summaryrefslogtreecommitdiff
path: root/net/sunrpc/svcsock.c
blob: ff1f8bf680aab43e741249912409b09013ba6fad (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
/*
 * linux/net/sunrpc/svcsock.c
 *
 * These are the RPC server socket internals.
 *
 * The server scheduling algorithm does not always distribute the load
 * evenly when servicing a single client. May need to modify the
 * svc_sock_enqueue procedure...
 *
 * TCP support is largely untested and may be a little slow. The problem
 * is that we currently do two separate recvfrom's, one for the 4-byte
 * record length, and the second for the actual record. This could possibly
 * be improved by always reading a minimum size of around 100 bytes and
 * tucking any superfluous bytes away in a temporary store. Still, that
 * leaves write requests out in the rain. An alternative may be to peek at
 * the first skb in the queue, and if it matches the next TCP sequence
 * number, to extract the record marker. Yuck.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/file.h>
#include <linux/freezer.h>
#include <net/sock.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>

#include <linux/sunrpc/types.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/stats.h>

/* SMP locking strategy:
 *
 *	svc_pool->sp_lock protects most of the fields of that pool.
 * 	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
 *	when both need to be taken (rare), svc_serv->sv_lock is first.
 *	BKL protects svc_serv->sv_nrthread.
 *	svc_sock->sk_defer_lock protects the svc_sock->sk_deferred list
 *	svc_sock->sk_flags.SK_BUSY prevents a svc_sock being enqueued multiply.
 *
 *	Some flags can be set to certain values at any time
 *	providing that certain rules are followed:
 *
 *	SK_CONN, SK_DATA, can be set or cleared at any time.
 *		after a set, svc_sock_enqueue must be called.	
 *		after a clear, the socket must be read/accepted
 *		 if this succeeds, it must be set again.
 *	SK_CLOSE can set at any time. It is never cleared.
 *
 */

#define RPCDBG_FACILITY	RPCDBG_SVCSOCK


static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
					 int *errp, int pmap_reg);
static void		svc_udp_data_ready(struct sock *, int);
static int		svc_udp_recvfrom(struct svc_rqst *);
static int		svc_udp_sendto(struct svc_rqst *);

static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);

/* apparently the "standard" is that clients close
 * idle connections after 5 minutes, servers after
 * 6 minutes
 *   http://www.connectathon.org/talks96/nfstcp.pdf
 */
static int svc_conn_age_period = 6*60;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key svc_key[2];
static struct lock_class_key svc_slock_key[2];

static inline void svc_reclassify_socket(struct socket *sock)
{
	struct sock *sk = sock->sk;
	BUG_ON(sk->sk_lock.owner != NULL);
	switch (sk->sk_family) {
	case AF_INET:
		sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
		    &svc_slock_key[0], "sk_lock-AF_INET-NFSD", &svc_key[0]);
		break;

	case AF_INET6:
		sock_lock_init_class_and_name(sk, "slock-AF_INET6-NFSD",
		    &svc_slock_key[1], "sk_lock-AF_INET6-NFSD", &svc_key[1]);
		break;

	default:
		BUG();
	}
}
#else
static inline void svc_reclassify_socket(struct socket *sock)
{
}
#endif

/*
 * Queue up an idle server thread.  Must have pool->sp_lock held.
 * Note: this is really a stack rather than a queue, so that we only
 * use as many different threads as we need, and the rest don't pollute
 * the cache.
 */
static inline void
svc_thread_enqueue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
	list_add(&rqstp->rq_list, &pool->sp_threads);
}

/*
 * Dequeue an nfsd thread.  Must have pool->sp_lock held.
 */
static inline void
svc_thread_dequeue(struct svc_pool *pool, struct svc_rqst *rqstp)
{
	list_del(&rqstp->rq_list);
}

/*
 * Release an skbuff after use
 */
static inline void
svc_release_skb(struct svc_rqst *rqstp)
{
	struct sk_buff *skb = rqstp->rq_skbuff;
	struct svc_deferred_req *dr = rqstp->rq_deferred;

	if (skb) {
		rqstp->rq_skbuff = NULL;

		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
		skb_free_datagram(rqstp->rq_sock->sk_sk, skb);
	}
	if (dr) {
		rqstp->rq_deferred = NULL;
		kfree(dr);
	}
}

/*
 * Any space to write?
 */
static inline unsigned long
svc_sock_wspace(struct svc_sock *svsk)
{
	int wspace;

	if (svsk->sk_sock->type == SOCK_STREAM)
		wspace = sk_stream_wspace(svsk->sk_sk);
	else
		wspace = sock_wspace(svsk->sk_sk);

	return wspace;
}

/*
 * Queue up a socket with data pending. If there are idle nfsd
 * processes, wake 'em up.
 *
 */
static void
svc_sock_enqueue(struct svc_sock *svsk)
{
	struct svc_serv	*serv = svsk->sk_server;
	struct svc_pool *pool;
	struct svc_rqst	*rqstp;
	int cpu;

	if (!(svsk->sk_flags &
	      ( (1<<SK_CONN)|(1<<SK_DATA)|(1<<SK_CLOSE)|(1<<SK_DEFERRED)) ))
		return;
	if (test_bit(SK_DEAD, &svsk->sk_flags))
		return;

	cpu = get_cpu();
	pool = svc_pool_for_cpu(svsk->sk_server, cpu);
	put_cpu();

	spin_lock_bh(&pool->sp_lock);

	if (!list_empty(&pool->sp_threads) &&
	    !list_empty(&pool->sp_sockets))
		printk(KERN_ERR
			"svc_sock_enqueue: threads and sockets both waiting??\n");

	if (test_bit(SK_DEAD, &svsk->sk_flags)) {
		/* Don't enqueue dead sockets */
		dprintk("svc: socket %p is dead, not enqueued\n", svsk->sk_sk);
		goto out_unlock;
	}

	/* Mark socket as busy. It will remain in this state until the
	 * server has processed all pending data and put the socket back
	 * on the idle list.  We update SK_BUSY atomically because
	 * it also guards against trying to enqueue the svc_sock twice.
	 */
	if (test_and_set_bit(SK_BUSY, &svsk->sk_flags)) {
		/* Don't enqueue socket while already enqueued */
		dprintk("svc: socket %p busy, not enqueued\n", svsk->sk_sk);
		goto out_unlock;
	}
	BUG_ON(svsk->sk_pool != NULL);
	svsk->sk_pool = pool;

	set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
	if (((atomic_read(&svsk->sk_reserved) + serv->sv_max_mesg)*2
	     > svc_sock_wspace(svsk))
	    && !test_bit(SK_CLOSE, &svsk->sk_flags)
	    && !test_bit(SK_CONN, &svsk->sk_flags)) {
		/* Don't enqueue while not enough space for reply */
		dprintk("svc: socket %p  no space, %d*2 > %ld, not enqueued\n",
			svsk->sk_sk, atomic_read(&svsk->sk_reserved)+serv->sv_max_mesg,
			svc_sock_wspace(svsk));
		svsk->sk_pool = NULL;
		clear_bit(SK_BUSY, &svsk->sk_flags);
		goto out_unlock;
	}
	clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);


	if (!list_empty(&pool->sp_threads)) {
		rqstp = list_entry(pool->sp_threads.next,
				   struct svc_rqst,
				   rq_list);
		dprintk("svc: socket %p served by daemon %p\n",
			svsk->sk_sk, rqstp);
		svc_thread_dequeue(pool, rqstp);
		if (rqstp->rq_sock)
			printk(KERN_ERR 
				"svc_sock_enqueue: server %p, rq_sock=%p!\n",
				rqstp, rqstp->rq_sock);
		rqstp->rq_sock = svsk;
		atomic_inc(&svsk->sk_inuse);
		rqstp->rq_reserved = serv->sv_max_mesg;
		atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
		BUG_ON(svsk->sk_pool != pool);
		wake_up(&rqstp->rq_wait);
	} else {
		dprintk("svc: socket %p put into queue\n", svsk->sk_sk);
		list_add_tail(&svsk->sk_ready, &pool->sp_sockets);
		BUG_ON(svsk->sk_pool != pool);
	}

out_unlock:
	spin_unlock_bh(&pool->sp_lock);
}

/*
 * Dequeue the first socket.  Must be called with the pool->sp_lock held.
 */
static inline struct svc_sock *
svc_sock_dequeue(struct svc_pool *pool)
{
	struct svc_sock	*svsk;

	if (list_empty(&pool->sp_sockets))
		return NULL;

	svsk = list_entry(pool->sp_sockets.next,
			  struct svc_sock, sk_ready);
	list_del_init(&svsk->sk_ready);

	dprintk("svc: socket %p dequeued, inuse=%d\n",
		svsk->sk_sk, atomic_read(&svsk->sk_inuse));

	return svsk;
}

/*
 * Having read something from a socket, check whether it
 * needs to be re-enqueued.
 * Note: SK_DATA only gets cleared when a read-attempt finds
 * no (or insufficient) data.
 */
static inline void
svc_sock_received(struct svc_sock *svsk)
{
	svsk->sk_pool = NULL;
	clear_bit(SK_BUSY, &svsk->sk_flags);
	svc_sock_enqueue(svsk);
}


/**
 * svc_reserve - change the space reserved for the reply to a request.
 * @rqstp:  The request in question
 * @space: new max space to reserve
 *
 * Each request reserves some space on the output queue of the socket
 * to make sure the reply fits.  This function reduces that reserved
 * space to be the amount of space used already, plus @space.
 *
 */
void svc_reserve(struct svc_rqst *rqstp, int space)
{
	space += rqstp->rq_res.head[0].iov_len;

	if (space < rqstp->rq_reserved) {
		struct svc_sock *svsk = rqstp->rq_sock;
		atomic_sub((rqstp->rq_reserved - space), &svsk->sk_reserved);
		rqstp->rq_reserved = space;

		svc_sock_enqueue(svsk);
	}
}

/*
 * Release a socket after use.
 */
static inline void
svc_sock_put(struct svc_sock *svsk)
{
	if (atomic_dec_and_test(&svsk->sk_inuse) &&
			test_bit(SK_DEAD, &svsk->sk_flags)) {
		dprintk("svc: releasing dead socket\n");
		if (svsk->sk_sock->file)
			sockfd_put(svsk->sk_sock);
		else
			sock_release(svsk->sk_sock);
		if (svsk->sk_info_authunix != NULL)
			svcauth_unix_info_release(svsk->sk_info_authunix);
		kfree(svsk);
	}
}

static void
svc_sock_release(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk = rqstp->rq_sock;

	svc_release_skb(rqstp);

	svc_free_res_pages(rqstp);
	rqstp->rq_res.page_len = 0;
	rqstp->rq_res.page_base = 0;


	/* Reset response buffer and release
	 * the reservation.
	 * But first, check that enough space was reserved
	 * for the reply, otherwise we have a bug!
	 */
	if ((rqstp->rq_res.len) >  rqstp->rq_reserved)
		printk(KERN_ERR "RPC request reserved %d but used %d\n",
		       rqstp->rq_reserved,
		       rqstp->rq_res.len);

	rqstp->rq_res.head[0].iov_len = 0;
	svc_reserve(rqstp, 0);
	rqstp->rq_sock = NULL;

	svc_sock_put(svsk);
}

/*
 * External function to wake up a server waiting for data
 * This really only makes sense for services like lockd
 * which have exactly one thread anyway.
 */
void
svc_wake_up(struct svc_serv *serv)
{
	struct svc_rqst	*rqstp;
	unsigned int i;
	struct svc_pool *pool;

	for (i = 0; i < serv->sv_nrpools; i++) {
		pool = &serv->sv_pools[i];

		spin_lock_bh(&pool->sp_lock);
		if (!list_empty(&pool->sp_threads)) {
			rqstp = list_entry(pool->sp_threads.next,
					   struct svc_rqst,
					   rq_list);
			dprintk("svc: daemon %p woken up.\n", rqstp);
			/*
			svc_thread_dequeue(pool, rqstp);
			rqstp->rq_sock = NULL;
			 */
			wake_up(&rqstp->rq_wait);
		}
		spin_unlock_bh(&pool->sp_lock);
	}
}

/*
 * Generic sendto routine
 */
static int
svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
{
	struct svc_sock	*svsk = rqstp->rq_sock;
	struct socket	*sock = svsk->sk_sock;
	int		slen;
	char 		buffer[CMSG_SPACE(sizeof(struct in_pktinfo))];
	struct cmsghdr *cmh = (struct cmsghdr *)buffer;
	struct in_pktinfo *pki = (struct in_pktinfo *)CMSG_DATA(cmh);
	int		len = 0;
	int		result;
	int		size;
	struct page	**ppage = xdr->pages;
	size_t		base = xdr->page_base;
	unsigned int	pglen = xdr->page_len;
	unsigned int	flags = MSG_MORE;

	slen = xdr->len;

	if (rqstp->rq_prot == IPPROTO_UDP) {
		/* set the source and destination */
		struct msghdr	msg;
		msg.msg_name    = &rqstp->rq_addr;
		msg.msg_namelen = sizeof(rqstp->rq_addr);
		msg.msg_iov     = NULL;
		msg.msg_iovlen  = 0;
		msg.msg_flags	= MSG_MORE;

		msg.msg_control = cmh;
		msg.msg_controllen = sizeof(buffer);
		cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
		cmh->cmsg_level = SOL_IP;
		cmh->cmsg_type = IP_PKTINFO;
		pki->ipi_ifindex = 0;
		pki->ipi_spec_dst.s_addr = rqstp->rq_daddr;

		if (sock_sendmsg(sock, &msg, 0) < 0)
			goto out;
	}

	/* send head */
	if (slen == xdr->head[0].iov_len)
		flags = 0;
	len = kernel_sendpage(sock, rqstp->rq_respages[0], 0,
				  xdr->head[0].iov_len, flags);
	if (len != xdr->head[0].iov_len)
		goto out;
	slen -= xdr->head[0].iov_len;
	if (slen == 0)
		goto out;

	/* send page data */
	size = PAGE_SIZE - base < pglen ? PAGE_SIZE - base : pglen;
	while (pglen > 0) {
		if (slen == size)
			flags = 0;
		result = kernel_sendpage(sock, *ppage, base, size, flags);
		if (result > 0)
			len += result;
		if (result != size)
			goto out;
		slen -= size;
		pglen -= size;
		size = PAGE_SIZE < pglen ? PAGE_SIZE : pglen;
		base = 0;
		ppage++;
	}
	/* send tail */
	if (xdr->tail[0].iov_len) {
		result = kernel_sendpage(sock, rqstp->rq_respages[0],
					     ((unsigned long)xdr->tail[0].iov_base)
					        & (PAGE_SIZE-1),
					     xdr->tail[0].iov_len, 0);

		if (result > 0)
			len += result;
	}
out:
	dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %x)\n",
			rqstp->rq_sock, xdr->head[0].iov_base, xdr->head[0].iov_len, xdr->len, len,
		rqstp->rq_addr.sin_addr.s_addr);

	return len;
}

/*
 * Report socket names for nfsdfs
 */
static int one_sock_name(char *buf, struct svc_sock *svsk)
{
	int len;

	switch(svsk->sk_sk->sk_family) {
	case AF_INET:
		len = sprintf(buf, "ipv4 %s %u.%u.%u.%u %d\n",
			      svsk->sk_sk->sk_protocol==IPPROTO_UDP?
			      "udp" : "tcp",
			      NIPQUAD(inet_sk(svsk->sk_sk)->rcv_saddr),
			      inet_sk(svsk->sk_sk)->num);
		break;
	default:
		len = sprintf(buf, "*unknown-%d*\n",
			       svsk->sk_sk->sk_family);
	}
	return len;
}

int
svc_sock_names(char *buf, struct svc_serv *serv, char *toclose)
{
	struct svc_sock *svsk, *closesk = NULL;
	int len = 0;

	if (!serv)
		return 0;
	spin_lock(&serv->sv_lock);
	list_for_each_entry(svsk, &serv->sv_permsocks, sk_list) {
		int onelen = one_sock_name(buf+len, svsk);
		if (toclose && strcmp(toclose, buf+len) == 0)
			closesk = svsk;
		else
			len += onelen;
	}
	spin_unlock(&serv->sv_lock);
	if (closesk)
		/* Should unregister with portmap, but you cannot
		 * unregister just one protocol...
		 */
		svc_delete_socket(closesk);
	else if (toclose)
		return -ENOENT;
	return len;
}
EXPORT_SYMBOL(svc_sock_names);

/*
 * Check input queue length
 */
static int
svc_recv_available(struct svc_sock *svsk)
{
	struct socket	*sock = svsk->sk_sock;
	int		avail, err;

	err = kernel_sock_ioctl(sock, TIOCINQ, (unsigned long) &avail);

	return (err >= 0)? avail : err;
}

/*
 * Generic recvfrom routine.
 */
static int
svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, int buflen)
{
	struct msghdr	msg;
	struct socket	*sock;
	int		len, alen;

	rqstp->rq_addrlen = sizeof(rqstp->rq_addr);
	sock = rqstp->rq_sock->sk_sock;

	msg.msg_name    = &rqstp->rq_addr;
	msg.msg_namelen = sizeof(rqstp->rq_addr);
	msg.msg_control = NULL;
	msg.msg_controllen = 0;

	msg.msg_flags	= MSG_DONTWAIT;

	len = kernel_recvmsg(sock, &msg, iov, nr, buflen, MSG_DONTWAIT);

	/* sock_recvmsg doesn't fill in the name/namelen, so we must..
	 * possibly we should cache this in the svc_sock structure
	 * at accept time. FIXME
	 */
	alen = sizeof(rqstp->rq_addr);
	kernel_getpeername(sock, (struct sockaddr *)&rqstp->rq_addr, &alen);

	dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
		rqstp->rq_sock, iov[0].iov_base, iov[0].iov_len, len);

	return len;
}

/*
 * Set socket snd and rcv buffer lengths
 */
static inline void
svc_sock_setbufsize(struct socket *sock, unsigned int snd, unsigned int rcv)
{
#if 0
	mm_segment_t	oldfs;
	oldfs = get_fs(); set_fs(KERNEL_DS);
	sock_setsockopt(sock, SOL_SOCKET, SO_SNDBUF,
			(char*)&snd, sizeof(snd));
	sock_setsockopt(sock, SOL_SOCKET, SO_RCVBUF,
			(char*)&rcv, sizeof(rcv));
#else
	/* sock_setsockopt limits use to sysctl_?mem_max,
	 * which isn't acceptable.  Until that is made conditional
	 * on not having CAP_SYS_RESOURCE or similar, we go direct...
	 * DaveM said I could!
	 */
	lock_sock(sock->sk);
	sock->sk->sk_sndbuf = snd * 2;
	sock->sk->sk_rcvbuf = rcv * 2;
	sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
	release_sock(sock->sk);
#endif
}
/*
 * INET callback when data has been received on the socket.
 */
static void
svc_udp_data_ready(struct sock *sk, int count)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	if (svsk) {
		dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
			svsk, sk, count, test_bit(SK_BUSY, &svsk->sk_flags));
		set_bit(SK_DATA, &svsk->sk_flags);
		svc_sock_enqueue(svsk);
	}
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
}

/*
 * INET callback when space is newly available on the socket.
 */
static void
svc_write_space(struct sock *sk)
{
	struct svc_sock	*svsk = (struct svc_sock *)(sk->sk_user_data);

	if (svsk) {
		dprintk("svc: socket %p(inet %p), write_space busy=%d\n",
			svsk, sk, test_bit(SK_BUSY, &svsk->sk_flags));
		svc_sock_enqueue(svsk);
	}

	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) {
		dprintk("RPC svc_write_space: someone sleeping on %p\n",
		       svsk);
		wake_up_interruptible(sk->sk_sleep);
	}
}

/*
 * Receive a datagram from a UDP socket.
 */
static int
svc_udp_recvfrom(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk = rqstp->rq_sock;
	struct svc_serv	*serv = svsk->sk_server;
	struct sk_buff	*skb;
	int		err, len;

	if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
	    /* udp sockets need large rcvbuf as all pending
	     * requests are still in that buffer.  sndbuf must
	     * also be large enough that there is enough space
	     * for one reply per thread.  We count all threads
	     * rather than threads in a particular pool, which
	     * provides an upper bound on the number of threads
	     * which will access the socket.
	     */
	    svc_sock_setbufsize(svsk->sk_sock,
				(serv->sv_nrthreads+3) * serv->sv_max_mesg,
				(serv->sv_nrthreads+3) * serv->sv_max_mesg);

	if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
		svc_sock_received(svsk);
		return svc_deferred_recv(rqstp);
	}

	clear_bit(SK_DATA, &svsk->sk_flags);
	while ((skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err)) == NULL) {
		if (err == -EAGAIN) {
			svc_sock_received(svsk);
			return err;
		}
		/* possibly an icmp error */
		dprintk("svc: recvfrom returned error %d\n", -err);
	}
	if (skb->tstamp.off_sec == 0) {
		struct timeval tv;

		tv.tv_sec = xtime.tv_sec;
		tv.tv_usec = xtime.tv_nsec / NSEC_PER_USEC;
		skb_set_timestamp(skb, &tv);
		/* Don't enable netstamp, sunrpc doesn't 
		   need that much accuracy */
	}
	skb_get_timestamp(skb, &svsk->sk_sk->sk_stamp);
	set_bit(SK_DATA, &svsk->sk_flags); /* there may be more data... */

	/*
	 * Maybe more packets - kick another thread ASAP.
	 */
	svc_sock_received(svsk);

	len  = skb->len - sizeof(struct udphdr);
	rqstp->rq_arg.len = len;

	rqstp->rq_prot        = IPPROTO_UDP;

	/* Get sender address */
	rqstp->rq_addr.sin_family = AF_INET;
	rqstp->rq_addr.sin_port = skb->h.uh->source;
	rqstp->rq_addr.sin_addr.s_addr = skb->nh.iph->saddr;
	rqstp->rq_daddr = skb->nh.iph->daddr;

	if (skb_is_nonlinear(skb)) {
		/* we have to copy */
		local_bh_disable();
		if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) {
			local_bh_enable();
			/* checksum error */
			skb_free_datagram(svsk->sk_sk, skb);
			return 0;
		}
		local_bh_enable();
		skb_free_datagram(svsk->sk_sk, skb); 
	} else {
		/* we can use it in-place */
		rqstp->rq_arg.head[0].iov_base = skb->data + sizeof(struct udphdr);
		rqstp->rq_arg.head[0].iov_len = len;
		if (skb_checksum_complete(skb)) {
			skb_free_datagram(svsk->sk_sk, skb);
			return 0;
		}
		rqstp->rq_skbuff = skb;
	}

	rqstp->rq_arg.page_base = 0;
	if (len <= rqstp->rq_arg.head[0].iov_len) {
		rqstp->rq_arg.head[0].iov_len = len;
		rqstp->rq_arg.page_len = 0;
		rqstp->rq_respages = rqstp->rq_pages+1;
	} else {
		rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
		rqstp->rq_respages = rqstp->rq_pages + 1 +
			(rqstp->rq_arg.page_len + PAGE_SIZE - 1)/ PAGE_SIZE;
	}

	if (serv->sv_stats)
		serv->sv_stats->netudpcnt++;

	return len;
}

static int
svc_udp_sendto(struct svc_rqst *rqstp)
{
	int		error;

	error = svc_sendto(rqstp, &rqstp->rq_res);
	if (error == -ECONNREFUSED)
		/* ICMP error on earlier request. */
		error = svc_sendto(rqstp, &rqstp->rq_res);

	return error;
}

static void
svc_udp_init(struct svc_sock *svsk)
{
	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
	svsk->sk_sk->sk_write_space = svc_write_space;
	svsk->sk_recvfrom = svc_udp_recvfrom;
	svsk->sk_sendto = svc_udp_sendto;

	/* initialise setting must have enough space to
	 * receive and respond to one request.  
	 * svc_udp_recvfrom will re-adjust if necessary
	 */
	svc_sock_setbufsize(svsk->sk_sock,
			    3 * svsk->sk_server->sv_max_mesg,
			    3 * svsk->sk_server->sv_max_mesg);

	set_bit(SK_DATA, &svsk->sk_flags); /* might have come in before data_ready set up */
	set_bit(SK_CHNGBUF, &svsk->sk_flags);
}

/*
 * A data_ready event on a listening socket means there's a connection
 * pending. Do not use state_change as a substitute for it.
 */
static void
svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	dprintk("svc: socket %p TCP (listen) state change %d\n",
		sk, sk->sk_state);

	/*
	 * This callback may called twice when a new connection
	 * is established as a child socket inherits everything
	 * from a parent LISTEN socket.
	 * 1) data_ready method of the parent socket will be called
	 *    when one of child sockets become ESTABLISHED.
	 * 2) data_ready method of the child socket may be called
	 *    when it receives data before the socket is accepted.
	 * In case of 2, we should ignore it silently.
	 */
	if (sk->sk_state == TCP_LISTEN) {
		if (svsk) {
			set_bit(SK_CONN, &svsk->sk_flags);
			svc_sock_enqueue(svsk);
		} else
			printk("svc: socket %p: no user data\n", sk);
	}

	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
}

/*
 * A state change on a connected socket means it's dying or dead.
 */
static void
svc_tcp_state_change(struct sock *sk)
{
	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;

	dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n",
		sk, sk->sk_state, sk->sk_user_data);

	if (!svsk)
		printk("svc: socket %p: no user data\n", sk);
	else {
		set_bit(SK_CLOSE, &svsk->sk_flags);
		svc_sock_enqueue(svsk);
	}
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
}

static void
svc_tcp_data_ready(struct sock *sk, int count)
{
	struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;

	dprintk("svc: socket %p TCP data ready (svsk %p)\n",
		sk, sk->sk_user_data);
	if (svsk) {
		set_bit(SK_DATA, &svsk->sk_flags);
		svc_sock_enqueue(svsk);
	}
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
}

/*
 * Accept a TCP connection
 */
static void
svc_tcp_accept(struct svc_sock *svsk)
{
	struct sockaddr_in sin;
	struct svc_serv	*serv = svsk->sk_server;
	struct socket	*sock = svsk->sk_sock;
	struct socket	*newsock;
	struct svc_sock	*newsvsk;
	int		err, slen;

	dprintk("svc: tcp_accept %p sock %p\n", svsk, sock);
	if (!sock)
		return;

	clear_bit(SK_CONN, &svsk->sk_flags);
	err = kernel_accept(sock, &newsock, O_NONBLOCK);
	if (err < 0) {
		if (err == -ENOMEM)
			printk(KERN_WARNING "%s: no more sockets!\n",
			       serv->sv_name);
		else if (err != -EAGAIN && net_ratelimit())
			printk(KERN_WARNING "%s: accept failed (err %d)!\n",
				   serv->sv_name, -err);
		return;
	}

	set_bit(SK_CONN, &svsk->sk_flags);
	svc_sock_enqueue(svsk);

	slen = sizeof(sin);
	err = kernel_getpeername(newsock, (struct sockaddr *) &sin, &slen);
	if (err < 0) {
		if (net_ratelimit())
			printk(KERN_WARNING "%s: peername failed (err %d)!\n",
				   serv->sv_name, -err);
		goto failed;		/* aborted connection or whatever */
	}

	/* Ideally, we would want to reject connections from unauthorized
	 * hosts here, but when we get encription, the IP of the host won't
	 * tell us anything. For now just warn about unpriv connections.
	 */
	if (ntohs(sin.sin_port) >= 1024) {
		dprintk(KERN_WARNING
			"%s: connect from unprivileged port: %u.%u.%u.%u:%d\n",
			serv->sv_name, 
			NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
	}

	dprintk("%s: connect from %u.%u.%u.%u:%04x\n", serv->sv_name,
			NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));

	/* make sure that a write doesn't block forever when
	 * low on memory
	 */
	newsock->sk->sk_sndtimeo = HZ*30;

	if (!(newsvsk = svc_setup_socket(serv, newsock, &err, 0)))
		goto failed;


	/* make sure that we don't have too many active connections.
	 * If we have, something must be dropped.
	 *
	 * There's no point in trying to do random drop here for
	 * DoS prevention. The NFS clients does 1 reconnect in 15
	 * seconds. An attacker can easily beat that.
	 *
	 * The only somewhat efficient mechanism would be if drop
	 * old connections from the same IP first. But right now
	 * we don't even record the client IP in svc_sock.
	 */
	if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
		struct svc_sock *svsk = NULL;
		spin_lock_bh(&serv->sv_lock);
		if (!list_empty(&serv->sv_tempsocks)) {
			if (net_ratelimit()) {
				/* Try to help the admin */
				printk(KERN_NOTICE "%s: too many open TCP "
					"sockets, consider increasing the "
					"number of nfsd threads\n",
						   serv->sv_name);
				printk(KERN_NOTICE "%s: last TCP connect from "
					"%u.%u.%u.%u:%d\n",
					serv->sv_name,
					NIPQUAD(sin.sin_addr.s_addr),
					ntohs(sin.sin_port));
			}
			/*
			 * Always select the oldest socket. It's not fair,
			 * but so is life
			 */
			svsk = list_entry(serv->sv_tempsocks.prev,
					  struct svc_sock,
					  sk_list);
			set_bit(SK_CLOSE, &svsk->sk_flags);
			atomic_inc(&svsk->sk_inuse);
		}
		spin_unlock_bh(&serv->sv_lock);

		if (svsk) {
			svc_sock_enqueue(svsk);
			svc_sock_put(svsk);
		}

	}

	if (serv->sv_stats)
		serv->sv_stats->nettcpconn++;

	return;

failed:
	sock_release(newsock);
	return;
}

/*
 * Receive data from a TCP socket.
 */
static int
svc_tcp_recvfrom(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk = rqstp->rq_sock;
	struct svc_serv	*serv = svsk->sk_server;
	int		len;
	struct kvec *vec;
	int pnum, vlen;

	dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
		svsk, test_bit(SK_DATA, &svsk->sk_flags),
		test_bit(SK_CONN, &svsk->sk_flags),
		test_bit(SK_CLOSE, &svsk->sk_flags));

	if ((rqstp->rq_deferred = svc_deferred_dequeue(svsk))) {
		svc_sock_received(svsk);
		return svc_deferred_recv(rqstp);
	}

	if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
		svc_delete_socket(svsk);
		return 0;
	}

	if (svsk->sk_sk->sk_state == TCP_LISTEN) {
		svc_tcp_accept(svsk);
		svc_sock_received(svsk);
		return 0;
	}

	if (test_and_clear_bit(SK_CHNGBUF, &svsk->sk_flags))
		/* sndbuf needs to have room for one request
		 * per thread, otherwise we can stall even when the
		 * network isn't a bottleneck.
		 *
		 * We count all threads rather than threads in a
		 * particular pool, which provides an upper bound
		 * on the number of threads which will access the socket.
		 *
		 * rcvbuf just needs to be able to hold a few requests.
		 * Normally they will be removed from the queue 
		 * as soon a a complete request arrives.
		 */
		svc_sock_setbufsize(svsk->sk_sock,
				    (serv->sv_nrthreads+3) * serv->sv_max_mesg,
				    3 * serv->sv_max_mesg);

	clear_bit(SK_DATA, &svsk->sk_flags);

	/* Receive data. If we haven't got the record length yet, get
	 * the next four bytes. Otherwise try to gobble up as much as
	 * possible up to the complete record length.
	 */
	if (svsk->sk_tcplen < 4) {
		unsigned long	want = 4 - svsk->sk_tcplen;
		struct kvec	iov;

		iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
		iov.iov_len  = want;
		if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
			goto error;
		svsk->sk_tcplen += len;

		if (len < want) {
			dprintk("svc: short recvfrom while reading record length (%d of %lu)\n",
			        len, want);
			svc_sock_received(svsk);
			return -EAGAIN; /* record header not complete */
		}

		svsk->sk_reclen = ntohl(svsk->sk_reclen);
		if (!(svsk->sk_reclen & 0x80000000)) {
			/* FIXME: technically, a record can be fragmented,
			 *  and non-terminal fragments will not have the top
			 *  bit set in the fragment length header.
			 *  But apparently no known nfs clients send fragmented
			 *  records. */
			if (net_ratelimit())
				printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
				       " (non-terminal)\n",
				       (unsigned long) svsk->sk_reclen);
			goto err_delete;
		}
		svsk->sk_reclen &= 0x7fffffff;
		dprintk("svc: TCP record, %d bytes\n", svsk->sk_reclen);
		if (svsk->sk_reclen > serv->sv_max_mesg) {
			if (net_ratelimit())
				printk(KERN_NOTICE "RPC: bad TCP reclen 0x%08lx"
				       " (large)\n",
				       (unsigned long) svsk->sk_reclen);
			goto err_delete;
		}
	}

	/* Check whether enough data is available */
	len = svc_recv_available(svsk);
	if (len < 0)
		goto error;

	if (len < svsk->sk_reclen) {
		dprintk("svc: incomplete TCP record (%d of %d)\n",
			len, svsk->sk_reclen);
		svc_sock_received(svsk);
		return -EAGAIN;	/* record not complete */
	}
	len = svsk->sk_reclen;
	set_bit(SK_DATA, &svsk->sk_flags);

	vec = rqstp->rq_vec;
	vec[0] = rqstp->rq_arg.head[0];
	vlen = PAGE_SIZE;
	pnum = 1;
	while (vlen < len) {
		vec[pnum].iov_base = page_address(rqstp->rq_pages[pnum]);
		vec[pnum].iov_len = PAGE_SIZE;
		pnum++;
		vlen += PAGE_SIZE;
	}
	rqstp->rq_respages = &rqstp->rq_pages[pnum];

	/* Now receive data */
	len = svc_recvfrom(rqstp, vec, pnum, len);
	if (len < 0)
		goto error;

	dprintk("svc: TCP complete record (%d bytes)\n", len);
	rqstp->rq_arg.len = len;
	rqstp->rq_arg.page_base = 0;
	if (len <= rqstp->rq_arg.head[0].iov_len) {
		rqstp->rq_arg.head[0].iov_len = len;
		rqstp->rq_arg.page_len = 0;
	} else {
		rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
	}

	rqstp->rq_skbuff      = NULL;
	rqstp->rq_prot	      = IPPROTO_TCP;

	/* Reset TCP read info */
	svsk->sk_reclen = 0;
	svsk->sk_tcplen = 0;

	svc_sock_received(svsk);
	if (serv->sv_stats)
		serv->sv_stats->nettcpcnt++;

	return len;

 err_delete:
	svc_delete_socket(svsk);
	return -EAGAIN;

 error:
	if (len == -EAGAIN) {
		dprintk("RPC: TCP recvfrom got EAGAIN\n");
		svc_sock_received(svsk);
	} else {
		printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
					svsk->sk_server->sv_name, -len);
		goto err_delete;
	}

	return len;
}

/*
 * Send out data on TCP socket.
 */
static int
svc_tcp_sendto(struct svc_rqst *rqstp)
{
	struct xdr_buf	*xbufp = &rqstp->rq_res;
	int sent;
	__be32 reclen;

	/* Set up the first element of the reply kvec.
	 * Any other kvecs that may be in use have been taken
	 * care of by the server implementation itself.
	 */
	reclen = htonl(0x80000000|((xbufp->len ) - 4));
	memcpy(xbufp->head[0].iov_base, &reclen, 4);

	if (test_bit(SK_DEAD, &rqstp->rq_sock->sk_flags))
		return -ENOTCONN;

	sent = svc_sendto(rqstp, &rqstp->rq_res);
	if (sent != xbufp->len) {
		printk(KERN_NOTICE "rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n",
		       rqstp->rq_sock->sk_server->sv_name,
		       (sent<0)?"got error":"sent only",
		       sent, xbufp->len);
		svc_delete_socket(rqstp->rq_sock);
		sent = -EAGAIN;
	}
	return sent;
}

static void
svc_tcp_init(struct svc_sock *svsk)
{
	struct sock	*sk = svsk->sk_sk;
	struct tcp_sock *tp = tcp_sk(sk);

	svsk->sk_recvfrom = svc_tcp_recvfrom;
	svsk->sk_sendto = svc_tcp_sendto;

	if (sk->sk_state == TCP_LISTEN) {
		dprintk("setting up TCP socket for listening\n");
		sk->sk_data_ready = svc_tcp_listen_data_ready;
		set_bit(SK_CONN, &svsk->sk_flags);
	} else {
		dprintk("setting up TCP socket for reading\n");
		sk->sk_state_change = svc_tcp_state_change;
		sk->sk_data_ready = svc_tcp_data_ready;
		sk->sk_write_space = svc_write_space;

		svsk->sk_reclen = 0;
		svsk->sk_tcplen = 0;

		tp->nonagle = 1;        /* disable Nagle's algorithm */

		/* initialise setting must have enough space to
		 * receive and respond to one request.  
		 * svc_tcp_recvfrom will re-adjust if necessary
		 */
		svc_sock_setbufsize(svsk->sk_sock,
				    3 * svsk->sk_server->sv_max_mesg,
				    3 * svsk->sk_server->sv_max_mesg);

		set_bit(SK_CHNGBUF, &svsk->sk_flags);
		set_bit(SK_DATA, &svsk->sk_flags);
		if (sk->sk_state != TCP_ESTABLISHED) 
			set_bit(SK_CLOSE, &svsk->sk_flags);
	}
}

void
svc_sock_update_bufs(struct svc_serv *serv)
{
	/*
	 * The number of server threads has changed. Update
	 * rcvbuf and sndbuf accordingly on all sockets
	 */
	struct list_head *le;

	spin_lock_bh(&serv->sv_lock);
	list_for_each(le, &serv->sv_permsocks) {
		struct svc_sock *svsk = 
			list_entry(le, struct svc_sock, sk_list);
		set_bit(SK_CHNGBUF, &svsk->sk_flags);
	}
	list_for_each(le, &serv->sv_tempsocks) {
		struct svc_sock *svsk =
			list_entry(le, struct svc_sock, sk_list);
		set_bit(SK_CHNGBUF, &svsk->sk_flags);
	}
	spin_unlock_bh(&serv->sv_lock);
}

/*
 * Receive the next request on any socket.  This code is carefully
 * organised not to touch any cachelines in the shared svc_serv
 * structure, only cachelines in the local svc_pool.
 */
int
svc_recv(struct svc_rqst *rqstp, long timeout)
{
	struct svc_sock		*svsk =NULL;
	struct svc_serv		*serv = rqstp->rq_server;
	struct svc_pool		*pool = rqstp->rq_pool;
	int			len, i;
	int 			pages;
	struct xdr_buf		*arg;
	DECLARE_WAITQUEUE(wait, current);

	dprintk("svc: server %p waiting for data (to = %ld)\n",
		rqstp, timeout);

	if (rqstp->rq_sock)
		printk(KERN_ERR 
			"svc_recv: service %p, socket not NULL!\n",
			 rqstp);
	if (waitqueue_active(&rqstp->rq_wait))
		printk(KERN_ERR 
			"svc_recv: service %p, wait queue active!\n",
			 rqstp);


	/* now allocate needed pages.  If we get a failure, sleep briefly */
	pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE;
	for (i=0; i < pages ; i++)
		while (rqstp->rq_pages[i] == NULL) {
			struct page *p = alloc_page(GFP_KERNEL);
			if (!p)
				schedule_timeout_uninterruptible(msecs_to_jiffies(500));
			rqstp->rq_pages[i] = p;
		}
	rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
	BUG_ON(pages >= RPCSVC_MAXPAGES);

	/* Make arg->head point to first page and arg->pages point to rest */
	arg = &rqstp->rq_arg;
	arg->head[0].iov_base = page_address(rqstp->rq_pages[0]);
	arg->head[0].iov_len = PAGE_SIZE;
	arg->pages = rqstp->rq_pages + 1;
	arg->page_base = 0;
	/* save at least one page for response */
	arg->page_len = (pages-2)*PAGE_SIZE;
	arg->len = (pages-1)*PAGE_SIZE;
	arg->tail[0].iov_len = 0;

	try_to_freeze();
	cond_resched();
	if (signalled())
		return -EINTR;

	spin_lock_bh(&pool->sp_lock);
	if ((svsk = svc_sock_dequeue(pool)) != NULL) {
		rqstp->rq_sock = svsk;
		atomic_inc(&svsk->sk_inuse);
		rqstp->rq_reserved = serv->sv_max_mesg;
		atomic_add(rqstp->rq_reserved, &svsk->sk_reserved);
	} else {
		/* No data pending. Go to sleep */
		svc_thread_enqueue(pool, rqstp);

		/*
		 * We have to be able to interrupt this wait
		 * to bring down the daemons ...
		 */
		set_current_state(TASK_INTERRUPTIBLE);
		add_wait_queue(&rqstp->rq_wait, &wait);
		spin_unlock_bh(&pool->sp_lock);

		schedule_timeout(timeout);

		try_to_freeze();

		spin_lock_bh(&pool->sp_lock);
		remove_wait_queue(&rqstp->rq_wait, &wait);

		if (!(svsk = rqstp->rq_sock)) {
			svc_thread_dequeue(pool, rqstp);
			spin_unlock_bh(&pool->sp_lock);
			dprintk("svc: server %p, no data yet\n", rqstp);
			return signalled()? -EINTR : -EAGAIN;
		}
	}
	spin_unlock_bh(&pool->sp_lock);

	dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
		 rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
	len = svsk->sk_recvfrom(rqstp);
	dprintk("svc: got len=%d\n", len);

	/* No data, incomplete (TCP) read, or accept() */
	if (len == 0 || len == -EAGAIN) {
		rqstp->rq_res.len = 0;
		svc_sock_release(rqstp);
		return -EAGAIN;
	}
	svsk->sk_lastrecv = get_seconds();
	clear_bit(SK_OLD, &svsk->sk_flags);

	rqstp->rq_secure  = ntohs(rqstp->rq_addr.sin_port) < 1024;
	rqstp->rq_chandle.defer = svc_defer;

	if (serv->sv_stats)
		serv->sv_stats->netcnt++;
	return len;
}

/* 
 * Drop request
 */
void
svc_drop(struct svc_rqst *rqstp)
{
	dprintk("svc: socket %p dropped request\n", rqstp->rq_sock);
	svc_sock_release(rqstp);
}

/*
 * Return reply to client.
 */
int
svc_send(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk;
	int		len;
	struct xdr_buf	*xb;

	if ((svsk = rqstp->rq_sock) == NULL) {
		printk(KERN_WARNING "NULL socket pointer in %s:%d\n",
				__FILE__, __LINE__);
		return -EFAULT;
	}

	/* release the receive skb before sending the reply */
	svc_release_skb(rqstp);

	/* calculate over-all length */
	xb = & rqstp->rq_res;
	xb->len = xb->head[0].iov_len +
		xb->page_len +
		xb->tail[0].iov_len;

	/* Grab svsk->sk_mutex to serialize outgoing data. */
	mutex_lock(&svsk->sk_mutex);
	if (test_bit(SK_DEAD, &svsk->sk_flags))
		len = -ENOTCONN;
	else
		len = svsk->sk_sendto(rqstp);
	mutex_unlock(&svsk->sk_mutex);
	svc_sock_release(rqstp);

	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
		return 0;
	return len;
}

/*
 * Timer function to close old temporary sockets, using
 * a mark-and-sweep algorithm.
 */
static void
svc_age_temp_sockets(unsigned long closure)
{
	struct svc_serv *serv = (struct svc_serv *)closure;
	struct svc_sock *svsk;
	struct list_head *le, *next;
	LIST_HEAD(to_be_aged);

	dprintk("svc_age_temp_sockets\n");

	if (!spin_trylock_bh(&serv->sv_lock)) {
		/* busy, try again 1 sec later */
		dprintk("svc_age_temp_sockets: busy\n");
		mod_timer(&serv->sv_temptimer, jiffies + HZ);
		return;
	}

	list_for_each_safe(le, next, &serv->sv_tempsocks) {
		svsk = list_entry(le, struct svc_sock, sk_list);

		if (!test_and_set_bit(SK_OLD, &svsk->sk_flags))
			continue;
		if (atomic_read(&svsk->sk_inuse) || test_bit(SK_BUSY, &svsk->sk_flags))
			continue;
		atomic_inc(&svsk->sk_inuse);
		list_move(le, &to_be_aged);
		set_bit(SK_CLOSE, &svsk->sk_flags);
		set_bit(SK_DETACHED, &svsk->sk_flags);
	}
	spin_unlock_bh(&serv->sv_lock);

	while (!list_empty(&to_be_aged)) {
		le = to_be_aged.next;
		/* fiddling the sk_list node is safe 'cos we're SK_DETACHED */
		list_del_init(le);
		svsk = list_entry(le, struct svc_sock, sk_list);

		dprintk("queuing svsk %p for closing, %lu seconds old\n",
			svsk, get_seconds() - svsk->sk_lastrecv);

		/* a thread will dequeue and close it soon */
		svc_sock_enqueue(svsk);
		svc_sock_put(svsk);
	}

	mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
}

/*
 * Initialize socket for RPC use and create svc_sock struct
 * XXX: May want to setsockopt SO_SNDBUF and SO_RCVBUF.
 */
static struct svc_sock *
svc_setup_socket(struct svc_serv *serv, struct socket *sock,
					int *errp, int pmap_register)
{
	struct svc_sock	*svsk;
	struct sock	*inet;

	dprintk("svc: svc_setup_socket %p\n", sock);
	if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) {
		*errp = -ENOMEM;
		return NULL;
	}

	inet = sock->sk;

	/* Register socket with portmapper */
	if (*errp >= 0 && pmap_register)
		*errp = svc_register(serv, inet->sk_protocol,
				     ntohs(inet_sk(inet)->sport));

	if (*errp < 0) {
		kfree(svsk);
		return NULL;
	}

	set_bit(SK_BUSY, &svsk->sk_flags);
	inet->sk_user_data = svsk;
	svsk->sk_sock = sock;
	svsk->sk_sk = inet;
	svsk->sk_ostate = inet->sk_state_change;
	svsk->sk_odata = inet->sk_data_ready;
	svsk->sk_owspace = inet->sk_write_space;
	svsk->sk_server = serv;
	atomic_set(&svsk->sk_inuse, 0);
	svsk->sk_lastrecv = get_seconds();
	spin_lock_init(&svsk->sk_defer_lock);
	INIT_LIST_HEAD(&svsk->sk_deferred);
	INIT_LIST_HEAD(&svsk->sk_ready);
	mutex_init(&svsk->sk_mutex);

	/* Initialize the socket */
	if (sock->type == SOCK_DGRAM)
		svc_udp_init(svsk);
	else
		svc_tcp_init(svsk);

	spin_lock_bh(&serv->sv_lock);
	if (!pmap_register) {
		set_bit(SK_TEMP, &svsk->sk_flags);
		list_add(&svsk->sk_list, &serv->sv_tempsocks);
		serv->sv_tmpcnt++;
		if (serv->sv_temptimer.function == NULL) {
			/* setup timer to age temp sockets */
			setup_timer(&serv->sv_temptimer, svc_age_temp_sockets,
					(unsigned long)serv);
			mod_timer(&serv->sv_temptimer,
					jiffies + svc_conn_age_period * HZ);
		}
	} else {
		clear_bit(SK_TEMP, &svsk->sk_flags);
		list_add(&svsk->sk_list, &serv->sv_permsocks);
	}
	spin_unlock_bh(&serv->sv_lock);

	dprintk("svc: svc_setup_socket created %p (inet %p)\n",
				svsk, svsk->sk_sk);

	clear_bit(SK_BUSY, &svsk->sk_flags);
	svc_sock_enqueue(svsk);
	return svsk;
}

int svc_addsock(struct svc_serv *serv,
		int fd,
		char *name_return,
		int *proto)
{
	int err = 0;
	struct socket *so = sockfd_lookup(fd, &err);
	struct svc_sock *svsk = NULL;

	if (!so)
		return err;
	if (so->sk->sk_family != AF_INET)
		err =  -EAFNOSUPPORT;
	else if (so->sk->sk_protocol != IPPROTO_TCP &&
	    so->sk->sk_protocol != IPPROTO_UDP)
		err =  -EPROTONOSUPPORT;
	else if (so->state > SS_UNCONNECTED)
		err = -EISCONN;
	else {
		svsk = svc_setup_socket(serv, so, &err, 1);
		if (svsk)
			err = 0;
	}
	if (err) {
		sockfd_put(so);
		return err;
	}
	if (proto) *proto = so->sk->sk_protocol;
	return one_sock_name(name_return, svsk);
}
EXPORT_SYMBOL_GPL(svc_addsock);

/*
 * Create socket for RPC service.
 */
static int
svc_create_socket(struct svc_serv *serv, int protocol, struct sockaddr_in *sin)
{
	struct svc_sock	*svsk;
	struct socket	*sock;
	int		error;
	int		type;

	dprintk("svc: svc_create_socket(%s, %d, %u.%u.%u.%u:%d)\n",
				serv->sv_program->pg_name, protocol,
				NIPQUAD(sin->sin_addr.s_addr),
				ntohs(sin->sin_port));

	if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) {
		printk(KERN_WARNING "svc: only UDP and TCP "
				"sockets supported\n");
		return -EINVAL;
	}
	type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM;

	if ((error = sock_create_kern(PF_INET, type, protocol, &sock)) < 0)
		return error;

	svc_reclassify_socket(sock);

	if (type == SOCK_STREAM)
		sock->sk->sk_reuse = 1; /* allow address reuse */
	error = kernel_bind(sock, (struct sockaddr *) sin,
					sizeof(*sin));
	if (error < 0)
		goto bummer;

	if (protocol == IPPROTO_TCP) {
		if ((error = kernel_listen(sock, 64)) < 0)
			goto bummer;
	}

	if ((svsk = svc_setup_socket(serv, sock, &error, 1)) != NULL)
		return 0;

bummer:
	dprintk("svc: svc_create_socket error = %d\n", -error);
	sock_release(sock);
	return error;
}

/*
 * Remove a dead socket
 */
void
svc_delete_socket(struct svc_sock *svsk)
{
	struct svc_serv	*serv;
	struct sock	*sk;

	dprintk("svc: svc_delete_socket(%p)\n", svsk);

	serv = svsk->sk_server;
	sk = svsk->sk_sk;

	sk->sk_state_change = svsk->sk_ostate;
	sk->sk_data_ready = svsk->sk_odata;
	sk->sk_write_space = svsk->sk_owspace;

	spin_lock_bh(&serv->sv_lock);

	if (!test_and_set_bit(SK_DETACHED, &svsk->sk_flags))
		list_del_init(&svsk->sk_list);
    	/*
	 * We used to delete the svc_sock from whichever list
	 * it's sk_ready node was on, but we don't actually
	 * need to.  This is because the only time we're called
	 * while still attached to a queue, the queue itself
	 * is about to be destroyed (in svc_destroy).
	 */
	if (!test_and_set_bit(SK_DEAD, &svsk->sk_flags))
		if (test_bit(SK_TEMP, &svsk->sk_flags))
			serv->sv_tmpcnt--;

	/* This atomic_inc should be needed - svc_delete_socket
	 * should have the semantic of dropping a reference.
	 * But it doesn't yet....
	 */
	atomic_inc(&svsk->sk_inuse);
	spin_unlock_bh(&serv->sv_lock);
	svc_sock_put(svsk);
}

/*
 * Make a socket for nfsd and lockd
 */
int
svc_makesock(struct svc_serv *serv, int protocol, unsigned short port)
{
	struct sockaddr_in	sin;

	dprintk("svc: creating socket proto = %d\n", protocol);
	sin.sin_family      = AF_INET;
	sin.sin_addr.s_addr = INADDR_ANY;
	sin.sin_port        = htons(port);
	return svc_create_socket(serv, protocol, &sin);
}

/*
 * Handle defer and revisit of requests 
 */

static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
{
	struct svc_deferred_req *dr = container_of(dreq, struct svc_deferred_req, handle);
	struct svc_sock *svsk;

	if (too_many) {
		svc_sock_put(dr->svsk);
		kfree(dr);
		return;
	}
	dprintk("revisit queued\n");
	svsk = dr->svsk;
	dr->svsk = NULL;
	spin_lock_bh(&svsk->sk_defer_lock);
	list_add(&dr->handle.recent, &svsk->sk_deferred);
	spin_unlock_bh(&svsk->sk_defer_lock);
	set_bit(SK_DEFERRED, &svsk->sk_flags);
	svc_sock_enqueue(svsk);
	svc_sock_put(svsk);
}

static struct cache_deferred_req *
svc_defer(struct cache_req *req)
{
	struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
	int size = sizeof(struct svc_deferred_req) + (rqstp->rq_arg.len);
	struct svc_deferred_req *dr;

	if (rqstp->rq_arg.page_len)
		return NULL; /* if more than a page, give up FIXME */
	if (rqstp->rq_deferred) {
		dr = rqstp->rq_deferred;
		rqstp->rq_deferred = NULL;
	} else {
		int skip  = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
		/* FIXME maybe discard if size too large */
		dr = kmalloc(size, GFP_KERNEL);
		if (dr == NULL)
			return NULL;

		dr->handle.owner = rqstp->rq_server;
		dr->prot = rqstp->rq_prot;
		dr->addr = rqstp->rq_addr;
		dr->daddr = rqstp->rq_daddr;
		dr->argslen = rqstp->rq_arg.len >> 2;
		memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip, dr->argslen<<2);
	}
	atomic_inc(&rqstp->rq_sock->sk_inuse);
	dr->svsk = rqstp->rq_sock;

	dr->handle.revisit = svc_revisit;
	return &dr->handle;
}

/*
 * recv data from a deferred request into an active one
 */
static int svc_deferred_recv(struct svc_rqst *rqstp)
{
	struct svc_deferred_req *dr = rqstp->rq_deferred;

	rqstp->rq_arg.head[0].iov_base = dr->args;
	rqstp->rq_arg.head[0].iov_len = dr->argslen<<2;
	rqstp->rq_arg.page_len = 0;
	rqstp->rq_arg.len = dr->argslen<<2;
	rqstp->rq_prot        = dr->prot;
	rqstp->rq_addr        = dr->addr;
	rqstp->rq_daddr       = dr->daddr;
	rqstp->rq_respages    = rqstp->rq_pages;
	return dr->argslen<<2;
}


static struct svc_deferred_req *svc_deferred_dequeue(struct svc_sock *svsk)
{
	struct svc_deferred_req *dr = NULL;
	
	if (!test_bit(SK_DEFERRED, &svsk->sk_flags))
		return NULL;
	spin_lock_bh(&svsk->sk_defer_lock);
	clear_bit(SK_DEFERRED, &svsk->sk_flags);
	if (!list_empty(&svsk->sk_deferred)) {
		dr = list_entry(svsk->sk_deferred.next,
				struct svc_deferred_req,
				handle.recent);
		list_del_init(&dr->handle.recent);
		set_bit(SK_DEFERRED, &svsk->sk_flags);
	}
	spin_unlock_bh(&svsk->sk_defer_lock);
	return dr;
}