aboutsummaryrefslogtreecommitdiff
path: root/net/sunrpc/xprtsock.c
blob: ddf0602603bdef4ac0a6ad29a9815bae56f04626 (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
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
/*
 * linux/net/sunrpc/xprtsock.c
 *
 * Client-side transport implementation for sockets.
 *
 * TCP callback races fixes (C) 1998 Red Hat
 * TCP send fixes (C) 1998 Red Hat
 * TCP NFS related read + write fixes
 *  (C) 1999 Dave Airlie, University of Limerick, Ireland <airlied@linux.ie>
 *
 * Rewrite of larges part of the code in order to stabilize TCP stuff.
 * Fix behaviour when socket buffer is full.
 *  (C) 1999 Trond Myklebust <trond.myklebust@fys.uio.no>
 *
 * IP socket transport implementation, (C) 2005 Chuck Lever <cel@netapp.com>
 *
 * IPv6 support contributed by Gilles Quillard, Bull Open Source, 2005.
 *   <gilles.quillard@bull.net>
 */

#include <linux/types.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/pagemap.h>
#include <linux/errno.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/un.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/file.h>
#ifdef CONFIG_SUNRPC_BACKCHANNEL
#include <linux/sunrpc/bc_xprt.h>
#endif

#include <net/sock.h>
#include <net/checksum.h>
#include <net/udp.h>
#include <net/tcp.h>

#include "sunrpc.h"

static void xs_close(struct rpc_xprt *xprt);

/*
 * xprtsock tunables
 */
static unsigned int xprt_udp_slot_table_entries = RPC_DEF_SLOT_TABLE;
static unsigned int xprt_tcp_slot_table_entries = RPC_MIN_SLOT_TABLE;
static unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE;

static unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT;
static unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT;

#define XS_TCP_LINGER_TO	(15U * HZ)
static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO;

/*
 * We can register our own files under /proc/sys/sunrpc by
 * calling register_sysctl_table() again.  The files in that
 * directory become the union of all files registered there.
 *
 * We simply need to make sure that we don't collide with
 * someone else's file names!
 */

#ifdef RPC_DEBUG

static unsigned int min_slot_table_size = RPC_MIN_SLOT_TABLE;
static unsigned int max_slot_table_size = RPC_MAX_SLOT_TABLE;
static unsigned int max_tcp_slot_table_limit = RPC_MAX_SLOT_TABLE_LIMIT;
static unsigned int xprt_min_resvport_limit = RPC_MIN_RESVPORT;
static unsigned int xprt_max_resvport_limit = RPC_MAX_RESVPORT;

static struct ctl_table_header *sunrpc_table_header;

/*
 * FIXME: changing the UDP slot table size should also resize the UDP
 *        socket buffers for existing UDP transports
 */
static struct ctl_table xs_tunables_table[] = {
	{
		.procname	= "udp_slot_table_entries",
		.data		= &xprt_udp_slot_table_entries,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &min_slot_table_size,
		.extra2		= &max_slot_table_size
	},
	{
		.procname	= "tcp_slot_table_entries",
		.data		= &xprt_tcp_slot_table_entries,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &min_slot_table_size,
		.extra2		= &max_slot_table_size
	},
	{
		.procname	= "tcp_max_slot_table_entries",
		.data		= &xprt_max_tcp_slot_table_entries,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &min_slot_table_size,
		.extra2		= &max_tcp_slot_table_limit
	},
	{
		.procname	= "min_resvport",
		.data		= &xprt_min_resvport,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &xprt_min_resvport_limit,
		.extra2		= &xprt_max_resvport_limit
	},
	{
		.procname	= "max_resvport",
		.data		= &xprt_max_resvport,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &xprt_min_resvport_limit,
		.extra2		= &xprt_max_resvport_limit
	},
	{
		.procname	= "tcp_fin_timeout",
		.data		= &xs_tcp_fin_timeout,
		.maxlen		= sizeof(xs_tcp_fin_timeout),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{ },
};

static struct ctl_table sunrpc_table[] = {
	{
		.procname	= "sunrpc",
		.mode		= 0555,
		.child		= xs_tunables_table
	},
	{ },
};

#endif

/*
 * Wait duration for a reply from the RPC portmapper.
 */
#define XS_BIND_TO		(60U * HZ)

/*
 * Delay if a UDP socket connect error occurs.  This is most likely some
 * kind of resource problem on the local host.
 */
#define XS_UDP_REEST_TO		(2U * HZ)

/*
 * The reestablish timeout allows clients to delay for a bit before attempting
 * to reconnect to a server that just dropped our connection.
 *
 * We implement an exponential backoff when trying to reestablish a TCP
 * transport connection with the server.  Some servers like to drop a TCP
 * connection when they are overworked, so we start with a short timeout and
 * increase over time if the server is down or not responding.
 */
#define XS_TCP_INIT_REEST_TO	(3U * HZ)
#define XS_TCP_MAX_REEST_TO	(5U * 60 * HZ)

/*
 * TCP idle timeout; client drops the transport socket if it is idle
 * for this long.  Note that we also timeout UDP sockets to prevent
 * holding port numbers when there is no RPC traffic.
 */
#define XS_IDLE_DISC_TO		(5U * 60 * HZ)

#ifdef RPC_DEBUG
# undef  RPC_DEBUG_DATA
# define RPCDBG_FACILITY	RPCDBG_TRANS
#endif

#ifdef RPC_DEBUG_DATA
static void xs_pktdump(char *msg, u32 *packet, unsigned int count)
{
	u8 *buf = (u8 *) packet;
	int j;

	dprintk("RPC:       %s\n", msg);
	for (j = 0; j < count && j < 128; j += 4) {
		if (!(j & 31)) {
			if (j)
				dprintk("\n");
			dprintk("0x%04x ", j);
		}
		dprintk("%02x%02x%02x%02x ",
			buf[j], buf[j+1], buf[j+2], buf[j+3]);
	}
	dprintk("\n");
}
#else
static inline void xs_pktdump(char *msg, u32 *packet, unsigned int count)
{
	/* NOP */
}
#endif

struct sock_xprt {
	struct rpc_xprt		xprt;

	/*
	 * Network layer
	 */
	struct socket *		sock;
	struct sock *		inet;

	/*
	 * State of TCP reply receive
	 */
	__be32			tcp_fraghdr,
				tcp_xid,
				tcp_calldir;

	u32			tcp_offset,
				tcp_reclen;

	unsigned long		tcp_copied,
				tcp_flags;

	/*
	 * Connection of transports
	 */
	struct delayed_work	connect_worker;
	struct sockaddr_storage	srcaddr;
	unsigned short		srcport;

	/*
	 * UDP socket buffer size parameters
	 */
	size_t			rcvsize,
				sndsize;

	/*
	 * Saved socket callback addresses
	 */
	void			(*old_data_ready)(struct sock *, int);
	void			(*old_state_change)(struct sock *);
	void			(*old_write_space)(struct sock *);
};

/*
 * TCP receive state flags
 */
#define TCP_RCV_LAST_FRAG	(1UL << 0)
#define TCP_RCV_COPY_FRAGHDR	(1UL << 1)
#define TCP_RCV_COPY_XID	(1UL << 2)
#define TCP_RCV_COPY_DATA	(1UL << 3)
#define TCP_RCV_READ_CALLDIR	(1UL << 4)
#define TCP_RCV_COPY_CALLDIR	(1UL << 5)

/*
 * TCP RPC flags
 */
#define TCP_RPC_REPLY		(1UL << 6)

static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
{
	return (struct sockaddr *) &xprt->addr;
}

static inline struct sockaddr_un *xs_addr_un(struct rpc_xprt *xprt)
{
	return (struct sockaddr_un *) &xprt->addr;
}

static inline struct sockaddr_in *xs_addr_in(struct rpc_xprt *xprt)
{
	return (struct sockaddr_in *) &xprt->addr;
}

static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt)
{
	return (struct sockaddr_in6 *) &xprt->addr;
}

static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)
{
	struct sockaddr *sap = xs_addr(xprt);
	struct sockaddr_in6 *sin6;
	struct sockaddr_in *sin;
	struct sockaddr_un *sun;
	char buf[128];

	switch (sap->sa_family) {
	case AF_LOCAL:
		sun = xs_addr_un(xprt);
		strlcpy(buf, sun->sun_path, sizeof(buf));
		xprt->address_strings[RPC_DISPLAY_ADDR] =
						kstrdup(buf, GFP_KERNEL);
		break;
	case AF_INET:
		(void)rpc_ntop(sap, buf, sizeof(buf));
		xprt->address_strings[RPC_DISPLAY_ADDR] =
						kstrdup(buf, GFP_KERNEL);
		sin = xs_addr_in(xprt);
		snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
		break;
	case AF_INET6:
		(void)rpc_ntop(sap, buf, sizeof(buf));
		xprt->address_strings[RPC_DISPLAY_ADDR] =
						kstrdup(buf, GFP_KERNEL);
		sin6 = xs_addr_in6(xprt);
		snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
		break;
	default:
		BUG();
	}

	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
}

static void xs_format_common_peer_ports(struct rpc_xprt *xprt)
{
	struct sockaddr *sap = xs_addr(xprt);
	char buf[128];

	snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);

	snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
}

static void xs_format_peer_addresses(struct rpc_xprt *xprt,
				     const char *protocol,
				     const char *netid)
{
	xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;
	xprt->address_strings[RPC_DISPLAY_NETID] = netid;
	xs_format_common_peer_addresses(xprt);
	xs_format_common_peer_ports(xprt);
}

static void xs_update_peer_port(struct rpc_xprt *xprt)
{
	kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
	kfree(xprt->address_strings[RPC_DISPLAY_PORT]);

	xs_format_common_peer_ports(xprt);
}

static void xs_free_peer_addresses(struct rpc_xprt *xprt)
{
	unsigned int i;

	for (i = 0; i < RPC_DISPLAY_MAX; i++)
		switch (i) {
		case RPC_DISPLAY_PROTO:
		case RPC_DISPLAY_NETID:
			continue;
		default:
			kfree(xprt->address_strings[i]);
		}
}

#define XS_SENDMSG_FLAGS	(MSG_DONTWAIT | MSG_NOSIGNAL)

static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more)
{
	struct msghdr msg = {
		.msg_name	= addr,
		.msg_namelen	= addrlen,
		.msg_flags	= XS_SENDMSG_FLAGS | (more ? MSG_MORE : 0),
	};
	struct kvec iov = {
		.iov_base	= vec->iov_base + base,
		.iov_len	= vec->iov_len - base,
	};

	if (iov.iov_len != 0)
		return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
	return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}

static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
{
	struct page **ppage;
	unsigned int remainder;
	int err, sent = 0;

	remainder = xdr->page_len - base;
	base += xdr->page_base;
	ppage = xdr->pages + (base >> PAGE_SHIFT);
	base &= ~PAGE_MASK;
	for(;;) {
		unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
		int flags = XS_SENDMSG_FLAGS;

		remainder -= len;
		if (remainder != 0 || more)
			flags |= MSG_MORE;
		err = sock->ops->sendpage(sock, *ppage, base, len, flags);
		if (remainder == 0 || err != len)
			break;
		sent += err;
		ppage++;
		base = 0;
	}
	if (sent == 0)
		return err;
	if (err > 0)
		sent += err;
	return sent;
}

/**
 * xs_sendpages - write pages directly to a socket
 * @sock: socket to send on
 * @addr: UDP only -- address of destination
 * @addrlen: UDP only -- length of destination address
 * @xdr: buffer containing this request
 * @base: starting position in the buffer
 *
 */
static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
{
	unsigned int remainder = xdr->len - base;
	int err, sent = 0;

	if (unlikely(!sock))
		return -ENOTSOCK;

	clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
	if (base != 0) {
		addr = NULL;
		addrlen = 0;
	}

	if (base < xdr->head[0].iov_len || addr != NULL) {
		unsigned int len = xdr->head[0].iov_len - base;
		remainder -= len;
		err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], base, remainder != 0);
		if (remainder == 0 || err != len)
			goto out;
		sent += err;
		base = 0;
	} else
		base -= xdr->head[0].iov_len;

	if (base < xdr->page_len) {
		unsigned int len = xdr->page_len - base;
		remainder -= len;
		err = xs_send_pagedata(sock, xdr, base, remainder != 0);
		if (remainder == 0 || err != len)
			goto out;
		sent += err;
		base = 0;
	} else
		base -= xdr->page_len;

	if (base >= xdr->tail[0].iov_len)
		return sent;
	err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0);
out:
	if (sent == 0)
		return err;
	if (err > 0)
		sent += err;
	return sent;
}

static void xs_nospace_callback(struct rpc_task *task)
{
	struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);

	transport->inet->sk_write_pending--;
	clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
}

/**
 * xs_nospace - place task on wait queue if transmit was incomplete
 * @task: task to put to sleep
 *
 */
static int xs_nospace(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	int ret = -EAGAIN;

	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
			task->tk_pid, req->rq_slen - req->rq_bytes_sent,
			req->rq_slen);

	/* Protect against races with write_space */
	spin_lock_bh(&xprt->transport_lock);

	/* Don't race with disconnect */
	if (xprt_connected(xprt)) {
		if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
			/*
			 * Notify TCP that we're limited by the application
			 * window size
			 */
			set_bit(SOCK_NOSPACE, &transport->sock->flags);
			transport->inet->sk_write_pending++;
			/* ...and wait for more buffer space */
			xprt_wait_for_buffer_space(task, xs_nospace_callback);
		}
	} else {
		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
		ret = -ENOTCONN;
	}

	spin_unlock_bh(&xprt->transport_lock);
	return ret;
}

/*
 * Construct a stream transport record marker in @buf.
 */
static inline void xs_encode_stream_record_marker(struct xdr_buf *buf)
{
	u32 reclen = buf->len - sizeof(rpc_fraghdr);
	rpc_fraghdr *base = buf->head[0].iov_base;
	*base = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | reclen);
}

/**
 * xs_local_send_request - write an RPC request to an AF_LOCAL socket
 * @task: RPC task that manages the state of an RPC request
 *
 * Return values:
 *        0:	The request has been sent
 *   EAGAIN:	The socket was blocked, please call again later to
 *		complete the request
 * ENOTCONN:	Caller needs to invoke connect logic then call again
 *    other:	Some other error occured, the request was not sent
 */
static int xs_local_send_request(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);
	struct xdr_buf *xdr = &req->rq_snd_buf;
	int status;

	xs_encode_stream_record_marker(&req->rq_snd_buf);

	xs_pktdump("packet data:",
			req->rq_svec->iov_base, req->rq_svec->iov_len);

	status = xs_sendpages(transport->sock, NULL, 0,
						xdr, req->rq_bytes_sent);
	dprintk("RPC:       %s(%u) = %d\n",
			__func__, xdr->len - req->rq_bytes_sent, status);
	if (likely(status >= 0)) {
		req->rq_bytes_sent += status;
		req->rq_xmit_bytes_sent += status;
		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
			req->rq_bytes_sent = 0;
			return 0;
		}
		status = -EAGAIN;
	}

	switch (status) {
	case -EAGAIN:
		status = xs_nospace(task);
		break;
	default:
		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
			-status);
	case -EPIPE:
		xs_close(xprt);
		status = -ENOTCONN;
	}

	return status;
}

/**
 * xs_udp_send_request - write an RPC request to a UDP socket
 * @task: address of RPC task that manages the state of an RPC request
 *
 * Return values:
 *        0:	The request has been sent
 *   EAGAIN:	The socket was blocked, please call again later to
 *		complete the request
 * ENOTCONN:	Caller needs to invoke connect logic then call again
 *    other:	Some other error occurred, the request was not sent
 */
static int xs_udp_send_request(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct xdr_buf *xdr = &req->rq_snd_buf;
	int status;

	xs_pktdump("packet data:",
				req->rq_svec->iov_base,
				req->rq_svec->iov_len);

	if (!xprt_bound(xprt))
		return -ENOTCONN;
	status = xs_sendpages(transport->sock,
			      xs_addr(xprt),
			      xprt->addrlen, xdr,
			      req->rq_bytes_sent);

	dprintk("RPC:       xs_udp_send_request(%u) = %d\n",
			xdr->len - req->rq_bytes_sent, status);

	if (status >= 0) {
		req->rq_xmit_bytes_sent += status;
		if (status >= req->rq_slen)
			return 0;
		/* Still some bytes left; set up for a retry later. */
		status = -EAGAIN;
	}

	switch (status) {
	case -ENOTSOCK:
		status = -ENOTCONN;
		/* Should we call xs_close() here? */
		break;
	case -EAGAIN:
		status = xs_nospace(task);
		break;
	default:
		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
			-status);
	case -ENETUNREACH:
	case -EPIPE:
	case -ECONNREFUSED:
		/* When the server has died, an ICMP port unreachable message
		 * prompts ECONNREFUSED. */
		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
	}

	return status;
}

/**
 * xs_tcp_shutdown - gracefully shut down a TCP socket
 * @xprt: transport
 *
 * Initiates a graceful shutdown of the TCP socket by calling the
 * equivalent of shutdown(SHUT_WR);
 */
static void xs_tcp_shutdown(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct socket *sock = transport->sock;

	if (sock != NULL)
		kernel_sock_shutdown(sock, SHUT_WR);
}

/**
 * xs_tcp_send_request - write an RPC request to a TCP socket
 * @task: address of RPC task that manages the state of an RPC request
 *
 * Return values:
 *        0:	The request has been sent
 *   EAGAIN:	The socket was blocked, please call again later to
 *		complete the request
 * ENOTCONN:	Caller needs to invoke connect logic then call again
 *    other:	Some other error occurred, the request was not sent
 *
 * XXX: In the case of soft timeouts, should we eventually give up
 *	if sendmsg is not able to make progress?
 */
static int xs_tcp_send_request(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct rpc_xprt *xprt = req->rq_xprt;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct xdr_buf *xdr = &req->rq_snd_buf;
	int status;

	xs_encode_stream_record_marker(&req->rq_snd_buf);

	xs_pktdump("packet data:",
				req->rq_svec->iov_base,
				req->rq_svec->iov_len);

	/* Continue transmitting the packet/record. We must be careful
	 * to cope with writespace callbacks arriving _after_ we have
	 * called sendmsg(). */
	while (1) {
		status = xs_sendpages(transport->sock,
					NULL, 0, xdr, req->rq_bytes_sent);

		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
				xdr->len - req->rq_bytes_sent, status);

		if (unlikely(status < 0))
			break;

		/* If we've sent the entire packet, immediately
		 * reset the count of bytes sent. */
		req->rq_bytes_sent += status;
		req->rq_xmit_bytes_sent += status;
		if (likely(req->rq_bytes_sent >= req->rq_slen)) {
			req->rq_bytes_sent = 0;
			return 0;
		}

		if (status != 0)
			continue;
		status = -EAGAIN;
		break;
	}

	switch (status) {
	case -ENOTSOCK:
		status = -ENOTCONN;
		/* Should we call xs_close() here? */
		break;
	case -EAGAIN:
		status = xs_nospace(task);
		break;
	default:
		dprintk("RPC:       sendmsg returned unrecognized error %d\n",
			-status);
	case -ECONNRESET:
		xs_tcp_shutdown(xprt);
	case -ECONNREFUSED:
	case -ENOTCONN:
	case -EPIPE:
		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
	}

	return status;
}

/**
 * xs_tcp_release_xprt - clean up after a tcp transmission
 * @xprt: transport
 * @task: rpc task
 *
 * This cleans up if an error causes us to abort the transmission of a request.
 * In this case, the socket may need to be reset in order to avoid confusing
 * the server.
 */
static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct rpc_rqst *req;

	if (task != xprt->snd_task)
		return;
	if (task == NULL)
		goto out_release;
	req = task->tk_rqstp;
	if (req == NULL)
		goto out_release;
	if (req->rq_bytes_sent == 0)
		goto out_release;
	if (req->rq_bytes_sent == req->rq_snd_buf.len)
		goto out_release;
	set_bit(XPRT_CLOSE_WAIT, &xprt->state);
out_release:
	xprt_release_xprt(xprt, task);
}

static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
{
	transport->old_data_ready = sk->sk_data_ready;
	transport->old_state_change = sk->sk_state_change;
	transport->old_write_space = sk->sk_write_space;
}

static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
{
	sk->sk_data_ready = transport->old_data_ready;
	sk->sk_state_change = transport->old_state_change;
	sk->sk_write_space = transport->old_write_space;
}

static void xs_reset_transport(struct sock_xprt *transport)
{
	struct socket *sock = transport->sock;
	struct sock *sk = transport->inet;

	if (sk == NULL)
		return;

	transport->srcport = 0;

	write_lock_bh(&sk->sk_callback_lock);
	transport->inet = NULL;
	transport->sock = NULL;

	sk->sk_user_data = NULL;

	xs_restore_old_callbacks(transport, sk);
	write_unlock_bh(&sk->sk_callback_lock);

	sk->sk_no_check = 0;

	sock_release(sock);
}

/**
 * xs_close - close a socket
 * @xprt: transport
 *
 * This is used when all requests are complete; ie, no DRC state remains
 * on the server we want to save.
 *
 * The caller _must_ be holding XPRT_LOCKED in order to avoid issues with
 * xs_reset_transport() zeroing the socket from underneath a writer.
 */
static void xs_close(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	dprintk("RPC:       xs_close xprt %p\n", xprt);

	xs_reset_transport(transport);
	xprt->reestablish_timeout = 0;

	smp_mb__before_clear_bit();
	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
	clear_bit(XPRT_CLOSING, &xprt->state);
	smp_mb__after_clear_bit();
	xprt_disconnect_done(xprt);
}

static void xs_tcp_close(struct rpc_xprt *xprt)
{
	if (test_and_clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state))
		xs_close(xprt);
	else
		xs_tcp_shutdown(xprt);
}

static void xs_local_destroy(struct rpc_xprt *xprt)
{
	xs_close(xprt);
	xs_free_peer_addresses(xprt);
	xprt_free(xprt);
	module_put(THIS_MODULE);
}

/**
 * xs_destroy - prepare to shutdown a transport
 * @xprt: doomed transport
 *
 */
static void xs_destroy(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	dprintk("RPC:       xs_destroy xprt %p\n", xprt);

	cancel_delayed_work_sync(&transport->connect_worker);

	xs_local_destroy(xprt);
}

static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
{
	return (struct rpc_xprt *) sk->sk_user_data;
}

static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
{
	struct xdr_skb_reader desc = {
		.skb		= skb,
		.offset		= sizeof(rpc_fraghdr),
		.count		= skb->len - sizeof(rpc_fraghdr),
	};

	if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
		return -1;
	if (desc.count)
		return -1;
	return 0;
}

/**
 * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
 * @sk: socket with data to read
 * @len: how much data to read
 *
 * Currently this assumes we can read the whole reply in a single gulp.
 */
static void xs_local_data_ready(struct sock *sk, int len)
{
	struct rpc_task *task;
	struct rpc_xprt *xprt;
	struct rpc_rqst *rovr;
	struct sk_buff *skb;
	int err, repsize, copied;
	u32 _xid;
	__be32 *xp;

	read_lock_bh(&sk->sk_callback_lock);
	dprintk("RPC:       %s...\n", __func__);
	xprt = xprt_from_sock(sk);
	if (xprt == NULL)
		goto out;

	skb = skb_recv_datagram(sk, 0, 1, &err);
	if (skb == NULL)
		goto out;

	repsize = skb->len - sizeof(rpc_fraghdr);
	if (repsize < 4) {
		dprintk("RPC:       impossible RPC reply size %d\n", repsize);
		goto dropit;
	}

	/* Copy the XID from the skb... */
	xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid);
	if (xp == NULL)
		goto dropit;

	/* Look up and lock the request corresponding to the given XID */
	spin_lock(&xprt->transport_lock);
	rovr = xprt_lookup_rqst(xprt, *xp);
	if (!rovr)
		goto out_unlock;
	task = rovr->rq_task;

	copied = rovr->rq_private_buf.buflen;
	if (copied > repsize)
		copied = repsize;

	if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) {
		dprintk("RPC:       sk_buff copy failed\n");
		goto out_unlock;
	}

	xprt_complete_rqst(task, copied);

 out_unlock:
	spin_unlock(&xprt->transport_lock);
 dropit:
	skb_free_datagram(sk, skb);
 out:
	read_unlock_bh(&sk->sk_callback_lock);
}

/**
 * xs_udp_data_ready - "data ready" callback for UDP sockets
 * @sk: socket with data to read
 * @len: how much data to read
 *
 */
static void xs_udp_data_ready(struct sock *sk, int len)
{
	struct rpc_task *task;
	struct rpc_xprt *xprt;
	struct rpc_rqst *rovr;
	struct sk_buff *skb;
	int err, repsize, copied;
	u32 _xid;
	__be32 *xp;

	read_lock_bh(&sk->sk_callback_lock);
	dprintk("RPC:       xs_udp_data_ready...\n");
	if (!(xprt = xprt_from_sock(sk)))
		goto out;

	if ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL)
		goto out;

	repsize = skb->len - sizeof(struct udphdr);
	if (repsize < 4) {
		dprintk("RPC:       impossible RPC reply size %d!\n", repsize);
		goto dropit;
	}

	/* Copy the XID from the skb... */
	xp = skb_header_pointer(skb, sizeof(struct udphdr),
				sizeof(_xid), &_xid);
	if (xp == NULL)
		goto dropit;

	/* Look up and lock the request corresponding to the given XID */
	spin_lock(&xprt->transport_lock);
	rovr = xprt_lookup_rqst(xprt, *xp);
	if (!rovr)
		goto out_unlock;
	task = rovr->rq_task;

	if ((copied = rovr->rq_private_buf.buflen) > repsize)
		copied = repsize;

	/* Suck it into the iovec, verify checksum if not done by hw. */
	if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) {
		UDPX_INC_STATS_BH(sk, UDP_MIB_INERRORS);
		goto out_unlock;
	}

	UDPX_INC_STATS_BH(sk, UDP_MIB_INDATAGRAMS);

	xprt_adjust_cwnd(xprt, task, copied);
	xprt_complete_rqst(task, copied);

 out_unlock:
	spin_unlock(&xprt->transport_lock);
 dropit:
	skb_free_datagram(sk, skb);
 out:
	read_unlock_bh(&sk->sk_callback_lock);
}

/*
 * Helper function to force a TCP close if the server is sending
 * junk and/or it has put us in CLOSE_WAIT
 */
static void xs_tcp_force_close(struct rpc_xprt *xprt)
{
	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
	xprt_force_disconnect(xprt);
}

static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	size_t len, used;
	char *p;

	p = ((char *) &transport->tcp_fraghdr) + transport->tcp_offset;
	len = sizeof(transport->tcp_fraghdr) - transport->tcp_offset;
	used = xdr_skb_read_bits(desc, p, len);
	transport->tcp_offset += used;
	if (used != len)
		return;

	transport->tcp_reclen = ntohl(transport->tcp_fraghdr);
	if (transport->tcp_reclen & RPC_LAST_STREAM_FRAGMENT)
		transport->tcp_flags |= TCP_RCV_LAST_FRAG;
	else
		transport->tcp_flags &= ~TCP_RCV_LAST_FRAG;
	transport->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK;

	transport->tcp_flags &= ~TCP_RCV_COPY_FRAGHDR;
	transport->tcp_offset = 0;

	/* Sanity check of the record length */
	if (unlikely(transport->tcp_reclen < 8)) {
		dprintk("RPC:       invalid TCP record fragment length\n");
		xs_tcp_force_close(xprt);
		return;
	}
	dprintk("RPC:       reading TCP record fragment of length %d\n",
			transport->tcp_reclen);
}

static void xs_tcp_check_fraghdr(struct sock_xprt *transport)
{
	if (transport->tcp_offset == transport->tcp_reclen) {
		transport->tcp_flags |= TCP_RCV_COPY_FRAGHDR;
		transport->tcp_offset = 0;
		if (transport->tcp_flags & TCP_RCV_LAST_FRAG) {
			transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
			transport->tcp_flags |= TCP_RCV_COPY_XID;
			transport->tcp_copied = 0;
		}
	}
}

static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
	size_t len, used;
	char *p;

	len = sizeof(transport->tcp_xid) - transport->tcp_offset;
	dprintk("RPC:       reading XID (%Zu bytes)\n", len);
	p = ((char *) &transport->tcp_xid) + transport->tcp_offset;
	used = xdr_skb_read_bits(desc, p, len);
	transport->tcp_offset += used;
	if (used != len)
		return;
	transport->tcp_flags &= ~TCP_RCV_COPY_XID;
	transport->tcp_flags |= TCP_RCV_READ_CALLDIR;
	transport->tcp_copied = 4;
	dprintk("RPC:       reading %s XID %08x\n",
			(transport->tcp_flags & TCP_RPC_REPLY) ? "reply for"
							      : "request with",
			ntohl(transport->tcp_xid));
	xs_tcp_check_fraghdr(transport);
}

static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
				       struct xdr_skb_reader *desc)
{
	size_t len, used;
	u32 offset;
	char *p;

	/*
	 * We want transport->tcp_offset to be 8 at the end of this routine
	 * (4 bytes for the xid and 4 bytes for the call/reply flag).
	 * When this function is called for the first time,
	 * transport->tcp_offset is 4 (after having already read the xid).
	 */
	offset = transport->tcp_offset - sizeof(transport->tcp_xid);
	len = sizeof(transport->tcp_calldir) - offset;
	dprintk("RPC:       reading CALL/REPLY flag (%Zu bytes)\n", len);
	p = ((char *) &transport->tcp_calldir) + offset;
	used = xdr_skb_read_bits(desc, p, len);
	transport->tcp_offset += used;
	if (used != len)
		return;
	transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR;
	/*
	 * We don't yet have the XDR buffer, so we will write the calldir
	 * out after we get the buffer from the 'struct rpc_rqst'
	 */
	switch (ntohl(transport->tcp_calldir)) {
	case RPC_REPLY:
		transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
		transport->tcp_flags |= TCP_RCV_COPY_DATA;
		transport->tcp_flags |= TCP_RPC_REPLY;
		break;
	case RPC_CALL:
		transport->tcp_flags |= TCP_RCV_COPY_CALLDIR;
		transport->tcp_flags |= TCP_RCV_COPY_DATA;
		transport->tcp_flags &= ~TCP_RPC_REPLY;
		break;
	default:
		dprintk("RPC:       invalid request message type\n");
		xs_tcp_force_close(&transport->xprt);
	}
	xs_tcp_check_fraghdr(transport);
}

static inline void xs_tcp_read_common(struct rpc_xprt *xprt,
				     struct xdr_skb_reader *desc,
				     struct rpc_rqst *req)
{
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);
	struct xdr_buf *rcvbuf;
	size_t len;
	ssize_t r;

	rcvbuf = &req->rq_private_buf;

	if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) {
		/*
		 * Save the RPC direction in the XDR buffer
		 */
		memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied,
			&transport->tcp_calldir,
			sizeof(transport->tcp_calldir));
		transport->tcp_copied += sizeof(transport->tcp_calldir);
		transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR;
	}

	len = desc->count;
	if (len > transport->tcp_reclen - transport->tcp_offset) {
		struct xdr_skb_reader my_desc;

		len = transport->tcp_reclen - transport->tcp_offset;
		memcpy(&my_desc, desc, sizeof(my_desc));
		my_desc.count = len;
		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
					  &my_desc, xdr_skb_read_bits);
		desc->count -= r;
		desc->offset += r;
	} else
		r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied,
					  desc, xdr_skb_read_bits);

	if (r > 0) {
		transport->tcp_copied += r;
		transport->tcp_offset += r;
	}
	if (r != len) {
		/* Error when copying to the receive buffer,
		 * usually because we weren't able to allocate
		 * additional buffer pages. All we can do now
		 * is turn off TCP_RCV_COPY_DATA, so the request
		 * will not receive any additional updates,
		 * and time out.
		 * Any remaining data from this record will
		 * be discarded.
		 */
		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
		dprintk("RPC:       XID %08x truncated request\n",
				ntohl(transport->tcp_xid));
		dprintk("RPC:       xprt = %p, tcp_copied = %lu, "
				"tcp_offset = %u, tcp_reclen = %u\n",
				xprt, transport->tcp_copied,
				transport->tcp_offset, transport->tcp_reclen);
		return;
	}

	dprintk("RPC:       XID %08x read %Zd bytes\n",
			ntohl(transport->tcp_xid), r);
	dprintk("RPC:       xprt = %p, tcp_copied = %lu, tcp_offset = %u, "
			"tcp_reclen = %u\n", xprt, transport->tcp_copied,
			transport->tcp_offset, transport->tcp_reclen);

	if (transport->tcp_copied == req->rq_private_buf.buflen)
		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
	else if (transport->tcp_offset == transport->tcp_reclen) {
		if (transport->tcp_flags & TCP_RCV_LAST_FRAG)
			transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
	}
}

/*
 * Finds the request corresponding to the RPC xid and invokes the common
 * tcp read code to read the data.
 */
static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
				    struct xdr_skb_reader *desc)
{
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);
	struct rpc_rqst *req;

	dprintk("RPC:       read reply XID %08x\n", ntohl(transport->tcp_xid));

	/* Find and lock the request corresponding to this xid */
	spin_lock(&xprt->transport_lock);
	req = xprt_lookup_rqst(xprt, transport->tcp_xid);
	if (!req) {
		dprintk("RPC:       XID %08x request not found!\n",
				ntohl(transport->tcp_xid));
		spin_unlock(&xprt->transport_lock);
		return -1;
	}

	xs_tcp_read_common(xprt, desc, req);

	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
		xprt_complete_rqst(req->rq_task, transport->tcp_copied);

	spin_unlock(&xprt->transport_lock);
	return 0;
}

#if defined(CONFIG_SUNRPC_BACKCHANNEL)
/*
 * Obtains an rpc_rqst previously allocated and invokes the common
 * tcp read code to read the data.  The result is placed in the callback
 * queue.
 * If we're unable to obtain the rpc_rqst we schedule the closing of the
 * connection and return -1.
 */
static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
				       struct xdr_skb_reader *desc)
{
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);
	struct rpc_rqst *req;

	req = xprt_alloc_bc_request(xprt);
	if (req == NULL) {
		printk(KERN_WARNING "Callback slot table overflowed\n");
		xprt_force_disconnect(xprt);
		return -1;
	}

	req->rq_xid = transport->tcp_xid;
	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
	xs_tcp_read_common(xprt, desc, req);

	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
		struct svc_serv *bc_serv = xprt->bc_serv;

		/*
		 * Add callback request to callback list.  The callback
		 * service sleeps on the sv_cb_waitq waiting for new
		 * requests.  Wake it up after adding enqueing the
		 * request.
		 */
		dprintk("RPC:       add callback request to list\n");
		spin_lock(&bc_serv->sv_cb_lock);
		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
		spin_unlock(&bc_serv->sv_cb_lock);
		wake_up(&bc_serv->sv_cb_waitq);
	}

	req->rq_private_buf.len = transport->tcp_copied;

	return 0;
}

static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
					struct xdr_skb_reader *desc)
{
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);

	return (transport->tcp_flags & TCP_RPC_REPLY) ?
		xs_tcp_read_reply(xprt, desc) :
		xs_tcp_read_callback(xprt, desc);
}
#else
static inline int _xs_tcp_read_data(struct rpc_xprt *xprt,
					struct xdr_skb_reader *desc)
{
	return xs_tcp_read_reply(xprt, desc);
}
#endif /* CONFIG_SUNRPC_BACKCHANNEL */

/*
 * Read data off the transport.  This can be either an RPC_CALL or an
 * RPC_REPLY.  Relay the processing to helper functions.
 */
static void xs_tcp_read_data(struct rpc_xprt *xprt,
				    struct xdr_skb_reader *desc)
{
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);

	if (_xs_tcp_read_data(xprt, desc) == 0)
		xs_tcp_check_fraghdr(transport);
	else {
		/*
		 * The transport_lock protects the request handling.
		 * There's no need to hold it to update the tcp_flags.
		 */
		transport->tcp_flags &= ~TCP_RCV_COPY_DATA;
	}
}

static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc)
{
	size_t len;

	len = transport->tcp_reclen - transport->tcp_offset;
	if (len > desc->count)
		len = desc->count;
	desc->count -= len;
	desc->offset += len;
	transport->tcp_offset += len;
	dprintk("RPC:       discarded %Zu bytes\n", len);
	xs_tcp_check_fraghdr(transport);
}

static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len)
{
	struct rpc_xprt *xprt = rd_desc->arg.data;
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct xdr_skb_reader desc = {
		.skb	= skb,
		.offset	= offset,
		.count	= len,
	};

	dprintk("RPC:       xs_tcp_data_recv started\n");
	do {
		/* Read in a new fragment marker if necessary */
		/* Can we ever really expect to get completely empty fragments? */
		if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) {
			xs_tcp_read_fraghdr(xprt, &desc);
			continue;
		}
		/* Read in the xid if necessary */
		if (transport->tcp_flags & TCP_RCV_COPY_XID) {
			xs_tcp_read_xid(transport, &desc);
			continue;
		}
		/* Read in the call/reply flag */
		if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) {
			xs_tcp_read_calldir(transport, &desc);
			continue;
		}
		/* Read in the request data */
		if (transport->tcp_flags & TCP_RCV_COPY_DATA) {
			xs_tcp_read_data(xprt, &desc);
			continue;
		}
		/* Skip over any trailing bytes on short reads */
		xs_tcp_read_discard(transport, &desc);
	} while (desc.count);
	dprintk("RPC:       xs_tcp_data_recv done\n");
	return len - desc.count;
}

/**
 * xs_tcp_data_ready - "data ready" callback for TCP sockets
 * @sk: socket with data to read
 * @bytes: how much data to read
 *
 */
static void xs_tcp_data_ready(struct sock *sk, int bytes)
{
	struct rpc_xprt *xprt;
	read_descriptor_t rd_desc;
	int read;

	dprintk("RPC:       xs_tcp_data_ready...\n");

	read_lock_bh(&sk->sk_callback_lock);
	if (!(xprt = xprt_from_sock(sk)))
		goto out;
	/* Any data means we had a useful conversation, so
	 * the we don't need to delay the next reconnect
	 */
	if (xprt->reestablish_timeout)
		xprt->reestablish_timeout = 0;

	/* We use rd_desc to pass struct xprt to xs_tcp_data_recv */
	rd_desc.arg.data = xprt;
	do {
		rd_desc.count = 65536;
		read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv);
	} while (read > 0);
out:
	read_unlock_bh(&sk->sk_callback_lock);
}

/*
 * Do the equivalent of linger/linger2 handling for dealing with
 * broken servers that don't close the socket in a timely
 * fashion
 */
static void xs_tcp_schedule_linger_timeout(struct rpc_xprt *xprt,
		unsigned long timeout)
{
	struct sock_xprt *transport;

	if (xprt_test_and_set_connecting(xprt))
		return;
	set_bit(XPRT_CONNECTION_ABORT, &xprt->state);
	transport = container_of(xprt, struct sock_xprt, xprt);
	queue_delayed_work(rpciod_workqueue, &transport->connect_worker,
			   timeout);
}

static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport;

	transport = container_of(xprt, struct sock_xprt, xprt);

	if (!test_bit(XPRT_CONNECTION_ABORT, &xprt->state) ||
	    !cancel_delayed_work(&transport->connect_worker))
		return;
	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
	xprt_clear_connecting(xprt);
}

static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
{
	smp_mb__before_clear_bit();
	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
	clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
	clear_bit(XPRT_CLOSING, &xprt->state);
	smp_mb__after_clear_bit();
}

static void xs_sock_mark_closed(struct rpc_xprt *xprt)
{
	xs_sock_reset_connection_flags(xprt);
	/* Mark transport as closed and wake up all pending tasks */
	xprt_disconnect_done(xprt);
}

/**
 * xs_tcp_state_change - callback to handle TCP socket state changes
 * @sk: socket whose state has changed
 *
 */
static void xs_tcp_state_change(struct sock *sk)
{
	struct rpc_xprt *xprt;

	read_lock_bh(&sk->sk_callback_lock);
	if (!(xprt = xprt_from_sock(sk)))
		goto out;
	dprintk("RPC:       xs_tcp_state_change client %p...\n", xprt);
	dprintk("RPC:       state %x conn %d dead %d zapped %d sk_shutdown %d\n",
			sk->sk_state, xprt_connected(xprt),
			sock_flag(sk, SOCK_DEAD),
			sock_flag(sk, SOCK_ZAPPED),
			sk->sk_shutdown);

	switch (sk->sk_state) {
	case TCP_ESTABLISHED:
		spin_lock(&xprt->transport_lock);
		if (!xprt_test_and_set_connected(xprt)) {
			struct sock_xprt *transport = container_of(xprt,
					struct sock_xprt, xprt);

			/* Reset TCP record info */
			transport->tcp_offset = 0;
			transport->tcp_reclen = 0;
			transport->tcp_copied = 0;
			transport->tcp_flags =
				TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID;

			xprt_wake_pending_tasks(xprt, -EAGAIN);
		}
		spin_unlock(&xprt->transport_lock);
		break;
	case TCP_FIN_WAIT1:
		/* The client initiated a shutdown of the socket */
		xprt->connect_cookie++;
		xprt->reestablish_timeout = 0;
		set_bit(XPRT_CLOSING, &xprt->state);
		smp_mb__before_clear_bit();
		clear_bit(XPRT_CONNECTED, &xprt->state);
		clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
		smp_mb__after_clear_bit();
		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
		break;
	case TCP_CLOSE_WAIT:
		/* The server initiated a shutdown of the socket */
		xprt->connect_cookie++;
		clear_bit(XPRT_CONNECTED, &xprt->state);
		xs_tcp_force_close(xprt);
	case TCP_CLOSING:
		/*
		 * If the server closed down the connection, make sure that
		 * we back off before reconnecting
		 */
		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
		break;
	case TCP_LAST_ACK:
		set_bit(XPRT_CLOSING, &xprt->state);
		xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
		smp_mb__before_clear_bit();
		clear_bit(XPRT_CONNECTED, &xprt->state);
		smp_mb__after_clear_bit();
		break;
	case TCP_CLOSE:
		xs_tcp_cancel_linger_timeout(xprt);
		xs_sock_mark_closed(xprt);
	}
 out:
	read_unlock_bh(&sk->sk_callback_lock);
}

static void xs_write_space(struct sock *sk)
{
	struct socket *sock;
	struct rpc_xprt *xprt;

	if (unlikely(!(sock = sk->sk_socket)))
		return;
	clear_bit(SOCK_NOSPACE, &sock->flags);

	if (unlikely(!(xprt = xprt_from_sock(sk))))
		return;
	if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
		return;

	xprt_write_space(xprt);
}

/**
 * xs_udp_write_space - callback invoked when socket buffer space
 *                             becomes available
 * @sk: socket whose state has changed
 *
 * Called when more output buffer space is available for this socket.
 * We try not to wake our writers until they can make "significant"
 * progress, otherwise we'll waste resources thrashing kernel_sendmsg
 * with a bunch of small requests.
 */
static void xs_udp_write_space(struct sock *sk)
{
	read_lock_bh(&sk->sk_callback_lock);

	/* from net/core/sock.c:sock_def_write_space */
	if (sock_writeable(sk))
		xs_write_space(sk);

	read_unlock_bh(&sk->sk_callback_lock);
}

/**
 * xs_tcp_write_space - callback invoked when socket buffer space
 *                             becomes available
 * @sk: socket whose state has changed
 *
 * Called when more output buffer space is available for this socket.
 * We try not to wake our writers until they can make "significant"
 * progress, otherwise we'll waste resources thrashing kernel_sendmsg
 * with a bunch of small requests.
 */
static void xs_tcp_write_space(struct sock *sk)
{
	read_lock_bh(&sk->sk_callback_lock);

	/* from net/core/stream.c:sk_stream_write_space */
	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
		xs_write_space(sk);

	read_unlock_bh(&sk->sk_callback_lock);
}

static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	struct sock *sk = transport->inet;

	if (transport->rcvsize) {
		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
		sk->sk_rcvbuf = transport->rcvsize * xprt->max_reqs * 2;
	}
	if (transport->sndsize) {
		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
		sk->sk_sndbuf = transport->sndsize * xprt->max_reqs * 2;
		sk->sk_write_space(sk);
	}
}

/**
 * xs_udp_set_buffer_size - set send and receive limits
 * @xprt: generic transport
 * @sndsize: requested size of send buffer, in bytes
 * @rcvsize: requested size of receive buffer, in bytes
 *
 * Set socket send and receive buffer size limits.
 */
static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	transport->sndsize = 0;
	if (sndsize)
		transport->sndsize = sndsize + 1024;
	transport->rcvsize = 0;
	if (rcvsize)
		transport->rcvsize = rcvsize + 1024;

	xs_udp_do_set_buffer_size(xprt);
}

/**
 * xs_udp_timer - called when a retransmit timeout occurs on a UDP transport
 * @task: task that timed out
 *
 * Adjust the congestion window after a retransmit timeout has occurred.
 */
static void xs_udp_timer(struct rpc_xprt *xprt, struct rpc_task *task)
{
	xprt_adjust_cwnd(xprt, task, -ETIMEDOUT);
}

static unsigned short xs_get_random_port(void)
{
	unsigned short range = xprt_max_resvport - xprt_min_resvport;
	unsigned short rand = (unsigned short) net_random() % range;
	return rand + xprt_min_resvport;
}

/**
 * xs_set_port - reset the port number in the remote endpoint address
 * @xprt: generic transport
 * @port: new port number
 *
 */
static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
{
	dprintk("RPC:       setting port for xprt %p to %u\n", xprt, port);

	rpc_set_port(xs_addr(xprt), port);
	xs_update_peer_port(xprt);
}

static unsigned short xs_get_srcport(struct sock_xprt *transport)
{
	unsigned short port = transport->srcport;

	if (port == 0 && transport->xprt.resvport)
		port = xs_get_random_port();
	return port;
}

static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port)
{
	if (transport->srcport != 0)
		transport->srcport = 0;
	if (!transport->xprt.resvport)
		return 0;
	if (port <= xprt_min_resvport || port > xprt_max_resvport)
		return xprt_max_resvport;
	return --port;
}
static int xs_bind(struct sock_xprt *transport, struct socket *sock)
{
	struct sockaddr_storage myaddr;
	int err, nloop = 0;
	unsigned short port = xs_get_srcport(transport);
	unsigned short last;

	memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen);
	do {
		rpc_set_port((struct sockaddr *)&myaddr, port);
		err = kernel_bind(sock, (struct sockaddr *)&myaddr,
				transport->xprt.addrlen);
		if (port == 0)
			break;
		if (err == 0) {
			transport->srcport = port;
			break;
		}
		last = port;
		port = xs_next_srcport(transport, port);
		if (port > last)
			nloop++;
	} while (err == -EADDRINUSE && nloop != 2);

	if (myaddr.ss_family == AF_INET)
		dprintk("RPC:       %s %pI4:%u: %s (%d)\n", __func__,
				&((struct sockaddr_in *)&myaddr)->sin_addr,
				port, err ? "failed" : "ok", err);
	else
		dprintk("RPC:       %s %pI6:%u: %s (%d)\n", __func__,
				&((struct sockaddr_in6 *)&myaddr)->sin6_addr,
				port, err ? "failed" : "ok", err);
	return err;
}

/*
 * We don't support autobind on AF_LOCAL sockets
 */
static void xs_local_rpcbind(struct rpc_task *task)
{
	rcu_read_lock();
	xprt_set_bound(rcu_dereference(task->tk_client->cl_xprt));
	rcu_read_unlock();
}

static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port)
{
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key xs_key[2];
static struct lock_class_key xs_slock_key[2];

static inline void xs_reclassify_socketu(struct socket *sock)
{
	struct sock *sk = sock->sk;

	sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC",
		&xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]);
}

static inline void xs_reclassify_socket4(struct socket *sock)
{
	struct sock *sk = sock->sk;

	sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC",
		&xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]);
}

static inline void xs_reclassify_socket6(struct socket *sock)
{
	struct sock *sk = sock->sk;

	sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
		&xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
}

static inline void xs_reclassify_socket(int family, struct socket *sock)
{
	WARN_ON_ONCE(sock_owned_by_user(sock->sk));
	if (sock_owned_by_user(sock->sk))
		return;

	switch (family) {
	case AF_LOCAL:
		xs_reclassify_socketu(sock);
		break;
	case AF_INET:
		xs_reclassify_socket4(sock);
		break;
	case AF_INET6:
		xs_reclassify_socket6(sock);
		break;
	}
}
#else
static inline void xs_reclassify_socketu(struct socket *sock)
{
}

static inline void xs_reclassify_socket4(struct socket *sock)
{
}

static inline void xs_reclassify_socket6(struct socket *sock)
{
}

static inline void xs_reclassify_socket(int family, struct socket *sock)
{
}
#endif

static struct socket *xs_create_sock(struct rpc_xprt *xprt,
		struct sock_xprt *transport, int family, int type, int protocol)
{
	struct socket *sock;
	int err;

	err = __sock_create(xprt->xprt_net, family, type, protocol, &sock, 1);
	if (err < 0) {
		dprintk("RPC:       can't create %d transport socket (%d).\n",
				protocol, -err);
		goto out;
	}
	xs_reclassify_socket(family, sock);

	err = xs_bind(transport, sock);
	if (err) {
		sock_release(sock);
		goto out;
	}

	return sock;
out:
	return ERR_PTR(err);
}

static int xs_local_finish_connecting(struct rpc_xprt *xprt,
				      struct socket *sock)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
									xprt);

	if (!transport->inet) {
		struct sock *sk = sock->sk;

		write_lock_bh(&sk->sk_callback_lock);

		xs_save_old_callbacks(transport, sk);

		sk->sk_user_data = xprt;
		sk->sk_data_ready = xs_local_data_ready;
		sk->sk_write_space = xs_udp_write_space;
		sk->sk_allocation = GFP_ATOMIC;

		xprt_clear_connected(xprt);

		/* Reset to new socket */
		transport->sock = sock;
		transport->inet = sk;

		write_unlock_bh(&sk->sk_callback_lock);
	}

	/* Tell the socket layer to start connecting... */
	xprt->stat.connect_count++;
	xprt->stat.connect_start = jiffies;
	return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0);
}

/**
 * xs_local_setup_socket - create AF_LOCAL socket, connect to a local endpoint
 * @xprt: RPC transport to connect
 * @transport: socket transport to connect
 * @create_sock: function to create a socket of the correct type
 */
static int xs_local_setup_socket(struct sock_xprt *transport)
{
	struct rpc_xprt *xprt = &transport->xprt;
	struct socket *sock;
	int status = -EIO;

	current->flags |= PF_FSTRANS;

	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
	status = __sock_create(xprt->xprt_net, AF_LOCAL,
					SOCK_STREAM, 0, &sock, 1);
	if (status < 0) {
		dprintk("RPC:       can't create AF_LOCAL "
			"transport socket (%d).\n", -status);
		goto out;
	}
	xs_reclassify_socketu(sock);

	dprintk("RPC:       worker connecting xprt %p via AF_LOCAL to %s\n",
			xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);

	status = xs_local_finish_connecting(xprt, sock);
	switch (status) {
	case 0:
		dprintk("RPC:       xprt %p connected to %s\n",
				xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
		xprt_set_connected(xprt);
		break;
	case -ENOENT:
		dprintk("RPC:       xprt %p: socket %s does not exist\n",
				xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
		break;
	case -ECONNREFUSED:
		dprintk("RPC:       xprt %p: connection refused for %s\n",
				xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
		break;
	default:
		printk(KERN_ERR "%s: unhandled error (%d) connecting to %s\n",
				__func__, -status,
				xprt->address_strings[RPC_DISPLAY_ADDR]);
	}

out:
	xprt_clear_connecting(xprt);
	xprt_wake_pending_tasks(xprt, status);
	current->flags &= ~PF_FSTRANS;
	return status;
}

static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	int ret;

	 if (RPC_IS_ASYNC(task)) {
		/*
		 * We want the AF_LOCAL connect to be resolved in the
		 * filesystem namespace of the process making the rpc
		 * call.  Thus we connect synchronously.
		 *
		 * If we want to support asynchronous AF_LOCAL calls,
		 * we'll need to figure out how to pass a namespace to
		 * connect.
		 */
		rpc_exit(task, -ENOTCONN);
		return;
	}
	ret = xs_local_setup_socket(transport);
	if (ret && !RPC_IS_SOFTCONN(task))
		msleep_interruptible(15000);
}

#ifdef CONFIG_SUNRPC_SWAP
static void xs_set_memalloc(struct rpc_xprt *xprt)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
			xprt);

	if (xprt->swapper)
		sk_set_memalloc(transport->inet);
}

/**
 * xs_swapper - Tag this transport as being used for swap.
 * @xprt: transport to tag
 * @enable: enable/disable
 *
 */
int xs_swapper(struct rpc_xprt *xprt, int enable)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
			xprt);
	int err = 0;

	if (enable) {
		xprt->swapper++;
		xs_set_memalloc(xprt);
	} else if (xprt->swapper) {
		xprt->swapper--;
		sk_clear_memalloc(transport->inet);
	}

	return err;
}
EXPORT_SYMBOL_GPL(xs_swapper);
#else
static void xs_set_memalloc(struct rpc_xprt *xprt)
{
}
#endif

static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	if (!transport->inet) {
		struct sock *sk = sock->sk;

		write_lock_bh(&sk->sk_callback_lock);

		xs_save_old_callbacks(transport, sk);

		sk->sk_user_data = xprt;
		sk->sk_data_ready = xs_udp_data_ready;
		sk->sk_write_space = xs_udp_write_space;
		sk->sk_no_check = UDP_CSUM_NORCV;
		sk->sk_allocation = GFP_ATOMIC;

		xprt_set_connected(xprt);

		/* Reset to new socket */
		transport->sock = sock;
		transport->inet = sk;

		xs_set_memalloc(xprt);

		write_unlock_bh(&sk->sk_callback_lock);
	}
	xs_udp_do_set_buffer_size(xprt);
}

static void xs_udp_setup_socket(struct work_struct *work)
{
	struct sock_xprt *transport =
		container_of(work, struct sock_xprt, connect_worker.work);
	struct rpc_xprt *xprt = &transport->xprt;
	struct socket *sock = transport->sock;
	int status = -EIO;

	current->flags |= PF_FSTRANS;

	/* Start by resetting any existing state */
	xs_reset_transport(transport);
	sock = xs_create_sock(xprt, transport,
			xs_addr(xprt)->sa_family, SOCK_DGRAM, IPPROTO_UDP);
	if (IS_ERR(sock))
		goto out;

	dprintk("RPC:       worker connecting xprt %p via %s to "
				"%s (port %s)\n", xprt,
			xprt->address_strings[RPC_DISPLAY_PROTO],
			xprt->address_strings[RPC_DISPLAY_ADDR],
			xprt->address_strings[RPC_DISPLAY_PORT]);

	xs_udp_finish_connecting(xprt, sock);
	status = 0;
out:
	xprt_clear_connecting(xprt);
	xprt_wake_pending_tasks(xprt, status);
	current->flags &= ~PF_FSTRANS;
}

/*
 * We need to preserve the port number so the reply cache on the server can
 * find our cached RPC replies when we get around to reconnecting.
 */
static void xs_abort_connection(struct sock_xprt *transport)
{
	int result;
	struct sockaddr any;

	dprintk("RPC:       disconnecting xprt %p to reuse port\n", transport);

	/*
	 * Disconnect the transport socket by doing a connect operation
	 * with AF_UNSPEC.  This should return immediately...
	 */
	memset(&any, 0, sizeof(any));
	any.sa_family = AF_UNSPEC;
	result = kernel_connect(transport->sock, &any, sizeof(any), 0);
	if (!result)
		xs_sock_reset_connection_flags(&transport->xprt);
	dprintk("RPC:       AF_UNSPEC connect return code %d\n", result);
}

static void xs_tcp_reuse_connection(struct sock_xprt *transport)
{
	unsigned int state = transport->inet->sk_state;

	if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) {
		/* we don't need to abort the connection if the socket
		 * hasn't undergone a shutdown
		 */
		if (transport->inet->sk_shutdown == 0)
			return;
		dprintk("RPC:       %s: TCP_CLOSEd and sk_shutdown set to %d\n",
				__func__, transport->inet->sk_shutdown);
	}
	if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) {
		/* we don't need to abort the connection if the socket
		 * hasn't undergone a shutdown
		 */
		if (transport->inet->sk_shutdown == 0)
			return;
		dprintk("RPC:       %s: ESTABLISHED/SYN_SENT "
				"sk_shutdown set to %d\n",
				__func__, transport->inet->sk_shutdown);
	}
	xs_abort_connection(transport);
}

static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	int ret = -ENOTCONN;

	if (!transport->inet) {
		struct sock *sk = sock->sk;

		write_lock_bh(&sk->sk_callback_lock);

		xs_save_old_callbacks(transport, sk);

		sk->sk_user_data = xprt;
		sk->sk_data_ready = xs_tcp_data_ready;
		sk->sk_state_change = xs_tcp_state_change;
		sk->sk_write_space = xs_tcp_write_space;
		sk->sk_allocation = GFP_ATOMIC;

		/* socket options */
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
		sock_reset_flag(sk, SOCK_LINGER);
		tcp_sk(sk)->linger2 = 0;
		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;

		xprt_clear_connected(xprt);

		/* Reset to new socket */
		transport->sock = sock;
		transport->inet = sk;

		write_unlock_bh(&sk->sk_callback_lock);
	}

	if (!xprt_bound(xprt))
		goto out;

	xs_set_memalloc(xprt);

	/* Tell the socket layer to start connecting... */
	xprt->stat.connect_count++;
	xprt->stat.connect_start = jiffies;
	ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
	switch (ret) {
	case 0:
	case -EINPROGRESS:
		/* SYN_SENT! */
		xprt->connect_cookie++;
		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
	}
out:
	return ret;
}

/**
 * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint
 * @xprt: RPC transport to connect
 * @transport: socket transport to connect
 * @create_sock: function to create a socket of the correct type
 *
 * Invoked by a work queue tasklet.
 */
static void xs_tcp_setup_socket(struct work_struct *work)
{
	struct sock_xprt *transport =
		container_of(work, struct sock_xprt, connect_worker.work);
	struct socket *sock = transport->sock;
	struct rpc_xprt *xprt = &transport->xprt;
	int status = -EIO;

	current->flags |= PF_FSTRANS;

	if (!sock) {
		clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
		sock = xs_create_sock(xprt, transport,
				xs_addr(xprt)->sa_family, SOCK_STREAM, IPPROTO_TCP);
		if (IS_ERR(sock)) {
			status = PTR_ERR(sock);
			goto out;
		}
	} else {
		int abort_and_exit;

		abort_and_exit = test_and_clear_bit(XPRT_CONNECTION_ABORT,
				&xprt->state);
		/* "close" the socket, preserving the local port */
		xs_tcp_reuse_connection(transport);

		if (abort_and_exit)
			goto out_eagain;
	}

	dprintk("RPC:       worker connecting xprt %p via %s to "
				"%s (port %s)\n", xprt,
			xprt->address_strings[RPC_DISPLAY_PROTO],
			xprt->address_strings[RPC_DISPLAY_ADDR],
			xprt->address_strings[RPC_DISPLAY_PORT]);

	status = xs_tcp_finish_connecting(xprt, sock);
	dprintk("RPC:       %p connect status %d connected %d sock state %d\n",
			xprt, -status, xprt_connected(xprt),
			sock->sk->sk_state);
	switch (status) {
	default:
		printk("%s: connect returned unhandled error %d\n",
			__func__, status);
	case -EADDRNOTAVAIL:
		/* We're probably in TIME_WAIT. Get rid of existing socket,
		 * and retry
		 */
		xs_tcp_force_close(xprt);
		break;
	case 0:
	case -EINPROGRESS:
	case -EALREADY:
		xprt_clear_connecting(xprt);
		current->flags &= ~PF_FSTRANS;
		return;
	case -EINVAL:
		/* Happens, for instance, if the user specified a link
		 * local IPv6 address without a scope-id.
		 */
	case -ECONNREFUSED:
	case -ECONNRESET:
	case -ENETUNREACH:
		/* retry with existing socket, after a delay */
		goto out;
	}
out_eagain:
	status = -EAGAIN;
out:
	xprt_clear_connecting(xprt);
	xprt_wake_pending_tasks(xprt, status);
	current->flags &= ~PF_FSTRANS;
}

/**
 * xs_connect - connect a socket to a remote endpoint
 * @xprt: pointer to transport structure
 * @task: address of RPC task that manages state of connect request
 *
 * TCP: If the remote end dropped the connection, delay reconnecting.
 *
 * UDP socket connects are synchronous, but we use a work queue anyway
 * to guarantee that even unprivileged user processes can set up a
 * socket on a privileged port.
 *
 * If a UDP socket connect fails, the delay behavior here prevents
 * retry floods (hard mounts).
 */
static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	if (transport->sock != NULL && !RPC_IS_SOFTCONN(task)) {
		dprintk("RPC:       xs_connect delayed xprt %p for %lu "
				"seconds\n",
				xprt, xprt->reestablish_timeout / HZ);
		queue_delayed_work(rpciod_workqueue,
				   &transport->connect_worker,
				   xprt->reestablish_timeout);
		xprt->reestablish_timeout <<= 1;
		if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
			xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
		if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO)
			xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
	} else {
		dprintk("RPC:       xs_connect scheduled xprt %p\n", xprt);
		queue_delayed_work(rpciod_workqueue,
				   &transport->connect_worker, 0);
	}
}

/**
 * xs_local_print_stats - display AF_LOCAL socket-specifc stats
 * @xprt: rpc_xprt struct containing statistics
 * @seq: output file
 *
 */
static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
{
	long idle_time = 0;

	if (xprt_connected(xprt))
		idle_time = (long)(jiffies - xprt->last_used) / HZ;

	seq_printf(seq, "\txprt:\tlocal %lu %lu %lu %ld %lu %lu %lu "
			"%llu %llu %lu %llu %llu\n",
			xprt->stat.bind_count,
			xprt->stat.connect_count,
			xprt->stat.connect_time,
			idle_time,
			xprt->stat.sends,
			xprt->stat.recvs,
			xprt->stat.bad_xids,
			xprt->stat.req_u,
			xprt->stat.bklog_u,
			xprt->stat.max_slots,
			xprt->stat.sending_u,
			xprt->stat.pending_u);
}

/**
 * xs_udp_print_stats - display UDP socket-specifc stats
 * @xprt: rpc_xprt struct containing statistics
 * @seq: output file
 *
 */
static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);

	seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %llu %llu "
			"%lu %llu %llu\n",
			transport->srcport,
			xprt->stat.bind_count,
			xprt->stat.sends,
			xprt->stat.recvs,
			xprt->stat.bad_xids,
			xprt->stat.req_u,
			xprt->stat.bklog_u,
			xprt->stat.max_slots,
			xprt->stat.sending_u,
			xprt->stat.pending_u);
}

/**
 * xs_tcp_print_stats - display TCP socket-specifc stats
 * @xprt: rpc_xprt struct containing statistics
 * @seq: output file
 *
 */
static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
{
	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
	long idle_time = 0;

	if (xprt_connected(xprt))
		idle_time = (long)(jiffies - xprt->last_used) / HZ;

	seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu "
			"%llu %llu %lu %llu %llu\n",
			transport->srcport,
			xprt->stat.bind_count,
			xprt->stat.connect_count,
			xprt->stat.connect_time,
			idle_time,
			xprt->stat.sends,
			xprt->stat.recvs,
			xprt->stat.bad_xids,
			xprt->stat.req_u,
			xprt->stat.bklog_u,
			xprt->stat.max_slots,
			xprt->stat.sending_u,
			xprt->stat.pending_u);
}

/*
 * Allocate a bunch of pages for a scratch buffer for the rpc code. The reason
 * we allocate pages instead doing a kmalloc like rpc_malloc is because we want
 * to use the server side send routines.
 */
static void *bc_malloc(struct rpc_task *task, size_t size)
{
	struct page *page;
	struct rpc_buffer *buf;

	WARN_ON_ONCE(size > PAGE_SIZE - sizeof(struct rpc_buffer));
	if (size > PAGE_SIZE - sizeof(struct rpc_buffer))
		return NULL;

	page = alloc_page(GFP_KERNEL);
	if (!page)
		return NULL;

	buf = page_address(page);
	buf->len = PAGE_SIZE;

	return buf->data;
}

/*
 * Free the space allocated in the bc_alloc routine
 */
static void bc_free(void *buffer)
{
	struct rpc_buffer *buf;

	if (!buffer)
		return;

	buf = container_of(buffer, struct rpc_buffer, data);
	free_page((unsigned long)buf);
}

/*
 * Use the svc_sock to send the callback. Must be called with svsk->sk_mutex
 * held. Borrows heavily from svc_tcp_sendto and xs_tcp_send_request.
 */
static int bc_sendto(struct rpc_rqst *req)
{
	int len;
	struct xdr_buf *xbufp = &req->rq_snd_buf;
	struct rpc_xprt *xprt = req->rq_xprt;
	struct sock_xprt *transport =
				container_of(xprt, struct sock_xprt, xprt);
	struct socket *sock = transport->sock;
	unsigned long headoff;
	unsigned long tailoff;

	xs_encode_stream_record_marker(xbufp);

	tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
	headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
	len = svc_send_common(sock, xbufp,
			      virt_to_page(xbufp->head[0].iov_base), headoff,
			      xbufp->tail[0].iov_base, tailoff);

	if (len != xbufp->len) {
		printk(KERN_NOTICE "Error sending entire callback!\n");
		len = -EAGAIN;
	}

	return len;
}

/*
 * The send routine. Borrows from svc_send
 */
static int bc_send_request(struct rpc_task *task)
{
	struct rpc_rqst *req = task->tk_rqstp;
	struct svc_xprt	*xprt;
	u32                     len;

	dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
	/*
	 * Get the server socket associated with this callback xprt
	 */
	xprt = req->rq_xprt->bc_xprt;

	/*
	 * Grab the mutex to serialize data as the connection is shared
	 * with the fore channel
	 */
	if (!mutex_trylock(&xprt->xpt_mutex)) {
		rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL);
		if (!mutex_trylock(&xprt->xpt_mutex))
			return -EAGAIN;
		rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task);
	}
	if (test_bit(XPT_DEAD, &xprt->xpt_flags))
		len = -ENOTCONN;
	else
		len = bc_sendto(req);
	mutex_unlock(&xprt->xpt_mutex);

	if (len > 0)
		len = 0;

	return len;
}

/*
 * The close routine. Since this is client initiated, we do nothing
 */

static void bc_close(struct rpc_xprt *xprt)
{
}

/*
 * The xprt destroy routine. Again, because this connection is client
 * initiated, we do nothing
 */

static void bc_destroy(struct rpc_xprt *xprt)
{
}

static struct rpc_xprt_ops xs_local_ops = {
	.reserve_xprt		= xprt_reserve_xprt,
	.release_xprt		= xs_tcp_release_xprt,
	.alloc_slot		= xprt_alloc_slot,
	.rpcbind		= xs_local_rpcbind,
	.set_port		= xs_local_set_port,
	.connect		= xs_local_connect,
	.buf_alloc		= rpc_malloc,
	.buf_free		= rpc_free,
	.send_request		= xs_local_send_request,
	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
	.close			= xs_close,
	.destroy		= xs_local_destroy,
	.print_stats		= xs_local_print_stats,
};

static struct rpc_xprt_ops xs_udp_ops = {
	.set_buffer_size	= xs_udp_set_buffer_size,
	.reserve_xprt		= xprt_reserve_xprt_cong,
	.release_xprt		= xprt_release_xprt_cong,
	.alloc_slot		= xprt_alloc_slot,
	.rpcbind		= rpcb_getport_async,
	.set_port		= xs_set_port,
	.connect		= xs_connect,
	.buf_alloc		= rpc_malloc,
	.buf_free		= rpc_free,
	.send_request		= xs_udp_send_request,
	.set_retrans_timeout	= xprt_set_retrans_timeout_rtt,
	.timer			= xs_udp_timer,
	.release_request	= xprt_release_rqst_cong,
	.close			= xs_close,
	.destroy		= xs_destroy,
	.print_stats		= xs_udp_print_stats,
};

static struct rpc_xprt_ops xs_tcp_ops = {
	.reserve_xprt		= xprt_reserve_xprt,
	.release_xprt		= xs_tcp_release_xprt,
	.alloc_slot		= xprt_lock_and_alloc_slot,
	.rpcbind		= rpcb_getport_async,
	.set_port		= xs_set_port,
	.connect		= xs_connect,
	.buf_alloc		= rpc_malloc,
	.buf_free		= rpc_free,
	.send_request		= xs_tcp_send_request,
	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
	.close			= xs_tcp_close,
	.destroy		= xs_destroy,
	.print_stats		= xs_tcp_print_stats,
};

/*
 * The rpc_xprt_ops for the server backchannel
 */

static struct rpc_xprt_ops bc_tcp_ops = {
	.reserve_xprt		= xprt_reserve_xprt,
	.release_xprt		= xprt_release_xprt,
	.alloc_slot		= xprt_alloc_slot,
	.buf_alloc		= bc_malloc,
	.buf_free		= bc_free,
	.send_request		= bc_send_request,
	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
	.close			= bc_close,
	.destroy		= bc_destroy,
	.print_stats		= xs_tcp_print_stats,
};

static int xs_init_anyaddr(const int family, struct sockaddr *sap)
{
	static const struct sockaddr_in sin = {
		.sin_family		= AF_INET,
		.sin_addr.s_addr	= htonl(INADDR_ANY),
	};
	static const struct sockaddr_in6 sin6 = {
		.sin6_family		= AF_INET6,
		.sin6_addr		= IN6ADDR_ANY_INIT,
	};

	switch (family) {
	case AF_LOCAL:
		break;
	case AF_INET:
		memcpy(sap, &sin, sizeof(sin));
		break;
	case AF_INET6:
		memcpy(sap, &sin6, sizeof(sin6));
		break;
	default:
		dprintk("RPC:       %s: Bad address family\n", __func__);
		return -EAFNOSUPPORT;
	}
	return 0;
}

static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
				      unsigned int slot_table_size,
				      unsigned int max_slot_table_size)
{
	struct rpc_xprt *xprt;
	struct sock_xprt *new;

	if (args->addrlen > sizeof(xprt->addr)) {
		dprintk("RPC:       xs_setup_xprt: address too large\n");
		return ERR_PTR(-EBADF);
	}

	xprt = xprt_alloc(args->net, sizeof(*new), slot_table_size,
			max_slot_table_size);
	if (xprt == NULL) {
		dprintk("RPC:       xs_setup_xprt: couldn't allocate "
				"rpc_xprt\n");
		return ERR_PTR(-ENOMEM);
	}

	new = container_of(xprt, struct sock_xprt, xprt);
	memcpy(&xprt->addr, args->dstaddr, args->addrlen);
	xprt->addrlen = args->addrlen;
	if (args->srcaddr)
		memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
	else {
		int err;
		err = xs_init_anyaddr(args->dstaddr->sa_family,
					(struct sockaddr *)&new->srcaddr);
		if (err != 0) {
			xprt_free(xprt);
			return ERR_PTR(err);
		}
	}

	return xprt;
}

static const struct rpc_timeout xs_local_default_timeout = {
	.to_initval = 10 * HZ,
	.to_maxval = 10 * HZ,
	.to_retries = 2,
};

/**
 * xs_setup_local - Set up transport to use an AF_LOCAL socket
 * @args: rpc transport creation arguments
 *
 * AF_LOCAL is a "tpi_cots_ord" transport, just like TCP
 */
static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
{
	struct sockaddr_un *sun = (struct sockaddr_un *)args->dstaddr;
	struct sock_xprt *transport;
	struct rpc_xprt *xprt;
	struct rpc_xprt *ret;

	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
			xprt_max_tcp_slot_table_entries);
	if (IS_ERR(xprt))
		return xprt;
	transport = container_of(xprt, struct sock_xprt, xprt);

	xprt->prot = 0;
	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;

	xprt->bind_timeout = XS_BIND_TO;
	xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
	xprt->idle_timeout = XS_IDLE_DISC_TO;

	xprt->ops = &xs_local_ops;
	xprt->timeout = &xs_local_default_timeout;

	switch (sun->sun_family) {
	case AF_LOCAL:
		if (sun->sun_path[0] != '/') {
			dprintk("RPC:       bad AF_LOCAL address: %s\n",
					sun->sun_path);
			ret = ERR_PTR(-EINVAL);
			goto out_err;
		}
		xprt_set_bound(xprt);
		xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL);
		ret = ERR_PTR(xs_local_setup_socket(transport));
		if (ret)
			goto out_err;
		break;
	default:
		ret = ERR_PTR(-EAFNOSUPPORT);
		goto out_err;
	}

	dprintk("RPC:       set up xprt to %s via AF_LOCAL\n",
			xprt->address_strings[RPC_DISPLAY_ADDR]);

	if (try_module_get(THIS_MODULE))
		return xprt;
	ret = ERR_PTR(-EINVAL);
out_err:
	xprt_free(xprt);
	return ret;
}

static const struct rpc_timeout xs_udp_default_timeout = {
	.to_initval = 5 * HZ,
	.to_maxval = 30 * HZ,
	.to_increment = 5 * HZ,
	.to_retries = 5,
};

/**
 * xs_setup_udp - Set up transport to use a UDP socket
 * @args: rpc transport creation arguments
 *
 */
static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
{
	struct sockaddr *addr = args->dstaddr;
	struct rpc_xprt *xprt;
	struct sock_xprt *transport;
	struct rpc_xprt *ret;

	xprt = xs_setup_xprt(args, xprt_udp_slot_table_entries,
			xprt_udp_slot_table_entries);
	if (IS_ERR(xprt))
		return xprt;
	transport = container_of(xprt, struct sock_xprt, xprt);

	xprt->prot = IPPROTO_UDP;
	xprt->tsh_size = 0;
	/* XXX: header size can vary due to auth type, IPv6, etc. */
	xprt->max_payload = (1U << 16) - (MAX_HEADER << 3);

	xprt->bind_timeout = XS_BIND_TO;
	xprt->reestablish_timeout = XS_UDP_REEST_TO;
	xprt->idle_timeout = XS_IDLE_DISC_TO;

	xprt->ops = &xs_udp_ops;

	xprt->timeout = &xs_udp_default_timeout;

	switch (addr->sa_family) {
	case AF_INET:
		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
			xprt_set_bound(xprt);

		INIT_DELAYED_WORK(&transport->connect_worker,
					xs_udp_setup_socket);
		xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
		break;
	case AF_INET6:
		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
			xprt_set_bound(xprt);

		INIT_DELAYED_WORK(&transport->connect_worker,
					xs_udp_setup_socket);
		xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
		break;
	default:
		ret = ERR_PTR(-EAFNOSUPPORT);
		goto out_err;
	}

	if (xprt_bound(xprt))
		dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
				xprt->address_strings[RPC_DISPLAY_ADDR],
				xprt->address_strings[RPC_DISPLAY_PORT],
				xprt->address_strings[RPC_DISPLAY_PROTO]);
	else
		dprintk("RPC:       set up xprt to %s (autobind) via %s\n",
				xprt->address_strings[RPC_DISPLAY_ADDR],
				xprt->address_strings[RPC_DISPLAY_PROTO]);

	if (try_module_get(THIS_MODULE))
		return xprt;
	ret = ERR_PTR(-EINVAL);
out_err:
	xprt_free(xprt);
	return ret;
}

static const struct rpc_timeout xs_tcp_default_timeout = {
	.to_initval = 60 * HZ,
	.to_maxval = 60 * HZ,
	.to_retries = 2,
};

/**
 * xs_setup_tcp - Set up transport to use a TCP socket
 * @args: rpc transport creation arguments
 *
 */
static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
{
	struct sockaddr *addr = args->dstaddr;
	struct rpc_xprt *xprt;
	struct sock_xprt *transport;
	struct rpc_xprt *ret;
	unsigned int max_slot_table_size = xprt_max_tcp_slot_table_entries;

	if (args->flags & XPRT_CREATE_INFINITE_SLOTS)
		max_slot_table_size = RPC_MAX_SLOT_TABLE_LIMIT;

	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
			max_slot_table_size);
	if (IS_ERR(xprt))
		return xprt;
	transport = container_of(xprt, struct sock_xprt, xprt);

	xprt->prot = IPPROTO_TCP;
	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;

	xprt->bind_timeout = XS_BIND_TO;
	xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
	xprt->idle_timeout = XS_IDLE_DISC_TO;

	xprt->ops = &xs_tcp_ops;
	xprt->timeout = &xs_tcp_default_timeout;

	switch (addr->sa_family) {
	case AF_INET:
		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
			xprt_set_bound(xprt);

		INIT_DELAYED_WORK(&transport->connect_worker,
					xs_tcp_setup_socket);
		xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
		break;
	case AF_INET6:
		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
			xprt_set_bound(xprt);

		INIT_DELAYED_WORK(&transport->connect_worker,
					xs_tcp_setup_socket);
		xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
		break;
	default:
		ret = ERR_PTR(-EAFNOSUPPORT);
		goto out_err;
	}

	if (xprt_bound(xprt))
		dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
				xprt->address_strings[RPC_DISPLAY_ADDR],
				xprt->address_strings[RPC_DISPLAY_PORT],
				xprt->address_strings[RPC_DISPLAY_PROTO]);
	else
		dprintk("RPC:       set up xprt to %s (autobind) via %s\n",
				xprt->address_strings[RPC_DISPLAY_ADDR],
				xprt->address_strings[RPC_DISPLAY_PROTO]);


	if (try_module_get(THIS_MODULE))
		return xprt;
	ret = ERR_PTR(-EINVAL);
out_err:
	xprt_free(xprt);
	return ret;
}

/**
 * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket
 * @args: rpc transport creation arguments
 *
 */
static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
{
	struct sockaddr *addr = args->dstaddr;
	struct rpc_xprt *xprt;
	struct sock_xprt *transport;
	struct svc_sock *bc_sock;
	struct rpc_xprt *ret;

	if (args->bc_xprt->xpt_bc_xprt) {
		/*
		 * This server connection already has a backchannel
		 * export; we can't create a new one, as we wouldn't be
		 * able to match replies based on xid any more.  So,
		 * reuse the already-existing one:
		 */
		 return args->bc_xprt->xpt_bc_xprt;
	}
	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
			xprt_tcp_slot_table_entries);
	if (IS_ERR(xprt))
		return xprt;
	transport = container_of(xprt, struct sock_xprt, xprt);

	xprt->prot = IPPROTO_TCP;
	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
	xprt->timeout = &xs_tcp_default_timeout;

	/* backchannel */
	xprt_set_bound(xprt);
	xprt->bind_timeout = 0;
	xprt->reestablish_timeout = 0;
	xprt->idle_timeout = 0;

	xprt->ops = &bc_tcp_ops;

	switch (addr->sa_family) {
	case AF_INET:
		xs_format_peer_addresses(xprt, "tcp",
					 RPCBIND_NETID_TCP);
		break;
	case AF_INET6:
		xs_format_peer_addresses(xprt, "tcp",
				   RPCBIND_NETID_TCP6);
		break;
	default:
		ret = ERR_PTR(-EAFNOSUPPORT);
		goto out_err;
	}

	dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
			xprt->address_strings[RPC_DISPLAY_ADDR],
			xprt->address_strings[RPC_DISPLAY_PORT],
			xprt->address_strings[RPC_DISPLAY_PROTO]);

	/*
	 * Once we've associated a backchannel xprt with a connection,
	 * we want to keep it around as long as long as the connection
	 * lasts, in case we need to start using it for a backchannel
	 * again; this reference won't be dropped until bc_xprt is
	 * destroyed.
	 */
	xprt_get(xprt);
	args->bc_xprt->xpt_bc_xprt = xprt;
	xprt->bc_xprt = args->bc_xprt;
	bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt);
	transport->sock = bc_sock->sk_sock;
	transport->inet = bc_sock->sk_sk;

	/*
	 * Since we don't want connections for the backchannel, we set
	 * the xprt status to connected
	 */
	xprt_set_connected(xprt);


	if (try_module_get(THIS_MODULE))
		return xprt;
	xprt_put(xprt);
	ret = ERR_PTR(-EINVAL);
out_err:
	xprt_free(xprt);
	return ret;
}

static struct xprt_class	xs_local_transport = {
	.list		= LIST_HEAD_INIT(xs_local_transport.list),
	.name		= "named UNIX socket",
	.owner		= THIS_MODULE,
	.ident		= XPRT_TRANSPORT_LOCAL,
	.setup		= xs_setup_local,
};

static struct xprt_class	xs_udp_transport = {
	.list		= LIST_HEAD_INIT(xs_udp_transport.list),
	.name		= "udp",
	.owner		= THIS_MODULE,
	.ident		= XPRT_TRANSPORT_UDP,
	.setup		= xs_setup_udp,
};

static struct xprt_class	xs_tcp_transport = {
	.list		= LIST_HEAD_INIT(xs_tcp_transport.list),
	.name		= "tcp",
	.owner		= THIS_MODULE,
	.ident		= XPRT_TRANSPORT_TCP,
	.setup		= xs_setup_tcp,
};

static struct xprt_class	xs_bc_tcp_transport = {
	.list		= LIST_HEAD_INIT(xs_bc_tcp_transport.list),
	.name		= "tcp NFSv4.1 backchannel",
	.owner		= THIS_MODULE,
	.ident		= XPRT_TRANSPORT_BC_TCP,
	.setup		= xs_setup_bc_tcp,
};

/**
 * init_socket_xprt - set up xprtsock's sysctls, register with RPC client
 *
 */
int init_socket_xprt(void)
{
#ifdef RPC_DEBUG
	if (!sunrpc_table_header)
		sunrpc_table_header = register_sysctl_table(sunrpc_table);
#endif

	xprt_register_transport(&xs_local_transport);
	xprt_register_transport(&xs_udp_transport);
	xprt_register_transport(&xs_tcp_transport);
	xprt_register_transport(&xs_bc_tcp_transport);

	return 0;
}

/**
 * cleanup_socket_xprt - remove xprtsock's sysctls, unregister
 *
 */
void cleanup_socket_xprt(void)
{
#ifdef RPC_DEBUG
	if (sunrpc_table_header) {
		unregister_sysctl_table(sunrpc_table_header);
		sunrpc_table_header = NULL;
	}
#endif

	xprt_unregister_transport(&xs_local_transport);
	xprt_unregister_transport(&xs_udp_transport);
	xprt_unregister_transport(&xs_tcp_transport);
	xprt_unregister_transport(&xs_bc_tcp_transport);
}

static int param_set_uint_minmax(const char *val,
		const struct kernel_param *kp,
		unsigned int min, unsigned int max)
{
	unsigned long num;
	int ret;

	if (!val)
		return -EINVAL;
	ret = strict_strtoul(val, 0, &num);
	if (ret == -EINVAL || num < min || num > max)
		return -EINVAL;
	*((unsigned int *)kp->arg) = num;
	return 0;
}

static int param_set_portnr(const char *val, const struct kernel_param *kp)
{
	return param_set_uint_minmax(val, kp,
			RPC_MIN_RESVPORT,
			RPC_MAX_RESVPORT);
}

static struct kernel_param_ops param_ops_portnr = {
	.set = param_set_portnr,
	.get = param_get_uint,
};

#define param_check_portnr(name, p) \
	__param_check(name, p, unsigned int);

module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);

static int param_set_slot_table_size(const char *val,
				     const struct kernel_param *kp)
{
	return param_set_uint_minmax(val, kp,
			RPC_MIN_SLOT_TABLE,
			RPC_MAX_SLOT_TABLE);
}

static struct kernel_param_ops param_ops_slot_table_size = {
	.set = param_set_slot_table_size,
	.get = param_get_uint,
};

#define param_check_slot_table_size(name, p) \
	__param_check(name, p, unsigned int);

static int param_set_max_slot_table_size(const char *val,
				     const struct kernel_param *kp)
{
	return param_set_uint_minmax(val, kp,
			RPC_MIN_SLOT_TABLE,
			RPC_MAX_SLOT_TABLE_LIMIT);
}

static struct kernel_param_ops param_ops_max_slot_table_size = {
	.set = param_set_max_slot_table_size,
	.get = param_get_uint,
};

#define param_check_max_slot_table_size(name, p) \
	__param_check(name, p, unsigned int);

module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries,
		   slot_table_size, 0644);
module_param_named(tcp_max_slot_table_entries, xprt_max_tcp_slot_table_entries,
		   max_slot_table_size, 0644);
module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries,
		   slot_table_size, 0644);