aboutsummaryrefslogtreecommitdiffstats
path: root/net/sunrpc/svcsock.c
blob: 7bd3bbba4710d82ff658bd6de998543bca0609a7 (plain) (blame)
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
/*
 * 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_xprt_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/kernel.h>
#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/ipv6.h>
#include <net/tcp.h>
#include <net/tcp_states.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>

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

#define RPCDBG_FACILITY	RPCDBG_SVCXPRT


static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
					 int *errp, int flags);
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 void		svc_sock_detach(struct svc_xprt *);
static void		svc_tcp_sock_detach(struct svc_xprt *);
static void		svc_sock_free(struct svc_xprt *);

static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
					  struct net *, struct sockaddr *,
					  int, int);
#if defined(CONFIG_NFS_V4_1)
static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int,
					     struct net *, struct sockaddr *,
					     int, int);
static void svc_bc_sock_free(struct svc_xprt *xprt);
#endif /* CONFIG_NFS_V4_1 */

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

static void svc_reclassify_socket(struct socket *sock)
{
	struct sock *sk = sock->sk;
	BUG_ON(sock_owned_by_user(sk));
	switch (sk->sk_family) {
	case AF_INET:
		sock_lock_init_class_and_name(sk, "slock-AF_INET-NFSD",
					      &svc_slock_key[0],
					      "sk_xprt.xpt_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_xprt.xpt_lock-AF_INET6-NFSD",
					      &svc_key[1]);
		break;

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

/*
 * Release an skbuff after use
 */
static void svc_release_skb(struct svc_rqst *rqstp)
{
	struct sk_buff *skb = rqstp->rq_xprt_ctxt;

	if (skb) {
		struct svc_sock *svsk =
			container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
		rqstp->rq_xprt_ctxt = NULL;

		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
		skb_free_datagram_locked(svsk->sk_sk, skb);
	}
}

union svc_pktinfo_u {
	struct in_pktinfo pkti;
	struct in6_pktinfo pkti6;
};
#define SVC_PKTINFO_SPACE \
	CMSG_SPACE(sizeof(union svc_pktinfo_u))

static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
{
	struct svc_sock *svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	switch (svsk->sk_sk->sk_family) {
	case AF_INET: {
			struct in_pktinfo *pki = CMSG_DATA(cmh);

			cmh->cmsg_level = SOL_IP;
			cmh->cmsg_type = IP_PKTINFO;
			pki->ipi_ifindex = 0;
			pki->ipi_spec_dst.s_addr = rqstp->rq_daddr.addr.s_addr;
			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
		}
		break;

	case AF_INET6: {
			struct in6_pktinfo *pki = CMSG_DATA(cmh);

			cmh->cmsg_level = SOL_IPV6;
			cmh->cmsg_type = IPV6_PKTINFO;
			pki->ipi6_ifindex = 0;
			ipv6_addr_copy(&pki->ipi6_addr,
					&rqstp->rq_daddr.addr6);
			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
		}
		break;
	}
}

/*
 * send routine intended to be shared by the fore- and back-channel
 */
int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
		    struct page *headpage, unsigned long headoffset,
		    struct page *tailpage, unsigned long tailoffset)
{
	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;
	int		slen;
	int		len = 0;

	slen = xdr->len;

	/* send head */
	if (slen == xdr->head[0].iov_len)
		flags = 0;
	len = kernel_sendpage(sock, headpage, headoffset,
				  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, tailpage, tailoffset,
				   xdr->tail[0].iov_len, 0);
		if (result > 0)
			len += result;
	}

out:
	return len;
}


/*
 * Generic sendto routine
 */
static int svc_sendto(struct svc_rqst *rqstp, struct xdr_buf *xdr)
{
	struct svc_sock	*svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct socket	*sock = svsk->sk_sock;
	union {
		struct cmsghdr	hdr;
		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
	} buffer;
	struct cmsghdr *cmh = &buffer.hdr;
	int		len = 0;
	unsigned long tailoff;
	unsigned long headoff;
	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);

	if (rqstp->rq_prot == IPPROTO_UDP) {
		struct msghdr msg = {
			.msg_name	= &rqstp->rq_addr,
			.msg_namelen	= rqstp->rq_addrlen,
			.msg_control	= cmh,
			.msg_controllen	= sizeof(buffer),
			.msg_flags	= MSG_MORE,
		};

		svc_set_cmsg_data(rqstp, cmh);

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

	tailoff = ((unsigned long)xdr->tail[0].iov_base) & (PAGE_SIZE-1);
	headoff = 0;
	len = svc_send_common(sock, xdr, rqstp->rq_respages[0], headoff,
			       rqstp->rq_respages[0], tailoff);

out:
	dprintk("svc: socket %p sendto([%p %Zu... ], %d) = %d (addr %s)\n",
		svsk, xdr->head[0].iov_base, xdr->head[0].iov_len,
		xdr->len, len, svc_print_addr(rqstp, buf, sizeof(buf)));

	return len;
}

/*
 * Report socket names for nfsdfs
 */
static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
{
	const struct sock *sk = svsk->sk_sk;
	const char *proto_name = sk->sk_protocol == IPPROTO_UDP ?
							"udp" : "tcp";
	int len;

	switch (sk->sk_family) {
	case PF_INET:
		len = snprintf(buf, remaining, "ipv4 %s %pI4 %d\n",
				proto_name,
				&inet_sk(sk)->inet_rcv_saddr,
				inet_sk(sk)->inet_num);
		break;
	case PF_INET6:
		len = snprintf(buf, remaining, "ipv6 %s %pI6 %d\n",
				proto_name,
				&inet6_sk(sk)->rcv_saddr,
				inet_sk(sk)->inet_num);
		break;
	default:
		len = snprintf(buf, remaining, "*unknown-%d*\n",
				sk->sk_family);
	}

	if (len >= remaining) {
		*buf = '\0';
		return -ENAMETOOLONG;
	}
	return len;
}

/**
 * svc_sock_names - construct a list of listener names in a string
 * @serv: pointer to RPC service
 * @buf: pointer to a buffer to fill in with socket names
 * @buflen: size of the buffer to be filled
 * @toclose: pointer to '\0'-terminated C string containing the name
 *		of a listener to be closed
 *
 * Fills in @buf with a '\n'-separated list of names of listener
 * sockets.  If @toclose is not NULL, the socket named by @toclose
 * is closed, and is not included in the output list.
 *
 * Returns positive length of the socket name string, or a negative
 * errno value on error.
 */
int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen,
		   const char *toclose)
{
	struct svc_sock *svsk, *closesk = NULL;
	int len = 0;

	if (!serv)
		return 0;

	spin_lock_bh(&serv->sv_lock);
	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list) {
		int onelen = svc_one_sock_name(svsk, buf + len, buflen - len);
		if (onelen < 0) {
			len = onelen;
			break;
		}
		if (toclose && strcmp(toclose, buf + len) == 0) {
			closesk = svsk;
			svc_xprt_get(&closesk->sk_xprt);
		} else
			len += onelen;
	}
	spin_unlock_bh(&serv->sv_lock);

	if (closesk) {
		/* Should unregister with portmap, but you cannot
		 * unregister just one protocol...
		 */
		svc_close_xprt(&closesk->sk_xprt);
		svc_xprt_put(&closesk->sk_xprt);
	} else if (toclose)
		return -ENOENT;
	return len;
}
EXPORT_SYMBOL_GPL(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 svc_sock *svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct msghdr msg = {
		.msg_flags	= MSG_DONTWAIT,
	};
	int len;

	rqstp->rq_xprt_hlen = 0;

	len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
				msg.msg_flags);

	dprintk("svc: socket %p recvfrom(%p, %Zu) = %d\n",
		svsk, iov[0].iov_base, iov[0].iov_len, len);
	return len;
}

/*
 * Set socket snd and rcv buffer lengths
 */
static 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;
	sock->sk->sk_write_space(sock->sk);
	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(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
		svc_xprt_enqueue(&svsk->sk_xprt);
	}
	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
		wake_up_interruptible(sk_sleep(sk));
}

/*
 * 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(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
		svc_xprt_enqueue(&svsk->sk_xprt);
	}

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

static void svc_tcp_write_space(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;

	if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock)
		clear_bit(SOCK_NOSPACE, &sock->flags);
	svc_write_space(sk);
}

/*
 * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo
 */
static int svc_udp_get_dest_address4(struct svc_rqst *rqstp,
				     struct cmsghdr *cmh)
{
	struct in_pktinfo *pki = CMSG_DATA(cmh);
	if (cmh->cmsg_type != IP_PKTINFO)
		return 0;
	rqstp->rq_daddr.addr.s_addr = pki->ipi_spec_dst.s_addr;
	return 1;
}

/*
 * See net/ipv6/datagram.c : datagram_recv_ctl
 */
static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
				     struct cmsghdr *cmh)
{
	struct in6_pktinfo *pki = CMSG_DATA(cmh);
	if (cmh->cmsg_type != IPV6_PKTINFO)
		return 0;
	ipv6_addr_copy(&rqstp->rq_daddr.addr6, &pki->ipi6_addr);
	return 1;
}

/*
 * Copy the UDP datagram's destination address to the rqstp structure.
 * The 'destination' address in this case is the address to which the
 * peer sent the datagram, i.e. our local address. For multihomed
 * hosts, this can change from msg to msg. Note that only the IP
 * address changes, the port number should remain the same.
 */
static int svc_udp_get_dest_address(struct svc_rqst *rqstp,
				    struct cmsghdr *cmh)
{
	switch (cmh->cmsg_level) {
	case SOL_IP:
		return svc_udp_get_dest_address4(rqstp, cmh);
	case SOL_IPV6:
		return svc_udp_get_dest_address6(rqstp, cmh);
	}

	return 0;
}

/*
 * Receive a datagram from a UDP socket.
 */
static int svc_udp_recvfrom(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
	struct sk_buff	*skb;
	union {
		struct cmsghdr	hdr;
		long		all[SVC_PKTINFO_SPACE / sizeof(long)];
	} buffer;
	struct cmsghdr *cmh = &buffer.hdr;
	struct msghdr msg = {
		.msg_name = svc_addr(rqstp),
		.msg_control = cmh,
		.msg_controllen = sizeof(buffer),
		.msg_flags = MSG_DONTWAIT,
	};
	size_t len;
	int err;

	if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_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);

	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
	skb = NULL;
	err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
			     0, 0, MSG_PEEK | MSG_DONTWAIT);
	if (err >= 0)
		skb = skb_recv_datagram(svsk->sk_sk, 0, 1, &err);

	if (skb == NULL) {
		if (err != -EAGAIN) {
			/* possibly an icmp error */
			dprintk("svc: recvfrom returned error %d\n", -err);
			set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
		}
		return -EAGAIN;
	}
	len = svc_addr_len(svc_addr(rqstp));
	if (len == 0)
		return -EAFNOSUPPORT;
	rqstp->rq_addrlen = len;
	if (skb->tstamp.tv64 == 0) {
		skb->tstamp = ktime_get_real();
		/* Don't enable netstamp, sunrpc doesn't
		   need that much accuracy */
	}
	svsk->sk_sk->sk_stamp = skb->tstamp;
	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */

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

	rqstp->rq_prot = IPPROTO_UDP;

	if (!svc_udp_get_dest_address(rqstp, cmh)) {
		if (net_ratelimit())
			printk(KERN_WARNING
				"svc: received unknown control message %d/%d; "
				"dropping RPC reply datagram\n",
					cmh->cmsg_level, cmh->cmsg_type);
		skb_free_datagram_locked(svsk->sk_sk, skb);
		return 0;
	}

	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_locked(svsk->sk_sk, skb);
			return 0;
		}
		local_bh_enable();
		skb_free_datagram_locked(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_locked(svsk->sk_sk, skb);
			return 0;
		}
		rqstp->rq_xprt_ctxt = 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 +
			DIV_ROUND_UP(rqstp->rq_arg.page_len, 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_prep_reply_hdr(struct svc_rqst *rqstp)
{
}

static int svc_udp_has_wspace(struct svc_xprt *xprt)
{
	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
	struct svc_serv	*serv = xprt->xpt_server;
	unsigned long required;

	/*
	 * Set the SOCK_NOSPACE flag before checking the available
	 * sock space.
	 */
	set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
	required = atomic_read(&svsk->sk_xprt.xpt_reserved) + serv->sv_max_mesg;
	if (required*2 > sock_wspace(svsk->sk_sk))
		return 0;
	clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
	return 1;
}

static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
{
	BUG();
	return NULL;
}

static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
				       struct net *net,
				       struct sockaddr *sa, int salen,
				       int flags)
{
	return svc_create_socket(serv, IPPROTO_UDP, net, sa, salen, flags);
}

static struct svc_xprt_ops svc_udp_ops = {
	.xpo_create = svc_udp_create,
	.xpo_recvfrom = svc_udp_recvfrom,
	.xpo_sendto = svc_udp_sendto,
	.xpo_release_rqst = svc_release_skb,
	.xpo_detach = svc_sock_detach,
	.xpo_free = svc_sock_free,
	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
	.xpo_has_wspace = svc_udp_has_wspace,
	.xpo_accept = svc_udp_accept,
};

static struct svc_xprt_class svc_udp_class = {
	.xcl_name = "udp",
	.xcl_owner = THIS_MODULE,
	.xcl_ops = &svc_udp_ops,
	.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
};

static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
	int err, level, optname, one = 1;

	svc_xprt_init(&svc_udp_class, &svsk->sk_xprt, serv);
	clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
	svsk->sk_sk->sk_data_ready = svc_udp_data_ready;
	svsk->sk_sk->sk_write_space = svc_write_space;

	/* 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_xprt.xpt_server->sv_max_mesg,
			    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);

	/* data might have come in before data_ready set up */
	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
	set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);

	/* make sure we get destination address info */
	switch (svsk->sk_sk->sk_family) {
	case AF_INET:
		level = SOL_IP;
		optname = IP_PKTINFO;
		break;
	case AF_INET6:
		level = SOL_IPV6;
		optname = IPV6_RECVPKTINFO;
		break;
	default:
		BUG();
	}
	err = kernel_setsockopt(svsk->sk_sock, level, optname,
					(char *)&one, sizeof(one));
	dprintk("svc: kernel_setsockopt returned %d\n", err);
}

/*
 * 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(XPT_CONN, &svsk->sk_xprt.xpt_flags);
			svc_xprt_enqueue(&svsk->sk_xprt);
		} else
			printk("svc: socket %p: no user data\n", sk);
	}

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

/*
 * 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(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
		svc_xprt_enqueue(&svsk->sk_xprt);
	}
	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
		wake_up_interruptible_all(sk_sleep(sk));
}

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(XPT_DATA, &svsk->sk_xprt.xpt_flags);
		svc_xprt_enqueue(&svsk->sk_xprt);
	}
	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
		wake_up_interruptible(sk_sleep(sk));
}

/*
 * Accept a TCP connection
 */
static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
{
	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
	struct sockaddr_storage addr;
	struct sockaddr	*sin = (struct sockaddr *) &addr;
	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
	struct socket	*sock = svsk->sk_sock;
	struct socket	*newsock;
	struct svc_sock	*newsvsk;
	int		err, slen;
	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);

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

	clear_bit(XPT_CONN, &svsk->sk_xprt.xpt_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 NULL;
	}
	set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags);

	err = kernel_getpeername(newsock, 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 encryption, the IP of the host won't
	 * tell us anything.  For now just warn about unpriv connections.
	 */
	if (!svc_port_is_privileged(sin)) {
		dprintk(KERN_WARNING
			"%s: connect from unprivileged port: %s\n",
			serv->sv_name,
			__svc_print_addr(sin, buf, sizeof(buf)));
	}
	dprintk("%s: connect from %s\n", serv->sv_name,
		__svc_print_addr(sin, buf, sizeof(buf)));

	/* 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,
				 (SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY))))
		goto failed;
	svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
	err = kernel_getsockname(newsock, sin, &slen);
	if (unlikely(err < 0)) {
		dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err);
		slen = offsetof(struct sockaddr, sa_data);
	}
	svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);

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

	return &newsvsk->sk_xprt;

failed:
	sock_release(newsock);
	return NULL;
}

/*
 * Receive data.
 * If we haven't gotten the record length yet, get the next four bytes.
 * Otherwise try to gobble up as much as possible up to the complete
 * record length.
 */
static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
{
	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
	int len;

	if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_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(XPT_DATA, &svsk->sk_xprt.xpt_flags);

	if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
		int		want = sizeof(rpc_fraghdr) - 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 %d)\n", len, want);
			goto err_again; /* record header not complete */
		}

		svsk->sk_reclen = ntohl(svsk->sk_reclen);
		if (!(svsk->sk_reclen & RPC_LAST_STREAM_FRAGMENT)) {
			/* 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: multiple fragments "
					"per record not supported\n");
			goto err_delete;
		}

		svsk->sk_reclen &= RPC_FRAGMENT_SIZE_MASK;
		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: "
					"fragment too large: 0x%08lx\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);
		goto err_again;	/* record not complete */
	}
	len = svsk->sk_reclen;
	set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);

	return len;
 error:
	if (len == -EAGAIN)
		dprintk("RPC: TCP recv_record got EAGAIN\n");
	return len;
 err_delete:
	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
 err_again:
	return -EAGAIN;
}

static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp,
			       struct rpc_rqst **reqpp, struct kvec *vec)
{
	struct rpc_rqst *req = NULL;
	u32 *p;
	u32 xid;
	u32 calldir;
	int len;

	len = svc_recvfrom(rqstp, vec, 1, 8);
	if (len < 0)
		goto error;

	p = (u32 *)rqstp->rq_arg.head[0].iov_base;
	xid = *p++;
	calldir = *p;

	if (calldir == 0) {
		/* REQUEST is the most common case */
		vec[0] = rqstp->rq_arg.head[0];
	} else {
		/* REPLY */
		struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;

		if (bc_xprt)
			req = xprt_lookup_rqst(bc_xprt, xid);

		if (!req) {
			printk(KERN_NOTICE
				"%s: Got unrecognized reply: "
				"calldir 0x%x xpt_bc_xprt %p xid %08x\n",
				__func__, ntohl(calldir),
				bc_xprt, xid);
			vec[0] = rqstp->rq_arg.head[0];
			goto out;
		}

		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
		       sizeof(struct xdr_buf));
		/* copy the xid and call direction */
		memcpy(req->rq_private_buf.head[0].iov_base,
		       rqstp->rq_arg.head[0].iov_base, 8);
		vec[0] = req->rq_private_buf.head[0];
	}
 out:
	vec[0].iov_base += 8;
	vec[0].iov_len -= 8;
	len = svsk->sk_reclen - 8;
 error:
	*reqpp = req;
	return len;
}

/*
 * Receive data from a TCP socket.
 */
static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
{
	struct svc_sock	*svsk =
		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
	struct svc_serv	*serv = svsk->sk_xprt.xpt_server;
	int		len;
	struct kvec *vec;
	int pnum, vlen;
	struct rpc_rqst *req = NULL;

	dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
		svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
		test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags),
		test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags));

	len = svc_tcp_recv_record(svsk, rqstp);
	if (len < 0)
		goto error;

	vec = rqstp->rq_vec;
	vec[0] = rqstp->rq_arg.head[0];
	vlen = PAGE_SIZE;

	/*
	 * We have enough data for the whole tcp record. Let's try and read the
	 * first 8 bytes to get the xid and the call direction. We can use this
	 * to figure out if this is a call or a reply to a callback. If
	 * sk_reclen is < 8 (xid and calldir), then this is a malformed packet.
	 * In that case, don't bother with the calldir and just read the data.
	 * It will be rejected in svc_process.
	 */
	if (len >= 8) {
		len = svc_process_calldir(svsk, rqstp, &req, vec);
		if (len < 0)
			goto err_again;
		vlen -= 8;
	}

	pnum = 1;
	while (vlen < len) {
		vec[pnum].iov_base = (req) ?
			page_address(req->rq_private_buf.pages[pnum - 1]) :
			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 err_again;

	/*
	 * Account for the 8 bytes we read earlier
	 */
	len += 8;

	if (req) {
		xprt_complete_rqst(req->rq_task, len);
		len = 0;
		goto out;
	}
	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_xprt_ctxt   = NULL;
	rqstp->rq_prot	      = IPPROTO_TCP;

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

	svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
	if (serv->sv_stats)
		serv->sv_stats->nettcpcnt++;

	return len;

err_again:
	if (len == -EAGAIN) {
		dprintk("RPC: TCP recvfrom got EAGAIN\n");
		return len;
	}
error:
	if (len != -EAGAIN) {
		printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
		       svsk->sk_xprt.xpt_server->sv_name, -len);
		set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
	}
	return -EAGAIN;
}

/*
 * 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);

	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_xprt->xpt_server->sv_name,
		       (sent<0)?"got error":"sent only",
		       sent, xbufp->len);
		set_bit(XPT_CLOSE, &rqstp->rq_xprt->xpt_flags);
		svc_xprt_enqueue(rqstp->rq_xprt);
		sent = -EAGAIN;
	}
	return sent;
}

/*
 * Setup response header. TCP has a 4B record length field.
 */
static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp)
{
	struct kvec *resv = &rqstp->rq_res.head[0];

	/* tcp needs a space for the record length... */
	svc_putnl(resv, 0);
}

static int svc_tcp_has_wspace(struct svc_xprt *xprt)
{
	struct svc_sock *svsk =	container_of(xprt, struct svc_sock, sk_xprt);
	struct svc_serv *serv = svsk->sk_xprt.xpt_server;
	int required;

	if (test_bit(XPT_LISTENER, &xprt->xpt_flags))
		return 1;
	required = atomic_read(&xprt->xpt_reserved) + serv->sv_max_mesg;
	if (sk_stream_wspace(svsk->sk_sk) >= required)
		return 1;
	set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
	return 0;
}

static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
				       struct net *net,
				       struct sockaddr *sa, int salen,
				       int flags)
{
	return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
}

#if defined(CONFIG_NFS_V4_1)
static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int,
					     struct net *, struct sockaddr *,
					     int, int);
static void svc_bc_sock_free(struct svc_xprt *xprt);

static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv,
				       struct net *net,
				       struct sockaddr *sa, int salen,
				       int flags)
{
	return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
}

static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt)
{
}

static struct svc_xprt_ops svc_tcp_bc_ops = {
	.xpo_create = svc_bc_tcp_create,
	.xpo_detach = svc_bc_tcp_sock_detach,
	.xpo_free = svc_bc_sock_free,
	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
};

static struct svc_xprt_class svc_tcp_bc_class = {
	.xcl_name = "tcp-bc",
	.xcl_owner = THIS_MODULE,
	.xcl_ops = &svc_tcp_bc_ops,
	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
};

static void svc_init_bc_xprt_sock(void)
{
	svc_reg_xprt_class(&svc_tcp_bc_class);
}

static void svc_cleanup_bc_xprt_sock(void)
{
	svc_unreg_xprt_class(&svc_tcp_bc_class);
}
#else /* CONFIG_NFS_V4_1 */
static void svc_init_bc_xprt_sock(void)
{
}

static void svc_cleanup_bc_xprt_sock(void)
{
}
#endif /* CONFIG_NFS_V4_1 */

static struct svc_xprt_ops svc_tcp_ops = {
	.xpo_create = svc_tcp_create,
	.xpo_recvfrom = svc_tcp_recvfrom,
	.xpo_sendto = svc_tcp_sendto,
	.xpo_release_rqst = svc_release_skb,
	.xpo_detach = svc_tcp_sock_detach,
	.xpo_free = svc_sock_free,
	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
	.xpo_has_wspace = svc_tcp_has_wspace,
	.xpo_accept = svc_tcp_accept,
};

static struct svc_xprt_class svc_tcp_class = {
	.xcl_name = "tcp",
	.xcl_owner = THIS_MODULE,
	.xcl_ops = &svc_tcp_ops,
	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
};

void svc_init_xprt_sock(void)
{
	svc_reg_xprt_class(&svc_tcp_class);
	svc_reg_xprt_class(&svc_udp_class);
	svc_init_bc_xprt_sock();
}

void svc_cleanup_xprt_sock(void)
{
	svc_unreg_xprt_class(&svc_tcp_class);
	svc_unreg_xprt_class(&svc_udp_class);
	svc_cleanup_bc_xprt_sock();
}

static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
{
	struct sock	*sk = svsk->sk_sk;

	svc_xprt_init(&svc_tcp_class, &svsk->sk_xprt, serv);
	set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags);
	if (sk->sk_state == TCP_LISTEN) {
		dprintk("setting up TCP socket for listening\n");
		set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags);
		sk->sk_data_ready = svc_tcp_listen_data_ready;
		set_bit(XPT_CONN, &svsk->sk_xprt.xpt_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_tcp_write_space;

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

		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;

		/* 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_xprt.xpt_server->sv_max_mesg,
				    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);

		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
		if (sk->sk_state != TCP_ESTABLISHED)
			set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_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 svc_sock *svsk;

	spin_lock_bh(&serv->sv_lock);
	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
	list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
	spin_unlock_bh(&serv->sv_lock);
}
EXPORT_SYMBOL_GPL(svc_sock_update_bufs);

/*
 * 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 flags)
{
	struct svc_sock	*svsk;
	struct sock	*inet;
	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);

	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_family, inet->sk_protocol,
				     ntohs(inet_sk(inet)->inet_sport));

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

	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;

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

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

	return svsk;
}

/**
 * svc_addsock - add a listener socket to an RPC service
 * @serv: pointer to RPC service to which to add a new listener
 * @fd: file descriptor of the new listener
 * @name_return: pointer to buffer to fill in with name of listener
 * @len: size of the buffer
 *
 * Fills in socket name and returns positive length of name if successful.
 * Name is terminated with '\n'.  On error, returns a negative errno
 * value.
 */
int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
		const size_t len)
{
	int err = 0;
	struct socket *so = sockfd_lookup(fd, &err);
	struct svc_sock *svsk = NULL;

	if (!so)
		return err;
	if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
		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 {
		if (!try_module_get(THIS_MODULE))
			err = -ENOENT;
		else
			svsk = svc_setup_socket(serv, so, &err,
						SVC_SOCK_DEFAULTS);
		if (svsk) {
			struct sockaddr_storage addr;
			struct sockaddr *sin = (struct sockaddr *)&addr;
			int salen;
			if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0)
				svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
			clear_bit(XPT_TEMP, &svsk->sk_xprt.xpt_flags);
			spin_lock_bh(&serv->sv_lock);
			list_add(&svsk->sk_xprt.xpt_list, &serv->sv_permsocks);
			spin_unlock_bh(&serv->sv_lock);
			svc_xprt_received(&svsk->sk_xprt);
			err = 0;
		} else
			module_put(THIS_MODULE);
	}
	if (err) {
		sockfd_put(so);
		return err;
	}
	return svc_one_sock_name(svsk, name_return, len);
}
EXPORT_SYMBOL_GPL(svc_addsock);

/*
 * Create socket for RPC service.
 */
static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
					  int protocol,
					  struct net *net,
					  struct sockaddr *sin, int len,
					  int flags)
{
	struct svc_sock	*svsk;
	struct socket	*sock;
	int		error;
	int		type;
	struct sockaddr_storage addr;
	struct sockaddr *newsin = (struct sockaddr *)&addr;
	int		newlen;
	int		family;
	int		val;
	RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);

	dprintk("svc: svc_create_socket(%s, %d, %s)\n",
			serv->sv_program->pg_name, protocol,
			__svc_print_addr(sin, buf, sizeof(buf)));

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

	type = (protocol == IPPROTO_UDP)? SOCK_DGRAM : SOCK_STREAM;
	switch (sin->sa_family) {
	case AF_INET6:
		family = PF_INET6;
		break;
	case AF_INET:
		family = PF_INET;
		break;
	default:
		return ERR_PTR(-EINVAL);
	}

	error = __sock_create(net, family, type, protocol, &sock, 1);
	if (error < 0)
		return ERR_PTR(error);

	svc_reclassify_socket(sock);

	/*
	 * If this is an PF_INET6 listener, we want to avoid
	 * getting requests from IPv4 remotes.  Those should
	 * be shunted to a PF_INET listener via rpcbind.
	 */
	val = 1;
	if (family == PF_INET6)
		kernel_setsockopt(sock, SOL_IPV6, IPV6_V6ONLY,
					(char *)&val, sizeof(val));

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

	newlen = len;
	error = kernel_getsockname(sock, newsin, &newlen);
	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, flags)) != NULL) {
		svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
		return (struct svc_xprt *)svsk;
	}

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

/*
 * Detach the svc_sock from the socket so that no
 * more callbacks occur.
 */
static void svc_sock_detach(struct svc_xprt *xprt)
{
	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
	struct sock *sk = svsk->sk_sk;

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

	/* put back the old socket callbacks */
	sk->sk_state_change = svsk->sk_ostate;
	sk->sk_data_ready = svsk->sk_odata;
	sk->sk_write_space = svsk->sk_owspace;

	if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
		wake_up_interruptible(sk_sleep(sk));
}

/*
 * Disconnect the socket, and reset the callbacks
 */
static void svc_tcp_sock_detach(struct svc_xprt *xprt)
{
	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);

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

	svc_sock_detach(xprt);

	if (!test_bit(XPT_LISTENER, &xprt->xpt_flags))
		kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR);
}

/*
 * Free the svc_sock's socket resources and the svc_sock itself.
 */
static void svc_sock_free(struct svc_xprt *xprt)
{
	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
	dprintk("svc: svc_sock_free(%p)\n", svsk);

	if (svsk->sk_sock->file)
		sockfd_put(svsk->sk_sock);
	else
		sock_release(svsk->sk_sock);
	kfree(svsk);
}

#if defined(CONFIG_NFS_V4_1)
/*
 * Create a back channel svc_xprt which shares the fore channel socket.
 */
static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv,
					     int protocol,
					     struct net *net,
					     struct sockaddr *sin, int len,
					     int flags)
{
	struct svc_sock *svsk;
	struct svc_xprt *xprt;

	if (protocol != IPPROTO_TCP) {
		printk(KERN_WARNING "svc: only TCP sockets"
			" supported on shared back channel\n");
		return ERR_PTR(-EINVAL);
	}

	svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
	if (!svsk)
		return ERR_PTR(-ENOMEM);

	xprt = &svsk->sk_xprt;
	svc_xprt_init(&svc_tcp_bc_class, xprt, serv);

	serv->sv_bc_xprt = xprt;

	return xprt;
}

/*
 * Free a back channel svc_sock.
 */
static void svc_bc_sock_free(struct svc_xprt *xprt)
{
	if (xprt) {
		kfree(xprt->xpt_bc_sid);
		kfree(container_of(xprt, struct svc_sock, sk_xprt));
	}
}
#endif /* CONFIG_NFS_V4_1 */