summaryrefslogtreecommitdiff
path: root/fs/dlm/lowcomms.c
blob: b48640709bbd71ae3944bfd9ae9e56642fcb7ac2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2009 Red Hat, Inc.  All rights reserved.
**
**  This copyrighted material is made available to anyone wishing to use,
**  modify, copy, or redistribute it subject to the terms and conditions
**  of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/

/*
 * lowcomms.c
 *
 * This is the "low-level" comms layer.
 *
 * It is responsible for sending/receiving messages
 * from other nodes in the cluster.
 *
 * Cluster nodes are referred to by their nodeids. nodeids are
 * simply 32 bit numbers to the locking module - if they need to
 * be expanded for the cluster infrastructure then that is its
 * responsibility. It is this layer's
 * responsibility to resolve these into IP address or
 * whatever it needs for inter-node communication.
 *
 * The comms level is two kernel threads that deal mainly with
 * the receiving of messages from other nodes and passing them
 * up to the mid-level comms layer (which understands the
 * message format) for execution by the locking core, and
 * a send thread which does all the setting up of connections
 * to remote nodes and the sending of data. Threads are not allowed
 * to send their own data because it may cause them to wait in times
 * of high load. Also, this way, the sending thread can collect together
 * messages bound for one node and send them in one block.
 *
 * lowcomms will choose to use either TCP or SCTP as its transport layer
 * depending on the configuration variable 'protocol'. This should be set
 * to 0 (default) for TCP or 1 for SCTP. It should be configured using a
 * cluster-wide mechanism as it must be the same on all nodes of the cluster
 * for the DLM to function.
 *
 */

#include <asm/ioctls.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mutex.h>
#include <linux/sctp.h>
#include <linux/slab.h>
#include <net/sctp/sctp.h>
#include <net/ipv6.h>

#include "dlm_internal.h"
#include "lowcomms.h"
#include "midcomms.h"
#include "config.h"

#define NEEDED_RMEM (4*1024*1024)
#define CONN_HASH_SIZE 32

/* Number of messages to send before rescheduling */
#define MAX_SEND_MSG_COUNT 25

struct cbuf {
	unsigned int base;
	unsigned int len;
	unsigned int mask;
};

static void cbuf_add(struct cbuf *cb, int n)
{
	cb->len += n;
}

static int cbuf_data(struct cbuf *cb)
{
	return ((cb->base + cb->len) & cb->mask);
}

static void cbuf_init(struct cbuf *cb, int size)
{
	cb->base = cb->len = 0;
	cb->mask = size-1;
}

static void cbuf_eat(struct cbuf *cb, int n)
{
	cb->len  -= n;
	cb->base += n;
	cb->base &= cb->mask;
}

static bool cbuf_empty(struct cbuf *cb)
{
	return cb->len == 0;
}

struct connection {
	struct socket *sock;	/* NULL if not connected */
	uint32_t nodeid;	/* So we know who we are in the list */
	struct mutex sock_mutex;
	unsigned long flags;
#define CF_READ_PENDING 1
#define CF_INIT_PENDING 4
#define CF_IS_OTHERCON 5
#define CF_CLOSE 6
#define CF_APP_LIMITED 7
#define CF_CLOSING 8
	struct list_head writequeue;  /* List of outgoing writequeue_entries */
	spinlock_t writequeue_lock;
	int (*rx_action) (struct connection *);	/* What to do when active */
	void (*connect_action) (struct connection *);	/* What to do to connect */
	struct page *rx_page;
	struct cbuf cb;
	int retries;
#define MAX_CONNECT_RETRIES 3
	struct hlist_node list;
	struct connection *othercon;
	struct work_struct rwork; /* Receive workqueue */
	struct work_struct swork; /* Send workqueue */
};
#define sock2con(x) ((struct connection *)(x)->sk_user_data)

/* An entry waiting to be sent */
struct writequeue_entry {
	struct list_head list;
	struct page *page;
	int offset;
	int len;
	int end;
	int users;
	struct connection *con;
};

struct dlm_node_addr {
	struct list_head list;
	int nodeid;
	int addr_count;
	int curr_addr_index;
	struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
};

static struct listen_sock_callbacks {
	void (*sk_error_report)(struct sock *);
	void (*sk_data_ready)(struct sock *);
	void (*sk_state_change)(struct sock *);
	void (*sk_write_space)(struct sock *);
} listen_sock;

static LIST_HEAD(dlm_node_addrs);
static DEFINE_SPINLOCK(dlm_node_addrs_spin);

static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
static int dlm_local_count;
static int dlm_allow_conn;

/* Work queues */
static struct workqueue_struct *recv_workqueue;
static struct workqueue_struct *send_workqueue;

static struct hlist_head connection_hash[CONN_HASH_SIZE];
static DEFINE_MUTEX(connections_lock);
static struct kmem_cache *con_cache;

static void process_recv_sockets(struct work_struct *work);
static void process_send_sockets(struct work_struct *work);


/* This is deliberately very simple because most clusters have simple
   sequential nodeids, so we should be able to go straight to a connection
   struct in the array */
static inline int nodeid_hash(int nodeid)
{
	return nodeid & (CONN_HASH_SIZE-1);
}

static struct connection *__find_con(int nodeid)
{
	int r;
	struct connection *con;

	r = nodeid_hash(nodeid);

	hlist_for_each_entry(con, &connection_hash[r], list) {
		if (con->nodeid == nodeid)
			return con;
	}
	return NULL;
}

/*
 * If 'allocation' is zero then we don't attempt to create a new
 * connection structure for this node.
 */
static struct connection *__nodeid2con(int nodeid, gfp_t alloc)
{
	struct connection *con = NULL;
	int r;

	con = __find_con(nodeid);
	if (con || !alloc)
		return con;

	con = kmem_cache_zalloc(con_cache, alloc);
	if (!con)
		return NULL;

	r = nodeid_hash(nodeid);
	hlist_add_head(&con->list, &connection_hash[r]);

	con->nodeid = nodeid;
	mutex_init(&con->sock_mutex);
	INIT_LIST_HEAD(&con->writequeue);
	spin_lock_init(&con->writequeue_lock);
	INIT_WORK(&con->swork, process_send_sockets);
	INIT_WORK(&con->rwork, process_recv_sockets);

	/* Setup action pointers for child sockets */
	if (con->nodeid) {
		struct connection *zerocon = __find_con(0);

		con->connect_action = zerocon->connect_action;
		if (!con->rx_action)
			con->rx_action = zerocon->rx_action;
	}

	return con;
}

/* Loop round all connections */
static void foreach_conn(void (*conn_func)(struct connection *c))
{
	int i;
	struct hlist_node *n;
	struct connection *con;

	for (i = 0; i < CONN_HASH_SIZE; i++) {
		hlist_for_each_entry_safe(con, n, &connection_hash[i], list)
			conn_func(con);
	}
}

static struct connection *nodeid2con(int nodeid, gfp_t allocation)
{
	struct connection *con;

	mutex_lock(&connections_lock);
	con = __nodeid2con(nodeid, allocation);
	mutex_unlock(&connections_lock);

	return con;
}

static struct dlm_node_addr *find_node_addr(int nodeid)
{
	struct dlm_node_addr *na;

	list_for_each_entry(na, &dlm_node_addrs, list) {
		if (na->nodeid == nodeid)
			return na;
	}
	return NULL;
}

static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
{
	switch (x->ss_family) {
	case AF_INET: {
		struct sockaddr_in *sinx = (struct sockaddr_in *)x;
		struct sockaddr_in *siny = (struct sockaddr_in *)y;
		if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
			return 0;
		if (sinx->sin_port != siny->sin_port)
			return 0;
		break;
	}
	case AF_INET6: {
		struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
		struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
		if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
			return 0;
		if (sinx->sin6_port != siny->sin6_port)
			return 0;
		break;
	}
	default:
		return 0;
	}
	return 1;
}

static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
			  struct sockaddr *sa_out, bool try_new_addr)
{
	struct sockaddr_storage sas;
	struct dlm_node_addr *na;

	if (!dlm_local_count)
		return -1;

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (na && na->addr_count) {
		memcpy(&sas, na->addr[na->curr_addr_index],
		       sizeof(struct sockaddr_storage));

		if (try_new_addr) {
			na->curr_addr_index++;
			if (na->curr_addr_index == na->addr_count)
				na->curr_addr_index = 0;
		}
	}
	spin_unlock(&dlm_node_addrs_spin);

	if (!na)
		return -EEXIST;

	if (!na->addr_count)
		return -ENOENT;

	if (sas_out)
		memcpy(sas_out, &sas, sizeof(struct sockaddr_storage));

	if (!sa_out)
		return 0;

	if (dlm_local_addr[0]->ss_family == AF_INET) {
		struct sockaddr_in *in4  = (struct sockaddr_in *) &sas;
		struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out;
		ret4->sin_addr.s_addr = in4->sin_addr.s_addr;
	} else {
		struct sockaddr_in6 *in6  = (struct sockaddr_in6 *) &sas;
		struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) sa_out;
		ret6->sin6_addr = in6->sin6_addr;
	}

	return 0;
}

static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
{
	struct dlm_node_addr *na;
	int rv = -EEXIST;
	int addr_i;

	spin_lock(&dlm_node_addrs_spin);
	list_for_each_entry(na, &dlm_node_addrs, list) {
		if (!na->addr_count)
			continue;

		for (addr_i = 0; addr_i < na->addr_count; addr_i++) {
			if (addr_compare(na->addr[addr_i], addr)) {
				*nodeid = na->nodeid;
				rv = 0;
				goto unlock;
			}
		}
	}
unlock:
	spin_unlock(&dlm_node_addrs_spin);
	return rv;
}

int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
{
	struct sockaddr_storage *new_addr;
	struct dlm_node_addr *new_node, *na;

	new_node = kzalloc(sizeof(struct dlm_node_addr), GFP_NOFS);
	if (!new_node)
		return -ENOMEM;

	new_addr = kzalloc(sizeof(struct sockaddr_storage), GFP_NOFS);
	if (!new_addr) {
		kfree(new_node);
		return -ENOMEM;
	}

	memcpy(new_addr, addr, len);

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (!na) {
		new_node->nodeid = nodeid;
		new_node->addr[0] = new_addr;
		new_node->addr_count = 1;
		list_add(&new_node->list, &dlm_node_addrs);
		spin_unlock(&dlm_node_addrs_spin);
		return 0;
	}

	if (na->addr_count >= DLM_MAX_ADDR_COUNT) {
		spin_unlock(&dlm_node_addrs_spin);
		kfree(new_addr);
		kfree(new_node);
		return -ENOSPC;
	}

	na->addr[na->addr_count++] = new_addr;
	spin_unlock(&dlm_node_addrs_spin);
	kfree(new_node);
	return 0;
}

/* Data available on socket or listen socket received a connect */
static void lowcomms_data_ready(struct sock *sk)
{
	struct connection *con = sock2con(sk);
	if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags))
		queue_work(recv_workqueue, &con->rwork);
}

static void lowcomms_write_space(struct sock *sk)
{
	struct connection *con = sock2con(sk);

	if (!con)
		return;

	clear_bit(SOCK_NOSPACE, &con->sock->flags);

	if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
		con->sock->sk->sk_write_pending--;
		clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
	}

	queue_work(send_workqueue, &con->swork);
}

static inline void lowcomms_connect_sock(struct connection *con)
{
	if (test_bit(CF_CLOSE, &con->flags))
		return;
	queue_work(send_workqueue, &con->swork);
	cond_resched();
}

static void lowcomms_state_change(struct sock *sk)
{
	/* SCTP layer is not calling sk_data_ready when the connection
	 * is done, so we catch the signal through here. Also, it
	 * doesn't switch socket state when entering shutdown, so we
	 * skip the write in that case.
	 */
	if (sk->sk_shutdown) {
		if (sk->sk_shutdown == RCV_SHUTDOWN)
			lowcomms_data_ready(sk);
	} else if (sk->sk_state == TCP_ESTABLISHED) {
		lowcomms_write_space(sk);
	}
}

int dlm_lowcomms_connect_node(int nodeid)
{
	struct connection *con;

	if (nodeid == dlm_our_nodeid())
		return 0;

	con = nodeid2con(nodeid, GFP_NOFS);
	if (!con)
		return -ENOMEM;
	lowcomms_connect_sock(con);
	return 0;
}

static void lowcomms_error_report(struct sock *sk)
{
	struct connection *con;
	struct sockaddr_storage saddr;
	int buflen;
	void (*orig_report)(struct sock *) = NULL;

	read_lock_bh(&sk->sk_callback_lock);
	con = sock2con(sk);
	if (con == NULL)
		goto out;

	orig_report = listen_sock.sk_error_report;
	if (con->sock == NULL ||
	    kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) {
		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
				   "sending to node %d, port %d, "
				   "sk_err=%d/%d\n", dlm_our_nodeid(),
				   con->nodeid, dlm_config.ci_tcp_port,
				   sk->sk_err, sk->sk_err_soft);
	} else if (saddr.ss_family == AF_INET) {
		struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr;

		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
				   "sending to node %d at %pI4, port %d, "
				   "sk_err=%d/%d\n", dlm_our_nodeid(),
				   con->nodeid, &sin4->sin_addr.s_addr,
				   dlm_config.ci_tcp_port, sk->sk_err,
				   sk->sk_err_soft);
	} else {
		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&saddr;

		printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
				   "sending to node %d at %u.%u.%u.%u, "
				   "port %d, sk_err=%d/%d\n", dlm_our_nodeid(),
				   con->nodeid, sin6->sin6_addr.s6_addr32[0],
				   sin6->sin6_addr.s6_addr32[1],
				   sin6->sin6_addr.s6_addr32[2],
				   sin6->sin6_addr.s6_addr32[3],
				   dlm_config.ci_tcp_port, sk->sk_err,
				   sk->sk_err_soft);
	}
out:
	read_unlock_bh(&sk->sk_callback_lock);
	if (orig_report)
		orig_report(sk);
}

/* Note: sk_callback_lock must be locked before calling this function. */
static void save_listen_callbacks(struct socket *sock)
{
	struct sock *sk = sock->sk;

	listen_sock.sk_data_ready = sk->sk_data_ready;
	listen_sock.sk_state_change = sk->sk_state_change;
	listen_sock.sk_write_space = sk->sk_write_space;
	listen_sock.sk_error_report = sk->sk_error_report;
}

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

	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_user_data = NULL;
	sk->sk_data_ready = listen_sock.sk_data_ready;
	sk->sk_state_change = listen_sock.sk_state_change;
	sk->sk_write_space = listen_sock.sk_write_space;
	sk->sk_error_report = listen_sock.sk_error_report;
	write_unlock_bh(&sk->sk_callback_lock);
}

/* Make a socket active */
static void add_sock(struct socket *sock, struct connection *con)
{
	struct sock *sk = sock->sk;

	write_lock_bh(&sk->sk_callback_lock);
	con->sock = sock;

	sk->sk_user_data = con;
	/* Install a data_ready callback */
	sk->sk_data_ready = lowcomms_data_ready;
	sk->sk_write_space = lowcomms_write_space;
	sk->sk_state_change = lowcomms_state_change;
	sk->sk_allocation = GFP_NOFS;
	sk->sk_error_report = lowcomms_error_report;
	write_unlock_bh(&sk->sk_callback_lock);
}

/* Add the port number to an IPv6 or 4 sockaddr and return the address
   length */
static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
			  int *addr_len)
{
	saddr->ss_family =  dlm_local_addr[0]->ss_family;
	if (saddr->ss_family == AF_INET) {
		struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
		in4_addr->sin_port = cpu_to_be16(port);
		*addr_len = sizeof(struct sockaddr_in);
		memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero));
	} else {
		struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
		in6_addr->sin6_port = cpu_to_be16(port);
		*addr_len = sizeof(struct sockaddr_in6);
	}
	memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len);
}

/* Close a remote connection and tidy up */
static void close_connection(struct connection *con, bool and_other,
			     bool tx, bool rx)
{
	bool closing = test_and_set_bit(CF_CLOSING, &con->flags);

	if (tx && !closing && cancel_work_sync(&con->swork))
		log_print("canceled swork for node %d", con->nodeid);
	if (rx && !closing && cancel_work_sync(&con->rwork))
		log_print("canceled rwork for node %d", con->nodeid);

	mutex_lock(&con->sock_mutex);
	if (con->sock) {
		restore_callbacks(con->sock);
		sock_release(con->sock);
		con->sock = NULL;
	}
	if (con->othercon && and_other) {
		/* Will only re-enter once. */
		close_connection(con->othercon, false, true, true);
	}
	if (con->rx_page) {
		__free_page(con->rx_page);
		con->rx_page = NULL;
	}

	con->retries = 0;
	mutex_unlock(&con->sock_mutex);
	clear_bit(CF_CLOSING, &con->flags);
}

/* Data received from remote end */
static int receive_from_sock(struct connection *con)
{
	int ret = 0;
	struct msghdr msg = {};
	struct kvec iov[2];
	unsigned len;
	int r;
	int call_again_soon = 0;
	int nvec;

	mutex_lock(&con->sock_mutex);

	if (con->sock == NULL) {
		ret = -EAGAIN;
		goto out_close;
	}
	if (con->nodeid == 0) {
		ret = -EINVAL;
		goto out_close;
	}

	if (con->rx_page == NULL) {
		/*
		 * This doesn't need to be atomic, but I think it should
		 * improve performance if it is.
		 */
		con->rx_page = alloc_page(GFP_ATOMIC);
		if (con->rx_page == NULL)
			goto out_resched;
		cbuf_init(&con->cb, PAGE_SIZE);
	}

	/*
	 * iov[0] is the bit of the circular buffer between the current end
	 * point (cb.base + cb.len) and the end of the buffer.
	 */
	iov[0].iov_len = con->cb.base - cbuf_data(&con->cb);
	iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb);
	iov[1].iov_len = 0;
	nvec = 1;

	/*
	 * iov[1] is the bit of the circular buffer between the start of the
	 * buffer and the start of the currently used section (cb.base)
	 */
	if (cbuf_data(&con->cb) >= con->cb.base) {
		iov[0].iov_len = PAGE_SIZE - cbuf_data(&con->cb);
		iov[1].iov_len = con->cb.base;
		iov[1].iov_base = page_address(con->rx_page);
		nvec = 2;
	}
	len = iov[0].iov_len + iov[1].iov_len;

	r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len,
			       MSG_DONTWAIT | MSG_NOSIGNAL);
	if (ret <= 0)
		goto out_close;
	else if (ret == len)
		call_again_soon = 1;

	cbuf_add(&con->cb, ret);
	ret = dlm_process_incoming_buffer(con->nodeid,
					  page_address(con->rx_page),
					  con->cb.base, con->cb.len,
					  PAGE_SIZE);
	if (ret == -EBADMSG) {
		log_print("lowcomms: addr=%p, base=%u, len=%u, read=%d",
			  page_address(con->rx_page), con->cb.base,
			  con->cb.len, r);
	}
	if (ret < 0)
		goto out_close;
	cbuf_eat(&con->cb, ret);

	if (cbuf_empty(&con->cb) && !call_again_soon) {
		__free_page(con->rx_page);
		con->rx_page = NULL;
	}

	if (call_again_soon)
		goto out_resched;
	mutex_unlock(&con->sock_mutex);
	return 0;

out_resched:
	if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
		queue_work(recv_workqueue, &con->rwork);
	mutex_unlock(&con->sock_mutex);
	return -EAGAIN;

out_close:
	mutex_unlock(&con->sock_mutex);
	if (ret != -EAGAIN) {
		close_connection(con, true, true, false);
		/* Reconnect when there is something to send */
	}
	/* Don't return success if we really got EOF */
	if (ret == 0)
		ret = -EAGAIN;

	return ret;
}

/* Listening socket is busy, accept a connection */
static int tcp_accept_from_sock(struct connection *con)
{
	int result;
	struct sockaddr_storage peeraddr;
	struct socket *newsock;
	int len;
	int nodeid;
	struct connection *newcon;
	struct connection *addcon;

	mutex_lock(&connections_lock);
	if (!dlm_allow_conn) {
		mutex_unlock(&connections_lock);
		return -1;
	}
	mutex_unlock(&connections_lock);

	memset(&peeraddr, 0, sizeof(peeraddr));
	result = sock_create_lite(dlm_local_addr[0]->ss_family,
				  SOCK_STREAM, IPPROTO_TCP, &newsock);
	if (result < 0)
		return -ENOMEM;

	mutex_lock_nested(&con->sock_mutex, 0);

	result = -ENOTCONN;
	if (con->sock == NULL)
		goto accept_err;

	newsock->type = con->sock->type;
	newsock->ops = con->sock->ops;

	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
	if (result < 0)
		goto accept_err;

	/* Get the connected socket's peer */
	memset(&peeraddr, 0, sizeof(peeraddr));
	if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr,
				  &len, 2)) {
		result = -ECONNABORTED;
		goto accept_err;
	}

	/* Get the new node's NODEID */
	make_sockaddr(&peeraddr, 0, &len);
	if (addr_to_nodeid(&peeraddr, &nodeid)) {
		unsigned char *b=(unsigned char *)&peeraddr;
		log_print("connect from non cluster node");
		print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, 
				     b, sizeof(struct sockaddr_storage));
		sock_release(newsock);
		mutex_unlock(&con->sock_mutex);
		return -1;
	}

	log_print("got connection from %d", nodeid);

	/*  Check to see if we already have a connection to this node. This
	 *  could happen if the two nodes initiate a connection at roughly
	 *  the same time and the connections cross on the wire.
	 *  In this case we store the incoming one in "othercon"
	 */
	newcon = nodeid2con(nodeid, GFP_NOFS);
	if (!newcon) {
		result = -ENOMEM;
		goto accept_err;
	}
	mutex_lock_nested(&newcon->sock_mutex, 1);
	if (newcon->sock) {
		struct connection *othercon = newcon->othercon;

		if (!othercon) {
			othercon = kmem_cache_zalloc(con_cache, GFP_NOFS);
			if (!othercon) {
				log_print("failed to allocate incoming socket");
				mutex_unlock(&newcon->sock_mutex);
				result = -ENOMEM;
				goto accept_err;
			}
			othercon->nodeid = nodeid;
			othercon->rx_action = receive_from_sock;
			mutex_init(&othercon->sock_mutex);
			INIT_WORK(&othercon->swork, process_send_sockets);
			INIT_WORK(&othercon->rwork, process_recv_sockets);
			set_bit(CF_IS_OTHERCON, &othercon->flags);
		}
		mutex_lock_nested(&othercon->sock_mutex, 2);
		if (!othercon->sock) {
			newcon->othercon = othercon;
			othercon->sock = newsock;
			newsock->sk->sk_user_data = othercon;
			add_sock(newsock, othercon);
			addcon = othercon;
			mutex_unlock(&othercon->sock_mutex);
		}
		else {
			printk("Extra connection from node %d attempted\n", nodeid);
			result = -EAGAIN;
			mutex_unlock(&othercon->sock_mutex);
			mutex_unlock(&newcon->sock_mutex);
			goto accept_err;
		}
	}
	else {
		newsock->sk->sk_user_data = newcon;
		newcon->rx_action = receive_from_sock;
		/* accept copies the sk after we've saved the callbacks, so we
		   don't want to save them a second time or comm errors will
		   result in calling sk_error_report recursively. */
		add_sock(newsock, newcon);
		addcon = newcon;
	}

	mutex_unlock(&newcon->sock_mutex);

	/*
	 * Add it to the active queue in case we got data
	 * between processing the accept adding the socket
	 * to the read_sockets list
	 */
	if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
		queue_work(recv_workqueue, &addcon->rwork);
	mutex_unlock(&con->sock_mutex);

	return 0;

accept_err:
	mutex_unlock(&con->sock_mutex);
	sock_release(newsock);

	if (result != -EAGAIN)
		log_print("error accepting connection from node: %d", result);
	return result;
}

static int sctp_accept_from_sock(struct connection *con)
{
	/* Check that the new node is in the lockspace */
	struct sctp_prim prim;
	int nodeid;
	int prim_len, ret;
	int addr_len;
	struct connection *newcon;
	struct connection *addcon;
	struct socket *newsock;

	mutex_lock(&connections_lock);
	if (!dlm_allow_conn) {
		mutex_unlock(&connections_lock);
		return -1;
	}
	mutex_unlock(&connections_lock);

	mutex_lock_nested(&con->sock_mutex, 0);

	ret = kernel_accept(con->sock, &newsock, O_NONBLOCK);
	if (ret < 0)
		goto accept_err;

	memset(&prim, 0, sizeof(struct sctp_prim));
	prim_len = sizeof(struct sctp_prim);

	ret = kernel_getsockopt(newsock, IPPROTO_SCTP, SCTP_PRIMARY_ADDR,
				(char *)&prim, &prim_len);
	if (ret < 0) {
		log_print("getsockopt/sctp_primary_addr failed: %d", ret);
		goto accept_err;
	}

	make_sockaddr(&prim.ssp_addr, 0, &addr_len);
	ret = addr_to_nodeid(&prim.ssp_addr, &nodeid);
	if (ret) {
		unsigned char *b = (unsigned char *)&prim.ssp_addr;

		log_print("reject connect from unknown addr");
		print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
				     b, sizeof(struct sockaddr_storage));
		goto accept_err;
	}

	newcon = nodeid2con(nodeid, GFP_NOFS);
	if (!newcon) {
		ret = -ENOMEM;
		goto accept_err;
	}

	mutex_lock_nested(&newcon->sock_mutex, 1);

	if (newcon->sock) {
		struct connection *othercon = newcon->othercon;

		if (!othercon) {
			othercon = kmem_cache_zalloc(con_cache, GFP_NOFS);
			if (!othercon) {
				log_print("failed to allocate incoming socket");
				mutex_unlock(&newcon->sock_mutex);
				ret = -ENOMEM;
				goto accept_err;
			}
			othercon->nodeid = nodeid;
			othercon->rx_action = receive_from_sock;
			mutex_init(&othercon->sock_mutex);
			INIT_WORK(&othercon->swork, process_send_sockets);
			INIT_WORK(&othercon->rwork, process_recv_sockets);
			set_bit(CF_IS_OTHERCON, &othercon->flags);
		}
		mutex_lock_nested(&othercon->sock_mutex, 2);
		if (!othercon->sock) {
			newcon->othercon = othercon;
			othercon->sock = newsock;
			newsock->sk->sk_user_data = othercon;
			add_sock(newsock, othercon);
			addcon = othercon;
			mutex_unlock(&othercon->sock_mutex);
		} else {
			printk("Extra connection from node %d attempted\n", nodeid);
			ret = -EAGAIN;
			mutex_unlock(&othercon->sock_mutex);
			mutex_unlock(&newcon->sock_mutex);
			goto accept_err;
		}
	} else {
		newsock->sk->sk_user_data = newcon;
		newcon->rx_action = receive_from_sock;
		add_sock(newsock, newcon);
		addcon = newcon;
	}

	log_print("connected to %d", nodeid);

	mutex_unlock(&newcon->sock_mutex);

	/*
	 * Add it to the active queue in case we got data
	 * between processing the accept adding the socket
	 * to the read_sockets list
	 */
	if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
		queue_work(recv_workqueue, &addcon->rwork);
	mutex_unlock(&con->sock_mutex);

	return 0;

accept_err:
	mutex_unlock(&con->sock_mutex);
	if (newsock)
		sock_release(newsock);
	if (ret != -EAGAIN)
		log_print("error accepting connection from node: %d", ret);

	return ret;
}

static void free_entry(struct writequeue_entry *e)
{
	__free_page(e->page);
	kfree(e);
}

/*
 * writequeue_entry_complete - try to delete and free write queue entry
 * @e: write queue entry to try to delete
 * @completed: bytes completed
 *
 * writequeue_lock must be held.
 */
static void writequeue_entry_complete(struct writequeue_entry *e, int completed)
{
	e->offset += completed;
	e->len -= completed;

	if (e->len == 0 && e->users == 0) {
		list_del(&e->list);
		free_entry(e);
	}
}

/*
 * sctp_bind_addrs - bind a SCTP socket to all our addresses
 */
static int sctp_bind_addrs(struct connection *con, uint16_t port)
{
	struct sockaddr_storage localaddr;
	int i, addr_len, result = 0;

	for (i = 0; i < dlm_local_count; i++) {
		memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr));
		make_sockaddr(&localaddr, port, &addr_len);

		if (!i)
			result = kernel_bind(con->sock,
					     (struct sockaddr *)&localaddr,
					     addr_len);
		else
			result = kernel_setsockopt(con->sock, SOL_SCTP,
						   SCTP_SOCKOPT_BINDX_ADD,
						   (char *)&localaddr, addr_len);

		if (result < 0) {
			log_print("Can't bind to %d addr number %d, %d.\n",
				  port, i + 1, result);
			break;
		}
	}
	return result;
}

/* Initiate an SCTP association.
   This is a special case of send_to_sock() in that we don't yet have a
   peeled-off socket for this association, so we use the listening socket
   and add the primary IP address of the remote node.
 */
static void sctp_connect_to_sock(struct connection *con)
{
	struct sockaddr_storage daddr;
	int one = 1;
	int result;
	int addr_len;
	struct socket *sock;

	if (con->nodeid == 0) {
		log_print("attempt to connect sock 0 foiled");
		return;
	}

	mutex_lock(&con->sock_mutex);

	/* Some odd races can cause double-connects, ignore them */
	if (con->retries++ > MAX_CONNECT_RETRIES)
		goto out;

	if (con->sock) {
		log_print("node %d already connected.", con->nodeid);
		goto out;
	}

	memset(&daddr, 0, sizeof(daddr));
	result = nodeid_to_addr(con->nodeid, &daddr, NULL, true);
	if (result < 0) {
		log_print("no address for nodeid %d", con->nodeid);
		goto out;
	}

	/* Create a socket to communicate with */
	result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
				  SOCK_STREAM, IPPROTO_SCTP, &sock);
	if (result < 0)
		goto socket_err;

	sock->sk->sk_user_data = con;
	con->rx_action = receive_from_sock;
	con->connect_action = sctp_connect_to_sock;
	add_sock(sock, con);

	/* Bind to all addresses. */
	if (sctp_bind_addrs(con, 0))
		goto bind_err;

	make_sockaddr(&daddr, dlm_config.ci_tcp_port, &addr_len);

	log_print("connecting to %d", con->nodeid);

	/* Turn off Nagle's algorithm */
	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
			  sizeof(one));

	result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
				   O_NONBLOCK);
	if (result == -EINPROGRESS)
		result = 0;
	if (result == 0)
		goto out;

bind_err:
	con->sock = NULL;
	sock_release(sock);

socket_err:
	/*
	 * Some errors are fatal and this list might need adjusting. For other
	 * errors we try again until the max number of retries is reached.
	 */
	if (result != -EHOSTUNREACH &&
	    result != -ENETUNREACH &&
	    result != -ENETDOWN &&
	    result != -EINVAL &&
	    result != -EPROTONOSUPPORT) {
		log_print("connect %d try %d error %d", con->nodeid,
			  con->retries, result);
		mutex_unlock(&con->sock_mutex);
		msleep(1000);
		lowcomms_connect_sock(con);
		return;
	}

out:
	mutex_unlock(&con->sock_mutex);
}

/* Connect a new socket to its peer */
static void tcp_connect_to_sock(struct connection *con)
{
	struct sockaddr_storage saddr, src_addr;
	int addr_len;
	struct socket *sock = NULL;
	int one = 1;
	int result;

	if (con->nodeid == 0) {
		log_print("attempt to connect sock 0 foiled");
		return;
	}

	mutex_lock(&con->sock_mutex);
	if (con->retries++ > MAX_CONNECT_RETRIES)
		goto out;

	/* Some odd races can cause double-connects, ignore them */
	if (con->sock)
		goto out;

	/* Create a socket to communicate with */
	result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
				  SOCK_STREAM, IPPROTO_TCP, &sock);
	if (result < 0)
		goto out_err;

	memset(&saddr, 0, sizeof(saddr));
	result = nodeid_to_addr(con->nodeid, &saddr, NULL, false);
	if (result < 0) {
		log_print("no address for nodeid %d", con->nodeid);
		goto out_err;
	}

	sock->sk->sk_user_data = con;
	con->rx_action = receive_from_sock;
	con->connect_action = tcp_connect_to_sock;
	add_sock(sock, con);

	/* Bind to our cluster-known address connecting to avoid
	   routing problems */
	memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
	make_sockaddr(&src_addr, 0, &addr_len);
	result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
				 addr_len);
	if (result < 0) {
		log_print("could not bind for connect: %d", result);
		/* This *may* not indicate a critical error */
	}

	make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);

	log_print("connecting to %d", con->nodeid);

	/* Turn off Nagle's algorithm */
	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
			  sizeof(one));

	result = sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
				   O_NONBLOCK);
	if (result == -EINPROGRESS)
		result = 0;
	if (result == 0)
		goto out;

out_err:
	if (con->sock) {
		sock_release(con->sock);
		con->sock = NULL;
	} else if (sock) {
		sock_release(sock);
	}
	/*
	 * Some errors are fatal and this list might need adjusting. For other
	 * errors we try again until the max number of retries is reached.
	 */
	if (result != -EHOSTUNREACH &&
	    result != -ENETUNREACH &&
	    result != -ENETDOWN && 
	    result != -EINVAL &&
	    result != -EPROTONOSUPPORT) {
		log_print("connect %d try %d error %d", con->nodeid,
			  con->retries, result);
		mutex_unlock(&con->sock_mutex);
		msleep(1000);
		lowcomms_connect_sock(con);
		return;
	}
out:
	mutex_unlock(&con->sock_mutex);
	return;
}

static struct socket *tcp_create_listen_sock(struct connection *con,
					     struct sockaddr_storage *saddr)
{
	struct socket *sock = NULL;
	int result = 0;
	int one = 1;
	int addr_len;

	if (dlm_local_addr[0]->ss_family == AF_INET)
		addr_len = sizeof(struct sockaddr_in);
	else
		addr_len = sizeof(struct sockaddr_in6);

	/* Create a socket to communicate with */
	result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
				  SOCK_STREAM, IPPROTO_TCP, &sock);
	if (result < 0) {
		log_print("Can't create listening comms socket");
		goto create_out;
	}

	/* Turn off Nagle's algorithm */
	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
			  sizeof(one));

	result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
				   (char *)&one, sizeof(one));

	if (result < 0) {
		log_print("Failed to set SO_REUSEADDR on socket: %d", result);
	}
	sock->sk->sk_user_data = con;
	save_listen_callbacks(sock);
	con->rx_action = tcp_accept_from_sock;
	con->connect_action = tcp_connect_to_sock;

	/* Bind to our port */
	make_sockaddr(saddr, dlm_config.ci_tcp_port, &addr_len);
	result = sock->ops->bind(sock, (struct sockaddr *) saddr, addr_len);
	if (result < 0) {
		log_print("Can't bind to port %d", dlm_config.ci_tcp_port);
		sock_release(sock);
		sock = NULL;
		con->sock = NULL;
		goto create_out;
	}
	result = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
				 (char *)&one, sizeof(one));
	if (result < 0) {
		log_print("Set keepalive failed: %d", result);
	}

	result = sock->ops->listen(sock, 5);
	if (result < 0) {
		log_print("Can't listen on port %d", dlm_config.ci_tcp_port);
		sock_release(sock);
		sock = NULL;
		goto create_out;
	}

create_out:
	return sock;
}

/* Get local addresses */
static void init_local(void)
{
	struct sockaddr_storage sas, *addr;
	int i;

	dlm_local_count = 0;
	for (i = 0; i < DLM_MAX_ADDR_COUNT; i++) {
		if (dlm_our_addr(&sas, i))
			break;

		addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS);
		if (!addr)
			break;
		dlm_local_addr[dlm_local_count++] = addr;
	}
}

/* Initialise SCTP socket and bind to all interfaces */
static int sctp_listen_for_all(void)
{
	struct socket *sock = NULL;
	int result = -EINVAL;
	struct connection *con = nodeid2con(0, GFP_NOFS);
	int bufsize = NEEDED_RMEM;
	int one = 1;

	if (!con)
		return -ENOMEM;

	log_print("Using SCTP for communications");

	result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
				  SOCK_STREAM, IPPROTO_SCTP, &sock);
	if (result < 0) {
		log_print("Can't create comms socket, check SCTP is loaded");
		goto out;
	}

	result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUFFORCE,
				 (char *)&bufsize, sizeof(bufsize));
	if (result)
		log_print("Error increasing buffer space on socket %d", result);

	result = kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
				   sizeof(one));
	if (result < 0)
		log_print("Could not set SCTP NODELAY error %d\n", result);

	write_lock_bh(&sock->sk->sk_callback_lock);
	/* Init con struct */
	sock->sk->sk_user_data = con;
	save_listen_callbacks(sock);
	con->sock = sock;
	con->sock->sk->sk_data_ready = lowcomms_data_ready;
	con->rx_action = sctp_accept_from_sock;
	con->connect_action = sctp_connect_to_sock;

	write_unlock_bh(&sock->sk->sk_callback_lock);

	/* Bind to all addresses. */
	if (sctp_bind_addrs(con, dlm_config.ci_tcp_port))
		goto create_delsock;

	result = sock->ops->listen(sock, 5);
	if (result < 0) {
		log_print("Can't set socket listening");
		goto create_delsock;
	}

	return 0;

create_delsock:
	sock_release(sock);
	con->sock = NULL;
out:
	return result;
}

static int tcp_listen_for_all(void)
{
	struct socket *sock = NULL;
	struct connection *con = nodeid2con(0, GFP_NOFS);
	int result = -EINVAL;

	if (!con)
		return -ENOMEM;

	/* We don't support multi-homed hosts */
	if (dlm_local_addr[1] != NULL) {
		log_print("TCP protocol can't handle multi-homed hosts, "
			  "try SCTP");
		return -EINVAL;
	}

	log_print("Using TCP for communications");

	sock = tcp_create_listen_sock(con, dlm_local_addr[0]);
	if (sock) {
		add_sock(sock, con);
		result = 0;
	}
	else {
		result = -EADDRINUSE;
	}

	return result;
}



static struct writequeue_entry *new_writequeue_entry(struct connection *con,
						     gfp_t allocation)
{
	struct writequeue_entry *entry;

	entry = kmalloc(sizeof(struct writequeue_entry), allocation);
	if (!entry)
		return NULL;

	entry->page = alloc_page(allocation);
	if (!entry->page) {
		kfree(entry);
		return NULL;
	}

	entry->offset = 0;
	entry->len = 0;
	entry->end = 0;
	entry->users = 0;
	entry->con = con;

	return entry;
}

void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
{
	struct connection *con;
	struct writequeue_entry *e;
	int offset = 0;

	con = nodeid2con(nodeid, allocation);
	if (!con)
		return NULL;

	spin_lock(&con->writequeue_lock);
	e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
	if ((&e->list == &con->writequeue) ||
	    (PAGE_SIZE - e->end < len)) {
		e = NULL;
	} else {
		offset = e->end;
		e->end += len;
		e->users++;
	}
	spin_unlock(&con->writequeue_lock);

	if (e) {
	got_one:
		*ppc = page_address(e->page) + offset;
		return e;
	}

	e = new_writequeue_entry(con, allocation);
	if (e) {
		spin_lock(&con->writequeue_lock);
		offset = e->end;
		e->end += len;
		e->users++;
		list_add_tail(&e->list, &con->writequeue);
		spin_unlock(&con->writequeue_lock);
		goto got_one;
	}
	return NULL;
}

void dlm_lowcomms_commit_buffer(void *mh)
{
	struct writequeue_entry *e = (struct writequeue_entry *)mh;
	struct connection *con = e->con;
	int users;

	spin_lock(&con->writequeue_lock);
	users = --e->users;
	if (users)
		goto out;
	e->len = e->end - e->offset;
	spin_unlock(&con->writequeue_lock);

	queue_work(send_workqueue, &con->swork);
	return;

out:
	spin_unlock(&con->writequeue_lock);
	return;
}

/* Send a message */
static void send_to_sock(struct connection *con)
{
	int ret = 0;
	const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
	struct writequeue_entry *e;
	int len, offset;
	int count = 0;

	mutex_lock(&con->sock_mutex);
	if (con->sock == NULL)
		goto out_connect;

	spin_lock(&con->writequeue_lock);
	for (;;) {
		e = list_entry(con->writequeue.next, struct writequeue_entry,
			       list);
		if ((struct list_head *) e == &con->writequeue)
			break;

		len = e->len;
		offset = e->offset;
		BUG_ON(len == 0 && e->users == 0);
		spin_unlock(&con->writequeue_lock);

		ret = 0;
		if (len) {
			ret = kernel_sendpage(con->sock, e->page, offset, len,
					      msg_flags);
			if (ret == -EAGAIN || ret == 0) {
				if (ret == -EAGAIN &&
				    test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
				    !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
					/* Notify TCP that we're limited by the
					 * application window size.
					 */
					set_bit(SOCK_NOSPACE, &con->sock->flags);
					con->sock->sk->sk_write_pending++;
				}
				cond_resched();
				goto out;
			} else if (ret < 0)
				goto send_error;
		}

		/* Don't starve people filling buffers */
		if (++count >= MAX_SEND_MSG_COUNT) {
			cond_resched();
			count = 0;
		}

		spin_lock(&con->writequeue_lock);
		writequeue_entry_complete(e, ret);
	}
	spin_unlock(&con->writequeue_lock);
out:
	mutex_unlock(&con->sock_mutex);
	return;

send_error:
	mutex_unlock(&con->sock_mutex);
	close_connection(con, true, false, true);
	/* Requeue the send work. When the work daemon runs again, it will try
	   a new connection, then call this function again. */
	queue_work(send_workqueue, &con->swork);
	return;

out_connect:
	mutex_unlock(&con->sock_mutex);
	queue_work(send_workqueue, &con->swork);
	cond_resched();
}

static void clean_one_writequeue(struct connection *con)
{
	struct writequeue_entry *e, *safe;

	spin_lock(&con->writequeue_lock);
	list_for_each_entry_safe(e, safe, &con->writequeue, list) {
		list_del(&e->list);
		free_entry(e);
	}
	spin_unlock(&con->writequeue_lock);
}

/* Called from recovery when it knows that a node has
   left the cluster */
int dlm_lowcomms_close(int nodeid)
{
	struct connection *con;
	struct dlm_node_addr *na;

	log_print("closing connection to node %d", nodeid);
	con = nodeid2con(nodeid, 0);
	if (con) {
		set_bit(CF_CLOSE, &con->flags);
		close_connection(con, true, true, true);
		clean_one_writequeue(con);
	}

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (na) {
		list_del(&na->list);
		while (na->addr_count--)
			kfree(na->addr[na->addr_count]);
		kfree(na);
	}
	spin_unlock(&dlm_node_addrs_spin);

	return 0;
}

/* Receive workqueue function */
static void process_recv_sockets(struct work_struct *work)
{
	struct connection *con = container_of(work, struct connection, rwork);
	int err;

	clear_bit(CF_READ_PENDING, &con->flags);
	do {
		err = con->rx_action(con);
	} while (!err);
}

/* Send workqueue function */
static void process_send_sockets(struct work_struct *work)
{
	struct connection *con = container_of(work, struct connection, swork);

	if (con->sock == NULL) /* not mutex protected so check it inside too */
		con->connect_action(con);
	if (!list_empty(&con->writequeue))
		send_to_sock(con);
}


/* Discard all entries on the write queues */
static void clean_writequeues(void)
{
	foreach_conn(clean_one_writequeue);
}

static void work_stop(void)
{
	destroy_workqueue(recv_workqueue);
	destroy_workqueue(send_workqueue);
}

static int work_start(void)
{
	recv_workqueue = alloc_workqueue("dlm_recv",
					 WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
	if (!recv_workqueue) {
		log_print("can't start dlm_recv");
		return -ENOMEM;
	}

	send_workqueue = alloc_workqueue("dlm_send",
					 WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
	if (!send_workqueue) {
		log_print("can't start dlm_send");
		destroy_workqueue(recv_workqueue);
		return -ENOMEM;
	}

	return 0;
}

static void _stop_conn(struct connection *con, bool and_other)
{
	mutex_lock(&con->sock_mutex);
	set_bit(CF_READ_PENDING, &con->flags);
	if (con->sock && con->sock->sk)
		con->sock->sk->sk_user_data = NULL;
	if (con->othercon && and_other)
		_stop_conn(con->othercon, false);
	mutex_unlock(&con->sock_mutex);
}

static void stop_conn(struct connection *con)
{
	_stop_conn(con, true);
}

static void free_conn(struct connection *con)
{
	close_connection(con, true, true, true);
	if (con->othercon)
		kmem_cache_free(con_cache, con->othercon);
	hlist_del(&con->list);
	kmem_cache_free(con_cache, con);
}

static void work_flush(void)
{
	int ok;
	int i;
	struct hlist_node *n;
	struct connection *con;

	flush_workqueue(recv_workqueue);
	flush_workqueue(send_workqueue);
	do {
		ok = 1;
		foreach_conn(stop_conn);
		flush_workqueue(recv_workqueue);
		flush_workqueue(send_workqueue);
		for (i = 0; i < CONN_HASH_SIZE && ok; i++) {
			hlist_for_each_entry_safe(con, n,
						  &connection_hash[i], list) {
				ok &= test_bit(CF_READ_PENDING, &con->flags);
				if (con->othercon)
					ok &= test_bit(CF_READ_PENDING,
						       &con->othercon->flags);
			}
		}
	} while (!ok);
}

void dlm_lowcomms_stop(void)
{
	/* Set all the flags to prevent any
	   socket activity.
	*/
	mutex_lock(&connections_lock);
	dlm_allow_conn = 0;
	mutex_unlock(&connections_lock);
	work_flush();
	clean_writequeues();
	foreach_conn(free_conn);
	work_stop();

	kmem_cache_destroy(con_cache);
}

int dlm_lowcomms_start(void)
{
	int error = -EINVAL;
	struct connection *con;
	int i;

	for (i = 0; i < CONN_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&connection_hash[i]);

	init_local();
	if (!dlm_local_count) {
		error = -ENOTCONN;
		log_print("no local IP address has been set");
		goto fail;
	}

	error = -ENOMEM;
	con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection),
				      __alignof__(struct connection), 0,
				      NULL);
	if (!con_cache)
		goto fail;

	error = work_start();
	if (error)
		goto fail_destroy;

	dlm_allow_conn = 1;

	/* Start listening */
	if (dlm_config.ci_protocol == 0)
		error = tcp_listen_for_all();
	else
		error = sctp_listen_for_all();
	if (error)
		goto fail_unlisten;

	return 0;

fail_unlisten:
	dlm_allow_conn = 0;
	con = nodeid2con(0,0);
	if (con) {
		close_connection(con, false, true, true);
		kmem_cache_free(con_cache, con);
	}
fail_destroy:
	kmem_cache_destroy(con_cache);
fail:
	return error;
}

void dlm_lowcomms_exit(void)
{
	struct dlm_node_addr *na, *safe;

	spin_lock(&dlm_node_addrs_spin);
	list_for_each_entry_safe(na, safe, &dlm_node_addrs, list) {
		list_del(&na->list);
		while (na->addr_count--)
			kfree(na->addr[na->addr_count]);
		kfree(na);
	}
	spin_unlock(&dlm_node_addrs_spin);
}