0' && name[l] != ' ')
continue;
/* Check if we're requesting proper table type */
if (ti->type != 0 && ti->type != ta->type)
return (NULL);
return (ta);
}
return (NULL);
}
/*
* Register new table algo @ta.
* Stores algo id inside @idx.
*
* Returns 0 on success.
*/
int
ipfw_add_table_algo(struct ip_fw_chain *ch, struct table_algo *ta, size_t size,
int *idx)
{
struct tables_config *tcfg;
struct table_algo *ta_new;
size_t sz;
if (size > sizeof(struct table_algo))
return (EINVAL);
/* Check for the required on-stack size for add/del */
sz = roundup2(ta->ta_buf_size, sizeof(void *));
if (sz > TA_BUF_SZ)
return (EINVAL);
KASSERT(ta->type <= IPFW_TABLE_MAXTYPE,("Increase IPFW_TABLE_MAXTYPE"));
/* Copy algorithm data to stable storage. */
ta_new = malloc(sizeof(struct table_algo), M_IPFW, M_WAITOK | M_ZERO);
memcpy(ta_new, ta, size);
tcfg = CHAIN_TO_TCFG(ch);
KASSERT(tcfg->algo_count < 255, ("Increase algo array size"));
tcfg->algo[++tcfg->algo_count] = ta_new;
ta_new->idx = tcfg->algo_count;
/* Set algorithm as default one for given type */
if ((ta_new->flags & TA_FLAG_DEFAULT) != 0 &&
tcfg->def_algo[ta_new->type] == NULL)
tcfg->def_algo[ta_new->type] = ta_new;
*idx = ta_new->idx;
return (0);
}
/*
* Unregisters table algo using @idx as id.
* XXX: It is NOT safe to call this function in any place
* other than ipfw instance destroy handler.
*/
void
ipfw_del_table_algo(struct ip_fw_chain *ch, int idx)
{
struct tables_config *tcfg;
struct table_algo *ta;
tcfg = CHAIN_TO_TCFG(ch);
KASSERT(idx <= tcfg->algo_count, ("algo idx %d out of range 1..%d",
idx, tcfg->algo_count));
ta = tcfg->algo[idx];
KASSERT(ta != NULL, ("algo idx %d is NULL", idx));
if (tcfg->def_algo[ta->type] == ta)
tcfg->def_algo[ta->type] = NULL;
free(ta, M_IPFW);
}
/*
* Lists all table algorithms currently available.
* Data layout (v0)(current):
* Request: [ ipfw_obj_lheader ], size = ipfw_obj_lheader.size
* Reply: [ ipfw_obj_lheader ipfw_ta_info x N ]
*
* Returns 0 on success
*/
static int
list_table_algo(struct ip_fw_chain *ch, ip_fw3_opheader *op3,
struct sockopt_data *sd)
{
struct _ipfw_obj_lheader *olh;
struct tables_config *tcfg;
ipfw_ta_info *i;
struct table_algo *ta;
uint32_t count, n, size;
olh = (struct _ipfw_obj_lheader *)ipfw_get_sopt_header(sd,sizeof(*olh));
if (olh == NULL)
return (EINVAL);
if (sd->valsize < olh->size)
return (EINVAL);
IPFW_UH_RLOCK(ch);
tcfg = CHAIN_TO_TCFG(ch);
count = tcfg->algo_count;
size = count * sizeof(ipfw_ta_info) + sizeof(ipfw_obj_lheader);
/* Fill in header regadless of buffer size */
olh->count = count;
olh->objsize = sizeof(ipfw_ta_info);
if (size > olh->size) {
olh->size = size;
IPFW_UH_RUNLOCK(ch);
return (ENOMEM);
}
olh->size = size;
for (n = 1; n <= count; n++) {
i = (ipfw_ta_info *)ipfw_get_sopt_space(sd, sizeof(*i));
KASSERT(i != NULL, ("previously checked buffer is not enough"));
ta = tcfg->algo[n];
strlcpy(i->algoname, ta->name, sizeof(i->algoname));
i->type = ta->type;
i->refcnt = ta->refcnt;
}
IPFW_UH_RUNLOCK(ch);
return (0);
}
static int
classify_srcdst(ipfw_insn *cmd, uint16_t *puidx, uint8_t *ptype)
{
/* Basic IPv4/IPv6 or u32 lookups */
*puidx = cmd->arg1;
/* Assume ADDR by default */
*ptype = IPFW_TABLE_ADDR;
int v;
if (F_LEN(cmd) > F_INSN_SIZE(ipfw_insn_u32)) {
/*
* generic lookup. The key must be
* in 32bit big-endian format.
*/
v = ((ipfw_insn_u32 *)cmd)->d[1];
switch (v) {
case 0:
case 1:
/* IPv4 src/dst */
break;
case 2:
case 3:
/* src/dst port */
*ptype = IPFW_TABLE_NUMBER;
break;
case 4:
/* uid/gid */
*ptype = IPFW_TABLE_NUMBER;
break;
case 5:
/* jid */
*ptype = IPFW_TABLE_NUMBER;
break;
case 6:
/* dscp */
*ptype = IPFW_TABLE_NUMBER;
break;
}
}
return (0);
}
static int
classify_via(ipfw_insn *cmd, uint16_t *puidx, uint8_t *ptype)
{
ipfw_insn_if *cmdif;
/* Interface table, possibly */
cmdif = (ipfw_insn_if *)cmd;
if (cmdif->name[0] != '\1')
return (1);
*ptype = IPFW_TABLE_INTERFACE;
*puidx = cmdif->p.kidx;
return (0);
}
static int
classify_flow(ipfw_insn *cmd, uint16_t *puidx, uint8_t *ptype)
{
*puidx = cmd->arg1;
*ptype = IPFW_TABLE_FLOW;
return (0);
}
static void
update_arg1(ipfw_insn *cmd, uint16_t idx)
{
cmd->arg1 = idx;
}
static void
update_via(ipfw_insn *cmd, uint16_t idx)
{
ipfw_insn_if *cmdif;
cmdif = (ipfw_insn_if *)cmd;
cmdif->p.kidx = idx;
}
static int
table_findbyname(struct ip_fw_chain *ch, struct tid_info *ti,
struct named_object **pno)
{
struct table_config *tc;
int error;
IPFW_UH_WLOCK_ASSERT(ch);
error = find_table_err(CHAIN_TO_NI(ch), ti, &tc);
if (error != 0)
return (error);
*pno = &tc->no;
return (0);
}
/* XXX: sets-sets! */
static struct named_object *
table_findbykidx(struct ip_fw_chain *ch, uint16_t idx)
{
struct namedobj_instance *ni;
struct table_config *tc;
IPFW_UH_WLOCK_ASSERT(ch);
ni = CHAIN_TO_NI(ch);
tc = (struct table_config *)ipfw_objhash_lookup_kidx(ni, idx);
KASSERT(tc != NULL, ("Table with index %d not found", idx));
return (&tc->no);
}
static int
table_manage_sets(struct ip_fw_chain *ch, uint16_t set, uint8_t new_set,
enum ipfw_sets_cmd cmd)
{
switch (cmd) {
case SWAP_ALL:
case TEST_ALL:
/*
* Return success for TEST_ALL, since nothing prevents
* move rules from one set to another. All tables are
* accessible from all sets when per-set tables sysctl
* is disabled.
*/
case MOVE_ALL:
case TEST_ONE:
case MOVE_ONE:
/*
* NOTE: we need to use ipfw_objhash_del/ipfw_objhash_add
* if set number will be used in hash function. Currently
* we can just use generic handler that replaces set value.
*/
if (V_fw_tables_sets == 0)
return (0);
break;
case COUNT_ONE:
/*
* Return EOPNOTSUPP for COUNT_ONE when per-set sysctl is
* disabled. This allow skip table's opcodes from additional
* checks when specific rules moved to another set.
*/
if (V_fw_tables_sets == 0)
return (EOPNOTSUPP);
}
/* Use generic sets handler when per-set sysctl is enabled. */
return (ipfw_obj_manage_sets(CHAIN_TO_NI(ch), IPFW_TLV_TBL_NAME,
set, new_set, cmd));
}
static struct opcode_obj_rewrite opcodes[] = {
{
.opcode = O_IP_SRC_LOOKUP,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_srcdst,
.update = update_arg1,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
{
.opcode = O_IP_DST_LOOKUP,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_srcdst,
.update = update_arg1,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
{
.opcode = O_IP_FLOW_LOOKUP,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_flow,
.update = update_arg1,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
{
.opcode = O_XMIT,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_via,
.update = update_via,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
{
.opcode = O_RECV,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_via,
.update = update_via,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
{
.opcode = O_VIA,
.etlv = IPFW_TLV_TBL_NAME,
.classifier = classify_via,
.update = update_via,
.find_byname = table_findbyname,
.find_bykidx = table_findbykidx,
.create_object = create_table_compat,
.manage_sets = table_manage_sets,
},
};
static int
test_sets_cb(struct namedobj_instance *ni __unused, struct named_object *no,
void *arg __unused)
{
/* Check that there aren't any tables in not default set */
if (no->set != 0)
return (EBUSY);
return (0);
}
/*
* Switch between "set 0" and "rule's set" table binding,
* Check all ruleset bindings and permits changing
* IFF each binding has both rule AND table in default set (set 0).
*
* Returns 0 on success.
*/
int
ipfw_switch_tables_namespace(struct ip_fw_chain *ch, unsigned int sets)
{
struct opcode_obj_rewrite *rw;
struct namedobj_instance *ni;
struct named_object *no;
struct ip_fw *rule;
ipfw_insn *cmd;
int cmdlen, i, l;
uint16_t kidx;
uint8_t subtype;
IPFW_UH_WLOCK(ch);
if (V_fw_tables_sets == sets) {
IPFW_UH_WUNLOCK(ch);
return (0);
}
ni = CHAIN_TO_NI(ch);
if (sets == 0) {
/*
* Prevent disabling sets support if we have some tables
* in not default sets.
*/
if (ipfw_objhash_foreach_type(ni, test_sets_cb,
NULL, IPFW_TLV_TBL_NAME) != 0) {
IPFW_UH_WUNLOCK(ch);
return (EBUSY);
}
}
/*
* Scan all rules and examine tables opcodes.
*/
for (i = 0; i < ch->n_rules; i++) {
rule = ch->map[i];
l = rule->cmd_len;
cmd = rule->cmd;
cmdlen = 0;
for ( ; l > 0 ; l -= cmdlen, cmd += cmdlen) {
cmdlen = F_LEN(cmd);
/* Check only tables opcodes */
for (kidx = 0, rw = opcodes;
rw < opcodes + nitems(opcodes); rw++) {
if (rw->opcode != cmd->opcode)
continue;
if (rw->classifier(cmd, &kidx, &subtype) == 0)
break;
}
if (kidx == 0)
continue;
no = ipfw_objhash_lookup_kidx(ni, kidx);
/* Check if both table object and rule has the set 0 */
if (no->set != 0 || rule->set != 0) {
IPFW_UH_WUNLOCK(ch);
return (EBUSY);
}
}
}
V_fw_tables_sets = sets;
IPFW_UH_WUNLOCK(ch);
return (0);
}
/*
* Checks table name for validity.
* Enforce basic length checks, the rest
* should be done in userland.
*
* Returns 0 if name is considered valid.
*/
static int
check_table_name(const char *name)
{
/*
* TODO: do some more complicated checks
*/
return (ipfw_check_object_name_generic(name));
}
/*
* Finds table config based on either legacy index
* or name in ntlv.
* Note @ti structure contains unchecked data from userland.
*
* Returns 0 in success and fills in @tc with found config
*/
static int
find_table_err(struct namedobj_instance *ni, struct tid_info *ti,
struct table_config **tc)
{
char *name, bname[16];
struct named_object *no;
ipfw_obj_ntlv *ntlv;
uint32_t set;
if (ti->tlvs != NULL) {
ntlv = ipfw_find_name_tlv_type(ti->tlvs, ti->tlen, ti->uidx,
IPFW_TLV_TBL_NAME);
if (ntlv == NULL)
return (EINVAL);
name = ntlv->name;
/*
* Use set provided by @ti instead of @ntlv one.
* This is needed due to different sets behavior
* controlled by V_fw_tables_sets.
*/
set = (V_fw_tables_sets != 0) ? ti->set : 0;
} else {
snprintf(bname, sizeof(bname), "%d", ti->uidx);
name = bname;
set = 0;
}
no = ipfw_objhash_lookup_name(ni, set, name);
*tc = (struct table_config *)no;
return (0);
}
/*
* Finds table config based on either legacy index
* or name in ntlv.
* Note @ti structure contains unchecked data from userland.
*
* Returns pointer to table_config or NULL.
*/
static struct table_config *
find_table(struct namedobj_instance *ni, struct tid_info *ti)
{
struct table_config *tc;
if (find_table_err(ni, ti, &tc) != 0)
return (NULL);
return (tc);
}
/*
* Allocate new table config structure using
* specified @algo and @aname.
*
* Returns pointer to config or NULL.
*/
static struct table_config *
alloc_table_config(struct ip_fw_chain *ch, struct tid_info *ti,
struct table_algo *ta, char *aname, uint8_t tflags)
{
char *name, bname[16];
struct table_config *tc;
int error;
ipfw_obj_ntlv *ntlv;
uint32_t set;
if (ti->tlvs != NULL) {
ntlv = ipfw_find_name_tlv_type(ti->tlvs, ti->tlen, ti->uidx,
IPFW_TLV_TBL_NAME);
if (ntlv == NULL)
return (NULL);
name = ntlv->name;
set = ntlv->set;
} else {
/* Compat part: convert number to string representation */
snprintf(bname, sizeof(bname), "%d", ti->uidx);
name = bname;
set = 0;
}
tc = malloc(sizeof(struct table_config), M_IPFW, M_WAITOK | M_ZERO);
tc->no.name = tc->tablename;
tc->no.subtype = ta->type;
tc->no.set = set;
tc->tflags = tflags;
tc->ta = ta;
strlcpy(tc->tablename, name, sizeof(tc->tablename));
/* Set "shared" value type by default */
tc->vshared = 1;
/* Preallocate data structures for new tables */
error = ta->init(ch, &tc->astate, &tc->ti_copy, aname, tflags);
if (error != 0) {
free(tc, M_IPFW);
return (NULL);
}
return (tc);
}
/*
* Destroys table state and config.
*/
static void
free_table_config(struct namedobj_instance *ni, struct table_config *tc)
{
KASSERT(tc->linked == 0, ("free() on linked config"));
/* UH lock MUST NOT be held */
/*
* We're using ta without any locking/referencing.
* TODO: fix this if we're going to use unloadable algos.
*/
tc->ta->destroy(tc->astate, &tc->ti_copy);
free(tc, M_IPFW);
}
/*
* Links @tc to @chain table named instance.
* Sets appropriate type/states in @chain table info.
*/
static void
link_table(struct ip_fw_chain *ch, struct table_config *tc)
{
struct namedobj_instance *ni;
struct table_info *ti;
uint16_t kidx;
IPFW_UH_WLOCK_ASSERT(ch);
IPFW_WLOCK_ASSERT(ch);
ni = CHAIN_TO_NI(ch);
kidx = tc->no.kidx;
ipfw_objhash_add(ni, &tc->no);
ti = KIDX_TO_TI(ch, kidx);
*ti = tc->ti_copy;
/* Notify algo on real @ti address */
if (tc->ta->change_ti != NULL)
tc->ta->change_ti(tc->astate, ti);
tc->linked = 1;
tc->ta->refcnt++;
}
/*
* Unlinks @tc from @chain table named instance.
* Zeroes states in @chain and stores them in @tc.
*/
static void
unlink_table(struct ip_fw_chain *ch, struct table_config *tc)
{
struct namedobj_instance *ni;
struct table_info *ti;
uint16_t kidx;
IPFW_UH_WLOCK_ASSERT(ch);
IPFW_WLOCK_ASSERT(ch);
ni = CHAIN_TO_NI(ch);
kidx = tc->no.kidx;
/* Clear state. @ti copy is already saved inside @tc */
ipfw_objhash_del(ni, &tc->no);
ti = KIDX_TO_TI(ch, kidx);
memset(ti, 0, sizeof(struct table_info));
tc->linked = 0;
tc->ta->refcnt--;
/* Notify algo on real @ti address */
if (tc->ta->change_ti != NULL)
tc->ta->change_ti(tc->astate, NULL);
}
static struct ipfw_sopt_handler scodes[] = {
{ IP_FW_TABLE_XCREATE, 0, HDIR_SET, create_table },
{ IP_FW_TABLE_XDESTROY, 0, HDIR_SET, flush_table_v0 },
{ IP_FW_TABLE_XFLUSH, 0, HDIR_SET, flush_table_v0 },
{ IP_FW_TABLE_XMODIFY, 0, HDIR_BOTH, modify_table },
{ IP_FW_TABLE_XINFO, 0, HDIR_GET, describe_table },
{ IP_FW_TABLES_XLIST, 0, HDIR_GET, list_tables },
{ IP_FW_TABLE_XLIST, 0, HDIR_GET, dump_table_v0 },
{ IP_FW_TABLE_XLIST, 1, HDIR_GET, dump_table_v1 },
{ IP_FW_TABLE_XADD, 0, HDIR_BOTH, manage_table_ent_v0 },
{ IP_FW_TABLE_XADD, 1, HDIR_BOTH, manage_table_ent_v1 },
{ IP_FW_TABLE_XDEL, 0, HDIR_BOTH, manage_table_ent_v0 },
{ IP_FW_TABLE_XDEL, 1, HDIR_BOTH, manage_table_ent_v1 },
{ IP_FW_TABLE_XFIND, 0, HDIR_GET, find_table_entry },
{ IP_FW_TABLE_XSWAP, 0, HDIR_SET, swap_table },
{ IP_FW_TABLES_ALIST, 0, HDIR_GET, list_table_algo },
{ IP_FW_TABLE_XGETSIZE, 0, HDIR_GET, get_table_size },
};
static int
destroy_table_locked(struct namedobj_instance *ni, struct named_object *no,
void *arg)
{
unlink_table((struct ip_fw_chain *)arg, (struct table_config *)no);
if (ipfw_objhash_free_idx(ni, no->kidx) != 0)
printf("Error unlinking kidx %d from table %s\n",
no->kidx, no->name);
free_table_config(ni, (struct table_config *)no);
return (0);
}
/*
* Shuts tables module down.
*/
void
ipfw_destroy_tables(struct ip_fw_chain *ch, int last)
{
IPFW_DEL_SOPT_HANDLER(last, scodes);
IPFW_DEL_OBJ_REWRITER(last, opcodes);
/* Remove all tables from working set */
IPFW_UH_WLOCK(ch);
IPFW_WLOCK(ch);
ipfw_objhash_foreach(CHAIN_TO_NI(ch), destroy_table_locked, ch);
IPFW_WUNLOCK(ch);
IPFW_UH_WUNLOCK(ch);
/* Free pointers itself */
free(ch->tablestate, M_IPFW);
ipfw_table_value_destroy(ch, last);
ipfw_table_algo_destroy(ch);
ipfw_objhash_destroy(CHAIN_TO_NI(ch));
free(CHAIN_TO_TCFG(ch), M_IPFW);
}
/*
* Starts tables module.
*/
int
ipfw_init_tables(struct ip_fw_chain *ch, int first)
{
struct tables_config *tcfg;
/* Allocate pointers */
ch->tablestate = malloc(V_fw_tables_max * sizeof(struct table_info),
M_IPFW, M_WAITOK | M_ZERO);
tcfg = malloc(sizeof(struct tables_config), M_IPFW, M_WAITOK | M_ZERO);
tcfg->namehash = ipfw_objhash_create(V_fw_tables_max);
ch->tblcfg = tcfg;
ipfw_table_value_init(ch, first);
ipfw_table_algo_init(ch);
IPFW_ADD_OBJ_REWRITER(first, opcodes);
IPFW_ADD_SOPT_HANDLER(first, scodes);
return (0);
}
|